Freight transportation using railways offers an efficient solution for moving large volumes of goods over a diverse range of distances, while reducing road congestion and environmental impact. The maintenance of the wheelsets from freight vehicles is vital to make this process safe and cost-effective. However, not enough efforts have been made to improve the maintenance of freight wagons. Consequently, this paper addresses a critical gap in identifying the most appropriate lifetime variable for wheelsets from freight wagons, by comparing time, mileage and gross ton mileage since maintenance. The methods used in this comparative study are regression analysis to model wear trajectories, survival analysis to model damage trajectories and reinforcement learning to model decision policies. The findings demonstrate that gross ton mileage is the most reliable variable for the maintenance of wheelsets from freight wagons. This paper underscores the critical role of gross ton mileage in predictive maintenance, offering actionable insights to enhance decision making and reduce costs, while improving reliability and safety of degrading assets.
NoldMCormanF. Increasing realism in modelling energy losses in railway vehicles and their impact to energy-efficient train control. Railw Eng Sci2024; 32: 257–285.
2.
MaramizonouzSNadimiSSkipperW, et al.CFD–DEM modelling of particle entrainment in wheel–rail interface: a parametric study on particle characteristics. Railw Eng Sci2025; 33: 259–270.
3.
AfonsoJLTantaMPintoJGO, et al.A review on power electronics technologies for power quality improvement. Energies; 14: 8585.
4.
StenströmCNorrbinPParidaA, et al.Preventive and corrective maintenance – cost comparison and cost–benefit analysis. Structure and Infrastructure Engineering2016; 12: 603–617.
5.
BragaJAPAntradeAR. Data-driven decision support system for degrading assets and its application under the perspective of a railway component. Transportation Engineering; 12: 100180.
6.
SunHHeDZhongJ, et al.Preventive maintenance optimization for key components of subway train bogie with consideration of failure risk. Eng Fail Anal2023; 154: 107634.
7.
WangNYangXChenJ, et al.Hazards correlation analysis of railway accidents: a real-world case study based on the decade-long UK railway accident data. Saf Sci2023; 166: 106238.
8.
DikmenFBayraktarMGucluR. Railway axle analyses: fatigue damage and life analysis of rail vehicle axle. Strojniski Vestnik/Journal of Mechanical Engineering2012; 58: 545–552.
9.
YinMXZhuTXuJT, et al.Service reliability of a heavy-haul wagon coupler body based on the SMOTE-Bootstrap-Bayes method. Eng Fail Anal2020; 118: 104836.
10.
TrueHChristiansenLEPlesnerAL, et al.On the problem of the dynamical reactions of a rolling wheelset to real track irregularities. Railw Eng Sci2023; 31: 1–19.
11.
De ArizonJVerlindenODehombreuxP. Prediction of wheel wear in urban railway transport: comparison of existing models. Veh Syst Dyn2007; 45: 849–866.
12.
PradhanSSamantarayAKBhattacharyyaR. Prediction of railway wheel wear and its influence on the vehicle dynamics in a specific operating sector of Indian railways network. Wear2018; 406–407: 92–104.
13.
IslamDMZLaparidouKBurgessA. Cost effective future derailment mitigation techniques for rail freight traffic management in Europe. Transport Res C Emerg Technol2016; 70: 185–196.
14.
LeiteMCostaMAAlvesT, et al.Reliability and availability assessment of railway locomotive bogies under correlated failures. Eng Fail Anal; 135: 106104.
15.
BevanAMolyneux-BerryPEickhoffB, et al.Development and validation of a wheel wear and rolling contact fatigue damage model. Wear2013; 307: 100–111.
16.
AndradeARStowJ. Statistical modelling of wear and damage trajectories of railway wheelsets. Qual Reliab Eng Int2016; 32: 2909–2923.
17.
LiQZhouJJiangZ, et al.Train wheel degradation modeling and remaining useful life prediction based on mixed effect model considering dependent measurement errors. IEEE Access2019; 7: 159058–159068.
18.
FreitasMADe ToledoMLGColosimoEA, et al.Using degradation data to assess reliability: a case study on train wheel degradation. Qual Reliab Eng Int2009; 25: 607–629.
19.
FerreiraJCFreitasMAColosimoEA. Degradation data analysis for samples under unequal operating conditions: a case study on train wheels. J Appl Stat2012; 39: 2721–2739.
20.
OliveiraRPBLoschiRHFreitasMA. Skew-Heavy-Tailed degradation models: an application to train wheel degradation. IEEE Trans Reliab2018; 67: 129–141.
21.
LinJAsplundMParidaA. Reliability analysis for degradation of locomotive wheels using parametric Bayesian approach. Qual Reliab Eng Int2014; 30: 657–667.
22.
AsplundMLinJ. Evaluating the measurement capability of a wheel profile measurement system by using GR&R. Measurement: Journal of the International Measurement Confederation2016; 92: 19–27.
23.
DengYLiuLLiM, et al.A data-driven wheel wear prediction model for rail train based on LM-OMP-NARXNN. J Comput Inf Sci Eng2023; 23: 021012.
24.
CaldeiraGACBragaJAPAndradeAR. Assessing wear evolutions in railway wheelsets using a survival modeling approach. ASCE-ASME J Risk Uncertain Eng Syst Part B Mech Eng2021; 7: 041001.
25.
DaiXQuSSuiH, et al.Reliability modelling of wheel wear deterioration using conditional bivariate gamma processes and Bayesian hierarchical models. Reliab Eng Syst Saf; 226: 108710.
26.
GrzywnaMSzkodaM. Examination of selected geometrical parameters of wheelsets of electric multiple unit. Transport Problems2022; 17: 161–174.
27.
YeYHuangCZengJ, et al.Predicting railway wheel wear by calibrating existing wear models: principle and application. Reliab Eng Syst Saf2023; 238: 109462.
28.
ZengYSongDZhangW, et al.A new physics-based data-driven guideline for wear modelling and prediction of train wheels. Wear2020; 456–457: 203355.
29.
ChiZChenRHuangS, et al.Multi-state system modeling and reliability assessment for groups of high-speed train wheels. Reliab Eng Syst Saf2020; 202: 107026.
30.
ChiZLinJChenR, et al.Data-driven approach to study the polygonization of high-speed railway train wheel-sets using field data of China’s HSR train. Measurement2020; 149: 107022.
31.
ChiCFSigmundDAstardiMO. Classification scheme for root cause and failure modes and effects analysis (FMEA) of passenger vehicle recalls. Reliab Eng Syst Saf; 200. DOI: 10.1016/j.ress.2020.106929, Epub ahead of print 2020.
32.
ZengYCSongDLZhangWH, et al.Stochastic failure process of railway vehicle dampers and the effects on suspension and vehicle dynamics. Veh Syst Dyn2021; 59: 703–718.
33.
ZhaoXWenZLiuD, et al.Observations and monitoring of the rolling contact fatigue of Chinese high speed wheels. In: Proceedings of 2016 IEEE International Wheelset Congress, IWC 2016, 2017, IEEE. pp. 55–59.
34.
ZengYSongDZhangW, et al.Physics-based data-driven interpretation and prediction of rolling contact fatigue damage on high-speed train wheels. Wear2021; 484–485: 203993.
LinJPulidoJAsplundM. Reliability analysis for preventive maintenance based on classical and Bayesian semi-parametric degradation approaches using locomotive wheel-sets as a case study. Reliab Eng Syst Saf2015; 134: 143–156.
37.
WangLXuHYuanH, et al.Optimizing the re-profiling strategy of metro wheels based on a data-driven wear model. Eur J Oper Res2015; 242: 975–986.
38.
JiangZBanjevicDMingchengEM, et al.Optimizing the re-profiling policy regarding metropolitan train wheels based on a semi-Markov decision process. Proc Inst Mech Eng O J Risk Reliab2017; 231: 495–507.
39.
MingchengELiBJiangZ, et al.An optimal reprofiling policy for high-speed train wheels subject to wear and external shocks using a semi-Markov decision process. IEEE Trans Reliab2018; 67: 1468–1481.
40.
AndradeARStowJ. Assessing the efficiency of maintenance operators: a case study of turning railway wheelsets on an under-floor wheel lathe. Proc Inst Mech Eng O J Risk Reliab2017; 231: 155–163.
41.
BragaJAPAndradeAR. Optimizing maintenance decisions in railway wheelsets: a Markov decision process approach. Proc Inst Mech Eng O J Risk Reliab2019; 233: 285–300.
42.
CostaAPBJPRamosAA. A data-driven maintenance policy for railway wheelset based on survival analysis and Markov decision process. Qual Reliab Eng Int2020; 37: 176–198.
43.
ZengYSongDZhangW, et al.An optimal life cycle reprofiling strategy of train wheels based on Markov decision process of wheel degradation. IEEE trans Intell Transp Syst2022; 23: 10354–10364.
44.
ZhangSFengYGaoX, et al.Modeling of fatigue failure for SiC/SiC ceramic matrix composites at elevated temperatures and multi-scale experimental validation. J Eur Ceram Soc2022; 42: 3395–3403.
45.
PagaimoJMagalhãesHCostaJN, et al.Derailment study of railway cargo vehicles using a response surface methodology. Veh Syst Dyn2022; 60: 309–334.
46.
MaglioMVernerssonTNielsenJCO, et al.Influence of railway wheel tread damage on wheel–rail impact loads and the durability of wheelsets. Railw Eng Sci2024; 32: 20–35.
47.
SpiryaginMWuQPolachO, et al.Problems, assumptions and solutions in locomotive design, traction and operational studies. Railw Eng Sci2022; 30: 265–288.
48.
PachecoPAMagelliMLopesMV, et al.The effectiveness of different wear indicators in quantifying wear on railway wheels of freight wagons. Railway Engineering Science2024; 32: 307–323.
49.
ZhaoXAnBZhaoX, et al.Local rolling contact fatigue and indentations on high-speed railway wheels: observations and numerical simulations. Int J Fatigue2017; 103: 5–16.
50.
ZhangHWeiXGuanQ, et al.Joint maintenance strategy optimization for Railway Bogie wheelset. Appl Sci2022; 12: 6934.
51.
YeDWenJZhengS, et al.Prediction of key parameters of wheelset based on LSTM neural network. Appl Sci2023; 13: 11935.
52.
IwnickiSSpiryaginMColeC, et al.Handbook of railway vehicle dynamics.
53.
BragaJAPCostaJNAmbrósioJ, et al.Robust assessment of railway vehicle safety risks in operation using a proposed data-driven wheel profile generation approach: design of computer experiments and surrogate models. Reliab Eng Syst Saf2024; 249: 110220.
54.
CEN (European Committee for Standardization). Railway Applications—in-service wheelset operation Requirements—in-service and off-vehicle wheelset maintenance.
55.
BragaJAPAndradeAR. Multivariate statistical aggregation and dimensionality reduction techniques to improve monitoring and maintenance in railways: the wheelset component. Reliab Eng Syst Saf216: 107932.
56.
ChenYLiYNiuG, et al.Offline and online measurement of the geometries of train wheelsets: a review. IEEE Trans Instrum Meas2022; 71: 1–15.
57.
AlemiACormanFLodewijksG. Condition monitoring approaches for the detection of railway wheel defects. Proc Inst Mech Eng F J Rail Rapid Transit2017; 231: 961–981.
58.
de Almeida CostaMPedro de Azevedo Peixoto BragaJRamos AndradeA. Assessing the performance of different devices in railway wheelset inspection. Measurement2020; 165: 108145.
59.
ShiHWangJWuP, et al.Field measurements of the evolution of wheel wear and vehicle dynamics for high-speed trains. Veh Syst Dyn2018; 56: 1187–1206.
MyersRHMontgomeryDCAnderson-CookCM. Response surface methodology: process and product optimization using designed experiments. John Wiley & Sons, 2016.
62.
BurnhamKPAndersonDR. Multimodel inference: understanding AIC and BIC in model selection. Sociol Methods Res2004; 33: 261–304.
63.
HastieT. All. Springer series in statistics the elements of statistical learning. Math Intel2009; 27: 83–85.
64.
KleinbaumDGKleinM. Survival analysis: A self-learning text.
65.
Almeida CostaMde Azevedo Peixoto BragaJPRamosAA. A data-driven maintenance policy for railway wheelset based on survival analysis and Markov decision process. Qual Reliab Eng Int2021; 37: 176–198.
66.
LongJS. Regression models for categorical and limited dependent variables. Advanced quantitative techniques in the social sciences, vol 7, p. 219. Sage.
67.
AlabdallahAOhlssonMPashamiS, et al.The concordance index decomposition: a measure for a deeper understanding of survival prediction models. Artif Intell Med2024; 148: 102781.
ChadèsIChapronGCrosMJ, et al.MDPtoolbox: a multi-platform toolbox to solve stochastic dynamic programming problems. Ecography2014; 37: 916–920.
70.
SanchoLCBBragaJAPAndradeAR. Optimizing maintenance decision in rails: a markov decision process approach. ASCE ASME J Risk Uncertain Eng Syst A Civ Eng2021; 7: 04020051.
71.
AndradeARStowJ. Assessing the potential cost savings of introducing the maintenance option of ‘Economic Tyre Turning’ in Great Britain railway wheelsets. Reliab Eng Syst Saf2017; 168: 317–325.
72.
MadanatS. Optimal infrastructure management decisions under uncertainty. Transp Res Part C Emerg Technol1993; 1: 77–88.
73.
AnderssonRAhlströmJKaboE, et al. Numerical investigation of crack initiation in rails and wheels affected by martensite spots. Int J Fatigue2018; 114: 238–251.
74.
MaglioMVernerssonTNielsenJCO, et al.Influence of railway wheel tread damage on wheel–rail impact loads and the durability of wheelsets. Railway Engineering Science. Epub ahead of print 2023. DOI: 10.1007/s40534-023-00316-2.
