Digital twin and particle swarm iterative feedback industrial design optimization method and device

Abstract

The application discloses an industrial design optimization method and device based on digital twinning and particle swarm iteration feedback. The method comprises the following steps: mapping a design parameter space associated with a digital twinning model of a product to be optimized into an initial population of a particle swarm optimization algorithm to complete initialization of a computing environment; performing multi-physical field simulation on the digital twinning model, and performing first-stage particle swarm optimization according to obtained simulation indexes to obtain a preliminary optimization solution set; performing consistency simulation verification on the preliminary optimization solution set on the same digital twinning model, and generating a target function weight update item and / or a constraint boundary update item of a simulation boundary condition according to engineering feedback information and simulation verification results; performing second-stage particle swarm iteration optimization based on the update items, and outputting an updated design parameter set; and backfilling the updated design parameter set to the same digital twinning model to perform verification, and outputting an engineering parameter set that passes the verification.

Description

Technical Field

[0001] This application relates to the field of industrial design, and more specifically, to an industrial design optimization method, apparatus, and storage medium based on digital twins and particle swarm iteration feedback. Background Technology

[0002] As the complexity of industrial design objects increases in terms of geometry, material selection, and manufacturing processes, the design phase often requires a joint trade-off among multiple physical indicators such as structural strength, thermal response, and vibration performance. Without a unified virtual prototype verification object and repeatable simulation evaluation criteria, design parameter adjustments typically rely on physical prototype fabrication and multiple rounds of manual comparison, making it difficult to develop a parameter set that can be directly used for subsequent engineering analysis during the design phase.

[0003] Current industrial design optimization typically relies on physical prototype fabrication, single-round simulation verification, or localized empirical corrections. This approach makes it difficult to continuously verify different parameter combinations on the same design model, and it also struggles to stably map the combined changes in geometric, material, and process parameters into a comprehensive evaluation of structural, thermal, and vibrational performance. This results in a lack of a consistent engineering loop between the parameter update process and the verification results.

[0004] Particle swarm optimization (PSO) algorithms can be used to search for candidate design parameters within a given parameter space. However, existing PSO processes typically only iterate based on pre-defined objective functions and constraints, lacking a mechanism to further convert simulation verification results into objective function weight update terms or constraint boundary update terms. When performance deviations still exist after verification, existing methods often require manual resetting of optimization conditions.

[0005] Digital twin technology can build virtual prototypes based on CAD (Computer-Aided Design) geometric data and perform multiphysics simulation analysis of structure, thermal, and vibration in virtual space. However, existing digital twin applications are mostly used for static simulation demonstration, one-way condition monitoring, or one-time parameter verification. Summary of the Invention

[0006] This application provides an industrial design optimization method, apparatus, storage medium, and electronic device based on digital twin and particle swarm iteration feedback. The simulation verification results after the first stage of optimization can be converted into executable weight update rules and / or constraint boundary update rules on the same virtual prototype, and the second stage of particle swarm iteration optimization is performed under the updated search conditions to output a set of verified engineering parameters.

[0007] According to one aspect of the embodiments of this application, an industrial design optimization method based on digital twins and particle swarm optimization iterative feedback is provided, comprising: The design parameter space associated with the digital twin model of the product to be optimized is mapped to the initial population of the particle swarm optimization algorithm, thus completing the initialization of the computing environment. Multiphysics simulations are performed on the digital twin model, and a first-stage particle swarm optimization is conducted based on the obtained simulation indices to obtain a preliminary optimized solution set. The initial optimized solution set is subjected to consistency simulation verification on the same digital twin model, and the objective function weight update term and / or the constraint boundary update term of the simulation boundary condition are generated based on the engineering feedback information and the simulation verification results. Based on the updated terms, a second-stage particle swarm optimization is performed to output the updated design parameter set. The updated design parameter set is backfilled into the same digital twin model for verification, and the verified engineering parameter set is output.

[0008] In one possible implementation, the simulation metrics include at least one of Von Mises equivalent stress, maximum displacement deformation, steady-state temperature field distribution, and vibration modal frequency, and the simulation verification is based on comparing the simulation metrics with a preset performance threshold or safety margin.

[0009] In one possible implementation, the preliminary optimized solution set is subjected to consistency simulation verification on the same digital twin model, and an objective function weight update term is generated based on engineering feedback information and simulation verification results, including: If any of the simulation metrics deviates from the corresponding preset performance threshold or safety margin, the simulation metric with the deviation will be marked as a metric to be corrected. Increase the weight coefficient of the index to be corrected in the objective function so that the particle swarm optimization in the second stage prioritizes correcting the performance deviation corresponding to the index to be corrected.

[0010] In one possible implementation, the preliminary optimized solution set is subjected to consistency simulation verification on the same digital twin model, and constraint boundary update terms for the simulation boundary conditions are generated based on engineering feedback information and simulation verification results, including: If any of the simulation metrics does not meet the corresponding preset performance threshold or safety margin, the upper limit threshold and / or lower limit threshold of the constraint term corresponding to the simulation metric are tightened or relaxed and updated, and the updated threshold is used as the constraint condition for the second stage particle swarm iterative optimization.

[0011] In one possible implementation, the engineering feedback information includes at least one of assembly clearance space constraints and modal frequency clearance intervals.

[0012] In one possible implementation, the step of backfilling the updated design parameter set into the same digital twin model for verification and outputting a verified set of engineering parameters includes: After the updated design parameter set is backfilled into the same digital twin model, multiphysics simulation verification is performed again. Generate performance evaluation results that include the verification results corresponding to the simulation indicators, as the basis for outputting the final engineering parameter set.

[0013] In one possible implementation, the digital twin model includes a manufacturing analysis layer; The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback also includes: Before outputting the final set of engineering parameters, a consistency check is performed. The manufacturing analysis layer performs a structural topology check on the backfilled scheme to ensure that the design changes do not cause interference in the assembly space and that all geometric corrections meet the preset molding process limitations.

[0014] In one possible implementation, the digital twin model includes a test analytics layer; The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback also includes: During the verification process of backfilling the updated design parameter set into the same digital twin model, in-depth structural integrity verification is performed. The test analysis layer performs fatigue damage accumulation simulation under full life cycle conditions on the backfill scheme to verify the reliability of the physical structure corresponding to the engineering parameter set under long-term repetitive motion conditions.

[0015] According to another aspect of the embodiments of this application, an industrial design optimization device based on digital twins and particle swarm optimization iterative feedback is provided, comprising: The computing environment initialization module is used to map the design parameter space associated with the digital twin model of the product to be optimized to the initial population of the particle swarm optimization algorithm, thus completing the initialization of the computing environment. The preliminary optimization solution set determination module is used to perform multiphysics simulation on the digital twin model and perform a first-stage particle swarm optimization based on the obtained simulation indexes to obtain a preliminary optimization solution set. The update term determination module is used to perform consistency simulation verification on the same digital twin model for the preliminary optimization solution set, and generate objective function weight update terms and / or simulation boundary constraint update terms based on engineering feedback information and simulation verification results. The updated design parameter set output module is used to perform a second-stage particle swarm optimization based on the updated item and output the updated design parameter set. The engineering parameter set verification module is used to backfill the updated design parameter set into the same digital twin model for verification, and output the verified engineering parameter set.

[0016] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program, when executed, performs the industrial design optimization method of digital twin and particle swarm iterative feedback provided in any embodiment of this application.

[0017] According to another aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute, through the computer program, the industrial design optimization method of digital twin and particle swarm iterative feedback provided in any embodiment of this application.

[0018] This application provides an industrial design optimization method, apparatus, storage medium, and electronic device based on digital twin and particle swarm optimization iterative feedback. By mapping the design parameter space to the initial population of the particle swarm optimization algorithm, the computational environment is initialized. Multiphysics simulation is performed on the digital twin model to obtain simulation indicators for evaluating the current scheme. This allows the simulation verification results after the first-stage optimization to be converted into executable weight update rules and / or constraint boundary update rules on the same virtual prototype. Under the updated search conditions, the second-stage particle swarm iterative optimization is performed to output a verified set of engineering parameters. This solves the problems in existing technologies where industrial design parameter optimization relies on single-round simulation or manual resetting of conditions, and it is difficult to convert verification results into second-stage optimization inputs on the same virtual prototype. It reduces the risk of parameter inconsistency caused by switching between different models, achieves targeted correction, improves the consistency between the output engineering parameter set and the preset service conditions, and performs post-hoc verification of assembly interference risks and process incompatibility risks caused by geometric corrections. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of an industrial design optimization method using digital twins and particle swarm optimization with iterative feedback, provided in an embodiment of this application. Figure 2 This is a schematic diagram of the structure of an industrial design optimization device based on digital twin and particle swarm iteration feedback provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating the structure of the digital twin model provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 5 This is a flowchart of another industrial design optimization method based on digital twins and particle swarm iteration feedback provided in the embodiments of this application. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0024] This embodiment provides an industrial design optimization method based on digital twins and particle swarm optimization, applicable to industrial design scenarios. Figure 1 A flowchart of an industrial design optimization method using digital twins and particle swarm optimization iterative feedback, provided for embodiments of this application, is included in the following steps: Step 110: Map the design parameter space associated with the digital twin model of the product to be optimized to the initial population of the particle swarm optimization algorithm, and complete the initialization of the computing environment; Among them, a digital twin model refers to a three-dimensional virtual prototype built based on the CAD geometric data of the product to be optimized, used to carry out design parameter backfilling, multiphysics simulation verification, and optimization result verification. For example... Figure 3The diagram illustrates the structure of a digital twin model. This model may include a design analysis layer, a manufacturing analysis layer, a testing analysis layer, and an operation and maintenance analysis layer, used to perform corresponding simulation analysis and verification on parameter combinations in the design parameter space. Before step 110, a digital twin model of a 3D virtual prototype of the product to be optimized can be constructed, and an associated design parameter space and simulation boundary conditions can be established. The design parameter space refers to a set of parameter values ​​consisting of at least two of the following: geometric parameters, material parameters, and process parameters, used to limit the search range of the particle swarm optimization algorithm. The design parameter space may include at least two of the following: geometric parameters, material parameters, and process parameters. The geometric parameters include at least wall thickness parameters and stiffener size parameters; the material parameters include at least material elastic modulus parameters and thermal conductivity parameters; and the process parameters include at least weight-reducing hole distribution parameters. Simulation boundary conditions refer to the geometric constraints, environmental conditions, and external loads used when performing multiphysics simulations on the digital twin model. The simulation boundary conditions may include geometric constraints, environmental conditions, and external loads. The geometric constraints include at least fixed support constraints and kinematic pair limits. The environmental conditions include at least ambient temperature, convective heat transfer coefficient, and atmospheric pressure. The external loads include at least one or more of transient impact forces, periodic vibration loads, and uniform pressure distributions. Initialization of the computational environment refers to the process of initially configuring the initial population, particle position vectors, velocity vectors, and iterative control parameters for the particle swarm optimization algorithm.

[0025] Step 120: Perform multiphysics simulation on the digital twin model, and perform the first stage of particle swarm optimization based on the obtained simulation index to obtain a preliminary optimized solution set; Among them, simulation indices refer to one or more of the structural performance indices, thermal performance indices, and vibration performance indices obtained through multiphysics simulation and used to evaluate the performance of candidate design schemes. The preliminary optimized solution set refers to the set of candidate design parameter combinations and their corresponding simulation index results output by the first-stage particle swarm optimization.

[0026] Step 130: Perform consistency simulation verification on the same digital twin model for the preliminary optimized solution set, and generate objective function weight update term and / or simulation boundary condition constraint boundary update term based on engineering feedback information and simulation verification results; Consistency simulation verification involves performing a unified evaluation caliber simulation verification on the preliminary optimized solution set under the same digital twin model and preset simulation boundary conditions to generate verification deviations that can be used for updating term generation. Objective function weight update terms refer to update objects generated based on simulation verification results, used to adjust the weight coefficients of corresponding performance indicators in the objective function. Constraint boundary update terms refer to update objects generated based on simulation verification results, used to adjust the upper and / or lower thresholds of corresponding constraint terms. Engineering feedback information refers to engineering constraint information input in structured record form that can jointly generate update terms with the simulation verification results. By enabling multi-physics simulation indicators to participate in parameter evaluation, the consistency between the output engineering parameter set and the preset service conditions can be improved. By converting simulation verification results into objective function weight update terms and / or constraint boundary update terms, the second-stage particle swarm optimization can perform targeted corrections for verification deviation terms.

[0027] Step 140: Perform the second stage of particle swarm optimization based on the updated terms, and output the updated design parameter set; By completing the first stage of particle swarm optimization, consistency simulation verification, update term generation, and the second stage of particle swarm iterative optimization on the same digital twin virtual model, the risk of parameter inconsistency caused by switching between different models can be reduced.

[0028] Step 150: Fill the updated design parameter set back into the same digital twin model to perform verification, and output the verified engineering parameter set.

[0029] The validated engineering parameter set refers to the combination of design parameters that meets the output conditions after backfilling verification. During the backfilling verification phase, the performance evaluation results are used to record whether the updated design parameter set meets the preset performance threshold or safety margin. The performance evaluation results include at least the parameter set number, simulation index name, simulation value, corresponding threshold or safety margin, and a pass / fail flag.

[0030] In one possible implementation, the simulation metrics include at least one of Von Mises equivalent stress, maximum displacement deformation, steady-state temperature field distribution, and vibration modal frequency, and the simulation verification is based on comparing the simulation metrics with a preset performance threshold or safety margin.

[0031] In one possible implementation, the preliminary optimized solution set is subjected to consistency simulation verification on the same digital twin model, and an objective function weight update term is generated based on engineering feedback information and simulation verification results, including: If any of the simulation metrics deviates from the corresponding preset performance threshold or safety margin, the simulation metric with the deviation will be marked as a metric to be corrected. Increase the weight coefficient of the index to be corrected in the objective function so that the particle swarm optimization in the second stage prioritizes correcting the performance deviation corresponding to the index to be corrected.

[0032] In one possible implementation, the preliminary optimized solution set is subjected to consistency simulation verification on the same digital twin model, and constraint boundary update terms for the simulation boundary conditions are generated based on engineering feedback information and simulation verification results, including: If any of the simulation metrics does not meet the corresponding preset performance threshold or safety margin, the upper limit threshold and / or lower limit threshold of the constraint term corresponding to the simulation metric are tightened or relaxed and updated, and the updated threshold is used as the constraint condition for the second stage particle swarm iterative optimization.

[0033] In one possible implementation, the engineering feedback information includes at least one of assembly clearance space constraints and modal frequency clearance intervals.

[0034] The engineering feedback information can be input in the form of a structured record, including at least a feedback type field, a target performance index field, a target area field, a constraint value field, and an execution priority field; wherein, the assembly avoidance space constraint is used to limit the space envelope that needs to be retained in the assembly state, and the modal frequency avoidance interval is used to limit the range of vibration frequencies that need to be avoided.

[0035] In one possible implementation, the step of backfilling the updated design parameter set into the same digital twin model for verification and outputting a verified set of engineering parameters includes: After the updated design parameter set is backfilled into the same digital twin model, multiphysics simulation verification is performed again. Generate performance evaluation results that include the verification results corresponding to the simulation indicators, as the basis for outputting the final engineering parameter set.

[0036] In one possible implementation, the digital twin model includes a manufacturing analysis layer; The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback also includes: Before outputting the final set of engineering parameters, a consistency check is performed. The manufacturing analysis layer performs a structural topology check on the backfilled scheme to ensure that the design changes do not cause interference in the assembly space and that all geometric corrections meet the preset molding process limitations.

[0037] By adding final verification and consistency checks before output, post-verification can be performed to address assembly interference risks and process incompatibility risks caused by geometric corrections.

[0038] In one alternative implementation, the digital twin model includes a test analytics layer; The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback also includes: During the verification process of backfilling the updated design parameter set into the same digital twin model, in-depth structural integrity verification is performed. The test analysis layer performs fatigue damage accumulation simulation under full life cycle conditions on the backfill scheme to verify the reliability of the physical structure corresponding to the engineering parameter set under long-term repetitive motion conditions.

[0039] By adding full-life-cycle fatigue damage accumulation simulation when needed, the reliability of the physical structure under long-term repetitive motion conditions can be further verified.

[0040] In an exemplary embodiment using the design of an industrial robot linkage as an example, the method uses the same digital twin virtual prototype as a unified object for the first stage of particle swarm optimization, consistency simulation verification, update term generation, the second stage of particle swarm iterative optimization, and final verification. Its basic process is as follows: Figure 5 As shown, it includes: CAD modeling and digital twin model mapping; the first stage: automated optimization; dynamic feedback reconstruction; the second stage: feedback-driven reinforcement; outputting optimal parameters and virtual verification.

[0041] The original CAD geometric data of the industrial robot links are imported into a digital twin platform to construct a corresponding 3D virtual prototype. The digital twin model includes a design analysis layer, a manufacturing analysis layer, and a test analysis layer. The design analysis layer receives geometric and material parameters and backfills them; the manufacturing analysis layer verifies whether the updated design parameters meet the preset molding process limitations; and the test analysis layer performs multiphysics simulation verification on the updated design parameters. Through this combination of modules, the virtual prototype maintains consistency with the product to be optimized in terms of geometric topology, assembly relationships, and material constitutive relations.

[0042] Simulation boundary conditions corresponding to the service state of the connecting rod are set on the digital twin model. These boundary conditions include: geometric constraints to define the fixed boundary and kinematic pair limits at the connecting flange; environmental conditions to define the ambient temperature, convective heat transfer coefficient, and atmospheric pressure; and external loads to define the inertial force and torsional load generated by acceleration. In this embodiment, the connecting flange is set to fully constrained and fixed, the inertial force is set to 500 N, the torsional load is set to 30 Nm, the ambient temperature gradient is set to -20℃ to 60℃, and the convective heat transfer coefficient and atmospheric pressure are used as preset environmental parameters to ensure that subsequent multiphysics simulations can reflect the mechanical, thermal, and vibrational responses of the connecting rod under complex operating conditions.

[0043] The geometric, material, and manufacturing parameters of the connecting rod structure are mapped to the initial population for a particle swarm optimization (PSO) algorithm. The geometric parameters include at least the wall thickness of the connecting rod mid-section and the thickness of the stiffeners; the material parameters include at least the elastic modulus and thermal conductivity; and the manufacturing parameters include at least the density of the weight-reducing holes. After setting preset upper and lower bounds for each parameter, an initial particle swarm is generated. The particle position vector, velocity vector, and iteration control parameters for each particle are then initialized to complete the computational environment initialization for the PSO algorithm, ensuring that the subsequent first-stage particle swarm optimization occurs within the preset search space.

[0044] Based on the linkage parameter optimization objective, multiphysics simulations are performed on a digital twin model to obtain simulation indices including at least VonMises equivalent stress, maximum displacement deformation, steady-state temperature field distribution, and the frequencies of the first six vibration modes. A first-stage particle swarm optimization is then performed based on these indices to obtain a preliminary optimized solution set. Each set of candidate design parameters in the preliminary optimized solution set is associated with and stored in relation to the corresponding simulation index results for use in subsequent consistency simulation verification and update term generation.

[0045] In this embodiment, structural strength verification is performed using a safety margin criterion, where the safety margin is the ratio of the allowable stress of the material to the maximum Von Mises equivalent stress, with a lower limit of 1.5. Vibration performance verification is based on whether the frequencies of the first to sixth modalities fall within a preset avoidance range. Thermal performance verification is based on whether the steady-state temperature of key components exceeds a preset temperature rise threshold. The above values ​​are only used as verification criteria in this embodiment.

[0046] The candidate design parameters from the preliminary optimized solution set are backfilled into the same digital twin model. Consistency simulation verification is performed under unified simulation boundary conditions and unified evaluation criteria, and the simulation verification results are compared with preset performance thresholds or safety margins. When any simulation index deviates from the corresponding preset performance threshold or safety margin, the simulation index is marked as an index to be corrected, and corresponding objective function weight update terms and / or constraint boundary update terms are generated.

[0047] In this embodiment, when the structural strength corresponding to the index to be corrected is insufficient, the weight coefficient of the structural strength index in the objective function is increased; when the vibration performance corresponding to the index to be corrected does not meet the frequency avoidance requirements, the upper and / or lower threshold values ​​of the corresponding modal frequency constraint term are updated; when the thermal performance corresponding to the index to be corrected exceeds the temperature rise threshold, the threshold range of the corresponding temperature constraint term is updated. Under the updated objective function weights and / or constraint boundary conditions, updated inputs are provided for the second-stage particle swarm optimization iteration.

[0048] In this embodiment, the engineering feedback information used to generate the update terms is input in a structured record format, including at least a feedback type field, a target performance index field, a target region field, a constraint value field, and an execution priority field. Specifically, the assembly avoidance space constraint defines the spatial envelope that the link must retain in its assembled state, and the modal frequency avoidance interval defines the range of vibration frequencies to be avoided. The engineering feedback information, together with the simulation verification results, participates in the generation of the objective function weight update term and / or constraint boundary update term.

[0049] Using the updated terms, a second-stage particle swarm optimization is performed under the updated objective function weights and / or constraint boundary conditions to obtain the updated design parameter set. In this embodiment, the second-stage particle swarm optimization is continued on the same digital twin model to avoid parameter mapping inconsistencies caused by changing the simulation object.

[0050] The updated design parameter set is then backfilled into the same digital twin model, final verification is performed, and a verified engineering parameter set is output. In one embodiment, the final verification includes re-performing multiphysics simulation verification and generating performance evaluation results. The performance evaluation results include at least the parameter set number, simulation index name, simulation value, corresponding threshold or safety margin, and pass / fail flag, and are stored in association with the updated design parameter set as the basis for outputting the final engineering parameter set.

[0051] Before outputting the final set of engineering parameters, the manufacturing analysis layer of the digital twin model performs consistency checks and structural topology verification on the backfilled solution to ensure that design changes do not cause assembly space interference and that all geometric corrections comply with preset molding process constraints. When assembly interference or process incompatibility is detected, the corresponding parameter combination can be marked as an invalid solution, and the second stage of particle swarm optimization can continue.

[0052] During the process of backfilling the updated design parameter set into the same digital twin model, performing final verification, and outputting the verified engineering parameter set, the test analysis layer of the digital twin model performs fatigue damage accumulation simulation under full life cycle conditions on the backfill scheme to verify the reliability of the physical structure corresponding to the engineering parameter set under long-term repetitive motion conditions. In this embodiment, fatigue verification under 1 million consecutive reciprocating motion conditions is used as an example of full life cycle condition verification; this value is only used as a condition for the embodiment.

[0053] Under the corresponding working conditions in this embodiment, the final output set of engineering parameters achieved a 25% weight reduction and a 15% increase in structural stiffness compared to the original design. The above results only represent the test results of this embodiment under the corresponding working conditions and verification criteria, and do not constitute a limitation on the scope of protection of this invention.

[0054] According to another aspect of the embodiments of this application, Figure 2 A schematic diagram of an industrial design optimization device based on digital twin and particle swarm optimization iterative feedback provided in this application embodiment is shown below. Figure 2 As shown, the device includes a computational environment initialization module 210, a preliminary optimization solution set determination module 220, an update item determination module 230, an updated design parameter set output module 240, and an engineering parameter set verification module 250, wherein: The computing environment initialization module 210 is used to map the design parameter space associated with the digital twin model of the product to be optimized to the initial population of the particle swarm optimization algorithm, thereby completing the initialization of the computing environment. The preliminary optimization solution set determination module 220 is used to perform multiphysics simulation on the digital twin model and perform a first-stage particle swarm optimization based on the obtained simulation index to obtain a preliminary optimization solution set. The update term determination module 230 is used to perform consistency simulation verification on the same digital twin model for the preliminary optimization solution set, and generate objective function weight update terms and / or simulation boundary constraint update terms based on engineering feedback information and simulation verification results. The updated design parameter set output module 240 is used to perform a second-stage particle swarm iterative optimization based on the updated item and output the updated design parameter set. The engineering parameter set verification module 250 is used to backfill the updated design parameter set into the same digital twin model for verification, and output the verified engineering parameter set.

[0055] In one possible implementation, the simulation metrics include at least one of Von Mises equivalent stress, maximum displacement deformation, steady-state temperature field distribution, and vibration modal frequency, and the simulation verification is based on comparing the simulation metrics with a preset performance threshold or safety margin.

[0056] In one possible implementation, the update item determination module 230 includes: The indicator to be corrected marking unit is used to mark the simulation indicator with the verification deviation as an indicator to be corrected if any of the simulation indicators shows a verification deviation relative to the corresponding preset performance threshold or the safety margin. The weight coefficient adjustment unit is used to increase the weight coefficient of the index to be corrected in the objective function, so that the second-stage particle swarm iteration optimization prioritizes the correction of the performance deviation corresponding to the index to be corrected.

[0057] In one possible implementation, the update item determination module 230 includes: The constraint update unit is used to tighten or relax the upper limit threshold and / or lower limit threshold of the constraint item corresponding to the simulation index if any of the simulation index does not meet the corresponding preset performance threshold or safety margin, and use the updated threshold as the constraint condition for the second stage particle swarm iterative optimization.

[0058] In one possible implementation, the engineering feedback information includes at least one of assembly clearance space constraints and modal frequency clearance intervals.

[0059] In one possible implementation, the engineering parameter set verification module 250 is used for: After the updated design parameter set is backfilled into the same digital twin model, multiphysics simulation verification is performed again. Generate performance evaluation results that include the verification results corresponding to the simulation indicators, as the basis for outputting the final engineering parameter set.

[0060] In one possible implementation, the digital twin model includes a manufacturing analysis layer; The industrial design optimization device based on digital twin and particle swarm iteration feedback also includes: The consistency check module is used to perform a consistency check before outputting the final engineering parameter set. The manufacturing analysis layer performs a structural topology check on the backfilled scheme to ensure that the design changes do not cause interference in the assembly space and that all geometric corrections meet the preset molding process limitations.

[0061] In one possible implementation, the digital twin model includes a test analytics layer; The industrial design optimization device based on digital twin and particle swarm iteration feedback also includes: The structural integrity verification module is used to perform in-depth structural integrity verification during the process of backfilling the updated design parameter set into the same digital twin model for verification. The test analysis layer performs fatigue damage accumulation simulation under full life cycle conditions on the backfill scheme to verify the reliability of the physical structure corresponding to the engineering parameter set under long-term repetitive motion conditions.

[0062] According to another aspect of the embodiments of this application, Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 4 As shown, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of processors 410 in the electronic device can be one or more. Figure 4 Taking a processor 410 as an example; the processor 410, memory 420, input device 430, and output device 440 in the electronic device can be connected via a bus or other means. Figure 4Taking the example of a connection between China and Israel via a bus.

[0063] The memory 420, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the digital twin and particle swarm iterative feedback industrial design optimization method in the embodiments of this application (e.g., the computing environment initialization module 210, the preliminary optimization solution set determination module 220, the update item determination module 230, the updated design parameter set output module 240, and the engineering parameter set verification module 250 in the digital twin and particle swarm iterative feedback industrial design optimization device). The processor 410 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 420, thereby realizing the aforementioned digital twin and particle swarm iterative feedback industrial design optimization method.

[0064] The memory 420 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 420 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 420 may further include memory remotely located relative to the processor 410, which can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0065] Input device 430 can be used to receive input digital or character information, and generate key signal inputs related to user settings and function control of the electronic device. It can also be a camera for acquiring images and a sound pickup device for acquiring audio data. Output device 440 may include display devices such as a screen, and audio devices such as a speaker. It should be noted that the specific composition of input device 430 and output device 440 can be set according to actual conditions. Processor 410 executes various functional applications and data processing of the electronic device by running software programs, instructions, and modules stored in memory 420.

[0066] According to another aspect of the embodiments of this application, the embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored program, wherein the program, when executed, performs the following digital twin and particle swarm iterative feedback industrial design optimization method, including: The design parameter space associated with the digital twin model of the product to be optimized is mapped to the initial population of the particle swarm optimization algorithm, thus completing the initialization of the computing environment. Multiphysics simulations are performed on the digital twin model, and a first-stage particle swarm optimization is conducted based on the obtained simulation indices to obtain a preliminary optimized solution set. The initial optimized solution set is subjected to consistency simulation verification on the same digital twin model, and the objective function weight update term and / or the constraint boundary update term of the simulation boundary condition are generated based on the engineering feedback information and the simulation verification results. Based on the updated terms, a second-stage particle swarm optimization is performed to output the updated design parameter set. The updated design parameter set is backfilled into the same digital twin model for verification, and the verified engineering parameter set is output.

[0067] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the method operations described above, but can also perform related operations in the industrial design optimization method of digital twin and particle swarm iterative feedback provided in any embodiment of this application.

[0068] Based on the above description of the implementation methods, those skilled in the art can clearly understand that this application can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0069] It is worth noting that in the above embodiments of the industrial design optimization device based on digital twin and particle swarm iteration feedback, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of this application.

[0070] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An industrial design optimization method using digital twins and particle swarm optimization with iterative feedback, characterized in that, include: The design parameter space associated with the digital twin model of the product to be optimized is mapped to the initial population of the particle swarm optimization algorithm, thus completing the initialization of the computing environment. Multiphysics simulations are performed on the digital twin model, and a first-stage particle swarm optimization is conducted based on the obtained simulation indices to obtain a preliminary optimized solution set. The initial optimized solution set is subjected to consistency simulation verification on the same digital twin model, and the objective function weight update term and / or the constraint boundary update term of the simulation boundary condition are generated based on the engineering feedback information and the simulation verification results. Based on the updated terms, a second-stage particle swarm optimization is performed to output the updated design parameter set. The updated design parameter set is then backfilled into the same digital twin model for verification, and the verified engineering parameter set is output. The process involves performing consistency simulation verification on the same digital twin model for the preliminary optimized solution set, and generating an objective function weight update term based on engineering feedback information and simulation verification results, including: If any of the simulation metrics deviates from the corresponding preset performance threshold or safety margin, the simulation metric that deviates from the verification will be marked as a metric to be corrected. Increase the weight coefficient of the index to be corrected in the objective function so that the second-stage particle swarm iteration optimization prioritizes the correction of the performance deviation corresponding to the index to be corrected. The preliminary optimized solution set is subjected to consistency simulation verification on the same digital twin model. Based on the engineering feedback information and simulation verification results, constraint boundary update terms for simulation boundary conditions are generated, including: if any simulation index does not meet the corresponding preset performance threshold or safety margin, the upper limit threshold and / or lower limit threshold of the constraint term corresponding to the simulation index are tightened or relaxed and updated, and the updated threshold is used as the constraint condition for the second stage particle swarm iterative optimization.

2. The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback as described in claim 1, characterized in that, The simulation metrics include at least one of Von Mises equivalent stress, maximum displacement deformation, steady-state temperature field distribution, and vibration modal frequency. The simulation verification is based on comparing the simulation metrics with a preset performance threshold or safety margin.

3. The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback as described in claim 1, characterized in that, The engineering feedback information includes at least one of the following: assembly clearance space constraints and modal frequency clearance ranges.

4. The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback as described in claim 1, characterized in that, The step of backfilling the updated design parameter set into the same digital twin model for verification and outputting the verified engineering parameter set includes: After the updated design parameter set is backfilled into the same digital twin model, multiphysics simulation verification is performed again. Generate performance evaluation results that include the verification results corresponding to the simulation indicators, as the basis for outputting the final engineering parameter set.

5. The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback as described in claim 4, characterized in that, The digital twin model includes a manufacturing analysis layer; The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback also includes: Before outputting the final set of engineering parameters, a consistency check is performed. The manufacturing analysis layer performs a structural topology check on the backfilled scheme to ensure that the design changes do not cause interference in the assembly space and that all geometric corrections meet the preset molding process limitations.

6. The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback as described in claim 4, characterized in that, The digital twin model includes a test and analysis layer; The industrial design optimization method based on digital twins and particle swarm optimization iterative feedback also includes: During the verification process of backfilling the updated design parameter set into the same digital twin model, in-depth structural integrity verification is performed. The test analysis layer performs fatigue damage accumulation simulation under full life cycle conditions on the backfill scheme to verify the reliability of the physical structure corresponding to the engineering parameter set under long-term repetitive motion conditions.

7. An industrial design optimization device based on digital twin and particle swarm optimization iterative feedback, characterized in that, include: The computing environment initialization module is used to map the design parameter space associated with the digital twin model of the product to be optimized to the initial population of the particle swarm optimization algorithm, thus completing the initialization of the computing environment. The preliminary optimization solution set determination module is used to perform multiphysics simulation on the digital twin model and perform a first-stage particle swarm optimization based on the obtained simulation indexes to obtain a preliminary optimization solution set. The update term determination module is used to perform consistency simulation verification on the same digital twin model for the preliminary optimization solution set, and generate objective function weight update terms and / or simulation boundary constraint update terms based on engineering feedback information and simulation verification results. The updated design parameter set output module is used to perform a second-stage particle swarm optimization based on the updated item and output the updated design parameter set. The engineering parameter set verification module is used to backfill the updated design parameter set into the same digital twin model for verification, and output the engineering parameter set that has passed the verification. The update item determination module includes: The indicator to be corrected is marked as an indicator to be corrected if any of the simulation indicators shows a verification deviation relative to the corresponding preset performance threshold or safety margin; the weight coefficient adjustment unit is used to increase the weight coefficient of the indicator to be corrected in the objective function so that the second-stage particle swarm iteration optimization prioritizes correcting the performance deviation corresponding to the indicator to be corrected. And / or, The constraint update unit is used to tighten or relax the upper limit threshold and / or lower limit threshold of the constraint item corresponding to the simulation index if any of the simulation index does not meet the corresponding preset performance threshold or safety margin, and use the updated threshold as the constraint condition for the second stage particle swarm iterative optimization.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the industrial design optimization method of digital twin and particle swarm iterative feedback as described in any one of claims 1 to 6.

Images