The high voltage circuit breaker is one of the most important electrical equipments, which controls and protects the power system. In order to improve the accuracy of fault diagnosis of high voltage circuit breakers, a fault diagnosis method of high voltage circuit breakers is proposed based on probabilistic neural network (PNN). This paper establishes PNN fault diagnosis model on the basis of analyzing the failure characteristics of high voltage circuit breaker to determine the characteristics of the signal. The model takes the collected feature data as the input of the network to get the class conditional probabilistic density function by Parzen window estimation method, then classifies characteristic data according to the Bayes decision rules. The simulation verifies that the probabilistic neural network fault diagnosis model has fast convergence, high fault diagnosis accuracy, easy to train and so on. Therefore, this method is an effective method of fault diagnosing and has good prospects.