Fault diagnosis of permanent magnet motor stator winding based on stacked auto encoder

Authors

TIAN Guang-qiang, School of Intelligent Engineering, Huanghe Jiaotong University, Jiaozuo, Henan 454950, China
FENG Wen-cheng, State Grid Jiaozuo Power Supply Company, Jiaozuo, Henan 454000, China
WANG Fu-zhong, School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo, Henan 454000, China

Abstract

Objective: To improve the accuracy and comprehensiveness of permanent magnet motor stator winding fault diagnosis. Methods: A fault diagnosis model of permanent magnet motor stator winding based on stack autoencoder （SAE） was proposed, and a neural network composed of SAE and Softmax classifier was used to train the network with fault sample data. The simulated annealing particle swarm optimization （SAPSO） algorithm was used to optimize the connection weight and bias of the network, and determined the optimal network structure. Results: The network had been used to realize the fault diagnosis of inter-turn short-circuit, inter-phase short-circuit, inter-phase insulation reduction, and poor contact of the terminals of the permanent magnet motor stator windings. Compared with wavelet analysis +Softmax, spectrum analysis +Softmax and SAE+Softmax, the diagnostic accuracy of this method was the highest, and the diagnostic rate was 99.40%. Conclusion: The optimized SAE+Softmax fault diagnosis model has good robustness and is less affected by motor speed and load changes, which can improve the accuracy of permanent magnet motor stator winding fault diagnosis.

Publication Date

11-28-2021

First Page

92

Last Page

98

DOI

10.13652/j.issn.1003-5788.2021.11.017

Recommended Citation

Guang-qiang, TIAN; Wen-cheng, FENG; and Fu-zhong, WANG (2021) "Fault diagnosis of permanent magnet motor stator winding based on stacked auto encoder," Food and Machinery: Vol. 37: Iss. 11, Article 17.
DOI: 10.13652/j.issn.1003-5788.2021.11.017
Available at: https://www.ifoodmm.cn/journal/vol37/iss11/17

References

[1] 包西平, 吉智, 朱涛. 高性能永磁同步伺服系统研究现状及发展[J]. 微电机, 2014, 47（7）: 84-88.
[2] 朱学建, 马永, 冯渝, 等. 直角坐标机器人瓶坯装箱生产线控制系统[J]. 食品与机械, 2012, 28（6）: 187-189.
[3] 薛寒, 谢利理, 叶留义. 基于模糊推理的电机故障诊断专家系统研究[J]. 计算机测量与控制, 2010, 18（1）: 8-10.
[4] 梁伟铭, 陈诚, 任纪良, 等. 永磁同步电机定子匝间短路故障诊断的研究现状及发展趋势[J]. 微电机, 2013, 46（2）: 1-4.
[5] 刘毅, 郑志国. 基于参数模型永磁同步电机定子绕组匝间短路故障研究[J]. 电机与控制应用, 2015, 42（10）: 48-54.
[6] 吴娟娟, 皮薇薇. 永磁同步电机轻微匝间短路故障的检测方法[J]. 电气传动, 2020, 50（4）: 98-103.
[7] 朱喜华, 李颖晖, 周飞帆, 等. 基于改进EMD算法的永磁同步电机故障特征提取[J]. 微电机, 2011, 44（2）: 65-69.
[8] 陈勇, 梁洪, 王成栋, 等. 基于改进小波包变换和信号融合的永磁同步电机匝间短路故障检测[J]. 电工技术学报, 2020, 35（S1）: 228-234.
[9] 袁国强, 李颖晖, 杨有泽. 基于局域均值分解的永磁同步电机故障诊断仿真[J]. 电光与控制, 2014, 21（10）: 106-109.
[10] 李垣江, 张周磊, 李梦含, 等. 采用深度学习的永磁同步电机匝间短路故障诊断方法[J]. 电机与控制学报, 2020, 24（9）: 173-180.
[11] 张周磊, 李垣江, 李梦含, 等. 基于深度学习的永磁同步电机故障诊断方法[J]. 计算机应用与软件, 2019, 36（10）: 123-129.
[12] 汪鑫, 王艳, 纪志成. 基于改进ELM的永磁同步电机故障诊断算法[J]. 系统仿真学报, 2017, 29（3）: 646-653.
[13] 陈柄任, 李颖晖, 李哲, 等. 基于流形学习的PMSM早期匝间短路故障特征提取[J]. 电力系统保护与控制, 2016, 44（17）: 18-19.
[14] 王攀, 陈雪娇. 基于堆栈式自动编码器的加密流量识别方法[J]. 计算机工程, 2018, 44（11）: 140-147.
[15] 屈相帅, 段斌, 尹桥宣, 等. 基于稀疏自动编码器深度神经网络的电能质量扰动分类方法[J]. 电力自动化设备, 2019, 39（5）: 157-162.
[16] 崔江, 唐军祥, 龚春英, 等. 一种基于改进堆栈自动编码器的航空发电机旋转整流器故障特征提取方法[J]. 中国电机工程学报, 2017, 37（19）: 5 696-5 706.
[17] 王惠中, 贺珂珂, 房理想. 深度学习在电机故障诊断中的应用研究[J]. 计算机仿真, 2019, 36（10）: 423-428.
[18] 陈福集, 黄亚驹. 基于SAPSO_ＲBF神经网络的网络舆情预测研究[J]. 武汉理工大学学报（信息与管理工程版）, 2017, 39（4）: 422-426.
[19] 巩敦卫, 曾现峰, 张勇. 基于改进模拟退火算法的机器人全局路径规划[J]. 系统仿真学报, 2013, 25（3）: 480-483, 488.