Abstract: The rolling force model is a foundation model of the process control system of a tandem cold rolling mill. Deformation resistance and friction factor have important effect on the prediction precision of rolling force. A parameter self-adaptive method was used to improve the prediction precision. During self-adapting process for the rolling force model, deformation resistance was regarded as the common property of each stand, and each stand decides its deformation resistance according to its absolute deformation grade. On this condition, friction factor was regarded as the special property of each stand, and different coefficients were given to the mathematical model for friction factor of each stand. This self-adaptive method can correct deformation resistance and friction factor at the same time. It is proved to be useful to improve the prediction precision of rolling force by practice.