文献类型：期刊文献

中文题名：石油馏分基础数据模型建模方法

英文题名：Modeling basic fraction data of petroleum distillation

作者：梅华[1,2];黄彪[2];钱锋[1]

机构：[1]华东理工大学化工过程先进控制和优化技术教育部重点实验室,上海200237;[2]Department of Chemical&Materials Engineering,University of Alberta

年份：2018

卷号：69

期号：3

起止页码：931

中文期刊名：化工学报

外文期刊名：CIESC Journal

收录：CSTPCD;;EI(收录号：20184105915761);Scopus;北大核心:【北大核心2017】；CSCD:【CSCD2017_2018】；

基金：国家自然科学基金重点项目(61333010);国家自然科学基金优秀青年基金项目(61422303);国家留学基金委资助项目(201606745013)~~

语种：中文

中文关键词：石油馏分;状态空间表征;基础馏分数据模型;非负矩阵分解;迭代优化

外文关键词：petroleum fractions; state space representation; basic fraction data model; non-negative matrix factorization; iterative optimization

摘要：石油馏分属性数据是石油化工生产过程中的重要基础数据,但是海量的现场数据包含了大量的冗余信息和测量误差,给化工过程实际生产带来很大的困扰。基于石油馏分状态空间表征法提出一种石油馏分基础数据模型建模方法。该方法通过非负矩阵分解算法得到一组初始基础馏分数据模型并在此基础上采用迭代更新策略,在保证模型预测精度的前提下尽可能地减少模型库的规模。仿真结果验证了本方法的有效性和实用性,在石油化工生产过程中具有广阔的应用前景。
Properties of petroleum fractions are important data of petrochemical processes.However,tremendouson-site data containing redundant information and measurement errors pose a great challenge to routine operationof chemical processes.A basic fraction data modelling method was proposed from characterization techniques ofstate space of petroleum fractions,in which an initial basic fraction data model was obtained via non-negative matrixfactorization and updated by an iterative strategy so that the scale of the model base set was minimized as much aspossible under circumstance of assured modelling accuracy.The results of simulation study verify that the proposedmethod is effective and suitable for a wide application to petrochemical processes.