Học máy trong chẩn đoán lỗi hệ thống kéo của tàu cao tốc: Một bài tổng quan

Huan Wang1, Yan-Fu Li1, Jianliang Ren2
1Department of Industrial Engineering, Tsinghua University, Beijing, China.
2Zhibo Lucchini Railway Equipment Co., Ltd., Taiyuan, China

Tóm tắt

Tàu cao tốc (HST) có những ưu điểm về sự thoải mái, hiệu quả và tiện lợi, và đã dần trở thành phương tiện giao thông chính. Khi quy mô hoạt động của HST tiếp tục mở rộng, việc đảm bảo an toàn và độ tin cậy của chúng trở nên cấp thiết hơn. Là thành phần cốt lõi của HST, độ tin cậy của hệ thống kéo có ảnh hưởng lớn đến hoạt động của tàu. Trong quá trình vận hành lâu dài của HST, các thành phần cốt lỗi của hệ thống kéo sẽ không tránh khỏi việc bị suy giảm hiệu suất ở nhiều mức độ khác nhau và gây ra nhiều sự cố, từ đó đe dọa đến an toàn chạy tàu. Do đó, việc thực hiện giám sát và chẩn đoán lỗi trên hệ thống kéo của HST là cần thiết. Trong những năm gần đây, học máy đã được ứng dụng rộng rãi trong các nhiệm vụ nhận dạng mẫu và đã thể hiện hiệu suất xuất sắc trong chẩn đoán lỗi hệ thống kéo. Học máy đã có những bước tiến đáng kể trong chẩn đoán lỗi hệ thống kéo; tuy nhiên, một nghiên cứu tổng quan hệ thống toàn diện vẫn còn thiếu trong lĩnh vực này. Bài báo này chủ yếu nhằm mục đích tổng hợp nghiên cứu và ứng dụng của học máy trong lĩnh vực chẩn đoán lỗi hệ thống kéo và phát thảo sơ đồ phát triển tương lai. Đầu tiên, cấu trúc và chức năng của hệ thống kéo HST được giới thiệu ngắn gọn. Sau đó, nghiên cứu và ứng dụng của học máy trong chẩn đoán lỗi hệ thống kéo được xem xét một cách tổng thể và có hệ thống. Cuối cùng, các thách thức trong việc chẩn đoán lỗi chính xác dưới điều kiện vận hành thực tế được chỉ ra, và các xu hướng nghiên cứu trong tương lai của học máy trong hệ thống kéo được thảo luận.

Từ khóa

#học máy #chẩn đoán lỗi #hệ thống kéo #tàu cao tốc

Tài liệu tham khảo

Aydin I, Karakose M, Akin E (2014). Monitoring of pantograph–catenary interaction by using particle swarm based contact wire tracking. In: International Conference on Systems, Signals and Image Processing. Dubrovnik: IEEE, 23–26 Aydin I, Karakose M, Akin E (2015). Anomaly detection using a modified kernel-based tracking in the pantograph–catenary system. Expert Systems with Applications, 42(2): 938–948 Bacha K, Souahlia S, Gossa M (2012). Power transformer fault diagnosis based on dissolved gas analysis by support vector machine. Electric Power Systems Research, 83(1): 73–79 Bi S, Feng D, Lin S, Guo X, Pan W (2020). State evaluation method of traction transformer based on variable weight coefficient and Bayesian network. In: 11th International Conference on Prognostics and System Health Management. Jinan: IEEE, 163–168 Brahimi M, Medjaher K, Leouatni M, Zerhouni N (2016). Development of a prognostics and health management system for the railway infrastructure: Review and methodology. In: Prognostics and System Health Management Conference. Chengdu: IEEE, 1–8 Cao J, Cui H, Li N (2014). Research on fault detection method and device of EMU traction motors. In: International Conference on Electrical and Information Technologies for Rail Transportation. Berlin, Heidelberg: Springer, 293–301 Carvalho S, Partidario M, Sheate W (2017). High speed rail comparative strategic assessments in EU member states. Environmental Impact Assessment Review, 66: 1–13 Chen H, Jiang B (2020a). A review of fault detection and diagnosis for the traction system in high-speed trains. IEEE Transactions on Intelligent Transportation Systems, 21(2): 450–465 Chen H, Jiang B, Ding S X, Huang B (2022). Data-driven fault diagnosis for traction systems in high-speed trains: A survey, challenges, and perspectives. IEEE Transactions on Intelligent Transportation Systems, 23(3): 1700–1716 Chen L C, Papandreou G, Kokkinos I, Murphy K, Yuille A L (2018). DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4): 834–848 Chen X, Zhang B, Gao D (2021). Bearing fault diagnosis base on multi-scale CNN and LSTM model. Journal of Intelligent Manufacturing, 32(4): 971–987 Chen Z, Chen W, Tao H, Peng T (2020b). Sensor fault diagnosis for high-speed traction converter system based on Bayesian network. In: Chinese Automation Congress. Shanghai: IEEE, 4969–4974 Chen Z, Li X, Yang C, Peng T, Yang C, Karimi H R, Gui W (2019). A data-driven ground fault detection and isolation method for main circuit in railway electrical traction system. ISA Transactions, 87: 264–271 Cheng H, Yao X (2018). Research on fault diagnosis of traction motor based on group decision making. In: 2nd International Workshop on Structural Health Monitoring for Railway System. Qingdao, China Cheng Y, Loo B P Y, Vickerman R (2015). High-speed rail networks, economic integration and regional specialisation in China and Europe. Travel Behaviour & Society, 2(1): 1–14 Cherif B D E, Bendiabdellah A, Tabbakh M (2020). An automatic diagnosis of an inverter IGBT open-circuit fault based on HHT-ANN. Electric Power Components and Systems, 48(6–7): 589–602 Dai C, Liu Z, Hu K, Huang K (2016). Fault diagnosis approach of traction transformers in high-speed railway combining kernel principal component analysis with random forest. IET Electrical Systems in Transportation, 6(3): 202–206 Dai J, Song H, Sheng G, Jiang X (2017). Dissolved gas analysis of insulating oil for power transformer fault diagnosis with deep belief network. IEEE Transactions on Dielectrics and Electrical Insulation, 24(5): 2828–2835 Ding G, Wang L, Song J, Lin Z (2010). Neural network based on wavelet packet-characteristic entropy and rough set theory for fault diagnosis. In: 2nd International Conference on Computer Engineering and Technology. Chengdu: IEEE, 560–564 Dong H, Chen F, Wang Z, Jia L, Qin Y, Man J (2021). An adaptive multisensor fault diagnosis method for high-speed train traction converters. IEEE Transactions on Power Electronics, 36(6): 6288–6302 Drabek P, Pittermann M, Cedl M (2010). Primary traction converter for multi-system locomotives. In: IEEE International Symposium on Industrial Electronics. Bari: IEEE, 1010–1015 Du H, Minku L L, Zhou H (2020). MARLINE: Multi-source mapping transfer learning for non-stationary environments. In: IEEE International Conference on Data Mining. Sorrento: IEEE, 122–131 Dujic D, Kieferndorf F, Canales F, Drofenik U (2012). Power electronic traction transformer technology. In: 7th International Power Electronics and Motion Control Conference. Harbin: IEEE, 636–642 Gou B, Xu Y, Xia Y, Deng Q, Ge X (2020). An online data-driven method for simultaneous diagnosis of IGBT and current sensor fault of three-phase PWM inverter in induction motor drives. IEEE Transactions on Power Electronics, 35(12): 13281–13294 Gu J, Huang M (2020). Fault diagnosis method for bearing of high-speed train based on multitask deep learning. Shock and Vibration, 8873504 Guo Q, Zhang X, Li J, Li G (2022). Fault diagnosis of modular multilevel converter based on adaptive chirp mode decomposition and temporal convolutional network. Engineering Applications of Artificial Intelligence, 107: 104544 Guzinski J, Abu-Rub H, Diguet M, Krzeminski Z, Lewicki A (2010). Speed and load torque observer application in high-speed train electric drive. IEEE Transactions on Industrial Electronics, 57(2): 565–574 Han T, Jiang D (2016). Rolling bearing fault diagnostic method based on VMD-AR model and random forest classifier. Shock and Vibration, 5132046 Han T, Li Y F, Qian M (2021a). A hybrid generalization network for intelligent fault diagnosis of rotating machinery under unseen working conditions. IEEE Transactions on Instrumentation and Measurement, 70: 1–11 Han T, Liu C, Wu R, Jiang D (2021b). Deep transfer learning with limited data for machinery fault diagnosis. Applied Soft Computing, 103: 107150 He K, Zhang X, Ren S, Sun J (2016). Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV: IEEE, 770–778 Hu H, Feng F, Wang T (2020). Open-circuit fault diagnosis of NPC inverter IGBT based on independent component analysis and neural network. Energy Reports, 6: 134–143 Hu K, Liu Z, Lin S (2016). Wavelet entropy-based traction inverter open switch fault diagnosis in high-speed railways. Entropy, 18(3): 78 Huang S, Chen W, Sun B, Tao T, Yang L (2020). Arc detection and recognition in the pantograph–catenary system based on multiinformation fusion. Transportation Research Record: Journal of the Transportation Research Board, 2674(10): 229–240 Huang S, Zhai Y, Zhang M, Hou X (2019). Arc detection and recognition in pantograph–catenary system based on convolutional neural network. Information Sciences, 501: 363–376 Hugo N, Stefanutti P, Pellerin M, Akdag A (2007). Power electronics traction transformer. In: European Conference on Power Electronics and Applications. Aalborg: IEEE, 1–10 Jiang S, Wei X, Yang Z (2019). Defect detection of pantograph slider based on improved faster R-CNN. In: Chinese Control and Decision Conference. Nanchang: IEEE, 5278–5283 Jiao Z, Ma C, Lin C, Nie X, Qing A (2021). Real-time detection of pantograph using improved CenterNet. In: 16th Conference on Industrial Electronics and Applications. Chengdu: IEEE, 85–89 Jordan M I, Mitchell T M (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245): 255–260 Karaduman G, Akin E (2020). A deep learning based method for detecting of wear on the current collector strips’ surfaces of the pantograph in railways. IEEE Access, 8: 183799–183812 Karaduman G, Akin E (2022). A new approach based on predictive maintenance using the fuzzy classifier in pantograph–catenary systems. IEEE Transactions on Intelligent Transportation Systems, 23(5): 4236–4246 Karaduman G, Karakose M, Akin E (2017). Deep learning based arc detection in pantograph–catenary systems. In: 10th International Conference on Electrical and Electronics Engineering. Bursa: IEEE, 904–908 Karakose E, Gencoglu M T, Karakose M, Aydin I, Akin E (2017). A new experimental approach using image processing-based tracking for an efficient fault diagnosis in pantograph–catenary systems. IEEE Transactions on Industrial Informatics, 13(2): 635–643 Karakose E, Gencoglu M T, Karakose M, Yaman O, Aydin I, Akin E (2018). A new arc detection method based on fuzzy logic using S-transform for pantograph–catenary systems. Journal of Intelligent Manufacturing, 29(4): 839–856 Ke L, Liu Z, Zhang Y (2020). Fault diagnosis of modular multilevel converter based on optimized support vector machine. In: 39th Chinese Control Conference. Shenyang: IEEE, 4204–4209 Khamidov O, Grishchenko A (2021). Locomotive asynchronous traction motor rolling bearing fault detection based on current intelligent methods. Journal of Physics: Conference Series, 2131(4): 042084 Kotsiantis S B, Zaharakis I D, Pintelas P E (2006). Machine learning: A review of classification and combining techniques. Artificial Intelligence Review, 26(3): 159–190 Kou L, Liu C, Cai G, Zhang Z (2020a). Fault diagnosis for power electronics converters based on deep feedforward network and wavelet compression. Electric Power Systems Research, 185: 106370 Kou L, Liu C, Cai G, Zhang Z, Zhou J N, Wang X M (2020b). Fault diagnosis for three-phase PWM rectifier based on deep feedforward network with transient synthetic features. ISA Transactions, 101: 399–407 Kulkarni S, Pappalardo C M, Shabana A A (2017). Pantograph/Catenary contact formulations. Journal of Vibration and Acoustics, 139(1): 011010 Lawrence M B, Bullock R G, Liu Z (2019). China’s High-Speed Rail Development. Washington, D.C.: World Bank Publications LeCun Y, Bengio Y, Hinton G (2015). Deep learning. Nature, 521(7553): 436–444 Lei Y, Yang B, Jiang X, Jia F, Li N, Nandi A K (2020). Applications of machine learning to machine fault diagnosis: A review and roadmap. Mechanical Systems and Signal Processing, 138: 106587 Li B, Luo C, Wang Z (2020). Application of GWO-SVM algorithm in arc detection of pantograph. IEEE Access, 8: 173865–173873 Li J, Hai C, Feng Z, Li G (2021a). A transformer fault diagnosis method based on parameters optimization of hybrid kernel extreme learning machine. IEEE Access, 9: 126891–126902 Li J, Zhang Q, Wang K, Wang J, Zhou T, Zhang Y (2016). Optimal dissolved gas ratios selected by genetic algorithm for power transformer fault diagnosis based on support vector machine. IEEE Transactions on Dielectrics and Electrical Insulation, 23(2): 1198–1206 Li L, Wu M, Wu S, Li J, Song K (2019). A three-phase to single-phase AC-DC-AC topology based on multi-converter in AC electric railway application. IEEE Access, 7: 111539–111558 Li X, Sun Z, Xue J, Ma Z (2021b). A concise review of recent few-shot meta-learning methods. Neurocomputing, 456: 463–468 Li Y (2022). Exploring real-time fault detection of high-speed train traction motor based on machine learning and wavelet analysis. Neural Computing & Applications, 34: 9301–9314 Li Y, Wei X (2018). Pantograph slide plate abrasion detection based on deep learning network. In: 3rd International Conference on Electrical and Information Technologies for Rail Transportation. Singapore: Springer, 215–224 Li Y H, Tian X J, Li X Q (2013). Identification of magnetizing inrush and internal short-circuit fault current in v/x-type traction transformer. Advances in Mechanical Engineering, 5: 905202 Li Z, Zhang Y, Abu-Siada A, Chen X, Li Z, Xu Y, Zhang L, Tong Y (2021c). Fault diagnosis of transformer windings based on decision tree and fully connected neural network. Energies, 14(6): 1531 Liao W, Yang D, Wang Y, Ren X (2021). Fault diagnosis of power transformers using graph convolutional network. CSEE Journal of Power and Energy Systems, 7(2): 241–249 Lin J, Su L, Yan Y, Sheng G, Xie D, Jiang X (2018). Prediction method for power transformer running state based on LSTM_DBN network. Energies, 11(7): 1880 Lin W, Peng G, Wu M, Lin Y, Jin L (2020). A fault detection method of high speed train pantograph based on deep learning. In: 8th International Conference on Condition Monitoring and Diagnosis. Phuket: IEEE, 254–257 Liu C, Gryllias K (2022). Simulation-driven domain adaptation for rolling element bearing fault diagnosis. IEEE Transactions on Industrial Informatics, 18(9): 5760–5770 Liu H, Han M (2012). Research of prognostics and health management for EMU. In: Prognostics and System Health Management Conference. Beijing: IEEE, 1–6 Liu J, Zhao Z, Tang C, Yao C, Li C, Islam S (2019a). Classifying transformer winding deformation fault types and degrees using FRA based on support vector machine. IEEE Access, 7: 112494–112504 Liu R, Yang B, Zio E, Chen X (2018). Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 108: 33–47 Liu S, Yu L, Zhang D (2019b). An efficient method for high-speed railway dropper fault detection based on depthwise separable convolution. IEEE Access, 7: 135678–135688 Liu W, Wang Z, Han J, Wang G (2013). Wind turbine fault diagnosis method based on diagonal spectrum and clustering binary tree SVM. Renewable Energy, 50: 1–6 Liu Z, Wang H, Liu J, Qin Y, Peng D (2021). Multitask learning based on lightweight 1DCNN for fault diagnosis of wheelset bearings. IEEE Transactions on Instrumentation and Measurement, 70: 1–11 Long H, Ma M, Guo W, Li F, Zhang X (2020). Fault diagnosis for IGBTs open-circuit faults in photovoltaic grid-connected inverters based on statistical analysis and machine learning. In: 1st China International Youth Conference on Electrical Engineering. Wuhan: IEEE, 1–6 Lu S, Liu Z, Li D, Shen Y (2021). Automatic wear measurement of pantograph slider based on multiview analysis. IEEE Transactions on Industrial Informatics, 17(5): 3111–3121 Luo Y, Yang Q, Liu S (2019). Novel vision-based abnormal behavior localization of pantograph–catenary for high-speed trains. IEEE Access, 7: 180935–180946 Ma M, Sun C, Chen X (2018). Deep coupling autoencoder for fault diagnosis with multimodal sensory data. IEEE Transactions on Industrial Informatics, 14(3): 1137–1145 MehdipourPicha H, Bo R, Chen H, Rana M M, Huang J, Hu F (2019). Transformer fault diagnosis using deep neural network. In: IEEE Innovative Smart Grid Technologies. Chengdu: IEEE, 4241–4245 Minku L L (2019). Transfer learning in non-stationary environments. In: Sayed-Mouchaweh M, ed. Learning from Data Streams in Evolving Environments. Cham: Springer, 13–37 Moosavi S S, Djerdir A, Aït-Amirat Y, Khaburi D A (2012a). Fault detection in 3-phase traction motor using artificial neural networks. In: IEEE Transportation Electrification Conference and Expo. Dearborn, MI: IEEE, 1–6 Moosavi S S, Djerdir A, Aït-Amirat Y, Kkuburi D A (2012b). Artificial neural networks based fault detection in 3-phase PMSM traction motor. In: 20th International Conference on Electrical Machines. Marseille: IEEE, 1579–1585 Na K, Lee K, Shin S, Kim H (2020). Detecting deformation on pantograph contact strip of railway vehicle on image processing and deep learning. Applied Sciences, 23(10): 8509 Nategh S, Boglietti A, Liu Y, Barber D, Brammer R, Lindberg D, Aglen O (2020). A review on different aspects of traction motor design for railway applications. IEEE Transactions on Industry Applications, 56(3): 2148–2157 Peng D, Liu C, Desmet W, Gryllias K (2021). Deep unsupervised transfer learning for health status prediction of a fleet of wind turbines with unbalanced data. In: Annual Conference of the PHM Society Peng D, Liu Z, Wang H, Qin Y, Jia L (2019). A novel deeper one-dimensional CNN with residual learning for fault diagnosis of wheelset bearings in high-speed trains. IEEE Access, 7: 10278–10293 Peng D, Wang H, Liu Z, Zhang W, Zuo M J, Chen J (2020a). Multibranch and multiscale CNN for fault diagnosis of wheelset bearings under strong noise and variable load condition. IEEE Transactions on Industrial Informatics, 16(7): 4949–4960 Peng T, Dai L, Chen Z, Ye C, Peng X (2020b). A probabilistic finite state automata-based fault detection method for traction motor. In: 29th International Symposium on Industrial Electronics. Delft: IEEE, 1199–1204 Phala K, Doorsamy W, Paul B S (2021). An intelligent fault monitoring system for railway neutral sections. In: International Conference on Communication and Computational Technologies. Singapore: Springer, 835–844 Popescu M, Goss J, Staton D A, Hawkins D, Chong Y C, Boglietti A (2018). Electrical vehicles: Practical solutions for power traction motor systems. IEEE Transactions on Industry Applications, 54(3): 2751–2762 Qin J, Zhou B, Mi Z (2019). Research of fault diagnosis and location of power transformer based on convolutional neural network. In: IEEE Innovative Smart Grid Technologies. Chengdu: IEEE, 3589–3594 Qu Z, Yuan S, Chi R, Chang L, Zhao L (2019). Genetic optimization method of pantograph and catenary comprehensive monitor status prediction model based on Adadelta deep neural network. IEEE Access, 7: 23210–23221 Ray D K, Rai A, Khetan A K, Mishra A, Chattopadhyay S (2020). Brush fault analysis for Indian DC traction locomotive using DWT-based multi-resolution analysis. Journal of The Institution of Engineers: Series B, 101(4): 335–345 Ren L, Lv W, Jiang S, Xiao Y (2016). Fault diagnosis using a joint model based on sparse representation and SVM. IEEE Transactions on Instrumentation and Measurement, 65(10): 2313–2320 Ren S, He K, Girshick R, Sun J (2017). Faster R-CNN: Towards realtime object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6): 1137–1149 Sakaidani Y, Kondo M (2018). Bearing fault detection for railway traction motors through leakage current. In: 13th International Conference on Electrical Machines. Alexandroupoli: IEEE, 1768–1774 Sarita K, Kumar S, Saket R K (2021). OC fault diagnosis of multilevel inverter using SVM technique and detection algorithm. Computers & Electrical Engineering, 96: 107481 Seifeddine S, Khmais B, Abdelkader C (2012). Power transformer fault diagnosis based on dissolved gas analysis by artificial neural network. In: 1st International Conference on Renewable Energies and Vehicular Technology. Nabeu: IEEE, 230–236 Shao H, Jiang H, Zhao H, Wang F (2017). A novel deep autoencoder feature learning method for rotating machinery fault diagnosis. Mechanical Systems and Signal Processing, 95: 187–204 Shao S, Yan R, Lu Y, Wang P, Gao R X (2020). DCNN-based multi-signal induction motor fault diagnosis. IEEE Transactions on Instrumentation and Measurement, 69(6): 2658–2669 Shen Y, Liu Z, Chang L (2018). A pantograph horn detection method based on deep learning network. In: 3rd Optoelectronics Global Conference. Shenzhen: IEEE, 85–89 Shi Y, Yi C, Lin J, Zhuang Z, Lai S (2020). Ensemble empirical mode decomposition-entropy and feature selection for pantograph fault diagnosis. Journal of Vibration and Control, 26(23–24): 2230–2242 Song H, Dai J, Luo L, Sheng G, Jiang X (2018). Power transformer operating state prediction method based on an LSTM network. Energies, 11(4): 914 Song H, Kim M, Park D, Shin Y, Lee J G (2022). Learning from noisy labels with deep neural networks: A survey. IEEE Transactions on Neural Networks and Learning Systems, in press, doi:https://doi.org/10.1109/TNNLS.2022.3152527 Sun R, Li L, Chen X, Wang J, Chai X, Zheng S (2020). Unsupervised learning based target localization method for pantograph video. In: 16th International Conference on Computational Intelligence and Security. Guilin: IEEE, 318–323 Sun X, Mao Z, Jiang B, Li M (2017). EEMD based incipient fault diagnosis for sensors faults in high-speed train traction systems. In: Chinese Automation Congress. Jinan: IEEE, 4804–4809 Tastimur C, Karaduman G, Akin E (2021). A novel method based on deep learning and image processing techniques for wearing inspection on the pantograph surface. In: Innovations in Intelligent Systems and Applications Conference. Elazig: IEEE, 1–7 Tran V T, Cattley R, Ball A, Liang B, Iwnicki S (2013). Fault diagnosis of induction motor based on a novel intelligent framework and transient current signals. Chemical Engineering Transactions, 33: 691–696 Uma Maheswari R, Umamaheswari R (2017). Trends in non-stationary signal processing techniques applied to vibration analysis of wind turbine drive train: A contemporary survey. Mechanical Systems and Signal Processing, 85: 296–311 Wan G, Liu X, Dong D (2009). Global fault diagnosis method of traction transformer based on improved fuzzy cellular neural network. In: 4th IEEE Conference on Industrial Electronics and Applications. Xi’an: IEEE, 353–357 Wang H, Liu Z, Peng D, Cheng Z (2022). Attention-guided joint learning CNN with noise robustness for bearing fault diagnosis and vibration signal denoising. ISA Transactions, 128(Part B): 470–484 Wang H, Xu J, Yan R, Gao R X (2020a). A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN. IEEE Transactions on Instrumentation and Measurement, 69(5): 2377–2389 Wang H, Zhang C, Zhang N, Chen Y, Chen Y (2019). Fault diagnosis for IGBTs open-circuit faults in high-speed trains based on convolutional neural network. In: Prognostics and System Health Management Conference. Qingdao: IEEE, 1–8 Wang L, Zhao X, Pei J, Tang G (2016). Transformer fault diagnosis using continuous sparse autoencoder. SpringerPlus, 5(1): 448 Wang T, He Y, Li B, Shi T (2018). Transformer fault diagnosis using self-powered RFID sensor and deep learning approach. IEEE Sensors Journal, 18(15): 6399–6411 Wang X, Yang B, Liu Q, Tu J, Chen C (2021). Diagnosis for IGBT open-circuit faults in photovoltaic inverters: A compressed sensing and CNN based method. In: 19th International Conference on Industrial Informatics. Palma de Mallorca: IEEE, 1–6 Wang Y, Quan W, Lu X, Peng Y, Zhou N, Zou D, Liu Y, Guo S, Zheng D (2020b). Anomaly detection of pantograph based on salient segmentation and generative adversarial networks. Journal of Physics: Conference Series, 1544(1): 012140 Wei X, Jiang S, Li Y, Li C, Jia L, Li Y (2020). Defect detection of pantograph slide based on deep learning and image processing technology. IEEE Transactions on Intelligent Transportation Systems, 21(3): 947–958 Wu C, Zhao J, Huang C, Zhang J (2012). Data-based fault diagnosis of traction converter and simulation study. In: 7th IEEE Conference on Industrial Electronics and Applications. Singapore: IEEE, 1512–1516 Xia Y, Gou B, Xu Y (2018a). A new ensemble-based classifier for IGBT open-circuit fault diagnosis in three-phase PWM converter. Protection and Control of Modern Power Systems, 3(1): 33 Xia Y, Gou B, Xu Y, Wilson G (2018b). Ensemble-based randomized classifier for data-driven fault diagnosis of IGBT in traction converters. In: IEEE Innovative Smart Grid Technologies. Singapore: IEEE, 74–79 Xia Y, Xu Y (2021). A transferrable data-driven method for IGBT open-circuit fault diagnosis in three-phase inverters. IEEE Transactions on Power Electronics, 36(12): 13478–13488 Xia Y, Xu Y, Gou B (2020). A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification. IEEE Transactions on Industrial Informatics, 16(8): 5223–5233 Xian X, Tang H, Tian Y, Liu Q, Fan Y (2021). Performance analysis of different machine learning algorithms for identifying and classifying the failures of traction motors. Journal of Physics: Conference Series, 2095(1): 012058 Xiao Y, Pan W, Guo X, Bi S, Feng D, Lin S (2020). Fault diagnosis of traction transformer based on Bayesian network. Energies, 13(18): 4966 Xu W A, Zhou J, Qiu G (2018). China’s high-speed rail network construction and planning over time: A network analysis. Journal of Transport Geography, 70: 40–54 Xu Y, Cai W, Xie T (2021a). Fault diagnosis of subway traction motor bearing based on information fusion under variable working conditions. Shock and Vibration, 5522887 Xu Y, Li C, Xie T (2021b). Intelligent diagnosis of subway traction motor bearing fault based on improved stacked denoising autoencoder. Shock and Vibration, 6656635 Yang H, Dobruszkes F, Wang J, Dijst M, Witte P (2018). Comparing China’s urban systems in high-speed railway and airline networks. Journal of Transport Geography, 68: 233–244 Yang Z, Huang X, Wu S, Peng H (2010). Traction technology for Chinese railways. In: International Power Electronics Conference. Sapporo: IEEE, 2842–2848 Yetis H, Karakose M, Aydin I, Akin E (2019). Bearing fault diagnosis in traction motor using the features extracted from filtered signals. In: International Artificial Intelligence and Data Processing Symposium. Malatya: IEEE, 1–4 Yuan F, Guo J, Xiao Z, Zeng B, Zhu W, Huang S (2019). A transformer fault diagnosis model based on chemical reaction optimization and twin support vector machine. Energies, 12(5): 960 Zang Y, Shangguan W, Cai B, Wang H, Pecht M G (2019). Methods for fault diagnosis of high-speed railways: A review. Proceedings of the Institution of Mechanical Engineers: Part O, Journal of Risk and Reliability, 233(5): 908–922 Zeng B, Guo J, Zhu W, Xiao Z, Yuan F, Huang S (2019). A transformer fault diagnosis model based on hybrid grey wolf optimizer and LS-SVM. Energies, 12(21): 4170 Zhang C, He Y, Du B, Yuan L, Li B, Jiang S (2020a). Transformer fault diagnosis method using IoT based monitoring system and ensemble machine learning. Future Generation Computer Systems, 108: 533–545 Zhang C, Wang C, Lu N, Jiang B (2019). An RBMs-BN method to RUL prediction of traction converter of CRH2 trains. Engineering Applications of Artificial Intelligence, 85: 46–56 Zhang D, Gao S, Yu L, Kang G, Zhan D, Wei X (2020b). A robust pantograph–catenary interaction condition monitoring method based on deep convolutional network. IEEE Transactions on Instrumentation and Measurement, 69(5): 1920–1929 Zhang Y, Ding X, Liu Y, Griffin P J (1996). An artificial neural network approach to transformer fault diagnosis. IEEE Transactions on Power Delivery, 11(4): 1836–1841 Zhang Y, Tiňo P, Leonardis A, Tang K (2021a). A survey on neural network interpretability. IEEE Transactions on Emerging Topics in Computational Intelligence, 5(5): 726–742 Zhang Z, Zhao Z, Li X, Zhang X, Wang S, Yan R, Chen X (2021b). Faster multiscale dictionary learning method with adaptive parameter estimation for fault diagnosis of traction motor bearings. IEEE Transactions on Instrumentation and Measurement, 70: 1–13 Zhao J, Wu C, Huang C, Wu F (2014). Parameter optimization algorithm of SVM for fault classification in traction converter. In: 26th Chinese Control and Decision Conference. Changsha: IEEE, 3786–3791 Zhao R, Yan R, Chen Z, Mao K, Wang P, Gao R X (2019). Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 115: 213–237 Zhong S, Fu S, Lin L (2019). A novel gas turbine fault diagnosis method based on transfer learning with CNN. Measurement, 137: 435–453 Zhou L, Wang D, Cui Y, Zhang L, Wang L, Guo L (2021a). A method for diagnosing the state of insulation paper in traction transformer based on FDS test and CS-DQ algorithm. IEEE Transactions on Transportation Electrification, 7(1): 91–103 Zhou Y, Yang X, Tao L, Yang L (2021b). Transformer fault diagnosis model based on improved gray wolf optimizer and probabilistic neural network. Energies, 14(11): 3029 Zhu J, Chen T, Fu Q (2014). The research and application of WNN in the fault diagnosis technology of electric locomotive main transformer. In: 7th IET International Conference on Power Electronics, Machines and Drives. Manchester: IEEE, 1–6 Zhu J, Chen T, Fu Q, Cheng S (2015). Detection of early failures within traction transformers based on Gaussian-PSO. In: 3rd International Conference on Electric Power Equipment, Switching Technology. Busan: IEEE, 488–491 Zhu J, Li S, Dong H (2021). Running status diagnosis of onboard traction transformers based on kernel principal component analysis and fuzzy clustering. IEEE Access, 9: 121835–121844 Zollanvari A, Kunanbayev K, Akhavan Bitaghsir S, Bagheri M (2021). Transformer fault prognosis using deep recurrent neural network over vibration signals. IEEE Transactions on Instrumentation and Measurement, 70: 1–11 Zou Y, Zhang Y, Mao H (2021). Fault diagnosis on the bearing of traction motor in high-speed trains based on deep learning. Alexandria Engineering Journal, 60(1): 1209–1219