Multivariable control of a linear system using feed-forward neural networks

Artificial neural networks have been applied to several control problems. However, most of those are single input, single output systems. A multivariable control of a linear process is considered in this paper. The advantage of using neural networks lie in their ability to learn the process dynamics from the observations of the gross behaviour of the process, without a mathematical model. The linear process was controlled well using neural networks. The performance does not improve by using past values of the state variables.<>