A method of obtaining three-dimensional data includes: obtaining three-dimensional reference data with respect to an object; aligning, on the three-dimensional reference data, a first frame obtained by scanning a first region of the object; aligning, on the three-dimensional reference data, a second frame obtained by scanning a second region of the object, at least a portion of the second region overlapping the first region; and obtaining the three-dimensional data by merging the first frame with the second frame based on an overlapping portion between the first region and the second region.

A facility for automated modelling of the cutting process for a particular material to be cut by a beam cutting tool, such as a waterjet cutting system, from empirical data to predict aspects of the waterjet's effect on the workpiece across a range of material thicknesses, across a range of cutting geometries, and across a range of cutting quality levels, all of which may be broader than, and independent of the actual requirements for a target workpiece, is described.

A facility for automated modelling of the cutting process for a particular material to be cut by a beam cutting tool, such as a waterjet cutting system, from empirical data to predict aspects of the waterjet's effect on the workpiece across a range of material thicknesses, across a range of cutting geometries, and across a range of cutting quality levels, all of which may be broader than, and independent of the actual requirements for a target workpiece, is described.

The subject technology is related to methods and apparatus for training a set of regression machine learning models with a training set to produce a set of predictive values for a pending manufacturing request, the training set including data extracted from a set of manufacturing transactions submitted by a set of entities of a supply chain. A multi-objective optimization model is implemented to (1) receive an input including the set of predictive values and a set of features of a physical object, and (2) generate an output with a set of attributes associated with a manufacture of the physical object in response to receiving the input, the output complying with a multi-objective condition satisfied in the multi-objective optimization model.

The subject technology is related to methods and apparatus for training a set of regression machine learning models with a training set to produce a set of predictive values for a pending manufacturing request, the training set including data extracted from a set of manufacturing transactions submitted by a set of entities of a supply chain. A multi-objective optimization model is implemented to (1) receive an input including the set of predictive values and a set of features of a physical object, and (2) generate an output with a set of attributes associated with a manufacture of the physical object in response to receiving the input, the output complying with a multi-objective condition satisfied in the multi-objective optimization model.

A method of guiding a semiconductor manufacturing process includes receiving semiconductor manufacturing process data corresponding to a target semiconductor product, generating first semiconductor characteristic data corresponding to the semiconductor manufacturing process data by using a technology computer-aided design (TCAD) model trained through machine learning based on training data including TCAD simulation data, generating second semiconductor characteristic data corresponding to the semiconductor manufacturing process data by using a compact model generated based on information of measurement of at least one semiconductor characteristic of a first semiconductor product, generating, based on the first semiconductor characteristic data and the second semiconductor characteristic data, a plurality of process policies respectively corresponding to a plurality of strategic references, by using a plurality of strategy models; and providing a final process policy corresponding to the target semiconductor product based on the plurality of process policies.

A method of guiding a semiconductor manufacturing process includes receiving semiconductor manufacturing process data corresponding to a target semiconductor product, generating first semiconductor characteristic data corresponding to the semiconductor manufacturing process data by using a technology computer-aided design (TCAD) model trained through machine learning based on training data including TCAD simulation data, generating second semiconductor characteristic data corresponding to the semiconductor manufacturing process data by using a compact model generated based on information of measurement of at least one semiconductor characteristic of a first semiconductor product, generating, based on the first semiconductor characteristic data and the second semiconductor characteristic data, a plurality of process policies respectively corresponding to a plurality of strategic references, by using a plurality of strategy models; and providing a final process policy corresponding to the target semiconductor product based on the plurality of process policies.

Systems, devices, and methods including selecting one or more sequences of machining types for a feature of one or more features, where the selection of the one or more sequences of machining types is based on the feature and a database of prior selections of machining types; selecting one or more tools for the selected one or more sequences of machining types, where the selection of the one or more tools is based on the feature, the selected one or more sequences of machining types, and a database of prior selections of one or more tools; and selecting one or more machining parameters for the selected one or more tools, where the selected machining parameters are based on the feature, the selected one or more sequences of machining types, the selected one or more tools, and a database of prior selections of one or more machining parameters.

Systems and methods for producing printed goods from textile material to address shortcoming of existing approaches for article production. According to the systems and methods described herein, the harvested and woven cotton may be shipped directly to garment decorators who may perform all remaining steps to provide customers with finished goods. As such, the systems and methods herein may eliminate the steps of the blank goods trade and current manufacturing processes.

An interpolation parameter calculation unit calculates an interpolation parameter of a predetermined interpolation calculation formula based on a first plurality of coordinate values input by means of a coordinate input unit and constituting a coordinate pattern for determining a locus pattern of one cycle when a laser beam is vibrated. A locus pattern calculation unit calculates a second plurality of coordinate values constituting the locus pattern based on an interpolation parameter, respective amplitudes of the locus pattern in an x-axis direction that is a moving direction of a processing head and a y-axis direction that is a direction orthogonal to the x-axis direction, a frequency of the locus pattern, and a control cycle of a beam vibration mechanism for vibrating the laser beam.