应用BP神经网络的二次反应清洁汽油辛烷值预测  

Prediction of Octane Number for Clean Gasoline Obtained from Secondary Reactions Based on Back-Propagation Neural Network

作　　者：周小伟[1] 袁俊[2] 杨伯伦[1] 

机构地区：[1]西安交通大学能源与动力工程学院,西安710049 [2]西安近代化学研究所,西安710065

出　　处：《西安交通大学学报》2010年第12期82-86,共5页Journal of Xi'an Jiaotong University

基　　金：国家"973计划"资助项目(2009CB219906);国家自然科学基金资助项目(20776117;20976144);高等学校博士学科点专项科研基金资助项目(20070698037)

摘　　要：借鉴复杂反应动力学研究中的集总方法,将汽油辛烷值看成汽油链烷烃集总、环烷烃集总、芳烃集总、烯烃集总的函数.采用多元线性回归和BP神经网络算法,分别建立了二次反应清洁汽油的研究法辛烷值预测模型,并进行了实例计算验证和对比分析.结果表明,BP神经网络模型的整体性能优于多元线性回归模型,其强大的非线性映射能力能够更好地反映汽油研究法辛烷值与各集总组分之间的复杂关系,且具有更好的预测性能,模型预测值与实验测得的汽油辛烷值的平均相对误差为0.39%,与文献报道的汽油辛烷值的平均相对误差为0.92%.The octane number of gasoline was considered as a function of paraffin lump,naphthalene lump,aromatics lump and olefins lump based on lumping concept for complex reaction kinetics.Back-propagation（BP） neural network and multiple linear regression were adopted to establish prediction models for the research octane number（RON） of clean gasoline obtained from secondary reactions,respectively.The two models were compared and verified via several cases.The results show that BP neural network model exhibits better performance than multiple linear regression model for the higher prediction accuracy due to strong nonlinear mapping ability to reflex the complex relationship between RON and lump components.The mean absolute relative error between predicted gasoline RON and experimental data gets 0.39%,and 0.92% for the reported results.

关 键 词：清洁汽油 辛烷值 集总 多元线性回归 BP神经网络 

分 类 号：TQ622[化学工程—精细化工] TP301.6[自动化与计算机技术—计算机系统结构]