Optimization and Simulation of Quality Properties in Paper Machine with Neural Networks

| The nal quality of paper depends on many quality and process variables. It is very dii-cult to nd theoretical rules of the behavior of paper properties when variables depend from each other and when the interdepen-dencies are not linear. In this paper we present a neural network based system for estimating the nal quality of paper from process measurements. Inverse computation of the network model is used to nd a control action that will produce the desired quality. A separate self-organizing map is used to monitor the movement of the operating point of the process and to give a hint of the estimation error of the network.