Research on Fault Prediction Method for Electric Multiple Unit Gearbox Based on Gated Recurrent Unit–Hidden Markov Model
Source abstract
Abstract
Due to the limited availability of fault samples and the expensive nature of marking fault samples in Electric Multiple Unit (EMU) gearbox monitoring data, a study was conducted to simulate the degradation process of key components in the CRH5 gearbox using rigid–flexible coupling dynamics. Vibration acceleration data from the simulation were utilized to create a six-dimensional hybrid feature domain representing the degradation process. By leveraging the capabilities of the Hidden Markov Model (HMM) for handling hidden transitive probabilities in temporal data and Gated Recurrent Unit (GRU) for addressing long-distance and high-dependence temporal data, a GRU-HMM fault prediction model was developed. This model was validated using monitoring data and the six-dimensional hybrid feature domain from the CRH5 gearbox and compared against actual maintenance records. The findings indicated that the GRU-HMM fault prediction model can effectively recognize the degradation patterns of multiple components, offering higher accuracy in fault prediction compared to traditional models. These research outcomes are expected to optimize EMU maintenance schedules based on usage conditions, enhance EMU utilization rates, and reduce operational and maintenance costs, thereby providing valuable theoretical support.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Engineering Diagnostics and Reliability · Machine Fault Diagnosis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Traffic and Transportation Engineering, Dalian Jiaotong University, Dalian 116028, China
School of Mechanical Engineering, Dalian Jiaotong University, Dalian 116028, China
Funding
Liaoning Provincial Education Department
References (39)
Show source-provided references
1. Integrated Vibro-Acoustic Analysis and Empirical Mode Decomposition for Fault Diagnosis of Gears in a Wind Turbine10.1016/j.prostr.2019.07.074 ↗
2. A composite fault feature extraction method for rotating machinery based on nonlinear mode decomposition
3. Based on improved MOMEDA for gearbox composite fault diagnosis
4. Novel Fourier quadrature transforms and analytic signal representations for nonlinear and non-stationary time-series analysis10.1098/rsos.181131 ↗
5. Application of EMD ANN and DNN for Self-Aligning Bearing Fault Diagnosis
6. Selecting effective intrinsic mode functions of empirical mode decomposition and variational mode decomposition using dynamic time warping algorithm for rolling element bearing fault diagnosis10.1177/0142331218790788 ↗
7. Michau, G., and Fink, O. (2019, January 17–20). Unsupervised Fault Detection in Varying Operating Conditions. Proceedings of the 2019 IEEE International Conference on Prognostics and Health Management 2019 (PHM 2019—San Francisco), San Francisco, CA, USA.10.1109/ICPHM.2019.8819383 ↗
8. Fujita, Y., Nagarajan, P., Kataoka, T., and Ishikawa, T. (2021). ChainerRL: A Deep Reinforcement Learning Library, Cornell University Library.
9. Deep Reinforcement Learning for Adaptive Learning Systems10.3102/10769986221129847 ↗
10. A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning10.1007/s11370-021-00398-z ↗
11. Zhang, Z., Zhang, X., Zhang, P., Wu, F., and Li, X. (2018). Gearbox Composite Fault Diagnosis Method Based on Minimum Entropy Deconvolution and Improved Dual-Tree Complex Wavelet Transform. Entropy, 21.10.3390/e21010018 ↗
12. A compound fault diagnosis method of rolling bearing based on wavelet scattering transform and improved soft threshold denoising algorithm10.1016/j.measurement.2022.111276 ↗
13. Tutivén, C., Vidal, Y., Insuasty, A., Campoverde-Vilela, L., and Achicanoy, W. (2022). Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVM. Energies, 15.10.3390/en15124381 ↗
14. Research on Bearing Fault Diagnosis Based on Multiscale Intrinsic Mode Permutation Entropy and SA-SVM10.3901/JME.2018.09.168 ↗
15. An Efficient CNN with Tunable Input-Size for Bearing Fault Diagnosis10.2991/ijcis.d.210113.001 ↗
16. Rao, M., and Zuo, M.J. (2018, January 17–20). In A New Strategy for Rotating Machinery Fault Diagnosis under Varying Speed Conditions Based on Deep Neural Networks and Order Tracking. Proceedings of the 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA.10.1109/ICMLA.2018.00197 ↗
17. Generalization of deep neural network for bearing fault diagnosis under different working conditions using multiple kernel method10.1016/j.neucom.2019.04.010 ↗
18. Semi-Supervised Gear Fault Diagnosis Using Raw Vibration Signal Based on Deep Learning10.1016/j.cja.2019.04.018 ↗
19. An intelligent fault diagnosis method for rotating machinery based on data fusion and deep residual neural network10.1007/s10489-021-02555-4 ↗
20. Improved Deep Transfer Auto-Encoder for Fault Diagnosis of Gearbox under Variable Working Conditions with Small Training Samples10.1109/ACCESS.2019.2936243 ↗
21. Wheel Defect Detection with Machine Learning10.1109/TITS.2017.2720721 ↗
22. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings10.1016/j.ymssp.2018.12.051 ↗
23. Vibration response characteristics of a dual-rotor with unbalance-misalignment coupling faults: Theoretical analysis and experimental study10.1016/j.mechmachtheory.2018.03.009 ↗
24. Research on Status Monitoring of Suspension Components in Rail Vehicles Based on Machine Learning Methods
25. Fu, Y., Huang, D., Qin, N., Liang, K., and Yang, Y. (2018, January 25–27). High-Speed Railway Bogie Fault Diagnosis Using LSTM Neural Network. Proceedings of the 2018 37th Chinese Control Conference (CCC), Wuhan, China.10.23919/ChiCC.2018.8483987 ↗
26. Convolutional Recurrent Neural Network for Fault Diagnosis of High-Speed Train Bogie10.1155/2018/4501952 ↗
27. Fault diagnosis of high-speed train bogie based on LSTM neural network
28. Transformer for High-Speed Train Wheel Wear Prediction with Multiplex Local-Global Temporal Fusion10.1109/TIM.2022.3216413 ↗
29. Cheng, C., Qiao, X., Fu, C., Wang, W., and Yin, X. (2019, January 5–7). Fault Prediction of High-Speed Train Running Gears Based on Hidden Markov Model and Analytic Hierarchy Process. Proceedings of the 2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), Xiamen, China.10.1109/SAFEPROCESS45799.2019.9213355 ↗
30. Schmidt, K., and Hoffmann, K.H. (2019, January 7–10). Modified Baum Welch Algorithm for Hidden Markov Models with Known Structure. Proceedings of the International Conference on Intelligent Human Systems Integration, San Diego, CA, USA.10.1007/978-3-030-11051-2_75 ↗
31. Zhu, H. (2019). Research on Vibration Characteristics and Fatigue Failure of Gearbox Box of High Speed EMU. [Ph.D. Thesis, Southwest Jiaotong University].
32. Research on Fault Characteristics of Gear Box Broken Teeth in High Speed Train Based on ADAMS
33. Song, W. (2020). Research on Wheel Rail Load Characteristics and Track Excitation of Standard High-Speed Trains. [Ph.D. Thesis, Beijing Jiaotong University].
34. Liao, P. (2019). A Calculation Model for Mesh Stiffness of Spiral Bevel Gears and Research on Vibration Characteristics of Transmission Systems. [Ph.D. Thesis, Chongqing University].
35. Lo, C.C., Lee, C.H., and Huang, W.C. (2020). Prognosis of Bearing and Gear Wears Using Convolutional Neural Network with Hybrid Loss Function. Sensors, 20.10.3390/s20123539 ↗
36. Using Deep Learning-Based Approach to Predict Remaining Useful Life of Rotating Components10.1109/TSMC.2017.2697842 ↗
37. Liu, H.K., Ding, K., He, G.L., Li, W.H., and Lin, H.B. (2024). Research on the prediction method of gear remaining service life by combined failure mechanism and convolutional neural network. J. Mech. Eng., Available online: http://kns.cnki.net/kcms/detail/11.2187.th.20240322.1652.020.html.
38. Highly Accurate Machine Fault Diagnosis Using Deep Transfer Learning10.1109/TII.2018.2864759 ↗
39. A time-series reconstruction model for gear performance degradation assessment