A novel sliding-mode fault-tolerant active control strategy for wind energy conversion system is proposed. For actuator fault of wind energy conversion system, predictive control theory and iterative learning algorithm are introduced to design the fault observer. Within the preset optimizing time span, the introduced virtual fault is adjusted by the difference between the fault observer output and the actual system output through repetitive iteration, so that it can effectively fit the actual value of the actuator fault, and the structure of the sliding fault-tolerant controller is adjusted real-time according to the fault observed value. When there is no fault, the fault observed value is zero and the system is running stably under the control of the sliding-mode controller. When actuator failure occurs, sliding fault-tolerant controller is adjusted real-time on the basis of fault observed value, and the hyperbolic tangent function is used to substitute the sign function to eliminate chattering. Experimental results show that good fault tolerance ability of the system under the control of sliding-mode fault-tolerant controller can be guaranteed, improving the efficiency of maximum wind energy capture for wind energy conversion system. © 2015, Editorial Department of Control Theory & Applications South China University of Technology. All right reserved.