An neural network based adaptive control for liquid level of molten steel smelting non-crystalloid flimsy alloy line

A new method based on neural network for controlling the liquid level of molten steel smelting non-crystalloid flimsy alloy line is presented. The improved BP neural network is used to adjust the parameter of the PID controller. The designed system retains not only the good robustness to the fluctuant of system parameters and effectiveness of the neural network, but also the universality of the PID controller. The result of simulation shows the availability for application and good dynamic characteristics of the controller. We conclude that the controller can satisfy the demand for the liquid level control of molten steel.