Using Machine Learning for Robust Target Prediction in a Basic Oxygen Furnace System

Juhee Bae,Gunnar Mathiason,Yurong Li,Niklas Kojola,Niclas Ståhl

doi:10.1007/s11663-020-01853-5

Juhee Bae, Gunnar Mathiason + Show 3 more

Open Access

https://doi.org/10.1007/s11663-020-01853-5

Copy DOI

Abstract

The steel-making process in a Basic Oxygen Furnace (BOF) must meet a combination of target values such as the final melt temperature and upper limits of the carbon and phosphorus content of the final melt with minimum material loss. An optimal blow end time (cut-off point), where these targets are met, often relies on the experience and skill of the operators who control the process, using both collected sensor readings and an implicit understanding of how the process develops. If the precision of hitting the optimal cut-off point can be improved, this immediately increases productivity as well as material and energy efficiency, thus decreasing environmental impact and cost. We examine the usage of standard machine learning models to predict the end-point targets using a full production dataset. Various causes of prediction uncertainty are explored and isolated using a combination of raw data and engineered features. In this study, we reach robust temperature, carbon, and phosphorus prediction hit rates of 88, 92, and 89 pct, respectively, using a large production dataset.

Highlights

THE Basic Oxygen Furnace (BOF) process for the decarburization of hot metal in primary steel making is very complex from a process control perspective since it takes place at very high temperatures and includes turbulent multi-phase mass flow and chemical reactions
For a subset of algorithms, we further evaluate the hit rates of the combinations of different feature groups (Table 3)
We find from the results of Experiment 1 (Section V–A) that certain machine learning (ML) algorithms perform better than others

Summary

Introduction

THE Basic Oxygen Furnace (BOF) process for the decarburization of hot metal in primary steel making is very complex from a process control perspective since it takes place at very high temperatures and includes turbulent multi-phase mass flow and chemical reactions. To reduce the carbon content through oxidization, oxygen is blown onto the heat by supersonic injection through a vertical lance. Fluxes such as lime and calcined dolomite are added to form a slag and remove impurities. During heat design and during the oxygen blow period, operators are usually assisted by some computer-based process guidance system. Such systems typically propose process parameters and operator actions for every heat

Objectives

Methods

Results

Conclusion