Control of nonlinear multivariable systems using a dynamic neural network

A complex control system, in general, consists of two or more independently designed and mutually affecting subsystems. Proper coordination and control of multiple subsystems is responsible for the overall functioning of the system. This necessitates the development of control schemes for multivariable systems. This is a formidable task; more so if the systems involved are nonlinear with unknown dynamics. Because of their parallelism, functional approximation and learning capabilities, artificial neural networks can be effectively employed to control multivariable systems. The intent of this paper is to describe a neural network called the dynamic neural processor (DNP), and to use this structure to control nonlinear multivariable systems. The DNP is a dynamic neural network developed based on the concept of neural subpopulations which is in sharp contrast with the conventionally assumed structure of artificial neural networks