Systematic Literature Review on Data-Driven Models for Predictive Maintenance of Railway Track: Implications in Geotechnical Engineering

Conventional planning of maintenance and renewal work for railway track is based on heuristics and simple scheduling. The railway industry is now collecting a large amount of data with the fast-paced development of sensor technologies. These data sets carry information about the conditions of various components in railway track. Since just before the beginning of the 21st century, data-driven models have been used in the predictive maintenance of railway track. This study presents a systematic literature review of data-driven models applied in the predictive maintenance of railway track. A taxonomy to classify the existing literature based on types of models and types of applications is provided. It is found that applying the deep learning methods, unsupervised methods, and ensemble methods are the new trends for predictive maintenance of railway track. Rail geometry irregularity, rail head defect, and missing rail components detection were the top three most commonly considered issues within the application of data-driven models. Prediction of rail breaks has received increasing attention in the last four years. Among these data-driven model applications, the collected data types are the most critical factors which affect selecting suitable models. Finally, this study discusses upcoming challenges in the predictive maintenance of railway track.

[1]  Yi-Qing Ni,et al.  Measurement and Forecasting of High-Speed Rail Track Slab Deformation under Uncertain SHM Data Using Variational Heteroscedastic Gaussian Process , 2019, Sensors.

[2]  Andrés López-Pita,et al.  Maintenance Costs of High-Speed Lines in Europe State of the Art , 2008 .

[3]  Qing He,et al.  Prediction of Railcar Remaining Useful Life by Multiple Data Source Fusion , 2015, IEEE Transactions on Intelligent Transportation Systems.

[4]  Ajay Kapoor,et al.  The current status of theory and practice on rail integrity in Japanese railways—rolling contact fatigue and corrugations , 2003 .

[5]  Aaqib Saeed,et al.  Predictive maintenance using tree-based classification techniques: A case of railway switches , 2019, Transportation Research Part C: Emerging Technologies.

[6]  Faeze Ghofrani,et al.  Exploring the impact of foot-by-foot track geometry on the occurrence of rail defects , 2019, Transportation Research Part C: Emerging Technologies.

[7]  Wenfei Bai,et al.  Improved Railway Track Geometry Degradation Modeling for Tamping Cycle Prediction , 2018 .

[8]  Angela Di Febbraro,et al.  A Rolling-Horizon Approach for Predictive Maintenance Planning to Reduce the Risk of Rail Service Disruptions , 2021, IEEE Transactions on Reliability.

[9]  Rob M.P. Goverde,et al.  Recent applications of big data analytics in railway transportation systems: A survey , 2018 .

[10]  Lior Rokach,et al.  Ensemble-based classifiers , 2010, Artificial Intelligence Review.

[11]  Angela Di Febbraro,et al.  Risk-based optimal scheduling of maintenance activities in a railway network , 2018, EURO J. Transp. Logist..

[12]  Lei Bai,et al.  Track grid health index for grid-based, data-driven railway track health evaluation , 2019, Advances in Mechanical Engineering.

[13]  Jia Chaolong,et al.  Track Irregularity Time Series Analysis and Trend Forecasting , 2012 .

[14]  Narendra Ahuja,et al.  Automated Visual Inspection of Railroad Tracks , 2013, IEEE Transactions on Intelligent Transportation Systems.

[15]  Wing Kong Chiu,et al.  Using Instrumented Revenue Vehicles to Inspect Track Integrity and Rolling Stock Performance in a Passenger Network During Peak Times , 2017 .

[16]  Javad Sadeghi,et al.  Development of improved railway track degradation models , 2010 .

[17]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[18]  Majidreza Nazem,et al.  Rail Degradation Prediction Models for Tram System: Melbourne Case Study , 2018 .

[19]  Eric Berggren.  Efficient Track Maintenance: Methodology for Combined Analysis of Condition Data , 2009 .

[20]  Mehmet Karakose,et al.  An adaptive fault diagnosis approach using pipeline implementation for railway inspection , 2018, Turkish J. Electr. Eng. Comput. Sci..

[21]  Tao Tang,et al.  A Bayesian network model for prediction of weather-related failures in railway turnout systems , 2017, Expert Syst. Appl..

[22]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[23]  Nan Chen,et al.  Prognostics and Health Management: A Review on Data Driven Approaches , 2015 .

[24]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Yu-Jiang Zhang,et al.  Objective Track Quality Indices , 2004 .

[26]  Christos Boutsidis,et al.  Randomized Dimensionality Reduction for $k$ -Means Clustering , 2011, IEEE Transactions on Information Theory.

[27]  Bart De Schutter,et al.  Probabilistic Defect-Based Risk Assessment Approach for Rail Failures in Railway Infrastructure , 2016, IFAC-PapersOnLine.

[28]  Nii O. Attoh-Okine,et al.  Machine Learning Ensembles and Rail Defects Prediction: Multilayer Stacking Methodology , 2019 .

[29]  Rolf Dollevoet,et al.  Health condition monitoring of insulated joints based on axle box acceleration measurements , 2016 .

[30]  Christophe Letot,et al.  Evaluation of the effect of tamping on the track geometry condition: A case study , 2018 .

[31]  Ying Li,et al.  Rail Component Detection, Optimization, and Assessment for Automatic Rail Track Inspection , 2014, IEEE Transactions on Intelligent Transportation Systems.

[32]  Yu Cui,et al.  Data-driven optimization of railway maintenance for track geometry , 2018 .

[33]  Quanshi Zhang,et al.  Visual interpretability for deep learning: a survey , 2018, Frontiers of Information Technology & Electronic Engineering.

[34]  John Andrews,et al.  The effects of tamping on railway track geometry degradation , 2013 .

[35]  Hitoshi Tsunashima,et al.  Condition Monitoring of Railway Tracks from Car-Body Vibration Using a Machine Learning Technique , 2019, Applied Sciences.

[36]  António Ramos Andrade,et al.  Hierarchical Bayesian modelling of rail track geometry degradation , 2013 .

[37]  Thyago P. Carvalho,et al.  A systematic literature review of machine learning methods applied to predictive maintenance , 2019, Comput. Ind. Eng..

[38]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[39]  David M. J. Tax,et al.  Semi-supervised rail defect detection from imbalanced image data , 2016 .

[40]  Majidreza Nazem,et al.  Development of a tram track degradation prediction model based on the acceleration data , 2019, Structure and Infrastructure Engineering.

[41]  Sara Moridpour,et al.  Degradation Prediction of Rail Tracks: A Review of the Existing Literature , 2018 .

[42]  Ettore Stella,et al.  A Real-Time Visual Inspection System for Railway Maintenance: Automatic Hexagonal-Headed Bolts Detection , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[43]  Bart De Schutter,et al.  A decision support approach for condition-based maintenance of rails based on big data analysis , 2018, Transportation Research Part C: Emerging Technologies.

[44]  Ayca Altay,et al.  Data-driven predictive maintenance scheduling policies for railways , 2019, Transportation Research Part C: Emerging Technologies.

[45]  António Ramos Andrade,et al.  A Bayesian model to assess rail track geometry degradation through its life-cycle , 2012 .

[46]  Bryan T. Adey,et al.  On the role of inspections and interventions in infrastructure management , 2012 .

[47]  Uday Kumar,et al.  Augmented utilisation of possession time: Analysis for track geometry maintenance , 2016 .

[48]  E. Stella,et al.  Visual recognition of fastening bolts for railroad maintenance , 2004, Pattern Recognit. Lett..

[49]  Li Zhuang,et al.  Automated vision inspection of rail surface cracks: A double-layer data-driven framework , 2018 .

[50]  Alireza Ahmadi,et al.  Track geometry degradation and maintenance modelling: A review , 2018 .

[51]  Futian Wang,et al.  Markov-based model for the prediction of railway track irregularities , 2015 .

[52]  Xiang Liu,et al.  Modeling of track geometry degradation and decisions on safety and maintenance: A literature review and possible future research directions , 2018 .

[53]  Luca Podofillini,et al.  Risk-informed optimisation of railway tracks inspection and maintenance procedures , 2006, Reliab. Eng. Syst. Saf..

[54]  Hakan Guler,et al.  Prediction of railway track geometry deterioration using artificial neural networks: a case study for Turkish state railways , 2014 .

[55]  Jing Lin,et al.  Deep Learning for Track Quality Evaluation of High-Speed Railway Based on Vehicle-Body Vibration Prediction , 2019, IEEE Access.

[56]  Andreas Hotho,et al.  A Brief Survey of Text Mining , 2005, LDV Forum.

[57]  Florian Auer,et al.  Application of Semantic Segmentation for an Autonomous Rail Tamping Assistance System , 2019 .

[58]  S. Moridpour,et al.  A review of rail track degradation prediction models , 2019, Australian Journal of Civil Engineering.

[59]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[60]  Nii O. Attoh-Okine,et al.  Principal components analysis and track quality index: A machine learning approach , 2018, Transportation Research Part C: Emerging Technologies.

[61]  Etienne Côme,et al.  Combined use of sensor data and structural knowledge processed by Bayesian network: Application to a railway diagnosis aid scheme , 2008 .

[62]  Buyue Qian,et al.  Improving rail network velocity: A machine learning approach to predictive maintenance , 2014 .

[63]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[64]  Yi Jiang,et al.  Fast classification for rail defect depths using a hybrid intelligent method , 2019, Optik.

[65]  Wei Xie,et al.  Decision support tool based on multi-source data analysis for the tram wheel-rail interface , 2018 .

[66]  M. Sol-Sánchez,et al.  Review of the design and maintenance technologies used to decelerate the deterioration of ballasted railway tracks , 2017 .

[67]  Bart De Schutter,et al.  A Big Data Analysis Approach for Rail Failure Risk Assessment , 2017, Risk analysis : an official publication of the Society for Risk Analysis.

[68]  James H. Garrett,et al.  Track-monitoring from the dynamic response of an operational train , 2017 .

[69]  Paul Weston,et al.  Perspectives on railway track geometry condition monitoring from in-service railway vehicles , 2015 .

[70]  Sung Ho Hwang,et al.  Deterioration Prediction of Track Geometry Using Periodic Measurement Data and Incremental Support Vector Regression Model , 2020 .

[71]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[72]  Duo Li,et al.  Relating track geometry to vehicle performance using neural network approach , 2006 .

[73]  Xiang Liu,et al.  Modeling Track Geometry Degradation Using Support Vector Machine Technique , 2016 .

[74]  Sophie Mercier,et al.  Bivariate Gamma wear processes for track geometry modelling, with application to intervention scheduling , 2012 .

[75]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[76]  Heung-Fai Lam,et al.  Railway ballast damage detection by Markov chain Monte Carlo-based Bayesian method , 2018 .

[77]  Nikolaos Doulamis,et al.  Deep Learning for Computer Vision: A Brief Review , 2018, Comput. Intell. Neurosci..

[78]  Tiedo Tinga,et al.  Rail wear and remaining life prediction using meta-models , 2020, International Journal of Rail Transportation.

[79]  Zhen Liu,et al.  Automatic Fault Detection of Multiple Targets in Railway Maintenance Based on Time-Scale Normalization , 2018, IEEE Transactions on Instrumentation and Measurement.

[80]  Raha Akhavan-Tabatabaei,et al.  An ensemble classifier to predict track geometry degradation , 2017, Reliab. Eng. Syst. Saf..