METHODS AND APPARATUS FOR ADDITIVE MANUFACTURING BASED ON MULTI-DIMENSIONAL BUILD PLATFORMS
An additive manufacturing system, a build platform and a method of operating are provided. The build platform includes a build volume section including at least one feature or functional element. The build platform further includes a controller to individually control the at least one functional element.
The present application claims the benefit of and is a Nonprovisional Application of U.S. Provisional Application Ser. No. 63/137,396 filed on Jan. 14, 2021, the contents of which are incorporated herein by reference in their entirety.
BACKGROUND OF THE DISCLOSUREThe subject matter disclosed herein relates to additive manufacturing methods and systems for fabrication of complex multi-dimensional objects, parts, assemblies, and structures.
Current additive manufacturing systems include fused filament fabrication (FFF)/fused deposition modeling (FDM), stereolithography (SLA), selective laser sintering (SLS), digital light projector (DLP) printers, paste or aerosol jet, and direct metal laser melting (DMLS) deposition technologies, one or more robotic actuators, and other tools for depositing multi-materials such as structural or functional thermoplastics, resins and metals, solid or flexible, conductive and insulating inks, pastes and other nano-particle materials; tools for sintering, aligning/measuring, ablation, milling, drilling, and component pick-and-place tools for placement of components such as electronic, electro-mechanical, or mechanical devices. All of these processes generally rely on planar build plate geometries as shown in
Generally, the deposited material forms either the target object, or is support material for the target object. It should be appreciated that when the target object has features, such as overhangs or hollow areas for example, the printer system may deposit material for the purpose of providing a surface to deposit the material of the feature and support the feature. This support structure is subsequently removed by the operator during post-processing. It should be appreciated that the material deposited for the support structure increases the part cost (more material used) and also slows down the fabrication process.
The target objects are fabricated, layer-by-layer in the Z axis by the extruder in accordance with execution of program instructions (i.e. G-code). In some applications the material selection uses a heated build plate (sometimes referred to hotbed) for material adhesion during extrusion or tool operations. The selection of an extruder (and any other tools), the movement of the extruder, and control of the build plate temperature profile are typically performed on a computer using software. Typically, an additive manufacturing system uses a CAD/CAM system in conjunction with a slicer software module. The software inputs a CAD model of the target object and generates the control instructions to the additive manufacturing system. This is code is typically represented in the G-code software language, however other software languages for additive manufacturing system control may be used.
Given the increasing utilization of additive manufacturing systems it is desirable to fabricate increasingly complex geometries, comprising multiple material characteristics with associated multiple operations and tools within the fabrication process. As a result additive manufacturing systems that expand beyond a 3-axis (X,Y,Z) range of motion have been proposed to include to 4-to-9-axis systems. These multi-axis systems overcome some of the geometrical fabrication and support for multiple tool positioning limitations of the 3-axis based additive manufacturing systems.
The use of planar build plate 100, 150 geometries within additive manufacturing systems had become less efficient and limited when used with multi-axis additive manufacturing systems especially as the number of tool axes increases. This is evident in cases where an additive manufactured object uses multiple tools that support movement and deposition positioning across complex trajectories such as curved or non-linear surface geometries and tool paths with material over-hangs that use support structures. Such challenges are compounded when additional materials and tools processes are used. Solutions to these challenges results in increasing requirements in terms of additional number of geometric tool axes, the complexity and amount of support materials, tool-path complexity, and limitations in material options. These increased requirements result in increased build time and need for additional additive manufacturing system processes and workflows. Further such limitations become increasingly challenging as the size, complexity, and functionality of the target object geometry increases.
Collectively, the challenges described lead to difficulty, and in some cases intractability, in the fabrication of objects such as those containing novel material characteristics. More generally, this results in increased production time and cost associated with the fabrication of products, components, parts, structures, and assemblies across a large class of additive manufacturing systems.
Accordingly, while existing additive manufacturing systems are suitable for their intended purposes the need for improvement remains, particular in providing an additive manufacturing system having the features described herein.
BRIEF DESCRIPTION OF THE DISCLOSUREAccording to one aspect of the disclosure a build platform is provided. The build platform includes a build volume section including at least one feature or functional element. The build platform further includes a controller to individually control the at least one functional element
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that the build platform is a multi-dimensional build platform.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that the controller is communicatively coupled to an additive manufacturing system via a communications interface.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that the additive manufacturing system includes a multi-dimensional build platform interface controller.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that the multi-dimensional build platform interface controller includes a microcontroller, a memory, a build platform additive system interface, a power management circuit, a wireless charging coil, an external power input, a battery, and a communication module.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that the controller is communicatively coupled to a power system via a power interface.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that the build platform further includes an interface section configured to couple with the additive manufacturing system, and a base section coupled to the interface section.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that the controller is disposed in the base section.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that the controller includes a microcontroller, a memory, a build volume driver module, a power management circuit, a wireless charging coil, an external power input, a battery, and a communication module.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that at least one of the at least one functional element includes a heater coil.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that to individually control the heater coil includes activating the heater coil, deactivating the heater coil, or changing a temperature responsive to a signal received from a multi-dimensional build platform interface controller.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that at least one of the at least one functional element includes a magnetic coil.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that to individually control the magnetic coil includes activating the magnetic coil, deactivating the magnetic coil, or changing a field responsive to a signal received from a multi-dimensional build platform interface controller.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that at least one of the at least one functional element includes an optical device.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that to individually control the optical device includes activating the optical device, deactivating the optical device, or changing an optical energy of the optical device responsive to a signal received from a multi-dimensional build platform interface controller.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that at least one of the at least one functional element is disposed in a layer of a plurality of layers of the build volume section other than a surface layer of the build volume section.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the build platform may further include that the build platform is a planar build platform.
These and other advantages and features will become more apparent from the following description taken in conjunction with the drawings.
The subject matter, which is regarded as the disclosure, is particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The foregoing and other features, and advantages of the disclosure are apparent from the following detailed description taken in conjunction with the accompanying drawings in which:
40B is a flow diagram of a method for fabricating an object or an assembly using a planar build platform modified with one or more embodiments of a multi-dimensional build platform in accordance with one or more embodiments;
The detailed description explains embodiments of the disclosure, together with advantages and features, by way of example with reference to the drawings.
DETAILED DESCRIPTION OF THE DISCLOSUREEmbodiments herein are directed to additive manufacturing and in particular to an additive manufacturing system having a multi-dimensional build platform. The multi-dimensional build platform allows for fabrication across a build platform geometry with multiple degrees of freedom, such as x, y, z, roll, rotation, pitch and/or yaw as well as fabrication of complex objects requiring dynamic properties of the multi-dimensional build platform including additional dimensions such as temporal, energy, information, physical parameters, chemical characteristics, organic and inorganic, or a combination thereof (representing features or functional capabilities of the multi-dimensional build platform) that can vary in time in a fully dynamic manner. Embodiments of the present disclosure provide advantages that includes reduction of cost and/or production time in additive manufacturing. Embodiments of the present disclosure provide further advantages in the reduction or elimination of traditional support material. Embodiments of the present disclosure provide further advantages in the fabrication of objects, parts, assemblies, sub-assemblies, or other structures (collectively referred to as a “target object”) whose composition, properties and behavior comprise properties that would otherwise be intractable to achieve utilizing contemporaneous additive manufacturing systems and build platform technology.
For convenience, the following terms build volume section, base section, and attachment interface section may be referred to as build volume, base, and attachment interface respectively. The term multi-dimensional build platform may also be referred to as build platform herein.
Referring to
In an embodiment, the three-dimensional space 200 may be defined in terms of an x-axis 202, a y-axis 204 and a z-axis 206. The 3D space 200 may further be defined in terms of a roll angle 208, pitch angle 210, or yaw angle 212. The multi-dimensional build platform 302 may also be positioned in 3D space and functional tool operations may be performed to the multi-dimensional build platform 302 to fabricate additional features and structures (mechanical, electromechanical, electronic components, devices, and systems, conductive circuitry, microfluidic, as non-limiting embodiments) to the target or fabricated object in the exemplary embodiment, the multi-dimensional build platform 302 defines one or more surfaces that extend in three-dimensional space. The multi-dimensional build platform 302, the fabrication assembly 304, or a combination thereof may be moved in three or more degrees of freedom 202, 204, 206, 208, 210, 212 (
In an embodiment the multi-dimensional build platform 302 may also be positioned to operate in a horizontal position as to emulate existing prior-art planar build platforms but with enhanced capabilities as described by the embodiments herein.
The fabrication assembly 304 may include any suitable additive manufacturing material handling unit, such as but not limited to an extruder for example. The type of material depositing device used in fabrication assembly 304 used will depend on the type of additive manufacturing system used, such as fused filament fabrication (FFF), fused deposition modeling (FDM), stereolithography (SLA), material or binder jetting, selective laser sintering (SLS), digital light projector (DLP), or direct metal laser sintering (DMLS) and other powder bed fusion methods. It should be appreciated that the multi-dimensional build platform 302 may be used in any known additive manufacturing system that is capable of operating in multiple dimensions (e.g., three or more degrees of freedom). The assembly may further include tools or systems used for fabricating the target object. These tools or systems may include but are not limited to: ink deposition systems (including nano-scale inks), aerosol jet systems, paste deposition and dispensing systems, optical or laser alignment tools, curing tools, sintering tools, surface energy tools, milling tools, cutting tools, pick and place tools, and laser ablation systems for example. It should be appreciated that while embodiments herein may refer to the deposition of plastic or powdered-metal materials, this is for example purposes and the claims should not be so limited. In other embodiments, the systems and methods disclosed herein may be applied to inorganic and/or organic materials including materials (such as biomolecular or biomaterials) used in additive manufacturing processes that are sometimes referred to as “bioprinting.”
It should be appreciated that the fabrication assembly 304 may include both additive manufacturing and subtractive manufacturing functionality to form the target object. For example, the fabrication assembly 304 may generate an initial form of the target object using additive manufacturing, then remove material (e.g., using a drill or end-mill) such as to form a pocket, and then place a sub-assembly (e.g., a circuit or a sensor) into the pocket using a pick and place tool.
In an embodiment, the geometry, characteristics, properties and functionality of the object to be fabricated (i.e., the target object) may be defined based on a specification and associated set of requirements as input typically defined by a Computer Aided Design (CAD) system or some other generative specification such as a 3D scanner or camera system or combinations of such tools and design systems. The output of such systems the object to be fabricated is typically described in surface or volumetric formats including but not limited to mesh, boundary-representations, volumetric, formats based on constructive geometry methods and operations, and point-clouds, any of which represent the target object. Embodiments of the present disclosure describe methods and systems for implementing the desired multi-dimensional build platform appropriate for fabricating the target object given the additive manufacturing systems capabilities.
In an embodiment, the drive assembly 306 is an articulated robotic arm that moves the fabrication assembly 304 relative to the multi-dimensional build platform 302. It should be appreciated that in other embodiments, other types of device assemblies may be used. For example, one or more robotic arms or actuators can coordinate multiple drive assembly units 306 and multi-dimensional build platforms 302 in an integrated cluster or network of fabrication systems operating in a coordinated manner. The fabrication system network comprising multiple multi-dimensional build platforms 302 (where each multi-dimensional build platform, in the network of multiple multi-dimensional build platforms, supports fabrication of a complete or partial target object assembly, sub-assembly or component) providing the advantage of further increases in production velocity or complexity of the target object and reduced manufacturing or product costs. The robotic arm and multiple multi-dimensional build platform fabrication system are for example purposes and the claims should not be so limited.
In an embodiment, the multi-dimensional build platform 302 includes three sections that may be formed as separate components that are coupled together, or integrally formed, depending on an embodiment as further described within the application disclosure. These sections include a build volume section 312, a base section 314 and an attachment interface section 316.
In contrast to the planar build plate 100, 150 (also known as build-plate, hotbed, printer bed, or print surface) in prior art systems, a multi-dimensional build platform 302 may take on a plurality of geometries including both linear and non-linear or curved surfaces or volumes across multiple dimensional axes. The build platform supports the use of complex material deposition or extruders, sintering, lasers, tools, actuators, additive manufacturing system platform movements (such as rotational, tilt, pitch, yaw, roll, X-Y-Z, spherical, Euler angles, and other axes of movement and their respective representations or transformations) within the capabilities supported by a multi-axis additive manufacturing system. A multi-axis additive manufacturing system supports tools and tool path orientations in arbitrary 3D space. It should be appreciated that prior art additive manufacturing systems include tools that operate normal to a Z-axis relative to a planar build plate 100, 150. This is difference from systems described herein that use the multi-dimensional build that provide for a potentially infinite set of multi-dimensional build platforms that can be synthesized to allow fabrication of the desired target object.
In an embodiment, the multi-dimensional build platform may emulate an existing/prior-art build platform. In other embodiments, as discussed in more detail herein, the multi-dimensional build platform may be an existing/prior-art build platform, such as that originally provided with the additive manufacturing system, that has been upgraded or modified to include the desired functional characteristics to fabricate the target object.
The build volume section 312, which is described in more detail with respect to
Below the build volume section 312, the second section is provided that includes a base section 314. The base section 314 is not included in the fabrication process, but rather is utilized to provide functionality support of the implementation of the given multi-dimensional build platform 302 (specifically, the build volume section 312 and a subsystem for integration to the additive manufacturing system controller) as discussed in more detail herein. A prior art base section 314 is shown in
The multi-dimensional build platform 302 may be either dynamically synthesized programmatically, such as where a new build platform is desired; or otherwise, reusable based on a library of pre-existing build platforms implemented during previous synthesis operations. In this embodiment, each newly created build platform is stored in a build platform model database for reusability across new additive fabrication scenarios. The model database and other components of the build platform software platform are collectively referred to multi-dimensional build platform synthesis system. It should be appreciated that in accordance with the embodiments described herein, a user defined multi-dimensional build platform may also be implemented, utilized, and stored for reuse in the model database.
Referring now to
The top most layer 415 directly faces the additive manufacturing tools (e.g., an extruder) and may be a surface layer defined by the build volume section 412 geometry. The properties of this layer 415 are defined to facilitate deposition by the tools of the additive manufacturing system and/or the required properties of the materials deposited by the additive manufacturing system. For example, the material properties of layer 415 may be configured for tool deposition of printable materials, can accept a thin adhesive layer, tape, or comprise a material structure that includes other binding, reagents or agents used by a wide range of printable materials (e.g., plastics, composites, metals, ceramics, resins, food, or biomaterials, organic and inorganic printable substances). In an embodiment, the layer 415 is chemically pretreated in accordance to the defined set of elements such that the layer 415 surface provides the required set of surface characteristics facilitating material (where there may be multiple material types deposited spanning the build volume section surface) adhesion with no further configuration or preparation of the build volume section required.
In an embodiment, the layer 415 is defined/configured to accept the printed materials of the additive manufacturing system. Moreover, in some embodiments the layer 415 is configured to provide a solid cover for any components used/formed/deposited in underlying layers 417, 419, 421 that implement features or functional elements (e.g., the heater/RF/magnetic generation coils should not be exposed, so the final layer 415 provides a “covering” surface).
As used herein, the final layer 415 is described as layer one of the plurality of layers of the build volume section and the initial layer (e.g. the furthest layer from layer one) is described as layer “N.” In an embodiment, the layer 415 (e.g. layer one) is configured to allow for the deposition of material by the additive manufacturing system (e.g. the extruder). In this embodiment, the layer 415 has a desired set of adhesive characteristics that is integral to the structure of layer 415 to allow material bonding during deposition while also allowing removal of the target object when the operations are completed. In other words, the outer surface of layer 415 has a desired surface energy pattern that allows the deposited material or set of materials to stick while allowing for target object removal.
To obtain the desired surface characteristics of layer 415, the surface mesh elements may optionally be subjected to a plasma treatment, a chemical treatment (e.g. to encapsulate or coat the surface with an adhesive, a primer, an organic or a inorganic substance), or by physically modifying the surface areas to have a desired surface roughness or surface energy characteristic. In some embodiments, the treatment of the layer 415 may be on an individual element basis, meaning that the treatment may be applied to a portion of the elements, or different elements may have different treatments applied. In this embodiment the surface characteristics of layer 415 is a represents a feature (adhesion or surface energy properties) of the corresponding elements making up layer 415. In some embodiments, the treatment of the surface occurs prior to the start of operation. In other embodiments, the additive manufacturing system performs the treatment during operation in accordance to the embodiments described (e.g. the additive manufacturing system includes tools to perform the treatment as defined by the desired layer 415 requirements).
The functional layers 413 comprises 1-to-N independently configurable layers, each layer having a tessellation surface or volume mesh (2D/3D) defined that is comprised of individually addressable elements, where a given mesh can have a single element or multiple elements. For any given layer, each element within the 2D/3D mesh implements a feature or functionality that is independently configurable The individually addressable elements may be arranged as a mesh that is uniform (i.e. all elements are the same) or nonuniform (i.e. elements of different sizes or shapes) or a combination of each in forming the desired tessellation pattern. A uniform mesh may produced in terms of any repeating geometry including but not limited to squares, rectangles, triangles, or polygonal shapes. The addressable elements may be different thicknesses on different layers. The addressable elements may comprise different features such as the nonlimiting examples including; materials that vary in characteristics or properties, composition, chemical and physical structure, organic or inorganic, biologic or cellular composition, polarization, actuation, and surface energy for example. Each of the addressable elements also may comprise one or more functional characteristics that may be programmably controlled by multi-dimensional build platform based on information from the additive manufacturing system such as tool activation/deactivation, tool and system state or events, tool types, status, positional/location data and any other information useful for multi-dimensional build platform utilization and operation for example. For example, the functional characteristic may be a parameter, such as temperature for example, that is controlled during operation. In an embodiment, the individually addressable elements may be referred to as having one of three states: fixed; static; or dynamic. When an element is fixed, it has a set functional characteristic that does not change from one fabrication process/run to another. For example, a build volume section may include elements that are a lattice structure for transferring thermal energy. These lattice elements are considered fixed since they do not change from one production run to the next. An element is considered “static,” when the functional characteristic remains constant during a particular operation, but may change from one production run to the next. For example, a static element may comprise a heater coil that remains at a constant temperature during production. However, at during a second production run, the temperature may be changed. An element is “dynamic” when the element changes during operation, such as a time variable temperature, or a movable surface for example. For example, a dynamic element may comprise a magnetic field coil whose field distribution may be held at some level or vary in time. For example, a dynamic element may comprise a heater coil having a temperature profile during operation that varies. This could be performed to provide a desired material characteristic to the deposited material for example.
Another nonlimiting example is a surface 415 element having material properties that change during the production run based on a lower (higher) layer changing. Such as a magnetic coil changes the polarization of a magnetic nano-particle coated ink making up the 415 surface so it reacts with a magnetic material being deposited for example. Still another example would include a surface 415 having a biomolecular property that changes in response to light or heat, and activates a bio printed materials in some desired manner or structure. Still another example includes a food deposition tool that deposits an eatable material (e.g. batter) on surface 415, where the underlying layers includes a set of elements (e.g. on layer 2) which activate heating elements to “cook” the batter in a predetermined manner in accordance to the geometry of the build volume section.
Referring now to
In the embodiment of
It should be appreciated that while a rectangular base section is illustrated in
It should be appreciated that the base sections shown and described with respect to
As discussed above, the build volume section 312 may include one or more layers each with individually addressable elements that allow for the depositing or processing of deposited material with defined or predetermined features or functional characteristics. These individually addressable elements may be fixed, static, or dynamic in configuration defined during the fabrication of the build volume section.
Referring now to
In the embodiment illustrated in
The individually addressable elements may be in the form of a 2D/3D tessellation surface or volume elements (voxels) for example. Both feature-based and functional-based characteristics may take the form of multiple or “N” dimensions in the fabrication process.
It should be appreciated that while embodiments herein may refer to a single feature or functional characteristic (e.g., material type, temperature gradient profile), each element may have multiple defined feature and/or functional characteristics. Feature characteristics may include, but are not limited to: deposited material properties, material temperature, polarization or directional and vectors, or a combinations thereof. Functional characteristics may include, but are not limited to: thermal, particle radiation, electro-magnetic radiation, photonic, optical, acoustic radiation, gravity, magnetic polarization, or a combinations thereof. As discussed above, where multiple feature or functional characteristics are applied to a single element, the functional characteristics may be applied simultaneously (e.g., temperature and a material property), sequentially, or a combination thereof.
It should further be appreciated that while the embodiment of
Referring now to
Referring to
Referring to
As shown in
As discussed above, the outer layer 321-1 is a solid material that covers or encases the underlying layers 321-2, 321-3, 321-N and has an outer surface suitable to receive or have material deposited thereon by the additive manufacturing system. It should be appreciated that it may not be desirable to have underlying layers 321-2, 321-3, 321-N exposed to the environment, such as when the underlying layers 321-2, 321-3, 321-N include components, such as coils, active components, or printed circuits for example. In some embodiments, the outer layer 321-1 is removably coupled to the underlying layers 321-2, 321-3, 321-N. This would allow for the outer layer 321-1 to be periodically replaced for example.
As discussed above, the layer 321-1 surface may have feature characteristics defined by treating or coating the layer (or portions of the layer) with other substances, chemicals, doped, sprayed, impregnated with organic and/or inorganic porous substances (e.g., inks, pastes, nano-particle, etc.) to improve target object adhesion and removal processes as well as provide a desired material characteristic interaction. For example, to provide a feature or functional characteristic that defines how the deposited material interacts with the defined material on layer 321-1 surface since the layer 321-1 may be the only portion of the build volume section that comes into contact with the material forming the target object. Thus the feature and functional characteristics of the layer 321-1 define how the target object adheres to the build volume, or how the build volume integrates into the target object in embodiments where the build volume becomes part of the target object. The fabrication surface composition of the build volume section can be enriched for a desired multi-material printing/additive-manufacturing process inclusive of bioprinting of both organic and inorganic target objects and structures.
The embodiment of
It should be appreciated that the zones illustrated in
It should be appreciated that while the embodiments of
Referring now to
It should be appreciated that while the embodiments of
Referring now to
In an embodiment, there may be five categories of the build volume section 312, each differing in the method by which a build volume section is generated or made available for use to the additive manufacturing system.
The first category is a simple build volume section that includes, but is not limited to simple geometries such as rectangular, polygonal, and circular slabs, as well as other geometric primitives (spheres, pyramids, cuboids, toroid, conical, cylinders) such as shown in
The second category involved more complex build volume section geometries that are computed based on a set of geometric primitives (e.g., those simple geometries described with respect to category one) and the use of generative methods as illustrated in
The third category includes predictively matched and defined based at least in part on predictive matching the target specification (as a 3D query object) to a build platform model database. The database comprises reusable build volume section geometries. The matching to an input CAD model specification may be based at least in part on STL formats, STEP formats, mesh, boundary representation, point clouds, or any other common geometrical surface or volume representation formats.
The fourth category directly synthesizes, from a 3D CAD specification or a 3-dimensional scan of a target object, to a target build volume section 312 that optimally matches the scanned target object.
The fifth category provides for direct implementation of the build platform as externally created and imported into the build platform synthesis system. In an embodiment the build platform model database described with respect to the third category and described in more detail herein.
In an embodiment, the first category is used to define the build volume section in a plurality of forms. From a simple set of geometrical patterns comprising different shapes, lengths, widths, and depths of circles, rectangles, polygons and irregular shapes, all as non-limiting geometric variants of the basic planar build platform; to more complex geometries resulting in a formal build volume section geometry comprising pluralities of boss extrusions and cuts forming a non-limiting set of build volume section geometries, shapes and configurations.
In an embodiment, when the first category does not provide a desired solution for the build volume section, the second category may be performed to provide a predictive recognition and intelligent matching of a database of build platform volume sections that have been previously generated. In this embodiment the predictive method is utilized to recognize/identify a target object and integrate additive manufacturing system and fabrication configuration and parameters, for the generation of a multi-dimensional object query vector (also referred to as a “search vector” or “multi-dimensional search vector”) that is then utilized to search through a spatial database of build platform objects. The process of 3D object recognition and retrieval through machine learning methods for deriving a build platform solution (or set of solutions) occurs prior to invoking a generative synthesis process as described in the third category. Where first category is used, the resultant of any new build platform is saved within a model database comprising available build platforms allowing it to be used in future fabrication operations.
In an embodiment, significantly more complex build volume section geometries are generated through the generative computing method of CSG in conjunction with a build volume section primitive library database. In this method, a library of geometric primitives (including as example: cylinders, cuboids, conical, spherical, toroid, spline surfaces and angular wedges; full solids or half-spaces, and combinations thereof) are utilized in conjunction with a plurality of computational operations (such as Boolean and other rigid transformations) to generate a build volume section in accordance to a desired target object geometry. The desired geometry represents the build volume section that reduces or minimizes both geometric and feature error (considering the additive manufacturing system capabilities) associated to fabrication of a given target object geometric, structural, and functional specification. In an embodiment the use of CSG operations and multiple optimizations and/or predictive methods are used to produce the build volume section for a given target object input, set of fabrication requirements/specifications, and additive manufacturing system capability specifications.
In still another embodiment, a method of defining a build volume section by direct synthesis is provided. In this embodiment, the build volume section is directly generated by the input target object specification from a 3D scan of a target object. As an example, a target object can be a human body part such as head or knee, or any other anatomical structure (
Finally, in another embodiment a method is provided that enables the user to define through external CAD system tools a complete design of a build platform, or any of the three sections 312, 314, 316. In this scenario the applicable user-generated build platform section or sections are imported, normalized, and parameterized for addition into the build platform model database for use by the build platform synthesis system. As an exemplary embodiment the user-generated build platform may be imported into the build platform for training predictive and machine learning methods thereby improving their recognition accuracy.
The build volume section 312 may be utilized to fabricate complex surface or volume geometries whereby the build volume section 312 provides for geometry, tool axis, and contour support functions enabling the efficient fabrication of the target object and a reusable manner across thousands of fabrications cycles of the additive manufacturing system 300. An embodiment extends the utilization of a given build volume section 312 for use as an integral sub-assembly or prebuilt component or sub-assembly of a given target object as a volume component of the corresponding target object. In this embodiment, the build volume section is not reusable, but rather is fused or is integrally formed into the target object as part of the fabrication process and final assembly. In other words, once the additive manufacturing process is complete, the build volume section is removed with, and remains part of, the fabricated target object. That is, a target object is fabricated and directly incorporates the build volume section as a prefabricated build component element. This provides a significant technical solution for reducing fabrication time, since the build volume section is a prebuilt component structure, fabrication time used by the additive manufacturing system can be reduced by the achievable volume of the build volume section relative to the total volume of the target object. In an embodiment a factor in utilizing of build volume section as a prebuilt component primitive includes the remainder (target object less build volume section geometry) of the target object material composition being aligned with the build volume section component composition and a suitable base section and attachment interface (described hereafter) are utilized. The decision and process for determining whether a build platform is for facilitating multi-axis fabrication processing only or incorporation into the final target object as an actual integral part primitive is discussed in more detail herein.
Referring now to
It should be appreciated that while the embodiment of
Referring now to
After the target object is formed in the build volume section 2012, the operator removes the fastener 2044 and the cap member 2043. This allows the cylindrical member 2042 together with the target object to be removed from the additive manufacturing system. In other words, the cylindrical member 2042 is a sub-assembly or sub-component of the target object. It should be appreciated that while the illustrated embodiment shows a cylindrically shaped build volume section member 2042, this is for example purposes and the claims should not be so limited. In other embodiments, the member 2042 may have other shapes and be comprised of a plurality of different surfaces. Further, the member 2042 may be formed from multiple components. In still further embodiments, the member 2042 may include a key or keyway that allows the member 2042 to be interlocked with the material deposited thereon. In an embodiment, the multi-dimensional build platform 2002 may be used with fixed, dynamic or static elements, or any of the feature or functional characteristic described herein.
Referring now to
Referring now to
Surface deformations and geometry manipulations of the build volume section are performed under the control of the microcontroller through microcoil current magnitude and direction control, as well as activation and deactivation instructions. The determination of microcoil currents, the current direction, respective activation/deactivation, and duration is based on the desired multi-dimensional build platform shape objectives such as target object geometry, determined during multi-dimensional build platform synthesis as described in more detail herein. The number of degrees of geometrical deformation or configurable multi-dimensional build platform shapes may be a function of the density and magnetic field strength characteristics. For example, microcoil magnetic field distribution is determined by both available coil current (power) and the microcoil geometry including size, shape, and number of coil-turns.
To achieve a reconfigurable build volume section surface, the build volume section 3100 (
During multi-dimensional build volume section synthesis, flexible material characteristics are considered along with the microcoil characteristics to determine the desired configuration to the microcontroller in order to execute the microcoil operational workflow (modulation of N microcoils) during additive manufacturing processes. This operational workflow or set of N microcontroller actuated modulations results in a variable build volume section geometry that is dynamic and fully programmable.
In an embodiment, the elements 3106 may include heating elements (not shown) that allow for selective heating of the reconfigured flexible surface layer 3102 in a similar manner described herein with respect to the static and dynamic heating of the multi-dimensional build platform. Thus, in some embodiments, the system can reconfigure the shape of the surface of the build volume section, the temperature distribution across the build volume section (e.g., different heating zones), or a combination thereof.
In an embodiment, the elements 3002 may be dynamic to allow the changing of the shape of the outer layer 3102 during the course of operation.
One additional example is provided for using multi-dimensional build platform for food industry. In this embodiment the implementation is a programmable baking sheet or pan product. It could be for a home product or for the commercial food industry. In the context of the multi-dimensional build platform, the reconfigurable build volume section (shape changing build platform section) is used as programmable baking sheet or pan with integral heating elements for “baking”. It would allow a user to pick a shape from a computer, mobile phone or tablet visually, which would communicate and send instructions (geometry selected, and heating profile for current “production” run) to the base section to provide instructions to both the heating elements and shape changing elements within the build volume section. In this case there may be no additive manufacturing system per se, in an embodiment the mobile phone or “remote host” system is the “controller” in this use-case, and with no loss of generality, the standalone build platform is utilized to fabricate a plurality of cakes, cookies, cupcakes and other food items with one baking sheet, pan, or tray that can produce many different kinds of shape food products. This would be of use to the food industry where a company can use one type of machine to make many different products, reconfigurable as need, or just-in-time, based on production needs, etc.
One type functional characteristic that may be used to accommodate different material deposition requirements is to provide heated surface profiles during fabrication. In an embodiment, the multi-dimensional build platform may provide a heated fabrication surface either through a dynamic (i.e. time variable during a production run) or static (i.e. constant during the production run) heating methods, both of which are shown in the embodiments of
In an embodiment involving static heating, the thermal energy or heat is generated external by a heating component 2300 (
In some embodiments, the fluid/gas intake is through the platform attachment interface section 2308, such as through opening 2310 for example. In this embodiment, the openings 2306 may be used as an exhaust or outlet for the fluid/gas.
In an embodiment, shown in
The operation of the static apparatus heating component 2300 is through thermal convection, whereby heated gas/vapor streams traverse the base manifold 2304, through the build volume section lattice 2200, heating the build volume section surface layer 2202. The multi-dimensional build volume section surface heat distribution is improved or optimized through configuring the patterned and controlled methods of build volume lattice 2200 implementation to facilitate desired adhesion of materials to the multi-dimensional build platform apparatus during the additive manufacturing process.
In an embodiment one factor in the utilization of a topological optimized lattice structure where thermal convection of heated gas/vapor streams traverse the base section 2302 and build volume sections 2312 through the build volume lattice 2200 that comprises a high-temperature resin material. In an embodiment, the lattice structure is configured for gas transport to the build volume section outer surface area 2202 whose material comprises copper, aluminum, ceramic, high-temperature resin materials, or a combination of the foregoing.
In an embodiment, both the lattice structure and the material characteristics of the build volume section 2312 are used with optimization methods for configuring a desired distributed thermal conduction implementing a static heating surface element for material deposition. In some embodiments, the general method of topology optimization refers to a generative process whereby material layout within a given design space is optimized or configured based at least in part on a predetermined set of parameters, constraints, and boundary conditions. In some embodiments, this allows for the increasing or maximizing of the performance of a given multi-dimensional build platform.
An embodiment of the build volume lattice 2200 is the implementation (by the programmatic synthesis methods described herein) of non-uniform lattice structures whereby one or more interior manifolds and fluidic pathways control the trajectory or flow path of heated convention gases to pre-determined surface regions or zones 2600 (
In an embodiment, a topological optimization method for the build volume section lattice 2200 is implemented to include at least one of the following methods; 1) a lattice structure that is non-uniformly graduated and shaped to a Venturi geometry in order to increase or maximize the heated gas transport velocity to the surface of the build volume section 2312 while slowing the gas velocity underneath the build volume section outer layer 2202 surface areas to increase or maximize heat-transfer; 2) a build volume lattice 2200 that directs substantially all convection of heated fluids/gases to the build volume section surface 2202 uniformly to achieve a substantially uniform heat distribution on the surface of the build volume section outer layer 2202; and 3) a build volume lattice 2200 that implements a fluidic manifold such that specific heated zones of arbitrary geometry are defined.
In an embodiment, the build volume lattice 2200 provides different heating zones associated with different materials and structures. In an embodiment, shape, density, and geometry of the build volume lattice 2200 is defined to provide a non-uniform distribution of heat to the build volume section in a predetermined manner In an embodiment, the build volume lattice 2200 is comprised of static elements that define zones 2600 (
In an embodiment shown in
In the previous embodiments, the build volume lattice 2200 structure additionally supports the redirection of heated fluids/gases such that an external thermal measurement system can accurately monitor the temperature profile of the multi-dimensional build platform and adjust the heated fluids/gases convection processes in accordance with the material deposition parameters of the additive manufacturing system.
It should be appreciated that the description of the heating of the multi-dimensional build platform as being either statically or dynamically heated is for example purposes and the claims should not be so limited. In other embodiments, the multi-dimensional build platform may include both elements that provide both static and dynamic heating. Further still, embodiments herein may refer or illustrate the flowing of gasses to heat the multi-dimensional build platform, but other heating means may be used, such as liquid heating mediums for example.
It should further be appreciated that while the example embodiments discuss heating of the build volume section via convection, this is for example purposes and the claims should not be so limited. In other embodiments, heating of the build volume section may be performed by conduction or radiation as well.
Referring now to
In the embodiment of
The embodiment of
It should be appreciated that in some embodiment the coils 2729 are connected through conductors beneath the surface 2727 such as through via's for example In other embodiments, the coils 2729 may be operated inductively. It should also be appreciated that the build volume section 2702 may include one or more outer layers that conform to the surface 2717 to allow deposition of material during the additive manufacturing process.
In some embodiments, it is desirable to use an existing prior art build platform as a partial build volume section (surface layer 1) for a multi-dimensional build platform in order to upgrade an existing additive manufacturing system. Such as, for example, the original build platform provided by the additive manufacturing system. Referring now to
As discussed herein, in embodiments, the multi-dimensional build platform may be either an emulated build platform that is adapted to fit within a prior art additive manufacturing system as previously described. It should be appreciated, that a multi-dimensional build platform may be implemented as a complete replacement, such that the multi-dimensional build volume section geometry substantially matches the original additive manufacturing system build platform.
In an embodiment, the multi-dimensional build platform 302 is an efficient means for the implementation of medical and sensor electronic devices 3400 such as NMR and MRI systems as is shown in
Other medical and sensor devices may also be efficiently fabricated utilizing the multi-dimensional build platform, including; flexible wearables and other coil assemblies associated with flexible materials that conform with human anatomical structures such as receive coils, vital signs monitoring, and other biometric sensor devices in use today. The multi-dimensional build platform may also be utilized in prosthetic applications such as artificial joints and other multi-dimensional anatomical structures or organs. In an embodiment, the anatomical geometry may be used in with bioprinting utilizing biomaterials such as for cellular structures, DNA, or stem cells for example that may be used to fabricate skin or an organ for example.
Referring now to
One or more of the embodiments described herein, as shown in
According to one or more embodiments described herein, the build volume controller 2804 includes one or more of a power interface(s) 2810 (wired and/or wireless); communication (“comms”) module 2812 (e.g., wired and/or wireless, such as Bluetooth™ and Wi-Fi); a processor-based microcontroller 2814 which can include or be communicatively coupled to a memory 2817 and/or persistent storage; a build volume driver module 2816 that includes hardware and/or software to control one or more functional elements, which can be a coil power driver (e.g., MOSFET power driver circuits) (see, e.g.,
In an embodiment, the build volume controller 2804 within the base section 2803 provides control and operational integration with the additive manufacturing system 2822 through a wireless communications medium that provides for command and control of the build volume controller 2804 with no wires, entangling, or restrictive connections being used. Thus, the multi-dimensional build platform 2802 and additive manufacturing system 2822 have multi-axis degrees of freedom and movement. To facilitate this, a power interface 2810 may provide power charging capability wirelessly (e.g., via induction) to the build volume controller 2804 and a communications interface 2818 may provide command and control wirelessly to the build volume controller 2804. However, in other embodiments, including where the additive manufacturing system 2822 has limited axes of movement, limited range of motion, and/or where high levels of power are provided over extended periods of time, the power interface 2810 may be a wired interface. In these embodiments, the communications interface 2818 may provide command and control wirelessly and/or via a wired link. According to an example, a build platform power interface controller 2826 controls a power system 2828, which supplies power to the build volume controller 2804, using wired and/or wireless methods, via the power interface 2810.
With continued reference to
With continuing reference to
The build volume controller 2804 can communicate with the multi-dimensional build platform interface controller 2820 over any suitable wired and/or wireless link (e.g., the communications interface 2818), such as Bluetooth™ (BT), 802.11 Wi-Fi, or another suitable communications interface. The communications interface 2818 is bidirectional and enables the additive manufacturing system 2822 to deliver instructions (through the multi-dimensional build platform interface controller 2820) to the build volume controller 2804 to manage one or more feature and functional elements, such as heater coils (see, e.g.,
The microcontroller 2814 is provided that is responsive to executable computer instructions for activating, deactivating, and/or otherwise controlling the features and/or functional elements from instructions computed during dynamic apparatus multi-dimensional build platform synthesis (as described herein) and in accordance with the additive manufacturing system tool path operations associated to a given set of target object fabrication instructions. In an embodiment, software instructions, such as G-code, generate fabrication and activation/deactivation operations that the microcontroller 2814 further processes into feature or functional pattern activation and deactivation operations during the fabrication process. In this manner, minimal energy is expended while still providing for material deposition requirements. The microcontroller 2814 can be any suitable microcontroller, micro-processor, FPGA, digital signal processor, etc. One such example is a SoC or SoM single chip Linux-based computer complete with peripheral functions, input-outputs, communication interfaces, memory, and non-volatile storage. The operating system and/or application software may be controlled, configured, and updated through command-and-control operations transported via the communications interface 2818 providing integration to the additive manufacturing system 2822 through the multi-dimensional build platform interface controller 2820. In an embodiment, operating system and/or application software may also be controlled, configured, and/or updated through command-and-control operations transported via the communications interface 2818 providing integration to a remote system (e.g., smartphone, tablet, computer, cloud system, etc.).
According to one or more embodiments described herein, the microcontroller 2814 supports multiple digital input-outputs which are utilized by the build volume driver module 2816 to control one or more power active driver circuits, where each driver controls power and/or a signal distribution to a given functional element. For example, one or more of the heater coils (see, e.g.,
With continued reference to
Referring now to
In some embodiments, integration of the multi-dimensional build platform interface controller 2820 into the additive manufacturing system 2822 may be achieved either through the general purpose I/O communications of the microcontroller 2814 in the case of parallel I/O or serial communications, or wirelessly utilizing Bluetooth, near-field communication (NFC), radio frequency (RF), infrared (IR), and/or Wi-Fi communication interfaces and the like (e.g., communications module 2812). For example, the communications module 2812 can implement any suitable short-range communication protocol. As mentioned, the functionality of the multi-dimensional build platform interface controller 2820 is to provide an integration mechanism of the multi-dimensional build platform 2802 to the additive manufacturing system 2822. However, as an embodiment, the direct integration, through wireless transports mentioned, of the multi-dimensional build platform 2802 with the additive manufacturing system 2822 is possible, provided the additive manufacturing system 2822 supports wireless communications. The control process is the synthesized programmatic set of command-and-control instructions to orchestrate the operation of the microcontroller 2814 as part of intelligent management of the functional elements (e.g., heater elements, magnetic elements, optical devices, etc.) of the build volume section (see, e.g.,
Referring now to
Referring now to
Referring now to
Referring now to
The features and functionality of the systems 2800A, 2800B, and 2800C are now described in more detail with reference to
Particularly, each of the systems 2800A, 2800B, and 2800C include within the respective base sections 2803A, 2803B, 2803C embedded hardware and/or software to provide build volume section control using the build volume controller 2804. For example, the build volume controller 2804 can control one or more of the feature and functional elements of the build volume section 2805A (e.g., temperature, magnetic polarization, optical characteristics, etc.). Such control can be fixed, static, and/or dynamic as described herein.
For example, with reference to
In an embodiment, the build volume controller 2804 within the base section (e.g., the base section 2803A, the base section 2803C, the base section 2803C) provides control and operational integration with the additive manufacturing system 2822 through a wireless communications medium that provides for command and control of the build volume controller 2804 with no wires, entangling, or restrictive connections being used. Thus, the multi-dimensional build platform and additive manufacturing system have desired freedom of movement. To facilitate this, a power interface 2810 may provide power charging capability wirelessly (e.g., via induction) to the build volume controller 2804 and a communications interface 2818 may provide command and control wirelessly to the build volume controller 2804. However, in other embodiments, including where the additive manufacturing system 2822 has limited axes of movement, limited range of motion, and/or where high levels of power are provided over extended periods of time, the power interface 2810 may be a wired interface. In these embodiments, the communications interface 2818 may provide command and control wirelessly and/or via a wired link. According to an example, a build platform power interface controller 2826 controls a power system 2828, which supplies power to the build volume controller 2804, using wired and/or wireless methods, via the power interface 2810.
With continued reference to
With continuing reference to
The build volume controller 2804 can communicate with the multi-dimensional build platform interface controller 2820 over any suitable wired and/or wireless link (e.g., the communications interface 2818), such as Bluetooth™ (BT), 802.11 Wi-Fi, or another suitable communications interface. The communications interface 2818 is bidirectional and enables the additive manufacturing system 2822 to deliver instructions (through the multi-dimensional build platform interface controller 2820) to the build volume controller 2804 to manage features, such as the heater coils (e.g., coil 1 2806a, coil 2 2806b, coil 3 2806c, coil 4 2806d, coil N 2806n), the magnetic coils (e.g., coil 1 2846a, coil 2 2846b, coil 3 2846c, coil 4 2846d, coil N 2846n), optical devices (e.g., optical device 1 2866a, optical device 2 2866b, optical device 3 2866c, optical device 4 2866d, optical device N 2846n), and/or the like, including combinations thereof. It should be appreciated that the build volume controller 2804 may manage any feature or functional characteristic as described herein and the embodiments described herein are not so limited to the disclosed feature or functional characteristics in
The microcontroller 2814 is provided that is responsive to executable computer instructions for activating, deactivating, and/or other wise controlling the features and/or functional elements from instructions computed during dynamic apparatus multi-dimensional build platform synthesis (as described herein) and in accordance with the additive manufacturing system tool path operations associated to a given set of target object fabrication instructions. In an embodiment, software instructions, such as G-code, generate fabrication and activation/deactivation operations that the microcontroller 2814 further processes into feature pattern activation and deactivation operations during the fabrication process. In this manner, minimal energy is expended while still providing for material deposition requirements. The microcontroller 2814 can be any suitable microcontroller, micro-processor, FPGA, digital signal processor, etc. One such example is a SoC or SoM single chip Linux-based computer complete with peripheral functions, input-outputs, communication interfaces, memory, and non-volatile storage. In an embodiment, the operating system and/or application software may be controlled, configured, and/or updated through command-and-control operations transported via the communications interface 2818 providing integration to the additive manufacturing system 2822 through the multi-dimensional build platform interface controller 2820. In an embodiment, operating system and/or application software may also be controlled, configured, and/or updated through command-and-control operations transported via the communications interface 2818 providing integration to a remote system (e.g., smartphone, tablet, computer, cloud system, etc.).
According to one or more embodiments described herein, the microcontroller 2814 supports multiple digital input-outputs which are utilized by the build volume driver module hardware to implement one or more power MOSFET driver circuits, where each driver controls power distribution to a given coil. For example, one or more of the heater coils (e.g., coil 1 2806a, coil 2 2806b, coil 3 2806c, coil 4 2806d, coil N 2806n) provide joule-based heating across the specified heater pattern specifications of the build volume section 2805A. With reference to
The multi-dimensional build platform interface controller 2820 provides an integration mechanism between the multi-dimensional build platform 2802A and the additive manufacturing system 2822. In some examples, the multi-dimensional build platform interface controller 2820 is based on the same hardware design as the build volume section 2805C, 2805B, 2805C and base section 2803A, 2803B, 2803C without the requirement of features (e.g., heater coils, magnetic coils, optical devices, etc.) or driver electronics. In some embodiments, this configuration is similar as to simplify the systems 2800A, 2800B, 2800C in terms of a common implementation method and secondly to reduce the total cost of the multi-dimensional build platform 2802A, 2802B, 2802C through use of common electronic components.
In this example, the build volume section 2805B includes magnetic coils 2846a, 2846b, 2846c, 2846d, . . . 2846n, which may be associated with magnetic elements (e.g., magnetic element 1 2848a, magnetic element 2 2848b, magnetic element N 2848n). According to one or more embodiments described herein, each magnetic element may include one or more magnetic field sensors, such as a Hall effect sensor, shown as sensors 2850. The sensors 2850 measure magnetic field strength in their respective magnetic elements. Readings from the sensors 2850 can be used to adjust, using the build volume driver module 2816 (e.g., a magnetic coil driver), the magnetic field within one or more of the magnetic elements 2848a, 2848b, 2848n. In one or more embodiments, each magnetic element can include a single sensor 2850, multiple sensors 2850, or no sensor.
The system 2800C of
In this example, the build volume section 2805C includes optical devices (ODs) 2866a, 2866b, 2866c, 2866d, . . . 2866n (e.g., LEDs, lasers, etc.), which may be associated with optical elements (e.g., optical element 1 2868a, optical element 2 2868b, . . . optical element N 2868n). According to one or more embodiments described herein, each optical element may include one or more optical sensors, shown as sensors 2870. The sensors 2870 measure optical energy so it can be known how much photonic power or energy is output from each of the optical devices 2866a-2866n in their respective optical elements. Readings from the sensors 2870 can be used to adjust, using the build volume driver module 2816 (e.g., an optical device driver), the optical characteristics within one or more of the optical elements 2868a, 2868b, 2868n. In one or more embodiments, each optical element can include a single sensor 2870, multiple sensors 2870, or no sensor.
It should be appreciated that the systems 2800B and 2800C operate substantially similarly to the system 2800A of
Turning now to
In the example of
In the example of
In the example of
Particularly,
A target object CAD model 3802 is input into the AMS code generator 3804 (which can be a slicer) using a suitable file type that describes the surface geometry of the object or assembly to be fabricated as a 3-dimensional object model, such as an STL file. According to one or more embodiments, the AMS code generator 3804 is a program that can support a slicer whose code output supports the operation of an additive manufacturing system (e.g., the additive manufacturing system 3806) that can operate in multiple degrees of freedom and supports fabrication operations over various surfaces.
It should be appreciated that the tools (e.g., a print head) and/or the build platform (e.g., the multi-dimensional build platform 3930) may have independent freedom or degrees of movement. As one example, a tool can move along the x-axis and/or y-axis while the build platform can move only along the z-axis. As another example, a tool can move along the x-axis and/or y-axis while the build platform can move only along the z-axis and/or rotate. As another example, a tool can move along the x-axis and/or y-axis while the build platform can move along the x-axis, the y-axis, and/or the z-axis and/or rotate. As another example, a tool can move along the x-axis, y-axis, and/or x-axis while the build platform can move along the x-axis, the y-axis, and/or the z-axis and/or rotate. In this example, the tools and build platform have independent degrees of freedom. As another example, other degrees of freedom (e.g., 5 axis, such as X,Y,Z, yaw, pitch, rotation, and roll; 7-axis; etc.) may be available and can be utilized.
It should be appreciated that one or more of the embodiments described herein can be implemented in the AMS code generator 3804 to support fabrication to non-planar build surfaces as is the case with the multi-dimensional build platform within additive manufacturing systems whose tool operations utilize a consistent orientation to the build surface. The STL file is also input into a multi-dimensional build platform synthesis 3920, which synthesizes the object model to determine a multi-dimensional build platform configuration to be used as described herein. In the example of
According to one or more embodiments described herein, the additive manufacturing system 3806 may also control a heating system (referred to as additive manufacturing system heat generation 3922) to generate directed convection heat 3924 for utilization by the multi-dimensional build platform 3930.
A target object CAD model 3802 is input into the AMS code generator 3804 using a suitable file type that describes the surface geometry of the object or assembly to be fabricated as a 3-dimensional object model, such as an STL file. The STL file is also input into the multi-dimensional build platform synthesis 3920, which synthesizes the object model to determine a multi-dimensional build platform configuration to be used as described herein.
Once the multi-dimensional build platform synthesis 3920 determines the multi-dimensional build platform configuration to be used, such configuration is provided to the AMS code generator 3804 to reference the target object fabrication relative to the multi-dimensional build platform geometry within the additive manufacturing system 3806 and to a multi-dimensional build platform control process 4022 as a software (SW) file 4021 (or other suitable file). For example, the software file 4021 can be a control script, library file, or other suitable software file. Using the STL files received from the target object CAD model 3802 and from the multi-dimensional build platform synthesis 3920, the AMS code generator 3804 converts the multi-dimensional object model configuration of the STL files into specific instructions for the additive manufacturing system 3806 to use to fabricate the object or assembly, such as by generating a G-code file. The additive manufacturing system 3806 controls a tool (such as a print head) using tool control 3808 to fabricate the object or assembly on the multi-dimensional build platform 4040. The additive manufacturing system 3806 controls the multi-dimensional build platform 4040 using build platform control 3812, which can include manipulating the orientation and location of the multi-dimensional build platform 4040.
The multi-dimensional build platform control process 4022 provides for real-time (or near-real-time) monitoring of the additive manufacturing system 3806. This enables synchronization between the multi-dimensional build platform 4040 and the additive manufacturing system 3806. Particularly, according to one or more embodiments, the multi-dimensional build platform control process 4022 monitors (e.g., “snoops”) position information, active tools, system, timing and state information (e.g., what the additive manufacturing system 3806 is doing) using the information 4023, which can be G-code control commands for example. Based on the information 4023, the multi-dimensional build platform control process 4022 can determine what operations the multi-dimensional build platform interface controller 4024 executes. Then, the multi-dimensional build platform interface controller 4024 controls the multi-dimensional build platform 4040 based on the build control 4025 generated by the multi-dimensional build platform control process 4022.
As an example, the multi-dimensional build platform control process 4022 also uses the software file 4021 from the multi-dimensional build platform synthesis 3920 and information 4023 from the additive manufacturing system 3806 to control the functional elements, such as heating coils (e.g., one or more of the heater coils 2806a, 2806b, 2806c, 2806d, 2806n of
According to one or more embodiments described herein the multi-dimensional build platform control process 4022 receives information 4023 from the additive manufacturing system 3806. The information 4023 could be received using a poll and/or a pull delivery method, whereby the multi-dimensional build platform control process 4022 requests the information 4023 from the additive manufacturing system 3806, and/or the information 4023 could be received using a push delivery method, whereby the additive manufacturing system 3806 pushes, streams, messages, or otherwise makes available the information 4023 to the multi-dimensional build platform control process 4022. The information 4023 can include default or generic commands (e.g., M commands) and/or other language extensions to turn the functional elements (e.g., heater coils, magnetic coils, optical devices, etc.) on or off as well as setting global characteristics (e.g., temperature, polarization, opacity, etc.). The multi-dimensional build platform control process 4022 uses the information 4023 along with geometry information of a current extruder or tool position to signal (via the multi-dimensional build platform interface controller 4024) the multi-dimensional build platform control process 4022 so that it knows which functional elements (e.g., one or more of heater coils 2806a, 2806b, 2806c, 2806d, 2806n) to, inter alia, activate/deactivate, control, synchronize timing, or otherwise when to do so, for how long, and at what temperature in accordance with the required global temperature characteristics and material requirements. In an embodiment, the G-code for the target object is received prior to fabrication of the target object so preheating or energizing the heater coils (e.g., heater coils 2806a, 2806b, 2806c, 2806d, 2806n) can occur so that when a real-time command (e.g., the G-code heater control commands) is received from the additive manufacturing system, a heat path trajectory would already have been calculated.
In some embodiments, the multi-dimensional build platform control process 4022 can use the information 4023 to geometrically reconfigure the multi-dimensional build platform 4040. For example, a surface geometry of the multi-dimensional build platform 4040 can be dynamically reprogrammable/reconfigurable as defined by the information 4023. According to one or more embodiments described herein, the dynamic geometrical reconfiguration of the multi-dimensional build platform 4040 is accomplished by programmatic control of each functional element. Particularly, electronic control, light control, or some other control/actuation can be used for reconfiguration/control of the surface geometry. Other methods for such control/reconfiguration can be implemented in the functional elements to control shape. The G-code (as described herein) or programming of the multi-dimensional build platform interface controller 2820 can be enhanced to add additional support for different control scenarios. For example, in the case of magnetic polarization (see, e.g.,
The target object CAD model 4104 represents a CAD model of a target object (i.e., an object or assembly to be fabricated). The target object multi-dimensional scan 4106 represents a multi-dimensional (e.g., 2D and/or 3D) scan of the target object or of an article associated with the target object. A scan can be useful when a target object is desired for a unique application. For example, in a case where the target object is a knee brace, a scan of a human's knee intended to use the knee brace can be used. The user-generated multi-dimensional build platform CAD model 4108 represents a CAD model generated by a user to be used to fabricate the target object as a multi-dimensional build platform itself.
The multi-dimensional build platform synthesis system application 4102 communicates with the additive manufacturing system 3806 and the multi-dimensional build platform control process 4022 in the additive manufacturing system domain 4112 to manufacture the target object given a suitable input file specification of the target object. Particularly, the multi-dimensional build platform synthesis system application 4102 can send the G-code configuration file to the additive manufacturing system 3806 software system and/or software code to the multi-dimensional build platform control process 4022 to orchestrate target object fabrication by the additive manufacturing system in conjunction with the multi-dimensional build platform. For example, an STL file is sent to the AMS code generator 3804, which can be part of the additive manufacturing system 3806 software preprocessing. The slicer uses the multi-dimensional build platform geometry information to reconcile the build platform (for example the build platform may no longer be a planer flatbed) to input target object STL to be fabricated.
According to an example, the multi-dimensional build platform synthesis system application 4102 runs on a local host computer (not shown) communicatively coupled to the additive manufacturing system 3806 and a multi-dimensional build platform control process 4022 as shown. The multi-dimensional build platform synthesis system application 4102 can be integrated into or executed by the local host computer, although other implementations are also possible. This example is referred to as the “local deployment” and utilizes the multi-dimensional build platform synthesis system 4150, which is integrated into the multi-dimensional build platform synthesis system application 4102. The features and functionality of the multi-dimensional build platform synthesis system application 4102 described with reference to
In another example, the multi-dimensional build platform synthesis system application 4102 can be implemented using cloud computing, which is referred to as the “cloud deployment” (e.g., cloud deployment 4113). In the cloud deployment 4113, at least some of the features and functionality of the multi-dimensional build platform synthesis system application 4102 are deployed to one or more cloud computing nodes, which together form the multi-dimensional build platform synthesis system 4152. For example, in one or more embodiments, a cloud computing system (e.g., the multi-dimensional build platform synthesis system 4152) can be in wired or wireless electronic communication with one or more of the elements of the system 4100, such as the multi-dimensional build platform synthesis system application 4102. Cloud computing can supplement, support, and/or replace some or all of the functionality of the elements of the system 4100, including the multi-dimensional build platform synthesis system application 4102. Additionally, some or all of the functionality of the elements of system 4100 can be implemented as a node or nodes of a cloud computing system. A cloud computing node is only one example of a suitable cloud computing node and is not intended to suggest any limitation as to the scope of use or functionality of embodiments described herein.
The multi-dimensional build platform synthesis system application 4102 receives one or more of a target object CAD model 4104, a target object multi-dimensional scan 4106, target object RGB-D image 4107, and/or a user-generated multi-dimensional build platform CAD model 4108 as described herein. These inputs are collectively referred to as the “input data.” The input data can take the form of an STL file, object file, mesh file, a point cloud file, B-rep, voxel, etc., each describing the geometry of the target object. The multi-dimensional build platform synthesis system application 4102 uses the received input data to perform multi-dimensional platform selection and synthesis as shown by block 4210, which is now described.
For the target object multi-dimensional scan 4106, the multi-dimensional build platform selection and synthesis at block 4210 performs parametric tagging of the target object to optimize multi-dimensional build platform synthesis at block 4212. For the target object CAD model 4104 and the user-generated multi-dimensional build platform CAD model 4108, the parametric tagging at block 4212 is processed similarly.
Next, an intelligent multi-dimensional build platform model matching engine 4214 determines whether the input data, in conjunction with parametric fabrication data, match an existing multi-dimensional build platform model. This is done, for example, using machine learning to compare the geometry and fabrication parametric data sets to data associated with existing multi-dimensional build platform models stored in a multi-dimensional build platform model database 4215. This enables the multi-dimensional build platform selection and synthesis at block 4210 to determine whether an existing model multi-dimensional build platform can be used as a multi-dimensional build platform for the object or assembly to be fabricated as indicated by the target object input data. It should be appreciated that, in some examples, the input data are tagged or enriched via automated and/or user control within the multi-dimensional build platform synthesis system application 4102. The input data includes geometry data, so parameterization occurs on the input data within a user interface of the multi-dimensional build platform synthesis system application 4102, for example. The techniques described in
A given candidate solution is returned by the intelligent multi-dimensional build platform model matching engine 4214 as a triplet of build volume section, base section, and attachment interface section grouped in accordance to a ranked order by similarity and alignment score based on geometries, feature/functional characteristics and fabrication parametric datasets in relation to the target object input dataset.
According to one or more embodiments described herein, the present techniques can incorporate and utilize rule-based decision making and artificial intelligence (AI) reasoning to accomplish the various operations described herein, namely performing multi-dimensional build platform model matching. The phrase “machine learning” broadly describes a function of electronic systems that learn from data. A machine learning system, engine, or module can include a trainable machine learning algorithm that can be trained, such as in an external cloud environment, to learn functional relationships between inputs and outputs that are currently unknown, and the resulting model can be used for performing multi-dimensional build platform model matching. In one or more embodiments, machine learning functionality can be implemented using an artificial neural network (ANN) having the capability to be trained to perform a currently unknown function. In machine learning and cognitive science, ANNs are a family of statistical learning models inspired by the biological neural networks of animals, and in particular the brain. ANNs can be used to estimate or approximate systems and functions that depend on a large number of inputs. Convolutional neural networks (CNN) are a class of deep, feed-forward ANN that are particularly useful at analyzing visual imagery.
ANNs can be embodied as so-called “neuromorphic” systems of interconnected processor elements that act as simulated “neurons” and exchange “messages” between each other in the form of electronic signals. Similar to the so-called “plasticity” of synaptic neurotransmitter connections that carry messages between biological neurons, the connections in ANNs that carry electronic messages between simulated neurons are provided with numeric weights that correspond to the strength or weakness of a given connection. The weights can be adjusted and tuned based on experience, making ANNs adaptive to inputs and capable of learning. For example, an ANN for handwriting recognition is defined by a set of input neurons that can be activated by the pixels of an input image. After being weighted and transformed by a function determined by the network's designer, the activation of these input neurons are then passed to other downstream neurons, which are often referred to as “hidden” neurons. This process is repeated until an output neuron is activated. The activated output neuron determines which character was read. In some examples, unsupervised methods of machine learning can be implemented, including iterative learning as in a random sample consensus (RANSAC) technique, clustering, etc. These and other methods for object recognition or comparison can be use in accordance with one or more of the embodiments described herein. Particularly, the present techniques can make use of any development in 3D object recognition and retrieval with no loss of generality relative to the extension method to include fabrication data as part of the model search and retrieval techniques as described herein. It should be appreciated that these same techniques can be applied in the case of multi-dimensional build platform model matching at block 4214.
If no match is detected by the intelligent multi-dimensional build platform model matching engine 4214, or if the matching process yields a solution set as returned by the multi-dimensional build platform model database 4215 is non-optimal as determined by the user, the multi-dimensional build platform synthesis 4216 can use multi-dimensional build platform geometry primitives stored in a multi-dimensional build platform primitive database 4218 to generate a new build volume section geometry model that is further enhanced to include fabrication feature data that can be used as a candidate multi-dimensional build volume section to fabricate the object or assembly specified by the input data. The next step in creating a complete synthesized multi-dimensional build platform within the multi-dimensional build platform synthesis 4216 is to associate the newly synthesized multi-dimensional build volume section with compatible base section and attachment interface section (as stored within the multi-dimensional build platform model database 4215) for the given multi-dimensional build volume section and fabrication parametric data. Then, the multi-dimensional build platform model database 4215 is updated with data from the previous step and to generate new indices so the new multi-dimensional build platform model or set of models are searchable by the intelligent multi-dimensional build platform model matching engine 4214. This process of generating a new multi-dimensional build platform model can be automated, such as by machine learning, or can be manual, such as by a user manually generating the new multi-dimensional build platform model or sub-sections such as the base section or attachment interface section. Once generated, a new multi-dimensional build platform model or sub-sections can be stored to the database 4215. It should further be appreciated that the user-generated multi-dimensional build platform CAD model 4108 can be stored directly in the multi-dimensional build platform model database 4215 and can additional be utilized by the intelligent multi-dimensional build platform model matching engine 4214 for training the machine learning system.
If a match in the form of a feasible solution or set of solutions are detected by the intelligent multi-dimensional build platform model matching engine 4214, or once a new multi-dimensional build platform model is generated at the multi-dimensional build platform synthesis 4216 and incorporated into the multi-dimensional build platform model database 4215 thereafter available within the multi-dimensional build platform solution set, a multi-dimensional build platform solution is selected. The method 4200 proceeds to a multi-dimensional build platform partitioning process 4220 shown in
According to an example, and with reference to
For multi-dimensional build platforms (as determined at block 4228), the method 4200 proceeds to the multi-dimensional build platform generation at block 4230 as shown in
At blocks 4230, 4232, 4234, 4236, and 4238, the method 4200 is again implemented using the multi-dimensional build platform synthesis at block 4210 and is controlled interactively using the multi-dimensional build platform synthesis system application 4102. At block 4230, build volume section mesh & layer generation and optimization of features/functional elements (e.g., heating, magnetic fields, optical devices, etc.) occurs. According to one or more embodiments described herein, mesh/layer generation and definition of properties occurs at block 4230 (see, e.g.,
At block 4236, the method 4200 includes generating the multi-dimensional build platform features/functions, component (such as sensors, electronic devices including analog and digital electronics, circuits and their interconnections/netlists, etc.) and toolpath information. Corresponding G-code is output to the toolpath process 4242. At block 4238, the multi-dimensional build platform command and control configuration (features/functions) and code configuration occurs and is output as G-code and/or a dynamic native library, and/or other computer language instructions and formats to the multi-dimensional build platform control process 4022. The AMS code generator 3804 (which may be a slicer, for example) causes the additive manufacturing system 3806 to fabricate the target object or assembly using the target object STL files and while considering the multi-dimensional build platform as part of the additive manufacturing system fabrication process. The AMS code generator 3804 also generates the multi-dimensional build platform manufacturing files used to fabricate at block 4244 in conjunction with the toolpath process 4242.
According to one or more embodiments described herein, the combination of the multi-dimensional build platform geometry generation at block 4234, the multi-dimensional build platform feature, functional, component, and toolpath generation at block 4236, the toolpath process 4242, and the fabricate multi-dimensional build platform block 4244 are instructions to build/fabricate the multi-dimensional build platform using instructions from the AMS code generator 3804. The AMS code generator 3804 in combination with the additive manufacturing system 3806 enables the fabrication of the desired multi-dimensional platform (including the build volume, interface, and base sections).
According to one or more embodiments described herein, the combination of the multi-dimensional build platform geometry generation at block 4234 and the multi-dimensional build platform control process 4022 provides code for controlling the functional elements (see, e.g.,
Additional processes also may be included, and it should be understood that the process depicted in
At block 4302, a user starts the multi-dimensional build platform synthesis system application 4102. At block 4304, the multi-dimensional build platform synthesis system execution is started either on the local deployment or cloud-based deployment (see, e.g.,
For example, the user defines the way in which the target object is to be made, its material characteristics, desired attributes, etc., and what the user is trying to accomplish. That is, the user define a target object mesh with one or more functional elements, and associates target object properties to corresponding mesh elements. The collection of target object properties are used to identify a suitable build volume section (such as in the multi-dimensional build platform model database 4215) or to create the build volume section (such as using synthesis as described herein). As an example, consider a target object as a planar slab made from approximately 50% of a first material on a first half and approximately 50% of a second material on a second half opposite the first half. In such a scenario, it might be that the first material needs a certain amount of heat (e.g., 200 F) applied while the second material needs a different amount of heat (e.g., 300 F) applied. The user defines these parameters at blocks 4307, 4308 as target object properties that are used to identify or create the build platform.
At block 4310, the user selects one or more (1:N) target additive manufacturing systems based on the target object properties from block 4308. That is, the user selects a type/model of additive manufacturing system that is suitable for fabricating the target object. At block 4312, the user defines additive manufacturing system operating parameters and configuration. At block 4314, the user invokes the intelligent multi-dimensional build platform model matching engine 4214 from
At block 4318, the intelligent multi-dimensional build platform model matching engine 4214 (see
At block 4320, the intelligent multi-dimensional build platform model matching engine 4214 returns a set of multi-dimensional build platform candidate solutions. A given candidate solution is a triplet of build volume section, base section, and attachment interface section grouped in accordance with a ranked order by similarity and alignment score based on geometries, feature/functional attributes, and fabrication parametric datasets in relation to the target object input dataset. For any given target object input, there can be one or more candidate solutions forming a candidate solution set. At block 4321, it is determined whether the solution set is an empty set or is outside the defined threshold criteria. If “no” at block 4321 (that is, if the solution set is not empty and is not outside defined threshold criteria), the method 4300 proceeds to block 4322.
At block 4322, the user evaluates and selects the multi-dimensional build platform from the set of solution candidate from the multi-dimensional build platform model database 4215. Then, at block 4323, the selected multi-dimensional build platform is implemented to fabricate the object and/or assembly. The method 4300 then proceeds to block 4428 (see
If “yes” at block 4321 (that is, if an empty set or the solution(s) are outside the defined threshold criteria), the method 4300 proceeds to block 4325. At block 4325, it is determined whether the solution(s) fit within the additive system usable fabrication volume. If “no” at block 4325, the method 4300 continues to block 4326 multi-dimensional build platform partitioning is performed as described herein, and the method 4300 returns to block 4318. If “yes” at block 4325, the method 4300 proceeds to block 4428 (see
With reference to
Additional processes also may be included, and it should be understood that the process depicted in
The geometry processing 4502 builds information about the geometry of the target object or a multi-dimensional build platform. To do this, the geometry processing 4502 processes geometry data using a multi-dimensional format conversion processor 4505 to convert various types of input data into various other types of output data that can be used downstream. For example, the multi-dimensional format conversion processor 4505 can convert one or more of the following input data types into different output data types: multi-format MESH and B-Rep data from a multi-format MESH and B-Rep importer 4506, RGB-D data (e.g., 2.5D data from scanners) from a RGB-D importer 4508, and/or point cloud data from a point cloud importer 4510. Examples of data fed into the importers 4506, 4508, 4510 include the target object CAD model 4104, the target object multi-dimensional scan 4106, the target object RGB-D image 4107, and/or the user-generated multi-dimensional build platform CAD model 4108 (see
A configurable multi-view scene generator 4520 can also receive data from the multi-dimensional format conversion processor 4505 and, using that data, can configure a multi-view scene dataset 4522 in the form of images. The configurable multi-view scene generator 4520 uses scenes/poses, for example, to take a camera view, put it in a unit sphere, and take snap shots of the unit sphere from different angles to generate the dataset 4522. In other examples, the configurable multi-view scene generator 4520 uses tetrahedrons or other geometries instead of spheres. The configurable multi-view scene generator 4520 can take planer views in some examples. Each of the various implementations of the configurable multi-view scene generator 4520 uses different views to generate internal datasets, selects what kind of view generation to execute, and then generates the multi-view scene dataset 4522 as images based thereon. In some examples, the configurable multi-view scene generator 4520 uses one or more scene generation techniques to generate the dataset 4522. For example, the configurable multi-view scene generator 4520 can generate a scene (i.e., the multi-view scene dataset 4522) using geometry primitives. The configurable multi-view scene generator 4520 is configurable in that the way in which views/scenes are generated can be configured, such as by selecting different geometry primitives to generate the scenes.
The feature and functional metadata processing 4504 builds information about the fabrication of a target object and/or a multi-dimensional build platform. To do this, feature and functional metadata processing 4504 uses an additive system & target object parametric fabrication vector and 2D/3D mesh/layer generator 4524 to generate fabrication features/functional datasets using the additive system profiles & target object attributes 4209 with selections and data provided by the user. For example, one or more configurable fields is built into the feature and functional metadata processing 4504 while one or more other fields can be based on user input. In some examples, the additive system profiles & target object attributes 4209 are imported so that they can be used for matching against the multi-dimensional build platform model database 4215. In other examples, such as when it is desired to add a new multi-dimensional build platform 4525 to the multi-dimensional build platform model database 4215, the new multi-dimensional build platform 4525 can be imported directly into the additive system & target object parametric fabrication vector and 2D/3D mesh/layer generator 4524. The additive system & target object parametric fabrication vector and 2D/3D mesh/layer generator 4524 generates a vector of features/functional metadata associated with the additive system profiles & target object attributes 4209, and its output is combined with the output of the geometry processing 4502. The additive system & target object parametric fabrication vector and 2D/3D mesh/layer generator 4524 also maps features/functional characteristics to their respective mesh/layer elements, which are addressable, on the build platform, as described herein.
The outputs of the geometry processing 4502 and the feature and functional metadata processing 4504 represent geometry information, feature/functional, and fabrication information respectively about the target object and/or or a multi-dimensional build platform. These outputs are used to generate a target object unified geometry and attribute dataset 4526 for a target object and/or a multi-dimensional build platform unified geometry and feature/functional training/predefined dataset 4528 for a multi-dimensional build platform. Each of datasets 4526, 4528 represent and contain the set of geometrical, properties, attributes, characteristics, and/or behavior associated with the imported target object and/or desired multi-dimensional build platform respectively.
As a result, the dataset 4528 is generated that is unified in nature (in an internal format) that has one dataset one per target object or one dataset per multi-dimensional build platform. These datasets representing either of target object or multi-dimensional build platform geometry models can take the form of voxels, point clouds, skeletons, etc. and can be enhanced in the case of a 3D target object with multiple views of the object as 2D images of the object. The models can be further enhanced with additive manufacturing system profiles and target object attributes (e.g., material type, etc.) that are not captured in the geometry.
The multi-dimensional geometry analysis 4602 analyzes the outputs of the multi-view scene processing block 4604, the object processing block 4606, the point cloud processing block 4608, and/or the skeleton processing block 4610 as input into a neural network or multiple neural networks, which use those outputs as inputs and generate a geometry classification label 4612 and the geometry vector 4614. For example, multiple neural network algorithms can be implemented by the multi-dimensional geometry analysis 4602. These multiple neural network algorithms can be based on multiple views or 2D images, voxels, point clouds, etc. depending upon the 3D shape recognition and retrieval algorithm in use. For example, multiple neural network algorithms can be executed, and the resulting results can be ranked and provided as part of a set of solutions. “Large-Scale 3D Shape Retrieval from ShapeNet Core55” to Manolis Savva, et al., is incorporated by reference. “A survey of Content Based 3D shape Retrieval Methods” to Johan W. H. Tangelder and Remco C. Veltkamp is also incorporated by reference herein.
A multi-dimensional object parametric fabrication feature/functional analysis 4618 analyzes the target object unified geometry and attribute dataset 4526 for a target object and the multi-dimensional build platform unified geometry and feature/functional training/predefined dataset 4528 using a neural network (or multiple neural networks). The neural network in the multi-dimensional object parametric fabrication feature/functional analysis 4618 generates a fabrication vector 4620, which enables consideration of functional capabilities, operation, and manufacturability of the multi-dimensional build platform.
In some cases, the unified multi-dimensional build platform query/update engine 4622 operates in an update mode to update a model stored in the multi-dimensional build platform model database 4215. In other cases, the unified multi-dimensional build platform query/update engine 4622 operates in a query mode to generate a multi-dimensional query to retrieve one or more models from the multi-dimensional build platform model database 4215. For example, in such cases, the unified multi-dimensional build platform query/update engine 4622 performs a similarity analysis using the geometry classification label 4612 and the geometry vector 4614. Particularly, the geometry classification label 4612 generated by the multi-dimensional geometry analysis 4602 indicates a class/category using for performing course filtering (as a first step of the similarity analysis) to identify a set of possible candidates. The geometry vector 4614 can the then be used (as a second step of the similarity analysis) to perform a finer filtering to perform a detailed lookup based on geometry characteristics of items stored in the multi-dimensional build platform model database 4215 using, for example, an L2 Euclidean distance measurement or other suitable similarity matching technique (e.g., wavelets, Fourier analysis, probability density, etc.). By using the two-step filtering in the similarity analysis/query processing, 3D object retrieval processing performance is improved, and processing time is reduced because the geometry classification label 4612 can be used to eliminate a portion of the stored models, meaning that the similarity matching (e.g., L2 Euclidean distance measurement) need not be performed on each of the stored models but only on a subset thereof (as identified by the geometry classification label 4612). To make this even more efficient, the multi-dimensional build platform model database 4215 is indexed, not as a lookup/relational database, but through a combination of classified multi-dimensional build platform models indexed by a geometry classification label-set. Within each category, the use of R-trees implementing a multi-dimensional index/key structure that organizes multi-dimensional spatial datasets can be implemented.
In some examples, the unified multi-dimensional build platform query/update engine 4622 can also use a label classifier to cut down the search space to pre-classify the models. The neural network of the multi-dimensional object parametric fabrication feature/functional analysis 4618 focuses on the features, functional characteristics, and fabrication aspects of the multi-dimensional build platform. This enables the unified multi-dimensional build platform query/update engine 4622 to combine geometry attributes (i.e., the geometry classification label 4612 and the geometry vector 4614) with fabrication attributes (i.e., the features such as material properties, functional characteristics such as active and dynamic components, aggregated into a single fabrication vector 4620) to find candidate set of solutions for a multi-dimensional build platform configuration.
The predictive pipeline 4702 produces a first rendering 4710 using the target object unified geometry and attribute dataset 4526. To do this, the predictive pipeline 4702 uses neural networks to recognize the shape of an object and generate a constructive solid geometry (CSG) operation tree. For example, the predictive pipeline 4702 uses a shape/primitive analysis pipeline 4706 to recognize the shape of the object using a first neural network(s). Then, predicted CSG tree generation 4708 generates the first rendering 4710 using a second neural network(s) to construct a CSG tree for the object. According to one or more embodiments described herein, the predictive pipeline 4702 induces a CSG tree using a parsing methodology. The predictive pipeline 4702 uses a set of neural networks (blocks 4706, 4708) to predict the CSG tree and render the tree to generate the first rendering 4710. “CSGNet: Neural Shape Parser for Constructive Solid Geometry” to Gopal Sharma, et al., is incorporated by reference.
The generative pipeline 4704 produces a second rendering 4712 using the target object unified geometry and attribute dataset 4526. A shape/primitive analysis 4714 implements a random sample consensus (RANSAC) technique used for computer vision, which is an unsupervised approach. A CSG tree program synthesis 4716 is performed that follows the CSG design model and uses a synthesis method using a CSG tree. An example of CSG tree generation is described in “InverseCSG: Automated Conversion of 3D Models to CSG Trees” to Tao Du, et al., which is incorporated by reference herein. In an example, the CSG tree includes leaves that are primitive shapes and edges that are interactions (e.g., unions). This approach provides a method to analyze a given 3D target/image and construct, through program synthesis, the second rendering 4712. The second rendering 4712 can be post-processed at 4718.
A similarity and scoring analysis 4722 is performed on the renderings 4710, 4712 to compare the renderings 4710, 4712, and score/rank the renderings 4710, 4712. Particularly, the similarity and scoring analysis 4722 compares the first rendering 4710 (from the predictive pipeline 4702) to the second rendering 4710 (from the generative pipeline 4704) to determine how good the predictive rendering (the first rendering 4710) as compared to the generative rendering (the second rendering 4712). The similarity and scoring analysis 4722 can be performed iteratively (e.g., a certain number of times, until a desired similarity has been obtained, etc.). In examples, the similarity and scoring analysis 4722 utilizes an L2 Euclidean distance measurement technique to compare the renderings 4710, 4712. It should be appreciated that L2 Euclidean distance measurement is one approach to measuring similarity, but others exist (e.g., wavelets, Fourier analysis, probability density, etc.) and are within the scope of the embodiments described herein. The similarity and scoring analysis 4722 determines whether the renderings 4710, 4712 are sufficiently similar, such as by comparing their Euclidean distances. For example, several CSG trees are returned and ranked using their Euclidean distances, and the highest ranked CSG tree is passed as geometry data for incorporation into the multi-dimensional build platform unified geometry and feature/functional training/predefined dataset 4528.
In some examples, the predictive pipeline 4702 uses a reenforced learning methodology to update/improve the neural networks of blocks 4706, 4708 to improve the predictive pipeline 4702. For example, at block 4720, an objective function uses reinforced learning to improve the predictive pipeline 4702 as shown using results of the similarity and scoring analysis 4722 and the target object metadata 4701. The objective function at block 4720 can re-train/improve the neural networks (blocks 4706, 4708) of the predictive pipeline 4702 by updating them using reinforced learning (see block 4720). In examples, the objective function at block 4720 has a reward function that is used to adjust weights based on comparing (see block 4722) the two renderings 4710, 4712 and the target object metadata 4701. In some examples, the reinforced learning (at block 4720) is performed iteratively, such as until the Euclidean distances meet a desired threshold.
The target object metadata 4701 also used to perform a multi-dimensional object parametric-based fabrication vector analysis 4730 using a neural network(s). Particularly, the multi-dimensional object parametric-based fabrication vector analysis 4730 generates a vector (i.e., a fabrication vector, such as the fabrication vector 4620) that is unified into a common index with the final geometry data (from block 4724) and the target object metadata 4701 into the multi-dimensional build platform unified geometry and feature/functional training/predefined dataset 4528. From this, an array of elements that include geometry, feature and functional characteristics, fabrication parameters, and other information is used as an index for the multi-dimensional build platform model database 4215.
According to one or more embodiments described herein, the predictive pipeline 4702 and the generative pipeline 4704 can be utilized together along with the similarity and scoring analysis 4722 and the objective function 4720 to implement a third (virtual) pipeline. The third (virtual) pipeline acts in a manner similar to a generative adversarial network (GAN) by using the generative pipeline 4704 to generate candidate solutions and then using the predictive pipeline 4702 (along with the similarity and scoring analysis 4722 and the objective function 4720) to evaluate a given solution instance in order to compute NN updates in 4706 and 4708 that improve the predictive pipeline so that is may in turn generate a new more optimal solution instance. The third (virtual) pipeline creates a corpus of build volume section solutions that are stored in the multi-dimensional build platform model database 4215 in a manner consistent with each individual pipeline 4702 and 4704.
From the foregoing, as shown in
It should be appreciated that while embodiments herein may refer to a specific target object being fabricated; this is for exemplary purposes and the claims should not be so limited. The system and build platforms described herein may be used fabricate any suitable target object, such as but not limited to: fixtures, components, sub-assemblies and finished products for the transportation, automotive, aerospace, marine, construction, energy, telecommunications, medical, biological, biomaterial, chemical, and internet of things (IoT) applications.
The term “about” is intended to include the degree of error associated with measurement of the particular quantity based upon the equipment available at the time of filing the application. For example, “about” can include a range of ±8% or 5%, or 2% of a given value.
Additionally, the term “exemplary” is used herein to mean “serving as an example, instance or illustration.” Any embodiment or design described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments or designs. The terms “at least one” and “one or more” are understood to include any integer number greater than or equal to one, i.e. one, two, three, four, etc. The terms “a plurality” are understood to include any integer number greater than or equal to two, i.e. two, three, four, five, etc. The term “connection” can include an indirect “connection” and a direct “connection.” It should also be noted that the terms “first”, “second”, “third”, “upper”, “lower”, and the like may be used herein to modify various elements. These modifiers do not imply a spatial, sequential, or hierarchical order to the modified elements unless specifically stated.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, element components, and/or groups thereof.
While the disclosure is provided in detail in connection with only a limited number of embodiments, it should be readily understood that the disclosure is not limited to such disclosed embodiments. Rather, the disclosure can be modified to incorporate any number of variations, alterations, substitutions or equivalent arrangements not heretofore described, but which are commensurate with the spirit and scope of the disclosure. Additionally, while various embodiments of the disclosure have been described, it is to be understood that the exemplary embodiment(s) may include only some of the described exemplary aspects. Accordingly, the disclosure is not to be seen as limited by the foregoing description, but is only limited by the scope of the appended claims.
Claims
1. A build platform, comprising:
- a build volume section comprising at least one feature or functional element; and
- a controller to individually control the at least one functional element.
2. The build platform of claim 1, wherein the build platform is a multi-dimensional build platform.
3. The build platform of claim 1, wherein the controller is communicatively coupled to an additive manufacturing system via a communications interface.
4. The build platform of claim 3, wherein the additive manufacturing system comprises a multi-dimensional build platform interface controller.
5. The build platform of claim 4, wherein the multi-dimensional build platform interface controller comprises:
- a microcontroller;
- a memory;
- a build platform additive system interface;
- a power management circuit;
- a wireless charging coil;
- an external power input;
- a battery; and
- a communication module.
6. The build platform of claim 1, wherein the controller is communicatively coupled to a power system via a power interface.
7. The build platform of claim 1, wherein the build platform further comprises:
- an interface section configured to couple with the additive manufacturing system; and
- a base section coupled to the interface section.
8. The build platform of claim 7, wherein the controller is disposed in the base section.
9. The build platform of claim 1, wherein the controller comprises:
- a microcontroller;
- a memory;
- a build volume driver module;
- a power management circuit;
- a wireless charging coil;
- an external power input;
- a battery; and
- a communication module.
10. The build platform of claim 1, wherein at least one of the at least one functional element comprises a heater coil.
11. The build platform of claim 10, wherein to individually control the heater coil comprises activating the heater coil, deactivating the heater coil, or changing a temperature responsive to a signal received from a multi-dimensional build platform interface controller.
12. The build platform of claim 1, wherein at least one of the at least one functional element comprises a magnetic coil.
13. The build platform of claim 12, wherein to individually control the magnetic coil comprises activating the magnetic coil, deactivating the magnetic coil, or changing a field responsive to a signal received from a multi-dimensional build platform interface controller.
14. The build platform of claim 1, wherein at least one of the at least one functional element comprises an optical device.
15. The build platform of claim 14, wherein to individually control the optical device comprises activating the optical device, deactivating the optical device, or changing an optical energy of the optical device responsive to a signal received from a multi-dimensional build platform interface controller.
16. The build platform of claim 1, wherein at least one of the at least one functional element is disposed in a layer of a plurality of layers of the build volume section other than a surface layer of the build volume section.
17. The build platform of claim 1, wherein the build platform is a planar build platform.
Type: Application
Filed: Jan 12, 2022
Publication Date: Jul 14, 2022
Inventor: Richard NEILL (Garrison, NY)
Application Number: 17/574,331