The Study Of Furnace-Temperature Control Strategy Of The Reheating Furnace Based On Wavelet Neural Network Predictive Control

Predictive Control (PC) is a kind of new algorithm of computer control developed from industrial process control in the late 1970's. It adopts control strategy such as multi-step prediction, moving horizon optimization, and feedback correction, so it has good control effect, and is adapted to the complex industrial processes, which are difficult to set up mathematic model. Therefore it is taken seriously by the home and abroad project and control fields, and has been used successfully in such fields as petrochemical industry, electric power, metallurgy, machinery etc.. And it is a kind of promising algorithm of computer control.The slab reheating furnace is an important equipment used to reheat the slabs before rolling in hot steel rolling industry, and is also a large consumer on the hot strip rolling line, so it is very important to study the optimal control technology for the reheating furnaces. The aim of production of the reheating furnace is "good quality, high product, low consumption", and it must satisfy the desired temperature while slab leaves furnace, and also surface oxide of slab and energy consumption must be least. Because the reheating furnace is nonlinear, uncertain, large inertia, it is a complex nonlinear system. So the optimal control of the reheating furnace is a complex problem of control and optimum, traditional control strategy is difficult to achieve good control effect.With regards to the characteristics of nonlinear, large inertia and large time-delay system, this paper puts forward a predictive control strategy based on the wavelet neural network (WNN) to control the temperature of the reheating furnace based on a lot of related literature, combining with product practice.Main work is as follows:(1) According to the product practice of the reheating furnace and complexity of modern industry, the application and research situation of optimal control of the reheating furnace are elaborated. The problems in the reheating furnace's optimal control are also pointed out.(2) PC theories are studied. Firstly research situation and development tendency of PC are surveyed, secondly basic ideas are elaborated, at last Neural Network PC (NNPC) is studied, and its predictive model and control algorithm are introduced.(3) Modeling and predicting of nonlinear system based on WNN is studied. True data of the reheating furnace is simulated by MATLAB, and WNN is used to realize predicting furnace temperature. When modeling, production practice is considered and key problem of WNN modeling is studied.(4) Because the reheating furnace is one of complex nonlinear systems, PC based on WNN is proposed to control of the slab furnace in this paper. Firstly predictive model of the furnace-temperature is set up with WNN, which is used to predict output value, then feedback correcting is used to reduce the model predictive error resulted from uncertain factors of the system in order to get the relatively precise predictive value. Based on these, moving optimization is adopted according to the quadratic cost function, so that the future control sequence is got. MATLAB simulation results indicate that the control method is feasible, which lays the foundation for the application and dissemination of this method.