Real-time prediction method for carbon content and temperature of molten pool for converter steelmaking in whole process

Abstract

The invention belongs to the field of iron and steel metallurgy, and particularly relates to a real-time prediction method for carbon content and temperature of a molten pool for converter steelmakingin the whole process. The real-time prediction method includes the following steps that raw material data, smelting process data and molten pool carbon content and temperature information data of a plurality of historical heats are obtained; the obtained data and the raw material data are fitted and converted into functional data, both response variables and concomitant variables are selected asfunctional data models for training, a functional molten pool temperature prediction model and a functional molten pool carbon content prediction model are obtained, and converting real-time data aresent to the functional molten pool temperature prediction model and the functional molten pool carbon content prediction model to get predicted values. A model which can be used for predicting the carbon content and temperature of the molten pool in real time in the whole process of smelting is established by means of functional data analysis, the internal rules of the raw material data and the smelting process data are fully excavated, and the real-time prediction method has good adaptability to an actual production process and good accuracy and can replace traditional carbon content and temperature prediction methods.

Description

technical field [0001] The invention belongs to the field of iron and steel metallurgy, and in particular relates to a full-process real-time prediction model of carbon content and temperature in a melting pool of converter steelmaking. Background technique [0002] Converter steelmaking is one of the important links in the iron and steel production process. Its purpose is to smelt molten iron with a certain composition and temperature through continuous oxygen blowing through an oxygen lance and adding auxiliary materials into a steel whose final temperature and chemical composition meet the requirements of the steel type. molten steel. Therefore, providing a method that can predict the carbon content and temperature of the molten pool in real time during the blowing process can reflect the reaction status in the molten pool in real time, assist in intelligent control of oxygen blowing, feeding, etc., and provide a "one-button" intelligent refining process. Steel provides ...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the fact that the prediction method based on the reaction mechanism in the prior art has too many assumptions, poor adaptability to actual production, and poor prediction accuracy, the data-driven prediction method cannot provide real-time prediction of the whole process, and the reaction process is still in a "black box state". ", the application cost of sub-gun detection system is too high, the present invention provides a real-time prediction model of carbon content and temperature in the melting pool of converter steelmaking, realizes real-time and accurate prediction of carbon content and temperature in the whole process of smelting, and outputs carbon content and the real-time change trend of temperature to guide converter steelmaking production

Images