A new method for evaluating the state of a circuit breaker based on the occurrence time of extreme point of vibration signal and the support vector machine（SVM） algorithm is proposed. The method takes the charged moment of tripping/closing coil as the zero time

and takes the occurrence time of extreme point of vibration signal as the characteristic parameter to establish a state evaluation model of circuit breaker by making use of the support vector machine optimized by particle swarm optimization. Five failures of circuit breakers are simulated

and the results show that the proposed method is suitable for state evaluation of vacuum circuit breaker.