Advertisement

Specifying a Condition-Based Maintenance Decision Support System of a Fleet of Cyber-Physical Systems

  • John Mbuli
  • Damien TrentesauxEmail author
  • Thierry Dailly
Conference paper
Part of the Studies in Computational Intelligence book series (SCI, volume 803)

Abstract

To obtain an effective condition-based maintenance (CBM) of a fleet of cyber-physical systems (CPSs), the associated supervision and decision support system (DSS) must be efficient tools as well. Through these tools, the human supervisor must have reliable and up to date information on each entity of the fleet as well as the information on the environment around the respective entities. Currently, despite a huge increase in industrial CBM implementation, the same effort has not been reflected on the design and specification of supervision and DSSs. The existing supervision and DSSs present several shortcomings which are problematic especially in the cases of large fleets of CPSs; hence CBM policies tend to be less effective in these cases. In this work, the authors propose a new approach with a set of specifications on the supervision and DSSs for effective CBM implementation. The specifications consist of, firstly, fleets of intelligent CPSs embedded with intelligent processing architectures allowing the communications and information exchange among the CPSs. Secondly, an intelligent virtual agent is embedded in the supervision and DSS in such a way that the human supervisor can communicate with all intelligent CPSs in the fleet via this virtual agent. The virtual intelligent agent will trigger and provide any necessary information to facilitate the supervision and decision making for effective CBM. This approach is intended to be firstly, a human-centred in design and secondly, it should reduce significantly the complexity of the supervisor’s tasks as well as improve the efficiency of CBM policies.

Keywords

Fleet supervision Decision support systems Artificial intelligence Cyber-physical systems Condition-based maintenance Human-centred approach 

Notes

Acknowledgements

Surferlab is funded by ERDF (European Regional Development Fund) and Hauts-de-France region. The authors would like to thank EU and the region for their support.

References

  1. 1.
    Alaswad, S., Xiang, Y.: A review on condition-based maintenance optimization models for stochastically deteriorating system. Reliab. Eng. Syst. Saf. 157, 54–63 (2017)CrossRefGoogle Scholar
  2. 2.
    Liu, Y., Peng, Y., Wang, B., Yao, S., Liu, Z.: Review on cyber-physical systems. IEEECAA J. Autom. Sin. 4(1), 27–40 (2017)CrossRefGoogle Scholar
  3. 3.
    Mbuli, J., Trentesaux, D., Clarhaut, J., Branger, G.: Decision support in condition-based maintenance of a fleet of cyber-physical systems: a fuzzy logic approach. In: Proceedings of 2017 Intelligent Systems Conference (IntelliSys), pp. 82–89. IEEE, UK (2017)Google Scholar
  4. 4.
    Noman, M.A., Nasr, E.S.A., Al-Shayea, A., Kaid, H.: Overview of predictive condition based maintenance research using bibliometric indicators. J. King Saud Univ. (2018) Google Scholar
  5. 5.
    Lin, L., Luo, B., Zhong, S.: Development and application of maintenance decision-making support system for aircraft fleet. Adv. Eng. Softw. 114, 192–207 (2017)CrossRefGoogle Scholar
  6. 6.
    Vujanović, D., Momčilović, V., Bojović, N., Papić, V.: Evaluation of vehicle fleet maintenance management indicators by application of DEMATEL and ANP. Expert Syst. Appl. 39(12), 10552–10563 (2012)CrossRefGoogle Scholar
  7. 7.
    Hu, J., Morais, H., Sousa, T., Lind, M.: Electric vehicle fleet management in smart grids: a review of services, optimization and control aspects. Renew. Sustain. Energy Rev. 56(Supplement C), 1207–1226 (2016)CrossRefGoogle Scholar
  8. 8.
    Belmonte, M.V., Pérez de la Cruz, J.L., Triguero, F.: Ontologies and agents for a bus fleet management system. Expert Syst. Appl. 34(2), 1351–1365 (2008)CrossRefGoogle Scholar
  9. 9.
    Awasthi, A., Chauhan, S.S., Parent, M., Proth, J.-M.: Centralized fleet management system for cybernetic transportation. Expert Syst. Appl. 38(4), 3710–3717 (2011)CrossRefGoogle Scholar
  10. 10.
    Trentesaux, D., Branger, G., Foundation of the surfer data management architecture and its application to train transportation. In: Borangiu, T., Trentesaux, D., Thomas, A., Cardin, O. (eds.) Service Orientation in Holonic and Multi-Agent Manufacturing: Proceedings of SOHOMA 2017. Studies in Computational Intelligence, vol. 762, pp. 111–125. Springer, Cham (2018)Google Scholar
  11. 11.
    Pacaux-Lemoine, M.-P., Trentesaux, D., Rey, G.Z., Millot, P.: Designing intelligent manufacturing systems through human–machine cooperation principles: a human-centered approach. Comput. Ind. Eng. 111, 581–595 (2017)CrossRefGoogle Scholar
  12. 12.
    Negnevitsky, M.: Artificial Intelligence: A Guide to Intelligent Systems. Addison-Wesley, Boston (2005)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • John Mbuli
    • 1
    • 2
  • Damien Trentesaux
    • 1
    • 2
    Email author
  • Thierry Dailly
    • 2
    • 3
  1. 1.UVHC, LAMIH UMR CNRS 8201ValenciennesFrance
  2. 2.SurferLabValenciennesFrance
  3. 3.Bombardier TransportCrespinFrance

Personalised recommendations