Predictive functional controller for HAWE generators based on neural network

The kite generator is a kind of high-altitude wind energy (HAWE) generation. The control systems play a key role in the stable and efficient operation of kite generators. In order to solve the difficulties in accurate modeling of non-rigid kite and real-time problems encountered when nonlinear model predictive control methods are applied to kite generators, a kind of predictive functional controller based on neural network is presented in this paper. With BP network used as predictive model for kite generators of carousel structure, the maximum generation controller is designed for kite generators using PFC principles. The implementation of closed loop control system is given, and its correctness and effectiveness are validated by simulation results, which also show that the PFC algorithm can meet the needs for speed of computation.