Abstract
Gas channelling is an uneven distribution of ascending gas through the burden layers in the blast furnace. This occurs due to the difference in permeability across the horizontal cross-section, which reduces the operational efficiency. When unattended, channelling can aggravate hanging and may further lead to burden slippage and chilling of the hearth, which is a nightmare for the blast furnace operator. The objective of this work is to develop a gas channelling assessment system based on statistical modelling by analysing the real-time data for parameters like stave temperature, pressure, gas utilisation ratio and uptake temperature. The criteria, which are indicative of the fluctuations in physical and chemical process parameters during gas channelling, are developed from process knowledge and theoretical understanding of the channelling with historical data of one of the blast furnaces of Tata Steel Jamshedpur, India. Optimum combinations of the criteria are found through fine-tuning of the statistical parameters and cross-validation with the preexisting events of gas channelling. The model is run on the test dataset, and the accuracy of the model is presented.
Get full access to this article
View all access options for this article.