s:The statistical characteristics of hot metal silicon data were concluded for Xianggang BF2 which was fed with raw materials of poor qualities and equipped with insufficient measuring sensors.

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.

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.

Prediction model of Blast Furnace Hot metal Si-content based on BP Neural network’s study;