Feasibility study of a rail vehicle damper fault detection by artificial neural networks

• Autorzy: Melnik Rafał , Koziak Seweryn , Dižo Ján , Kuźmierowski Tomasz , Piotrowska Ewa

Identyfikatory

DOI

10.17531/ein.2023.1.5

• Języki publikacji: EN

Abstrakty

EN

The aim of the study was to investigate rail vehicle dynamics under primary suspension dampers faults and explore possibility of its detection by means of artificial neural networks. For these purposes two types of analysis were carried out: preliminary analysis of 1 DOF rail vehicle model and a second one - a passenger coach benchmark model was tested in multibody simulation software - MSC.Adams with use of VI-Rail package. Acceleration signals obtained from the latter analysis served as an input data into the artificial neural network (ANN). ANNs of different number of hidden layers were capable of detecting faults for the trained suspension fault cases, however, achieved accuracy was below 63% at the best. These results can be considered satisfactory considering the complexity of dynamic phenomena occurring in the vibration system of a rail vehicle.

Słowa kluczowe

EN

rail vehicle; damper; suspension; fault detection; neural networks

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2023
• Tom: Vol. 25, no. 1
• Strony: art. no. 5
• Opis fizyczny: Bibliogr. 43 poz., rys., tab., wykr.

Twórcy

autor

Melnik Rafał

• Lomza State University of Applied Sciences, Faculty of Computer Science and Technology, Akademicka 1, Lomza, Poland

• https://orcid.org/0000-0003-2900-784X

autor

Koziak Seweryn

• Warsaw University of Technology, Faculty of Transport, Koszykowa 75, Warsaw, Poland

• https://orcid.org/0000-0002-6922-3574

autor

Dižo Ján

• University of Žilina, Faculty of Mechanical Engineering, Univerzitná 8215/1, Žilina, Slovakia

• https://orcid.org/0000-0001-9433-392X

autor

Kuźmierowski Tomasz

• Lomza State University of Applied Sciences, Faculty of Computer Science and Technology, Akademicka 1, Lomza, Poland

• https://orcid.org/0000-0002-6090-8948

autor

Piotrowska Ewa

• Lomza State University of Applied Sciences, Faculty of Computer Science and Technology, Akademicka 1, Lomza, Poland

• https://orcid.org/0000-0003-3163-0753

Bibliografia

• 1. Ankrah A A, Kimotho J K, Muvengei O M. Fusion of Model-Based and Data Driven Based Fault Diagnostic Methods for Railway Vehicle Suspension. Journal of Intelligent Learning Systems and Applications 2020; 12(03): 51–81, https://doi.org/10.4236/jilsa.2020.123004.
• 2. Banerjee K, C. V, Gupta R et al. Exploring Alternatives to Softmax Function: Proceedings of the 2nd International Conference on Deep Learning Theory and Applications, SCITEPRESS - Science and Technology Publications: 2021: 81–86, https://doi.org/10.5220/0010502000810086.
• 3. Dai L, Chi M, Guo Z et al. A physical model-neural network coupled modelling methodology of the hydraulic damper for railway vehicles. Vehicle System Dynamics 2022: 1–22, https://doi.org/10.1080/00423114.2022.2053171.
• 4. Dumitriu M. Condition Monitoring of the Dampers in the Railway Vehicle Suspension Based on the Vibrations Response Analysis of the Bogie. Sensors 2022; 22(9): 3290, https://doi.org/10.3390/s22093290.
• 5. Dumitriu M. Fault detection of damper in railway vehicle suspension based on the cross-correlation analysis of bogie accelerations. Mechanics & Industry 2019; 20(1): 102, https://doi.org/10.1051/meca/2018051.
• 6. EN 14363, Railway applications - Testing for the acceptance of running characteristics of railway vehicles - Testing of running behaviour and stationary tests, European Committee for Standardization, 2016.
• 7. ERRI B176 RP1, Preliminary studies and specifications – specification for a bogie with improved curving characteristics, Utrecht, Netherlands, 1989
• 8. Fjellström C, Nyström K. Deep learning, stochastic gradient descent and diffusion maps. Journal of Computational Mathematics and Data Science 2022; 4: 100054, https://doi.org/10.1016/j.jcmds.2022.100054.
• 9. Hayashi Y, Tsunashima H, Marumo Y. Fault Detection of Railway Vehicle Suspension Systems Using Multiple-Model Approach. Journal of Mechanical Systems for Transportation and Logistics 2008; 1(1): 88–99, https://doi.org/10.1299/jmtl.1.88.
• 10. http://www.ikolej.pl/zaklady-laboratoria-i-osrodki/osrodek-eksploatacji-toru-doswiadczalnego/
• 11. https://keras.io/api/losses/
• 12. Hu H, Tang B, Gong X et al. Intelligent Fault Diagnosis of the High-Speed Train With Big Data Based on Deep Neural Networks. IEEE Transactions on Industrial Informatics 2017; 13(4): 2106–2116, https://doi.org/10.1109/TII.2017.2683528.
• 13. Iwnicki S. Manchester Benchmarks for Rail Vehicle Simulation. Vehicle System Dynamics 1998; 30(3–4): 295–313, https://doi.org/10.1080/00423119808969454.
• 14. Kalker J J. A Fast Algorithm for the Simplified Theory of Rolling Contact. Vehicle System Dynamics 1982; 11(1): 1–13, https://doi.org/10.1080/00423118208968684.
• 15. Karlsson H, Qazizadeh A, Stichel S, Berg M. Condition Monitoring of Rail Vehicle Suspension Elements: A Machine Learning Approach. In Klomp M, Bruzelius F, Nielsen J, Hillemyr A (eds): Advances in Dynamics of Vehicles on Roads and Tracks, Cham, Springer International Publishing: 2020: 119–127, https://doi.org/10.1007/978-3-030-38077-9_14.
• 16. Konowrocki R, Chojnacki A. Analysis of rail vehicles’ operational reliability in the aspect of safety against derailment based on various methods of determining the assessment criterion. Eksploatacja i Niezawodnosc - Maintenance and Reliability 2019; 22(1): 73–85, https://doi.org/10.17531/ein.2020.1.9.
• 17. Konowrocki R, Kalinowski D, Szolc T, Marczewski A. Identification of safety hazards and operating conditions of the low-floor tram with independently rotating wheels with various drive control algorithms. Eksploatacja i Niezawodnosc - Maintenance and Reliability 2021; 23(1): 21–33, https://doi.org/10.17531/ein.2021.1.3.
• 18. Kouretas I, Paliouras V. Simplified Hardware Implementation of the Softmax Activation Function. 2019 8th International Conference on Modern Circuits and Systems Technologies (MOCAST), Thessaloniki, Greece, IEEE: 2019: 1–4, https://doi.org/10.1109/MOCAST.2019.8741677.
• 19. Kraemer P, Friedmann H, Richter M. Vibration-based damage identification on the suspension of a railway waggon – Findings from snap-back experiments with transient excitation. International Journal of Rail Transportation 2020; 8(4): 387–400, https://doi.org/10.1080/23248378.2019.1675190.
• 20. Li P, Goodall R, Weston P et al. Estimation of railway vehicle suspension parameters for condition monitoring. Control Engineering Practice 2007; 15(1): 43–55, https://doi.org/10.1016/j.conengprac.2006.02.021.
• 21. Li P, Goodall R. Model based condition monitoring for railway vehicle systems. Control 2004, University of Bath, 2004, ID-508.
• 22. Liu X Y, Alfi S, Bruni S. An efficient recursive least square-based condition monitoring approach for a rail vehicle suspension system. Vehicle System Dynamics 2016; 54(6): 814–830, https://doi.org/10.1080/00423114.2016.1164869.
• 23. McConville J B, McGrath J F. Introduction to ADAMS theory. Ann Arbor, Michigan, USA, Mechanical Dynamics, Inc.: 1998.
• 24. Mei T X, Ding X J. Condition monitoring of rail vehicle suspensions based on changes in system dynamic interactions. Vehicle System Dynamics 2009; 47(9): 1167–1181, https://doi.org/10.1080/00423110802553087.
• 25. Melnik R, Kostrzewski M. Rail Vehicle’s Suspension Monitoring System - Analysis of Results Obtained in Tests of the Prototype. Key Engineering Materials 2012; 518: 281–288, https://doi.org/10.4028/www.scientific.net/KEM.518.281.
• 26. Melnik R, Koziak S. Rail vehicle suspension condition monitoring – approach and implementation. Journal of Vibroengineering 2017; 19(1): 487–501, https://doi.org/10.21595/jve.2016.17072.
• 27. Mitschke M. Dynamik der Kraftfahrzeuge. B: Schwingungen. 2., völlig neubearb. Aufl. Berlin Heidelberg, Springer: 1984.
• 28. Petrović D, Atmadzhova D, Bižić M. Advantages of installation of rubber-metal elements in suspension of railway vehicles. Split, Croatia, University of Zagreb: 2014; Road and Rail Infrastructure III: 491–497.
• 29. Ren J, Jin W, Li L et al. Performance Degradation Estimation of High-Speed Train Bogie Based on 1D-ConvLSTM Time-Distributed Convolutional Neural Network. Computational Intelligence and Neuroscience 2022; 2022: 1–16, https://doi.org/10.1155/2022/5030175.
• 30. Sakellariou J S, Petsounis K A, Fassois S D. Vibration based fault diagnosis for railway vehicle suspensions via a functional model based method: A feasibility study. Journal of Mechanical Science and Technology 2015; 29(2): 471–484, https://doi.org/10.1007/s12206-015-0107-0.
• 31. Same M H, Gandubert G, Gleeton G et al. Simplified Welch Algorithm for Spectrum Monitoring. Applied Sciences 2020; 11(1): 86, https://doi.org/10.3390/app11010086.
• 32. Sorribes-Palmer, Felix, Luber, Bernd, Fuchs, Josef et al. Data-driven fault diagnosis of bogie suspension components with on-board acoustic sensors. 2020; 5(1): 13.
• 33. UIC 518, Testing and approval of railway vehicles from the point of view of their dynamic behaviour – Safety – Track fatigue – Ride quality. International Union of Railways (UIC) Leaflet, 2009.
• 34. Wang W L, Zhou Z R, Yu D S et al. Rail vehicle dynamic response to a nonlinear physical ‘in-service’ model of its secondary suspension hydraulic dampers. Mechanical Systems and Signal Processing 2017; 95: 138–157, https://doi.org/10.1016/j.ymssp.2017.03.031.
• 35. Wei X, Guo K, Jia L et al. Fault Isolation of Light Rail Vehicle Suspension System Based on D-S Evidence Theory and Improvement Application Case. Journal of Intelligent Learning Systems and Applications 2013; 05(04): 245–253, https://doi.org/10.4236/jilsa.2013.54029.
• 36. Wei X, Jia L, Liu H. Data-driven fault detection of vertical rail vehicle suspension systems. Proceedings of 2012 UKACC International Conference on Control, Cardiff, United Kingdom, IEEE: 2012: 589–594, https://doi.org/10.1109/CONTROL.2012.6334696.
• 37. Welch P. The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms. IEEE Transactions on Audio and Electroacoustics 1967; 15(2): 70–73, https://doi.org/10.1109/TAU.1967.1161901.
• 38. Wu Y, Jin W, Ren J, Sun Z. Fault Diagnosis of High-Speed Train Bogie Based on Synchrony Group Convolutions. Shock and Vibration 2019; 2019: 1–13, https://doi.org/10.1155/2019/7230194.
• 39. Ye Y, Huang P, Zhang Y. Deep learning-based fault diagnostic network of high-speed train secondary suspension systems for immunity to track irregularities and wheel wear. Railway Engineering Science 2022; 30(1): 96–116, https://doi.org/10.1007/s40534-021-00252-z.
• 40. Zboinski K, Golofit-Stawinska M. Investigation into nonlinear phenomena for various railway vehicles in transition curves at velocities close to critical one. Nonlinear Dynamics 2019; 98(3): 1555–1601, https://doi.org/10.1007/s11071-019-05041-2.
• 41. Zeng Y C, Song D L, Zhang W H et al. Stochastic failure process of railway vehicle dampers and the effects on suspension and vehicle dynamics. Vehicle System Dynamics 2021; 59(5): 703–718, https://doi.org/10.1080/00423114.2019.1711136.
• 42. Zhou B, Han C, Guo T. Convergence of Stochastic Gradient Descent in Deep Neural Network. Acta Mathematicae Applicatae Sinica, English Series 2021; 37(1): 126–136, https://doi.org/10.1007/s10255-021-0991-2.
• 43. Zoljic-Beglerovic S, Stettinger G, Luber B, Horn M. Railway Suspension System Fault Diagnosis using Cubature Kalman Filter Techniques. IFAC-PapersOnLine 2018; 51(24): 1330–1335, https://doi.org/10.1016/j.ifacol.2018.09.562

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).