Current controller for induction motor using an Artificial Neural Network trained with a Lyapunov based algorithm

This paper presents the use of a training algorithm based on a Lyapunov function approach applied to a stator current controller based on a state variable description of the induction machine plus a reference model. The results obtained with the proposed controller are compared with a previously reported method based on a Nonlinear Auto-Regressive Moving Average with eXogenous inputs (NARMAX) description of the induction machine. The proposed Lyapunov based training algorithm is used to ensure convergence of the weights towards a global minimum in the error function. Real time simulations employing a DSP based test bench are used to test the validity of the algorithms and the results are verified by a practical implementation of these controllers.