Multi-physics field coupling driven electromagnetic structure topology collaborative optimization method and device and storage medium

Abstract

The invention relates to the technical field of artificial electromagnetic structures, and particularly discloses a multi-physics field coupling driven electromagnetic structure topology collaborative optimization method and device and a storage medium, and the method comprises the steps: building an electromagnetic-thermal-stress multi-physics field coupling model, and quantifying the performance attenuation law of a topological structure under a complex working condition; based on an electromagnetic-thermal-stress multi-physics field coupling model, constructing a gradient optimization framework based on topological sensitivity analysis, and identifying a high-sensitivity area as a preferential optimization area; the integrated generative adversarial network generates an anti-disturbance topological configuration; and deploying a multi-physics field collaborative optimization algorithm and implementing dynamic iteration. The problems that a traditional single physical field optimization method in the prior art is large in limitation, low in calculation efficiency and insufficient in robustness are solved.

Description

Technical Field

[0001] The present application relates to the technical field of artificial electromagnetic structures, and in particular to a method, device and storage medium for collaborative optimization of electromagnetic structure topology driven by multi-physical field coupling. Background Art

[0002] With the rapid development of 5G / 6G communications, aerospace, and new energy vehicles, the working environment of electromagnetic devices is becoming increasingly complex (such as high frequency, high temperature, and high mechanical load). Traditional single physical field optimization methods have great limitations, low computational efficiency, and insufficient robustness. Summary of the Invention

[0003] The purpose of this application is to provide a method, device and storage medium for electromagnetic structure topology collaborative optimization driven by multi-physical field coupling, so as to solve the problems in the prior art of traditional single physical field optimization methods that have great limitations, low computational efficiency and insufficient robustness.

[0004] To achieve the above objectives, the present invention provides a method for electromagnetic structure topology collaborative optimization driven by multi-physics field coupling, comprising:

[0005] Establish an electromagnetic-thermal-stress multi-physics field coupling model to quantify the performance degradation law of topological structures under complex working conditions;

[0006] Based on the electromagnetic-thermal-stress multi-physics field coupling model, a gradient optimization framework based on topological sensitivity analysis is constructed to identify highly sensitive areas as priority optimization areas;

[0007] Ensemble the generative adversarial network to generate disturbance-resistant topological configurations;

[0008] Deploy multi-physics collaborative optimization algorithms and perform dynamic iterations.

[0009] Optionally, establishing a multi-physics field coupling model specifically includes:

[0010] The electromagnetic structure topology parameters are defined as a multidimensional vector, which includes electromagnetic parameters, thermal parameters and stress parameters. The multidimensional vector is P = [ε r ,κ,E,α], where ε r is the relative dielectric constant, κ is the thermal conductivity, E is the elastic modulus, and α is the thermal expansion coefficient;

[0011] Based on the multidimensional vector, the Maxwell equations, heat conduction equations and elasticity equations are solved simultaneously by the finite element method:

[0012]

[0013] Where E is the electric field intensity, T is the temperature field, σ is the stress tensor, F is the volume force, Q is the heat source power density, μ is the magnetic permeability, ε is the absolute dielectric constant, and ω is the angular frequency;

[0014] Define the multi-physics performance attenuation index Γ=λ1Δη+λ2ΔT+λ3Δε v M, where Δη is the change in transmission efficiency, ΔT is the temperature rise, and Δε v M is the von Mises strain increment, and λ1, λ2, and λ3 are weight coefficients.

[0015] Optionally, the construction of a gradient optimization framework for topological sensitivity analysis specifically includes:

[0016] The electromagnetic-thermal-stress multiphysics sensitivity of the electromagnetic-thermal-stress multiphysics coupled model is calculated using the adjoint variable method:

[0017]

[0018] Among them, ρ e is the topological density distribution, φ i It is the response of electromagnetic, thermal and stress fields;

[0019] Setting thresholds Select units with a sensitivity higher than the threshold τ (such as waveguide bends and heat concentration areas) as priority optimization areas;

[0020] Use the moving asymptote algorithm (MMA) to update ρ e , the iteration step size α=0.05, and the convergence condition is ‖Δρ‖2<10 -3 .

[0021] Optionally, the network architecture of the adversarial generative network includes: a generator and a discriminator, and the input of the generator is a random noise vector and multi-physics field constraints, outputting the candidate topological density distribution. The discriminator inputs real topological samples or generated samples and outputs the authenticity probability p∈[0,1]. The generator adopts a 5-layer deconvolution network, the discriminator adopts a 4-layer convolution network, and the activation function is LeakyReLU.

[0022] Optionally, the deploying of a multi-physics field collaborative optimization algorithm specifically includes:

[0023] The topological sensitivity analysis module of the gradient optimization framework and the generator are embedded in the COMSOL Multiphysics App Builder and tested via LiveLink. TM The interface realizes data interaction.

[0024] Optionally, the implementing dynamic iteration specifically includes:

[0025] A sensitivity analysis is performed on the electromagnetic-thermal-stress multi-physics field coupling model, and highly sensitive areas are identified as priority optimization areas. Based on the sensitivity distribution, a generative adversarial network is used to generate candidate anti-disturbance topological configurations. The candidate anti-disturbance topological configurations are iteratively optimized to screen out the Pareto optimal solution set. The Pareto optimal solution is input into the moving asymptote algorithm to update the topological density distribution until convergence or the maximum number of iterations is reached.

[0026] Optionally, it also includes:

[0027] Integrate multi-physics collaborative optimization algorithms into industrial simulation platforms and verify multi-physics performance.

[0028] To achieve the above-mentioned purpose, the present application further provides a multi-physical field coupling-driven electromagnetic structure topology collaborative optimization device, comprising: a memory; and

[0029] A processor connected to the memory, wherein the processor is configured to execute the steps of the method described above.

[0030] To achieve the above objectives, the present application also provides a computer storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a machine.

[0031] The embodiments of the present application have the following advantages:

[0032] The multi-physics coupling-driven electromagnetic structure topology collaborative optimization method proposed in this application achieves the following breakthrough advantages through sensitivity-guided gradient optimization and GAN-enhanced anti-disturbance design:

[0033] 1. By solving multi-physics field equations simultaneously, the performance of multiple physical fields can be improved synergistically, and electromagnetic-thermal-stress global optimization can be achieved;

[0034] 2. Implement defect-tolerant design by introducing GAN-generated anti-disturbance topology configurations;

[0035] 3. By prioritizing the optimization of high-sensitivity areas, we can reduce invalid calculations and improve computing efficiency;

[0036] 4. Generate tolerant topological configurations through adversarial training to control the performance deviation caused by processing errors within a reasonable range. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] To more clearly illustrate the embodiments of this application or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are merely illustrative, and those skilled in the art can, without inventive effort, derive other implementation drawings based on the provided drawings.

[0038] Figure 1 A flowchart of a method for collaborative optimization of electromagnetic structure topology driven by multi-physics field coupling provided in at least one embodiment of the present application;

[0039] Figure 2 A module block diagram of a multi-physics field coupling-driven electromagnetic structure topology collaborative optimization device provided in at least one embodiment of the present application. DETAILED DESCRIPTION

[0040] The following specific embodiments illustrate the implementation of this application. Those familiar with the art can easily understand the other advantages and functions of this application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0041] It should be noted that, in the claims and description of this application, the steps may be executed substantially in parallel or in reverse order under appropriate circumstances, depending on the functions involved.

[0042] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0043] An embodiment of the present application provides a method for electromagnetic structure topology collaborative optimization driven by multi-physical field coupling, referring to Figure 1 , Figure 1 A flowchart of a method for collaborative optimization of electromagnetic structure topology driven by multi-physics field coupling is provided in at least one embodiment of the present application. It should be understood that the method may also include additional boxes not shown and / or the boxes shown may be omitted, and the scope of the present application is not limited in this respect.

[0044] In step 101 , an electromagnetic-thermal-stress multi-physics field coupling model is established to quantify the performance degradation law of the topological structure under complex working conditions.

[0045] In some embodiments, establishing a multi-physics field coupling model specifically includes:

[0046] The electromagnetic structure topology parameters are defined as a multidimensional vector, which includes electromagnetic parameters, thermal parameters and stress parameters. The multidimensional vector is P = [ε r ,κ,E,α], where ε r is the relative dielectric constant, κ is the thermal conductivity, E is the elastic modulus, and α is the thermal expansion coefficient;

[0047] Based on the multidimensional vector, the Maxwell equations, heat conduction equations and elasticity equations are solved simultaneously by the finite element method:

[0048]

[0049] Where E is the electric field intensity, T is the temperature field, σ is the stress tensor, F is the volume force, Q is the heat source power density, μ is the magnetic permeability, ε is the absolute dielectric constant, and ω is the angular frequency;

[0050] Define the multi-physics performance attenuation index Γ=λ1Δη+λ2ΔT+λ3Δε v M, where Δη is the change in transmission efficiency, ΔT is the temperature rise, and Δε v M is the von Mises strain increment, and λ1, λ2, and λ3 are weight coefficients.

[0051] At step 102 , based on the electromagnetic-thermal-stress multi-physics field coupling model, a gradient optimization framework based on topological sensitivity analysis is constructed to identify highly sensitive areas as priority optimization areas.

[0052] In some embodiments, constructing a gradient optimization framework for topological sensitivity analysis specifically includes:

[0053] The electromagnetic-thermal-stress multiphysics sensitivity of the electromagnetic-thermal-stress multiphysics coupled model is calculated using the adjoint variable method:

[0054]

[0055] Among them, ρ e is the topological density distribution, φ i It is the response of electromagnetic, thermal and stress fields;

[0056] Setting thresholds Select units with a sensitivity higher than the threshold τ (such as waveguide bends and heat concentration areas) as priority optimization areas;

[0057] Use the moving asymptote algorithm (MMA) to update ρ e , the iteration step size α=0.05, and the convergence condition is ‖Δρ‖2<10 -3 .

[0058] At step 103 , a generative adversarial network (GAN) is integrated to generate a perturbation-resistant topological configuration.

[0059] In some embodiments, the network architecture of the adversarial generative network includes: a generator and a discriminator, wherein the input of the generator is a random noise vector and multi-physics field constraints, outputting the candidate topological density distribution. The discriminator inputs real topological samples or generated samples and outputs the authenticity probability p∈[0,1]. The generator adopts a 5-layer deconvolution network, the discriminator adopts a 4-layer convolution network, and the activation function is LeakyReLU (slope = 0.2).

[0060] At step 104 , a multi-physics collaborative optimization algorithm is deployed and dynamic iteration is performed.

[0061] In some embodiments, deploying a multi-physics collaborative optimization algorithm specifically includes:

[0062] The topological sensitivity analysis module of the gradient optimization framework and the generator are embedded in the COMSOL Multiphysics App Builder and tested via LiveLink. TM The interface realizes data interaction.

[0063] In some embodiments, the implementing dynamic iteration specifically includes:

[0064] A sensitivity analysis is performed on the electromagnetic-thermal-stress multi-physics field coupling model, and highly sensitive areas are identified as priority optimization areas. Based on the sensitivity distribution, a generative adversarial network is used to generate candidate anti-disturbance topological configurations. The candidate anti-disturbance topological configurations are iteratively optimized to screen out the Pareto optimal solution set. The Pareto optimal solution is input into the moving asymptote algorithm to update the topological density distribution until convergence or the maximum number of iterations is reached.

[0065] In some embodiments, further comprising:

[0066] Integrate multi-physics collaborative optimization algorithms into industrial simulation platforms and verify multi-physics performance, including:

[0067] Encapsulate the optimization algorithm as a custom ANSYS Workbench module, supporting parameterized input (frequency bands, thermal loads, stress constraints);

[0068] Through the ACT (Application Customization Toolkit) extended interface, a one-click optimization function is provided.

[0069] The proposed multi-physics coupling-driven electromagnetic structure topology collaborative optimization method achieves the following breakthrough advantages through sensitivity-guided gradient optimization and GAN-enhanced anti-disturbance design:

[0070] 1. By solving multi-physics field equations simultaneously, the performance of multiple physical fields can be improved synergistically, and electromagnetic-thermal-stress global optimization can be achieved;

[0071] 2. Implement defect-tolerant design by introducing GAN-generated anti-disturbance topology configurations;

[0072] 3. By prioritizing the optimization of high-sensitivity areas, we can reduce invalid calculations and improve computing efficiency;

[0073] 4. Generate tolerant topological configurations through adversarial training to control the performance deviation caused by processing errors within a reasonable range.

[0074] Figure 2 A block diagram of a multi-physics field coupling-driven electromagnetic structure topology collaborative optimization device provided in at least one embodiment of the present application. The device includes:

[0075] A memory 201; and a processor 202 connected to the memory 201, wherein the processor 202 is configured to: establish an electromagnetic-thermal-stress multi-physics field coupling model to quantify the performance degradation law of the topological structure under complex working conditions;

[0076] Based on the electromagnetic-thermal-stress multi-physics field coupling model, a gradient optimization framework based on topological sensitivity analysis is constructed to identify highly sensitive areas as priority optimization areas;

[0077] Ensemble the generative adversarial network to generate disturbance-resistant topological configurations;

[0078] Deploy multi-physics collaborative optimization algorithms and perform dynamic iterations.

[0079] In some embodiments, the processor 202 is further configured to: establish the multi-physics field coupling model, specifically including:

[0080] The electromagnetic structure topology parameters are defined as a multidimensional vector, which includes electromagnetic parameters, thermal parameters and stress parameters. The multidimensional vector is P = [ε r ,κ,E,α], where ε r is the relative dielectric constant, κ is the thermal conductivity, E is the elastic modulus, and α is the thermal expansion coefficient;

[0081] Based on the multidimensional vector, the Maxwell equations, heat conduction equations and elasticity equations are solved simultaneously by the finite element method:

[0082]

[0083] Where E is the electric field intensity, T is the temperature field, σ is the stress tensor, F is the volume force, Q is the heat source power density, μ is the magnetic permeability, ε is the absolute dielectric constant, and ω is the angular frequency;

[0084] Define the multi-physics performance attenuation index Γ=λ1Δη+λ2ΔT+λ3Δε v M, where Δη is the change in transmission efficiency, ΔT is the temperature rise, and Δε vM is the von Mises strain increment, and λ1, λ2, and λ3 are weight coefficients.

[0085] In some embodiments, the processor 202 is further configured to: construct a gradient optimization framework for topology sensitivity analysis, specifically including:

[0086] The electromagnetic-thermal-stress multiphysics sensitivity of the electromagnetic-thermal-stress multiphysics coupled model is calculated using the adjoint variable method:

[0087]

[0088] Among them, ρ e is the topological density distribution, φ i It is the response of electromagnetic, thermal and stress fields;

[0089] Setting thresholds Select units with a sensitivity higher than the threshold τ (such as waveguide bends and heat concentration areas) as priority optimization areas;

[0090] Use the moving asymptote algorithm (MMA) to update ρ e , the iteration step size α=0.05, and the convergence condition is ‖Δρ‖2<10 -3 .

[0091] In some embodiments, the processor 202 is further configured to: the network architecture of the adversarial generative network includes: a generator and a discriminator, the input of the generator is a random noise vector and multi-physics field constraints, outputting the candidate topological density distribution. The discriminator inputs real topological samples or generated samples and outputs the authenticity probability p∈[0,1]. The generator adopts a 5-layer deconvolution network, the discriminator adopts a 4-layer convolution network, and the activation function is LeakyReLU.

[0092] In some embodiments, the processor 202 is further configured to: deploy the multi-physics collaborative optimization algorithm, specifically including:

[0093] The topological sensitivity analysis module of the gradient optimization framework and the generator are embedded in the COMSOL Multiphysics App Builder and tested via LiveLink. TM The interface realizes data interaction.

[0094] In some embodiments, the processor 202 is further configured to: implement dynamic iteration, specifically including:

[0095] A sensitivity analysis is performed on the electromagnetic-thermal-stress multi-physics field coupling model, and highly sensitive areas are identified as priority optimization areas. Based on the sensitivity distribution, a generative adversarial network is used to generate candidate anti-disturbance topological configurations. The candidate anti-disturbance topological configurations are iteratively optimized to screen out the Pareto optimal solution set. The Pareto optimal solution is input into the moving asymptote algorithm to update the topological density distribution until convergence or the maximum number of iterations is reached.

[0096] In some embodiments, the processor 202 is further configured to:

[0097] Integrate multi-physics collaborative optimization algorithms into industrial simulation platforms and verify multi-physics performance.

[0098] The specific implementation method is referred to the aforementioned method embodiment and will not be repeated here.

[0099] The present application may be a method, apparatus, system and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present application.

[0100] Computer-readable storage medium can be a tangible device that can keep and store the instructions used by the instruction execution device.Computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device or any suitable combination thereof.More specific examples (non-exhaustive list) of computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove having instructions stored thereon, and any suitable combination thereof.Computer-readable storage medium used herein is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated by waveguides or other transmission media (for example, light pulses by fiber optic cables), or electrical signals transmitted by wires.

[0101] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0102] The computer program instructions for performing the operation of the present application can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data or source code or object code written in any combination of one or more programming languages, wherein the programming language includes object-oriented programming languages such as Smalltalk, C++, and conventional procedural programming languages such as "C" language or similar programming languages. Computer-readable program instructions can be executed completely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or executed completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer by any type of network including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (such as by using an Internet service provider to connect to the Internet). In certain embodiments, by utilizing the state information of computer-readable program instructions to personalize electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (PLAs), the electronic circuits can execute computer-readable program instructions, thereby realizing various aspects of the present application.

[0103] Various aspects of the present application are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0104] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0105] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0106] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a special hardware-based system that performs the function or action of the specification, or can be implemented by a combination of special hardware and computer instructions.

[0107] Note that, unless otherwise directly stated, all features disclosed in this specification (including any accompanying claims, abstracts and drawings) may be replaced by alternative features for achieving the same, equivalent or similar purposes. Therefore, unless otherwise explicitly stated, each feature disclosed is only an example of a group of equivalent or similar features. Where used, further, preferably, further and more preferably are a simple starting point for elaborating another embodiment based on the aforementioned embodiment, and the content of the further, preferably, further or more preferably followed by the above embodiment is combined with the aforementioned embodiment as a complete composition of another embodiment. Several further, preferably, further or more preferably settings following the same embodiment can be arbitrarily combined to form another embodiment.

[0108] Although the present application has been described in detail above using general descriptions and specific embodiments, it will be apparent to those skilled in the art that modifications or improvements may be made based on the present application. Therefore, such modifications or improvements, which do not depart from the spirit of the present application, are within the scope of protection claimed in the present application.

Claims

1. A method for electromagnetic structure topology collaborative optimization driven by multi-physical field coupling, characterized in that: include: Establish an electromagnetic-thermal-stress multi-physics field coupling model to quantify the performance degradation law of topological structures under complex working conditions; Based on the electromagnetic-thermal-stress multi-physics field coupling model, a gradient optimization framework based on topological sensitivity analysis is constructed to identify highly sensitive areas as priority optimization areas; Ensemble the generative adversarial network to generate disturbance-resistant topological configurations; Deploy multi-physics collaborative optimization algorithms and perform dynamic iterations.

2. The electromagnetic structure topology collaborative optimization method driven by multi-physical field coupling according to claim 1 is characterized in that: The establishment of the multi-physics field coupling model specifically includes: The electromagnetic structure topology parameters are defined as a multidimensional vector, which includes electromagnetic parameters, thermal parameters and stress parameters. The multidimensional vector is P = [ε r ,κ,E,α], where ε r is the relative dielectric constant, κ is the thermal conductivity, E is the elastic modulus, and α is the thermal expansion coefficient; Based on the multidimensional vector, the Maxwell equations, heat conduction equations and elasticity equations are solved simultaneously by the finite element method: Where E is the electric field intensity, T is the temperature field, σ is the stress tensor, F is the volume force, Q is the heat source power density, μ is the magnetic permeability, ε is the absolute dielectric constant, and ω is the angular frequency; Define the multi-physics performance attenuation index Γ=λ1Δη+λ2ΔT+λ3Δε v M, where Δη is the change in transmission efficiency, ΔT is the temperature rise, and Δε v M is the von Mises strain increment, and λ1, λ2, and λ3 are weight coefficients.

3. The electromagnetic structure topology collaborative optimization method driven by multi-physical field coupling according to claim 2 is characterized in that: The gradient optimization framework for constructing topological sensitivity analysis specifically includes: The electromagnetic-thermal-stress multiphysics sensitivity of the electromagnetic-thermal-stress multiphysics coupled model is calculated using the adjoint variable method: Among them, ρ e is the topological density distribution, φ i It is the response of electromagnetic, thermal and stress fields; Setting thresholds Select units with a sensitivity higher than the threshold τ (such as waveguide bends and heat concentration areas) as priority optimization areas; Use the moving asymptote algorithm (MMA) to update ρ e , the iteration step size α=0.05, and the convergence condition is ‖Δρ‖2<10 -3 .

4. The electromagnetic structure topology collaborative optimization method driven by multi-physical field coupling according to claim 3 is characterized in that: The network architecture of the adversarial generative network includes: a generator and a discriminator, and the input of the generator is a random noise vector and multi-physics field constraints, outputting the candidate topological density distribution. The discriminator inputs real topological samples or generated samples and outputs the authenticity probability p∈[0,1]. The generator adopts a 5-layer deconvolution network, the discriminator adopts a 4-layer convolution network, and the activation function is LeakyReLU.

5. The electromagnetic structure topology collaborative optimization method driven by multi-physical field coupling according to claim 4 is characterized in that: The deployment of the multi-physics field collaborative optimization algorithm specifically includes: The topological sensitivity analysis module of the gradient optimization framework and the generator are embedded in the COMSOL Multiphysics App Builder and tested via LiveLink. TM The interface realizes data interaction.

6. The electromagnetic structure topology collaborative optimization method driven by multi-physical field coupling according to claim 5 is characterized in that: The implementation of dynamic iteration specifically includes: A sensitivity analysis is performed on the electromagnetic-thermal-stress multi-physics field coupling model, and highly sensitive areas are identified as priority optimization areas. Based on the sensitivity distribution, a generative adversarial network is used to generate candidate anti-disturbance topological configurations. The candidate anti-disturbance topological configurations are iteratively optimized to screen out the Pareto optimal solution set. The Pareto optimal solution is input into the moving asymptote algorithm to update the topological density distribution until convergence or the maximum number of iterations is reached.

7. The electromagnetic structure topology collaborative optimization method driven by multi-physical field coupling according to claim 6 is characterized in that: Also includes: Integrate multi-physics collaborative optimization algorithms into industrial simulation platforms and verify multi-physics performance.

8. A multi-physics field coupling-driven electromagnetic structure topology collaborative optimization device, characterized in that: include: Memory; as well as A processor connected to the memory, the processor being configured to perform the steps of the method according to any one of claims 1 to 7.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a machine, the steps of the method according to any one of claims 1 to 7 are implemented.

Images