The Application Of Neural Network Based On Adaptive Genetic Algorithm To Predict Temperature Of Blast Furnace

Iron and steel industry is the pillar of the national economy and blast furnace is very important for iron and steel industry. The temperature of blast furnace affects the normal produce and stabilization of blast furnace and the quality of production directly, which is an important guideline of estimating condition. In the natural condition, the silicon content of molten iron becomes direct ratio with the temperature. Because the silicon content of molten iron can indirectly reflect the change of temperature, this task choose the model of the silicon content of molten iron as the temperature model of blast furnace.In this paper, adaptive genetic algorithm and BP neural network are combined, AGA-BP network model is introduced This model makes use of global optimization of adaptive genetic algorithm and local optimization of BP neural network to modify the power value of network. The problem of slow convergence speed and being prone to converge to minimum are solved for the best neural network. In this paper, the model is applied to predict temperature of blast furnace, the testing and simulating results are satisfactory. The numerical results of AGA-BP network model show that the prediction precision is improved and the iterative numbers are much less than the normal BP network model and improved BP network model.