Answers are grounded in this paper and cite their sources.
The endpoint carbon content is one of the most important target in BOF (Basic Oxygen Furnace) steelmaking production. In this study, a real time carbon content prediction method is proposed for second blow period. Firstly, the traditional time-based exponential decarburization model is translated into an oxygen-based exponential decarburization model. Then, a valid data driven method named case-based reasoning is used to establish the key parameter in the decarburization model. To improve the precise of the model, a mutual information (MI) based variable selection algorithm is adopted to choose important variables as the condition attributes. Tests are implemented on a practical 180t converter in a steel plant to verify the proposed method. Results show that this real time carbon content prediction method can predict the endpoint carbon content precisely. Also, it can help the practical production on blowing endpoint control.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2017) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: