Mold level control based on fuzzy neural network

Mold level control is a crucial part in the continuous casting process. However, uncomfortable uncertainties and nonlinearities of this system lead considerable challenges and difficulties for a traditional PID controller. The model of AC servo electric cylinder, stopper flow characteristics, characteristics of the casting speed, mold and liquid level detection device were established. A new mold level controller based on fuzzy neural work was designed with a distinct network structure and on line parameters revising capability. Simulation results show that the new controller has better performance than the controller based on PID in the following aspects: better following performance for furnace temperature varying, shorter overshoot, shorter adjusting time and greater robustness.