摘要
为了预防神东煤在气化过程中结渣的问题,以部分神东矿区煤的灰成分为自变量,灰熔点软化温度ST和流动温度FT为因变量,建立了Bagging集成CHAID决策树算法的灰熔点预测模型。结果表明:针对本文数据集,CHAID决策树最大树深度设置为5,决策树个数设置为10的模型预测效果最好;模型对小样本的FT预测精度略高于ST预测精度。因此,基于Bagging集成CHAID决策树预测煤灰熔融温度模型对气化炉的安全稳定运行提供重要指导。
In order to prevent the problem of slagging in the gasification process of Shendong coal,an ash melting point prediction model with Bagging integrated CHAID decision tree algorithm was established with ash composition of some Shendong mine coals as the independent variables and ash melting point softening temperature ST and flow temperature FT as the dependent variables.The results showed that for the data set of this paper,the model with the maximum tree depth set to 5 and the number of decision trees set to 10 had the best prediction effect,the model had a slightly higher accuracy of FT prediction than ST prediction for small samples.Therefore,the integrated CHAID decision tree prediction model based on Bagging for coal ash melt temperature prediction provided important guidance for the safe and stable operation of gasifier.
作者
张挺
李寒旭
张晔
陈和荆
ZHANG Ting;LI Han-xu;ZHANG Ye;CHEN He-jing(School of Chemical Engineering,Auhui University of Science and Technology,Anhui Huainan 232001,China)
出处
《广州化工》
CAS
2022年第14期179-183,188,共6页
GuangZhou Chemical Industry