Converter oxygen consumption prediction method based on grey prediction and neural network combined model

Abstract

A converter oxygen consumption prediction method based on grey prediction and a neural network combined model belongs to that technical field of oxygen prediction of converter in iron and steel enterprise. The oxygen consumption of a converter is predicted by analyzing the factors that affect oxygen consumption. Based on the nonlinear computational characteristics of Elman feedback neural network,the grey system theory can not only accelerate the convergence rate of artificial neural network prediction model, but also more effectively show the change law of oxygen consumption in converter, and improve the accuracy of prediction. By combining with the combined model of grey prediction and Elman neural network, the combined model has strong global searching ability, and optimizes the network at the same time, and adds appropriate operators, which enhances the ability of searching local optimal solution and global optimal solution, and can effectively improve the prediction accuracy, guide the steelmaking production to use oxygen reasonably, and improve the production efficiency.

Description

technical field [0001] The invention belongs to the technical field of converter oxygen forecasting in iron and steel enterprises, and in particular provides a forecasting method for converter oxygen consumption based on a combination model of gray forecasting and Elman neural network. Background technique [0002] Iron and steel enterprises are industries with high energy consumption and high emissions. Oxygen system is an indispensable energy equipment in the smelting process. The process of using oxygen in converter steelmaking is an important link in steel production, which directly affects the quality of the final molten steel. At the same time, the use of a large amount of oxygen in converter steelmaking has also brought about the problem of unreasonable consumption. Oxygen top-blown converter steelmaking is to blow high-pressure oxygen from the top of the converter to react with molten iron in the converter. Elements such as carbon, silicon, phosphorus, and sulfur in ...

AI Technical Summary

Problems solved by technology

[0006] The object of the present invention is to provide a kind of prediction method of the oxygen consumption of the converter based on gray prediction and Elman neural network combined model, has solved the problem of the oxygen consumption of the converter, can improve prediction accuracy effectively, guide steelmaking production to use oxygen rationally, improve Productivity

Images