Quantification and prediction of furnace cylinder activity based on LASSO-GWO-CNN hybrid model

Abstract

Blast furnace smelting environments are complex and characterised by multi-scale, non-linear and strong coupling, and it is often difficult for operators to detect changes in cylinder activity in a timely manner. Quantifying the cylinder activity is the basis for monitoring and improving the cylinder activity. Aiming at the traditional method of quantifying the cylinder activity, which relies heavily on a single empirical formula and is difficult to realise the prediction effect of the cylinder activity, this paper proposes a new method of quantitatively characterising the cylinder activity by combining the core dead material column temperature index and the dead material pile cleanliness index, which comprehensively takes into account the thermodynamic and kinetic characteristics of the cylinder, and is able to more accurately and comprehensively assess the state of the cylinder activity. Firstly, a new quantitative cylinder activity formula is set according to the combined index, in which the weights of the indexes will be gradually adjusted in the iterative process of the model, and the entropy weighting method is adopted for its operation; a hierarchical affiliation function is established, and the calculation of the affiliation is used to judge the degree of contribution of the new indexes to the active state of the furnace cylinder with different weights in order to assist in finalising the final weights of the indexes, and the final weights of the indexes are then validated through the analysis of the calculation examples. Afterwards, the rationality of the final weights and the effectiveness of the proposed quantisation method are verified through case analysis. Finally, the LASSO algorithm is used to filter the feature variables, and the Grey Wolf Optimisation (GWO) optimised Convolutional Neural Network (CNN) based cylinder activity prediction model is proposed. According to the results of the comparative validation between five different prediction models, the prediction accuracy of the GWO-CNN model reaches more than 90%, which indicates that the model has a higher prediction performance in predicting the furnace cylinder activity.