In light of the problem that the pitch angle output changes caused by the pitch system faults of the wind turbine, an inverter predictor approach is proposed to diagnose the fault of the pitch actuator based on the Linear Parameter Vary (LPV) model of pitch system of the wind turbine. Firstly, the hydraulic pressure is selected as the scheduling variable and the nonlinear model of pitch system of the wind turbine is transformed into LPV model, making the model more precise. Secondly, considering the boundary problem described by model uncertainties, the interval prediction algorithm is introduced. Then the fault is judged according to whether the output of the pitch angle is in the range upper and lower bound. Finally, the proposed algorithm is simulated in the wind turbine system. The simulation results show that the proposed algorithm can estimate the pitch actuator fault well and the robustness of the fault diagnosis is improved. This work is supported by National Natural Science Foundation of China (No. 61572237).