One embodiment of the present invention sets forth a technique for controlling the execution of a physical process. The technique includes receiving, as input to a machine learning model that is configured to adapt a simulation of the physical process executing in a virtual environment to a physical world, simulated output for controlling how the physical process performs a task in the virtual environment and real-world data collected from the physical process performing the task in the physical world. The technique also includes performing, by the machine learning model, one or more operations on the simulated output and the real-world data to generate augmented output. The technique further includes transmitting the augmented output to the physical process to control how the physical process performs the task in the physical world.

One embodiment of the present invention sets forth a technique for generating simulated training data for a physical process. The technique includes receiving, as input to at least one machine learning model, a first simulated image of a first object, wherein the at least one machine learning model includes mappings between simulated images generated from models of physical objects and real-world images of the physical objects. The technique also includes performing, by the at least one machine learning model, one or more operations on the first simulated image to generate a first augmented image of the first object. The technique further includes transmitting the first augmented image to a training pipeline for an additional machine learning model that controls a behavior of the physical process.

Methods, systems, and apparatus, including medium-encoded computer program products, for integrating control and operation of multi-tooltip processes with computer-aided manufacturing and/or design software and systems include method(s) including: obtaining toolpaths for manufacturing a physical structure and process control constraints, each of the toolpaths corresponding to a respective tooltip of a computer-controlled tool of a manufacturing system, each of the toolpaths designates a respective path for the respective tooltip within a workspace, and the process control constraints define capabilities of each of the respective tooltips within the workspace; defining a main toolpath and metadata defining operational parameters for the toolpaths based on the process control constraints; simulating manufacturing of the physical structure using the main toolpath and the metadata; and providing at least the main toolpath and the metadata for use in manufacturing the physical structure by the computer-controlled manufacturing system from the main toolpath and the metadata.

One embodiment of the present invention sets forth a technique for generating simulated training data for a physical process. The technique includes receiving, as input to at least one machine learning model, a first simulated image of a first object, wherein the at least one machine learning model includes mappings between simulated images generated from models of physical objects and real-world images of the physical objects. The technique also includes performing, by the at least one machine learning model, one or more operations on the first simulated image to generate a first augmented image of the first object. The technique further includes transmitting the first augmented image to a training pipeline for an additional machine learning model that controls a behavior of the physical process.

A method for monitoring machining processes in workpiece processing including steps of planning a processing process on the basis of a predetermined final shape of a workpiece to be achieved in the processing process and of quality features of the final shape of the workpiece and simulating the planned processing process in a computer-aided simulation. Target values of parameters of the simulated processing process occurring during the simulated processing process are detected and stored in the context of the computer-aided simulation. During the real processing process carried out according to the planned and simulated processing process, the parameters considered in the simulation are monitored and the actual values thereof are detected. By comparing actual values of parameters detected during the real processing process with the target values of these parameters detected during the simulation, the quality of the processing process and/or of the processed workpiece is assessed.

Methods, systems, and apparatus, including medium-encoded computer program products, for integrating control and operation of multi-tooltip processes with computer-aided manufacturing and/or design software and systems include method(s) including: obtaining toolpaths for manufacturing a physical structure and process control constraints, each of the toolpaths corresponding to a respective tooltip of a computer-controlled tool of a manufacturing system, each of the toolpaths designates a respective path for the respective tooltip within a workspace, and the process control constraints define capabilities of each of the respective tooltips within the workspace; defining a main toolpath and metadata defining operational parameters for the toolpaths based on the process control constraints; simulating manufacturing of the physical structure using the main toolpath and the metadata; and providing at least the main toolpath and the metadata for use in manufacturing the physical structure by the computer-controlled manufacturing system from the main toolpath and the metadata.

One embodiment of the present invention sets forth a technique for generating simulated training data for a physical process. The technique includes receiving, as input to at least one machine learning model, a first simulated image of a first object, wherein the at least one machine learning model includes mappings between simulated images generated from models of physical objects and real-world images of the physical objects. The technique also includes performing, by the at least one machine learning model, one or more operations on the first simulated image to generate a first augmented image of the first object. The technique further includes transmitting the first augmented image to a training pipeline for an additional machine learning model that controls a behavior of the physical process.

The present invention relates to the field of intelligent machining, in particular to a parallel control method based on multi-period differential sampling and digital twinning technologies, the method comprising the following steps of: a. detecting machining conditions of dotting machine equipment by using a multi-period differential sampling technology; b. establishing a digital twinning control model; and c. controlling a simulation model of the dotting machine equipment according to a detection judgment result so as to perform parallel control on the dotting machine equipment. According to the parallel control method based on multi-period differential sampling and digital twinning modelling provided by the present invention, for the digital twinning model of the dotting machine equipment, the parallel control method establishes a simulation model and a detection model of the dotting machine equipment by using a virtual-real synchronization technology; simulation dotting machine equipment operates in synchronization with the physical dotting machine equipment.

One embodiment of the present invention sets forth a technique for controlling the execution of a physical process. The technique includes receiving, as input to a machine learning model that is configured to adapt a simulation of the physical process executing in a virtual environment to a physical world, simulated output for controlling how the physical process performs a task in the virtual environment and real-world data collected from the physical process performing the task in the physical world. The technique also includes performing, by the machine learning model, one or more operations on the simulated output and the real-world data to generate augmented output. The technique further includes transmitting the augmented output to the physical process to control how the physical process performs the task in the physical world.

The present invention relates to the field of intelligent machining, in particular to a parallel control method based on multi-period differential sampling and digital twinning technologies, the method comprising the following steps of: a. detecting machining conditions of dotting machine equipment by using a multi-period differential sampling technology; b. establishing a digital twinning control model; and c. controlling a simulation model of the dotting machine equipment according to a detection judgment result so as to perform parallel control on the dotting machine equipment. According to the parallel control method based on multi-period differential sampling and digital twinning modelling provided by the present invention, for the digital twinning model of the dotting machine equipment, the parallel control method establishes a simulation model and a detection model of the dotting machine equipment by using a virtual-real synchronization technology; simulation dotting machine equipment operates in synchronization with the physical dotting machine equipment.