Abstract: This disclosure teaches techniques, devices, and systems for automatically generating design parameters of a structural model (or any component that is defined by one or more parameters) to be produced by additive manufacturing, using machine-learning models to avoid production failures. In aspects, a topology optimization framework (e.g., with optimization iterations, or loops) is used to efficiently explore the expanded design space of additive manufacturing components is disclosed.

Abstract: A representation of an initial design domain, at least one subtractive tool assembly, machine degrees of freedom, and a termination criterion are used to iteratively generate intermediate part designs by redistributing the material within the design domain. A measure of inaccessibility of exteriors of the intermediate part designs by the at least one subtractive manufacturing tool assembly are generated. The measure of inaccessibility is used to inform generation of an intermediate part design at a next iteration. The iterative algorithm is terminated when the termination criterion is satisfied, the result of the iterative algorithm being a part design accessible for subtractive manufacturing.

Abstract: A method includes receiving a representation of a near-net shape including a 3D part and a support volume. The method also includes calculating a measure of inaccessibility of the support volume by at least one subtractive tool assembly. The method also includes calculating a measure of change in a physical quantity of interest with respect to a change in the near-net shape. The method also includes constructing a physics-aware inaccessibility measure based at least partially upon the measure of inaccessibility, the measure of change, or both. The method also includes creating a plan to remove at least a portion of the support volume using the at least one subtractive tool assembly based at least partially upon the physics-aware inaccessibility measure.

Abstract: Two or more computational services are defined that each represent a respective different manufacturing capability used to partially create a target part model. A common space shared among the computational services is defined to reference the target part model and manufacturing primitives corresponding to each capability. The computational services are queried to construct a logical representation of the planning space based on intersections among the primitives. One or more process plans are formed using the different manufacturing capabilities to manufacture the part.

Abstract: A method includes receiving a representation of a near-net shape including a 3D part and a support volume. The method also includes calculating a measure of inaccessibility of the support volume by at least one subtractive tool assembly. The method also includes calculating a measure of change in a physical quantity of interest with respect to a change in the near-net shape. The method also includes constructing a physics-aware inaccessibility measure based at least partially upon the measure of inaccessibility, the measure of change, or both. The method also includes creating a plan to remove at least a portion of the support volume using the at least one subtractive tool assembly based at least partially upon the physics-aware inaccessibility measure.

Abstract: A method includes receiving a representation of an initial design domain. The method also includes iteratively generating intermediate part designs by redistributing material within the initial design domain. The intermediate part designs each include a 3D part and a support volume. The method also includes calculating a measure of inaccessibility of the support volume of each intermediate part design by at least one subtractive tool assembly. At least one of the intermediate part designs is generated based at least partially upon the measure of inaccessibility of a previous one of the intermediate part designs.

Abstract: A systematic approach to constructing process plans for hybrid manufacturing is provided. The process plans include arbitrary combinations of AM and SM processes. Unlike the suboptimal conventional practice, the sequence of AM and SM modalities is not fixed beforehand. Rather, all potentially viable process plans to fabricate a desired target part from arbitrary alternating sequences of pre-defined AM and SM modalities are explored in a systematic fashion. Once the state space of all process plans has been enumerated in terms of a partially ordered set of states, advanced artificial intelligence (AI) planning techniques are utilized to rapidly explore the state space, eliminate invalid process plans, for instance, process plans that make no physical sense, and optimize among the valid process plans using a cost function, for instance, manufacturing time and material or process costs.

Abstract: A target system is coupled to a diagnosis engine that uses a lumped parameter model of the system for diagnosis. A proximity search in is performed in a computer-aided design model of the system to find groups of components that may be affected by resistive or parasitic interactions between the individual components in the groups. The lumped parameter model is augmented by adding elements that emulate the resistive or parasitic interactions between the individual components in the groups. The augmented lumped model is used by the diagnosis engine to perform diagnosis on the system.

Abstract: A three-dimensional object model is divided into slices that are targeted for an additive manufacturing process operable to deposit material at a variable deposition size ranging between minimum and maximum printable feature sizes. For each of the slices, a thinning algorithm is applied to contours of the slice to form a meso-skeleton. Topological features of the thinned slice are reduced over a number of passes such that a portion of the meso-skeleton is reduced to a single pixel wide line. Based on the number of passes, a slice-specific printable feature size within the range of the minimum and maximum printable feature sizes is determined. An adjusted slice is formed by sweeping the meso-skeleton with the slice-specific printable feature size. The adjusted slices are assembled into an object model which is used to create a manufactured object.

Abstract: A geometry model is defined of a part targeted for a manufacturing operation that includes an additive process followed by a subtractive process. Potential build orientations of the geometry model used in the additive processes are defined, as are one or more removal tools of the subtractive process. For each of the potential build orientations, supports that are used by the additive process at the orientation are determined. One of the build orientations is selected that minimizes portions of one of the supports that are inaccessible via at least one of the removal tools.

Abstract: Two or more computational services are defined that each represent a respective different manufacturing capability used to partially create a target part model. A common space shared among the computational services is defined to reference the target part model and manufacturing primitives corresponding to each capability. The computational services are queried to construct a logical representation of the planning space based on intersections among the primitives. One or more process plans are formed using the different manufacturing capabilities to manufacture the part.

Abstract: A computer representation of a printable product part and a plan for the printable product part to be deposited using an additive manufacturing process are received. The printable product part comprises an accumulation of material deposited by the additive manufacturing process. The plan comprises a tool-path representation of the printable product part and process parameters. A plurality of as-printed shapes of the printable product part are determined after it has been deposited according to the plan. Geometric differences between any of the plurality of as-printed shapes with the computer representation of the product part are determined.

Abstract: Parameters of a set of tools are stored on a storage device. The tools are part of a manufacturing assembly usable for removing one or more support structures from a part. The support structures are formed with the part to facilitate additive manufacturing of the part. A near-net shape is modeled which includes the part combined with the support structures. A process plan is developed that includes subtractive manufacturing operations by the manufacturing assembly that remove the support structures. The process plan repeatedly updates the near-net shape as each one of the support structures is incrementally removed.

Abstract: A plurality of scanned prints of a product part and a scan-path are received. A shape of a minimum printable feature of the product part is determined by analyzing the respective prints in a scan-path representation. A manufacturing error of the minimum printable feature is determined based on the analysis. A manufacturing error of a shape of the part is determined based on the determined manufacturing error of the minimum printable feature. An estimated manufactured shape of the part is produced based on the determined manufacturing error of the part.

Abstract: The present disclosure is directed to a method and system for hierarchical multi-scale design with the aid of a digital computer. A hierarchical representation of a shape and material distribution is constructed which satisfies a top-level constraint at a top-level of representation. Properties for families of designs at each of the lower levels of representation that satisfy additional constraints link each of the lower levels of representation to at least a next higher level of the representation.

Abstract: A method for designing microstructures includes receiving at least one material property constraint for a design of at least one microstructure, the at least one microstructure configured to be a part of a larger macrostructure. At least one neighborhood connectivity constraint for the design of the at least one microstructure is received. One or more designs of the at least one microstructure is generated using a generative adversarial network (GAN) that is based on the at least one material property constraint and the at least one neighborhood connectivity constraint.

Abstract: A method for producing a design includes receiving a set of design constraints. A spatial field is created based on the design constraints. The spatial field is represented with a linear combination of one or more bases. A number of the one or more bases is less than a number of elements in the spatial field. Respective weights are optimized for each of the one or more bases. A design is produced based on the spatial field and the weights.

Abstract: A nozzle for a printing system is disclosed. The nozzle includes a tank in communication with a source of printing material. The nozzle also includes a constricted dissipative section in communication with the tank, which may include an elongated internal channel. The nozzle may also include a shaping tip in communication with the constricted dissipative section may include an exit orifice. The constricted dissipative section may be axisymmetric and may include at least three internal channels not in communication with one another. Also disclosed is an array of nozzles for a printing system including a plurality of nozzles, with each nozzle including a tank in communication with a source of printing material, a constricted dissipative section in communication with the tank and configured to obstruct fluid flow and having an elongated internal channel, and a shaping tip in communication with the constricted dissipative section may include an exit orifice.

Abstract: Set differences between an as-designed and an as-manufactured model are computed. Topological deviations between the as-designed model and the as-manufactured model are determined based under-deposition and over-deposition features of the set differences. Based on the discrepancies, an input to a manufacturing instrument is changed to reduce topological differences between the as-manufactured model and the as-designed model.

Abstract: A drop-on-demand (DOD) printer is disclosed having an ejector which may include a nozzle, the nozzle including a tank in communication with a source of printing material, a constricted dissipative section in communication with the tank, which may include an elongated internal channel, and a shaping tip in communication with the constricted dissipative section which can include an exit orifice. The (DOD) printer also includes a power source configured to supply one or more pulses of power to the ejector, which causes one or more drops of the printing material to be jetted out of the nozzle. The DOD printer may include a constricted dissipative section configured to obstruct fluid flow that is cylindrical or axisymmetric and having a diameter less than a diameter of the tank and less than a diameter of the shaping tip. The DOD printer may include a nozzle or an array of nozzles.