A novel energy feedback control method of flywheel energy storage system based on radial basis function neural network

A novel energy feedback control method based on radial basis function neural network (RBFNN) for flywheel energy storage system (FESS) driven by brushless DC motor (BLDCM) is proposed and applied in a wind power conversion. The RBFNN is trained off-line by adding new hidden neurons in the process of learning. Compared with the traditional PID controller, the proposed method can further reduce the ripple of DC bus voltage to improve the stability of output power when wind speed changes, which enhances the reliability and safety of the power system. A stand-alone wind energy generation system including a FESS driven by a BLDCM is simulated by Matlab/Simulink. The simulation results verify the effectiveness and correctness of the proposed method.