基于多尺度特征融合卷积神经网络的牵引电机转子断条故障诊断方法

doi:10.19595/j.cnki.1000-6753.tces.250208

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (7314 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract A traction motor is a key component of the traction transmission system in high-speed trains, which converts electrical energy into mechanical energy and provides power for the train. Accurate diagnosis of a broken rotor bar fault in a traction motor is crucial for the safe operation of high-speed trains, and it is also a key aspect of fault prognostics and health management (PHM). When a broken rotor bar fault occurs in the traction motor, the fault frequency is close to the power supply frequency, and the amplitude is small, making it easy to be masked. The fault frequency varies widely, resulting in significant changes in feature scale. Extracting practical features and obtaining accurate diagnosis results are challenging. This paper proposes a fault diagnosis method based on multi-scale feature fusion convolutional neural networks (MSFFCNN).
To eliminate the power frequency component in the current signal and enhance the fault features, a current preprocessing method based on Hilbert transform (HT) is proposed. Firstly, the envelope analysis is used to eliminate the power supply frequency and enhance the fault features. Then, the obtained envelope signal is converted into an image. A multi-scale feature extraction module with attention fusion is constructed. Multiple convolution kernels are used to extract features simultaneously. Efficient channel attention (ECA) is employed for the weighted fusion of multi-scale features to enhance relevant features and suppress irrelevant features. Then, the MSFFCNN is designed to identify broken rotor bar faults and their corresponding fault degrees. Experiments were conducted on two datasets of broken rotor bars, and ablation and comparison experiments were designed to verify the proposed method.
The results of the ablation experiment show that, compared with the pretreatment without HT, the accuracy of the proposed method increases by 13.37%, 1.40%, and 0.80% when the training ratio is 20%, 40%, and 60%, respectively. Compared to the case without the ECA mechanism, the accuracy of the proposed method increases by 0.69%, 0.62%, and 0.15% when the training ratio is 20%, 40%, and 60%, respectively. The proposed method achieves a higher average diagnostic accuracy and F1 score on both data sets than the comparison method at all training set ratios. When the proportion of the training set is 60%, the average diagnostic accuracy of the proposed method on the two data sets reaches 99.85% and 99.82%. The visualization results show that the feature boundaries of different fault categories extracted by the proposed method are clear, which can effectively distinguish the broken rotor bar fault under various loads and power supply frequencies.
The following conclusions can be drawn. (1) HT is used for current preprocessing to eliminate the influence of the power frequency component, and the broken rotor bar fault features are enhanced. The generated images contain more detailed information, making it easier to extract practical fault features and improve diagnostic accuracy. (2) ECA fuses multi-scale features to automatically realize effective feature extraction and avoid overfitting, enabling the model to adapt to different loads and power supply frequencies. As a result, the diagnostic accuracy and generalization performance of the model are improved. (3) Compared with the related methods, the proposed diagnostic method shows strong feature extraction ability, noise resistance, and generalization performance. It can identify broken rotor bar faults more accurately, providing a reference for the targeted setting of traction motor maintenance plans.

Key words： Hilbert transformation multi-scale convolutional attention mechanism fault diagnosis broken rotor bar

Received: 11 February 2025

PACS:

TM307

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Ding Zhuo
	Zhang Hesheng
	Tang Yicong
	Hong Jianfeng

Cite this article:

Ding Zhuo,Zhang Hesheng,Tang Yicong等. The Fault Diagnosis Method of Traction Motor Broken Rotor Bar Based on Multi-Scale Feature Fusion Convolutional Neural Networks[J]. Transactions of China Electrotechnical Society, 2026, 41(2): 512-526.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.250208 OR https://dgjsxb.ces-transaction.com/EN/Y2026/V41/I2/512

[1] 丁荣军, 宋文胜, 麻宸伟. 列车电力牵引系统控制与状态监测综述及展望[J]. 中国电机工程学报, 2024, 44(17): 6973-6991.
Ding Rongjun, Song Wensheng, Ma Chenwei.Overview and prospect of control and condition monitoring of train electric traction systems[J]. Proceedings of the CSEE, 2024, 44(17): 6973-6991.
[2] 《“复兴号”中国标准动车组》编委会. “复兴号”中国标准动车组(CR400型)[M]. 北京: 中国铁道出版社有限公司, 2012.
[3] 张大勇. 铁路交流牵引电机故障诊断技术研究及应用[J]. 中国铁路, 2021(5): 1-11.
Zhang Dayong.Research and application of fault diagnosis technology for railway AC traction motor[J]. China Railway, 2021(5): 1-11.
[4] Atta M E E, Ibrahim D K, Gilany M I. Broken bar fault detection and diagnosis techniques for induction motors and drives: state of the art[J]. IEEE Access, 2022, 10: 88504-88526.
[5] Bazghandi R, Hoseintabar M M, Abolghasemi V, et al.A novel mode un-mixing approach in variational mode decomposition for fault detection in wound rotor induction machines[J]. Energies, 2023, 16(14): 5551.
[6] Puche-Panadero R, Pineda-Sanchez M, Riera-Guasp M, et al.Improved resolution of the MCSA method via Hilbert transform, enabling the diagnosis of rotor asymmetries at very low slip[J]. IEEE Transactions on Energy Conversion, 2009, 24(1): 52-59.
[7] 夏志凌, 胡凯波, 刘心悦, 等. 基于变模态分解的异步电机转子断条故障诊断[J]. 电工技术学报, 2023, 38(8): 2048-2059.
Xia Zhiling, Hu Kaibo, Liu Xinyue, et al.Fault diagnosis of rotor broken bar in induction motor based on variable mode decomposition[J]. Transa- ctions of China Electrotechnical Society, 2023, 38(8): 2048-2059.
[8] Singh G, Naikan V N A. Detection of half broken rotor bar fault in VFD driven induction motor drive using motor square current MUSIC analysis[J]. Mechanical Systems and Signal Processing, 2018, 110: 333-348.
[9] 曹建刚, 张博, 贺竹林. 希尔伯特变换在牵引电机转子断条故障诊断中的应用研究[J]. 城市轨道交通研究, 2013, 16(5): 46-49.
Cao Jiangang, Zhang Bo, He Zhulin.Application of Hilbert transform in fault diagnosis of traction motors[J]. Urban Mass Transit, 2013, 16(5): 46-49.
[10] 王万丁, 宋向金, 陈前, 等. 采用整流技术的变频供电感应电机转子断条故障诊断方法[J]. 电工技术学报, 2022, 37(16): 4074-4083.
Wang Wanding, Song Xiangjin, Chen Qian, et al.Broken rotor bar fault diagnosis in inverter-fed induction motors using the rectification technology[J]. Transactions of China Electrotechnical Society, 2022, 37(16): 4074-4083.
[11] 王照伟, 郭雯君, 宋向金, 等. 融合TKEO和Goerztel算法的感应电机转子断条故障诊断[J]. 电工技术学报, 2024, 39(12): 3679-3690.
Wang Zhaowei, Guo Wenjun, Song Xiangjin, et al.Fault diagnosis of broken rotor bar in induction motor based on TKEO and Goertzel algorithm[J]. Transa- ctions of China Electrotechnical Society, 2024, 39(12): 3679-3690.
[12] Kong Haipeng, Cheng Xiaoqing, Niu Buzhao, et al.Fault diagnosis method for EMU traction motor based on machine learning[C]//2024 Global Reliability and Prognostics and Health Management Conference, Beijing, China, 2024: 1-6.
[13] 张坤鹏, 李昊, 安春兰, 等. 融合能量熵编码和分类模型的牵引电机故障诊断[J]. 铁道学报, 2023, 45(9): 64-73.
Zhang Kunpeng, Li Hao, An Chunlan, et al.Fault diagnosis of traction motor based on fusion of energy entropy coding and classification model[J]. Journal of the China Railway Society, 2023, 45(9): 64-73.
[14] Abdellatif S, Aissa C, Hamou A A, et al.A deep learning based on sparse auto-encoder with MCSA for broken rotor bar fault detection and diagnosis[C]// 2018 International Conference on Electrical Sciences and Technologies in Maghreb (CISTEM), Algiers, Algeria, 2018: 1-6.
[15] Lee H, Jeong H, Koo G, et al.Attention recurrent neural network-based severity estimation method for interturn short-circuit fault in permanent magnet synchronous machines[J]. IEEE Transactions on Industrial Electronics, 2021, 68(4): 3445-3453.
[16] 张宝杰, 麻宸伟, 贾震, 等. 基于卷积神经网络的牵引电机定子绕组匝间短路故障诊断[J]. 铁道学报, 2024, 46(4): 73-79.
Zhang Baojie, Ma Chenwei, Jia Zhen, et al.Fault diagnosis of stator winding inter-turn short circuit in traction motors based on convolutional neural network[J]. Journal of the China Railway Society, 2024, 46(4): 73-79.
[17] 张辉, 戈宝军, 韩斌, 等. 基于GAF-CapsNet的电机轴承故障诊断方法[J]. 电工技术学报, 2023, 38(10): 2675-2685.
Zhang Hui, Ge Baojun, Han Bin, et al.Fault diagnosis method of motor bearing based on GAF-CapsNet[J]. Transactions of China Electrotechnical Society, 2023, 38(10): 2675-2685.
[18] Kou Linlin, Qin Yong, Zhao Xuejun, et al.A multi- dimension end-to-end CNN model for rotating devices fault diagnosis on high-speed train bogie[J]. IEEE Transactions on Vehicular Technology, 2020, 69(3): 2513-2524.
[19] Tran M Q, Liu Mengkun, Tran Q V, et al.Effective fault diagnosis based on wavelet and convolutional attention neural network for induction motors[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 71: 3501613.
[20] 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, 2017, 65(7): 5990-5998.
[21] Valtierra-Rodriguez M, Rivera-Guillen J R, Basurto- Hurtado J A, et al. Convolutional neural network and motor current signature analysis during the transient state for detection of broken rotor bars in induction motors[J]. Sensors, 2020, 20(13): 3721.
[22] 丁伟, 宋俊材, 陆思良, 等. 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, et al.High- resistance connection fault diagnosis of permanent magnet synchronous motor based on two-dimensional recursive fusion of multi-channel signals and ECA- ConvNeXt[J]. Transactions of China Electrotechnical Society, 2024, 39(20): 6397-6408.
[23] Xie Tingli, Huang Xufeng, Choi S K.Intelligent mechanical fault diagnosis using multisensor fusion and convolution neural network[J]. IEEE Transa- ctions on Industrial Informatics, 2021, 18(5): 3213-3223.
[24] 王照伟, 刘传帅, 赵文祥, 等. 多尺度多任务注意力卷积神经网络滚动轴承故障诊断方法[J]. 电机与控制学报, 2024, 28(7): 65-76.
Wang Zhaowei, Liu Chuanshuai, Zhao Wenxiang, et al.Rolling bearing fault diagnosis with multi-scale multi-task attention convolutional neural network[J]. Electric Machines and Control, 2024, 28(7): 65-76.
[25] Zhu Qingyun, Lu Jingfeng, Wang Xiaoxian, et al.Real-time quality inspection of motor rotor using cost-effective intelligent edge system[J]. IEEE Internet of Things Journal, 2022, 10(8): 7393-7404.
[26] Wang Qilong, Wu Banggu, Zhu Pengfei, et al.ECA-net: efficient channel attention for deep con- volutional neural networks[C]//2020 IEEE/CVF Con- ference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020: 11531-11539.
[27] He Liu, Wang Dong, Yi Cai, et al.Extracting cyclo- stationarity of repetitive transients from envelope spectrum based on prior-unknown blind decon- volution technique[J]. Signal Processing, 2021, 183: 107997.
[28] 邱锡鹏. 神经网络与深度学习[M]. 北京: 机械工业出版社, 2020.
[29] Ioffe S, Szegedy C.Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning, Lille, France, 2015: 1-11.
[30] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al.Deep residual learning for image recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016: 770-778.
[31] Vaswani A, Shazeer N, Parmar N, et al.Attention is all you need[C]//31st Conference on Neural Infor- mation Processing Systems, Long Beach, CA, USA, 2017: 6000-6010.
[32] Szegedy C, Ioffe S, Vanhoucke V, et al.Inception-v4, Inception-ResNet and the impact of residual con- nections on learning[C]//Advances in Neural Infor- mation Processing Systems, Long Beach, California, 2017: 11231-11239.
[33] Aline E T, Rogerio A F, Marcelo S, et al. Experi- mental database for detecting and diagnosing rotor broken bar in a three-phase induction motor[DB/OL]. (2020-09-24) [2024-11-28]. https://ieee-dataport.org/open-access/experimental-database-detecting-and-diagnosing-rotor-broken-bar-three-phase-induction.