Cost-effective fault diagnosis of a multi-component dynamic system under corrective maintenance

Abstract

Maintenance planning and execution are challenging tasks for every system with complex structure. Interdependent nature of the components that builds up the system may have significant effect on system integrity. While preventive maintenance actions can be carried out in a more planned fashion, corrective actions are more time sensitive as they directly affect the availability of the system. This study proposes a cost-effective dynamic Bayesian network modeling scheme to be used in the planning of corrective maintenance actions on systems having hidden components which have stochastic and structural dependencies. In such context, the regenerative air heater system which is a key element of a power plant is taken into consideration. The proposed maintenance framework offers several methods, each aiming to balance the cost with the probability effect using a normalization procedure. The methodologies are extensively simulated for sensitivity analysis under various downtime cost values. Fault effect methods with worst state probability efficiency measures give the least total cost for all downtime cost values and their distinction becomes significant as this value increases. Further statistical analysis concludes that considerable gains on maintenance costs can be achieved by the proposed approach.