A method of classified HV circuit breaker fault signal based on EEMD and SOM neural network

During the operation of high voltage circuit breaker, the change of vibration signal reflects the mechanical state of the circuit beaker. Aiming at the nonlinearity and non-stationarity of high voltage circuit breaker vibration signal, this paper present a fault diagnosis method based on the ensemble empirical mode decomposition (EEMD) for correlation dimension and self-organizing feature mapping (SOM) neural Networks. First, the vibration signal is decomposed by EEMD, then we get the eigenvector of the vibration signal by calculating the correlation dimension of the intrinsic mode function (IMF). Finally, automatic fault identification is carried out in the SOM neural network, which is trained by input of the eigenvector. The results show that the method proposed in this paper can identify the fault types accurately and quickly, and has a certain reference value for the fault diagnosis of high voltage circuit breaker.