Physics-Informed Generative Adversarial Network-Based Modeling and Simulation of Linear Electric Machines
Source abstract
Abstract
The demand for fast magnetic field approximation for the optimal design of electromagnetic devices is urgent nowadays. However, due to the lack of a publicly available dataset and the unclear definition of each parameter in the magnetic field dataset, the expansion of data-driven magnetic field approximation is severely limited. This study presents a physics-informed generative adversarial network (PIGAN), as well as a permanent magnet linear synchronous motor (PMLSM)-based magnetic field dataset, for fast magnetic field approximation. It includes the current density, material distribution, electromagnetic material properties, and other parameters of the electric machine. Physics-informed loss functions are utilized in the training process, making the output governed by Maxwell’s equation. Different slot-pole combinations of the PMLSM are involved in the dataset to extend the generalization of PIGAN. Some indicators for the further evaluation of magnetic approximation performance, including image-based metrics and calculation methods for the performance of electric motors, are presented in this study. Some challenges of magnetic field approximation using PIGAN are also discussed. The effectiveness of the physics-informed method is verified by comparing the magnetic field approximation results and the performance analysis results of the PMLSM with FEM, and the speed of PIGAN is approximately 40 times faster than that of FEM, while the accuracy is similar.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Model Reduction and Neural Networks · Magnetic Properties and Applications · Advanced Image Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, The Hong Kong Polytechnic University, Hong Kong, China
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
Funding
Research Grant Council of the Hong Kong Government
References (37)
Show source-provided references
1. Li, Y., Lei, G., Bramerdorfer, G., Peng, S., Sun, X., and Zhu, J. (2021). Machine Learning for Design Optimization of Electromagnetic Devices: Recent Developments and Future Directions. Appl. Sci., 11.10.3390/app11041627 ↗
2. A Comparative Study on Overall Efficiency of 2-Dimensional Wireless Power Transfer Systems Using Rotational and Directional Methods10.1109/TIE.2020.3048317 ↗
3. A Novel Asymmetric-Magnetic-Pole Interior PM Machine with Magnet-Axis-Shifting Effect10.1109/TIA.2021.3111153 ↗
4. MLPF: Efficient Machine-Learned Particle-Flow Reconstruction Using Graph Neural Networks10.1140/epjc/s10052-021-09158-w ↗
5. StressGAN: A Generative Deep Learning Model for Two-Dimensional Stress Distribution Prediction10.1115/1.4049805 ↗
6. Dynamic Balancing of Super-Critical Rotating Structures Using Slow-Speed Data via Parametric Excitation10.1016/j.jsv.2017.11.029 ↗
7. Jha, D., Smedsrud, P.H., Riegler, M.A., Johansen, D., De Lange, T., Halvorsen, P., and Johansen, H.D. (2019, January 9–11). ResUNet++: An Advanced Architecture for Medical Image Segmentation. Proceedings of the 2019 IEEE International Symposium on Multimedia (ISM), San Diego, CA, USA.10.1109/ISM46123.2019.00049 ↗
8. Hanke, S., Wallscheid, O., and Böcker, J. (2020). Data Set Description: Identifying the Physics Behind an Electric Motor—Data-Driven Learning of the Electrical Behavior (Part I). arXiv.
9. Estimating Electric Motor Temperatures with Deep Residual Machine Learning10.1109/TPEL.2020.3045596 ↗
10. Mcgregor, S., Dhuri, D., Berea, A., and Muñoz-Jaramillo, A. (2017, January 8). FlareNet: A Deep Learning Framework for Solar Phenomena Prediction. Proceedings of the Workshop on Deep Learning for Physical Sciences (DLPS 2017), NIPS 2017, Long Beach, CA, USA.
11. Mokhtar, F., Kansal, R., Diaz, D., Duarte, J., Pata, J., Pierini, M., and Vlimant, J.-R. (2021). Explaining Machine-Learned Particle-Flow Reconstruction. arXiv.
12. Learning-Based Fast Electromagnetic Scattering Solver Through Generative Adversarial Network10.1109/TAP.2020.3026447 ↗
13. Investigation of Convolutional Neural Network U-Net under Small Datasets in Transformer Magneto-Thermal Coupled Analysis10.1108/COMPEL-12-2019-0491 ↗
14. Wu, H., Niu, S., Zhang, Y., Zhao, X., and Fu, W. (2022). Fast Magnetic Field Approximation Method for Simulation of Coaxial Magnetic Gears Using AI. IEEE J. Emerg. Sel. Top. Ind. Electron., 1–9.10.1109/JESTIE.2022.3185558 ↗
15. Streak Lines as Tangent Curves of a Derived Vector Field10.1109/TVCG.2010.198 ↗
16. Deep Learning for Magnetic Field Estimation10.1109/TMAG.2019.2899304 ↗
17. Brunton, S.L., Budišić, M., Kaiser, E., and Kutz, J.N. (2021). Modern Koopman Theory for Dynamical Systems. arXiv.10.1137/21M1401243 ↗
18. A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders10.1109/TII.2020.2967556 ↗
19. Deep Learning for Universal Linear Embeddings of Nonlinear Dynamics10.1038/s41467-018-07210-0 ↗
20. Mohammadi, M.H., Ghorbanian, V., and Lowther, D.A. (2018, January 3–6). A Data-Driven Approach for Design Knowledge Extraction of Synchronous Reluctance Machines Using Multi-Physical Analysis. Proceedings of the 2018 23rd International Conference on Electrical Machines, ICEM 2018, Alexandroupoli, Greece.10.1109/ICELMACH.2018.8506851 ↗
21. Machine Learning Accelerated Computational Fluid Dynamics10.1073/pnas.2101784118 ↗
22. Training Sample Selection Strategy Applied to CNN in Magneto-Thermal Coupled Analysis
23. Inverse Design of Magnetic Fields Using Deep Learning10.1109/TMAG.2021.3082431 ↗
24. Multi-Objective Topology Optimization of Rotating Machines Using Deep Learning10.1109/TMAG.2019.2899934 ↗
25. Two-Dimensional Electromagnetic Solver Based on Deep Learning Technique10.1109/JMMCT.2020.2995811 ↗
26. Generative Adversarial Networks10.1145/3422622 ↗
27. Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-Image Translation with Conditional Adversarial Networks. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
28. Arora, S., Ge, R., Liang, Y., Ma, T., and Zhang, Y. (2017, January 6–11). Generalization and Equilibrium in Generative Adversarial Nets (GANs). Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney Australia.
29. Remy, G., Krebs, G., Tounzi, A., and Barre, P. (2007, January 16–19). Finite Element Analysis of a PMLSM (Part 1)—Meshing Techniques and Thrust Computations. Proceedings of the 6th International Symposium on Linear Drives for Industrial Applications, Lille, France.
30. Remy, G., Krebs, G., Tounzi, A., and Barre, P. (2007, January 16–19). Finite Element Analysis of a PMLSM (Part 2)—Cogging Force and End-Effect Force Calculations. Proceedings of the 6th International Symposium on Linear Drives for Industrial Applications, Lille, France.
31. Detent Force Calculations of a PMLSM Using the Finite Element Method10.1541/ieejias.129.462 ↗
32. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2–4). TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, Savannah, GA, USA.
33. Kingma, D.P., and Ba, J.L. (2015, January 7–9). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA.
34. Deep Neural Network for Simulation of Magnetic Flux Leakage Testing10.1016/j.measurement.2020.108726 ↗
35. Pan, J., Liu, Y., Dong, J., Zhang, J., Ren, J., Tang, J., Tai, Y.W., and Yang, M.H. (2018). Physics-Based Generative Adversarial Models for Image Restoration and Beyond. arXiv.
36. Horé, A., and Ziou, D. (2010, January 23–26). Image Quality Metrics: PSNR vs. SSIM. Proceedings of the International Conference on Pattern Recognition, Istanbul, Turkey.10.1109/ICPR.2010.579 ↗
37. Pollok, S., Olden-Jørgensen, N., Jørgensen, P.S., and Bjørk, R. (2022). Magnetic Field Prediction Using Generative Adversarial Networks. arXiv.10.1016/j.jmmm.2023.170556 ↗