Transmittance function-based robust detection, isolation and precise estimation of degradation in railway vehicle suspension components under varying travelling conditions

Abstract

A transmittance function-based diagnosis methodology for robust detection, isolation, and precise estimation of railway vehicle suspension components degradation under varying travelling conditions is presented. The methodology is based on transmittance function data-driven stochastic functionally pooled models, which are capable of representing the vehicle dynamics under varying operating conditions. This characteristic ensures robustness in fault/degradation diagnosis as the effects of varying travelling conditions on vehicle dynamics may fully or partly obscure the degradation effects. Degradation detection is accomplished in an unsupervised manner, while isolation and estimation are supervised. The travelling conditions are considered non-measurable in the inspection phase, where the methodology is assessed via different scenarios and the transmittance function is employed for the regularization of track excitation uncertainty. The methodology is validated through thousands of Monte Carlo simulations with a Simpack-based 54-degree-of-freedom vehicle model of the Attiko Metro company using acceleration signals from two points on the vehicle. A wide range of travelling speeds, passenger payloads, and different levels of degradation (through stiffness reduction) of the primary suspension conical rubber spring and the air spring of the secondary suspension are considered, combined with different realizations of track irregularities following the ERRI B176 standard. The results indicate excellent detection performance for even early stage degradation levels, while correct isolation is achieved for approximately 94% and 99% of the test cases considered in the vehicle’s primary and secondary suspension components, respectively. The corresponding degradation level estimation accuracy for these components is demonstrated via the mean absolute error, which is 2.45% ± 2.92% and 4.05% ± 3.66%. The methodology’s performance is additionally compared with that of a state-of-the-art data-driven method, showing an overall superior performance.

Keywords

Railway vehicle suspension / Fault detection and isolation / Degradation diagnosis / On-board vibration signals / Data-driven method / Functional models / Varying operating conditions

References

[1] Brant J, Liang B. Ball A, Gelman L, Rao B. Condition monitoring systems in the railway industry. Advances in asset management and condition monitoring, 2020, Cham, Springer International Publishing671683

[2] Bruni S, Goodall R, Mei TXet al.. Control and monitoring for railway vehicle dynamics. Veh Syst Dyn, 2007, 45(7–8): 743-779

[3] Tsunashima H (2017) Railway condition monitoring, present and future. In: The proceedings of the transportation and logistics conference 2017.26:CL. The Japan Society of Mechanical Engineers, Sakai

[4] Fassois SD, Sakellariou JS. Time-series methods for fault detection and identification in vibrating structures. Phil Trans R Soc A, 2006, 365(1851): 411-448

[5] Aravanis TCI, Sakellariou JS, Fassois SD. A stochastic functional model based method for random vibration based robust fault detection under variable non-measurable operating conditions with application to railway vehicle suspensions. J Sound Vib, 2020, 466: 115006

[6] Vlachospyros G, Fassois SD, Sakellariou JS. On-board vibration-based robust and unsupervised degradation detection in railway suspensions under various travelling speeds via a Multiple Model framework. Veh Syst Dyn, 2023, 62(6): 1446-1470

[7] Si XS, Zhang ZX, Hu CH. Data-driven remaining useful life prognosis techniques, 2017, Berlin, Springer

[8] Iliopoulos IA, Sakellariou JS. Remaining useful life estimation of hollow worn railway vehicle wheels via on-board random vibration-based wheel tread depth estimation. Sensors, 2024, 24(2): 375

[9] Bernal E, Spiryagin M, Cole C. Onboard condition monitoring sensors, systems and techniques for freight railway vehicles: a review. IEEE Sens J, 2019, 1914-24

[10] Strano S, Terzo M. Review on model-based methods for on-board condition monitoring in railway vehicle dynamics. Adv Mech Eng, 2019, 11(2): 1687814019826795

[11] Jesussek M, Ellermann K. Fault detection and isolation for a nonlinear railway vehicle suspension with a hybrid extended Kalman filter. Veh Syst Dyn, 2013, 51101489-1501

[12] Jesussek M, Ellermann K. Fault detection and isolation for a full-scale railway vehicle suspension with multiple Kalman filters. Veh Syst Dyn, 2014, 52(12): 1695-1715

[13] Jesussek M, Ellermann K. Fault detection and isolation for a railway vehicle by evaluating estimation residuals. Proced IUTAM, 2015, 13: 14-23

[14] Li P, Goodall R, Weston Pet al.. Estimation of railway vehicle suspension parameters for condition monitoring. Control Eng Pract, 2007, 15(1): 43-55

[15] Mori H, Tsunashima H. Condition monitoring of railway vehicle suspension using multiple model approach. J Mech Syst Transp Logist, 2010, 3(1): 243-258

[16] Liu XY, Alfi S, Bruni S. An efficient recursive least square-based condition monitoring approach for a rail vehicle suspension system. Veh Syst Dyn, 2016, 54(6): 814-830

[17] Lebel D, Soize C, Fünfschilling Cet al.. High-speed train suspension health monitoring using computational dynamics and acceleration measurements. Veh Syst Dyn, 2020, 58(6): 911-932

[18] Mei TX, Ding XJ. A model-less technique for the fault detection of rail vehicle suspensions. Veh Syst Dyn, 2008, 46(sup1): 277-287

[19] Li C, Luo S, Cole Cet al.. Bolster spring fault detection strategy for heavy haul wagons. Veh Syst Dyn, 2018, 56(10): 1604-1621

[20] Dumitriu M. Fault detection of damper in railway vehicle suspension based on the cross-correlation analysis of bogie accelerations. Mech Ind, 2019, 20(1): 102

[21] Dumitriu M. Condition monitoring of the dampers in the railway vehicle suspension based on the vibrations response analysis of the bogie. Sensors, 2022, 2293290

[22] Melnik R, Koziak S. Rail vehicle suspension condition monitoring - approach and implementation. J Vibroeng, 2017, 191487-501

[23] Vlachospyros G, Kaliorakis N, Iliopoulos IA et al (2020) On the problem of on-board vibration-based fault detection in railway suspensions under varying operating conditions: a feasibility study. In: Proceedings of XI international conference on structural dynamics (EURODYN 2020), Athens, pp 960–971

[24] Vlachospyros G, Fassois SD, Sakellariou JS (2022) Miso transmittance based robust and unsupervised fault detection in railway suspensions under payload and track uncertainty. In: Proceedings of the international conference on noise and vibration engineering (ISMA2022), Leuven, pp. 3277–3291

[25] Qin N, Sun Y, Gu Pet al.. Bogie fault identification based on EEMD information entropy and manifold learning. IFAC-PapersOnLine, 2017, 50(1): 315-318

[26] Wu Y, Jin W, Ren Jet al.. Fault diagnosis of high-speed train bogie based on synchrony group convolutions. Shock Vib, 2019, 2019: 7230194

[27] Zhang Y, Qin N, Huang Det al.. Fault diagnosis of high-speed train bogie based on deep neural network. IFAC-PapersOnLine, 2019, 52(24): 135-139

[28] Wu Y, Jin W, Li Yet al.. Detecting unexpected faults of high-speed train bogie based on Bayesian deep learning. IEEE Trans Veh Technol, 2021, 70(1): 158-172

[29] Su L, Ma L, Qin Net al.. Fault diagnosis of high-speed train bogie by residual-squeeze net. IEEE Trans Ind Inf, 2019, 15(7): 3856-3863

[30] Wu Y, Jin W, Ren Jet al.. A multi-perspective architecture for high-speed train fault diagnosis based on variational mode decomposition and enhanced multi-scale structure. Appl Intell, 2019, 49(11): 3923-3937

[31] Wei X, Jia L, Guo Ket al.. On fault isolation for rail vehicle suspension systems. Veh Syst Dyn, 2014, 52(6): 847-873

[32] Ye Y, Zhang Y, Wang Qet al.. Fault diagnosis of high-speed train suspension systems using multiscale permutation entropy and linear local tangent space alignment. Mech Syst Signal Process, 2020, 138: 106565

[33] 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. Railw Eng Sci, 2022, 30(1): 96-116

[34] Qin N, Wu B, Huang Det al.. Stepwise adaptive convolutional network for fault diagnosis of high-speed train bogie under variant running speeds. IEEE Trans Ind Inf, 2022, 18(12): 8389-8398

[35] Karlsson H, Qazizadeh A, Stichel Set al.et al.. Klomp M, Bruzelius F, Nielsen Jet al.et al.. Condition monitoring of rail vehicle suspension elements: a machine learning approach. Lecture notes in mechanical engineering. Advances in dynamics of vehicles on roads and tracks, 2020, Cham, Springer International Publishing119-127

[36] Vlachospyros G, Fassois SD, Sakellariou JS. Vibration-based railway suspension monitoring under varying operating conditions via robust statistical time series type methods. e-J Nondestruct Test, 2024, 29(7): 1-9

[37] Sakellariou JS, Petsounis KA, Fassois SD. Vibration based fault diagnosis for railway vehicle suspensions via a functional model based method: a feasibility study. J Mech Sci Technol, 2015, 29(2): 471-484

[38] Ren J, Jin W, Wu Y. A CNN-based structure for performance degradation estimation of high-speed train lateral damper. IEEE Access, 2020, 8: 198139-198151

[39] Ren J, Jin W, Li Let al.. Performance degradation estimation of high-speed train bogie based on 1D-ConvLSTM time-distributed convolutional neural network. Comput Intell Neurosci, 2022, 2022: e5030175

[40] Ren J, Jin W, Wu Yet al.. A grouping-attention convolutional neural network for performance degradation estimation of high-speed train lateral damper. Appl Intell, 2023, 53(1): 658-682

[41] Ren J, Jin W, Wu Yet al.. Research on performance degradation estimation of key components of high-speed train bogie based on multi-task learning. Entropy, 2023, 25(4): 696

[42] Fawcett T. An introduction to roc analysis. Pattern Recognit Lett, 2006, 278861-874

[43] McGill R, Tukey JW, Larsen WA. Variations of box plots. Am Stat, 1978, 32(1): 12-16

[44] Dassault Systèmes (2019) Simpack documentation. https://www.3ds.com/products/simulia/simpack, Accessed 14 Jan 2020

[45] Bruni S, Vinolas J, Berg Met al.. Modelling of suspension components in a rail vehicle dynamics context. Veh Syst Dyn, 2011, 49(7): 1021-1072

[46] Kalker JJ. A fast algorithm for the simplified theory of rolling contact. Veh Syst Dyn, 1982, 11(1): 1-13

[47] European Rail Research Institute (1989) Specification for a bogie with improved curving characteristics for body tilt. Report No. B176/RP1, Utrecht

[48] Bruni S, Meijaard JP, Rill Get al.. State-of-the-art and challenges of railway and road vehicle dynamics with multibody dynamics approaches. Multibody Syst Dyn, 2020, 49(1): 1-32

[49] Ljung L. System identification: theory for the user, 19982Upper Saddle River, Pearson186-187

[50] Sakellariou JS, Fassois SD. Functionally pooled models for the global identification of stochastic systems under different pseudo-static operating conditions. Mech Syst Signal Process, 2016, 72–73: 785-807

[51] Kopsaftopoulos FP, Fassois SD. Vector-dependent functionally pooled ARX models for the identification of systems under multiple operating conditions. IFAC Proc, 2012, 45(16): 310-315

[52] Sakaris CS, Sakellariou JS, Fassois SD. Random-vibration-based damage detection and precise localization on a lab-scale aircraft stabilizer structure via the generalized functional model based method. Struct Health Monit, 2017, 16(5): 594-610

[53] Kopsaftopoulos F, Fassois S. A functional model based statistical time series method for vibration based damage detection, localization, and magnitude estimation. Mech Syst Signal Process, 2013, 39(1): 143-161

[54] Nocedal J, Wright SJ. Numerical optimization, 1999, New York, Springer

[55] Fassois SD, Sakellariou JS. Statistical time series methods for SHM, 2009, Chichester, John Wiley & Sons Ltd

[56] Poulimenos AG, Sakellariou JS. A transmittance-based methodology for damage detection under uncertainty: an application to a set of composite beams with manufacturing variability subject to impact damage and varying operating conditions. Struct Health Monit, 2019, 18(1): 318-333

[57] Acxess Spring (2025) Standard spring rate tolerance. https://www.thespringstore.com/standard-spring-rate-tolerance.html, Accessed 14 Jan 2025

[58] Press WH. Numerical recipes: the art of scientific computing, 20073New York, Cambridge University Press

Funding

Hellenic Foundation for Research and Innovation(010819)

RIGHTS & PERMISSIONS

The Author(s)