基于神经网络和粒子群算法的永磁同步电机运行与振动性能优化

微特电机 ›› 2023, Vol. 51 ›› Issue (2): 26-30.

基于神经网络和粒子群算法的永磁同步电机运行与振动性能优化

胡文韬¹, 李华², 郑东¹, 华春蓉¹, 沈思思³

1.西南交通大学机械工程学院,成都 610031;
2.山东省东营市胜利油田石油化工总厂中心化验室,东营 257000;
3.国家知识产权局专利局专利审查协作四川中心,成都 610014

收稿日期:2021-12-29 出版日期:2023-02-28 发布日期:2023-03-01
通讯作者: 郑东(1987—),男,硕士生导师,主要研究方向为永磁同步电机振动与噪声控制。
作者简介:胡文韬(1997—),男,硕士研究生,主要研究方向为电机振动与噪声控制。

Optimization of Operation and Vibration Performance of Permanent Magnet Synchronous Motor Based on Neural Network and Particle Swarm Algorithm

HU Wentao¹, LI Hua², ZHENG Dong¹, HUA Chunrong¹, SHEN Sisi³

1. School of Mechanical Engineering, Southwest Jiaotong University,Chengdu 610031,China;
2. Central Laboratory of Petrochemical Complex, Shengli Oilfield, Dongying City, Shandong Province, Dongying 257000,China;
3. Sichuan Center for Patent Examination Cooperation of the Patent Office of the State IntellectualProperty Office, Chengdu 610014,China

Received:2021-12-29 Online:2023-02-28 Published:2023-03-01

摘要/Abstract

摘要： 为了兼顾新能源驱动电机的运行性能和振动性能,对该型号驱动电机进行综合优化。采用数值计算方法分析8极48槽永磁同步电机的主要结构参数对电机运行性能和振动性能的影响,建立神经网络模型拟合电机结构参数与性能表现之间的映射关系,并基于测试数据集进行验证;使用粒子群算法优化电机的结构参数,从而获得驱动电机振动性能和运行性能之间的非劣最优解。优化后的电机与初始样机相比在驱动性能基本保持不变的基础上,转矩脉动和振动位移方面都有了明显的优化。

关键词: 永磁同步电机, 电磁振动, 粒子群算法, 神经网络, 多目标优化

Abstract: In order to take into account the operation and virbation performance of the new energy drive motor, the drive motor of the model was comprehensively optimized.The numerical calculation method was used to analyze the influence of the main structural parameters of the 8-pole 48-slot synchronous motor on the different performance of the motor, and a neural network model was established to fit the mapping relationship between the motor's structural parameters and performance. The particle swarm algorithm was used to optimize the structural parameters of the motor to obtain a non-inferior optimal solution between the vibration performance and the running performance of the drive motor. Compared with the original prototype, the optimized motor had obvious optimization in terms of torque ripple and vibration displacement.

Key words: permanent magnet synchronous motor(PMSM), electromagnetic vibration, particle swarm algorithm, neural network, multi-objective optimization

中图分类号:

TM351

胡文韬, 李华, 郑东, 华春蓉, 沈思思. 基于神经网络和粒子群算法的永磁同步电机运行与振动性能优化[J]. 微特电机, 2023, 51(2): 26-30.

HU Wentao, LI Hua, ZHENG Dong, HUA Chunrong, SHEN Sisi. Optimization of Operation and Vibration Performance of Permanent Magnet Synchronous Motor Based on Neural Network and Particle Swarm Algorithm[J]. Small & Special Electrical Machines, 2023, 51(2): 26-30.

参考文献

[1] 吕纯池.新能源电动汽车核心技术发展现状与趋势综述[J].科技与创新,2020(17):80-81.
[2] 沈思思,郑东,张静.汽车空调箱鼓风机电机振动噪声控制研究[J].噪声与振动控制,2020,40(5):133-139,151.
[3] 张静,王洪强,张继鑫,等.汽车空调箱鼓风机噪声源识别的实验研究[J].噪声与振动控制,2019,39(5):73-77.
[4] ZOU J,LAN H,XU Y,et al.Analysis of global and local force harmonics and their effects on vibration in permanent magnet synchronous machines[J].IEEE Transactions on Energy Conversion,2017,32(4):1523-1532.
[5] SHIN H J,CHOI J Y ,PARK H I ,et al.Vibration analysis and measurements through prediction of electromagnetic vibration sources of permanent magnet synchronous motor based on analytical magnetic field calculations[J].IEEE Transactions on Magnetics,2012,48(11):4216-4219.
[6] XIANG C ,LIU F ,LIU H ,et al.Nonlinear dynamic behaviors of permanent magnet synchronous motors in electric vehicles caused by unbalanced magnetic pull[J].Journal of Sound & Vibration,2016:277-294.
[7] LAZARI P,WANG J B, CHEN L,et al.A computationally efficient design technique for electric-vehicle traction machines[J].IEEE Transactions on Industry Applications,2014,50(5):3203-3213.
[8] 肖兰,郭嘉,范镇南.笼型异步电机启动场路耦合时步有限元仿真[J].矿山机械,2011,39(3):119-123.
[9] 胡之光.电机电磁场的分析与计算[M].-2版(修订本).北京:机械工业出版社,1989.
[10] 黄锐,郑东.基于Kriging模型和粒子群算法的不等厚永磁电机优化设计[J].微特电机,2020,48(7):19-23.
[11] HECHT-NIELSEN.Theory of the backpropagation neural network[J].International Joint Conference on Neural Networks,1989(1):593-605.
[12] LIPPMANN R P .An introduction to computing with neural nets[J].IEEE ASSP Magazine,1988,4(2):4-22.
[13] 沈思思.新能源汽车驱动电机运行与振动性能的综合优化[D].成都:西南交通大学,2020.

[1]	刘慧娟, 周佳明, 易元元, 宋腾飞. 永磁同步电机拓扑结构对散热性能的影响[J]. 微特电机, 2023, 51(2): 13-19.
[2]	王雅哲, 马其华. 基于JMAG与modeFRONTIER的车用永磁同步电机多目标优化[J]. 微特电机, 2023, 51(2): 31-37.
[3]	田艳丰, 吴宋林, 王哲, 王健宇. 永磁同步电机的双口三自由度内模自适应控制器设计[J]. 微特电机, 2023, 51(1): 32-37.
[4]	高鹏, 尹强, 孙乐, 姜泽超, 刘国栋. 一种抑制齿槽转矩的高精度定位伺服控制方法[J]. 微特电机, 2022, 50(9): 36-42.
[5]	孙维国, 胡岩, 吴家成. 电动汽车用增程发电机的设计与优化[J]. 微特电机, 2022, 50(8): 8-14.
[6]	刘娜, 钟成堡, 陈飞龙, 杨文德. 极弧系数对永磁同步电机齿槽转矩影响的分析[J]. 微特电机, 2022, 50(8): 15-18.
[7]	李飞, 邱鑫, 杨建飞, 陈秋仲, 陈洪生. 基于非线性积分滑模补偿的永磁同步电机无差拍预测控制[J]. 微特电机, 2022, 50(8): 31-36.
[8]	桂永麟, 于新红. 永磁同步电机全速域无传感器控制[J]. 微特电机, 2022, 50(8): 37-41.
[9]	李跃, 刘侃, 张冰鑫, 周世超, 胡伟, 屈阳华, 耿扬策. 基于高频阻抗检测的隐极式永磁同步电机三步无位置传感器起动技术[J]. 微特电机, 2022, 50(7): 1-8.
[10]	孟庆博, 王志强. 基于电流前馈的储能飞轮充放电功率控制[J]. 微特电机, 2022, 50(7): 29-33.
[11]	杨宇健, 赵世伟, 杨向宇. 基于梯度下降搜索法的IPMSM最大转矩电流比控制[J]. 微特电机, 2022, 50(7): 34-39.
[12]	袁潇, 杨泽斌, 徐雷钧. 基于改进型滑模观测器的永磁同步电机无传感器控制策略[J]. 微特电机, 2022, 50(7): 47-52.
[13]	汪世平, 祝海荣, 蔡慧, 邹志杨, 马玉龙. 基于变正则化参数仿射投影算法的PMSM参数辨识[J]. 微特电机, 2022, 50(6): 36-40.
[14]	周尔卓, 沈艳霞. 基于RBF神经网络的直驱风力发电系统反推控制[J]. 微特电机, 2022, 50(6): 41-45.
[15]	薛赛, 贺青川, 潘骏, 黄晓诚. 基于分形盒维数和GA-SVM的PMSM动态偏心故障诊断方法研究[J]. 微特电机, 2022, 50(5): 1-6.