The forcast of slag addition during the ladle furnace (LF) refining process based on LWOA-TSVR

Abstract

LF refining slag addition is an important factor affecting the end steel composition of the refining process. In order to better control the end steel composition and improve the production efficiency, this paper uses an improved whale optimization algorithm to optimize twin support vector machines to establish a LF refining slag addition prediction model. The LWOA-TSVR model is trained and tested by historical data, and the model has a strong generalization capability and high accuracy. Applying the model to the industrial production process, it was verified that the model has high prediction accuracy and can provide guidance for the actual refining production process of LF refining slag addition, which is important for the control of the end steel composition.

Keywords

• LF
• refining
• slag addition
• prediction model
• validation