Abstract: A three-dimensional discretized computer model of a part in a three-dimensional discretized design space comprising three-dimensional geometrical elements is obtained. A signed distance field based on a geometry of the three-dimensional discretized computer model of the part as represented in the three-dimensional geometrical elements of the three-dimensional discretized design space is produced. At least one non-branching cooling channel in a portion of the three-dimensional discretized design space is generated.

Abstract: A three-dimensional computer model of a cooling mold for a part and a specification of an initial layout of one or more cooling channels integrated into the cooling mold is obtained. Data regarding temperatures of a cavity surface of the cooling mold in contact with the part is produced. Individual portions of the one or more cooling channels are moved toward hotter portions of the cavity surface, without moving any branch junctions of the one or more cooling channels and while keeping one or more diameters of the one or more cooling channels constant.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design and manufacture of physical structures using toolpaths generated by reinforcement learning for use with subtractive manufacturing systems and techniques, include: obtaining, in a computer aided design or manufacturing program, a three dimensional model of a manufacturable object; generating toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model; and providing the toolpaths to the computer-controlled manufacturing system to manufacture at le

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design and manufacture of physical structures using toolpaths generated by reinforcement learning for use with subtractive manufacturing systems and techniques, include: obtaining, in a computer aided design or manufacturing program, a three dimensional model of a manufacturable object; generating toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model; and providing the toolpaths to the computer-controlled manufacturing system to manufacture at le

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design and manufacture of physical structures using subtractive manufacturing systems and techniques include, in one aspect, a method including obtaining information regarding a geometry of a part to be machined by a computer-controlled manufacturing system from a workpiece; based on the information regarding the geometry, identifying machine components to be used by the computer-controlled manufacturing system during machining the part; determining a position for the machining of the part with respect to at least one of the machine components, to even out wear on the machine components, based on data indicating previous positions, movements and wear of components associated with the computer-controlled manufacturing system; and providing instructions usable by the computer-controlled manufacturing system, wherein the instructions are configured to cause the computer-controlled manufacturing system to use t

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predictive machining for forging distortions. In one aspect, a method includes obtaining a mesh model of a machined part to be machined from a forged part and residual stress field data for the forged part, where the mesh model includes multiple nodes corresponding to at least one boundary of the machined part, updating the mesh model by applying the residual stress field data to the multiple nodes corresponding to the at least one boundary to change positions of the multiple nodes in the mesh model, repeating the updating until an amount of change to each of the positions of the multiple nodes in the mesh model satisfies a correction criteria, and providing the compensated mesh model for use in machining the machined part from the forged part.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design and manufacture of physical structures using toolpaths generated by reinforcement learning for use with subtractive manufacturing systems and techniques, include: obtaining, in a computer aided design or manufacturing program, a three dimensional model of a manufacturable object; generating toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model; and providing the toolpaths to the computer-controlled manufacturing system to manufacture at le

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predictive machining for forging distortions. In one aspect, a method includes obtaining a mesh model of a machined part to be machined from a forged part and residual stress field data for the forged part, where the mesh model includes multiple nodes corresponding to at least one boundary of the machined part, updating the mesh model by applying the residual stress field data to the multiple nodes corresponding to the at least one boundary to change positions of the multiple nodes in the mesh model, repeating the updating until an amount of change to each of the positions of the multiple nodes in the mesh model satisfies a correction criteria, and providing the compensated mesh model for use in machining the machined part from the forged part.