RESEARCH PAPER
Reliability Prediction Method for Onboard ATP Based on Optimized Empirical Mode Decomposition
1
Lanzhou Jiaotong University, China
Submission date: 2025-05-07
Final revision date: 2025-09-16
Acceptance date: 2025-10-28
Online publication date: 2025-11-21
Publication date: 2025-11-21
Eksploatacja i Niezawodność – Maintenance and Reliability 2026;28(2):213708
HIGHLIGHTS
- Time series decomposition is applied to predict ATP failure rates.
- The proposed model demonstrates robust performance with small training datasets.
- A hybrid WLSSVM-temporal decomposition framework is proposed.
KEYWORDS
TOPICS
ABSTRACT
Automatic Train Protection (ATP) system reliability significantly impacts rail safety and maintenance efficiency, but current strategies lack data-driven spare parts optimization. We propose a hybrid failure rate prediction model combining time-varying filtered empirical mode decomposition (TVFEMD) and machine learning. First, ATP operational data undergoes interval segmentation and zero-value preprocessing. Next, grey wolf optimization (GWO) adaptively tunes TVFEMD parameters to decompose failure rate series into intrinsic mode functions (IMFs). Each IMF is independently predicted via weighted least squares support vector machine (WLSSVM), with final outputs aggregated through superposition. Validated using real ATP system data, the model achieves 0.0028 MAE, 0.0066 RMSE, and 0.0139 MAPE for 10-minute interval predictions with zero-inflated data, surpassing baseline methods. Results confirm its effectiveness for ATP failure rate forecasting.
REFERENCES (54)
1.
Shi Z, Li Y, Guo J, et al. Testing Modeling Method for Engineering Testing of High-Speed Railway Signaling System. Journal of Southwest Jiaotong University, 2024; 59(5): 1023-1033, https://doi.org/10.3969/j.issn....
2.
Shangguan W, Hu F, Yuan M, et al. Reliability Analysis Method for On-board Equipment of Train Control System Based on Resilience Effect. Journal of the China Railway Society, 2018; 40(6): 75-82, https://doi.org/10.3969/j.issn....
3.
Zheng S, Cheng J, Sun D. ATP On-board Equipment Fault Classification and Management Method Research. Railway Signalling & Communication, 2013; 49(7): 1-4, https://doi.org/10.13879/j.iss....
4.
Deng L, Liu J, Liu M, Cao Y, Wen C, Deng X. Remaining Useful Life Prediction Based on Cross-Temporal Dynamic Graph Convolutional Network. Eksploatacja i Niezawodność - Maintenance and Reliability, 2025, https://doi.org/10.17531/ein/2....
5.
Kang R. Intelligent Operations for ATP Systems of High-speed Railway Based on Machine Learning [D]. Beijing Jiaotong University, 2022, https://doi.org/10.26944/d.cnk....
6.
Balakrishnan K, Mani I, Sankaran D. Predicting the overall equipment efficiency of core drill rigs in mining using ANN and improving it using MCDM. Eksploatacja i Niezawodność - Maintenance and Reliability, 2023; 25(3), https://doi.org/10.17531/ein/1....
7.
Lv Q, He G, Cheng J. Research on Operation and Maintenance Management of ATP On-board Equipment Based on Information Technology. Railway Signalling & Communication, 2014; 50(1): 4-7, https://doi.org/10.13879/j.iss....
8.
Yuan Y, Zhang Y, Ding H. Research on Key Technology of Industrial Artificial Intelligence and Its Application in Predictive Maintenance. Acta Automatica Sinica, 2020; 46(10): 2013-2030, https://doi.org/10.16383/j.aas....
9.
Yang B, Liang X, Xu S, et al. A time-series based deep survival analysis model for failure prediction in urban infrastructure systems. Engineering Applications of Artificial Intelligence, 2024; 136(Part A): 15, https://doi.org/10.1016/j.enga....
10.
Li W, Ma Y, Nie P, et al. Grey GM(1,N) and PLS Combined Model for Failure Rate Prediction of Airborne Equipment. Fire Control & Command Control, 2022; 47(8): 98-102, https://doi.org/10.3969/j.issn....
11.
Xu D, Zhou C, Guan C, et al. Research on the Equipment Failure Rate Prediction Method Based on ARMA-BP Combined Model. Fire Control & Command Control, 2021; 46(1): 83-87, https://doi.org/10.3969/j.issn....
12.
Kang J, Lu Y, Zhao B, et al. Remaining useful life prediction of cylinder liner based on nonlinear degradation model. Eksploatacja i Niezawodność, 2022; 24(1), https://doi.org/10.17531/ein.2....
13.
Li R, Kang R. Research on failure rate forecasting method based on ARMA model. Systems Engineering and Electronics, 2008; (8): 1588-1591, https://doi.org/10.3321/j.issn....
14.
Sun Y, Li C, Wei Y, et al. Fault rate prediction method of circuit breaker based on hybrid learning method. Mechanical & Electrical Technique of Hydropower Station, 2023; 46(12): 117-120, https://doi.org/10.13599/j.cnk....
15.
Wang H, Zhao X, Guo Q, et al. A novel hybrid model by integrating TCN with TVFEMD and permutation entropy for monthly non-stationary runoff prediction. Scientific Reports, 2024; 14(1), https://doi.org/10.1038/s41598....
16.
Jinyong G, Sheng L, Junshan T, et al. Traffic Flow Prediction for Highway Based on Multi-Task Spatiotemporal Graph Network. Transportation Safety and Environment, 2025, https://doi.org/10.1093/tse/td....
17.
Wang C, Lin H, Yang M, et al. Ultra-short-term wind farm cluster interval power prediction based on cluster division and MQ-WaveNet-MSA. Electric Power Systems Research, 2025; 244, https://doi.org/10.1016/j.epsr....
18.
Zhang J, Sun T, Guo X, et al. Short-term photovoltaic power prediction with CPO-BILSTM based on quadratic decomposition. Electric Power Systems Research, 2025; 243, https://doi.org/10.1016/j.epsr....
19.
Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition method and the Hilbert spectrum for non-stationary time series analysis. Proceedings of the Royal Society A, 1998, https://doi.org/10.1098/rspa.1....
20.
Poongadan S, Lineesh M C. A hybrid deep learning network for non-linear time series prediction. Journal of Mathematics and Computer Science, 2022; 12: Article ID 158, https://doi.org/10.28919/jmcs/....
21.
Flandrin P, Rilling G, Goncalves P. Empirical mode decomposition as a filter bank. IEEE Signal Processing Letters, 2004; 11(2): 112-114, https://doi.org/10.1109/LSP.20....
22.
Xu T, Lu C, Wang H, et al. Fault rate prediction method based on relevant vector EMD and GMDH reconstruction. Journal of Vibration, Measurement & Diagnosis, 2018; 38(6): 1275-1285+1300, https://doi.org/10.16450/j.cnk....
23.
Hu Y, Li F, Yang S. Failure rate prediction and early warning monitoring based on flight test data. Journal of Ordnance Equipment Engineering, 2020; 41(7): 224-227, https://doi.org/10.11809/bqzbg....
24.
Wu Z, Huang N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method. Advances in Adaptive Data Analysis, 2011; 1(1), https://doi.org/10.1142/S17935....
25.
Zhang J, Zhang J, Zhong M, et al. Weak fault diagnosis of wind turbine bearings based on PSO-VMD-MCKD method. Journal of Vibration, Measurement & Diagnosis, 2020; 40(2): 287-296+418, https://doi.org/10.16450/j.cnk....
26.
Li N, Yang D, Wang Z, et al. Chatter online monitoring method for roll grinder using TVFEMD and instantaneous energy ratio. Journal of Electronic Measurement and Instrumentation, 2024; 38(1): 228-236, https://doi.org/10.13382/j.jem....
27.
Li S, Xin J, Jiang L, et al. A denoising method for bridge monitoring data based on TVFEMD-IMF energy entropy increment. Journal of Vibration, Measurement & Diagnosis, 2024; 44(1): 178-185+206, https://doi.org/10.16450/j.cnk....
28.
Wang D, Li X, Huang Y, et al. Short-term wind speed prediction based on time-varying filtered empirical modal decomposition with spatio-temporal correlation error correction. Journal of North China Electric Power University (Natural Science Edition), 2025, https://doi.org/10.1109/CCDC62....
29.
Zhang N, Zhu Y, Sun N, et al. Vibration trend prediction of hydropower units based on OVMD-TVFEMD secondary decomposition and HPO-ELM. Water Resources and Power, 2023; 41(10): 204-207+199, https://doi.org/10.20040/j.cnk....
30.
Heng A, Zhi B, Wei C. A time varying filter approach for empirical mode decomposition. Signal Processing, 2017, https://doi.org/10.1016/j.sigp....
31.
Ma X, Lu X, Zhang Z, et al. A non-contact HRV estimation method based on TVF-EMD. Journal of Data Acquisition and Processing, 2024; 39(4): 1009-1019, https://doi.org/10.16337/j.100....
32.
Zang X, Zhang T, Shao X, et al. A transformer internal mechanical fault diagnosis method based on TVFEMD and SSA-LSSVM. Electric Machines & Control Application, 2023; 50(9): 49-56, https://doi.org/10.12177/emca.....
33.
Deng Z, Xie J, Cui D. Daily sediment concentration prediction based on TVFEMDII-Ten Fish Swarm Algorithm-DHKELM model. China Rural Water and Hydropower, 2025, https://doi.org/10.12396/znsd.....
34.
Tan B, Wang D, Shi J, et al. Temperature field prediction of steel-concrete composite decks using TVFEMD-stacking ensemble algorithm. Journal of Zhejiang University-Science A (Applied Physics & Engineering), 2024; 25(9): 732-748, https://doi.org/10.1631/jzus.A....
35.
Yin Y. Research on short-term load forecasting of microgrid based on TVFEMD-WOA-LSTM-ARMAX [D]. Wuhan University of Science and Technology, 2024, https://doi.org/10.1007/s42341....
36.
Wang X, Shang H, Li N. Research on advanced manufacturing process monitoring and fault prediction method based on machine learning. Automation and Machine Learning, 2023; 4: 87-92, https://doi.org/10.23977/autml....
37.
Liang J, Yin L, Xin Y, et al. Short-term photovoltaic power prediction based on CEEMDAN-PE and BiLSTM neural network. Electric Power Systems Research, 2025; 246: 111706, https://doi.org/10.1016/j.epsr....
38.
Cortes C, Vapnik V. Support-vector networks. Machine Learning, 1995; 20(3): 273-297, https://doi.org/10.1023/A:1022....
39.
Suykens J A K, Vandewalle J. Least squares support vector machine classifiers. Neural Processing Letters, 1999; 9(3): 293-300, https://doi.org/10.1023/A:1018....
40.
Xiong R, Xiao C, Li Y. Electric drive system of shovel forecasting based on wavelet and least square support vector machines. Journal of China Jiliang University, 2008; (1): 51-55.
41.
Cui J, Li Q. Application of improved WLSSVM model in the prediction of gasoline dry point at the top of atmospheric tower. Journal of Liaoning Petrochemical University, 2023; 43(1): 67-72, https://doi.org/10.12422/j.iss....
42.
Zhang X, Zhang Y. Prediction of external corrosion rate of buried pipelines based on KPCA-ALO-WLSSVM. Journal of Safety and Environment, 2022; 22(4): 1804-1812, https://doi.org/10.13637/j.iss....
43.
Chang X, Yang S, Yang D. Temperature modeling of PVC stripping process using weighted least square support vector machine. Plastics Science and Technology, 2020; 48(4): 74-77, https://doi.org/10.15925/j.cnk....
44.
Suykens J A K, Brabanter J D, Lukas L, et al. Weighted least squares support vector machines: robustness and sparse approximation. Neurocomputing, 2002; 48(1-4): 85-105, https://doi.org/10.1016/S0925-....
45.
Wang R, Wang Y, Lu J. Prediction of photovoltaic power generation based on ICEEMDAN-DTW and ISMA-WLSSVM. Journal of Engineering for Thermal Energy and Power, 2023; 38(9): 131-140, https://doi.org/10.16146/j.cnk....
46.
Chen K, Ding M, Liu J, et al. Short term wind power prediction based on WLSSVM optimized by improved grey wolf optimization algorithm. Inner Mongolia Electric Power, 2024; 42(2): 1-7, https://doi.org/10.19929/j.cnk....
47.
Lei X. Multiverse optimization algorithm optimizes network traffic prediction of weighted least squares support vector machine. Automation & Instrumentation, 2023; (5): 51-55, https://doi.org/10.14016/j.cnk....
48.
Badar A Q H. Grey wolf optimizer. Advances in Engineering Software, 2014; 69: 46-61, https://doi.org/10.1016/j.adve....
49.
Cao W. Fault diagnosis of tooth surface spalling of planetary gearbox based on GWO-TVF-EMD method [D]. Xi'an Technological University, 2021, https://doi.org/10.13224/j.cnk....
50.
Zhao S, Wei Z, Guo S, et al. Method for removing multi-frequency vibration information from 3D laser-scanned pavement point clouds. Laser & Optoelectronics Progress, 2023; (20): 060, https://doi.org/10.3788/LOP223....
51.
Tang G, Wang X. Parameter optimized variational mode decomposition method with application to incipient fault diagnosis of rolling bearing. Journal of Xi'an Jiaotong University, 2015; 49(5): 73-81, https://doi.org/10.7652/xjtuxb....
52.
Unser M. Splines: a perfect fit for signal and image processing. IEEE Signal Processing Magazine, 1999; 16(6): 22-38, https://doi.org/10.1109/79.799....
53.
Kang R, Wang J, Cheng J, et al. Prediction of failure rate of ATP on-board equipment based on chaos theory. Journal of the China Railway Society, 2016; 38(9): 59-65, https://doi.org/10.3969/j.issn....
54.
Fernandez Martinez R, Alberdi R, Fernandez E, et al. Improvement of transmission line ampacity utilization via machine learning-based dynamic line rating prediction. Electric Power Systems Research, 2024; 236: 110931, https://doi.org/10.1016/j.epsr....
Share
RELATED ARTICLE
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
