基于有限样本的永磁同步电机退磁故障诊断方法

莫 钰; 李垣江; 魏海峰; 张 懿

doi:10.11993/j.issn.2096-3920.2021.05.011

基于有限样本的永磁同步电机退磁故障诊断方法

doi: 10.11993/j.issn.2096-3920.2021.05.011

江苏科技大学电子信息学院, 江苏镇江, 212003

基金项目: 国家自然科学基金项目资助(51977101)

详细信息

作者简介:
莫钰(1996-), 男, 硕士, 主要研究方向为水下机器人深度学习、故障诊断.

中图分类号: TM351 TP277.3
计量
- 文章访问数: 54
- HTML全文浏览量: 21
- PDF下载量: 17
- 被引次数: 0
出版历程
- 收稿日期: 2020-12-01
- 修回日期: 2020-12-17
- 刊出日期: 2021-10-31

Demagnetization Fault Diagnosis Method for a Permanent Magnet Synchronous Motor Based on Limited Samples

School of Electronic Information, Jiangsu University of Science and Technology, Zhenjiang 212003, China

摘要

摘要: 针对永磁同步电机(PMSM)因样本数据稀少、可用性低、特征弱化和结构复杂等因素引发的退磁识别问题, 提出一种融合稀疏自编码与最小二乘生成式对抗网络的退磁故障诊断方法。该方法首先采集PMSM的电磁转矩和磁动势分布数据构成有限样本集合, 其次采用最小二乘生成式对抗网络对样本在保持特征分布一致的条件下进行标签化扩张, 最后运用稀疏自编码网络和Soft max分类器对样本进行训练和分类, 实现退磁故障的诊断与识别。在模型训练和故障识别过程中, 一方面合理设计深度网络隐层节点、训练算法以及层数等影响学习效率的参数; 另一方面训练优化网络并测试验证网络的优劣以提高故障诊断性能。经过多次试验, 最终可实现PMSM退磁故障的有效诊断。
- 永磁同步电机 /
- 退磁 /
- 最小二乘生成对抗网络 /
- 故障诊断 /
- 稀疏自编码
Abstract: Aiming at the demagnetization identification problem of permanent magnet synchronous motor due to the sparse sample data, low availability, weak feature and complex structure, this paper proposes a demagnetization fault diagnosis method combining sparse self-encoding and least squares generative countermeasure network. This method first collects the electromagnetic torque and magnetomotive force distribution data of the permanent magnet synchronous motor to form a limited sample set. Secondly, the least squares generative confrontation network is used to label and expand the sample while maintaining the same feature distribution, and finally use sparse The self-encoding network and Soft max classifier train and classify the samples to realize the diagnosis and identification of demagnetization faults. In the process of model training and fault identification, on the one hand, the parameters that affect learning efficiency such as the hidden nodes of the deep network, the training algorithm and the number of layers are rationally designed; on the other hand, the optimized network is trained and tested and verified to improve the fault diagnosis performance. After many tests, the effective diagnosis of permanent magnet synchronous motor demagnetization fault was finally realized
- permanent magnet synchronous motor(PMSM) /
- demagnetization /
- fault diagnosis /
- least squares generative countermeasure network /
- sparse autoencoder

HTML全文

参考文献(26)

[1]	张明明, 刘维亭, 魏海峰, 等. 基于滑模观测器PMSM单相霍尔位置传感器故障容错控制算法[J]. 水下无人系统学报, 2019, 27(6): 651-657. Zhang Ming-ming, Liu Wei-ting, Wei Hai-feng, et al. PMSM Single-phase Hall Position Sensor Fault-tolerant Control Algorithm Based on Sliding Mode Observer[J]. Journal of Underwater Unmanned Systems, 2019, 27(6): 651-657.
[2]	尤钱亮, 魏海峰, 常徐, 等. 基于三自由度动态内模解耦的PMSM弱磁控制[J]. 水下无人系统学报, 2020, 28 (1): 57-66. You Qian-liang, Wei Hai-feng, Chang Xu, et al. PMSM Field Weakening Control Based on Three-degree-of- freedom Dynamic Internal Model Decoupling[J]. Journal of Underwater Unmanned Systems, 2020, 28(1): 57-66.
[3]	李红梅, 陈涛, 姚宏洋. 电动汽车PMSM退磁故障机理、诊断及发展[J]. 电工技术学报, 2013(8): 276-284. Li Hong-mei, Chen Tao, Yao Hong-yang. Demagnetization Fault Mechanism, Diagnosis and Development of Electric Vehicle PMSM[J]. Acta Electrotechnics, 2013(8): 276-284.
[4]	Ding S, Hang J, Li H, et al．Demagnetisation Fault Detection in PMSM Using Zero Sequence Current Components[J]. Electronics Letters, 2017, 53(3): 148-150．
[5]	Zhang Z, Xie Z, Ma H, et al．Analysis of Demagnetization Fault Back-EMF of Permanent Magnet Synchronous Motor Using Mathematical Model Based on Magnetic Field Superposition Principle[J]. Tekhnichna Elektrodynamika, 2016(2): 42-48.
[6]	李红梅, 陈涛. 基于分形维数的PMSM局部退磁故障诊断[J]. 电工技术学报, 2017, 32(7): 1-10. Li Hong-mei, Chen Tao. Fault Diagnosis of PMSM Local Demagnetization Based on Fractal Dimension[J]. Transactions of the Chinese Society of Electrical Engineering, 2017, 32(7): 1-10.
[7]	Hong J, Hyun D, Lee S B, et al. Automated Monitoring of Magnet Quality for Permanent Magnet Synchronous Motors at Standstill[J]. IEEE Transactions on Industry Application, 2010, 46(4): 1397-1405.
[8]	Holakooie M H, Ojaghi M, Taheri A. Full-order Luenberger Observer Based on Fuzzy-logic Control for Sensorless Field-oriented Control of a Single-sided Linear Induction Motor[J]. ISA Transactions, 2016, 60: 96-108.
[9]	许良, 赵吉文, 宋俊材, 等. 基于ALE-MRAS磁链观测器的永磁同步直线电机均匀退磁诊断研究[J]. 中国电机工程学报, 2019, 39(24): 7347-7350. Xu Liang, Zhao Ji-wen, Song Jun-cai, et al. Research on Uniform Demagnetization Diagnosis of Permanent Magnet Synchronous Linear Motor Based on ALE-MRAS Flux Linkage Observer[J]. Proceedings of the Chinese Society of Electrical Engineering, 2019, 39(24): 7347-7350.
[10]	Haddad R Z, Strangas E G. Fault Detection and Classification in Permanent Magnet Synchronous Machines Using Fast Fourier Transform and Linear Discriminant Analysis[C]//2013 9th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives. Valencia, Spain: IEEE, 2013: 99-104.
[11]	唐旭, 王秀和, 李莹. 三相不对称供电异步起动永磁同步电动机的退磁研究[J]. 中国电机工程学报, 2015, 35 (23): 6172-6178. Tang Xu, Wang Xiu-he, Li Ying. Study on Demagnetization of Asynchronous Start Permanent Magnet Synchronous Motor with Three-phase Asymmetrical Power Supply[J]. Proceedings of the Chinese Society of Electrical Engineering, 2015, 35(23): 6172-6178.
[12]	Yu F, Xu X．A Short-term Load Forecasting Model of Natural Gas Based on Optimized Genetic Algorithm and Improved BP Neural Network[J]. Applied Energy, 2014, 134: 102-113．
[13]	Jing C, Hou J. SVM and PCA Based Fault Classification Approaches for Complicated Industrial Process[J]. Neurocomputing, 2015, 167: 636-642.
[14]	袁圃, 毛剑琳, 向凤红, 等. 改进的基于遗传优化BP神经网络的电网故障诊断[J]. 电力系统及其自动化学报, 2017, 29(1): 118-122. Yuan Pu, Mao Jian-lin, Xiang Feng-hong, et al. Improved Grid Fault Diagnosis Based on Genetic Optimization BP Neural Network[J]. Journal of Electric Power System and Automation, 2017, 29(1): 118-122.
[15]	高佳程, 朱永利, 郑艳艳, 等. 基于VMD-WVD分布与堆栈稀疏自编码网络的局放类型识别[J]. 中国电机工程学报, 2019, 39(14): 4118-4129. Gao Jia-cheng, Zhu Yong-li, Zheng Yan-yan, et al. Partial Discharge Type Recognition Based on VMD-WVD Distribution and Stack Sparse Autoencoding Network[J]. Proceedings of the Chinese Society of Electrical Engineering, 2019, 39(14): 4118-4129.
[16]	Mao X, Li Q, Xie H, et al. On the Effectiveness of Least Squares Generative Adversarial Networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2019, 41(12): 2947-2960.
[17]	孙文珺, 邵思羽, 严如强. 基于稀疏自动编码深度神经网络的感应电动机故障诊断[J]. 机械工程学报, 2016, 52(9): 65-71. Sun Wen-jun, Shao Si-yu, Yan Ru-qiang. Induction Motor Fault Diagnosis Based on Sparse Automatic Coding Deep Neural Network[J]. Chinese Journal of Mechanical En- gineering, 2016, 52(9): 65-71.
[18]	黄守道, 邓建国, 罗德荣. 电机瞬态过程分析的MATLAB建模与仿真[M]. 北京: 电子工业出版社, 2013．
[19]	曲忠杰, 张志艳, 李丽, 等. 永磁同步发电机定子绕组匝间短路故障数学模型及其仿真[J]. 轻工学报, 2019, 34(1): 101-108. Qu Zhong-jie, Zhang Zhi-yan, Li Li, et al. Mathematical Model and Simulation of Short Circuit Fault of Stator Winding of Permanent Magnet Synchronous Generator[J]. Journal of Light Industry, 2019, 34(1): 101-108.
[20]	夏孟杰, 严冬冬, 杭俊, 等. 基于LabVIEW的永磁同步电机匝间短路故障在线诊断系统研究[J]. 日用电器, 2018 (155): 123-127. Xia Meng-jie, Yan Dong-dong, Hang Jun, et al. Research on the LabVIEW-based on-line Diagnosis System for Interturn Short Circuit Faults of Permanent Magnet Synchronous Motor[J]. Electrical Appliances, 2018(155): 123-127.
[21]	杨存祥, 刘树博, 张志艳. 矢量控制永磁同步电机失磁故障诊断方法研究[J]. 轻工学报, 2017, 32(4): 58-65. Yang Cun-xiang, Liu Shu-bo, Zhang Zhi-yan. Research on Fault Diagnosis Method of Vector Control Permanent Magnet Synchronous Motor Loss of Excitation[J]. Journal of Light Industry, 2017, 32(4): 58-65.
[22]	关世海, 赵东芝, 王步瑶, 等. 异步起动永磁同步电机非正常工况退磁分析[J]. 大电机技术, 2020(3): 7-12. Guan Shi-hai, Zhao Dong-zhi, Wang Bu-yao, et al. Demagnetization Analysis of Asynchronous Start Permanent Magnet Synchronous Motor under Abnormal Operating Conditions[J]. Large Motor Technology, 2020(3): 7-12.
[23]	张文达, 李争, 杜深慧, 等. 矩形转子槽异步起动永磁同步电机退磁问题研究[J]. 日用电器, 2018 (155): 90-95. Zhang Wen-da, Li Zheng, Du Shen-hui, et al. Research on the Demagnetization Problem of Asynchronous Start Permanent Magnet Synchronous Motor with Rectangular Rotor Slots[J]. Electrical Appliances, 2018 (155): 90-95.
[24]	唐旭, 王秀和, 徐定旺. 异步起动永磁同步电动机起动过程中永磁体平均工作点的解析计算[J]. 电机与控制学报, 2017, 21(5): 8-14. Tang Xu, Wang Xiu-he, Xu Ding-wang. Analytic Calculation of the Average Operating Point of Permanent Magnets during the Starting Process of Asynchronous Start Permanent Magnet Synchronous Motors[J]. Journal of Electrical Machines and Control, 2017, 21(5): 8-14.
[25]	唐任远. 现代永磁电机理论与设计[M]. 北京: 机械工业出版社, 2008: 13-34.
[26]	丁頔, 南国防. CNN-RNN融合法在旋转机械故障诊断中的应用[J]. 轻工学报, 2020, 35(1): 102-108. Ding Di, Nan Guo-fang. The Application of CNN-RNN Fusion Method in the Fault Diagnosis of Rotating Machinery[J]. Journal of Light Industry, 2020, 35(1): 102-108.