Mohammad Partovi - School of Industrial Engineering, College of Engineering, University of Tehran, Iran
Mohsen Amra - Department of Industrial Engineering, South-Tehran Branch, Islamic Azad University, Tehran, Iran
Mohammadjavad Pahlevanzadeh - Department of Management and Accounting, College of Farabi, University of Tehran, Iran
Abbas Alwardi - Industrial Engineering Department, Faculty of Industry, Management and Accounting, Shahabdanesh University, Qom, Iran
Mohammad Reza Fathi - 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.

maintenance, prediction, Bayesian networks, conditional probability