| 151 | 15 | 406 |
| 下载次数 | 被引频次 | 阅读次数 |
针对多向主元分析法(MPCA)在间歇过程监控过程中需要预测过程未来输出的困难,提出了一种新的步进多向主元分析方法。该方法通过建立一系列的PCA模型,避免了对预估过程变量未来输出的需要,通过引入遗忘因子能够自然地处理多阶段间歇过程的情况。对于多阶段链霉素发酵过程的监控表明,相对于普通MPCA,步进MPCA能够更精确地对过程故障行为进行描述。
Abstract：Multi-way principal component analysis (MPCA) has been successfully applied to the monitoring of batch and semi-batch process in most chemical industry. A new approach using the process variable trajectories to monitoring batch process was proposed. It overcomes the need of estimating or filling in the unknown part of the process variable trajectory deviations from the current time until the end. The approach is based on a multi-way PCA method that processes the data in a sequential and adaptive manner. The adaptive rate is easily controlled through a parameter that controls the weight of past data in a summation manner. This algorithm was evaluated with industrial fermentation process data and was compared with the traditional MPCA. The method has significant benefit especially in monitoring multi-stage batch process where the latent vector structure can change at several points during the batch.
[1]NomikosP,MacGregorJ F.Monitoring of batch processes using multi-way principal components analysis[J].AmInstChemEng,1994,40:1361-1375.
[2]NomikosP,MacGregorJ F.MultivariateSPC charts for batch processes[J].Technometrics,1995,37:41-59.
[3]RnnarS,MacGregorJ F.Adaptive batch monitoring using hierarchicalPCA [J].ChemometricsIntellLabSyst,1998,30:73-81.
[4]JolliffeI T.PrincipalComponentAnalysis[M].NewYork:Springer-Verlag,1986.
[5]JacksonJ E.A UsersGuide toPrincipalComponents[M].NewYork:WileyInter-science,1991.
[6]ZHONG Wei-hong(钟卫鸿),CEN Pei-lin(岑沛霖),MA Jun(马骏),TONG Jing-jing(童景景).Study on kinetic models for batch fermentation and synthesis of alkaline pekinese by spirillospora(间歇发酵螺孢菌产碱性果胶酶过程动力学研究)[J].J ChemEng ofChineseUniv(高校化学工程学报),2002,16(3):311-314.
[7]ZHANG Quan-ling(张泉灵),JIN Xiao-ming(金晓明),WANG Shu-qing(王树青).Streptomycin fermentation process modeling with principal component analysis and fuzzy model(基于主元分析和模糊模型的链霉素发酵过程建模)[J].J WuxiUniversity ofLightIndustry(无锡轻工大学学报),2000,19(5)446-450.
[8]CHEN Yuan-qing(陈元青),CHEN Qi(陈琦),WANG Shu-qing(王树青).Multivariate statistical analysis for streplomycin fermentation(多元统计分析方法在链霉素发酵中的应用)[J].ChineseJournal ofBiotechnology(生物工程学报),1999,15(3)368-372.
基本信息:
中图分类号:TP277
引用信息:
[1]谢磊,何宁,王树青.步进MPCA及其在间歇过程监控中的应用[J],2004(05):643-647.
基金信息:
863资助项目(2001AA413110)。