Browse by author
Lookup NU author(s): Dr Barry Wise, Dr Neal Gallagher, Professor Elaine Martin
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
Monitoring and fault detection of batch chemical processes are complicated by stretching of the time axis, resulting in batches of different length. This paper offers an approach to the unequal time axis problem using the parallel factor analysis 2 (PARAFAC2) model. Unlike PARAFAC, the PARAFAC2 model does not assume parallel proportional profiles, but only that the matrix of profiles preserves its 'inner product structure' from sample to sample. PARAFAC2 also allows each matrix in the multiway array to have a different number of rows. It has previously been demonstrated how the PARAFAC2 model can be used to model chromatographic data with retention time shifts. Fault detection and, to a lesser extent, diagnosis in a semiconductor etch process are considered in this paper. It is demonstrated that PARAFAC2 can effectively model batch process data from semiconductor manufacture with unequal dimension in one of the orders, such as the unequal batch length problem. It is shown that the PARAFAC2 model has approximately the same sensitivity to faults as other competing methods. including principal component analysis (PCA), unfold PCA (often referred to as multiway PCA), trilinear decomposition (TLD) and conventional PARAFAC. The advantage of PARAFAC2 is that it is easier to apply than MPCA, TLD and PARAFAC, because unequal batch lengths can be handled directly rather than through preprocessing methods. It also provides additional diagnostic information: the recovered batch profiles. It is likely, however, that it is less sensitive to faults than conventional PARAFAC. Copyright (C) 2001 John Wiley & Sons, Ltd.
Author(s): Wise BM, Gallagher NB, Martin EB
Publication type: Article
Publication status: Published
Journal: Journal of Chemometrics
Year: 2001
Volume: 15
Issue: 4
Pages: 285-298
ISSN (print): 0886-9383
ISSN (electronic): 1099-128X
Publisher: Wiley-Blackwell Publishing Ltd.
URL: http://dx.doi.org/10.1002/cem.689
DOI: 10.1002/cem.689
Altmetrics provided by Altmetric
