Predictive Maintenance Approach for Complex Equipment Based on Petri Net Failure Mechanism Propagation Model

Abstract

The aim of this paper is to propose a comprehensive approach for predictive maintenance of complex equipment. The approach relies on a physics of failure model based on expert knowledge. The model can be represented as a multi-state Petri Net where different failure mechanisms have been discretized using physical degradation states. Each state can be detected by a unique combination of symptoms that can be measured from diagnostic tools. Based on actual existing diagnostic information, a diagnostic algorithm enables the identification of active failure mechanisms and estimates their progression in the Petri Net. Specific maintenance actions and their potential effect on the system can be associated with targeted states. Thereafter, a prognostic algorithm using a coloured Petri Net propagation method spreads active failure mechanisms though their related remaining states towards the targeted states. This allows specific maintenance actions to be proposed in a timeframe and thus enables predictive maintenance. Case study is presented for a real hydro generator. Finally, model limits are discussed and potential areas of further research are identified.