Detection and classification of abnormal process situations using multidimensional wavelet domain hidden Markov trees

Authors
Bakhtazad, A Palazoglu, A Romagnoli, JA
Citation
A. Bakhtazad et al., Detection and classification of abnormal process situations using multidimensional wavelet domain hidden Markov trees, COMPUT CH E, 24(2-7), 2000, pp. 769-775
Citations number
10
Categorie Soggetti
Chemical Engineering
Journal title
COMPUTERS & CHEMICAL ENGINEERING
ISSN journal
00981354 → ACNP
Volume
24
Issue
2-7
Year of publication
2000
Pages
769 - 775
Database
ISI
SICI code
0098-1354(20000715)24:2-7<769:DACOAP>2.0.ZU;2-2
Abstract
This paper addresses the detection of abnormal process situations during pl ant operation via an effective trending strategy. Wavelet-domain hidden Mar kov models (HMMs) are exploited as a powerful tool for statistical modeling and processing of wavelet coefficients. We focus on the multivariate probl em as many variables contribute to the decision regarding process status. A simulation study illustrates the salient features of the proposed framewor k. (C) 2000 Elsevier Science Ltd. All rights reserved.