A computer-implemented method is provided for determining a cut pattern of a lathe. The lathe is numerically controlled by a control device and includes a tool with a cutter acting on a workpiece. The workpiece has a start contour and a target contour to be achieved by cutting the workpiece according to the cut pattern. The method includes determining a path of a n-th layer of the cut pattern, wherein the n-th layer includes: for n≥2: an infeed path linear and/or parallel to the target contour; a circular infeed path starting tangent to the target contour; an intermediate path linear and/or parallel to the target contour; a circular outfeed path ending tangent to the target contour; and for n≥2: a smoothing path linear and/or parallel to the target contour.

In a CAD data-based automatic operation device of a machining center equipped with a CNC device, the CNC device is provided in a storage unit with a learned model generated by learning beforehand machining conditions including a tool used and cutting conditions, a manufacturing process including a tool trajectory, and a machining program that caused the manufacturing process to be performed in correspondence with one another with respect to each feature subjected to various cutting operations. An automatic machining command generation unit provided in a control unit is provided with: a feature extraction function of extracting features from three-dimensional CAD design data of a machined product; an automatic manufacturing process setting function of automatically determining required machining conditions and automatically setting a manufacturing process including a tool trajectory, by applying each feature to the learned model; an all manufacturing process setting function of determining a procedure for manufacturing processes for all the features; and a machining command generation function of generating a machining command for causing a machine tool to perform all the manufacturing processes based on the learned model. The automatic manufacturing process setting function is further provided with a function of displaying a 3D model of the machined product generated based on the three-dimensional CAD design data in one or more possible different directions of mounting to a machining unit in a selectable and executable manner and the manufacturing processes are automatically set based on the determined mounting direction.

A toolpath topology design method based on vector field in sub-regional processing for the curved surface is disclosed which comprising: finding the functional relationships in feeding direction between the chord error and the normal curvature and between the scallop-height error and the normal curvature; establishing the bi-objective optimization model and calculating the optimal feeding direction at each cutting contact point within the surface through the constructed evaluation function, the space vector field is built; calculating divergence and rotation of the projected vector field and according to whether them are zeros or not to classify different sub-regions, the primary surface segmentation is achieved, etc. The method is applied for the complex curved surface processing, which can reduce the machining error and enhance the feed motion stability.

An automated method for generating toolpaths in double sided incremental forming (DSIF) operations is disclosed which uses a geometrically constructed map to build a structure of all the geometric features that is capable of tracking and forming the features in the correct order while simultaneously keeping track of the location of the virgin material. The aforementioned method allows toolpaths for complex. geometries in the DSIF process to be generated automatically.

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 least the portion of the manufacturable object.

A method for CNC manufacturing is provided. The method includes computer-reading a digital model of a 3D part within a first topological space. An offset surface for the digital model in the first topological space is computer-generated. The offset surface in the first topological space is computer-transformed to a transformed offset surface in a second topological space embedded in the first topological space. A plurality of contours are computer-identified, at which a corresponding plurality of embedded parallel planes intersect the transformed offset surface in the second topological space. The plurality of contours in the second topological space are computer-transformed into a corresponding plurality of transformed contours in the first topological space. A CNC toolpath is computer-generated that traces each of the plurality of transformed contours in the first topological space, the CNC toolpath useable by a CNC machine to manufacture the 3D part.

Systems, methods, and machine readable media are provided for slot capacity adjustment. A utilization rate of a facility for a plurality of time slots is determined. Slots having a utilization rate that can have an associated capacity increased are identified and the capacity for the slots having a utilization rate that can be increased is increased. Slots having a utilization rate that can have an associated capacity decreased are identified and these slots have their capacity decreased. A slot-to-slot capacity variance of greater than a smoothing threshold are identified and smoothed. A capacity schedule is produced based on the capacity increases, capacity decreases, and capacity smoothing.

This tool selection method is provided with: a step for respectively calculating, with respect to a plurality of known workpieces, feature amounts based on the shapes of a plurality of machining surfaces wherein, to each of the plurality of known workpieces, one main tool which is preselected from a tool list that includes a plurality of tools is allocated as being suitable for machining the plurality of machining surfaces; a step for executing, with respect to the plurality of known workpieces, machine learning by taking the feature amounts as inputs and the main tools as outputs; a step for calculating a feature amount for a target workpiece; and a step for selecting, with respect to the target workpiece, a main tool from the tool list on the basis of a machine learning result obtained by using the feature amount of the target workpiece as an input.

A method automatically determines machining parameters for a machining process, in which a machining head is guided along a machining path over at least one workpiece to be machined, and, depending on the respective position along the machining path, certain machining parameters are selected from stored machining parameters on the basis of predefined conditions for machining the at least one workpiece, and a device machines a workpiece. The limit values for the machining parameters are determined during the machining process to be performed, and new machining parameters for the machining process to be performed are specified by taking these limit values into consideration.

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 least the portion of the manufacturable object.