A pattern recognition methodology for fault detection: a circuit breaker case study

Maintenance strategies have evolved from standard cyclic maintenance to more advanced approaches like Condition Based Maintenance and Predictive Maintenance approach. Even if lot of work has been done regarding these methodologies applied on machines or industrial plants, the same care is not applied to other critical devices. In the case of Low Voltage Circuit Breakers, in particular for critical applications, conservative approaches are usually applied. That implies a scheduled replacement of devices could occur with a significant Remaining Useful-Life. This paper deals with Pattern Recognition techniques supporting the first step of prognostics of an electrical circuit breaker. The goal is to develop a methodology for Fault Detection, the first phase of a system of Fault Detection and Isolation.