Due to the nonstationarity, complex transmission path, high system noise and serious modulation phenomenon of wind turbine gearbox vibration signal, the conventional spectrum analysis method was difficult to identify the fault location of gearbox. In order to solve the above problems, a fault diagnosis method of wind turbine planetary gearbox based on synchronous extraction（SET）and vold-Kalman filter（SEV） was proposed in this paper. This paper first describes the principle and process of the proposed method. The vibration signal of the generator bearing was extracted by the local energy maximum method based on SET（LMS）, and then the instantaneous frequency was accurately extracted based on the ward Kaman filter to obtain the complete phase information. Finally, the detailed fault location information of wind turbine gearbox was obtained by order analysis. Simulation and experimental analysis verify the effectiveness of the proposed method.