A design of model driven cascade PID controllers using a neural network

Since most process systems have nonlinearities, it is necessary to consider the design of schemes to deal with such systems. In this paper, a new design scheme of PID controllers is proposed. This scheme is designed based on the IMC, which is a kind of the model driven controllers. The internal model consists of the design-oriented model and the full model. The full model is designed by using the neural network. The inner PID control system is first constructed for the augmented system, which is composed of the controlled subject and the internal model, and this control system is designed by the pole-assignment method. Furthermore, the outer PID controller is designed in order to remove the steady state error. Finally, the effectiveness of the newly proposed control scheme is numerically evaluated on a simulation example.