Induction Machine Current Loop Neuro Controller Employing a Lyapunov based Training Algorithm

This paper presents a practical implementation of a continually online trained artificial neural network (COT-ANN) employing a Lyapunov based training algorithm. The proposed Lyapunov based training algorithm ensures stability and a global minimum for the ANN weights. The COT-ANN is used to control a PWM based current loop in an induction machine. Real time simulations employing a DSP based test bench are used to test the validity of the algorithm and the results are verified by a practical implementation of this controller.