In order to accurately predict the remaining useful life of D-cable for high-speed train and ensure the safe and efficient operation of trains, a prediction method of remaining useful life of D-cable for high-speed train based on SA-LSTM is proposed. Firstly, the internal structure, main failure mode and failure mechanism of D-cable are analyzed, and the finite element model of D-cable is constructed. Secondly, based on the thermal breakdown failure mechanism, the accelerated degradation data set of whole life cycle for D-cable under different thermal stress conditions is constructed. Then, the random forest (RF) algorithm is used to actively screen the key degradation features, and the self-attention (SA) mechanism is introduced to fuse statistical features and combine the long short-term memory (LSTM) network to achieve accurate prediction of remaining useful life (RUL). Finally, the effectiveness of the proposed method is verified by the D-cable degradation simulation data set. The results show that compared with the traditional methods such as LSTM, GRU, SVR and FNN, the proposed method has excellent performance. Under 6 typical thermal stress conditions, the average absolute error is reduced by 52.4% and the average root mean square error is reduced by 49.7%, which improves the RUL prediction accuracy of D-cable under complex working conditions. This method has reference value for improving the level of railway risk prevention and control, and ensuring train safe operation.
LUOLingfeng, CAOHefei. Analysis and Optimization of Electromagnetic Interference of Medium-Low Speed Maglev BTM Equipment [J]. Railway Signalling & Communication Engineering, 2023, 20 (7): 64-69. in Chinese
LUOYunfei, YISheng, QIXiaonan, et al. Performance Detection Method of Cable D for 300T on-Board Equipment [J]. Railway Signalling & Communication Engineering, 2022, 19 (3): 27-32. in Chinese
YanqiLÜ. Fault Analysis and Suggestions on Fault Handling of Onboard Balise Transmission System of CTCS3-300T Train Control System [J]. Railway Signalling & Communication Engineering, 2021, 18 (9): 99-103. in Chinese
[7]
陈惠冬.300T型ATP设备D电缆固定支架的研制[J].上海铁道科技,2014(4):40-41.
[8]
CHENHuidong. Development of the D Cable Fixing Bracket for 300T Type ATP Equipment [J]. Shanghai Railway Science and Technology, 2014 (4): 40-41. in Chinese
SONGLimin. Electromagnetic Shielding and Protection of D-Interface Cable for 380A Train [J]. Railway Signalling & Communication, 2017, 53 (): 72-74. in Chinese
[13]
ILIOPOULOSI A, SAKELLARIOUJ S. Remaining Useful Life Estimation of Hollow Worn Railway Vehicle Wheels via on-Board Random Vibration-Based Wheel Tread Depth Estimation [J]. Sensors, 2024, 24 (2): 375.
[14]
YANGT H, LIS H, DUANS Y, et al. Performance Degradation Model and Reliability Evaluation of Brush DC Motor for Intelligent on-off Valve [J]. Journal of Electrical Engineering & Technology, 2023, 18 (3): 1909-1918.
WUYi, YINHongxiang, ZHANGPengpai, et al. Fatigue Life Prediction of High-Speed EMU Axle with Foreign Object Damage [J]. China Railway Science, 2021, 42 (2): 116-124. in Chinese
[17]
ZHANGB C, SUIY K, BUQ Y, et al. Remaining Useful Life Estimation for Micro Switches of Railway Vehicles [J]. Control Engineering Practice, 2019, 84: 82-91.
WANGYuxuan, WANGZhifeng, NIEShaofeng, et al. Crack Extension and Life Prediction of Fastening Spring Clip in Heavy-Haul Railways [J]. Journal of Traffic and Transportation Engineering, 2025, 25 (1): 221-233. in Chinese
[20]
WANGC, ZHUT, YANGB, et al. Remaining Useful Life Prediction Framework for Crack Propagation with a Case Study of Railway Heavy Duty Coupler Condition Monitoring [J]. Reliability Engineering & System Safety, 2023, 230: 108915.
[21]
GUANQ L, WEIX K, JIAL M, et al. RUL Prediction of Railway PCCS Based on Wiener Process Model with Unequal Interval Wear Data [J]. Applied Sciences, 2020, 10 (5): 1616.
[22]
LIUL, ZHANGZ H, QUZ J, et al. Remaining Useful Life Prediction for a Catenary, Utilizing Bayesian Optimization of Stacking [J]. Electronics, 2023, 12 (7): 1744.
[23]
MAL X, YUY X, LIH Y, et al. Investigation of Metro Train-Induced Environmental Vibration Using a Coupled Sliced Finite Element-Infinite Element Model [J]. KSCE Journal of Civil Engineering, 2024, 28 (6): 2380-2398.
XiaoyanLÜ, LIUChunhuang, ZHUJiansheng. Improved Algorithm of Decision Tree Based on Key Decision Factor and Its Applications in Railway Transportation [J]. Journal of the China Railway Society, 2011, 33 (9): 62-67. in Chinese
[26]
KHELIFR, CHEBEL-MORELLOB, MALINOWSKIS, et al. Direct Remaining Useful Life Estimation Based on Support Vector Regression [J]. IEEE Transactions on Industrial Electronics, 2017, 64 (3): 2276-2285.
[27]
SHANGZ W, ZHANGB R, LIW X, et al. Machine Remaining Life Prediction Based on Multi-Layer Self-Attention and Temporal Convolution Network [J]. Complex & Intelligent Systems, 2022, 8 (2): 1409-1424.
[28]
CHENZ H, WUM, ZHAOR, et al. Machine Remaining Useful Life Prediction via an Attention-Based Deep Learning Approach [J]. IEEE Transactions on Industrial Electronics, 2021, 68 (3): 2521-2531.
SUNBo, YANGZongye, ZHANGBowen, et al. Research on Spectral Efficiency of T2T Communication Based on CNN-LSTM-NOMA [J]. China Railway Science, 2025, 46 (1): 192-199. in Chinese