WO2024181969A1

WO2024181969A1 - Physics-based simulation of milling operations in an industrial metaverse

Info

Publication number: WO2024181969A1
Application number: PCT/US2023/014097
Authority: WO
Inventors: Ashish Gupta; Scott Kolb; Yu-Chin CHAN; Patrick RIBAS
Original assignee: Siemens Aktiengesellschaft; Siemens Corporation
Priority date: 2023-02-28
Filing date: 2023-02-28
Publication date: 2024-09-06

Abstract

System and method are disclosed for simulating manufacturing of a part by material removal. A simulation module executes a simulation of material removal by a cutting tool based on a sparse voxelization of a workpiece material and a discretized set of tool surface points. A voxelization module generates a sparse voxelization of the workpiece material and a discretization of tool surface points. A tool physics module computes reaction forces based on a set of marked tool surface points and marked material voxels and computes resulting temperature increase used to predict resulting tool wear over the course of a material removal step. The tool wear information is exported to the simulation module using a feedback loop.

Description

PHYSICS-BASED SIMULATION OF MILLING OPERATIONS IN AN INDUSTRIAL META VERSE

TECHNICAL FIELD

[0001] This application relates to digital twins. More particularly, this application relates to physics-based simulation of machining material in manufacturing operations in an industrial metaverse.

BACKGROUND

[0002] One may describe “Industrial Metaverse” as a set of technologies that enables the creation of digital twins of real-world products and processes. A digital twin is a virtual replica of a product or process used to predict how the physical entity will perform throughout its lifecycle. In a digital environment, problems can be found, analyzed, and fixed quickly. Ideally, problems can be discovered before they arise. An objective for industrial metaverse is to enable a whole new level of collaboration where distance between collaborators is irrelevant and a team can work together across countries and continents as if together in the very same room, in front of the very same machines or objects. A digital twin can allow interaction in real time, appearing like a real machine, and behaving as if in a real environment, subjected to the physical effects of temperature and friction from physical contact with materials.

SUMMARY

[0003] In this disclosure, a system and method apply a Universal Scene Description (USD) platform with GPU acceleration tools to computer aided design (CAD) and computer aided manufacturing (CAM) data associated with an industrial machine used for material removing on a manufactured workpiece. The machine assembly is digitized and the cutting tool and the object material are converted into a voxel representation in USD data suitable for simulations of material removal operations such as milling, grinding, lathing, or drilling to produce a desired object. A cutting physics module simulates friction, heat and tool wear to provide updates to the tool geometry during the sequence of simulated tool operations. In an aspect, a graphing tool is used for defining the simulation as custom graphs of nodes to carry out a sequence of tasks in every frame of the simulation.

[0004] In an aspect, a system and associated methods take geometric parts and manufacturing process data from an CAD/CAM based tool (e.g., Siemens NX) and setup a milling simulation inside USD based platform (e.g., NVIDIA Omniverse) to enable generation of a graphing extension (e.g., NVIDIA Omnigraph) customized with graphs of nodes to carry out a sequence of material removal machining tasks.

[0005] Aspects include a system for simulating manufacturing by material removal including a graphical processing unit (GPU) and non-transitory memory having stored thereon modules executed by the GPU. A simulation module simulates material removal by a cutting tool based on a sparse voxelization of a workpiece material and a discretized set of tool surface points. A voxelization module generates a sparse voxelization of the workpiece material and a discretization of tool surface points. A tool physics module computes reaction forces based on a set of marked tool surface points and marked material voxels, to compute resulting temperature increase, and to predict resulting tool wear over the course of material removal step. The tool wear information is exported to the simulation module using a feedback loop.

[0006] Aspects include a method for simulating manufacturing by material removal including a graphical processing unit (GPU) and non-transitory memory having stored thereon modules executed by the GPU. The method includes simulating material removal by a cutting tool based on a sparse voxelization of a workpiece material and a discretized set of tool surface points. The method further includes generating a sparse voxelization of the workpiece material and a discretization of tool surface points. The method further includes computing reaction forces based on a set of marked tool surface points and marked material voxels, and computing resulting temperature increase, used to predict resulting tool wear over the course of material removal step. The tool wear information is exported to the simulation module using a feedback loop.

BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Non-limiting and non-exhaustive embodiments of the present disclosure are described with reference to the following FIGURES, wherein like reference numerals refer to like elements throughout the drawings unless otherwise specified.

[0008] FIG. 1 illustrates an example of a framework for generating a simulation of a material removal machine operation on a workpiece in accordance with embodiments of this disclosure.

[0009] FIG. 2 illustrates an example of snapshots for a simulated workpiece receiving a series of milling operations in accordance with embodiments of this disclosure.

[0010] FIG. 3 illustrates an example of a time sequence for simulated machine tool surface points interacting with voxels of a workpiece in accordance with embodiments of this disclosure.

[0011] FIG. 4 illustrates an example of a computing environment within which embodiments of the disclosure may be implemented.

[0012] FIG. 5 illustrates an example of 2D topology for sparse voxelization. DETAILED DESCRIPTION

[0013] Method and system are disclosed to improve simulation of a material removal machine fabricating a workpiece product. Material removal is simulated by representing the workpiece material as voxels and representing the machine tool as surface points on a cylinder. A physics module computes physics related to the reaction forces for modeling tool wear and impact on material removal. Advantages of the tool wear simulation include (i) a feedback loop between material removal simulation and physics module provides continuous updates of the tool geometry, forces, and temperatures as the tool wears down over manufacture of multiple workpiece bodies; (ii) dimensional errors of manufactured (milled) parts due to a worn tool are visualized, providing an estimation for tool replacement scheduling. The framework for material removal simulation is implemented as software extensions in an integrated development environment (IDE). Using such an extension, a user may setup a material removal machine, a workpiece, and a material removal program to be simulated. The material removal program can more easily be developed using custom graphs of nodes to carry out as sequence of tasks in every frame of the simulation. The GPU acceleration enables (i) a finer discretization, both spatially and temporally, for improved accuracy without affecting performance, and (ii) various add-ons that may be simulated, such as coolant flow or chip formation to create a simulation that approaches reality, not possible using conventional CPU processors. GPU acceleration and ray tracing improves the visualization display, with truer real-time and realistic simulation. Unlike rasterized colored meshes, ray tracing may simulate reflection, refraction and other optical effects. Furthermore, besides animating the tool and the changes in workpiece geometry, one may also animate chip formation, or coolant flow, as the material is being removed from the workpiece. Embodiments also enable cloud collaboration, where multiple engineers sitting at different locations may work on the same simulation in parallel.

[0014] FIG. 1 illustrates an example framework for simulation of manufacturing by machined material removal in accordance with embodiments of this disclosure. Framework 100 includes a USD platform 110, with USD schema extension 111, USD object mesh module 112, GPU memory 114, and simulation module 116. In an embodiment, USD platform 110 is implemented using NVIDIA Omniverse. Voxelization module 121 and tool physics module 131 perform operations to support USD platform 110.

[0015] In an embodiment, converter 102 is configured to convert a CAD representation of a material removal machine into a USD schema extension 111, including USD assembly representation 113, which includes 3D layer information and interrelation information of the assembly (e.g., a worktable and activators which support the workpiece during material removal) for generating realistic animation of the machine components in motion during simulated work operations. During this conversion, assembly structure of the machine as represented in the original JT file, such as grouping and hierarchal containment of components and sub-assemblies, are maintained in the USD data file. Converter 102 is further configured to transform 3D CAD information regarding the tool and workpiece into USD object mesh 112 data. In an embodiment, CAD-CAM environments represent information received from CAD-CAM tool 101 in formats such as PRT (a model part file saved in a 3D model format used by a 3D CAD program) or JT (Jupiter Tessellation, an ISO-standardized 3D CAD data exchange format used for product visualization).

[0016] In an aspect, converter 102 is configured to transform CAM data related to the motion of the tool into a standardized G-code format to represent the tool motion 115, such as along each axis in 3D space (e.g., X,Y,Z Cartesian axes), as part of USD schema extension 111. G-code is a computer numerical control (CNC) programming language used mainly in computer-aided manufacturing to control automated machine tools. G-code instructions are provided to a machine controller (industrial computer) that tells the motors where to move, how fast to move, and what path to follow. For example, a machine tool such as a lathe or mill implements a cutting tool that is moved according to these instructions through a toolpath cutting away material to leave only the finished workpiece. An unfinished workpiece is precisely positioned in any of up to nine axes around the three dimensions relative to a toolpath and either the tool, the workpiece or both can move relative to each other. G-code instructions instruct the machine tool as to the type of action to be performed, which can include the following: rapid movement, controlled feed, series of controlled feed movements, and tool offset. In an embodiment, a USD schema is extended to incorporate the G-code program and a generic specification of the material removal machine. Moveable parts are identified by USD primitives and the type of motion, such as linear movement along any axis in 3D space. A G-code processing application of the USD schema 111 provides the means to animate the material removal machine movements.

[0017] USD schema extension 111 further includes characteristics of workpiece material 117 (e.g., material type, density, hardness, etc.) entered by user via CAD/CAM tool 101. For example, an aluminum workpiece behaves differently during material removal than a vinyl workpiece in terms of chip formation and accumulation (i.e., bits of material cast off during milling by the cutting tool) and allowable cutting depth with each tool pass. Consequently, USD schema extension 111 includes material information 117 such that simulation module 116 can generate a realistic simulation that includes accurate chip formation information useful for realistic animation in visualization 118 and for predicting cutting deviations caused by the chip formation. [0018] Voxelization module 121 is configured to receive the workpiece data from USD object mesh module 112 and discretize the mesh into voxels, shown as object voxelization 122, using a hierarchical data structure that provides efficient methods to store and manipulate sparse volumetric data discretized on 3D grids. FIG. 5 shows an example of 2D topology for sparse voxelization. This voxelization is executed by a GPU and the workpiece voxels reside in the GPU memory 114 according to data atlas 501. An example of an implementation for voxelization module 121 is NVIDIA GVDB. In an embodiment, the voxelization data is stored as a sparse voxel structure having a range of voxel sizes, such as large, medium and small, for conserving GPU memory 114 and to enable faster queries. In some embodiments, the GPU memory 114 is arranged using a CUDA programming model and the data of the sparse voxel structure is stored in executable threads or warps in single instruction multiple thread format.

[0019] In a parallel process, voxelization module 121 receives an object mesh representation 112 of the cutting tool, approximates the tool as a cylinder, and creates a set of sample points on the cylindrical surface of the tool. The tool surface points are transferred to the GPU memory 114.

[0020] Simulation module 116 is configured to execute simulated material removal in a series of material removal steps, with each step including the following operations. The current tool position is received from tool motion module 115. Discretized tool surface points 123 are transformed to the current tool position. Interaction between the tool surface points and workpiece voxels are determined. For example, for each tool surface point that interacts with a workpiece voxel, the tool surface point and workpiece voxel is identified and marked. Marked voxels are removed and the hierarchy of workpiece voxels are updated. The marked tool surface points are exported to tool physics module 131 for physics computations. The GPU efficiently processes the material removal voxels using parallel processing such that a voxel is not removed until all voxels that need to be removed in a material removal step have been identified. In an embodiment, simulation module 116 receives the machine assembly information 113, tool motion data 115 and material data 117 and renders visualization 118 as a representation of the machine operation, tool motion, and material removal as a realistic animation. FIG. 2 illustrates an example of visualization 118 for the workpiece in a time lapse series 200 of material removal step images.

[0021] Tool physics module 131 provides a feedback loop to receives the marked tools surface points and compares these with the sample surface points 123. FIG. 3 illustrates an example of a time series 300 of marked tool surface points for a sequence of material removal steps as described above. Given the marked tool surface points from the simulation module 116 and the history of the tool motion 115, tool physics module 131 computes the reaction forces generated at each step of the material removal process, along with the friction forces and subsequent increase in temperature at the interface between the tool and the workpiece material. In an embodiment, each cutting edge on the tool surface is discretized along the axial direction of the tool. Analytical physics-based models are applied using cutting force parameters that include tangential, distal and normal friction, as well as terms including but not limited to blunt cutting edge and flank wear effect. The physics models are coupled with the simulation module 116 such that they are performed only at discretized cutting edges that he within the tool-workpiece interface for each step of the tool path. Additionally, forces may be calculated at sub-steps of each tool path step by further segmenting into forces per tool revolution(s).

[0022] Tool physics module 131 simulates the physics by employing regression models using baseline data from actual tool wear trials to approximate the wear of the cutting tool over time and includes the impact on the forces and temperature increases. With the feedback loop between tool physics module 131 and simulation module 116, the tool geometry, forces and temperatures are continuously updated as the simulated tool wears down over the repeated simulations of material removal steps and for multiple workpieces being virtually manufactured. Predicted dimensional errors for milled workpieces are manifested in the simulation visualization 118 due to the worn tool, which is useful for estimating when a tool replacement should be planned.

[0023] For embodiments that implement NVIDIA Omniverse for the USD platform 110, the building block by which a developer can write custom applications inside Omniverse are called extensions. Standard Omniverse apps such as “Omniverse Create”, or “Omniverse View” are developed using different extensions, such as viewport, stage, physics etc. One can write a new extension using another app called “Omniverse Code” which is an Integrated Development Environment (IDE) for developing new extensions. The system and methods described herein can be implemented as a material removal simulation extension, wherein a user can setup a material removal machine, a workpiece, the G-code and call upon the simulation to run. The simulation in turn can be defined using NVIDIA OmniGraph, allowing a developer to write custom graphs of nodes to carry out a sequence of tasks in every frame of the simulation.

[0024] Advantages of the disclosed framework include the following. A manufacturing-based extension for simulation module 116 extension uses an editor feature of the USD platform 110 to select objects in play, including the machine tool and workpiece object, extend the objects with physics, and designate any parameters (e.g., velocity, gravity) that will be factored into the simulation. The material removal machine is included in the simulation scene, capable of animating all moveable components during the simulated operations, with motions captured in any 3D axis. A holistic view is provided by visualization 118 regarding the physical effects of machining the material, such as temperature, friction, and various forces involved. While conventional approaches for understanding the physics of manufacturing by material removal rely on cameras to capture training images for machine learning, tens of thousands of images would be required for proper training to learn instances where a manufactured part deviates from the design. However, using the simulation framework 100, manufacturing engineers and manufacturing users have an alternative approach that eliminates the burden of generating training images.

[0025] In addition, framework 100 provides a reliable prognostic mechanism for predicting a problematic machining operation prone to breaking cutting tools (e.g., topology features requiring sharp turns, and/or effects of chip buildup). Tool breakdown is a significant problem for manufacturing operations, resulting in factory shutdowns and decline in manufacturing output. Simulations by framework 100 can discover which particular tool operation is susceptible to breakdown, allowing for reprogramming the tool movement to remedy the potential tool failure.

[0026] Currently, manufacturers and manufacturing engineers rely on CAD/CAM tools alone, such as CAD/CAM tool 101, that generate tool paths given the desired material removal on a workpiece, along with the depth of the cutting/milling. But what is not provided is complex physics considerations such as temperature, forces on tool, etc., which can only be accounted by relying on engineering experience and many trials and errors. Framework 100 provides a simulation that allows for optimized trade off analysis for high product output rate vs. tool breakdown costs.

[0027] FIG. 4 shows an example of a computer environment within which embodiments of the disclosure may be implemented to execute CFD meta learning. A computing device 410 includes a processor 415 and memory 411 (e.g., a non-transitory computer readable media) on which is stored various computer applications, modules or executable programs. In an embodiment, computing device includes one or more of the following modules: a USD platform module 403, a voxelization module 405, and tool physics module 407, which execute functionality of respective components USD platform module 110, voxelization module 121, and tool physics module 131 as shown in FIG. 1.

[0028] As shown in FIG. 4, as an alternative computer implementation of material removal simulation, the modules for one or more of modules 110, 121, 131 may be deployed as cloudbased or web-based operations, as shown by USD platform module 443, voxelization module 445, and tool physics module 447 respectively, or as a divided operation shared by local modules 403, 405, 407 and web-based modules 443, 445, 447.

[0029] A network 460, such as a local area network (LAN), wide area network (WAN), or an internet based network, connects modules of computing device 410 and to cloud based modules 443, 445, 447.

[0030] User interface module 414 provides an interface between modules 403, 405, 407 and user interface 430 devices, such as display device 431 and user input device 432. GUI engine 413 drives the display of an interactive user interface on display device 431 , allowing a user to receive visualizations of analysis results and assisting user entry of learning objectives and domain constraints for USD platform module 403, 443, voxelization module 405, 445, and tool physics module 407, 447.

[0031] Computer readable medium instructions for carrying out operations of the present disclosure may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0032] Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, may be implemented by computer readable medium instructions.

[0033] The program modules, applications, computer-executable instructions, code, or the like depicted in FIG. 4 as being stored in the system memory 411 are merely illustrative and not exhaustive and that processing described as being supported by any particular module may alternatively be distributed across multiple modules or performed by a different module. In addition, various program module(s), script(s), plug-in(s), Application Programming Interface(s) (API(s)), or any other suitable computer-executable code hosted locally on the computer system 410, remote network devices storing modules 443, 445, 447, and/or hosted on other computing device(s) accessible via one or more of the network(s) 460, may be provided to support functionality provided by the program modules, applications, or computer-executable code 8 and/or additional or alternate functionality. Further, functionality may be modularized differently such that processing described as being supported collectively by the collection of program modules depicted in FIG. 4 may be performed by a fewer or greater number of modules, or functionality described as being supported by any particular module may be supported, at least in part, by another module. In addition, program modules that support the functionality described herein may form part of one or more applications executable across any number of systems or devices in accordance with any suitable computing model such as, for example, a client-server model, a peer-to-peer model, and so forth. In addition, any of the functionality described as being supported by any of the program modules depicted in FIG. 4 may be implemented, at least partially, in hardware and/or firmware across any number of devices.

[0034] It should further be appreciated that the computer system 410 may include alternate and/or additional hardware, software, or firmware components beyond those described or depicted without departing from the scope of the disclosure. More particularly, it should be appreciated that software, firmware, or hardware components depicted as forming part of the computer system 410 are merely illustrative and that some components may not be present or additional components may be provided in various embodiments. While various illustrative program modules have been depicted and described as software modules stored in system memory 411, it should be appreciated that functionality described as being supported by the program modules may be enabled by any combination of hardware, software, and/or firmware. It should further be appreciated that each of the above-mentioned modules may, in various embodiments, represent a logical partitioning of supported functionality. This logical partitioning is depicted for ease of explanation of the functionality and may not be representative of the structure of software, hardware, and/or firmware for implementing the functionality. Accordingly, it should be appreciated that functionality described as being provided by a particular module may, in various embodiments, be provided at least in part by one or more other modules. Further, one or more depicted modules may not be present in certain embodiments, while in other embodiments, additional modules not depicted may be present and may support at least a portion of the described functionality and/or additional functionality. Moreover, while certain modules may be depicted and described as sub-modules of another module, in certain embodiments, such modules may be provided as independent modules or as sub-modules of other modules.

[0035] Although specific embodiments of the disclosure have been described, one of ordinary skill in the art will recognize that numerous other modifications and alternative embodiments are within the scope of the disclosure. For example, any of the functionality and/or processing capabilities described with respect to a particular device or component may be performed by any other device or component. Further, while various illustrative implementations and architectures have been described in accordance with embodiments of the disclosure, one of ordinary skill in the art will appreciate that numerous other modifications to the illustrative implementations and architectures described herein are also within the scope of this disclosure. In addition, it should be appreciated that any operation, element, component, data, or the like described herein as being based on another operation, element, component, data, or the like can be additionally based on one or more other operations, elements, components, data, or the like. Accordingly, the phrase “based on,” or variants thereof, should be interpreted as “based at least in part on.” [0036] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

Claims

CLAIMS What is claimed is:

1. A system for simulating manufacturing of a part by material removal, comprising: a graphical processing unit (GPU); and a non-transitory memory having stored thereon modules executed by the GPU, the modules comprising: a simulation module configured to execute a simulation of material removal by a cutting tool based on a sparse voxelization of a workpiece material and a discretized set of tool surface points; a voxelization module configured to generate a sparse voxelization of the workpiece material and a discretization of tool surface points; and a tool physics module configured to compute reaction forces based on a set of marked tool surface points and marked material voxels, to compute resulting temperature increase, and to predict resulting tool wear over the course of a material removal step, wherein the tool wear information is exported to the simulation module using a feedback loop.

2. The system of claim 1, further comprising: a converter configured to transform a computer aided design (CAD) representation of a material removal machine into a universal scene description (USD) schema extension, and transform computer aided manufacturing (CAM) data related to the motion of the cutting tool into a standardized G-code format, wherein the simulation module uses the transformed CAD representation and transformed CAM data for executing the simulation.

3. The system of claim 1, further comprising: a converter configured to transform a computer aided design (CAD) information regarding the cutting tool and the workpiece material into USD object mesh data, wherein the voxelization module uses the USD object mesh data to generate the sparse voxelization.

4. The system of claim 1, wherein the simulation module receives a universal scene description (USD) schema description of workpiece material characteristics which is used by the simulation module to generate chip formation information, and to predict cutting deviations based on the chip formation information.

5. The system of claim 1, wherein the sparse voxelization is stored as a sparse voxel structure having a range of voxel sizes for conserving the GPU memory, and the data of the sparse voxel structure is stored in executable threads or warps in single instruction multiple thread format.

6. The system of claim 1, wherein the tool physics module is further configured to apply analytical physics based models using cutting force parameters that include tangential, distal and normal friction, and terms including blunt cutting edge and flank wear effect.

7. The system of claim 6, wherein the models are coupled with the simulation module such that the models are performed only at discretized cutting edges that lie within the interface between the workpiece and the cutting tool for each step of the tool path.

8. The system of claim 1, wherein the simulation module is further configured to generate a visualization of dimensional errors of the manufactured part due to the predicted tool wear.

9. The system of claim 1, wherein the simulation module is further configured to provide an estimation for tool replacement scheduling based on the predicted tool wear.

10. A computer-implemented method for simulating manufacturing of a part by material removal, comprising: executing a simulation of material removal by a cutting tool based on a sparse voxelization of a workpiece material and a discretized set of tool surface points; generating a sparse voxelization of the workpiece material and a discretization of tool surface points; and computing reaction forces based on a set of marked tool surface points and marked material voxels; computing temperature increase resulting from the computed reaction forces; and predicting resulting tool wear over the course of a material removal step, wherein the tool wear information is exported to the simulation module using a feedback loop.

11. The method of claim 10, further comprising: transforming a computer aided design (CAD) representation of a material removal machine into a universal scene description (USD) schema extension, and transforming computer aided manufacturing (CAM) data related to the motion of the cutting tool into a standardized G-code format used for executing the simulation.

12. The method of claim 10, further comprising: transforming a computer aided design (CAD) information regarding the cutting tool and the workpiece material into USD object mesh data used to generate the sparse voxelization.

13. The method of claim 10, further comprising: receiving a universal scene description (USD) schema description of workpiece material characteristics, wherein executing the simulation further includes: using (USD) schema description of workpiece material characteristics to generate chip formation information, and predicting cutting deviations based on the chip formation information.

14. The method of claim 10, wherein predicting tool wear further comprises: applying analytical physics based models using cutting force parameters that include tangential, distal and normal friction, and terms including blunt cutting edge and flank wear effect, wherein the models are coupled with the simulation module such that the models are performed only at discretized cutting edges that lie within the interface between the workpiece and the cutting tool for each step of the tool path.

15. The method of claim 10, wherein executing the simulation further comprises: generating a visualization of dimensional errors of the manufactured part due to the predicted tool wear, and providing an estimation for tool replacement scheduling based on the predicted tool wear.