High Voltage Circuit Breaker Fault Diagnosis Based on Reasoning chain and Bayes

Abstract

In order to find the reason of the high voltage circuit breaker rejection quickly, an fault diagnosis method based on reasoning chain and Bayesian network (BN) is presented in the paper. Firstly, the concept of event set is introduced. A fault symptom set is constructed based on the measured circuit breaker characteristic parameters and warning signals. And the direct cause of circuit breaker failure, such as a part of the circuit breaker components or mechanism failure constitute the fault cause set. After that, when the high voltage circuit breaker fails, a subset of fault symptoms and fault causes is obtained according to the information. Then an reasoning chain is constructed according to the causal relationship between the two. Finally, a corresponding Bayesian network model for reasoning chain is built. The probability of fault causes is obtained by Bayesian backward reasoning, so as to realize the rapid analysis of circuit breaker faults. And the effectiveness of the method is verified by the result of practical fault diagnosis examples.