A DBN Based Prognosis Model for a Complex Dynamic System: A Case Study in a Thermal Power Plant

Abstract

With the development of industry, complexity of systems and equipment has increased extensively. This results in the introduction of many interdependencies (stochastic, structural and economic) among the components of systems. Neglecting these interdependencies, when planning maintenance actions, leads to undesirable outcomes such as prolonged downtime and higher costs. That is why a multi-component system approach needs to be taken into account in maintenance planning models. However, maintenance planning is a difficult task in multi-component systems because of their complexities.

Energy production systems are notable examples of such complex structures consisting of many interacting components. Maintenance planning is extremely crucial for this sector since any unexpected malfunction leads to very serious costs. Therefore, the aim of this study is to formulate the maintenance problem of a multi-component dynamic system in thermal power plants focusing on system reliability prognosis. Bayesian networks (BN) are probabilistic graphical models that have been extensively used to represent and model the causal relations. A dynamic Bayesian network (DBN) is an extended BN which has a temporal dimension. We propose to use DBNs to prognose the reliabilities of components and processes of a dynamic system in a thermal power plant and show that this representation is efficient to model the interdependencies and degradations in such a system.