Fault diagnosis of high voltage circuit breaker based on ICEEMDAN sample entropy and SVM (CICED 2022)

In order to identify the fault of circuit breaker simply and accurately, a method based on improved adaptive noise complete set empirical mode decomposition (ICEEMDAN) and support vector machine (SVM) is proposed. Firstly, ICEEMDAN is used to decompose the vibration signal, and then the obtained modal function (IMF) is used to eliminate the false IMF component by using its correlation. Finally, the IMF component with high correlation is calculated by sample entropy to obtain the characteristic vector of vibration signal, which is input into support vector machine for fault classification, and the classification results are obtained. The experimental results show that the classification accuracy is 100%.