汽油调合辛烷值预测模型的建立与求解  

Establishment and solution of octane number prediction model for gasoline blending

作　　者：张嘉桐 Zhang Jiatong(Petrochina Jinxi Petrochemical Company,Huludao 125001)

机构地区：[1]中国石油锦西石化公司,辽宁葫芦岛125001

出　　处：《石化技术》2023年第12期13-14,12,共3页Petrochemical Industry Technology

摘　　要：建立了汽油调合的辛烷值(RON)预测模型,利用成品油历史调合数据,采用最小二乘法回归模型系数,使用LINGO优化求解器求解,计算值与实际值平均偏差为0.175%,复相关系数为0.9872,模型精度较高,优于文献值,可以用于汽油调合的辛烷值预测。In this paper,the Ron Prediction model for gasoline blending was established.The model coefficients were calculated using the least squares regression model and the LINGO optimization solver using the historical blending data of refined oil products,the average deviation between the calculated value and the actual value is 0.175%,and the multiple correlation coefficient is 0.9872.The accuracy of the model is higher than that in the literature,and it can be used to predict the octane number of gasoline blending.

关 键 词：汽油调合 辛烷值 预测模型 

分 类 号：TE626.21[石油与天然气工程—油气加工工程]