This paper deals with an input-output linearization for a nonlinear ice clamping system based on Peltier cells used in an innovative manufacturing system. For this model-based design, a third-order state-space model based on physical principles is derived. Unknown states as well as disturbances are estimated by a dual extended Kalman filter. Based on the estimated states and disturbances, an input-output linearization of the nonlinear system can be performed, with an asymptotically stable internal dynamics. Accordingly, an accurate tracking control is designed to follow a desired cold-side temperature even in the presence of disturbances. Meaningful simulation results are shown that point out the effectiveness of the proposed control approach.