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 study, three kinds of steels are manufactured by varying the rolling conditions, and their microstructures are analyzed. Tensile and Charpy impact tests are performed at room temperature to investigate the correlation between microstructure and mechanical properties. In addition, heat affected zone(HAZ) specimens are fabricated through the simulation of the welding process, and the HAZ microstructure is analyzed. The Charpy impact test of the HAZ specimens is performed at -40 oC to investigate the low temperature HAZ toughness. The main microstructures of steels are quasi-polygonal ferrite and pearlite with fine grains. Because coarse granular bainite forms with an increasing finish rolling temperature, the strength decreases and elongation increases. In the steel with the lowest reduction ratio, coarse granular bainite forms. In the HAZ specimens, fine acicular ferrites are the main features of the microstructure. The volume fraction of coarse bainitic ferrite and granular bainite increases with an increasing finish rolling temperature. The Charpy impact energy at -40 oC decreases with an increasing volume fraction of bainitic ferrite and granular bainite. In the HAZ specimen with the lowest reduction ratio, coarse bainitic ferrite and granular bainite forms and the Charpy impact energy at -40 oC is the lowest.