A DESIGN OF MULTILOOP PID CONTROLLERS WITH A NEURAL-NET BASED DECOUPLER

Abstract

In process industries, PID control schemes have been widely used due to their simple structures and easiness of comprehending the physical meanings of control parameters. However, the good control performance cannot be obtained by simply using PID controlschemes, since most processes are considered as nonlinear multivariable systems with mutual interactions. In this paper, a design method of multiloop PID controllers neural-net based decoupler is proposed for nonlinear multivariable systems with mutual interactions. The proposed method consists of a decoupler given by the sum of a static decoupler and a neural-net based decoupler, and multi-loop PID controllers. Finally, the effectiveness of the proposed control scheme is evaluated on the simulation examples.