High-Resistance Connection Fault Diagnosis of Permanent Magnet Synchronous Motor Based on Two-Dimensional Recursive Fusion of Multi-Channel Signals and ECA-ConvNeXt
Ding Wei1, Song Juncai2, Lu Siliang1, Wang Xiaoxian3
1. School of Electrical Engineering and Automation Anhui University Hefei 230601 China; 2. School of Internet Anhui University Hefei 230039 China; 3. School of Electronic and Information Engineering Anhui University Hefei 230601 China
Abstract：The measurement error of traditional high-resistance connection (HRC) fault diagnosis method for permanent magnet synchronous motor (PMSM) is typically high, and it is difficult to evaluate HRC fault comprehensively and quantitatively. Modern diagnosticmethods of HRC fault are realized by the symmetry monitoring system of injection signal method and zero-sequence component detection method. However, these methods based on signal injection strategy are invasive diagnostics, which may have an impact on the original drive system. The method based on zero sequence component must have neutral points and additional resistance network, and the application scenario is limited. To solve the above problems, this paper proposes a data-driven method to realize the HRC fault diagnosis of PMSM, and establishes the fault mode of the system through a large number of existing historical data, without the need for a prior known model or signal mode. Firstly, a simulated PMSM model is established to obtain the three-phase current signal as an effective fault signal. Secondly, the recursive graph method is innovatively introduced to map the three-phase current signals into two-dimensional recursive images and perform multi-channel fusion. The fused images contain more feature information and avoid the influence of artificial feature extraction during fault signal processing. Then, ConvNeXt is introduced to effectively solve the gradient dispersion problem of the existing classification model, and a new ECA-ConvNeXt classification model is obtained by integrating the attention mechanism, which improves the adaptability of the network in the channel dimension and enhances the generalization ability of the model. The simulation results show that compared with the basic ConvNeXt, the accuracy of ECA-ConvNeXt on the test set sample is improved from 98.05% to 99.18%. Compared with models such as GoogLeNet, ResNet and Swin Transformer, the ECA-ConvNeXt proposed in this paper also has higher performance indexes and more advantages in identifying early HRC faults. To verify the robustness of the model in the presence of input data noise, Gaussian noise is added to the original input data. The results show that the effect of these noises is not significant. Finally, through the establishment of prototype experimental platform verification, it is proved that the identification accuracy of the new method proposed in this paper is as high as 97.35%, and it can accurately identify the location and severity of high resistance contact faults of permanent magnet synchronous motors. Based on the analysis of simulation and test data, this paper draws the following conclusions: (1) This paper uses data-driven method to realize the non-invasive diagnosis of HRC fault of permanent magnet synchronous motor, avoiding the problem that the mathematical and electromagnetic relationship is too complicated in the model diagnosis method. (2) The two-dimensional recursive graph signal conversion method is innovatively introduced into the field of high resistance fault diagnosis of permanent magnet motors, and one-dimensional three-phase current signals are transformed into two-dimensional recursive images respectively and channel fusion is carried out to enhance fault characteristics, eliminate the influence of artificial feature extraction, and lay a rich fault information foundation for the classification and recognition of HRC faults of permanent magnet synchronous motors. (3) An ECA-ConvNeXt classification model with added attention mechanism was proposed to solve the gradient dispersion problem, improve the adaptability of the model in the channel dimension, and increase the classification accuracy of the model on the experimental data set from 96.53% to 97.35%. The comparison between the proposed method and other classification models proves the superiority of this classification model.
丁伟, 宋俊材, 陆思良, 王骁贤. 基于多通道信号二维递归融合和ECA-ConvNeXt的永磁同步电机高阻接触故障诊断[J]. 电工技术学报, 2024, 39(20): 6397-6408.
Ding Wei, Song Juncai, Lu Siliang, Wang Xiaoxian. High-Resistance Connection Fault Diagnosis of Permanent Magnet Synchronous Motor Based on Two-Dimensional Recursive Fusion of Multi-Channel Signals and ECA-ConvNeXt. Transactions of China Electrotechnical Society, 2024, 39(20): 6397-6408.
[1] Chen Hao, He Jiangbiao, Guan Xing, et al.High- resistance connection diagnosis in five-phase PMSMs based on the method of magnetic field pendulous oscillation and symmetrical components[J]. IEEE Transactions on Industrial Electronics, 2022, 69(3): 2288-2299. [2] 崔刚, 熊斌, 黄康杰, 等. 电动汽车用永磁电机的失磁空间分布特性及影响因素[J]. 电工技术学报, 2023, 38(22): 5959-5974. Cui Gang, Xiong Bin, Huang Kangjie, et al.Spatial distribution characteristics and influencing factors of demagnetization of permanent magnet motor for electric vehicle[J]. Transactions of China Electrotechnical Society, 2023, 38(22): 5959-5974. [3] 沐俊文, 葛兴来, 朱丹. 地铁永磁牵引系统复矢量电流环稳定性研究[J]. 电气工程学报, 2022, 17(2): 92-100. Mu Junwen, Ge Xinglai, Zhu Dan.Research on current loop stability of metro permanent magnet traction system[J]. Journal of Electrical Engineering, 2022, 17(2): 92-100. [4] 陈少先, 丁树业, 申淑锋, 等. 船舶用表贴式永磁同步电机的电磁振动分析与抑制[J]. 电工技术学报, 2023, 38(5): 1275-1286, 1298. Chen Shaoxian, Ding Shuye, Shen Shufeng, et al.Analysis and suppression of electromagnetic vibration of surface mounted permanent magnet synchronous motor for ships[J]. Transactions of China Electrotechnical Society, 2023, 38(5): 1275-1286, 1298. [5] 周立, 苏美霞, 王杰. 永磁同步电机模糊多矢量模型预测控制[J]. 电气工程学报, 2022, 17(4): 181-192. Zhou Li, Su Meixia, Wang Jie.Fuzzy multi-vector model predictive control of permanent magnet syn- chronous motor[J]. Journal of Electrical Engineering, 2022, 17(4): 181-192. [6] 于艳君, 崔明恺, 柴凤. 双绕组永磁同步电机滑模变结构控制[J]. 电工技术学报, 2022, 37(22): 5799-5807. Yu Yanjun,Cui Mingkai, Chai Feng.Sliding mode variable structure control of a dual-winding per- manent magnet synchronous motor[J]. Transactions of China Electrotechnical Society, 2022, 37(22): 5799-5807. [7] 张伟伟, 肖飞, 刘计龙, 等. 轨道交通车辆永磁同步牵引系统断电区穿越控制策略[J]. 电工技术学报, 2021, 36(16): 3483-3492. Zhang Weiwei, Xiao Fei, Liu Jilong, et al.Power-off area traversing control strategy of permanent magnet synchronous motor traction system in rail transit vehicle[J]. Transactions of China Electrotechnical Society, 2021, 36(16): 3483-3492. [8] 杭俊, 孙无双, 赖江龙, 等. 基于跨极式探测线圈的双三相永磁同步电机故障诊断方法[J]. 电机与控制学报, 2023, 27(7): 163-173. Hang Jun, Sun Wushuang, Lai Jianglong, et al.Fault diagnosis method of dual three phase permanent magnet synchronous motor based on transpolar search coil[J]. Electric Machines and Control, 2023, 27(7): 163-173. [9] 陈昊, 张楠, 高彩霞, 等. 永磁同步电机匝间短路故障短路线圈定位方法[J]. 电机与控制学报, 2023, 27(3): 124-134. Chen Hao, Zhang Nan, Gao Caixia, et al.Fault coil location approach of permanent magnet synchronous motor with interturn short circuit fault[J]. Electric Machines and Control, 2023, 27(3): 124-134. [10] 张业成, 刘国海, 陈前. 基于电流波动特征的永磁同步电机匝间短路与局部退磁故障分类诊断研究[J]. 电工技术学报, 2022, 37(7): 1634-1643, 1653. Zhang Yecheng, Liu Guohai, Chen Qian.Discrimination of interturn short-circuit and local demagnetization in permanent magnet synchronous motor based on current fluctuation characteristics[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1634-1643, 1653. [11] Hu Rongguang, Wang Jiabin, Mills A R, et al.High-frequency voltage injection based stator interturn fault detection in permanent magnet machines[J]. IEEE Transactions on Power Electronics, 2021, 36(1): 785-794. [12] 高彩霞, 苗壮, 陈昊, 等. 基于线圈子单元的永磁同步电机健康与定子绕组短路故障数学模型[J]. 电工技术学报, 2023, 38(4): 957-969. Gao Caixia, Miao Zhuang, Chen Hao, et al.A mathematical model based on coil sub-element for permanent magnet synchronous motor with health and stator winding short-circuit fault[J]. Transactions of China Electrotechnical Society, 2023, 38(4): 957-969. [13] Kommuri S K, Park Y, Lee Sangbin.High-resistance fault control in permanent magnet synchronous motors[J]. IEEE/ASME Transactions on Mechatronics, 2020, 25(1): 271-281. [14] de la Barrera P M, Bossio G R, Solsona J A. High-resistance connection detection in induction motor drives using signal injection[J]. IEEE Transactions on Industrial Electronics, 2014, 61(7): 3563-3573. [15] de la Barrera P M, Bossio G R, Leidhold R. Online voltage sensorles shigh-resistance connection diagnosis in induction motor drives[J]. IEEE Transactions on Industrial Electronics, 2015, 62(7): 4374-4384. [16] Hang Jun, Wu Han, Ding Shichuan, et al.A DC-flux-injection method for fault diagnosis of high-resistance connection in direct-torque-controlled PMSM drive system[J]. IEEE Transactions on Power Electronics, 2020, 35(3): 3029-3042. [17] Hu Rongguang, Wang Jiabin, Mills A R, et al.Detection and classification of turn fault and high resistance connection fault in permanent magnet machines based on zero sequence voltage[J]. IEEE Transactions on Power Electronics, 2020, 35(2): 1922-1933. [18] Zhang Jianzhong, Hang Jun, Ding Shichuan, et al.Online diagnosis and localization of high-resistance connection in PMSM with improved fault indicator[J]. IEEE Transactions on Power Electronics, 2017, 32(5): 3585-3594. [19] Wang Hui, Lu Siliang, Qian Gang, et al.A two-step strategy for online fault detection of high-resistance connection in BLDC motor[J]. IEEE Transactions on Power Electronics, 2020, 35(3): 3043-3053. [20] Hang Jun, Zhang Jianzhong, Ding Shichuan, et al.Fault diagnosis of high-resistance connection in a nine-phase flux-switching permanent-magnet machine considering the neutral-point connection model[J]. IEEE Transactions on Power Electronics, 2017, 32(8): 6444-6454. [21] 王骁贤, 陆思良, 何清波, 等. 变转速工况下基于多传感器信号深度特征融合的电机故障诊断研究[J]. 仪器仪表学报, 2022, 43(3): 59-67. Wang Xiaoxian, Lu Siliang, He Qingbo, et al.Motor fault diagnosis based on deep feature fusion of multi-sensor data under variable speed condition[J]. Chinese Journal of Scientific Instrument, 2022, 43(3): 59-67. [22] Seshadrinath J, Singh B, Panigrahi B K.Incipient turn fault detection and condition monitoring of induction machine using analytical wavelet transform[J]. IEEE Transactions on Industry Applications, 2014, 50(3): 2235-2242. [23] 武智超, 王慧, 王吉亮, 等. 基于阵列漏磁信号分析的无刷直流电机高阻接触故障诊断研究[J]. 电子测量与仪器学报, 2021, 35(11): 108-114. Wu Zhichao, Wang Hui, Wang Jiliang, et al.Fault diagnosis of high resistance connection in brushless DC motor based on analysis of array leakage flux signals[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(11): 108-114. [24] Liu Xiaoping, Xia Lijian, Shi Jian, et al.A fault diagnosis method of rolling bearing based on improved recurrence plot and convolutional neural network[J]. IEEE Sensors Journal, 2023, 23(10): 10767-10775. [25] 杨秋玉, 阮江军, 张灿, 等. 基于定量递归分析的高压断路器机械缺陷辨识及应用[J]. 电工技术学报, 2020, 35(18): 3848-3859. Yang Qiuyu, Ruan Jiangjun, Zhang Can, et al.Study and application of mechanical defect identification for high-voltage circuit breakers using recurrence quantification analysis[J]. Transactions of China Electrotechnical Society, 2020, 35(18): 3848-3859. [26] Wen Long, Li Xinyu, Gao Liang, et al.A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5990-5998. [27] Lu Siliang, Qian Gang, He Qingbo, 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. [28] Hu Yuan, Li Xiang, Zhou Nan, et al.A sample update-based convolutional neural network framework for object detection in large-area remote sensing images[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(6): 947-951. [29] Liu Zhuang, Mao Hanzi, Wu Chaoyuan, et al.A ConvNet for the 2020s[C]//2022 IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022: 11966-11976. [30] Wang Qilong, Wu Banggu, Zhu Pengfei, et al.ECA-net: efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020: 11531-11539.
2024, Vol. 39 
