永磁同步电机性能分析的典型深度学习模型与训练方法

doi:10.19595/j.cnki.1000-6753.tces.180394

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (19702 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract This paper introduces the deep learning algorithm of artificial intelligence, and establishes the cogging torque prediction analysis method of permanent magnet synchronous motor (PMSM). This lays a foundation for solving the problem of data isolation between motor design, application characteristics and system integration analysis. The relationship between the four structural parameters of PMSM which are air gap, pole embrace, magnet thickness and magnet width and the performance of the cogging torque is selected as the research object. The PMSM is with eight pole-pairs, 48 stator slots. Then, 625 sets of training samples of deep learning about cogging torque are generated by FEM. We build a prediction model with 4 inputs, one output, and 4 hidden layers, which is trained and optimized by using the artificial intelligence deep learning algorithm. The 575 groups in the 625 sets of data are used to train the deep learning prediction model, and the 50 group is used to test the generalization ability of the prediction model. The feasibility of artificial intelligence deep learning prediction model is verified with the FEM.

Key words： Permanent magnet synchronous motor finite element method artificial intelligence deep learning cogging torque

Received: 22 March 2018 Published: 26 September 2018

PACS:

TM351

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Jin Liang
	Wang Fei
	Yang Qingxin
	Wang Dongmei
	Kou Xiaofei

Cite this article:

Jin Liang,Wang Fei,Yang Qingxin等. Typical Deep Learning Model and Training Method for Performance Analysis of Permanent Magnet Synchronous Motor[J]. Transactions of China Electrotechnical Society, 2018, 33(zk1): 41-48.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.180394 OR https://dgjsxb.ces-transaction.com/EN/Y2018/V33/Izk1/41

[1] 张凤阁, 杜光辉, 王天煜, 等. 高速电机发展与设计综述[J]. 电工技术学报, 2016, 31(7): 1-18.
Zhang Fengge, Du Guanghui, Wang Tianyu, et al.Review on development and design of high speed machines[J]. Transactions of China Electrotechnical Society, 2016, 31(7): 1-18.
[2] 谷鑫, 胡升, 史婷娜, 等. 基于神经网络的永磁同步电机多参数解耦在线辨识[J]. 电工技术学报, 2015, 30(6): 114-121.
Gu Xin, Hu Sheng, Shi Tingna, et al.Muti-parameter decoupling online identification of permanent magnet synchronous motor based on neura[J]. Transactions of China Electrotechnical Society, 2015, 30(6): 114-121.
[3] 陈浩, 刘向东, 赵静. 高带宽低速大转矩永磁同步电动机的优化设计[J]. 电工技术学报, 2014, 29(增刊1): 108-114.
Chen Hao, Liu Xiangdong, Zhao Jing.Design and optimization of a high-bandwidth low-speed high-torque permanent magnetic synchronous motor[J]. Transactions of China Electrotechnical Society, 2014, 29(S1): 108-114.
[4] 唐旭, 王秀和, 田蒙蒙, 等. 基于改变定子齿槽参数的异步起动永磁同步电动机齿槽转矩削弱措施研究[J]. 电工技术学报, 2016, 31(23): 1-8.
Tang Xu, Wang Xiuhe, Tian Mengmeng, et al.Study of reduction methods of cogging torque in line-start permanent magnet synchronous motor by changing the parameters ofstator teeth and slots[J]. Transactions of China Electrotechnical Society, 2016, 31(23): 1-8.
[5] 王道涵, 王秀和. 新型永磁型磁通切换型磁阻电机齿槽转矩机理分析和解析分析模型[J]. 电工技术学报, 2015, 30(10): 77-82.
Wang Daohan, Wang Xiuhe.Preliminary study for mechanisms and analytical model of coggingtorque in novel permanent magnet flux switching machine[J]. Transactions of China Electrotechnical Society, 2015, 30(10): 77-82.
[6] 包广清, 郑文鹏, 江建中. 一种改进粒子群算法在横向磁通永磁电机优化中的应用[J]. 电机与控制应用, 2008, 35(8): 27-31.
Bao Guangqing, Zheng Wenpeng, Jiang Jianzhong.Application of an improved particle swarm optimization for transverse flux permanent magnet machine optimization[J]. Electric Machines & Control Application, 2008, 35(8): 27-31.
[7] 赵希梅, 金鸿雁. 基于Elman神经网络的永磁直线同步电机互补滑模控制[J]. 电工技术学报, 2018, 33(5): 973-979.
Zhao Ximei, Jin Hongyan.Complementary sliding mode control for permanent magnet linear synchronous motor based on Elman neural network[J]. Transactions of China Electrotechnical Society, 2018, 33(5): 973-979.
[8] 孙立志, 张弓, 赵红茹, 等. 遗传算法在永磁电机气隙磁场设计中的应用[J]. 哈尔滨工业大学学报, 2000, 32(1): 71-74.
Sun Lizhi, Zhang Gong, Zhao Hongru, et al.Application of genetic algorithms to design of pole shapein permanent magnet motors[J]. Journal of Harbin Institute of Technology, 2000, 32(1): 71-74.
[9] 白凤仙, 邵玉槐, 孙建中. 利用智能型模拟退火算法进行开关磁阻电机磁极几何形状的优化[J]. 中国电机工程学报, 2003, 23(1): 127-132.
Bai Fengxian, Shao Yuhuai, Sun Jianzhong.Optimization design of pole shape of srm by using intellingent simulated annealing algorithm[J]. Proceedings of the CSEE, 2003, 23(1): 127-132.
[10] 赵永威, 李婷, 蔺博宇. 基于深度学习编码模型的图像分类方法[J]. 工程科学与技术, 2017, 49(1): 213-220.
Zhao Yongwei, Li Ting, Lin Boyu.Image classification method based on deep Learning coding model[J]. Science Technology and Engineering, 2017, 49(1): 213-220.
[11] 李智, 侯兴哲, 刘永相, 等. 基于深度学习的充电站容量规划方法[J]. 电力系统保护与控制, 2017, 45(21): 67-73.
Li Zhi, Hou Xingzhe, Liu Yongxiang, et al.A capacity planning method of charging station based on depth learning[J]. Power System Protection and Control, 2017, 45(21): 67-73.
[12] Hinton G, Osindero S, Teh Y W.A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
[13] Hinton G.To recognize shapes, first learn to generate images[J]. Progress in Brain Research, 2007, 165(6): 535-547.
[14] Lecun Y, Bottou L, Bengio Y, et al.Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[15] 张晓宇, 王晓远. 减少齿槽转矩的无刷直流电机优化设计[J]. 微电机, 2013, 46(1): 24-27.
Zhang Xiaoyu, Wang Xiaoyuan.Optimization of design to reduce cogging torque in permanent magnet brushless DC motor[J]. Micromotors, 2013, 46(1): 24-27.
[16] 史婷娜, 刘华, 陈炜, 等. 考虑逆变器非线性因素的表贴式永磁同步电机参数辨识[J]. 电工技术学报, 2017, 32(7): 77-83.
Shi Tingna, Liu Hua, Chen Wei, et al.Parameter identification of surface permanent magnet synchronous machines considering voltage-source inverter nonlinearity[J]. Transactions of China Electrotechnical Society, 2017, 32(7): 77-83.
[17] 孔祥玉, 郑锋, 鄂志君, 等. 基于深度信念网络的短期负荷预测方法[J]. 电力系统自动化, 2018, 42(5): 133-139.
Kong Xiangyu, Zheng Feng, E Zhijun, et al. Short term load forecasting based on deep belief network[J]. Automation of Electric Power Systems, 2018, 42(5): 133-139.