Abstract: An approach to intelligent additive manufacturing makes use of one or more of machine learning, feedback using machine vision, and determination of machine state. In some examples, a machine learning transformation receives data representing a partially fabricated object and a model of an additional part (e.g., layer) of the part, and produces a modified model that is provided to a printer. The machine learning predistorter can compensate for imperfections in the partially fabricated object as well as non-ideal characteristics of the printer, thereby achieving high accuracy.

Abstract: An approach to precision additive fabrication uses jetting of cationic compositions in conjunction with a non-contact (e.g., optical) feedback approach. By not requiring contact to control the surface geometry of the object being manufactured, the approach is tolerant of the relative slow curing of the cationic composition, while maintaining the benefit of control of the deposition processes according to feedback during the fabrication processes. This approach provides a way to manufacture precision objects and benefit from material properties of the fabricated objects, for example, with isotropic properties, which may be at least partially a result of the slow curing, and flexible structures, which may not be attainable using conventional jetted acrylates.

Abstract: A method for additive fabrication of an object on a build platform includes depositing material onto a partial fabrication of the object in a number of passes of a printhead over the partial fabrication. The depositing includes repeatedly depositing material onto the partial fabrication in a pass of the printhead over the partial fabrication. The depositing includes depositing a first material onto the partial fabrication at a first height relative to the build platform, and depositing a second material onto the partial fabrication at a second height relative to the build platform, the second height being less than the first height, the depositing of the second material including forming at least one material transition region between the second material at the second height and first material at the second height deposited in a previous pass.

Abstract: An additive fabrication approach involves fabricating a platform on a build plate. The fabrication system is then calibrated based on the fabricated platform, and an object is then fabricating on the fabricated platform according to the calibration.

Abstract: A method for additive manufacturing includes forming an object including depositing a first material including a first coloring component and a second material including a second coloring component, wherein both the first material and the second material further include a corresponding fluorescent component, scanning the object, including causing an emission of an optical signal from the object, wherein the emission of the optical signal is caused at least in part by an emission from the fluorescent components interacting with the first coloring component and the second coloring component as it passes from the fluorescent components to the surface of the object, sensing the emission of the optical signal, and determining presence of the first material and the second material based at least in part on the sensed emission of the optical signal.

Abstract: An approach to intelligent additive manufacturing makes use of one or more of machine learning, feedback using machine vision, and determination of machine state. In some examples, a machine learning transformation receives data representing a partially fabricated object and a model of an additional part (e.g., layer) of the part, and produces a modified model that is provided to a printer. The machine learning predistorter can compensate for imperfections in the partially fabricated object as well as non-ideal characteristics of the printer, thereby achieving high accuracy.

Abstract: A profilometer provides, to a controller, a feedback signal indicative of topography of an exposed surface of an object that is being manufactured by a 3d printer. The profilometer includes an emitter and a camera. The emitter illuminates a region of surface of the object with a pattern having an edge that defines a boundary of an illuminated portion of the surface. The camera receives an image that transitions between a first state in which the edge is visible in the image at a location that is indicative of the surface's depth and a second state in which the edge is not visible at all. From this second state, the controller obtains information representative of a depth of the surface.

Abstract: An approach to intelligent additive manufacturing makes use of one or more of machine learning, feedback using machine vision, and determination of machine state. In some examples, a machine learning transformation receives data representing a partially fabricated object and a model of an additional part (e.g., layer) of the part, and produces a modified model that is provided to a printer. The machine learning predistorter can compensate for imperfections in the partially fabricated object as well as non-ideal characteristics of the printer, thereby achieving high accuracy.

Abstract: A method for additive fabrication by 3D printing includes processing model data representing material transition boundaries of an object to be printed to form build data for use in controlling printing of a plurality of successive layers to form the object, the build data comprising, for each location of a plurality of locations in a two-dimensional arrangement, material transition data for representing heights of material transitions in a third dimension, and repeating for each layer of the plurality of successive layers, receiving surface height data representing a height of a partial fabrication of the object at respective locations of a plurality of locations on a surface of the partial fabrication for each location of the plurality of locations, using the height at the location to access the material transition data corresponding to the location in the build data, and using the material transition data to determine material to be deposited at that location, and causing emission of the determined material

Abstract: An approach to intelligent additive manufacturing makes use of one or more of machine learning, feedback using machine vision, and determination of machine state. In some examples, a machine learning transformation receives data representing a partially fabricated object and a model of an additional part (e.g., layer) of the part, and produces a modified model that is provided to a printer. The machine learning predistorter can compensate for imperfections in the partially fabricated object as well as non-ideal characteristics of the printer, thereby achieving high accuracy.

Abstract: An approach to precision additive fabrication uses jetting of cationic compositions in conjunction with a non-contact (e.g., optical) feedback approach. By not requiring contact to control the surface geometry of the object being manufactured, the approach is tolerant of the relative slow curing of the cationic composition, while maintaining the benefit of control of the deposition processes according to feedback during the fabrication processes. This approach provides a way to manufacture precision objects and benefit from material properties of the fabricated objects, for example, with isotropic properties, which may be at least partially a result of the slow curing, and flexible structures, which may not be attainable using conventional jetted acrylates.

Abstract: An approach to intelligent additive manufacturing makes use of one or more of machine learning, feedback using machine vision, and determination of machine state. In some examples, a machine learning transformation receives data representing a partially fabricated object and a model of an additional part (e.g., layer) of the part, and produces a modified model that is provided to a printer. The machine learning predistorter can compensate for imperfections in the partially fabricated object as well as non-ideal characteristics of the printer, thereby achieving high accuracy.

Abstract: An approach to intelligent additive manufacturing makes use of one or more of machine learning, feedback using machine vision, and determination of machine state. In some examples, a machine learning transformation receives data representing a partially fabricated object and a model of an additional part (e.g., layer) of the part, and produces a modified model that is provided to a printer. The machine learning predistorter can compensate for imperfections in the partially fabricated object as well as non-ideal characteristics of the printer, thereby achieving high accuracy.

Abstract: An approach to intelligent additive manufacturing makes use of one or more of machine learning, feedback using machine vision, and determination of machine state. In some examples, a machine learning transformation receives data representing a partially fabricated object and a model of an additional part (e.g., layer) of the part, and produces a modified model that is provided to a printer. The machine learning predistorter can compensate for imperfections in the partially fabricated object as well as non-ideal characteristics of the printer, thereby achieving high accuracy.

Abstract: A profilometer provides, to a controller, a feedback signal indicative of topography of an exposed surface of an object that is being manufactured by a 3d printer. The profilometer includes an emitter and a camera. The emitter illuminates a region of surface of the object with a pattern having an edge that defines a boundary of an illuminated portion of the surface. The camera receives an image that transitions between a first state in which the edge is visible in the image at a location that is indicative of the surface's depth and a second state in which the edge is not visible at all. From this second state, the controller obtains information representative of a depth of the surface.

Abstract: An additive fabrication approach involves fabricating a platform on a build plate. The fabrication system is then calibrated based on the fabricated platform, and an object is then fabricating on the fabricated platform according to the calibration.

Abstract: A method includes generating correction data for a construction material that is used by an additive-manufacturing machine to manufacture an object. This correction data compensates for an interaction of the construction material with first radiation that has been used to illuminate the construction material.

Abstract: An approach to improving optical scanning increases the strength of optical reflection from the build material during fabrication. In some examples, the approach makes use of an additive (or a combination of multiple additives) that increases the received signal strength and/or improves the received signal-to-noise ratio in optical scanning for industrial metrology. Elements not naturally present in the material are introduced in the additives in order to increase fluorescence, scattering or luminescence. Such additives may include one or more of: small molecules, polymers, peptides, proteins, metal or semiconductive nanoparticles, and silicate nanoparticles.

Abstract: An approach to precision additive fabrication uses jetting of cationic compositions in conjunction with a non-contact (e.g., optical) feedback approach. By not requiring contact to control the surface geometry of the object being manufactured, the approach is tolerant of the relative slow curing of the cationic composition, while maintaining the benefit of control of the deposition processes according to feedback during the fabrication processes. This approach provides a way to manufacture precision objects and benefit from material properties of the fabricated objects, for example, with isotropic properties, which may be at least partially a result of the slow curing, and flexible structures, which may not be attainable using conventional jetted acrylates.

Abstract: A method for additive manufacturing includes forming an object including depositing a first material including a first coloring component and a second material including a second coloring component, wherein both the first material and the second material further include a corresponding fluorescent component, scanning the object, including causing an emission of an optical signal from the object, wherein the emission of the optical signal is caused at least in part by an emission from the fluorescent components interacting with the first coloring component and the second coloring component as it passes from the fluorescent components to the surface of the object, sensing the emission of the optical signal, and determining presence of the first material and the second material based at least in part on the sensed emission of the optical signal.