Machine learning: approaches to predicting reliability and developing maintenance strategies

Subash Singh, B. Vien, D. Welshby, W.K. Chiu

download PDF

Abstract. Current approaches to maintenance of rolling stock bogies are focused on compliance to wear limits as stipulated by OEM specifications. OEM recommendations are critical to providing an industry wide approach to safety and compliance. These are not operation specific and are often not the most cost-effective solutions. A system approach to reliability is an established approach that is applied in less complex systems where the relationships between components are well defined with historical data and predictable conditions. Extending this approach to more complex multi-variate systems where many relationships are not intuitively obvious or mathematically defined presents a challenge. Machine learning techniques have been applied to address such problems with examples in image recognition, tool wear prediction using multiple sensory inputs and estimating railway bogie wear using vibration inputs. [8,9,10] The aim of the study is to extend and adapt machine-learning techniques to the area of developing maintenance strategies for optimal business benefit with a specific focus on railway bogie maintenance. This study aims to present an insight into the variables, which includes bogie tracking condition affecting track side wear rate. A finding is that an in-depth study of each independent variable’s individual impact is a necessary step to efficient modelling. These include track geometry, operating and bogie component wear variables. Track side wear, curve radius, superelevation and track top variance have been found to be significant predictors of track side wear rate. These impact predictions are not consistent between the different rail tracks and are not exhaustive. Specifically, the impact of bogie performance requires inclusion. Combining these variables mathematically using statistical inference and convolutional theory with maximum likelihood estimators would establish a predictor for side wear rate for the specific operation. The paper finally discusses the relationship of area wear rate to side wear rate and the influences of grinding frequency and rail material type.

Track Geometry, Track Quality Index (TQI), Track Condition Monitoring Vehicle (TCMV), Side Wear (SW), Side Wear Rate (SWR), Area Wear (AW), Area Wear Rate (AWR), Rail Operations, Terrain, Tracking Bias, Flange Difference (FD) Measurement Data, Machine Learning, Convolutional Theory, Gross Metric Tonnes (GMT), Head-Hardened Rail (HH), Through-hardened Rail (THH), Absolute (abs), Maximum Likelihood Estimator (MLE), Ordinary Least Squares (OLE), Original Equipment Manufacturer (OEM)

Published online 3/30/2023, 7 pages
Copyright © 2023 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA

Citation: Subash Singh, B. Vien, D. Welshby, W.K. Chiu, Machine learning: approaches to predicting reliability and developing maintenance strategies, Materials Research Proceedings, Vol. 27, pp 308-314, 2023


The article was published as article 40 of the book Structural Health Monitoring

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

[1] K. Doganay and M Bohlin, “Maintenance plan optimisation for a train fleet,” WIT Transactions on The Built Environment, vol 114, 2010 IT Press.
[2] CP Ward, RM Goodall, R Dixon, G Charles, “Condition Monitoring of Rail Vehicle Bogies,” UKACC International Conference on Control, Coventry, UK, pp 1178-1183.
[3] R Santos, PF Teixeira, AP Antunes, “Planning and scheduling efficient heavy rail track maintenance through a Decision Rules Model,” Research in Transportation Economics 54(2015) 20-32, 2015 Elsevier Ltd.
[4] M Gopalakrishnan, A Skoogh, “Machine criticality assessment for productivity improvement, Smart maintenance decision support,” International Journal of Productivity and Performance Management Vol68 No. 5, 2019 pp 858-878, Emerald Publishing Limited.
[6] F Aghazadeh, A Tahan, M Thomas,”Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process”,The International Journal of Advanced Manufacturing Technology (2018) 98:3217-3227.
[7] H Liu, L Li, J Ma, “Rolling Bearing Fault Diagnosis Based on STFT-Deep Learning and Sound Signals,” Hindawi Publishing Corporation, Shock and Vibration, Volume 2016, Article ID 6127479, 12 pages.
[8] Y Wu, W Jin, J Ren, Z Sun, “Fault Diagnosis of High-Speed Train Bogie Based on Synchrony Group Convolutions,” Hindawi, Shock and Vibration, Volume 2019, Article ID 7230194, 13 pages.
[9] C Yang, Y Sun, C Ladubec, Y Liu,”Developing Machine Learning-Based Models for Railway Inspection,” Appl. Sci, 2021,11,13.
[10] A Shebani, S Iwnicki, “Prediction of wheel and rail wear under different contact conditions using artificial neural networks,” Wear 406-407(2018), 173-184, Elsevier Ltd.
[11] A Meyer, “WheelView Freight Measurement Parameters,”Beena Vision Systems Inc.,pp 2,5, 2016,
[12] A. Troiano, “Track Geometry Measuring System, Operating Manuals On Board Monitoring Systems,” Mermec, P118013A11Y VV 501 Rev 1.0 (2015), pp 16-20
[13] A. Troiano,“Rail Profile Measuring System, Operating Manual On Board Monitoring Systems, „Mermec, P118013A11Z VV 501 Annex C Rev 1.0 (2015), pp 16-21
[14] X. Yan, X. Gang Su,“Linear Regression Analysis, Theory and Computing,“World Scientific Publishing Co. Pte. Ltd.(2009).
[15] R. Christensen,“Advanced Linear Modelling“,Springer Science+Business Media, New York, (2001).
[16] C Flatt, RL Jacobs, „Principle Assumptions of Regression Analysis: Testing, Techniques, and Statistical Reporting of Imperfect Data Sets, Advances in Developing Human Resources, Vol 21(4) 2019 pp 484-502, Sage.
[17] D.S. Young,“Handbook of Regression Methods“,CRC Press, New York, (2017).
[18] Kumar, B, Python SciPy Curve Fit – Detailed Guide, Python Guides, Copyright 2022,