Variable selection and forecast method of silicon content in molten iron of blast furnace

Abstract

The invention discloses a variable selection and forecast method of the silicon content in molten iron of a blast furnace. According to the method, blast furnace process parameters of a prediction model of the silicon content in molten iron of a blast furnace are used as input variables; after normalization preprocessing is performed on sample data of the input variables, variable selection is performed on the sample data of the input variables by using a multivariate correlation analysis method and a Spearman rank correlation analysis method, to remove the correlation between production process parameters; and a support vector machine algorithm is used to establish the forecast model of the silicon content in molten iron of the blast furnace, and particle swarm optimization algorithm is introduced to optimize model parameters. The variable selection and forecast method of the silicon content in molten iron of a blast furnace has universal applicability in forecasting the silicon content in molten iron during smelting of a blast furnace, and can achieve desirable forecast accuracy and improve the forecast hit rate of the silicon content in molten iron.

Description

technical field [0001] The invention relates to a variable selection forecasting method for the silicon content of molten iron in a blast furnace. Background technique [0002] Blast furnace production is a complex chemical, kinetic, and thermodynamic process under closed conditions, and is a complex, highly coupled nonlinear system. Maintaining a reasonable furnace temperature is one of the key factors for the stable production of blast furnaces. During the smelting process, if the furnace temperature is controlled within the normal range, the blast furnace will run smoothly. If the furnace temperature control fluctuates abnormally, and the stroke is "overheated" or "overcooled", it is easy to induce furnace condition failure. The quality of furnace temperature control directly affects the fluctuation of furnace conditions, and the state of furnace conditions determines the control mode of furnace temperature. Therefore, the difficulty of comprehensive automatic control ...

AI Technical Summary

Problems solved by technology

At present, the models for predicting the silicon content of blast furnace hot metal based on data-driven ideas mainly include autoregressive models, neural network models, nonlinear time series analysis models, fuzzy models, Bayesian network models, partial least squares models, and support vector models. Most of these models use all relevant variables collected from blast furnace data as independent variables when predicting the silicon content of blast furnace hot metal. Although the variable value as an independent variable can make full use of the rich data characteristics of the blast furnace, it also brings in a lot of noise, which provides a great obstacle to the prediction accuracy of the silicon content.

Images