基于炼钢终点预测及收得率与终点碳温相关性分析的合金加入量计算研究

Research on Calculation of Alloy Addition Amount Based on Prediction of Steelmaking Endpoint and Correlation Analysis between Yield and Endpoint Carbon Temperature

合金元素的加入对于钢材的性能和质量具有重要影响,而合金元素的收得率则直接关系到炼钢过程的经济效益和资源利用效率。为了提高合金元素的收得率,基于炼钢终点温度、终点碳和合金加入量,优化计算合金元素收得率的模型。对比分析发现,收得率模型的准确率比机理模型和数据模型有很大提升,有利于提高炼钢工艺中合金元素的利用率。

The addition of alloying elements has a significant impact on the performance and quality of steel,and the yield of alloying elements is directly related to the economic benefits and resource utilization efficiency of the steelmaking process.The aim of this study is to use the XGBoost ensemble learning algorithm to predict the endpoint temperature and endpoint carbon content in the steelmaking process using the amount of molten iron and scrap added as features,and further calculate the corelation coeficients between endpoint temperature and yield,as well as the correlation coefficients between endpoint carbon and yield,and use the correlation coefficients to calculate yield.The calculated yield and known alloy grade parameters are used to calculate the amount of alloy added using an alloy mechanism model.At the same time,we also use XCBoost to predict silicon manganese alloys and silicon carbon alloys as alloy recommendation data models,as well as a mechanism model for calculating the recommended addition amount of alloys without using calculated yield;The comparative analysis of the three models found that the yield model had a significant improvement in accuracy compared to the other two models..