二元线性回归法预测焦炭强度的研究  

Research on Prediction of Intensity of Coke with Binary Linear Regression Method

作　　者：高志芳[1] 单晓云[2] 朱书全[1] 李洪波[2] 

机构地区：[1]中国矿业大学(北京),北京100083 [2]河北理工大学,河北唐山063009

出　　处：《选煤技术》2006年第6期1-3,共3页Coal Preparation Technology

基　　金：河北省科技攻关项目(编号:04212205);河北理工大学科学基金项目

摘　　要：选取决定焦炭质量的主要指标———挥发分和粘结指数,运用二元线性回归的方法预测焦炭的强度。模型采用开滦集团单种煤及其配合的混煤和相应焦炭的数据,研究结果表明,运用此模型可以有效控制混煤的挥发分和粘结指数,保证焦炭的质量,检验配煤的合理性,以达到合理指导配煤炼焦的目的。Intensity of coke is predicted by use of binary linear regression method through selection of volatile and binding property as a main index for determining of coke quality.The data used in model is from single coal of Kailuan Group blending coal and its corresponding coking production.The research indicates that the model can be used to effectively control volatile matter and binding index of blending coal so as to ensure coke having required quality and to check the reasonability of coal blending for the aim of directing process of coking blended coal.

关 键 词：线性回归 焦炭强度 挥发分 粘结指数 

分 类 号：O212[理学—概率论与数理统计] TQ520[理学—数学]