WO2020023811A1 - Synthèse et optimisation de conceptions d'objet 3d à l'aide de conceptions existantes - Google Patents

Synthèse et optimisation de conceptions d'objet 3d à l'aide de conceptions existantes Download PDF

Info

Publication number
WO2020023811A1
WO2020023811A1 PCT/US2019/043542 US2019043542W WO2020023811A1 WO 2020023811 A1 WO2020023811 A1 WO 2020023811A1 US 2019043542 W US2019043542 W US 2019043542W WO 2020023811 A1 WO2020023811 A1 WO 2020023811A1
Authority
WO
WIPO (PCT)
Prior art keywords
designs
recited
new
existing designs
existing
Prior art date
Application number
PCT/US2019/043542
Other languages
English (en)
Inventor
Lucia MIRABELLA
Suraj Ravi MUSUVATHY
Wei Chen
Original Assignee
Siemens Aktiengesellschaft
Siemens Corporation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens Aktiengesellschaft, Siemens Corporation filed Critical Siemens Aktiengesellschaft
Publication of WO2020023811A1 publication Critical patent/WO2020023811A1/fr

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y50/00—Data acquisition or data processing for additive manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]

Definitions

  • This application relates to computer aided design methodologies and systems.
  • the technology described herein is particularly well-suited for, but not limited to, designs for additive manufacturing and other fabrication methods.
  • Design space exploration generally refers to the systematic analysis of potential design points based on parameters of interest.
  • the potential design points may be subject to constraints or limitations.
  • Design space exploration can include various design optimization techniques.
  • Example design optimization techniques for CAD systems include topology optimization, shape optimization, and size optimization.
  • Design optimization can be performed for a variety of disciplines such as aerodynamics, hydrodynamics, heat transfer, structural mechanics, acoustics, etc.
  • a topology optimization tool may result in the identification of the major load paths in a particular model, thereby enabling the creation of a design in which material is minimized so as to reduce weight without compromising the structural integrity of the design.
  • the parameterized design may include design parameters having a finite range of values.
  • the set of all designs that are generated by selecting combinations of the design parameter values can define the design space.
  • the design parameters can be used in design optimization algorithms, so as to generate a design that satisfies design requirements.
  • the selection or creation of a suitable parameterized design for optimization typically requires expert knowledge of a designer or engineer, and thus current approaches to defining the parameterized design are often manually intensive.
  • the designer/engineer might inadvertently exclude portions of a given design space from various optimization analyses, for example, because of limited expertise or time constraints. Such exclusions may result in a sub-optimal final design or inefficient design space exploration.
  • a CAD system may obtain a plurality of pre-existing designs.
  • Each of the plurality of pre-existing designs may represent a three-dimensional (3D) object.
  • each of the plurality of pre- existing designs may represent a different design for the 3D object.
  • the CAD system may construct a parameterized model of a design space corresponding to the 3D object.
  • the parameterized model may define a plurality of latent parameters and a plurality of latent coordinates associated with each of the plurality of latent parameters, so as to define a plurality of new designs for the 3D object.
  • the parameterized model is constructed by training a generational adversarial network (GAN) using the plurality of pre-existing designs.
  • GAN generational adversarial network
  • FIG. 1 illustrates an example of a computer-aided design (CAD) model construction process according to embodiments of the present disclosure.
  • CAD computer-aided design
  • FIG. 2 depicts example inputs to the CAD construction process depicted in FIG. 1 , according to embodiments of this disclosure.
  • FIG. 3 shows a block diagram of an example of a CAD system according to embodiments of this disclosure.
  • FIG. 4 is a flow diagram of another example process for constructing a CAD model according to embodiments of this disclosure.
  • FIG. 5 depicts an example parameterized model that is generated as part of the example process for constructing the CAD model shown in FIG. 4, in accordance with embodiments of this disclosure.
  • FIG. 6 shows an example of a computing environment within which embodiments of the disclosure may be implemented.
  • CAD computer aided design
  • Pre-existing designs may include designs that have been created for a particular component or components, such as a mechanical component.
  • the pre- existing designs may represent a three-dimensional (3D) object.
  • CAD models representative of new designs are constructed.
  • a generational adversarial network (GAN) can be trained using the pre- existing designs, such that the GAN model may then construct a parameterized model of a design space.
  • the parameterized model can define a plurality of new designs for a given 3D object.
  • the disclosed methods and systems present an improvement to the functionality of the computer used to perform such a computer-based task. Furthermore, the disclosed methods and systems can create new CAD models, and thus designs, that are not generated using current approaches to design. For example, creating a parameterized design typically requires expert knowledge of a designer or engineer, and thus current approaches to defining the parameterized design are often manually intensive. Furthermore, the designer/engineer might inadvertently exclude portions of a given design space from various optimization analyses, for example, because of limited expertise or time constraints. The disclosed methods and systems can present an improvement to final designs and can improve efficiency with respect to design space exploration.
  • a CAD system for instance a CAD system 301 (see Fig. 3) obtains a plurality of pre-existing or existing designs 103.
  • the pre-existing designs 103 may each represent a 3D object.
  • the pre-existing designs 103 may each represent different designs for the same 3D object.
  • the pre-existing designs 103 may include all previous designs for a particular 3D object.
  • the pre- existing designs may include a subset of the previous designs for a particular 3D object.
  • the pre-existing designs 103 may each represent different designs for 3D objects that are different from, but similar to, each other.
  • the 3D object is an object that is manufactured by additive manufacturing.
  • the pre-existing designs 103 may correspond to designs of a mechanical component that has changed over time.
  • the pre-existing designs 103 may also include designs that were previously manufactured and implemented in practice, or designs that have not been manufactured or implemented.
  • the pre-existing designs 103 may be retrieved from a database of designs corresponding to a particular component or 3D object.
  • the pre-existing designs may be retrieved from a database of designs that correspond to a particular function.
  • the CAD system 301 may obtain the pre-existing designs 103 in various formats. Examples of formats of the pre-existing designs 103 include, without limitation, 3D scans, boundary representation (B-Rep)
  • the pre-existing designs 103 may be each formatted as a 3D scan, a CAD model, or a topology optimized model.
  • the pre-existing designs 103 may be obtained by the CAD system 301 in the form of a voxel 202.
  • the CAD system 301 may convert the voxel 202 into a polygonal surface, such as a six view depth map 204.
  • the CAD system 301 can derive depth maps from voxels that represent the pre-existing designs 103.
  • the CAD system 301 may obtain the pre-existing designs 103 formatted as polygonal surfaces or depth maps.
  • the depth map 204 can be derived by observing the corresponding object or voxel 202 from six (or some fixed number of) different viewpoints, and computing the distance from each point of the object or voxel surface to a viewing plane that passes through the viewpoint. It will be understood that the six view depth map 204 is illustrated for purposes of example, thus the number of viewpoints can vary in various depth maps as desired, and all such depth maps are within the scope of this disclosure. In some examples, machine learning is more computationally efficient when the learning is performed using a lower dimensional (2D instead of 3D) embedding of the data.
  • the CAD system 301 learns parameterization and limits.
  • the CAD system 301 constructs a parameterized model, for instance a parameterized model 500, based on the plurality of pre-existing designs 103.
  • the parameterized model 500 may be of a design space 201 that corresponds to a particular 3D object, for instance the 3D object represented by the plurality of pre-existing designs 103.
  • the design space 201 may include an initial CAD model geometry, for instance one of the pre-existing designs 103, along with the region in space around which the geometry can grow or shrink.
  • the parameterized model 500 may be constructed by training a neural network using the plurality of pre-existing designs 103.
  • the plurality of pre-existing designs 103 may be constructed by training a neural network using the plurality of pre-existing designs 103.
  • parameterized model 500 is constructed by training a generational adversarial network (GAN) using the plurality of pre-existing designs 103.
  • GAN generational adversarial network
  • the GAN may be trained using depth maps, for instance six view depth maps 204, of the pre-existing designs 103.
  • training the GAN with six view depth maps 204 is more computationally efficient than the training the GAN with voxels 202.
  • the GAN may learn latent parameters associated with the pre-existing designs 103, and thus the 3D object represented by the pre-existing designs 103.
  • some or all of the pre-existing designs related to a particular 3D object can be modeled in an efficient and automatic manner, and such a model may serve as the basis for new and improved designs, as further described herein.
  • the GAN includes a generator neural network and a discriminator neural network.
  • the generator neural network can be embodied in, or can include, for example, a deconvolutional neural network.
  • the discriminator neural network can be embodied in, or can include, for example, a convolutional neural network. Each of such neural network competes with each other in a zero-sum game framework.
  • the parameterized model 500 defines a plurality of latent parameters or dimensions 502 and a plurality of latent coordinates or values 504 associated with each of the plurality of latent dimensions or parameters 502, so as to define a plurality of new designs 506 for a given 3D object.
  • the parameterized model 500 can define a model of the design space corresponding to the given 3D object.
  • the example model 500 includes ten (10) parameters 502 (represented in columns labeled 0-9) that are each associated with five (5) coordinates 504 (represented in rows labeled 2, 1 , 0, -1 , and -2), though it will be understood that the model 500 is simplified for purposes of explanation, and thus the model 500 may include any number of parameters and coordinates as desired. Furthermore, while the model 500 is depicted as a matrix, it will be understood that the complexity of the model that is constructed can vary in accordance with various embodiments of this disclosure.
  • a given latent parameter 502 may represent visible
  • the corresponding new design 506 is adjusted in a manner that is identifiable by a user, such as a CAD designer.
  • a user such as a CAD designer.
  • the latent coordinate 504 that is associated with the latent parameter 502 represent in column nine (9) is varied, the size of an opening 508 is affected.
  • the opening 508 is wider when the parameter at column nine (9) is associated with the latent coordinate two (2), as compared to when the parameter at column nine (9) is associated with the latent coordinate negative two (- 2).
  • adjusting the value 504 corresponding to a given parameter 502 does not result in a visually identifiable change to the new designs 506.
  • an optimization is performed on the new designs 506.
  • the CAD system 301 in particular an optimization tool, may perform a single-disciplinary or multi-disciplinary optimization on each of the plurality of new designs 306. In doing so, the designs that perform the best may be identified.
  • one or more designs from the plurality of new designs is selected.
  • a single-disciplinary optimization applies design mechanisms to achieve a single objective.
  • a multi-disciplinary optimization applies design mechanisms that can incorporate multiple disciplines, so as to achieve multiple objectives.
  • a user may determine that the designs selected from the new designs are adequate. Alternatively, the user may determine that further designs are desired. In some examples, the CAD system 301 may determine whether further designs are desired. Such a determination may be based on a predetermined number of iterations for performing optimizations. Alternatively, or additionally, such a determination may be based on whether one or more design objectives have been satisfied. If it is determined at 108 that no further designs or edits are needed, at least one final design or CAD model 1 1 1 is constructed and obtained as result of the optimization at 106. Post- processing may be performed on the final CAD model 1 1 1.
  • Post-processing may include, for example, translation of the final design or model 1 1 1 into instructions that may be executed by a 3D printer or other fabrication device to create a physical representation of the design or final CAD model 1 1 1.
  • Techniques for translation of a design to such instructions are device-specific and generally known in the art; thus, such techniques are not described in detail herein.
  • the process may proceed to 1 12, where one or more boundary conditions that limit the new designs 306 for the 3D object are identified.
  • the identified boundary conditions are relaxed so as to define adjusted boundary conditions, and the process returns to 106, where the parametric model is optimized using the adjusted boundary conditions. If more edits are needed, in accordance with the illustrated example, steps 106, 108, 1 10, and 1 12 may be repeated until the final CAD model 1 11 is generated.
  • the CAD system 301 may include one or more processors 31 1 and a memory 321 having stored applications, agents, and computer program modules to implement the embodiments of this disclosure including a design tools application 322, a topology optimization program module 323, a GAN engine module 331 , and a multi-disciplinary optimization program module 341.
  • a module may refer to a software component that performs one or more functions. Each module may be a discrete unit, or the functionality of multiple modules can be combined into one or more units that form part of a large program.
  • the design tools application 322, topology optimization program module 323, GAN engine module 331 , and the multi-disciplinary optimization program module 341 are organized to form a program for design space exploration and optimization.
  • Design tools application 322 may be implemented as a CAD product modeling or drawing application such as Siemens NX, AutoCAD, or the like, which provides an interface for a user, such as a designer, to develop 3D rendering of objects.
  • a user may apply the design tools application 322 to a final design once it is received from the topology optimization program 323 or the multi-disciplinary optimization program 341.
  • the final design(s) may include several editable parametric shapes representing void regions and several editable parametric shapes representing solid regions.
  • GUI graphical user interface
  • the multi-disciplinary optimization module 341 may include a simulation module 342 and an optimizer 343.
  • the multi-disciplinary optimization module 341 may execute various algorithms so as to optimize designs based on multiple objectives or design criteria.
  • the topology optimization program module 323 may execute various algorithms so as to perform topology optimizations on various designs of 3D objects.
  • the multi-disciplinary optimization module 341 and the topology optimization program module 323 may receive designs from the GAN engine module 331.
  • the multi-disciplinary optimization module 341 and/or the topology optimization program module 323 may receive a parameterized model of a design space from the GAN module 331 , wherein the parameterized model is generated by the GAN module 331 using existing designs.
  • the multi-disciplinary optimization module 341 , in particular the simulation module 342 or the optimizer 343, and the topology optimization program module 323 may receive one or more initial design criteria from a user or the GAN 331 , such as the size for the design space, physical load information, material, weight, and density information, or any other relevant property needed for the optimization or simulation, as well as any design constraints.
  • the topology optimization program module 323 may execute an objective function that represents a quantity to be minimized for best performance, such as minimal
  • the program 323 or module 341 may solve for the remaining unknown variables, such as material distribution, by applying differential equations for example.
  • the topology optimization program module 323 or the multi-disciplinary optimization module 341 may operate using discrete or continuous variables. Discrete modifications to the topology geometry may occur as a series of operations.
  • the GAN module 331 may include a generator 332, discriminator 333, and parametric modeling module 335.
  • the GAN module 331 may obtain a plurality of pre- existing designs, for instance from the processor 31 1 or from the design tools
  • the GAN module 331 may construct a parameterized model of a design space corresponding to a 3D object.
  • the GAN module 331 in particular the generator 332 and discriminator 333, can be trained using the plurality of pre-existing designs.
  • FIG. 4 shows a flow diagram of an example process 400 for constructing a CAD model, in accordance with embodiments of this disclosure.
  • a CAD system for instance the CAD system 301 , obtains existing designs.
  • the existing designs may each represent and correspond to a 3D object.
  • the existing designs may include pre- existing designs, for instance pre-existing designs that were previously generated for the 3D object.
  • the existing designs may further include new designs that are based on the pre-existing designs, as further described herein with reference to FIG. 4.
  • the designs may each correspond to a 3D object.
  • the existing designs may each represent different designs for the same 3D object.
  • the existing designs may each represent different designs for 3D objects that are different from, but similar to, each other.
  • the 3D object is an object that is manufactured by additive manufacturing.
  • the existing designs include, without limitation, mechanical components of a machine, medical devices, tools, and the like.
  • the existing designs may be retrieved from a database of designs, for instance stored in memory 321 , which correspond to a particular 3D object or function.
  • the existing designs may also be received as a result of optimizing a parametric model that is based on the pre-existing designs.
  • the existing designs may be formatted the same or differently as compared to each other. Examples of formats of the existing designs include, without limitation, 3D scans, boundary representation (B-Rep) CAD models, parametric CAD models, and previously topology optimized models.
  • a parameterized model is constructed based on the existing designs, at 404.
  • a GAN may be trained using the existing designs to construct the parameterized model.
  • the GAN can learn the implicit parameterization that defines the existing designs.
  • the GAN can generate the parameterized model of the design space that corresponds to the 3D object represented by the existing designs.
  • the parameterized model defines a plurality of new designs for the 3D object.
  • the new designs defined by the parameterized model may also be referred to as feasible designs or new feasible designs.
  • the parameterized model may define a plurality of latent parameters and a plurality of latent coordinates associated with each of the plurality of latent parameters, such that each combination of latent coordinate and latent parameter defines a respective new feasible design.
  • the parameterized model may further include one or more boundary conditions that limit the new feasible designs for the 3D object.
  • the boundary conditions can define ranges that correspond to parameters defined by the parameterized model.
  • the optimization may be constrained by one or more boundary conditions or limitations.
  • an example limitation may require that a particular aspect of a given design is within a range of sizes.
  • an example condition may require that a particular aspect of a given design is fixed to, or connects to, another component having a pre-defined interface. It will be understood that limitations and boundary conditions can vary based upon the object being designed, and all such limitations and boundary conditions are contemplated as being within the scope of this disclosure.
  • a performance simulation is performed on each of the new designs defined by the parameterized model generated by the GAN.
  • the performance simulation may be constrained by one or more boundary conditions.
  • the boundary conditions that limit the new designs for the 3D object are defined by the parameterized model.
  • boundary conditions that constrain the performance simulation may be defined by a user of the CAD system 301. Based on the performance simulation, the CAD system 301 may determine a set of the new designs that perform better than the new designs that are not in the set. Stated another way, the best performing designs may be identified as a result of the performance simulation.
  • a user or the GAN can determine whether there are limits or boundary conditions that can be relaxed. If it is determined that limits or boundary conditions can be relaxed, the process may proceed to 410, where one or more boundary conditions are adjusted, so as to define a new set of boundary conditions. The process may then return to 406, where another performance simulation, for instance a second performance simulation, is performed. The second performance simulation is constrained by the new set of boundary conditions.
  • one or more designs are selected from the plurality of new designs. The designs may be selected based on the multi-disciplinary optimization or simulations performed at 406.
  • one or more adjusted designs may be determined based on the performance simulation that was performed within the adjusted boundary conditions.
  • the adjusted designs are different than the plurality of new designs defined by the parameterized model.
  • a topology optimization may be performed on the one or more selected designs or adjusted designs, at 410.
  • the topology optimization may generate one or more updated designs 415.
  • the topology optimization may perform a topology optimization algorithm that iteratively generates one or more modifications to a topology of a given selected design to ultimately produce a complex geometric model (i.e. , an updated design) that is optimized according to various parameters.
  • the topology optimization for a particular selected design may be complete after a fixed number of iterations or after a predetermined objective is satisfied.
  • the CAD system 301 may determine whether further designs are desired. Such a determination may be based on a predetermined number of iterations for performing optimizations or simulations. Alternatively, or additionally, such a determination may be based on whether one or more design objectives have been satisfied. If it is determined at 416 that no further designs or edits are needed, at least one final design or CAD model 41 1 is constructed and obtained as a result of the optimization at 414.
  • the process may return to 402, where existing designs are obtained.
  • the existing designs may include the pre-existing designs of the 3D object or the updated designs 415, or a combination thereof.
  • another, for instance a second, parameterized model of the design space corresponding to the 3D object can be constructed.
  • the second parameterized model can be based on the pre-existing designs and the updated designs.
  • the second parameterized model may define a second plurality of latent parameters and a second plurality of latent coordinates associated with each of the second plurality of latent parameters, so as to define a second plurality of new designs for the 3D object.
  • more new designs can be defined by the second parameterized model, at 404.
  • the remaining steps may also be repeated until no more edits or designs are needed, and the final CAD model 41 1 is generated.
  • any number of parameterized models may be constructed and revised during the process 400.
  • Post-processing may be performed on the final CAD model 41 1.
  • Post- processing may include, for example, translation of the final design or model 41 1 into instructions that may be executed by a 3D printer or other fabrication device to create a physical representation of the design or final CAD model 41 1.
  • Techniques for translation of a design to such instructions are device-specific and generally known in the art; thus, such techniques are not described in detail herein.
  • FIG. 6 illustrates an example of a computing environment within which embodiments of the present disclosure may be implemented.
  • a computing environment 600 includes a computer system 610 that may include a communication mechanism such as a system bus 621 or other communication mechanism for communicating information within the computer system 610.
  • the computer system 610 further includes one or more processors 620 coupled with the system bus 621 for processing the information.
  • the processors 620 may include one or more central processing units
  • a processor as described herein is a device for executing machine- readable instructions stored on a computer readable medium, for performing tasks and may comprise any one or combination of, hardware and firmware.
  • a processor may also comprise memory storing machine-readable instructions executable for performing tasks.
  • a processor acts upon information by manipulating, analyzing, modifying, converting or transmitting information for use by an executable procedure or an information device, and/or by routing the information to an output device.
  • a processor may use or comprise the capabilities of a computer, controller or microprocessor, for example, and be conditioned using executable instructions to perform special purpose functions not performed by a general purpose computer.
  • a processor may include any type of suitable processing unit including, but not limited to, a central processing unit, a microprocessor, a Reduced Instruction Set Computer (RISC) microprocessor, a RISC microprocessor, a RISC microprocessor, a RISC microprocessor, a RISC microprocessor, a RISC microprocessor, a RISC
  • processors 620 may have any suitable microarchitecture design that includes any number of constituent components such as, for example, registers, multiplexers, arithmetic logic units, cache controllers for controlling read/write operations to cache memory, branch predictors, or the like.
  • the microarchitecture design of the processor may be capable of supporting any of a variety of instruction sets.
  • a processor may be coupled (electrically and/or as comprising executable components) with any other processor enabling interaction and/or communication there-between.
  • a user interface processor or generator is a known element comprising electronic circuitry or software or a combination of both for generating display images or portions thereof.
  • a user interface comprises one or more display images enabling user interaction with a processor or other device.
  • the system bus 621 may include at least one of a system bus, a memory bus, an address bus, or a message bus, and may permit exchange of information (e.g., data (including computer-executable code), signaling, etc.) between various components of the system bus 621 .
  • information e.g., data (including computer-executable code), signaling, etc.
  • the system bus 621 may include, without limitation, a memory bus or a memory controller, a peripheral bus, an accelerated graphics port, and so forth.
  • the system bus 621 may be associated with any suitable bus architecture including, without limitation, an Industry Standard Architecture (ISA), a Micro Channel Architecture (MCA), an Enhanced ISA (EISA), a Video Electronics Standards Association (VESA) architecture, an Accelerated Graphics Port (AGP) architecture, a Peripheral Component Interconnects (PCI) architecture, a PCI-Express architecture, a Personal Computer Memory Card International Association (PCMCIA) architecture, a Universal Serial Bus (USB) architecture, and so forth.
  • ISA Industry Standard Architecture
  • MCA Micro Channel Architecture
  • EISA Enhanced ISA
  • VESA Video Electronics Standards Association
  • AGP Accelerated Graphics Port
  • PCI Peripheral Component Interconnects
  • PCMCIA Personal Computer Memory Card International Association
  • USB Universal Serial Bus
  • the computer system 610 may also include a system memory 630 coupled to the system bus 621 for storing information and instructions to be executed by processors 620.
  • the system memory 630 may include computer readable storage media in the form of volatile and/or nonvolatile memory, such as read only memory (ROM) 631 and/or random access memory (RAM) 632.
  • the RAM 632 may include other dynamic storage device(s) (e.g., dynamic RAM, static RAM, and synchronous DRAM).
  • the ROM 631 may include other static storage device(s) (e.g., programmable ROM, erasable PROM, and electrically erasable PROM).
  • system memory 630 may be used for storing temporary variables or other intermediate information during the execution of instructions by the processors 620.
  • a basic input/output system 633 (BIOS) containing the basic routines that help to transfer information between elements within computer system 610, such as during start-up, may be stored in the ROM 631.
  • RAM 632 may contain data and/or program modules that are immediately accessible to and/or presently being operated on by the processors 620.
  • System memory 630 may additionally include, for example, operating system 634, application programs 635, and other program modules 636.
  • Application programs 635 may also include a user portal for development of the application program, allowing input parameters to be entered and modified as necessary.
  • the operating system 634 may be loaded into the memory 630 and may provide an interface between other application software executing on the computer system 610 and hardware resources of the computer system 610. More specifically, the operating system 634 may include a set of computer-executable instructions for managing hardware resources of the computer system 610 and for providing common services to other application programs (e.g., managing memory allocation among various application programs). In certain example embodiments, the operating system 634 may control execution of one or more of the program modules depicted as being stored in the data storage 640.
  • the operating system 634 may include any operating system now known or which may be developed in the future including, but not limited to, any server operating system, any mainframe operating system, or any other proprietary or non-proprietary operating system.
  • the computer system 610 may also include a disk/media controller 643 coupled to the system bus 621 to control one or more storage devices for storing information and instructions, such as a magnetic hard disk 641 and/or a removable media drive 642 (e.g., floppy disk drive, compact disc drive, tape drive, flash drive, and/or solid state drive).
  • Storage devices 640 may be added to the computer system 610 using an appropriate device interface (e.g., a small computer system interface (SCSI), integrated device electronics (IDE), Universal Serial Bus (USB), or FireWire).
  • Storage devices 641 , 642 may be external to the computer system 610.
  • the computer system 610 may also include a field device interface 665 coupled to the system bus 621 to control a field device 666, such as a device used in a production line.
  • the computer system 610 may include a user input interface or GUI 661 , which may comprise one or more input devices, such as a keyboard, touchscreen, tablet and/or a pointing device, for interacting with a computer user and providing information to the processors 620.
  • the computer system 610 may perform a portion or all of the processing steps of embodiments of the invention in response to the processors 620 executing one or more sequences of one or more instructions contained in a memory, such as the system memory 630. Such instructions may be read into the system memory 630 from another computer readable medium of storage 640, such as the magnetic hard disk 641 or the removable media drive 642.
  • the magnetic hard disk 641 and/or removable media drive 642 may contain one or more data stores and data files used by
  • the data store 640 may include, but are not limited to, databases (e.g., relational, object-oriented, etc.), file systems, flat files, distributed data stores in which data is stored on more than one node of a computer network, peer-to-peer network data stores, or the like.
  • the data stores may store various types of data such as, for example, skill data, sensor data, or any other data generated in accordance with the embodiments of the disclosure.
  • Data store contents and data files may be encrypted to improve security.
  • the processors 620 may also be employed in a multi-processing arrangement to execute the one or more sequences of instructions contained in system memory 630. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions.
  • the computer system 610 may include at least one computer readable medium or memory for holding instructions programmed according to embodiments of the invention and for containing data structures, tables, records, or other data described herein.
  • the term“computer readable medium” as used herein refers to any medium that participates in providing instructions to the processors 620 for execution.
  • a computer readable medium may take many forms including, but not limited to, non-transitory, non-volatile media, volatile media, and transmission media.
  • Non-limiting examples of non-volatile media include optical disks, solid state drives, magnetic disks, and magneto-optical disks, such as magnetic hard disk 641 or removable media drive 642.
  • Non-limiting examples of volatile media include dynamic memory, such as system memory 630.
  • Non-limiting examples of transmission media include coaxial cables, copper wire, and fiber optics, including the wires that make up the system bus 621. Transmission media may also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.
  • 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
  • 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.
  • 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).
  • LAN local area network
  • WAN wide area network
  • Internet Service Provider for example, AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • programmable logic circuitry 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.
  • FPGA field-programmable gate arrays
  • PLA programmable logic arrays
  • the computing environment 600 may further include the computer system 610 operating in a networked environment using logical connections to one or more remote computers, such as remote computing device 680.
  • the network interface 670 may enable communication, for example, with other remote devices 680 or systems and/or the storage devices 641 , 642 via the network 671.
  • Remote computing device 680 may be a personal computer (laptop or desktop), a mobile device, a server, a router, a network PC, a peer device or other common network node, and typically includes many or all of the elements described above relative to computer system 610.
  • computer system 610 may include modem 672 for establishing communications over a network 671 , such as the Internet. Modem 672 may be connected to system bus 621 via user network interface 670, or via another appropriate mechanism.
  • Network 671 may be any network or system generally known in the art, including the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a direct connection or series of
  • the network 671 may be wired, wireless or a
  • Wired connections may be implemented using Ethernet, Universal Serial Bus (USB), RJ-6, or any other wired connection generally known in the art.
  • Wireless connections may be implemented using Wi-Fi, WiMAX, and Bluetooth, infrared, cellular networks, satellite or any other wireless connection methodology generally known in the art. Additionally, several networks may work alone or in communication with each other to facilitate communication in the network 671.
  • program modules, applications, computer- executable instructions, code, or the like depicted in FIG. 6 as being stored in the system memory 630 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.
  • 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 610, the remote device 680, and/or hosted on other computing device(s) accessible via one or more of the network(s) 671 may be provided to support functionality provided by the program modules, applications, or computer-executable code depicted in FIG.
  • functionality may be modularized differently such that processing described as being supported collectively by the collection of program modules depicted in FIG. 6 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.
  • 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.
  • any of the functionality described as being supported by any of the program modules depicted in FIG. 6 may be implemented, at least partially, in hardware and/or firmware across any number of devices.
  • the computer system 610 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 610 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 630, 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.
  • 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).
  • the functions noted in the block may occur out of the order noted in the Figures.
  • 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.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Geometry (AREA)
  • Materials Engineering (AREA)
  • Manufacturing & Machinery (AREA)
  • Chemical & Material Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Processing Or Creating Images (AREA)

Abstract

L'invention concerne un système et un procédé pour construire un modèle paramétré pour la conception assistée par ordinateur (CAO) d'un objet. Un système de CAO peut obtenir une pluralité de conceptions préexistantes. La pluralité de conceptions préexistantes peuvent représenter chacune un objet tridimensionnel (3D). Sur la base de la pluralité de conceptions préexistantes, le système de CAO peut construire un modèle paramétré d'un espace de conception correspondant à l'objet 3D. Le modèle paramétré peut définir une pluralité de paramètres latents et une pluralité de coordonnées latentes associées à chaque paramètre latent de la pluralité de paramètres latents, de façon à définir une pluralité de nouvelles conceptions pour l'objet 3D. Le modèle paramétré peut être construit par entraînement d'un réseau antagoniste génératif (GAN) à l'aide de la pluralité de conceptions préexistantes.
PCT/US2019/043542 2018-07-27 2019-07-26 Synthèse et optimisation de conceptions d'objet 3d à l'aide de conceptions existantes WO2020023811A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201862711026P 2018-07-27 2018-07-27
US62/711,026 2018-07-27

Publications (1)

Publication Number Publication Date
WO2020023811A1 true WO2020023811A1 (fr) 2020-01-30

Family

ID=67544465

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2019/043542 WO2020023811A1 (fr) 2018-07-27 2019-07-26 Synthèse et optimisation de conceptions d'objet 3d à l'aide de conceptions existantes

Country Status (1)

Country Link
WO (1) WO2020023811A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113221278A (zh) * 2021-05-14 2021-08-06 南京莱斯电子设备有限公司 一种车载光电平台照准架轻量化方法
CN114297176A (zh) * 2021-12-15 2022-04-08 东南大学 基于人工智能的中国古典园林假山自动生成方法及系统
DE102021129531A1 (de) 2021-11-12 2023-05-17 Dr. Ing. H.C. F. Porsche Aktiengesellschaft Verfahren zur Entwicklung eines technischen Bauteils

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018022752A1 (fr) * 2016-07-27 2018-02-01 James R. Glidewell Dental Ceramics, Inc. Automatisation de la cao dentaire par un apprentissage en profondeur

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018022752A1 (fr) * 2016-07-27 2018-02-01 James R. Glidewell Dental Ceramics, Inc. Automatisation de la cao dentaire par un apprentissage en profondeur

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
CEM C TUTUM ET AL: "Functional Generative Design: An Evolutionary Approach to 3D-Printing", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 19 April 2018 (2018-04-19), XP080872549, DOI: 10.1145/3205455.3205635 *
EDWARD SMITH ET AL: "Improved Adversarial Systems for 3D Object Generation and Reconstruction", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 29 July 2017 (2017-07-29), pages 1 - 10, XP081294656 *
JERRY LIU ET AL: "Interactive 3D Modeling with a Generative Adversarial Network", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 16 June 2017 (2017-06-16), XP080770297, DOI: 10.1109/3DV.2017.00024 *
JIAJUN WU ET AL: "Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 24 October 2016 (2016-10-24), XP080816424 *
YONGGYUN YU ET AL: "Deep learning for determining a near-optimal topological design without any iteration", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 13 January 2018 (2018-01-13), XP081195456 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113221278A (zh) * 2021-05-14 2021-08-06 南京莱斯电子设备有限公司 一种车载光电平台照准架轻量化方法
CN113221278B (zh) * 2021-05-14 2024-01-23 南京莱斯电子设备有限公司 一种车载光电平台照准架轻量化方法
DE102021129531A1 (de) 2021-11-12 2023-05-17 Dr. Ing. H.C. F. Porsche Aktiengesellschaft Verfahren zur Entwicklung eines technischen Bauteils
CN114297176A (zh) * 2021-12-15 2022-04-08 东南大学 基于人工智能的中国古典园林假山自动生成方法及系统

Similar Documents

Publication Publication Date Title
US10937211B2 (en) Automated parametrization of floor-plan sketches for multi-objective building optimization tasks
US10339266B2 (en) Mechanisms for constructing spline surfaces to provide inter-surface continuity
US10216172B2 (en) Functional 3-D: optimized lattice partitioning of solid 3-D models to control mechanical properties for additive manufacturing
US8799837B2 (en) Optimizing a netlist circuit representation by leveraging binary decision diagrams to perform rewriting
WO2020023811A1 (fr) Synthèse et optimisation de conceptions d'objet 3d à l'aide de conceptions existantes
Cuillière et al. Integration of CAD, FEA and topology optimization through a unified topological model
JP2022036024A (ja) パラメータ化された３ｄモデルを出力するニューラルネットワーク
WO2020055595A1 (fr) Système de conception assistée par ordinateur pour la représentation basée sur un programme de structures en treillis
Keshavarzi et al. Sketchopt: Sketch-based parametric model retrieval for generative design
Shi et al. Cranial implant design through multiaxial slice inpainting using deep learning
JP2002279005A (ja) 三次元解析モデル生成方法、装置、三次元解析モデル生成プログラム及びその記録媒体
WO2021163282A1 (fr) Système de conception détaillée pour structures en treillis
US10943037B2 (en) Generating a CAD model from a finite element mesh
WO2021025906A1 (fr) Optimisation de topologie à contraintes de surplomb locales pour impression 3d
Davis et al. The flexibility of logic programming
EP3647972A1 (fr) Procédé d'entraînement d'un réseau de neurones à convolution pour effectuer la simulation d'un produit physique, procédé correspondant pour effectuer la simulation d'un produit physique et réseau de neurones à convolution
Potter et al. Ordered line integral methods for solving the eikonal equation
Lai et al. Small blend suppression from B-rep models in computer-aided engineering analysis
WO2020056107A1 (fr) Pipeline de simulation automatisée pour conception assistée par ordinateur générée par simulation rapide
WO2020005274A1 (fr) Suivi d'une optimisation de topologie pour construire une topologie modifiable
WO2020068364A1 (fr) Solveurs itératifs ayant une convergence accélérée
US20230305526A1 (en) Subdivision-based surface editor
Crozet et al. Fast computation of local minimal distances between CAD models for dynamics simulation
Fayolle et al. Rounding, filleting and smoothing of implicit surfaces
US20230297743A1 (en) Deep neural networks for synthesis and optimization of smooth surfaced 3d objects

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19750017

Country of ref document: EP

Kind code of ref document: A1