According to metallurgical thermodynamics, the main factors on silicon content of molten steel in Masteel CSP process were analyzed within the compositions equilibrium of molten steel with top slags in ladle.

With fuzzy theory and stochastic theory,a new intelligent model is developed to approach the random nonlinear dynamic system of the change of silicon content in molten iron,where noise influencing the fuzzy prediction system is thoroughly considered.

In this paper,ANN(Artificial Neural Network)method is applied to predict the silicon content in molten iron,Several variables have been selected,and a three layers BP(Background Propagation)neural network model is set up.

Prediction of silicon content in hot metal based on EMD-SVM nonlinear combined model;

It is essential to predict silicon content in hot metal accurately for the purpose of controlling blast furnace under good operation condition.

It decomposes the time series of original silicon content in hot metal to different layers through wavelet analysis.

Based on the algorithm of Kolmogorov entropy presented by Grassberger and Procaccia, as the time series data of silicon content in molten iron of No.

In a period of time after putting the direct air cooling unit into operation,the silicon content in steam and water fails to reach the set standard,leading to scalling of silicon and silicate in the steam turbine,affecting the efficiency of unit.

Application of SVM to prediction of silicon content in hot metal;

The support vector regression based on the chaos particle swarm optimization algorithm for the prediction of silicon content in hot metal

A new approach to predict the silicon content in hot metal is based on Bayesian network.