In this study, a fuzz system for more accurate control of rolling force set-up was developed to improve the thickness control at the finishing rolling units in hot rolling. Through the analysis of real production data it was found that the accuracy of the rolling force determined from the finishing mill set-up(FSU) model dominantly governed the thickness uniformity in rolled plates at the front. Based on this analysis, the major processing parameters mostly relevant in determining the measured load data in the FSU model were selected and used as input and output variables for the currently developed fuzzy system. The input and output variables of the developed fuzzy rules were determined from a correlation study of the hot rolling process data. A linear function between rolling force and the chosen process variables was introduced in the present study for development of the fuzzy rules in the, finishing mill stands such as F4, F5, F6, and F7. The coefficients involved with the fuzzy rules for these stands were determined by applying the regression method to treat the production data. According to the simulation results in the cases with large thickness errors, it was found that the developed fuzzy system produced better load predictions at the finishing mill, especially at the last 7th stand, than the load values provided by the FSU model.