基于特征重构深度置信网络的车用电机复合故障定位研究

doi:10.3901/JME.2024.06.091

摘要/Abstract

摘要： 永磁同步电机(Permanent magnet synchronous motor, PMSM)故障产生的机理较为复杂且每种电机故障的产生通常相互关联，复合故障定位是其故障诊断研究的难点所在。在电动汽车应用场合中，PMSM普遍存在变转速工作模式，变工况下的PMSM故障定位在工程应用中将具有重要价值。为了提高变转速工况下车用PMSM的复合故障定位精度，对基于特征重构和深度置信网络(Deep belief network, DBN)的新型PMSM复合故障定位方法进行研究。首先基于PMSM的振动特性分析，明晰转子偏心及轴承内圈故障下电机的复合故障特征分量；然后采用Vold-Kalman阶比追踪(Vold-Kalman filtering order tracking，VKF-OT)和角域重构算法实现对复合故障特征分量提取与重构，以减弱或消除转速变化对复合故障特征的影响。最后将特征重构信号用于构建基于DBN的故障定位模型，从而实现变转速工况下车用电机复合故障的定位。试验结果表明，基于特征重构深度置信网络的复合故障定位精度可达99.5%。

关键词: 永磁同步电机, 变转速, 复合故障, 故障定位, 深度置信网络

Abstract: The faulting mechanism of permanent magnet synchronous motor (PMSM) is complicated. Meanwhile, the occurrence of each kind of motor fault type is usually related to other faults. Therefore, the compound fault location of PMSM is difficult to be researched. Besides that, it’s common for PMSM to operate under variable speed conditions in automotive applications. Thus, realizing the fault location under variable operating conditions would be of great value in engineering applications. In order to improve the compound fault location accuracy of PMSM under variable speeds, a novel PMSM compound fault location method based on feature reconstruction and the deep belief network (DBN) is studied. Firstly, based on the vibration characteristic analysis of PMSM, the compound fault characteristic components of PMSM under rotor eccentricity, bearing inner ring fault, and the faulting mechanism of the compound fault are clarified. Next, the Vold-Kalman filtering order tracking (VKF-OT) and the angle-domain reconstruction algorithms are employed to extract the compound fault feature component and reconstruct the signal, thus the influence of variable speeds on the compound fault feature could be weakened or eliminated. Finally, the reconstructed signal is used to construct the fault location model based on DBN, and the compound fault of PMSM under variable speeds can be diagnosed. The experimental results show that the compound-fault-location accuracy based on the feature reconstruction and DBN can reach 99.5%.

Key words: permanent magnet synchronous motor, variable speeds, compound fault, fault location, deep belief network

中图分类号:

TM341

赵嗣芳, 宋强, 王明生, 赖武轩. 基于特征重构深度置信网络的车用电机复合故障定位研究[J]. 机械工程学报, 2024, 60(6): 91-103.

ZHAO Sifang, SONG Qiang, WANG Mingsheng, LAI Wuxuan. Study of Compound Fault Location for Vehicle Motors Based on the Deep Belief Network with Feature Reconstruction[J]. Journal of Mechanical Engineering, 2024, 60(6): 91-103.

参考文献

[1] GONG Chao，HU Yihua，LI Wenzhen，et al. Hybrid DC-bus capacitor discharge strategy using internal windings and external bleeder for surface-mounted PMSM-based EV powertrains in emergency[J]. IEEE Transactions on Industrial Electronics，2021，68(3)：1905-1915.
[2] 李晓华，赵容健，田晓彤. 逆变器供电对电动汽车内置式永磁同步电机振动噪声特性影响研究[J]. 电工技术学报，2020，35(21)：4455-4464. LI Xiaohua，ZHAO Rongjian，TIAN Xiaotong. Study on vibration and noise characteristics of interior permanent magnet synchronous machine for electric vehicles by inverter[J]. Transactions of China Electrotechnical Society，2020，35(21)：4455-4464.
[3] 马琮淦，左曙光，杨德良. 电动车用永磁同步电机的转矩阶次特征分析[J]. 振动与冲击，2013，32(13)：81-87. Ma Conggan，ZUO Shuguang，YANG Deliang. Order feature analysis for torque ripple of permanent magnet synchronous motor for an electric vehicle[J]. Journal of Vibration and Shock，2013，32(13)：81-87.
[4] EBRAHIMI B M，FAIZ J，ROSHTKHARI M J. Static-，dynamic-，and mixed-eccentricity fault diagnoses in permanent-magnet synchronous motors[J]. IEEE Transactions on Industrial Electronics，2009，56(11)：4727-4739.
[5] MOOSAVI S S，ESMAILI Q，DJERDIR A，et al. Inter-turn fault detection in stator winding of PMSM using wavelet transform[C/CD]//2017 IEEE Vehicle Power and Propulsion Conference (VPPC). IEEE，2017：1-5.
[6] CHEN Yong，LIANG Siyuan，LI Wanfu，et al. Faults and diagnosis methods of permanent magnet synchronous motors：A review[J]. Applied Sciences，2019，9(2)，2116.
[7] ISHIKAWA T，SEKI Y，KURITA N. Analysis for fault detection of vector-controlled permanent magnet synchronous motor with permanent magnet defect[J]. IEEE Transactions on Magnetics，2013，49(5)：2331-2334.
[8] 曾冲，黄嵩，杨永明. 永磁同步电机定子齿磁通分析与偏心故障在线诊断[J].哈尔滨工业大学学报，2020，52(3)：186-194. ZENG Chong，HUANG Song，YANG Yongming. Tooth flux analysis and eccentricity fault diagnosis for permanent magnet synchronous motor[J]. Journal of Harbin Institute of technology，2020，52(3)：186-194.
[9] SONG Qiang，ZHAO Sifang，WANG Mingsheng. On the accuracy of fault diagnosis for rolling element bearings using improved DFA and multi-sensor data fusion method[J]. Sensors，2020，20(22)：6465.
[10] 陈勇，梁洪，王成栋. 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(1)：228-234. CHEN Yong，LIANG Hong，WANG Chengdong. Detection of stator inter-turn short-circuit fault in pmsm based on improved wavelet packet transform and signal fusion[J]. Transactions of China Electrotechnical Society，2020，35(1)：228-234
[11] 胡茑庆，陈徽鹏，程哲，等. 基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报，2019，55(7)：9-18. HU Niaoqing，CHEN Huipeng，CHENG Zhe，et al. Fault diagnosis for planetary gearbox based on EMD and deep convolutional neural networks[J]. Journal of Mechanical Engineering，2019，55(7)：9-18.
[12] ELBOUCHIKHI E，CHOQUEUSE V，AMIRAT Y，et al. An efficient Hilbert–Huang transform-based bearing faults detection in induction machines[J]. IEEE Transactions on Energy Conversion，2017，32(2)：401-413.
[13] ZHU Min，HU Wensong，FENG Guodong，et al. Vold-Kalman filtering order tracking based rotor flux linkage monitoring in PMSM[C/CD]//2018 XIII International Conf. on Elec. Machines (ICEM)，Alexandropoulos，Greece，2018：1972-1978.
[14] OSMAN S，WANG W. A morphological Hilbert-Huang transform technique for bearing fault detection[J]. IEEE Transactions on Instrumentation and Measurement，2016，65(11)：2646-2656.
[15] LECUN Y，BENGIO Y，HINTON G. Deeplearning[J]. Nature，2015，521(7553)：436-444．
[16] 赵光权，葛强强，刘小勇，等. 基于DBN的故障特征提取及诊断方法研究[J]. 仪器仪表学报，2016，37(9)：1946-1953. ZHAO Guangquan，GE Qiangqiang，LIU Xiaoyong，et al. Fault feature extraction and diagnosis method based on deep belief network[J]. Chinese Journal of Scientific Instrument，2016，37(9)：1946-1953.
[17] 王欢，郑安文，许小伟.永磁同步电机匝间短路-退磁耦合故障分析[J]. 微特电机，2018，46(11)：29-34. WANG Huan，ZHENG Anwen，XU Xiaowei. Fault analysis of interturn short-circuit-demagnetization of permanent magnet synchronous motor[J]. Small & Special Electrical Machines，2018，46(11)：29-34.
[18] MA Jinghe，QIU Chidong，LUO Jiajia，et al. The current eigenfrequencies for bearing fault of mixed eccentric motor based on amplitude modulation[J]. Applied Mechanics and Materials，2014，8(66)：273-276.
[19] 何水龙，沈徐红，蒋占四. 基于S函数三相异步电机复合故障特征研究[J]. 微电机，2019，52(9)：6-13. HE Shuilong，SHEN Xuhong，JIANG Zhansi. Research on fault characteristics of composite fault of three-phase asynchronous motor based on S-function[J]. Micromotors，2019，52(9)：6-13.
[20] 王臻，李承，林志芳. 定子电流二次方法的异步电机转子复合故障诊断[J]. 电工技术学报，2016，31(16)：50-56. WANG Zhen，LI Cheng，LIN Zhifang. Rotor composite fault diagnosis in asynchronous motor using the square calculation of stator current[J]. Transactions of China Electrotechnical Society，2016，31(16)：50-56.
[21] 贾朱植，杨理践，祝洪宇，等. 时变转速运行状态下鼠笼电机转子断条故障诊断[J]. 仪器仪表学报，2016，37(4)：834-842. JIA Zhuzhi，YANG Lijian，ZHU Hongyu，et al. Fault diagnosis of broken rotor bars in squirrel cage motor under time-varying rotating speed operation condition[J]. Journal of Instrumentation，2016，37(4)：834-842.
[22] ZHU Z，XIA Z，WU L，et al. Analytical modeling and finite-element computation of radial vibration force in fractional-slot permanent-magnet brushless machines[J]. IEEE Transactions on Industry Applications，2010，46(5)：1908-1918.
[23] RAKIB I，IQBAL H. Analytical model for predicting noise and vibration in permanent-magnet synchronous motors[J]. IEEE Transactions on Industry Applications，2010，46(6)：1810-1819.
[24] CAPPELLI L，COIA Y，MARIGNETTI F，et al. Analysis of eccentricity in permanent-magnet tubular machines[J]. IEEE Transactions on Industrial Electronics，2014，61(5)：2208-2216.
[25] FERHAT Ç. Detection of eccentricity fault based on vibration in the PMSM[J]. Results in Physics，2018，10(3)：760-765.
[26] LIN Fu，ZUO Shuguang，DENG Wenzhe，et al. Modeling and analysis of acoustic noise in external rotor in-wheel motor considering doppler effect[J]. IEEE Transactions on Industrial Electronics，2018，65(6)：4524-4533.
[27] 孟涛，廖明夫. 利用时延相关解调法诊断滚动轴承的故障[J]. 航空学报，2004，25(1)：41-44. MENG Tao，LIAO Mingfu. Fault diagnosis of rolling bearing using time delay correlation demodulation method[J]. Acta Aeronautica ET Astronautica Sinica，2004，25(1)：41-44.
[28] BOUDINAR A，BENOUZZA N，BENDIABDELLAH A，et al. Induction motor bearing fault analysis using a Root-MUSIC method[J]. IEEE Transactions on Industry Applications，2016，52(5)：3851-3860.
[29] CONG Feiyun，CHEN Jin，DONG Guangming，et al. Vibration model of rolling element bearings in a rotor-bearing system for fault diagnosis[J]. Journal of Sound and Vibration，2013，8(8)：2081-2097.
[30] 郭瑜，秦树人，汤宝平，等. 基于瞬时频率估计的旋转机械阶比跟踪[J]. 机械工程学报，2003(3)：32-36. GUO Yu，QIN Shuren，TANG Baoping，et al. Order tracking of rotating machinery based on instantaneous frequency estimation[J]. Journal of Mechanical Engineering，2003(3)：32-36.
[31] 章翔峰，孙文磊，姜宏. 基于VKF-OT和DFA的齿轮时变状态特征提取方[J]. 振动、测试与诊断，2018，38(2)：299-304，419. ZHANG Xiangfeng，SUN Wenlei，JIANG Hong. Gear time-varying state feature extraction method based on VKF-OT and DFA[J]. Journal of Vibration，Measurement & Diagnosis，2018，38(2)：299-304，419.