High-voltage Circuit Breaker Fault Diagnosis Model Based on Coil Current and KNN

High-voltage circuit breaker is one of the most critical equipment in power system, and the operating mechanism fault is the main fault state of circuit breaker. This paper uses the coil current and K-Nearest Neighbor (K-NN) classification methodology for diagnosing and recognizing the operating mechanism fault of circuit breaker. Firstly, to collect the coil current of normal state and common fault states, we conduct an experiment to simulate three common fault working states of operating mechanism from a 126kV SF6 circuit breaker; extract the feature vectors from the different states according to the characteristic of the close coil current; and, use KNN classification algorithm to establish the fault diagnosis model. Finally, we use the testing samples to verify the diagnosis model. The result shows that the new proposal can diagnose and recognize the fault states of the high-voltage circuit-breaker operating mechanism objectively, accurately and effectively.