Mold level variations in continuous casting are believed to be the main cause of surface defects in the final product. Although a PID controller is well capable of controlling the level under normal conditions, it cannot prevent large variations of mold level when a disturbance occurs in the form of nozzle unclogging. In this paper, dual controller architecture is presented, a PID controller is used as the main controller of the plant and an adaptive neuro-fuzzy controller is used as an auxiliary controller to help the PID during disturbed phases. The control is passed back to the PID controller after the disturbance is being dealt with. Simulation results prove the effectiveness of this control strategy in reducing mold level variations during the unclogging period.