|
|
|
| Current Density Field Prediction Method for Electromagnetic Rail Launcher at High Speed |
| Jin Liang1,2, Song Juheng1,2, Ma Tianci1, Yin Zhenhao1, Zhang Chenyuan1 |
1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology Tianjin 300401 China;
2. Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province Hebei University of Technology Tianjin 300401 China |
|
|
|
Abstract During the electromagnetic rail launcher's launch process, the current distribution on the rail cross-section and armature-rail contact surfaces exhibits significant inhomogeneity, with current density approaching the material's bearing limit. Calculating the current density field during the launching process is one of the necessary conditions to realize the fine design of its structure. However, due to the complexity of the problem involving multi-field coupling and nonlinearity, refining the modeling and calculations using the finite element method (FEM) is time-consuming, often spanning hours or even days. Affected by the velocity skinning effect, the electromagnetic field control equation is a convection-diffusion equation, which is difficult or even impossible to compute at high speeds. Considering that the deep neural network has a powerful feature extraction ability and can learn the time-space change law of the field from numerical simulation data, this paper proposes a current density field prediction method based on ResUnet-Trans-CGAN at high speed. The dataset is obtained using FEM, and the high-precision interpolation prediction of the current density field and the extrapolation prediction of the difficult-to-stabilize computation stage at high speed can be realized after the training is completed, and the single computation time is within seconds.
First, to realize the direct generation of the current density field, this paper uses the generative adversarial network (GAN), which is currently one of the most widely used image generation models. The conditional generative adversarial network (CGAN) addresses GAN's uncontrollable image generation issue by introducing a conditional variable y to the generator and discriminator. In order to realize the one-to-one mapping from input parameters to current density field, this paper removes the random noise z in the input, and directly inputs the excitation current, armature conductivity, rail structure parameters and time t into the neural network as the conditional variables, and establishes the current density field prediction model based on CGAN. Then, to improve the feature extraction capability for complex current density field distributions, the ResUnet-Trans network is constructed as the feature generator of CGAN. The U-Net structure is used to realize the fusion of different levels of features, short Residuals are introduced to inhibit the deep neural network degradation, and the Transformer is introduced to enhance the model's ability to extract global features. Second, dropout and a cosine annealing algorithm for adaptive learning rate adjustment are introduced in the model to curb overfitting and improve prediction accuracy. Further, a transfer learning training strategy, transitioning from low to high conductivity, is applied during training to improve the model's extrapolation prediction accuracy and generalization ability. Finally, the accuracy of model interpolation and extrapolation prediction is verified with the examples of low-speed and high-speed electromagnetic rail launcher, respectively.
The results show that for interpolation prediction, the ResUnet-Trans-CGAN proposed in this paper has the highest accuracy with the mean absolute percentage error (MAPE) value of current density field prediction less than 1.5% compared to CGAN, Unet-CGAN and ResUnet-Trans. After using the transfer learning training strategy from low to high conductivity, the MAPE is reduced by 9.59% and 19.0% at the rail cross-section and at the armature-rail contact surface, respectively. When extrapolating the prediction at high speeds, the MAPE of the current density field at the rail cross-section is reduced from 1.83% to 1.52% and the training speed is improved by 17.0%, and that at the armature-rail contact surface is reduced from 3.47% to 2.43%, and the training speed is improved by 22.1%, after using the Transfer Learning training strategy of moving from low to high conductivity on the test set. The model can generate the current density field directly at the stage where it is difficult to perform stable numerical simulation at high speed.
|
|
Received: 20 September 2023
|
|
|
|
|
|
[1] 张嘉炜, 鲁军勇, 谭赛, 等. 考虑初始接触压力的滑动电接触界面磁扩散模型[J]. 电工技术学报, 2022, 37(2): 488-495.
Zhang Jiawei, Lu Junyong, Tan Sai, et al.A magnetic diffusion model of electromagnetic launcher considering initial contact pressure[J]. Transactions of China Electrotechnical Society, 2022, 37(2): 488-495.
[2] 古刚, 吴立周, 耿昊, 等. 基于电磁-流场耦合的轨道冷却仿真分析[J]. 电工技术学报, 2020, 35(17): 3601-3608.
Gu Gang, Wu Lizhou, Geng Hao, et al.Simulation and analysis of rail cooling based on electromagnetic and fluid field coupling[J]. Transactions of China Electro-technical Society, 2020, 35(17): 3601-3608.
[3] 阮景煇, 陈立学, 夏胜国, 等. 电磁轨道炮电流分布特性研究综述[J]. 电工技术学报, 2020, 35(21): 4423-4431.
Ruan Jinghui, Chen Lixue, Xia Shengguo, et al.A review of current distribution in electromagnetic railguns[J]. Transactions of China Electrotechnical Society, 2020, 35(21): 4423-4431.
[4] 王增基, 陈立学, 尤彭昊, 等. 考虑速度趋肤效应与接触电阻影响的枢轨界面电流分布特性[J]. 电工技术学报, 2022, 37(19): 5003-5010.
Wang Zengji, Chen Lixue, You Penghao, et al.Current distribution characteristics of armature-rail interface under velocity skin effect and contact resistance[J]. Transactions of China Electrotechnical Society, 2022, 37(19): 5003-5010.
[5] Hsieh K.A Lagrangian formulation for mechanically, thermally coupled electromagnetic diffusive processes with moving conductors[J]. IEEE Transactions on Magnetics, 1995, 31(1): 604-609.
[6] Hsieh K T.Hybrid FE/BE implementation on electromechanical systems with moving conductors[J]. IEEE Transactions on Magnetics, 2007, 43(3): 1131-1133.
[7] 阮江军, 张宇, 张宇娇, 等. 电气设备电磁多物理场数值仿真研究与应用[J]. 高电压技术, 2020, 46(3): 737-756.
Ruan Jiangjun, Zhang Yu, Zhang Yujiao, et al.Numerical simulation research and applications of electromagnetic multiphysical field for electrical equipment[J]. High Voltage Engineering, 2020, 46(3): 737-756.
[8] 胡万君, 刘刚, 朱章宸, 等. 油浸式电力变压器绕组稳态温升降阶计算方法研究[J]. 中国电机工程学报, 2023, 43(16): 6505-6517.
Hu Wanjun, Liu Gang, Zhu Zhangchen, et al.Reduced order calculation method of steady temperature rise of oil immersed power transformer[J]. Proceedings of the CSEE, 2023, 43(16): 6505-6517.
[9] Kutz J N.Deep learning in fluid dynamics[J]. Journal of Fluid Mechanics, 2017, 814: 1-4.
[10] 马伟明, 鲁军勇. 电磁发射技术的研究现状与挑战[J]. 电工技术学报, 2023, 38(15): 3943-3959.
Ma Weiming, Lu Junyong.Research progress and challenges of electromagnetic launch technology[J]. Transactions of China Electrotechnical Society, 2023, 38(15): 3943-3959.
[11] Khan A, Ghorbanian V, Lowther D.Deep learning for magnetic field estimation[J]. IEEE Transactions on Magnetics, 2019, 55(6): 7202304.
[12] Gong Ruohan, Tang Zuqi.Investigation of convolutional neural network U-net under small datasets in transformer magneto-thermal coupled analysis[J]. COMPEL-the International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 2020, 39(4): 959-970.
[13] 金亮, 冯裕霖, 曹佳豪, 等. 基于注意力与长短期记忆网络的变压器代理模型[J]. 电气技术, 2021, 22(7): 65-71, 77.
Jin Liang, Feng Yulin, Cao Jiahao, et al.Transformer surrogate model based on attention and long-short term memory[J]. Electrical Engineering, 2021, 22(7): 65-71, 77.
[14] Jin Liang, Liu Yuankai, Yang Qingxin, et al.Prediction method of motor magnetic field based on improved linknet model[J]. COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 2023, 42(1): 90-100.
[15] Lu Junyong, Tang Yinyin, Zeng Delin, et al.Fault prediction of electromagnetic launch system based on knowledge prediction time series[J]. IEEE Tran-sactions on Industry Applications, 2021, 57(2): 1830-1839.
[16] Liu J G, Dong Z Q, Ren R, et al.An initial velocity model study of electromagnetic railgun based on back propagation neural network[J]. Journal of Physics: Conference Series, 2020, 1507(7): 072018.
[17] 纪守领, 杜天宇, 邓水光, 等. 深度学习模型鲁棒性研究综述[J]. 计算机学报, 2022, 45(1): 190-206.
Ji Shouling, Du Tianyu, Deng Shuiguang, et al.Robustness certification research on deep learning models: a survey[J]. Chinese Journal of Computers, 2022, 45(1): 190-206.
[18] Han Renkun, Wang Yixing, Zhang Yang, et al.A novel spatial-temporal prediction method for unsteady wake flows based on hybrid deep neural network[J]. Physics of Fluids, 2019, 31(12): 127101.
[19] 王琛, 王颖, 郑涛, 等. 基于ResNet-LSTM网络和注意力机制的综合能源系统多元负荷预测[J]. 电工技术学报, 2022, 37(7): 1789-1799.
Wang Chen, Wang Ying, Zheng Tao, et al.Multi-energy load forecasting in integrated energy system based on ResNet-LSTM network and attention mechanism[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1789-1799.
[20] 吴鑫, 张艳丽, 王振, 等. 基于深度学习的电工钢片磁畴磁化过程预测与特征量提取[J]. 电工技术学报, 2023, 38(9): 2289-2298.
Wu Xin, Zhang Yanli, Wang Zhen, et al.Prediction of magnetic domains magnetization process and feature extraction of electrical steel sheet based on deep learning[J]. Transactions of China Electrotechnical Society, 2023, 38(9): 2289-2298.
[21] Goodfellow I J, Pouget-Abadie J, Mirza M, et al.Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Canada, 2014, 2: 2672-2680.
[22] Mirza M, Osindero S. Conditional generative adversarial nets[J]. arXiv:1411.1784, 2014.
[23] Faulkner C A, Jankowski D S, Castellini J E, et al.Fast prediction of indoor airflow distribution inspired by synthetic image generation artificial intelligence[J]. Building Simulation, 2023, 16(7): 1219-1238.
[24] Wu Haizhou, Liu Xuejun, An Wei, et al.A deep learning approach for efficiently and accurately evaluating the flow field of supercritical airfoils[J]. Computers & Fluids, 2020, 198: 104393.
[25] Ronneberger O, Fischer P, Brox T.U-Net: convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention, Freiburg, Germany, 2015: 234-241.
[26] Zhang Zhengxin, Liu Qingjie, Wang Yunhong.Road extraction by deep residual U-net[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5): 749-753.
[27] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016: 770-778.
[28] Vaswani A, Shazeer N, Parmar N, et al.Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems, Red Hook, NY, USA, 2017: 6000-6010.
[29] Jin Xiaowei, Cheng Peng, Chen Wenli, et al.Prediction model of velocity field around circular cylinder over various Reynolds numbers by fusion convolutional neural networks based on pressure on the cylinder[J]. Physics of Fluids, 2018, 30(4): 047105.
[30] Lee S, You D.Data-driven prediction of unsteady flow over a circular cylinder using deep learning[J]. Journal of Fluid Mechanics, 2019, 879: 217-254.
[31] Jin Liang, Gong Dexin, Yan Yingang, et al.Armature electromagnetic force extrapolation prediction method for electromagnetic railgun at high speed[J]. Applied Sciences, 2023, 13(6): 3819.
[32] 房佳姝, 刘崇茹, 苏晨博, 等. 基于自注意力Transformer编码器的多阶段电力系统暂态稳定评估方法[J]. 中国电机工程学报, 2023, 43(15): 5745-5759.
Fang Jiashu, Liu Chongru, Su Chenbo, et al.Multi-stage transient stability assessment of power system based on self-attention transformer encoder[J]. Proceedings of the CSEE, 2023, 43(15): 5745-5759.
[33] Hsieh K T, Kim B K.International railgun modelling effort[J]. IEEE Transactions on Magnetics, 1997, 33(1): 245-248.
[34] Price J H, Yun H D.Design and testing of integrated metal armature sabots for launch of armour penetrating projectiles from electric guns[J]. IEEE Transactions on Magnetics, 1995, 31(1): 219-224.
[35] Yang K S, Kim S H, Lee B, et al.Electromagnetic launch experiments using a 4.8-MJ pulsed power supply[J]. IEEE Transactions on Plasma Science, 2015, 43(5): 1358-1361. |
|
|
|
2024, Vol. 39 
