Neural Networks for Quality Prediction in Papermaking, 2001 Process Control, Electrical & Info. Conference Proceedings

Peter J. Edwards, Alan F. Murray--This paper describes the application of artificial neural network techniques to the papermaking industry, particularly for the prediction of paper "curl". Paper curl is a common problem and can only be measured reliably off-line, after manufacture. By providing the machine operator with a tool able to predict curl, adjustments can be made to the machine and paper characteristics to maximize yield and reduce customer dissatisfaction. Here therefore we predict, from characteristics of the current reel, (a) whether the paper curl will be acceptable and (b) the level of curl. For both cases we include confidence measures. In addition we discuss other areas where we are seeking to apply neural network technology. The techniques described in this paper are widely applicable to industry where direct prediction of a quality measure and its acceptability are desirable, with a clear indication of prediction confidence.