A neural network based RLS parameter estimation algorithm and its application in predictive control

A method which uses neural networks to improve the performance of recursive least squares (RLS) algorithms in estimating the parameters of nonlinear processes is presented. Its application in a process gain-adaptive algorithm is described. This method uses neural networks to learn the parameter updating process of standard RLS algorithms and to relate these parameters to the operating conditions. Experimental results when using this method in modeling and control of a heat transfer process of an air-handling plant are reported and show great potential.<
>