Mechanical property control system for cold rolled steel sheet through locally weighted regression model

A new control method is proposed for controlling mechanical property in cold-rolled steel sheet production process. The proposed method is based on a locally weighted regression model, which is a type of Just-In-Time models. The mechanical property control system using the proposed method was developed and has been applied to actual plants. The proposed method determines the optimal heat treatment temperature from the information of the pre-processes which has actual process data. Significant effects on reducing mechanical property deviations and model maintenance load have been achieved in commercial production. The developed system has made contributions to improving yield and production rate.