基于自适应变量加权的汽油辛烷值预测方法  

Prediction method of gasoline octane number based on adaptive variable weighting

作　　者：赵林 李希[1,2] 谢永芳 易嘉闻[1,2] 吴健辉 胡文静 ZHAO Lin;LI Xi;XIE Yong-fang;YI Jia-wen;WU Jian-hui;HU Wen-jing(School of Information Science and Engineering,Hunan Institute of Science and Technology,Yueyang 414006,China;Research Center of Machine Vision and Artificial Intelligence,Hunan Institute of Science and Technology,Yueyang 414006,China;School of Automation,Central South University,Changsha 410083,China)

机构地区：[1]湖南理工学院信息科学与工程学院,湖南岳阳414006 [2]湖南理工学院机器视觉及人工智能研究中心,湖南岳阳414006 [3]中南大学自动化学院,长沙410083

出　　处：《控制与决策》2022年第10期2738-2744,共7页Control and Decision

基　　金：湖南省自然科学基金项目(2019JJ40110,2019JJ40104);湖南省教育厅科学研究项目(18B349,19A201);湖南省研究生科研创新项目(CX20190932,CX20190930)。

摘　　要：针对汽油精制过程中控制变量之间非线性和强耦联性,产品汽油中辛烷值难以测定的问题,提出一种基于自适应变量加权的汽油辛烷值预测方法.首先,利用一种新颖的变量加权模块捕获变量之间的相关性获取变量权重,通过自适应变量加权的方式提升主要变量的重要性,抑制其他次要变量的作用;然后,考虑到汽油脱硫过程对辛烷值的影响,输入加权激活后的变量到辛烷值预测模块,模型同时输出辛烷值和硫含量的预测结果;最后,基于工业数据进行模型验证,结果表明,与无变量加权模块的神经网络预测方法,基于随机森林的神经网络预测方法和基于变量加权堆叠自编码器的预测方法相比较,所提出的自适应变量加权汽油辛烷值预测方法具有更高的预测精度,可以用来优化汽油精制过程的操作条件.In the gasoline refining process, maintaining the gasoline research octane number(RON) is the focus of gasoline cleaning. However, due to the nonlinearity and strong coupling between the control variables in the petroleum refining process, it is difficult to measure the octane number in the product gasoline. Considering the importance of different variables to the octane number, a gasoline octane number prediction method based on adaptive variable weighting is proposed to predict the octane number. In this method, a novel variable weighting module is used to capture the correlation between the variables to obtain the variable weights, and the importance of the main variables is enhanced using the adaptive variable weighting method, and the effects of other secondary variables are suppressed.Then, considering the impact of gasoline desulfurization on the octane number, the weighted variables are input to the octane number prediction module, and the model outputs the prediction results of the octane number and sulfur content.Finally, model validation is performed based on industrial data. The results show that, compared with the neural network prediction method without the variable weighting module, the neural network prediction method based on the random forest algorithm and the prediction method based on the variable-wise weighted stacked autoencoder, the prediction method of the gasoline octane number based on adaptive variable weight has higher prediction accuracy, and it can be used to optimize the operating conditions of the gasoline refining process.

关 键 词：自适应变量加权 神经网络 软测量 辛烷值预测 汽油精制过程 深度学习 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]