A DBN based reactive maintenance model for a complex system in thermal power plants

Abstract

Thermal power plants consist of several complex systems having many interacting hidden components. Any unexpected failure may lead to prolonged downtime and serious lost profits. Therefore, implementing an effective maintenance policy is crucial for this sector. Although preventive maintenance has become a more popular strategy, it does not completely prevent the need for corrective maintenance. Our aim in this study is to tackle the corrective maintenance implementation problem of a multi-component partially observable dynamic system based on a regenerative air heater in a thermal power plant. We propose eight methods having different efficiency measures with respect to time, effect and probability criteria to minimize the total number of maintenance activities in a given planning horizon. Performances of these methods are evaluated under corrective maintenance strategy using dynamic Bayesian networks. The results show that fault effect methods with best working state probability measure perform better than the others considering both the total amount of maintenance activities and also the solution time. We also point out how the methods can be implemented in real-life and how the results can be used for requirements planning. Furthermore, the proposed methods can be used for the corrective maintenance of all systems having hidden interacting components.