Artificial neural network based speed controller for induction motors

This paper presents an intelligent indirect field oriented control (IFOC) technique for saturated induction motor (IM) drives in order to achieve high dynamic performance and wide operating range. The IFOC of IM drives has been traditionally carried out using linear proportional-integral (PI) controllers. As an IM is a nonlinear device due to the saturation phenomenon, conventional PI-IFOC methods provide poor performance, limited disturbance rejection capability and longer convergence time. The artificial neural network (ANN) has been widely used as an intelligent controller for nonlinear systems. ANN provides an adaptive learning ability to the controllers to better characterize the system dynamics for achieving accurate and fast responses. However, due to the iterative nature of neural networks, training of the ANN is excessively slow for saturated IM drives. In this paper, a novel neural network map (NNM) is developed to find input weights of the neurons; without the need for any recurrent training process. The proposed technique is applied on a 3-phase 4-pole 208V ¼ hp IFOC-IM drives. Both the simulation and experimental investigation have been carried out for the same motor drive, and the results are depicted and analyzed in this paper. A relative comparison between the PI controller and the proposed NNM based ANN controller indicates that the ANN mapping controller yields superior performance.