Fault Diagnosis of High Voltage Vacuum Circuit Breaker with Electromagnetic Repulsion Mechanism Based on Wavelet Packet Decomposition and Random Forest

At present, high voltage vacuum circuit breakers (HVVCBs) based on electromagnetic repulsion mechanism (ERM) have been more and more used in power system. However, the mechanical parts of HVVCBs are easy to be damaged because of the short opening time, high speed and large impact of ERM. Therefore, a method based on wavelet packet decomposition (WPD) and random forest (RF) is proposed to diagnose the fault occurred in HVVCB with ERM. Firstly, the opening vibration signals of ERM at two positions and six different conditions are obtained. Then, WPD is used to analyze the time-frequency characteristics of the vibration signal and the normalized energy vector of each frequency band of the vibration signal is calculated. Finally, the fault diagnosis and classification are carried out based on random forest. The experimental results indicate that the proposed method can quickly and effectively identify the mechanical and electrical circuit faults in HVVCB with ERM.