Application of Bayesian network to tendency prediction of blast furnace silicon content in hot metal

Authors:
Wenhui Wang
Affiliations:
Basic Department, Zhejiang Water Conservancy and Hydropower College, Hangzhou, China
Venue:
LSMS'07 Proceedings of the Life system modeling and simulation 2007 international conference on Bio-Inspired computational intelligence and applications
Year:
2007

Citing 3
Cited 0

Introduction to Grey system theory

The Journal of Grey System
Causality: models, reasoning, and inference

Causality: models, reasoning, and inference
Bayesian Networks for Data Mining

Data Mining and Knowledge Discovery

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new method for predicting the change tendency of silicon content in hot metal based on Bayesian networks. Firstly, some important factors that affect silicon content are selected out using grey relationship analysis (GRA). Secondly, a Bayesian network (BN) model is constructed to predict silicon content in hot metal based on the causal relationship of the factors. The model shows good performance due to the high percentages of prediction hitting the target, and can help blast furnace (BF) foreman acquaint himself with the status of BF.