Modeling of Hot Rolling Industrial Process Using Fuzzy Logic

Steel making is known as a complex manufacturing industrial process. Automation of the process represents a challenge. Empirical mathematical modeling of the process was used to design mill equipment, ensure productivity and service quality. This modeling approach shows many problems associated to complexity and time consumption. Soft computing techniques show significant modeling capabilities on handling complex nonlinear systems modeling. In this paper, we explore the use of Takagi-Sugeno (TS) technique to develop fuzzy models for the Hot-Rolling industrial nonlinear process. We propose three models for the rolling force, torque and slab temperature. A set of rules and membership functions which represents the dynamical relationship between the input and output of these models shall be presented. The performance of the fuzzy models will be compared to the known empirical models for the hot rolling system. Experimental data measured from the Ereg̃li Iron and Steel Factory in Turkey shall be used for the verification of the model outstanding performance.