Fault diagnosis of permanent-magnet motors via a multiscale signal tuning auto-encoder

PDF(1803 KB)

Journal of Vibration and Shock ›› 2022, Vol. 41 ›› Issue (14) : 164-171.

WANG Wenlong1,HE Changbo1,WANG Xiaoxian2,LU Siliang1

Author information +

History +

Abstract

Permanent-magnet motors have been intensively adapted in industrial automation and electrical vehicles. Motor fault diagnosis is of significant to guarantee the accuracy of motion control and to avoid the breakdown loss. Modern signal processing and artificial intelligence methods have been applied in motor fault diagnosis. However, detecting the motor faults in heavy noise conditions is still a challenge. This study designs a new multiscale signal tuning auto-encoder to improve the accuracy of motor fault diagnosis. First, the vibration signal of the motor is acquired, and the signal is decomposed into multiple components using wavelet transform. The effects of the multiscale features on the classification accuracy are investigated. The original signal is adjusted and reconstructed according to the information generated from the multiscale features. Finally, the adjusted signal is inputted into the auto-encoder model to realize motor fault recognition. The experimental results indicate that the proposed method can effectively identify 8 types of motor healthy and fault conditions and has good anti-noise capacity and stability.
Key words: permanent-magnet motors; fault diagnosis; wavelet transform; multiscale signal tuning; auto-encoder

Key words

permanent-magnet motors / fault diagnosis / wavelet transform / multiscale signal tuning / auto-encoder

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

WANG Wenlong1,HE Changbo1,WANG Xiaoxian2,LU Siliang1. Fault diagnosis of permanent-magnet motors via a multiscale signal tuning auto-encoder[J]. Journal of Vibration and Shock, 2022, 41(14): 164-171

References

[1] 李涛，段礼祥，张东宁. 自适应卷积神经网络在旋转机械故障诊断中的应用[J]. 振动与冲击,2020,39(16):275-282+288.
LI Tao, DUAN Li-xiang, ZHANG Dong-ning. Application of adaptive convolutional neural network in rotating machinery fault diagnosis [J]. Vibration and Shock,2020,39(16) 275-282+288.
[2] 昝涛,王辉,刘智豪,王民,高相胜.基于多输入层卷积神经网络的滚动轴承故障诊断模型[J].振动与冲击,2020,39(12):142-149+163.
ZAN Tao, WANG Hui, LIU Zhi-hao, WANG Min, GAO Xiang-sheng. A fault diagnosis model for rolling bearings based on a multi-input layer convolutional neural network [J].Vibration and Shock,2020,39(12):142-149+163.
[3] 郭明军，李伟光，杨期江，赵学智. 深度卷积神经网络在滑动轴承转子轴心轨迹识别中的应用[J].振动与冲击,2021,40(03):233-239+283.
GUO Ming-jun, LI Wei-guang, Yang Qi-jiang, Zhao Xue-zhi. Application of deep convolution neural network in identification of journal bearing rotor center orbit [J]. Vibration and Shock,2021,40(03):233-239+283.
[4] YAN Xiaoan, JIA Minping. A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling earing [J]. Neurocomputing, 2018, 313: 47-64.
[5] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504-507.
[6] KHAN S, YAIRI T. A review on the application of deep learning in system health management [J]. Mechanical Systems and Signal Processing, 2018, 107: 241-265.
[7] 胡晓依，荆云建，宋志坤，侯银庆. 基于CNN-SVM的深度卷积神经网络轴承故障识别研究[J]. 振动与冲击,2019,38(18):173-178.
HU Xiao-yi, JING Yun-jian, SONG Zhi-kun, HOU Yin-qing. Bearing fault identification by using deep convolution neural networks based on CNN-SVM [J]. Vibration and Shock,2019,38(18):173-178.
[8] 赵春华，胡恒星，陈保家，张毅娜，肖嘉伟. 基于深度学习特征提取和WOA-SVM状态识别的轴承故障诊断[J].振动与冲击,2019,38(10):31-37+48.
ZHAO Chun-hua, HU Heng-xing, CHEN Bao-jia, ZHANG Yi-na, XIAO Jia-wei. Bearing fault diagnosis based on deep learning feature extraction and WOA-SVM state recognition[J]. Vibration and Shock,2019,38(10):31-37+48.
[9] 杨平,苏燕辰,张振.基于卷积胶囊网络的滚动轴承故障诊断研究[J].振动与冲击,2020,39(04):55-62+68.
YANG Ping,SU Yan-chen,ZHANG Zhen. A study on rolling bearing fault diagnosis based on convolution capsule network [J]. Vibration and Shock,2020,39(04):55-62+68.
[10] HOANG D T, KANG H J. Rolling element bearing fault diagnosis using convolutional neural network and vibration image [J]. Cognitive Systems Research, 2019, 53: 42-50.
[11] LEI Jin-hao, LIU Chao, JIANG Dong-xiang. Fault diagnosis of wind turbine based on Long Short-term memory networks [J]. Renewable Energy, 2019, 133: 422-432.
[12] 李晴晴, 侯瑞春, 丁香乾. 基于改进堆叠自编码器的滚动轴承故障诊断[J].计算机工程与设计,2019,40(07):2064-2070.
LI Qing-qing, HOU Rui-chun, DING Xiang-qian. Roller bearing fault diagnosis based on improved stacked auto-encoder [J].Computer Engineering and Design ,2019,40(07):2064-2070.
[13] 徐活耀，陈里里. 基于堆栈稀疏自编码器的滚动轴承故障诊断[J].机床与液压,2020,48(14):190-194.
XU Huo-yao, CHEN Li-li. Fault diagnosis of rolling bearing based on stack sparse autoencoder[J]. Machine Tool and Hydraulics, 2020, 48(14): 190-19
[14] 陈仁祥，杨星，杨黎霞，王家序，徐向阳，陈思杨. 栈式稀疏加噪自编码深度神经网络的滚动轴承损伤程度诊断[J].振动与冲击,2017,36(21):125-131+137.
CHEN Ren-xiang, YANG Xing, YANG Li-xia, WANG Jia-xu, XU Xiang-yang, Chen Si-yang. Fault severity diagnosis method for rolling bearings based on a stacked sparse denoising auto-encoder [J]. Vibration and Shock, 2017, 36(21): 125 -131+137.
[15] 罗金，童靳于，郑近德，潘海洋，潘紫微. 基于EEMD和堆叠稀疏自编码的滚动轴承故障诊断方法[J].噪声与振动控制,2020,40(02):115-120.
LUO Jin, TONG Jin-yu, ZHENG Jin-de, PAN Hai-yang, PAN Zi-wei. Fault diagnosis method for rolling bearings based on EEMD and stacked sparse auto-encoder [J]. Noise and Vibration Control,2020,40(02):115-120.
[16] 张智恒，周凤星，严保康，喻尚. 基于改进堆叠稀疏降噪自编码器的轴承故障诊断[J] .轴承,2021(02):35-41.
ZHANG Zhi-heng, ZHOU Feng-xing, YAN Bao-kang, YU Shang. Fault diagnosis for bearings based on improved stacked sparse denoising auto-encoder [J]. Bearing, 2021(02): 35-41.
[17] 杨建华，韩帅，张帅，刘后广，唐超权. 强噪声背景下滚动轴承微弱故障特征信号的经验模态分解[J].振动工程学报,2020,33(03):582-589.
YANG Jian-hua, HAN Shuai, ZHANG Shuai, LIU Hou-guang, TANG Chao-quan. Empirical mode decomposition of weak fault characteristic signal of rolling bearing under strong noise background [J]. Chinese Journal of Vibration Engineering,2020,33(03):582-589.
[18] 徐元博，蔡宗琰，胡永彪，丁凯. 强噪声背景下频率加权能量算子和变分模态分解在轴承故障提取中的应用[J].振动工程学报,2018,31(03):513-522.
XU Yuan-bo, CAI Zong-yan, HU Yong-biao, DING Kai. A frequency-weighted energy operator and variational mode decomposition for bearing fault detection [J]. Chinese Journal of Vibration Engineering,2018,31(03):513-522.
[19] LI Yong, CHENG Gang, LIU Chang. Research on bearing fault diagnosis based on spectrum characteristics under strong noise interference [J]. Measurement,2021,169.108509
[20] He Qing-bo, Wang Jun, Liu Yong-bin, Dai Dao-yi, Kong Fan-rang. Multiscale noise tuning of stochastic resonance for enhanced fault diagnosis in rotating machines [J]. Mechanical Systems and Signal Processing,2012,28: 443-457.
[21] Lu S, Qian G, He Q, et al. In Situ Motor Fault Diagnosis Using Enhanced Convolutional Neural Network in an Embedded System[J]. IEEE Sensors Journal, 2020, 20(15):8287-8296.
[22] Xia M, Li T, Liu L, et al. Intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder [J]. IET Science Measurement & Technology, 2017, 11(6): 687-695.
[23] 庄雨璇,李奇,杨冰如,陈良,沈长青.基于LSTM的轴承故障诊断端到端方法[J].噪声与振动控制,2019,39(06):187-193.
ZHUANG Yu-xuan, LI Qi, YANG Bing-ru, CHEN Liang, SHEN Chang-qing. An end-to-end approach for bearing fault diagnosis based on LSTM [J]. Noise and Vibration Control, 2019, 39(06): 187-193.