基于PARAFAC2的多时段间歇过程时段划分  

PARAFAC2-based phase partition of multiphase batch processes

作　　者：曹雪 王建林[1] 邱科鹏 刘伟旻 韩锐 CAO Xue;WANG JianLin;QIU KePeng;LIU WeiMin;HAN Rui(College of Information Science and Technology,Beijing University of Chemical Technology,Beijing 100029,China)

机构地区：[1]北京化工大学信息科学与技术学院,北京100029

出　　处：《北京化工大学学报（自然科学版）》2019年第2期77-82,共6页Journal of Beijing University of Chemical Technology(Natural Science Edition)

基　　金：国家自然科学基金(61240047);北京市自然科学基金(4152041)

摘　　要：针对间歇过程多时段特性,提出一种基于平行因子分解2(PARAFAC2)的多时段间歇过程时段划分方法。首先对每一个时间片矩阵进行平行因子分解2(PARAFAC2)建模,得到时间片矩阵的模型控制限,然后从间歇过程初始时刻开始,按照时序依次将每个时间片添加到时间块并进行PARAFAC2建模,得到时间块矩阵的模型控制限后,通过评估时间片和时间块模型控制限的差异性来确定初始时段划分点,最后利用时段评价划分指标(PPCI)获取最佳的时段划分结果。通过青霉素发酵过程仿真实验验证了本文方法的有效性。A method of phase partition of multiphase batch processes based on parallel factor analysis 2(PARAFAC2) is presented.Firstly,a model of each time-slice matrix was built based on PARAFAC2 and the control limit of each time-slice matrix was calculated.Secondly,starting from the initial time of the batch process,each time slice matrix was sequentially added to the time block matrix and a model based on PARAFAC2 was built,and the control limit of each time block matrix was calculated.Thirdly,the phase partition result was determined by evaluating the difference between the time slice and the time block model control limits.Finally,the optimal phase partition result was chosen according to the phase partition combination index(PPCI).Comparison of the simulation results and experimental data for the penicillin fermentation process verified the effectiveness of the proposed method.

关 键 词：间歇过程 多时段 三维数据 平行因子分解2(PARAFAC2) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]