Theoretical control and experimental verification of carded web density Part III: Neural network controller design

A nonminimum phase property of a carded web system introduces difficulties for both classical control and neural network inverse model control. In thi s part of the series of papers, a two-stage artificial neural network model , including a controlled system learning scheme and controller design, is i llustrated by application to feedback control for uniformly carded web dens ity. A learning scheme is introduced using the dynamic model for general le arning of the neural network along with a modified error back propagation a lgorithm based on propagation of the output error through the plant. A perf ormance comparison is made of conventional control versus the artificial ne ural network control scheme, and the advantages of the new control strategy are effectively revealed by computer simulations.