TOWARDS PULTRUSION PROCESS OPTIMIZATION USING ARTIFICIAL NEURAL NETWORKS

The pultrusion process involves resin impregnated fibres and mats pass ed through a heated die, which cures the resin and produces the final product. When the process is examined in detail the number of paramete rs affecting the final product quality and process efficiency is very large. Parameters can range from the basic such as process speed, to t he more complex such as the crosslinking reaction of the resin in the die. More important than the individual parameters are the relationshi ps between these different parameters. Due to the complexity of the pr oblem, the more usual compact mathematical descriptions of the whole p rocess are not feasible in commercial manufacturing environments. This paper describes the use of artificial neural networks (ANNs) for pult rusion process modelling of real process data and their potential for intelligent machine control. It details how the use of ANNs can offer insights into the importance of the connections between the individual process parameters without having any 'knowledge' of the process. Suc h insights could lead to a greater understanding of the process, reduc ed product development time and increased manufacturing process capabi lity and efficiency. (C) 1998 Published by Elsevier Science S.A. All r ights reserved.