基于分类回归树的高炉铁水硅含量预测模型

A Prediction Model of Hot Metal Silicon Content based on Algorithm of Classification and Regression Tree

针对高炉铁水硅含量的预测问题,作者探索出基于分类回归树算法的建模策略,为高炉炉温控制提供了新的可选思路.针对某高炉的在线生产数据,分别建立了分类回归树预测模型和支持向量机预测模型,并从命中率、均方根误差对模型的性能进行了分析.结果表明:分类回归树模型的预测精度整体优于支持向量机模型,尤其在炉况波动较大时预测效果较好.

A prediction model of hot metal silicon content is established by classification and regression Tree （CART） algorithm. Using the online production data of a blast furnace（BF）, the performance of CART model is compared with the support vector machine（SVM） model, from the hit rate of prediction and the root mean square error. The results show that the CART model can achieve better prediction performance. The research provides a new modeling framework for exploring temperature control in BF.