Abstract: A method of optimizing a process having a plurality of potential inputs, comprising selecting a first set of inputs from the plurality of potential inputs, providing the first set of inputs from the to a first optimization process, running an objective function on the first set of inputs to produce a value corresponding to the set of inputs, providing the value to a second optimization process, running an acquisition function in the second optimization process to select a new candidate set of inputs from the plurality of potential inputs, and providing the selected new candidate set of inputs to the first optimization process. In one embodiment, the inputs are a set of lattice kernels for constructing a structural object. A Bayesian optimization is used to select sub-sets of kernels from the set of inputs. The inputs are provided to a topology optimization for evaluation.

Abstract: A computing system may include an access engine and a defect detection engine. The access engine may be configured to access a slice contour of a given layer of a 3-dimensional (3D) object designed for manufacture through an additive manufacturing process and obtain hatch tracking for the slice contour, the hatch tracking representative of an energy path to melt metal powder for constructing the given layer through the additive manufacturing process. The defect detection engine may be configured to construct, from the slice contour, an as-built image for the given layer by rendering the hatch tracking in the slice contour; construct, from the slice contour, an idealized image for the given layer; and identify defects in the given layer via image analysis between the as-built image and the idealized image.

Abstract: A computing system may include a transition generation engine configured to access a computer-aided design (CAD) object comprising an external surface and an internal lattice structure represented through repeating unit cells of a lattice design, the internal lattice structure represented as a signed distance field (SDF). The transition generation engine may generate a transition structure for the CAD object within a transition distance from the external surface, including by applying a secondary SDF to modify a portion of the internal lattice structure within the transition distance from the external surface. The computing system may also include an object processing engine may be configured to process the CAD object comprising the transition structure (230) in support of physical manufacture of the CAD object.

Abstract: A computing system may include a transition generation engine configured to access a computer-aided design (CAD) object comprising an external surface and an internal lattice structure represented through repeating unit cells of a lattice design, the internal lattice structure represented as a signed distance field (SDF). The transition generation engine may generate a transition structure for the CAD object within a transition distance from the external surface, including by applying a secondary SDF to modify a portion of the internal lattice structure within the transition distance from the external surface. The computing system may also include an object processing engine may be configured to process the CAD object comprising the transition structure (230) in support of physical manufacture of the CAD object.

Abstract: A computing system may include an access engine and a defect detection engine. The access engine may be configured to access a slice contour of a given layer of a 3-dimensional (3D) object designed for manufacture through an additive manufacturing process and obtain hatch tracking for the slice contour, the hatch tracking representative of an energy path to melt metal powder for constructing the given layer through the additive manufacturing process. The defect detection engine may be configured to construct, from the slice contour, an as-built image for the given layer by rendering the hatch tracking in the slice contour; construct, from the slice contour, an idealized image for the given layer; and identify defects in the given layer via image analysis between the as-built image and the idealized image.