Research on Confirmation of Tension Leveller Basic Technological Parameters Based on Neural Network and Genetic Algorithm

摘要

Confirmation of tension leveller basic technological parameters is the most important factor of leveling strip. Up to now, most factories use experts’ experience to decide these parameters, without any established rule to follow. For better quality of strip, a valid method is needed to decide technological parameters precisely and reasonably. This paper uses a method, based on neural network and genetic algorithm, to solve this problem. Neural network has a good ability to extract rules from work process of tension leveller. Then using neural network, which has learned from a lot of working swatch, to be the evaluation of fitness, genetic algorithm could easily find the best or better technological parameters. At the end of this paper, examinations are given to show the effect of this method.