A decision support approach for condition-based maintenance of rails based on big data analysis

Abstract In this paper, a decision support approach is proposed for condition-based maintenance of rails relying on expert-based systems. The methodology takes into account both the actual conditions of the rails (using axle box acceleration measurements and rail video images) and the prior knowledge of the railway track. The approach provides an integrated estimation of the rail health conditions to support the maintenance decisions for a given time period. An expert-based system is defined to analyse interdependency between the prior knowledge of the track (defined by influential factors) and the surface defect measurements over the rail. When the rail health conditions is computed, the different track segments are prioritized, in order to facilitate grinding planning of those segments of rail that are prone to critical conditions. In this paper, real-life rail conditions measurements from the track Amersfoort-Weert in the Dutch railway network are used to show the benefits of the proposed methodology. The results support infrastructure managers to analyse the problems in their rail infrastructure and to efficiently perform a condition-based maintenance decision making.

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

[2]  Ming Xie.  Fundamentals of Robotics - Linking Perception to Action , 2003, Series in Machine Perception and Artificial Intelligence.

[3]  L. Wynter,et al.  Incident Duration Prediction with Hybrid Tree-based Quantile Regression , 2013 .

[4]  Do Thompson,et al.  Ultrasonic surface wave propagation and interaction with surface defects on rail track head , 2006 .

[5]  David M. J. Tax,et al.  Evaluating Classification Performance with only Positive and Unlabeled Samples , 2014, S+SSPR.

[6]  Zili Li,et al.  Squat growth—Some observations and the validation of numerical predictions , 2011 .

[7]  Zili Li.  Squats on railway rails , 2009 .

[8]  C. Tyler Dick,et al.  Risk-Based Optimization of Rail Defect Inspection Frequency for Petroleum Crude Oil Transportation , 2016 .

[9]  S L Grassie,et al.  Squats and squat-type defects in rails: the understanding to date , 2012 .

[10]  Masashi Miwa,et al.  Actual Data Analysis of Alignment Irregularity Growth and its Prediction Model , 2005 .

[11]  Paulo Fonseca Teixeira,et al.  Strategic Model to Optimize Railway-Track Renewal Operations at a Network Level , 2016 .

[12]  J Zywiel,et al.  INNOVATIVE MEASURING SYSTEM UNVEILED , 2001 .

[13]  Dennis Huisman,et al.  Scheduling preventive railway maintenance activities , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[14]  Aditya Parida,et al.  Development of a multi‐criteria hierarchical framework for maintenance performance measurement (MPM) , 2007 .

[15]  Mohd Rapik Saat,et al.  Analysis of Causes of Major Train Derailment and Their Effect on Accident Rates , 2012 .

[16]  T. Makino,et al.  The effect of slip ratio on the rolling contact fatigue property of railway wheel steel , 2012 .

[17]  Nii Attoh-Okine,et al.  Big Data and Differential Privacy: Analysis Strategies for Railway Track Engineering , 2017 .

[18]  Ulf Olofsson,et al.  Wheel-Rail Interface Handbook , 2009 .

[19]  K. D. Vo,et al.  Comparisons of stress, heat and wear generated by AC versus DC locomotives under diverse operational conditions , 2015 .

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

[21]  Dewan Md Zahurul Islam,et al.  Cost effective future derailment mitigation techniques for rail freight traffic management in Europe , 2016 .

[22]  Stuart L. Grassie,et al.  Tractive effort, curving and surface damage of rails: Part 1. Forces exerted on the rails , 2005 .

[23]  Alberto Bemporad,et al.  Control of systems integrating logic, dynamics, and constraints , 1999, Autom..

[24]  Rui Li,et al.  Optimization of preventive condition-based tamping for railway tracks , 2016, Eur. J. Oper. Res..

[25]  Rui Santos,et al.  Heuristic Analysis of the Effective Range of a Track Tamping Machine , 2012 .

[26]  Xinping Yan,et al.  Classification of Automatic Radar Plotting Aid targets based on improved Fuzzy C-Means , 2015 .

[27]  Tsutomu Yamada,et al.  Detection of Damage and Crack in Railhead by Using Eddy Current Testing , 2011 .

[28]  Murtaza Haider,et al.  Beyond the hype: Big data concepts, methods, and analytics , 2015, Int. J. Inf. Manag..

[29]  Bart De Schutter,et al.  Multi-level condition-based maintenance planning for railway infrastructures – A scenario-based chance-constrained approach , 2017 .

[30]  Ping Wang,et al.  The effect of track alignment irregularity on wheel-rail contact geometry relationship in a turnout zone , 2012 .

[31]  Andreas Fischer,et al.  A railway maintenance scheduling problem with customer costs , 2015, EURO J. Transp. Logist..

[32]  Yanfeng Ouyang,et al.  Optimal Clustering of Railroad Track Maintenance Jobs , 2014, Comput. Aided Civ. Infrastructure Eng..

[33]  Alan J Bing,et al.  DEVELOPMENT OF RAILROAD TRACK DEGRADATION MODELS , 1983 .

[34]  J C Corbin,et al.  PERFORMANCE-BASED TRACK-QUALITY MEASURES AND THEIR APPLICATION TO MAINTENANCE-OF-WAY PLANNING , 1981 .

[35]  Davide Anguita,et al.  Condition Based Maintenance in Railway Transportation Systems Based on Big Data Streaming Analysis , 2015, INNS Conference on Big Data.

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

[37]  P. J. Mutton,et al.  Rolling contact fatigue in railway wheels under high axle loads , 1991 .

[38]  Y. Nakai,et al.  Effect of defect shape on rolling contact fatigue crack initiation and propagation in high strength steel , 2016 .

[39]  M. Tosun,et al.  Rule-based Mamdani-type fuzzy modelling of thermal performance of multi-layer precast concrete panels used in residential buildings in Turkey , 2011, Expert Syst. Appl..

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

[41]  Jens C. O. Nielsen,et al.  Influence of Short-Pitch Wheel/Rail Corrugation on Rolling Contact Fatigue of Railway Wheels , 2005 .

[42]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[43]  Z. Popović,et al.  Rail inspection of RCF defects , 2013 .

[44]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[45]  C. Esveld,et al.  An investigation into the causes of squats—Correlation analysis and numerical modeling , 2008 .

[46]  A. Parida,et al.  Maintenance performance indicators (MPIs) for benchmarking the railway infrastructure , 2009 .

[47]  Rolf Dollevoet,et al.  Improvements in Axle Box Acceleration Measurements for the Detection of Light Squats in Railway Infrastructure , 2015, IEEE Transactions on Industrial Electronics.

[48]  Yanfeng Ouyang,et al.  Track maintenance production team scheduling in railroad networks , 2012 .

[49]  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.

[50]  Lei Xu,et al.  A novel model for determining the amplitude-wavelength limits of track irregularities accompanied by a reliability assessment in railway vehicle-track dynamics , 2017 .

[51]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

[53]  Rachel S. Edwards,et al.  Ultrasonic surface wave propagation and interaction with surface defects on rail track head , 2007 .

[54]  Stefano Mariani,et al.  Noncontact ultrasonic guided wave inspection of rails , 2013 .

[55]  Qing He,et al.  Track geometry defect rectification based on track deterioration modelling and derailment risk assessment , 2015, J. Oper. Res. Soc..

[56]  David Fletcher,et al.  Simulation study of thermally initiated rail defects , 2014 .

[57]  Peter Veit.  Track Quality - Luxury or Necessity? , 2007 .

[58]  Rolf Dollevoet,et al.  Robust and predictive fuzzy key performance indicators for condition-based treatment of squats in railway infrastructures , 2017 .

[59]  Cesar A. Sciammarella,et al.  Experimental evaluation of rolling contact fatigue in railroad wheels , 2016 .

[60]  Xiang Liu,et al.  Analysis of Derailments by Accident Cause , 2011 .

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

[62]  P. Fonseca Teixeira,et al.  Uncertainty in Rail-Track Geometry Degradation: Lisbon-Oporto Line Case Study , 2011 .

[63]  ImageNet Classification with Deep Convolutional Neural , 2013 .

[64]  Adam S. Markowski,et al.  Fuzzy logic for piping risk assessment (pfLOPA) , 2009 .

[65]  Rolf Dollevoet,et al.  Dutch research results on wheel/rail interface management: 2001–2013 and beyond , 2014 .

[66]  Antonino Staiano,et al.  A fuzzy decision system for genetically modified plant environmental risk assessment using Mamdani inference , 2015, Expert Syst. Appl..

[67]  A Hamid,et al.  TRACK-QUALITY INDICES AND TRACK-DEGRADATION MODELS FOR MAINTENANCE-OF-WAY PLANNING , 1981 .

[68]  Bart De Schutter,et al.  Deep convolutional neural networks for detection of rail surface defects , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).