Application of Neural Networks and State-Space Averaging to dc/dc PWM Converters in Sliding-Mode Operation

A novel output feedback neural controller is presented in this paper for the implementation of sliding-mode control of dc/dc converters. The controller, which consists of a multilayer perceptron, has been trained in order to be robust for large variations of system parameters and state variables. Fast dynamic behavior is the other main advantage of the proposed controller, which allows realization of all beneficial features of the sliding-mode control technique. Other advantages of the controller are simplicity and low cost. Computer simulations have been carried out to investigate the effectiveness of the controller in voltage regulation for a relatively complex dc/dc converter topology of the Cuk converter. Simulation results confirm the excellent performance of the control system in response to large signal variations. In order to verify the simulation results, a controller prototype has been designed and built using analog components. The controller is applied to regulate the output voltage of the Cuk converter. Experimental results confirm the analytical and simulation achievements.