Neural network learning approach of intelligent multimodel controller

The authors present a novel intelligent control scheme based on an artificial neural network. The proposed controller is based on the multimodel approach to improve the system performance of a complex control system of linear or nonlinear characteristics when it operates at various operating conditions. The multimodel control scheme depends on the multiple representation of a process using different models that generate the control signal needed to make the system follow a prescribed desired trajectory. The proposed controller is implemented by a multilayer neural network to locate the model that best represents the process and generate the desired control signal to drive the process along the desired path. The proposed controller is robust as it can accommodate high and sudden deviation from the prescribed trajectory. Simulation results are included to illustrate the potential of the controller developed