A predictive modeling for blast furnace by integrating neural network with partial least squares regression

The prediction of the important running variables of blast furnace (BF) has been a major study subject as one of the most important means for the monitoring BF state in ferrous metallurgy industry. In this paper, a prediction model for BF by integrating a neural network (NN) with partial least square regression (PLS) is presented. The selection of influencing operational parameters of BF on parameter to be predicted is explored according to the minimization of residuals based on the theory of path analysis. The selected influencing parameter data series are processed as the inputs of the prediction model. In order to validate this prediction model, silicon content in hot metal of BF is taken as the parameter to be predicted. The model is trained and evaluated with industrial data, and the results show that it works well. Further modification of this prediction model is also analyzed to improve its application in the industry.