DEVELOPMENT OF FUZZY CONTROL ALGORITHM FOR SHAPE CONTROL IN COLD-ROLLING

In this study, fuzzy theory is introduced in controlling the strip shape in cold rolling. Fuzzy control algorithm is developed based on the production data and operational knowledge. The cold-rolled products are characterized into several types based on its irregularity, 'edge wave', 'center buckle', 'W-type', and 'M-type'. The developed fuzzy controller calculates for each type of irregular strip shape, the change of bender forces of work and intermediate rolls, using fuzzy rules and fuzzy inference. To simulate the continuous shape control, the fuzzy controller is combined with the emulator which is developed using neural network. The developed fuzzy controller and emulator simulate the cold rolling process until the irregularities converge to the tolerable range to produce a uniform cross-sectional shape. The results from the various simulations demonstrate that the developed fuzzy control algorithm works for various types of irregular cross-sectional shapes as well as simple shapes.