ANFIS based sound vibration combined fault diagnosis of high voltage circuit breaker (HVCB)

HVCB is an essential component of any power system. Finding its fault early on is beneficial to maintaining the stability of the power system. The combined acoustic and vibration signal generated by the action of mechanical components of an HVCB, as a homologous signal, can more effectively reflect the state information of an HVCB in the event of a fault than a single signal. ANFIS fault diagnosis model composed of fuzzy theory in a neural network is proposed to address the problem of low accuracy in the field of fault diagnosis of the HVCB. Firstly, the noise reduction of the acoustic vibration signal is optimized based on wavelet analysis and CS-VMD, the local minimum envelope entropy is extracted, and the entropy weight method is used to fuse the local minimum envelope entropy of the acoustic vibration signal to form a composite feature vector, and the ANFIS fault diagnosis model is established. The experimental results show that the fault diagnosis method proposed in this paper has a low error in diagnosis results, and the accuracy has been greatly improved compared with the traditional diagnosis method. The eigenvector composed of sound vibration combined signal can more accurately reflect the operating state of the HVCB