Advancing wind energy: adaptive neural network control for optimized permanent magnet synchronous generators

Our contribution in this paper is to design an adaptive neural network (NN) based control of a permanent magnet synchronous generator in order to overcome the effect of structured and unstructured uncertainties and external disturbances, in addition to ensuring the stability of the system, the proposed robust control strategy compensates adaptively for significant uncertainties present in uncertain nonlinear systems. First, we present the vector control of PMSG model applying two tests: with and without constrains, and then, the neural network control with PI controllers. However, conventional controllers suffer from limitations due to the presence of these high uncertainties. Therefore, we aim to improve the efficiency of artificial neural control by using dynamic compensators instead of PI controllers. The estimated states are used as inputs to the neural network (NN). Simulations of the proposed control algorithm are conducted then compared to the previous controllers: vector control and neural network control with PI controllers. Furthermore, using dynamic compensators in artificial neural control achieved both efficiency and optimality. Results have been successfully confirmed via computer simulations using MATLAB.