It is necessary to monitor the operation state of the High voltage circuit breaker (HVCB) and analyze the fault by the related signal, the fault of HVCB operating mechanism is closely associated with coil current, mechanical vibration and other factors. The method of fault diagnosis for HVCB based on Hilbert-Huang transform (HHT) and support vector machine is proposed to analyze faults accurately and quickly in high voltage circuit breakers, determining the characteristic and category of the fault. HVCB testing platform based on LabVIEW and acquisition equipment gain the signals of mechanical vibration. The model of fault diagnosis for HVCB is established by using support vector machine (SVM). The data are trained by SVM, thus the type of fault can be clearly determined. The method can obtain better diagnosis results, it is also suitable for fault diagnosis for HVCB.