Transfer of process monitoring models between plants: Batch systems

被引:9
作者
Facco, Pierantonio [1 ]
Largoni, Martina [1 ]
Tomba, Emanuele [1 ]
Bezzo, Fabrizio [1 ]
Barolo, Massimiliano [1 ]
机构
[1] Univ Padua, Dept Ind Engn, Comp Aided Proc Engn Lab, CAPE Lab, I-35131 Padua, PD, Italy
关键词
Batch process monitoring; Model transfer; Multiway PGA; Joint-Y PLS;
D O I
10.1016/j.cherd.2013.07.010
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
In this paper, the problem of transferring a process monitoring model between different batch plants is addressed. By exploiting the data coming from a source plant similar to the target plant to which a batch production needs to be transferred, it is possible to transfer a process monitoring model to the target plant under the assumption that the source plant and the target plant are driven by the same fundamental laws. Two transfer methodologies are proposed. The first one is based on multiway principal component analysis, and exploits the information of similar ("common") variables that are measured both in the source plant and in the target plant. The second methodology is based on the use of multiway joint-Y partial least-squares regression and exploits all the measured data, i.e. common variables as well as variables that are measured only in one of the two plants. The effectiveness of the proposed methodologies is demonstrated using a benchmark simulated fed-batch fermentation process for penicillin production. (C) 2013 The Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.
引用
收藏
页码:273 / 284
页数:12
相关论文
共 21 条
  • [1] Dealing with missing data in MSPC: several methods, different interpretations, some examples
    Arteaga, F
    Ferrer, A
    [J]. JOURNAL OF CHEMOMETRICS, 2002, 16 (8-10) : 408 - 418
  • [2] A modular simulation package for fed-batch fermentation:: penicillin production
    Birol, G
    Ündey, C
    Çinar, A
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 2002, 26 (11) : 1553 - 1565
  • [3] Bilinear modelling of batch processes.: Part I:: theoretical discussion
    Camacho, Jose
    Pico, Jesus
    Ferrer, Alberto
    [J]. JOURNAL OF CHEMOMETRICS, 2008, 22 (5-6) : 299 - 308
  • [4] Industrial implementation of on-line multivariate quality control
    Chiang, Leo H.
    Colegrove, Lloyd F.
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2007, 88 (02) : 143 - 153
  • [5] Cinar A., 2003, BATCH FERMENTATION M
  • [6] Transfer of Process Monitoring Models between Different Plants Using Latent Variable Techniques
    Facco, Pierantonio
    Tomba, Emanuele
    Bezzo, Fabrizio
    Garcia-Munoz, Salvador
    Barolo, Massimiliano
    [J]. INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2012, 51 (21) : 7327 - 7339
  • [7] Feundale RN, 2002, CHEMOMETR INTELL LAB, V64, P181
  • [8] Model predictive monitoring for batch processes
    García-Muñoz, S
    Kourti, T
    MacGregor, JF
    [J]. INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2004, 43 (18) : 5929 - 5941
  • [9] Establishing multivariate specifications for incoming materials using data from multiple scales
    Garcia-Munoz, Salvador
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2009, 98 (01) : 51 - 57
  • [10] Product transfer between plants using historical process data
    Jaeckle, CM
    MacGregor, JF
    [J]. AICHE JOURNAL, 2000, 46 (10) : 1989 - 1997