Machinery fault diagnosis of high voltage circuit breaker based on empirical mode decomposition

To research the characteristics of mechanical vibration signals of high voltage circuit breakers, a new method for fault diagnosis was proposed based on improved empirical mode decomposition (EMD) energy entropy and support vector machine (SVM); and feasible diagnostic steps and analysis were also introduced. Firstly, the original vibration signals were decomposed into a number of intrinsic mode functions (IMF) by the EMD method. Secondly, the energy entropy vector was extracted with the segmental energy of IMF based on the theory of entropy and the method of equal energy, and was considered as the input vector of SVM. The Binary tree vector machine was used to solve the multi-class classification problem; and the gradient method and cross-validation were taken to optimize model parameters. The experiment shows that the proposed method is effective to diagnose the machinery faults of high voltage circuit breakers.