Perspective and prediction of the rule of high temperature melting of SiO2 via visual analysis

Abstract

This paper focuses on how to see through the melting behavior of solid iron tailings in molten blast furnace slag and take a new non-contact visual analytical method to predict its melting law. The optimized convolution neural network (CNN) is used to track the moving target in charge coupled device (CCD) camera system efficiently and accurately, and the melting behavior of SiO2 is described by coordinate translation transformation theory. Hierarchical agglomerative clustering (HAC) and delaunay triangulation were used to extract the characteristic parameters of the melting process of SiO2. The prediction model of the melting rate of SiO2 at high temperature was established by least square fitting (LSF) and dimensional analysis, and compared with the actual melting rate of SiO2 obtained by experiments. The results show that the melting characteristics of SiO2 at high temperature are in accordance with certain function rule. The performance of optimized CNN in terms of processing time and the accuracy are significantly improved, and the fusion rate prediction model of SiO2 is verified by 100% accuracy. It provides theoretical support and model basis for the improvement of slag cotton preparation technology.