The Design Of Reheating Furnace Control System And Research On Control Method For Furnace Temperature

Reheating furnace is one of the most important heating equipment used to reheat the slabs before rolling in steel rolling process, which also consumes a great amount of energy. It is a crucial goal to improve heating efficiency of reheating furnace and reduce the energy consumption as much as possible. And this goal is also meaningful for steel industry to reduce manufacturing cost and environmental pollution. So the research of reheating furnace modeling and optimal control is becoming more and more important.The reheating furnace is typically a complex industrial process, which almost owns all characteristics of complex systems, such as difficulty to establish an exact mathematic model, severe interference, non-linear, large time-delay and so on, Which results that the conventional PID control technique is difficult to achieve good control effect.Based on the automatic control system of Tang Steel Co.NO.1 walking beam reheating furnace and According to the requirement of the produce process of reheating furnace,this paper design loop control and computer process supervision of the whole system. We use the PLC of Simense to realize the control loop of temperature, pressure, flux and so on. Rely on the configuration software of WINCC to carry out the supervisory function of the material, parameter, alarm and so on.Combining with the practical characteristics of walking beam reheating furnace, we have done a research on building up a model and its application to the control of furnace temperature in this paper. At first, this paper identifies the model of the furnace temperature object through BP network and GA-BP. Comparing the two models and choosing the model based on GA-BP which is the better one as the control object. Then designing a kind of new controller based on fuzzy neural network. The controller has a distinct network structure. The learning ability of the neural network is used to revise the parameters of network to enhance the learning ability of the fuzzy control. At last, the system is simulated using the SIMULINK in MATLAB, and the result shows the evidence that compared to furnace temperature control system based on PID, the furnace temperature control system based on fuzzy neural network has a better performance in the following aspects:better following performance as the furnace temperature varying, less adjusting time, less overshoot, greater anti-interference ability and robustness.