Data-driven robust strategies for joint optimization of rail renewal and maintenance planning

Abstract We study the problem of rail renewal and maintenance planning. The problem is to determine when and what type of maintenance tasks or rail renewal are required to be performed on different segments to maintain the rail in a safe and reliable condition. This problem is formulated as a Mixed Integer Linear Programming (MILP) model. The model applies Track Quality Index and also defines a new index to represent the current condition of the rail. Maintenance recovery effect is intrinsically uncertain; therefore, we develop data-driven uncertainty set approximation approaches and leverage robust optimization to handle the uncertainty. Data-driven uncertainty sets are constructed by approximating convex hulls of uncertain data points and by adding cutting planes to mix of classic robust uncertainty sets. We also obtained the robust counterpart formulations of the proposed MILP model for constructed uncertainty sets. Furthermore, a heuristic algorithm is developed to facilitate solving the model for large instances. Applicability and efficiency of the proposed approach are demonstrated through an illustrative case study of a Class I freight railroad network in the United States. Our analyses reveal that the proposed approaches introduce efficient strategies to deal with uncertainties in rail networks at the reasonable cost of increasing the budget.

[1]  Gang Rong,et al.  Data-driven rolling-horizon robust optimization for petrochemical scheduling using probability density contours , 2018, Comput. Chem. Eng..

[2]  Jaakko Kujala,et al.  Integrated scheduling of preventive maintenance and renewal projects for multi-unit systems with grouping and balancing , 2017, Comput. Ind. Eng..

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

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

[5]  Melvyn Sim,et al.  The Price of Robustness , 2004, Oper. Res..

[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]  Vishal Gupta,et al.  Data-driven robust optimization , 2013, Math. Program..

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

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

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

[11]  Yanfeng Ouyang,et al.  A Heuristic Approach to the Railroad Track Maintenance Scheduling Problem , 2011, Comput. Aided Civ. Infrastructure Eng..

[12]  Chao Shang,et al.  Data-driven robust optimization based on kernel learning , 2017, Comput. Chem. Eng..

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

[14]  David P. Dobkin,et al.  The quickhull algorithm for convex hulls , 1996, TOMS.

[15]  John D. Andrews,et al.  Optimal Scheduling of Track Maintenance on a Railway Network , 2013, Qual. Reliab. Eng. Int..

[16]  Dick den Hertog,et al.  Adjustable robust strategies for flood protection , 2016 .

[17]  Paulo Fonseca Teixeira,et al.  Availability Approach to Optimizing Railway Track Renewal Operations , 2013 .

[18]  Jeffery D. Weir,et al.  Robust goal programming for multi-objective optimization of data-driven problems: A use case for the United States transportation command's liner rate setting problem , 2020 .

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

[20]  Andreas Hartmann,et al.  Maintenance Scheduling for Railway Tracks under Limited Possession Time , 2018, Journal of Transportation Engineering, Part A: Systems.

[21]  Fengqi You,et al.  Data-Driven Stochastic Robust Optimization: General Computational Framework and Algorithm Leveraging Machine Learning for Optimization under Uncertainty in the Big Data Era , 2017, Comput. Chem. Eng..

[22]  Masashi Miwa,et al.  Mathematical modeling analyses for obtaining an optimal railway track maintenance schedule , 2006 .

[23]  Cécile Murat,et al.  Recent advances in robust optimization: An overview , 2014, Eur. J. Oper. Res..

[24]  Brian J. Lunday,et al.  Robust, multi-objective optimization for the military medical evacuation location-allocation problem , 2020 .

[25]  Ziyou Gao,et al.  Integrated optimization of train scheduling and maintenance planning on high-speed railway corridors , 2019, Omega.

[26]  Luís Alçada-Almeida,et al.  Large Scale Railway Renewal Planning with a Multiobjective Modeling Approach , 2018, ATMOS.

[27]  Zhihua Zhang,et al.  Impact of unused life for track sections and available workforce in scheduling tamping actions on ballasted tracks , 2017 .

[28]  Michael Burrow,et al.  A genetic-algorithm-based approach for scheduling the renewal of railway track components , 2009 .

[29]  Fengqi You,et al.  Optimization under Uncertainty in the Era of Big Data and Deep Learning: When Machine Learning Meets Mathematical Programming , 2019, Comput. Chem. Eng..

[30]  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.

[31]  Fengqi You,et al.  Data‐driven adaptive nested robust optimization: General modeling framework and efficient computational algorithm for decision making under uncertainty , 2017 .

[32]  Gang Rong,et al.  Data-driven robust optimization under correlated uncertainty: A case study of production scheduling in ethylene plant , 2018, Comput. Chem. Eng..

[33]  Jianmin Zhao,et al.  Optimizing Policies of Railway Ballast Tamping and Renewal , 2006 .

[34]  C. Floudas,et al.  A Comparative Theoretical and Computational Study on Robust Counterpart Optimization: I. Robust Linear Optimization and Robust Mixed Integer Linear Optimization. , 2011, Industrial & engineering chemistry research.

[35]  Gabriella Budai-Balke.  Operations Research Models for Scheduling Railway Infrastructure Maintenance , 2002 .

[36]  Xian Liu,et al.  Survival Analysis: Models and Applications , 2012 .

[37]  Masashi Miwa.  Mathematical Programming Model Analysis for the Optimal Track Maintenance Schedule , 2002 .

[38]  Allen L. Soyster,et al.  Technical Note - Convex Programming with Set-Inclusive Constraints and Applications to Inexact Linear Programming , 1973, Oper. Res..

[39]  Roberto Tadei,et al.  New heuristics for the stochastic tactical railway maintenance problem , 2016 .

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

[41]  P. Fonseca Teixeira,et al.  Biobjective Optimization Model for Maintenance and Renewal Decisions Related to Rail Track Geometry , 2011 .

[42]  Rui Calçada,et al.  Integer Programming to Optimize Tamping in Railway Tracks as Preventive Maintenance , 2012 .

[43]  Emil Gustavsson,et al.  Scheduling tamping operations on railway tracks using mixed integer linear programming , 2015, EURO J. Transp. Logist..

[44]  Sung Ho Hwang,et al.  Tamping and Renewal Optimization of Ballasted Track Using Track Measurement Data and Genetic Algorithm , 2018 .

[45]  Paulo Fonseca Teixeira,et al.  Optimisation model to schedule railway track renewal operations: a life-cycle cost approach , 2015 .

[46]  Isabel M. Ribeiro,et al.  Railway condition-based maintenance model with stochastic deterioration , 2014 .

[47]  Stefan Nickel,et al.  A structuring review on multi-stage optimization under uncertainty: Aligning concepts from theory and practice , 2020 .