Improvement of the Blast Furnace Viscosity Prediction Model Based on Discrete Points Data

Abstract

Viscosity is considered to be a significant indicator of the metallurgical property of blast furnace slag. An improved model for viscosity prediction based on the Chou model was presented in this article. The updated model has optimized the selection strategy of distance algorithm and negative weights at the reference points. Therefore, the extensionality prediction disadvantage in the original model was ameliorated by this approach. The model prediction was compared with viscosity data of slags of compositions typical to BF operations obtained from a domestic steel plant. The results show that the approach can predict the viscosity with average error of 9.23 pct and mean standard deviation of 0.046 Pa s.