Predictable Maintenance: A Bayesian Network-based Model

Document Type : Original Research Article


1 School of Industrial Engineering, College of Engineering, University of Tehran, Iran

2 Department of Industrial Engineering, South-Tehran Branch, Islamic Azad University, Tehran, Iran

3 Department of Management and Accounting, College of Farabi, University of Tehran, Iran

4 Industrial Engineering Department, Faculty of Industry, Management and Accounting, Shahabdanesh University, Qom, Iran

5 Associate Professor, College of Farabi, University of Tehran, Iran


Industries' increasing progress and complexity has made maintenance and repair tasks very challenging, complex, and time-consuming. Maintenance is one of the important sectors in several industries, and improvement in this sector can have excellent results. This paper develops a new maintenance prediction model based on Bayesian networks (BN) capabilities. The models include several variables that experts determine and their influence on each other's-called conditional probability tables-which are learned from historical data. The model is implemented in an automobile repair department case study to show its performance. The model is evaluated through a sensitivity analysis, and the results show the proficiency of the proposal mode.


Main Subjects

  1. Selcuk, "Predictive maintenance, its implementation and latest trends," Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, vol. 231, no. 9, pp. 1670-1679, 2017.
  2. Levitt, Complete guide to preventive and predictive maintenance. Industrial Press Inc., 2003.
  3. K. Jardine, D. Lin, and D. Banjevic, "A review on machinery diagnostics and prognostics implementing condition-based maintenance," Mechanical systems and signal processing, vol. 20, no. 7, pp. 1483-1510, 2006.
  4. Lughofer and M. Sayed-Mouchaweh, Predictive maintenance in dynamic systems: advanced methods, decision support tools and real-world applications. Springer, 2019.
  5. Weber and C. Simon, Benefits of Bayesian network models. John Wiley & Sons, 2016.
  6. Zhexue, Q. Zhuqi, L. Xu, Y. Yongmin, and Z. Yi, "Multistage Bayesian fusion evaluation technique endorsing immersive virtual maintenance," Measurement, vol. 177, p. 109344, 2021.
  7. Zhang and D. W. R. Marsh, "Managing infrastructure asset: Bayesian networks for inspection and maintenance decisions reasoning and planning," Reliability Engineering & System Safety, vol. 207, p. 107328, 2021.
  8. -T. Li, X.-N. He, and J. Shuai, "Risk analysis and maintenance decision making of natural gas pipelines with external corrosion based on Bayesian network," Petroleum Science, vol. 19, no. 3, pp. 1250-1261, 2022.
  9. Dojer, "Learning Bayesian networks from datasets joining continuous and discrete variables," International Journal of Approximate Reasoning, vol. 78, pp. 116-124, 2016.
  10. Nie, C. P. de Campos, and Q. Ji, "Efficient learning of Bayesian networks with bounded tree-width," International Journal of Approximate Reasoning, vol. 80, pp. 412-427, 2017.
  11. Yu, V. A. Smith, P. P. Wang, A. J. Hartemink, and E. D. Jarvis, "Advances to Bayesian network inference for generating causal networks from observational biological data," Bioinformatics, vol. 20, no. 18, pp. 3594-3603, 2004.
  12. D. Garvey, S. Carnovale, and S. Yeniyurt, "An analytical framework for supply network risk propagation: A Bayesian network approach," European Journal of Operational Research, vol. 243, no. 2, pp. 618-627, 2015.
  13. Jiang and X. Liu, "Hidden Markov model for municipal waste generation forecasting under uncertainties," European Journal of Operational Research, vol. 250, no. 2, pp. 639-651, 2016.
  14. Buntine, "Backoff methods for estimating parameters of a Bayesian network," in Advanced Methodologies for Bayesian Networks, 2017: PMLR, pp. 3-3.
  15. E. Neapolitan, Learning bayesian networks. Pearson Prentice Hall Upper Saddle River, 2004.
  16. J. Russell, Artificial intelligence a modern approach. Malaysia: Pearson Education, Inc., 2016.