Journal
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
Volume 14, Issue 2, Pages 1286-1296Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TASE.2016.2538560
Keywords
Blast furnace hearth; electromotive force (EMF); filtering; forecasting; liquid level; nonlinear systems; time-delay neural network (TDNN); time-series analysis
Categories
Ask authors/readers for more resources
The extraction of molten iron and slag in the liquid phase from the lower part of a blast furnace (hearth) is usually accomplished according to operational experience and involves a high degree of uncertainty, mainly because the liquid level cannot be directly measured. This study presents a methodology for obtaining multistep models to forecast the hearth liquid level by measuring a voltage generated on the blast furnace shell, which is strongly correlated with the hearth liquid level. The results show that this electrical signal is a nonstationary and nonlinear time-series that, after appropriate treatment, can be represented by a time-delay neural network (TDNN) model. Some comparisons are made with linear time-series models represented by an autoregressive moving average model and a seasonal autoregressive integrated moving average model, and the results indicate that the TDNN model provides better forecasting performance up to one hour ahead. Note to Practitioners-This work was motivated by the need for better knowledge regarding the liquid level in a blast furnace hearth because this information affects the strategy of the opening and closing of tapholes in the blast furnace and, consequently, the production control and operational quality. Due to the difficulties of measuring the liquid level in the hearth directly, a system was installed that uses a voltage generated in the hearth shell as a liquid-level sensor in the hearth. In this study, the analysis and treatment of this signal is performed by achieving a stationary, nonlinear signal strongly correlated with the level of molten iron and slag inside the blast furnace hearth. A mathematical model that represents this signal was developed and implemented online in the blast furnace digital control system to enable forecasting of the liquid level up to one hour ahead. This computational tool aids operators and engineers in deciding in advance the instants to open or close the tapholes, thereby increasing safety and financial gains.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available