Zhou WANG, Jian CHANG
This study analyzes the factors affecting end-point manganese content in the BOF steelmaking process, aiming to develop a reliable predictive model. A multiple linear regression model was constructed based on actual production data to predict the end-point manganese content. To enhance prediction accuracy, an artificial neural network (ANN) approach was employed, resulting in the establishment of a backpropagation (BP) neural network model. Furthermore, a combined genetic algorithm and BP neural network model (GA-BP) was developed, integrating the strengths of both methodologies. Comparative validation of these models demonstrated that the GA-BP neural network model achieved the highest prediction accuracy, with hit rates of 90% and 84% for predictive errors within ±0.03% and ±0.025%, respectively. The results indicate that the combined GA-BP model outperforms the traditional regression and BP models, providing a highly accurate and beneficial tool for optimizing manganese content prediction in actual steel production processes.
@article{d471d8ef-6764-4ab6-bb59-9abfb1a8d083,
title={054 Prediction Model of End point Manganese Content for BOF Steelmaking Process},
author={Zhou WANG and Jian CHANG},
year={2026},
language={en}
}TY - JOUR TI - 054 Prediction Model of End point Manganese Content for BOF Steelmaking Process AU - Zhou WANG AU - Jian CHANG PY - 2026 LA - en ER -
This paper addresses the challenge of assessing the feasibility of wind power plant projects at sites with insufficient or no local historic wind data
Important advances in electrochemical engineering technology over the last three decades have fostered the development of a lternative methods to alle
Increasing volumes of waste printed circuit boards from obsolete electronic equipment posed escalating environmental risks and resource losses due to
The leachability tests for manufacturing scrap TV boards (STVB) have indicated the release of metals beyond the limit levels with potential problems f