In order to solve the problem of the difference in applicability of a single model in predicting the failure rate, TSOBP-ARIMA-Prophet combined model was proposed on the basis of considering the characteristics of the EMU traction system failure rate data. Firstly, in view of the complex nonlinearity of the EMU traction system failure rate, the tuna swarm algorithm (TSO) was introduced to optimize the BP model and train the TSOBP prediction model. Secondly, aiming at the non-stationary fluctuation of the failure rate, the ARIMA prediction model was selected. Then, according to the seasonal periodicity of the failure rate, the Prophet prediction model was selected. Finally, the reciprocal variance method was used to weight the prediction results of the three models, and the prediction results of the TSOBP-ARIMA-Prophet combined model were obtained. Taking an EMU traction system as an example, the combined model is used to predict the failure rate, and its prediction ability is verified by comparing with three single models and the TSOBP-ARIMA combined model. The results show that the mean square error of the combined model is 0.075 2, which is 45.83%, 61.65% and 53.42% lower than that of the TSOBP, ARIMA and Prophet models respectively, and the prediction accuracy is significantly improved, and the perception of data trend is better than that of the TSOBP-ARIMA combined model, which can effectively improve the prediction ability of the failure rate of the EMU traction system.
WANGTongjun. Innovation and Practice of Construction and Operation Management for Intelligent High-Speed Railway Based on System Theory [J]. China Railway Science, 2021, 42 (2): 1-8. in Chinese
LIJianwei, CHENGXiaoqing, QINYong, et al. Reliability Prediction of Urban Rail Transit Vehicles Based on BP Neural Network [J]. Journal of Central South University (Science and Technology), 2013, 44 (): 42-46. in Chinese
ZHAYuanyuan, WANGTingling, SHANGGuanwei. Bayesian Network-Based Fault Diagnosis for on-Board Equipment of Train Controlled System [J]. Journal of Beijing Jiaotong University, 2021, 45 (5): 37-45. in Chinese
LIUQi, WANGJunfeng. Research on Failure Rate Prediction of on-Board ATP Based on MEA-Optimized Chaos-Elman Model [J]. Journal of Railway Science and Engineering, 2019, 16 (12): 3094-3101. in Chinese
LUBihong, ZHANGBinghai, QUBaozhang. Failure Mode Effect Criticality Analysis for Traction Power Supply System of Electric Multiple Unit [J]. Vibration, Testing and Diagnostics, 2016, 36 (1): 97-101, 200. in Chinese
SUNJianfang. Research on Main Top Technical Indexes for Traction System of 400 km · h-1 EMU [J]. China Railway Science, 2017, 38 (5): 70-77. in Chinese
ZHOUXinli. Reliability Analysis of the High Voltage Traction System for CR400AF EMU Based on FMECA [J]. Rail Transportation Equipment and Technology, 2021 (1): 4-6, 9. in Chinese
SHENJianlei, WUYong, TANWenjun, et al. Fault Analysis and Solutions for High Voltage a Terminal of Traction Transformer [J]. Electric Locomotives & Mass Transit Vehicles, 2021, 44 (1): 93-95. in Chinese
[17]
刘一凡.动车组故障预测技术研究[D]. 石家庄:石家庄铁道大学,2022.
[18]
LIUYifan. Research on Fault Prediction Technology of EMU [D]. Shijiazhuang: Shijiazhuang Tiedao University, 2022. in Chinese
[19]
朱湘.基于寿命周期费用和可靠性评估的动车组维修策略优化[D].北京:中国铁道科学研究院,2023.
[20]
ZHUXiang. Optimization Maintenance Strategy for EMU Based on Life Cycle Cost and Reliability Assessment [D]. Beijing: China Academy of Railway Science, 2023. in Chinese
ZHANGMingming, ZHANGHesheng, LIUYang, et al. Early Failure Rate Estimation of High-Speed EMU Motor Set Based on Fault Tree and Bayesian Network [J]. Journal of Beijing Jiaotong University, 2021, 45 (6): 51-57. in Chinese
[23]
LIWenqiang, ZHANGChang. Application of Combination Forecasting Model in Aircraft Failure Rate Forecasting [J]. Computational Intelligence and Neuroscience, 2022: 6729608.
JIYuwei, WUHonglan. Fault Detection Method of Aircraft Bleed Air System Based on SVM [J]. Measurement & Control Technology, 2021, 40 (3): 51-55. in Chinese
CHENGYubo, CHEJianguo, YANGZuobin, et al. Requirement Forecast of Maintenance Equipment Based on Exponential Smoothing [J]. Command Control & Simulation, 2009, 31 (1): 115-117. in Chinese
WANGXin, WUJi, LIUChao, et al. Exploring LSTM Based Recurrent Neural Network for Failure Time Series Prediction [J]. Journal of Beijing University of Aeronautics and Astronautics, 2018 (44): 772-784. in Chinese
LIYuan, ZHENGAngang, TANHuang, et al. A New Method for Predicting the Monthly Fault Number of Watt-Hour Meters Based on Time Series [J]. Electric Power, 2020, 53 (6): 72-80. in Chinese
[32]
YiLYU, JIANGYijie. Examination on Avionics System Fault Prediction Technology Based on Ashy Neural Network and Fuzzy Recognition [J]. Journal of Intelligent and Fuzzy Systems, 2020, 38 (4): 3939-3947.
ZHANGYunlong, PANQuan, ZHANGHongcai. New Synthetic Prediction Method Based on SVR and Its Application [J]. Journal of Air Force Engineering University (Natural Science Edition), 2005 (3): 19-21, 46. in Chinese
WEIWei, ZHAOXiaoqiang, WUJin. Time Series Prediction of Fault Rate of High-Speed Railway on-Board Equipment Based on VMD-ICSO-GRU [J]. Journal of the China Railway Society, 2023, 45 (6): 58-68. in Chinese
[37]
周志华.机器学习[M].北京:清华大学出版社,2016.
[38]
ZHOUZhihua. Machine Learning [M]. Beijing: Tsinghua University Press, 2016. in Chinese
[39]
李瑞莹,康锐.基于神经网络的故障率预测方法[J].航空学报,2008,29(2):357-363.
[40]
LIRuiying, KANGRui. Failure Rate Forecasting Method Based on Neural Networks [J]. Acta Aeronautica et Astronautica Sinica, 2008, 29 (2): 357-363. in Chinese
[41]
WEIRuonan, JIANGJu, XUHaiyan, et al. Novel Topology Convolutional Neural Network Fault Diagnosis for Aircraft Actuators and Their Sensors [J]. Transactions of the Institute of Measurement and Control, 2021, 43 (11): 2551-2566.
FENGJian, YAOHanqi, HUANGXiaohu, et al. Application of ARIMA Algorithm to Industrial Controller Fault Prediction [J]. Process Automation Instrumentation, 2022, 43 (11): 62-67. in Chinese
DUHongbing, XINGMengke, ZHAODechao. Application of Prophet-LSTM Combined Model in Prediction of Air Transportation Incidents [J]. Journal of Safety and Environment, 2023: 1-9. in Chinese
[46]
冯玎.基于运行特性的高铁牵引供电系统可靠性与风险评估研究[D].成都:西南交通大学,2019.
[47]
FENGYue. Research on Reliability and Risk Assessment of High-Speed Railway Traction Power Supply System Based on Operation Characteristics [D]. Chengdu: Southwest Jiaotong University, 2019. in Chinese
GAOFengyang, WANGWenxiang, ZHANGHaoran, et al. Operation and Maintenance Strategy for the Electrical System of Urban Rail Vehicle without Overhead Contact Line Based on State and Risk Assessment [J]. China Railway Science, 2022, 43 (4): 148-156. in Chinese
QUANYiming, YUMin, WANGWenbo, et al. Short-Term Wind Speed Prediction Based on Fractal Optimization of VMD-GA-BP [J]. Acta Energiae Solaris Sinica, 2023, 44 (7): 436-446. in Chinese
LIANGQiangsheng, XUXinyue, LIULiqiang. Data-Driven Short-Term Passenger Flow Prediction Model for Urban Rail Transit [J]. China Railway Science, 2020, 41 (4): 153-162. in Chinese