Fault Diagnosis Method for Train Traction Transmission System Based on Gram Angle Field and Parallel Convolutional Transformer

doi:10.3901/JME.2025.24.168

Abstract

Abstract: The stability and reliability of the transmission system is critical to the safe operation of trains. However, existing fault diagnosis methods have limitations in handling non-stationary signals and capturing complex features. To overcome these limitations, a train traction driveline fault diagnosis method based on Gram angular field(GAF) and parallel convolutional Transformer is proposed. The GAF is used to generate time-frequency images to capture the global information and nonlinear features of the time series. Further, the Gram sum field and Gram difference field maps are sampled by means of parallel convolutional processing, respectively, to enrich the fault information from different dimensions and effectively improve the feature extraction capability and computational efficiency of the model. In addition, the Transformer Encoder structure is introduced at the back-end of the model, which is used in conjunction with the convolutional neural network to enhance the expression and analysis capability of complex time-frequency features. Experimental validation shows that the proposed method has high accuracy and efficiency in train transmission system fault diagnosis.

Key words: traction drive system, fault diagnosis, gram angle field, Transformer, convolutional neural network

CLC Number:

U279

MEN Zhihui, GONG Dao, ZHOU Jinsong, ZHOU Kai. Fault Diagnosis Method for Train Traction Transmission System Based on Gram Angle Field and Parallel Convolutional Transformer[J]. Journal of Mechanical Engineering, 2025, 61(24): 168-179.

References

[1] 刘广宇,宫岛,周劲松,等. 基于Sobol'法的动车组车体弹性异常振动全局灵敏度分析与优化[J]. 中南大学学报(自然科学版),2024,55(5):1940-1952. LIU Guangyu,GONG Dao,ZHOU Jinsong,et al. Global sensitivity analysis and optimization of abnormal elastic vibration of EMU car body based on Sobol' method[J]. Journal of Central South University (Science and Technology),2024,55(5):1940-1952.
[2] 王秋实,周劲松,宫岛,等. 基于核密度应力谱外推的转向架构架疲劳寿命评估[J]. 交通运输工程学报,2021,21(6):278-288. WANG Qiushi,ZHOU Jinsong,GONG Dao,et al. Fatigue life evaluation of bogie frame based on kerneldensity extrapolation for stress spectrum[J]. Journal of Traffic and Transportation Engineering,2021,21(6):278-288.
[3] MA J E,LUO C,QIU L,et al. Recent advances in traction drive technology for rail transit[J]. Journal of Zhejiang University-Science A,2023,24:177-188.
[4] CHEN Z W,CHEN W Y,FAN X Y,et al. JITL-MBN:A real-time causality representation learning for sensor fault diagnosis of traction drive system in high-speed trains[J]. IEEE Transactions on Neural Networks and Learning Systems,2024,35(5):6243-6254.
[5] ZHANG K,YANG J W,LIU C D,et al. Dynamic characteristics of a traction drive system in high-speed train based on electromechanical coupling modeling under variable conditions[J]. Energies,2022,15(3):1202.
[6] LIU Y,WANG B,ZHANG B. et al. Establishment of dynamic model for axle box bearing of high-speed trains under variable speed conditions[J]. Chinese Journal of Mechanical Engineering,2022,35:47.
[7] LIU Y,CHEN Z,NING J,et al. Improved dynamics model of locomotive traction motor with elasticity of rotor shaft and supporting bearings[J]. Chinese Journal of Mechanical Engineering,2022,35:90.
[8] CHEN X,CHEN Z,CHEN S,et al. Unsupervised gan with fine-tuning:A novel framework for induction motor fault diagnosis in scarcely labeled sample scenarios[J]. IEEE Transactions on Instrumentation and Measurement,2024,73:3528911.
[9] DOU W,ZHANG L,CHANG H,et al. Fatigue characterization on a cast aluminum beam of a high-speed train through numerical simulation and experiments[J]. Chinese Journal of Mechanical Engineering,2021,34:108.
[10] CHEN S,GUO L,FAN J,et al. Bandwidth-aware adaptive chirp mode decomposition for railway bearing fault diagnosis[J]. Structural Health Monitoring,2023,2:876-902.
[11] 孙鑫威,纪爱敏,杜占涛,等. 动车组齿轮箱滚动轴承变转速故障诊断方法[J]. 哈尔滨工业大学学报,2023,55(1):106-115. SONG Xinwei,JI Aimin,DU Zhantao,et al. Fault diagnosis method for variable speed of rolling bearing in emu gearbox[J]. Journal of Harbin Institute of Technology,2023,55(1):106-115.
[12] 郭蕾,蔡育宏,张俊,等. 基于频率响应与图像特征提取的动车组变压器绕组状态诊断方法研究[J]. 铁道学报,2024,46(4):47-56. GUO Lei,CAI Yuhong,ZHANG Jun,et al. Research on diagnosis method for state of transformer winding of trainsetbased on frequency response and lmage feature extraction[J]. Journal of the China Railway Society,2024,46(4):47-56.
[13] 宋宏智,李秀杰,邱战国,等. 基于改进VMD的高速动车组轴箱轴承故障识别方法[J]. 中国铁道科学,2023,44(3):146-154. SONG Hongzhi,LI Xiujie,QIU Zhanguo,et al. Fault identification method of axle box bearing of high-speedemus based on improved vmd[J]. China Railway Science,2023,44(3):146-154.
[14] 张龙,胡燕青,赵丽娟,等. 多通道信息融合与深度迁移学习的旋转机械故障诊断[J]. 中国机械工程,2023,34(8):966-975. ZHANG Long,HU Yanqing,ZHAO Lijuan,et al. Multichannel information fusionand deep transfer learning for rotating machinery fault diagnosis[J]. China Mechanical Engineering,2023,34(8):966-975.
[15] 张国栋,尹强,羊柳,等. 基于格拉姆角场和PSO-CNN的滚动轴承故障诊断方法[J]. 兵器装备工程学报,2024,45(4):301-308. ZHANG Guodong,YIN Qiang,YANG Liu,et al. Rolling bearing fault diagnosis method based on gramian angle field and PSO-CNN[J]. Journal of Ordnance Equipment Engineering,2024,45(4):301-308.
[16] PAN H Y,XU H F,ZHENG J D,et al. A semi-supervised matrixized graph embedding machine for roller bearing fault diagnosis under few-labeled samples[J]. IEEE Transactions on Industrial Informatics,2024,20(1):854-863.
[17] GAO Q H,HUANG T,ZHAO K,et al. Multi-source weighted source-free domain transfer method for rotating machinery fault diagnosis[J]. Expert Systems with Applications,2024,237:121585.
[18] LI X,YU S P,LEI Y G,et al. Intelligent machinery fault diagnosis with event-based camera[J]. IEEE Transactions on Industrial Informatics,2024,20(1):380-389.
[19] LI T F,SUN C,FINK O,et al,Filter-informed spectral graph wavelet networks for multiscale feature extraction and intelligent fault diagnosis[J]. IEEE Transactions on Cybernetics,2024,54(1):506-518.
[20] XU Y D,FENG K,YAN X A,et al. CFCNN:A novel convolutional fusion framework for collaborative fault identification of rotating machinery[J]. Information Fusion,2023,95:1-16.
[21] HU C Y,WU J Y,SUN C,et al. Interinstance and intratemporal self-supervised learning with few labeled data for fault diagnosis[J]. Transactions on Industrial Informatics,2023,19(5):6502-6512.
[22] 赵靖,杨绍普,李强,等. 一种残差注意力迁移学习方法及其在滚动轴承故障诊断中的应用[J]. 中国机械工程,2023,34(3):332-343. ZHAO Jing,YANG Shaopu,LI Qiang,et al. A new transfer learning method with residual attention and its applications on rolling bearing fault diagnosis[J]. China Mechanical Engineering,2023,34(3):332-343.
[23] 邵海东,林健,闵志闪,等. 分布外样本干扰下基于改进半监督原型网络的齿轮箱跨域故障诊断[J]. 机械工程学报,2024,60(4):212-221. SHAO Haidong,LIN Jian,MIN Zhishan,et al. Improved semi-supervised prototype network for cross-domain fault diagnosis of gearbox under out-of-distribution interference samples[J]. Journal of Mechanical Engineering,2024,60(4):212-221.
[24] ZHANG Q X,CUI J G,XIAO W S,et al. Demagnetization fault diagnosis of a pmsm for electric drilling tools using GAF and CNN[J]. Electronics,2024,13(1):189.
[25] ZHAO P,PANG X Y,LI F,et al. Gearbox fault diagnosis method based on improved semi-supervised mtdl and gaf[J]. Measurement and Control,2024,57(8):1181-1193.
[26] CHEN X H,ZHANG B K,GAO D. Bearing fault diagnosis base on multi-scale cnn and lstm model[J]. Journal of Intelligent Manufacturing,2020,32:971-987.
[27] SHEN Q M,ZHANG Z Q. Fault diagnosis method for bearing based on attention mechanism and multi-scale convolutional neural network[J]. IEEE Access,2024,12:12940-12952.
[28] WENG C Y,LU B C,GU Q,et al. A novel multisensor fusion transformer and its application into rotating machinery fault diagnosis journal[J]. IEEE Transactions on Instrumentation and Measurement,2023,72:1-12.
[29] LIU W K,ZHANG Z G,ZHANG J R,et al. A novel fault diagnosis method of rolling bearings combining convolutional neural network and transformer[J]. Electronics,2023,12(8):1838.
[30] 张西宁,刘书语,余迪,等. 改进深度卷积神经网络及其在变工况滚动轴承故障诊断中的应用[J]. 西安交通大学学报,2021,55(6):1-8. ZHANG Xining,LIU Shuyu,YU Di,et al. Improved deep convolutional neural network with applications to bearing fault diagnosis under variable conditions[J]. Journal of Xi'an Jiaotong University,2021,55(6):1-8.
[31] DING A,QIN Y,WANG B,et al. Evolvable graph neural network for system-level incremental fault diagnosis of train transmission systems[J]. Mechanical Systems and Signal Processing,2024,210:111175.
[32] MAATEN L,GEOFFREY E. Visualizing data using t-sne[J]. Journal of Machine Learning Research,2008,9:2579-2605.
[33] NASERI T S,GHAREHCHOPOGH F S. A feature selection based on the farmland fertility algorithm for improved intrusion detection systems[J]. Journal of Network and Systems Management,2022,30:40.
[34] HU C Q,LI Y H,CHEN Z,et al. Research on fault diagnosis of rolling bearing based on multi-sensor bi-layer information fusion under small samples[J]. Review of Scientific Instruments,2023,94:115106.
[35] HU C Q,LI Y H,CHEN Z,et al. A novel rolling bearing fault diagnosis method based on parameter optimization variational mode decomposition with feature weighted reconstruction and multi-target attention convolutional neural networks under small samples[J]. Review of Scientific Instruments,2023,94:075109.
[36] LI Y H,MEN Z H,BAI X N,et al. A bearing fault diagnosis method based on m-sscnn and m-lr attention mechanism[J/OL]. Structural Health Monitoring,2024:1-23[2025-1-21]. https://doi.org/10.1177/14759217241244477.
[37] MEN Z H,HU C Q,LI Y H,et al. Ahybrid intelligent gearbox fault diagnosis method based on ewceemd and whale optimization algorithm-optimized svm[J]. International Journal of Structural Integrity,2023,14(2):322-336.
[38] MEN Z H,CHEN Z,LI Y H,et al. Railway wagon bearing fault diagnosis method based on improved sparrow search algorithm optimizing variational mode decomposition and multi-level convolutional neural network[J]. Review of Scientific Instruments,2024,95:045104.
[39] LI Y H,WANG D L,ZHAO X,et al. Research on rolling bearing fault diagnosis method based on simulation and experiment fusion drive[J]. Review of Scientific Instruments,2024,95(6):065107.