In this study, a new model using artificial neural networks is proposed to improve the thickness error between the plates, which occurs when the rolling conditions change a lot during the thick rolling. The model was developed by using Python, and the input values are the change in the finish rolling temperature between the plates, the change in target tensile strength, the change in target thickness, and the change in rolling force. The new model is 31.76% better than the existing model based on the standard deviation value of the thickness error. This result is expected to reduce quality costs when applied to online models at actual production sites in the future.

In this work, measured data from thickness gauge behind of the finishing mill stand was used for increasing accuracy of thickness control in plate rolling process. The Automatic Gauge Control (AGC) system of the mill could control roll gap for the remaining rolling passes based on the difference between measured and calculated thickness. This work was possible with some modification in software product system to use measured data without additional installation of equipment. As a result, the accuracy of thickness has been increased up to 31%. The accuracy of thickness control was defined as a standard deviation of the differences between target and measured final thickness of average.

결정립 미세화는 강도와 인성을 동시에 향상시킬 수 있는 유일한 방법이다. 제어압연과 가속냉각은 공정 중에 재결정과 결정립 조대화 거동을 조절함으로써 기계적 성질을 향상시키는 효과적인 방법으로 알려져 있으며, 반복열처리에 의한 반복상변태는 결정립 미세화 방법 중의 하나이다. 본 연구에서는 제어압연과 반복열처리를 복합 적용하여 그 효과를 관찰하였다. Mo 첨가효과와 공정변수의 효과를 관찰하기 위해 Mo이 첨가된 저탄소강 시편을 준비하여 Gleeble로 가공열처리 모의실험을 하였다. Mo첨가는 결정립 조대화 온도를 상승시키고, 오스테나이트 재결정을 억제하는 효과를 나타내었다. 오스테나이트 결정립 미세화에 가장 효과적인 공정조건은 반복 열처리 제어압연을 두번 실시하는 것이고, 첫번째보다 두번째 압연율을 더 크게 하는 것이었다