JILSA  Vol.12 No.3 , August 2020
Fusion of Model-Based and Data Driven Based Fault Diagnostic Methods for Railway Vehicle Suspension
Abstract: Transportation of freight and passengers by train is one of the oldest types of transport, and has now taken root in most of the developing countries especially in Africa. Recently, with the advent and development of high-speed trains, continuous monitoring of the railway vehicle suspension is of significant importance. For this reason, railway vehicles should be monitored continuously to avoid catastrophic events, ensure comfort, safety, and also improved performance while reducing life cycle costs. The suspension system is a very important part of the railway vehicle which supports the car-body and the bogie, isolates the forces generated by the track unevenness at the wheels and also controls the attitude of the car-body with respect to the track surface for ride comfort. Its reliability is directly related to the vehicle safety. The railway vehicle suspension often develops faults; worn springs and dampers in the primary and secondary suspension. To avoid a complete system failure, early detection of fault in the suspension of trains is of high importance. The main contribution of the research work is the prediction of faulty regimes of a railway vehicle suspension based on a hybrid model. The hybrid model framework is in four folds; first, modeling of vehicle suspension system to generate vertical acceleration of the railway vehicle, parameter estimation or identification was performed to obtain the nominal parameter values of the vehicle suspension system based on the measured data in the second fold, furthermore, a supervised machine learning model was built to predict faulty and healthy state of the suspension system components (damage scenarios) based on support vector machine (SVM) and lastly, the development of a new SVM model with the damage scenarios to predict faults on the test data. The level of degradation at which the spring and damper becomes faulty for both primary and secondary suspension system was determined. The spring and damper becomes faulty when the nominal values degrade by 50% and 40% and 30% and 40% for the secondary and primary suspension system respectively. The proposed model was able to predict faulty components with an accuracy of 0.844 for the primary and secondary suspension system.
Cite this paper: Ankrah, A. , Kimotho, J. and Muvengei, O. (2020) Fusion of Model-Based and Data Driven Based Fault Diagnostic Methods for Railway Vehicle Suspension. Journal of Intelligent Learning Systems and Applications, 12, 51-81. doi: 10.4236/jilsa.2020.123004.

[1]   Iwnicki, S. (2006) Handbook of Railway Vehicle Dynamics. CRC Press, Boca Raton.

[2]   Wei, X. and Jia, L. (2014) MBPLS-Based Rail Vehicle Suspension System Fault Detection. The 26th Chinese Control and Decision Conference (2014 CCDC), Changsha, 31 May-2 June 2014, 3602-3607.

[3]   Xu, B., Zhang, J. and Guan, X. (2015) Estimation of the Parameters of a Railway Vehicle Suspension Using Model-Based Filters with Uncertainties. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 229, 785-797.

[4]   Dumitriu, M. (2019) Numerical Analysis of the Vertical Bogie Accelerations at Failure of the Damper in the Primary Suspension of the Railway Vehicle. Materials Science Forum, Vol. 957. 43-52.

[5]   Atamuradov, V., Medjaher, K., Dersin, P., Lamoureux, B. and Zerhouni, N. (2017) Prognostics and Health Management for Maintenance Practitioners—Review, Implementation and Tools Evaluation. International Journal of Prognostics and Health Management, 8, 1-31.

[6]   Peng, X. and Jin, X. (2018) Rail Suspension System Fault Detection Using Deep Semi-Supervised Feature Extraction with One-Class Data. Proceedings of the Annual Conference of the PHM Society, Vol. 10, 1-11.

[7]   Mori, H. and Tsunashima, H. (2010) Condition Monitoring of Railway Vehicle Suspension Using Multiple Model Approach. Journal of Mechanical Systems for Transportation and Logistics, 3, 243-258.

[8]   Li, P. and Goodall, R. (2004) Model-Based Condition Monitoring for Railway Vehicle Systems. University of Bath, Bath.

[9]   Melnik, R. and Koziak, S. (2017) Rail Vehicle Suspension Condition Monitoring Approach and Implementation. Journal of Vibroengineering, 19, 487-501.

[10]   Wei, X., Liu, H. and Qin, Y. (2011) Fault Diagnosis of Rail Vehicle Suspension Systems by Using GLRT. Control and Decision Conference (CCDC), 3, 1932-1936.

[11]   Wei, X., Jia, L. and Liu, H. (2012) Data-Driven Fault Detection of Vertical Rail Vehicle Suspension Systems. UKACC International Conference on Control (CONTROL), Cardiff, 3-5 September 2012, 589-594.

[12]   Wei, X., Guo, Y., Jia, L. and Liu, H. (2013) Fault Detection of Rail Vehicle Suspension System Based on CPCA. 2013 Conference on Control and Fault-Tolerant Systems (SysTol), Nice, 9-11 October 2013, 700-705.

[13]   Ding, X. and Mei, T. (2008) Fault Detection for Vehicle Suspensions Based on System Dynamic Interactions. Proceedings of the UKACC International Conference on Control, Manchester, 2-4 September 2008, 1-6.

[14]   Al, S., Bionda, S., Bruni, S. and Gasparetto, L. (2011) Condition Monitoring of Suspension Components in Railway Bogies. Institution of Engineering and Technology, London.

[15]   Wu, Y., Jiang, B., Lu, N. and Zhou, D. (2015) Tomfir-Based Incipient Fault Detection and Estimation for High-Speed Rail Vehicle Suspension System. Journal of the Franklin Institute, 352, 1672-1692.

[16]   Melnik, R. and Sowiński, B. (2014) The Selection Procedure of Diagnostic Indicator of Suspension Fault Modes for the Rail Vehicles Monitoring System. 7th European Workshop on Structural Health Monitoring, Nantes, 8-11 July 2014, 159-166.

[17]   Ding, X. (2009) Fault Detection and Isolation for Railway Vehicle Suspensions. PhD Dissertation.

[18]   Robson, J. and Kamash, K. (1977) Road Surface Description in Relation to Vehicle Response. Vehicle System Dynamics, 6, 153-157.

[19]   PHM Data Challenge 2017.

[20]   Kimotho, J.K. (2016) Development and Performance Evaluation of Prognostic Approaches for Technical Systems. PhD Dissertation, University of Paderborn, Paderborn.

[21]   Maksoud, E.A.A., Barakat, S. and Elmogy, M. (2019) Medical Images Analysis Based on Multilabel Classification. In: Machine Learning in Bio-Signal Analysis and Diagnostic Imaging, Elsevier, Amsterdam, 209-245.

[22]   Medjaher, K., Camci, F. and Zerhouni, N. (2012) Feature Extraction and Evaluation for Health Assessment and Failure Prognostics. Proceedings of the First European Conference of the Prognostics and Health Management Society, Dresden, 3-5 July 2012, 98-103.

[23]   Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P. and Gao, R.X. (2019) Deep Learning and Its Applications to Machine Health Monitoring. Mechanical Systems and Signal Processing, 115, 213-237.

[24]   Kimotho, J.K. and Sextro, W. (2014) An Approach for Feature Extraction and Selection from Non-Trending Data for Machinery Prognosis. Proceedings of the Second European Conference of the Prognostics and Health Management Society, Nantes, 8-10 July 2014, 1-8.

[25]   Niu, G. (2017) Data-Driven Technology for Engineering Systems Health Management. Springer, Berlin.

[26]   Patel, C., Gohil, P. and Borhade, B. (2010) Modelling and Vibration Analysis of a Road Profile Measuring System. International Journal of Automotive and Mechanical Engineering, 1, 13-28.