Synchronous Learning Algorithm with Gain Scheduling for Both Time-variant and Rolling Conditional Factor

摘要

A modeling error consists of two factors; one is a time-variant factor like the influence of roll wear, and the other is a factor of rolling conditions like the size characteristic. If both factors are not distinguished when learning the modeling errors and when adaptation of a setup control for the following rolling piece are executed, the appropriate compensation is not obtained, therefore accuracy gets worse. We propose the synchronous learning algorithm for both factors with learning gain scheduling to improve learning efficiency. Finally, the application simulation using hot-rolled width data shows that standard deviation for modeling error can be reduced 20% compared with the conventional method.