A PI control strategy using neural network adaptive wavelet is proposed in this paper to deal with the control of wind energy conversion systems (WECS). It is based on single layer feed forward neural networks with hidden nodes of adaptive wavelet functions controller and an infinite impulse response (IIR) recurrent structure. The IIR is combined with cascading to the neural network to provide double local structure, resulting in improving speed of learning. In the present paper Morlet, Shannon and Rational function with Second-order Poles (RASP1) mother wavelet functions are experimented for identification of unknown dynamics of WECS. Number of neurons (wavelets) in hidden layer, with the highest convergence speed is derived for neural network based on wavelets. The PI neuro controller is based on a certain model structure to approximately identify the system dynamics of WECS, and control its response. The proposed controller is studied in three situations: without noise, with measurement input noise and with disturbance output noise. An example of typical WECS case study is investigated to show the effectiveness and efficiency of the proposed algorithm, compared with PI controller based on multilayer perceptron (MLP) neural network.
Adaptive PI control, wavelets, wind energy conversion systems
