<p>In view of the problems of time-varying disturbance and model parameter variation in the practical application of direct-driven wave power generation system, an adaptive control strategy based on Radial Basis Function (RBF) neural network is proposed. By analyzing the hydrodynamic model of a direct-drive wave energy converter (WEC), the maximum power capture condition is obtained by using the equivalent circuit method. The nonlinear state-space model of direct-drive wave power generation system is constructed based on the idea of maximum force per ampere (MFPA) control. Through the coordinate transformation and state feedback, the canonical form is achieved. An adaptive state feedback tracking controller is designed, in which RBF neural network is used to approximate the unknown function in the controller. The effects of time-varying disturbance and model parameter variation on the system are suppressed effectively. The system is in the desired operation state, and then maximum power tracking control is achieved. Simulation results show that the proposed control strategy effectively improves the transient and steady-state tracking performance, and has good fault-tolerant and anti-disturbance robustness.</p>