Distributed Chance-Constrained Model Predictive Control for Condition-Based Maintenance Planning for Railway Infrastructures

  • Zhou SuEmail author
  • Ali Jamshidi
  • Alfredo Núñez
  • Simone Baldi
  • Bart De Schutter


We develop a Model Predictive Control (MPC) approach for condition-based maintenance planning under uncertainty for railway infrastructure systems composed of multiple components. Piecewise-affine models with uncertain parameters are used to capture both the nonlinearity and uncertainties in the deterioration process. To keep a balance between robustness and optimality, we formulate the MPC optimization problem as a chance-constrained problem, which ensures that the constraints, e.g., bounds on the degradation level, are satisfied with a given probabilistic guarantee. Two distributed algorithms, one based on Dantzig-Wolfe decomposition and the other derived from a constraint-tightening technique, are proposed to improve the scalability of the MPC approach. Computational experiments show that the distributed method based on Dantzig-Wolfe decomposition performs the best in terms of computational time and convergence to global optimality. By comparing the chance-constrained MPC approaches with deterministic approach, and traditional time-based maintenance approach, we show that despite their high computational requirements, chance-constrained MPC approaches are cost-efficient and robust in the presence of uncertainties.



Research sponsored by the NWO/ProRail project “Multi-party risk management and key performance indicator design at the whole system level (PYRAMIDS),” project 438-12-300, which is partly financed by the Netherlands Organisation for Scientific Research (NWO).


  1. 1.
    Zoeteman, A., Li, Z., Dollevoet, R.: Dutch research results in wheel rail interface management: 2001–2013 and beyond. Proc. Inst. Mech. Eng. F J. Rail Rapid Transit 228(6), 642–651 (2014)Google Scholar
  2. 2.
    Sandström, J., Ekberg, A.: Predicting crack growth and risks of rail breaks due to wheel flat impacts in heavy haul operations. Proc. Inst. Mech. Eng. F J. Rail Rapid Transit 223(2), 153–161 (2009)Google Scholar
  3. 3.
    Jamshidi, A., Núñez, A., Li, Z., Dollevoet, R.: Maintenance decision indicators for treating squats in railway infrastructures. In: 94th Annual Meeting Transportation Research Board, Washington, 11–15 January 2015. TRB (2015)Google Scholar
  4. 4.
    Zoeteman, A.: Life cycle cost analysis for managing rail infrastructure. Eur. J. Transp. Infrastruct. Res. 1(4) (2001)Google Scholar
  5. 5.
    Al-Douri, Y., Tretten, P., Karim, R.: Improvement of railway performance: a study of Swedish railway infrastructure. Int. J. Mod. Transport. 24(1), 22–37 (2016)Google Scholar
  6. 6.
    Kobbacy, K., Murthy, D.: Complex System Maintenance Handbook. Springer Science & Business Media, London (2008)zbMATHGoogle Scholar
  7. 7.
    Ben-Daya, M., Kumar, U., Murthy, D.: Condition-based maintenance. In: Introduction to Maintenance Engineering: Modeling, Optimization, and Management, pp. 355–387. Wiley, Chichester (2016)Google Scholar
  8. 8.
    Jardine, A., Lin, D., Banjevic, D.: A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech. Syst. Sig. Process. 20(7), 1483–1510 (2006)Google Scholar
  9. 9.
    Fararooy, S., Allan, J.: Condition-based maintenance of railway signalling equipment. In: International Conference on Electric Railways in a United Europe, pp. 33–37. IET, Amsterdam (1995)Google Scholar
  10. 10.
    Ahmad, R., Kamaruddin, S.: An overview of time-based and condition-based maintenance in industrial application. Comput. Ind. Eng. 63(1), 135–149 (2012)Google Scholar
  11. 11.
    Dekker, R.: Applications of maintenance optimization models: a review and analysis. Reliab. Eng. Syst. Saf. 51(3), 229–240 (1996)Google Scholar
  12. 12.
    Scarf, P.: On the application of mathematical models in maintenance. Eur. J. Oper. Res. 99(3), 493–506 (1997)zbMATHGoogle Scholar
  13. 13.
    Wen, M., Li, R., Salling, K.: Optimization of preventive condition-based tamping for railway tracks. Eur. J. Oper. Res. 252(2), 455–465 (2016)MathSciNetzbMATHGoogle Scholar
  14. 14.
    Famurewa, S., Xin, T., Rantatalo, M., Kumar, U.: Optimisation of maintenance track possession time: a tamping case study. Proc. Inst. Mech. Eng. F J. Rail Rapid Transit 229(1), 12–22 (2015)Google Scholar
  15. 15.
    Mercier, S., Meier-Hirmer, C., Roussignol, M.: Bivariate Gamma wear processes for track geometry modelling, with application to intervention scheduling. Struct. Infrastruct. Eng. 8(4), 357–366 (2012)Google Scholar
  16. 16.
    Quiroga, L., Schnieder, E.: Monte Carlo simulation of railway track geometry deterioration and restoration. Proc. Inst. Mech. Eng. O J. Risk Reliab. 226,(3), 274–282 (2012)Google Scholar
  17. 17.
    Vale, C., Ribeiro, I.: Railway condition-based maintenance model with stochastic deterioration. J. Civ. Eng. Manag. 20(5), 686–692 (2014)Google Scholar
  18. 18.
    Jamshidi, A., Faghih-Roohi, S., Hajizadeh, S., Núñez, A., Dollevoet, R., Li, Z., De Schutter, B.: A big data analysis approach for rail failure risk assessment. Risk Anal. 37(8), 1495–1507 (2017)Google Scholar
  19. 19.
    Camacho, E., Alba, C.: Model Predictive Control. Springer Science & Business Media, London (2013)Google Scholar
  20. 20.
    Rawlings, J., Mayne, D.: Model Predictive Control: Theory and Design. Nob Hill Publishing, Madison (2009)Google Scholar
  21. 21.
    Nikolaou, M.: Model predictive controllers: a critical synthesis of theory and industrial needs. Adv. Chem. Eng. 26, 131–204 (2001)Google Scholar
  22. 22.
    Zafra-Cabeza, A., Maestre, J., Ridao, M., Camacho, E., Sánchez, L.: Hierarchical distributed model predictive control for risk mitigation: an irrigation canal case study. J. Process Control 21(5), 787–799 (2011)Google Scholar
  23. 23.
    Schildbach, G., Morari, M.: Scenario-based model predictive control for multi-echelon supply chain management. Eur. J. Oper. Res. 252(2), 540–549 (2016)MathSciNetzbMATHGoogle Scholar
  24. 24.
    Nandola, N., Rivera, D.: An improved formulation of hybrid model predictive control with application to production-inventory systems. IEEE Trans. Control Syst. Technol. 21(1), 121–135 (2013)Google Scholar
  25. 25.
    Bemporad, A., Morari, M.: Control of systems integrating logic, dynamics, and constraints. Automatica 35(3), 407–427 (1999)MathSciNetzbMATHGoogle Scholar
  26. 26.
    De Schutter, B., De Moor, B.: Optimal traffic light control for a single intersection. Eur. J. Control. 4(3), 260–276 (1998)zbMATHGoogle Scholar
  27. 27.
    Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends® Mach. Learn. 3(1), 1–122 (2011)zbMATHGoogle Scholar
  28. 28.
    Feizollahi, M., Costley, M., Ahmed, S., Grijalva, S.: Large-scale decentralized unit commitment. Int. J. Electr. Power Energy Syst. 73, 97–106 (2015)Google Scholar
  29. 29.
    Sebastio, S., Gnecco, G., Bemporad, A.: Optimal distributed task scheduling in volunteer clouds. Comput. Oper. Res. 81, 231–246 (2017)MathSciNetzbMATHGoogle Scholar
  30. 30.
    Mendes, P., Maestre, J., Bordons, C., Normey-Rico, J.: A practical approach for hybrid distributed mpc. J. Process Control 55, 30–41 (2017)Google Scholar
  31. 31.
    Kuwata, Y., Richards, A., Schouwenaars, T., How, J.: Distributed robust receding horizon control for multivehicle guidance. IEEE Trans. Control Syst. Technol. 15(4), 627–641 (2007)Google Scholar
  32. 32.
    Benders, J.: Partitioning procedures for solving mixed-variables programming problems. Numer. Math. 4(1), 238–252 (1962)MathSciNetzbMATHGoogle Scholar
  33. 33.
    Dantzig, G., Wolfe, P.: Decomposition principle for linear programs. Oper. Res. 8(1), 101–111 (1960)zbMATHGoogle Scholar
  34. 34.
    Rahmaniani, R., Crainic, T., Gendreau, M., Rei, W.: The Benders decomposition algorithm: a literature review. Eur. J. Oper. Res. 259(3), 801–817 (2016)MathSciNetzbMATHGoogle Scholar
  35. 35.
    Gunnerud, V., Foss, B.: Oil production optimization-a piecewise linear model, solved with two decomposition strategies. Comput. Chem. Eng. 34(11), 1803–1812 (2010)Google Scholar
  36. 36.
    Morari, M., Zafiriou, E.: Robust Process Control, vol. 488. Prentice Hall, Englewood Cliffs (1989)Google Scholar
  37. 37.
    Gruber, J., Ramirez, D., Limon, D., Alamo, T.: Computationally efficient nonlinear min-max model predictive control based on Volterra series models – application to a pilot plant. J. Process Control 23(4), 543–560 (2013)Google Scholar
  38. 38.
    Prekopa, A.: On probabilistic constrained programming. In: Proceedings of the Princeton Symposium on Mathematical Programming, pp. 113–138. Princeton University Press, Princeton (1970)Google Scholar
  39. 39.
    Grosso, J., Ocampo-Martínez, C., Puig, V., Joseph, B.: Chance-constrained model predictive control for drinking water networks. J. Process Control 24(5), 504–516 (2014)Google Scholar
  40. 40.
    Jurado, I., Maestre, J., Velarde, P., Ocampo-Martinez, C., Fernández, I., Tejera, B.I., del Prado, J.: Stock management in hospital pharmacy using chance-constrained model predictive control. Comput. Biol. Med. 72, 248–255 (2016)Google Scholar
  41. 41.
    Su, Z., Jamshidi, A., Núñez, A., Baldi, S., De Schutter, B.: Multi-level condition-based maintenance planning for railway infrastructures – a scenario-based chance-constrained approach. Transp. Res. C Emerg. Tech. 84, 92–123 (2017)Google Scholar
  42. 42.
    Pintér, J.: Deterministic approximations of probability inequalities. Z. Oper. Res. 33(4), 219–239 (1989)MathSciNetzbMATHGoogle Scholar
  43. 43.
    Calafiore, G., Campi, M.: The scenario approach to robust control design. IEEE Trans. Autom. Control 51(5), 742–753 (2006)MathSciNetzbMATHGoogle Scholar
  44. 44.
    Shapiro, A.: Sample average approximation. In: Encyclopedia of Operations Research and Management Science, pp. 1350–1355. Springer, Boston (2013)Google Scholar
  45. 45.
    Esfahani, P., Sutter, T., Lygeros, J.: Performance bounds for the scenario approach and an extension to a class of non-convex programs. IEEE Trans. Autom. Control 60(1), 46–58 (2015)MathSciNetzbMATHGoogle Scholar
  46. 46.
    Margellos, K., Goulart, P., Lygeros, J.: On the road between robust optimization and the scenario approach for chance constrained optimization problems. IEEE Trans. Autom. Control 59(8), 2258–2263 (2014)MathSciNetzbMATHGoogle Scholar
  47. 47.
    Alamo, T., Tempo, R., Luque, A.: On the sample complexity of randomized approaches to the analysis and design under uncertainty. In: American Control Conference (ACC), 2010, pp. 4671–4676. IEEE, Baltimore (2010)Google Scholar
  48. 48.
    Su, Z., Núñez, A., Jamshidi, A., Baldi, S., Li, Z., Dollevoet, R., De Schutter, B.: Model predictive control for maintenance operations planning of railway infrastructures: In: Computational Logistics (Proceedings of the 6th International Conference on Computational Logistics (ICCL’15), Delft, Sept. 2015), pp. 673–688 (2015)Google Scholar
  49. 49.
    Dantzig, G., Ramser, J.: The truck dispatching problem. Manag. Sci. 6(1), 80–91 (1959)MathSciNetzbMATHGoogle Scholar
  50. 50.
    Chisci, L., Rossiter, J., Zappa, G.: Systems with persistent disturbances: predictive control with restricted constraints. Automatica 37(7), 1019–1028 (2001)MathSciNetzbMATHGoogle Scholar
  51. 51.
    Cassels, J.: An Introduction to the Geometry of Numbers. Springer Science & Business Media, Berlin (2012)Google Scholar
  52. 52.
    Vanderbeck, F., Wolsey, L.: Reformulation and decomposition of integer programs. In: Jünger, M., Liebling, T., Naddef, D., Nemhauser, G., Pulleyblank, W., Reinelt, G., Rinaldi, G., Wolsey, L. (eds.) 50 Years of Integer Programming 1958–2008, pp. 431–502. Springer, Berlin (2010)zbMATHGoogle Scholar
  53. 53.
    Li, Z., Molodova, M., Núñez, A., Dollevoet, R.: Improvements in axle box acceleration measurements for the detection of light squats in railway infrastructure. IEEE Trans. Ind. Electron. 62(7), 4385–4397 (2015)Google Scholar
  54. 54.
    Molodova, M., Li, Z., Núñez, A., Dollevoet, R.: Automatic detection of squats in railway infrastructure. IEEE Trans. Intell. Transp. Syst. 15(5), 1980–1990 (2014)Google Scholar
  55. 55.
    Song, Z., Yamada, T., Shitara, H., Takemura, Y.: Detection of damage and crack in railhead by using eddy current testing. J. Electromagn. Anal. Appl. 3(12), 546 (2011)Google Scholar
  56. 56.
    Fan, Y., Dixon, S., Edwards, R., Jian, X.: Ultrasonic surface wave propagation and interaction with surface defects on rail track head. NDT & E Int. 40(6), 471–477 (2007)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Zhou Su
    • 1
    Email author
  • Ali Jamshidi
    • 1
  • Alfredo Núñez
    • 1
  • Simone Baldi
    • 2
  • Bart De Schutter
    • 2
  1. 1.Delft Center for Systems and ControlDelftThe Netherlands
  2. 2.Section of Railway EngineeringDelftThe Netherlands

Personalised recommendations