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.
作者
张嘉桐
Zhang Jiatong(Petrochina Jinxi Petrochemical Company,Huludao 125001)
出处
《石化技术》
CAS
2023年第12期13-14,12,共3页
Petrochemical Industry Technology
关键词
汽油调合
辛烷值
预测模型
Gasoline blending
Octane number
Predictive model
