基于机器学习算法的焦炭质量预测模型开发  

Development of Coke Quality Prediction Model Based on Machine Learning Algorithm

作　　者：孙晴亮 王军 李杰 张晓萍 胡俊 Sun Qingliang;Wang Jun;Li Jie;Zhang Xiaoping;Hu Jun(Ma'anshan Iron&Steel Co.Ltd.,Ma'anshan Anhui,243011,China)

机构地区：[1]马钢股份公司,安徽马鞍山243011

出　　处：《安徽冶金科技职业学院学报》2024年第3期1-3,6,共4页Journal of Anhui Vocational College of Metallurgy and Technology

摘　　要：焦炭质量预测对于焦化企业的配煤炼焦质量控制具有重要意义。本文使用某焦化企业近两年的质量数据,结合炼焦理论和特征工程筛选特征,以及生产工艺相关参数,对焦炭质量的各指标建立预测模型;同时,对比多个机器学习模型在数据集上的预测效果,确定了最佳预测模型。结果表明,本文模型对该厂的焦炭质量预测效果较好,能够有效指导炼焦生产。Coke quality prediction is meaningful to the coal blending and coking quality control of coke production facilities,In this study,recent two-years coal quality data of a coking plant is used,combining with relative parameters of production process,to build prediction model for several coke quality targets.Both coking theory and feature engineering methods are used to select features,along with prediction results of multiple machine learning models compared on the dataset,to determine the most predictive model.The result shows that,the model is predictive of the coke quality of the coking plant.

关 键 词：焦炭质量 特征工程 机器学习 预测模型 

分 类 号：TQ520.6[化学工程—煤化学工程] TP181[自动化与计算机技术—控制理论与控制工程]