Online railway wheel defect detection under varying running-speed conditions by multi-kernel relevance vector machine

다국어 초록 (Multilingual Abstract)

The degradation of wheel tread may result in serious hazards in the railway operation system. Therefore, timely wheel defect diagnosis of in-service trains to avoid tragic events is of particular importance. The focus of this study is to develop a novel wheel defect detection approach based on the relevance vector machine (RVM) which enables online detection of potentially defective wheels with trackside monitoring data acquired under different running-speed conditions. With the dynamic strain responses collected by a trackside monitoring system, the cumulative Fourier amplitudes (CFA) characterizing the effect of individual wheels are extracted to formulate multiple probabilistic regression models (MPRMs) in terms of multi-kernel RVM, which accommodate both variables of vibration frequency and running speed. Compared with the general single-kernel RVM-based model, the proposed multi-kernel MPRM approach bears better local and global representation ability and generalization performance, which are prerequisite for reliable wheel defect detection by means of data acquired under different running-speed conditions. After formulating the MPRMs, we adopt a Bayesian null hypothesis indicator for wheel defect identification and quantification, and the proposed method is demonstrated by utilizing real-world monitoring data acquired by an FBG-based trackside monitoring system deployed on a high-speed trial railway. The results testify the validity of the proposed method for wheel defect detection under different running-speed conditions.

참고문헌 (Reference)

1 Vittorio Belotti, "Wheel-flat diagnostic tool via wavelet transform" Elsevier BV 20 (20): 1953-1966, 2006

2 Xiao-Zhou Li ; Yi-Qing Ni, "Wheel tread defect detection for high-speed trains using FBG-based online monitoring techniques" 국제구조공학회 21 (21): 687-694, 2018

3 Massimo Leonardo Filograno, "Wheel Flat Detection in High-Speed Railway Systems Using Fiber Bragg Gratings" Institute of Electrical and Electronics Engineers (IEEE) 13 (13): 4808-4816, 2013

4 Gabriel Krummenacher, "Wheel Defect Detection With Machine Learning" Institute of Electrical and Electronics Engineers (IEEE) 19 (19): 1176-1187, 2018

5 D. Milković, "Wayside system for wheel–rail contact forces measurements" Elsevier BV 46 (46): 3308-3318, 2013

6 Xiao-Zhou Liu, "Wayside Detection of Wheel Minor Defects in High-Speed Trains by a Bayesian Blind Source Separation Method" MDPI AG 19 (19): 3981-, 2019

7 M Pau, "Ultrasonic waves for effective assessment of wheel-rail contact anomalies" SAGE Publications 219 (219): 79-90, 2005

8 Asa Ben-Hur, "Support Vector Machines and Kernels for Computational Biology" Public Library of Science (PLoS) 4 (4): e1000173-, 2008

9 Xingwen Wu ; Maoru Chi, "Study on stress states of a wheelset axle due to a defective wheel" 대한기계학회 30 (30): 4845-4857, 2016

10 Brant Stratman, "Structural Health Monitoring of Railroad Wheels Using Wheel Impact Load Detectors" Springer Science and Business Media LLC 7 (7): 218-225, 2007

11 Zhang, Q., "Sparse Bayesian learning approach for damage detection in a population of nominally identical structures" The Hong Kong Polytechnic University 2020

12 Tipping, M.E., "Sparse Bayesian learning and the relevance vector machine" Test accounts 1 : 211-244, 2001

13 Y.W. Wang, "Real-time defect detection of high-speed train wheels by using Bayesian forecasting and dynamic model" Elsevier BV 139 : 106654-, 2020

14 Chuliang Wei, "Real-Time Train Wheel Condition Monitoring by Fiber Bragg Grating Sensors" SAGE Publications 8 (8): 409048-, 2011

15 M. L. Filograno, "Real-Time Monitoring of Railway Traffic Using Fiber Bragg Grating Sensors" Institute of Electrical and Electronics Engineers (IEEE) 12 (12): 85-92, 2012

16 G. Kouroussis, "Railway-induced ground vibrations – a review of vehicle effects" Informa UK Limited 2 (2): 69-110, 2014

17 Ali Jamshidi, "Probabilistic Defect-Based Risk Assessment Approach for Rail Failures in Railway Infrastructure" Elsevier BV 49 (49): 73-77, 2016

18 Murray Aitkin, "Posterior Bayes Factors" Wiley 53 (53): 111-128, 1991

19 A Johansson, "Out-of-round railway wheels—wheel-rail contact forces and track response derived from field tests and numerical simulations" SAGE Publications 217 (217): 135-146, 2003

20 Baolei Wei, "Optimal solution for novel grey polynomial prediction model" Elsevier BV 62 : 717-727, 2018

21 Lin-Hao Zhang ; You-Wu Wang ; Yi-Qing Ni ; Siu-Kai Lai, "Online condition assessment of high-speed trains based on Bayesian forecasting approach and time series analysis" 국제구조공학회 21 (21): 705-713, 2018

22 C. J. Willmott, "On the use of dimensioned measures of error to evaluate the performance of spatial interpolators" Informa UK Limited 20 (20): 89-102, 2006

23 M Petersson, "Noise-related roughness of railway wheel treads-full-scale testing of brake blocks" SAGE Publications 214 (214): 63-77, 2000

24 Rainer Pohl, "NDT techniques for railroad wheel and gauge corner inspection" Elsevier BV 37 (37): 89-94, 2004

25 Yi-Qing Ni ; Su-Mei Wang ; Gao-Feng Jiang ; Yang Lu ; Guobin Lin ; Hong-Liang Pan ; Junqi Xu ; Shuo Hao, "Multiple damage detection of maglev rail joints using time-frequency spectrogram and convolutional neural network" 국제구조공학회 29 (29): 625-640, 2022

26 Rao V Dukkipati, "Impact Loads due to Wheel Flats and Shells" Informa UK Limited 31 (31): 1-22, 1999

27 Yue Wu, "Experimental analysis of the mechanism of high-order polygonal wear of wheels of a high-speed train" Zhejiang University Press 18 (18): 579-592, 2017

28 Natasha Flyer, "Enhancing finite differences with radial basis functions: Experiments on the Navier–Stokes equations" Elsevier BV 316 : 39-62, 2016

29 B. MORYS, "ENLARGEMENT OF OUT-OF-ROUND WHEEL PROFILES ON HIGH SPEED TRAINS" Elsevier BV 227 (227): 965-978, 1999

30 Rajib Ul Alam Uzzal, "Dynamic analysis of railway vehicle-track interactions due to wheel flat with a pitch-plane vehicle model" Bangladesh Journals Online (JOL) 39 (39): 86-94, 1970

31 Liu, X. Z., "Condition-based maintenance of high-speed railway vehicle wheels through trackside monitoring" 2018

32 Matthias Asplund, "Condition monitoring and e-maintenance solution of railway wheels" Emerald 20 (20): 216-232, 2014

33 Robert Gilmore Pontius, "Components of information for multiple resolution comparison between maps that share a real variable" Springer Science and Business Media LLC 15 (15): 111-142, 2007

34 S.M. Wong, "Compactly supported radial basis functions for shallow water equations" Elsevier BV 127 (127): 79-101, 2002

35 Marin, J. M., "Bayesian Core: A Practical Approach to Computational Bayesian Statistics" Springer 2007

36 Kass, R. E., "Bayes factors" 90 (90): 773-795, 1995

37 Holger Lipowsky, "Application of Bayesian Forecasting to Change Detection and Prognosis of Gas Turbine Performance" ASME International 132 (132): 2009

38 Rob J. Hyndman, "Another look at measures of forecast accuracy" Elsevier BV 22 (22): 679-688, 2006

39 Xuesong Jin, "An investigation into the mechanism of the polygonal wear of metro train wheels and its effect on the dynamic behaviour of a wheel/rail system" Informa UK Limited 50 (50): 1817-1834, 2012

40 K. Bollas, "Acoustic emission monitoring of wheel sets on moving trains" Elsevier BV 48 : 1266-1272, 2013

41 Flyer, N., "A radial basis function method for the shallow water equations on a sphere" 465 (465): 1949-1976, 2009

42 D W Barke, "A Review of the Effects of Out-Of-Round Wheels on Track and Vehicle Components" SAGE Publications 219 (219): 151-175, 2005

43 T.X WU, "A HYBRID MODEL FOR THE NOISE GENERATION DUE TO RAILWAY WHEEL FLATS" Elsevier BV 251 (251): 115-139, 2002

44 Yi-Qing Ni, "A Bayesian machine learning approach for online detection of railway wheel defects using track-side monitoring" SAGE Publications 20 (20): 1536-1550, 2020