Recurrent neural networks-based multivariable system PID predictive control

Abstract

A nonlinear proportion integration differentiation (PID) controller is proposed on the basis of recurrent neural networks, due to the difficulty of tuning the parameters of conventional PID controller. In the control process of nonlinear multivariable system, a decoupling controller was constructed, which took advantage of multi-nonlinear PID controllers in parallel. With the idea of predictive control, two multivariable predictive control strategies were established. One strategy involved the use of the general minimum variance control function on the basis of recursive multi-step predictive method. The other involved the adoption of multi-step predictive cost energy to train the weights of the decoupling controller. Simulation studies have shown the efficiency of these strategies.