Detecting faults in process systems with singular spectrum analysis

In this study, process monitoring based on signal decomposition by use of singular spectrum analysis (SSA) is considered. SSA makes use of adaptive basis functions to decompose a time series into multiple components that may be periodic, aperiodic or random. Two variants of SSA are considered in thi...

Full description

Bibliographic Details
Main Authors: Krishnannair, S., Aldrich, Chris, Jemwa, G.
Format: Journal Article
Published: Elsevier 2016
Online Access:http://hdl.handle.net/20.500.11937/7250
_version_ 1848745315642900480
author Krishnannair, S.
Aldrich, Chris
Jemwa, G.
author_facet Krishnannair, S.
Aldrich, Chris
Jemwa, G.
author_sort Krishnannair, S.
building Curtin Institutional Repository
collection Online Access
description In this study, process monitoring based on signal decomposition by use of singular spectrum analysis (SSA) is considered. SSA makes use of adaptive basis functions to decompose a time series into multiple components that may be periodic, aperiodic or random. Two variants of SSA are considered in this investigation. In the first, the conventional approach is used based on latent variables extracted from the covariances of the lagged trajectory matrix of the process variables. The second approach is identical to the first approach, except that the covariances of the lagged trajectory matrices are replaced by Euclidean distance dissimilarities to decompose the variables into additive components. These components are subsequently monitored and the merits of the two approaches are considered on the basis of two case studies using simulated nonlinear data and data from the benchmark Tennessee Eastman process.
first_indexed 2025-11-14T06:15:25Z
format Journal Article
id curtin-20.500.11937-7250
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:15:25Z
publishDate 2016
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-72502017-09-13T14:39:53Z Detecting faults in process systems with singular spectrum analysis Krishnannair, S. Aldrich, Chris Jemwa, G. In this study, process monitoring based on signal decomposition by use of singular spectrum analysis (SSA) is considered. SSA makes use of adaptive basis functions to decompose a time series into multiple components that may be periodic, aperiodic or random. Two variants of SSA are considered in this investigation. In the first, the conventional approach is used based on latent variables extracted from the covariances of the lagged trajectory matrix of the process variables. The second approach is identical to the first approach, except that the covariances of the lagged trajectory matrices are replaced by Euclidean distance dissimilarities to decompose the variables into additive components. These components are subsequently monitored and the merits of the two approaches are considered on the basis of two case studies using simulated nonlinear data and data from the benchmark Tennessee Eastman process. 2016 Journal Article http://hdl.handle.net/20.500.11937/7250 10.1016/j.cherd.2016.07.014 Elsevier restricted
spellingShingle Krishnannair, S.
Aldrich, Chris
Jemwa, G.
Detecting faults in process systems with singular spectrum analysis
title Detecting faults in process systems with singular spectrum analysis
title_full Detecting faults in process systems with singular spectrum analysis
title_fullStr Detecting faults in process systems with singular spectrum analysis
title_full_unstemmed Detecting faults in process systems with singular spectrum analysis
title_short Detecting faults in process systems with singular spectrum analysis
title_sort detecting faults in process systems with singular spectrum analysis
url http://hdl.handle.net/20.500.11937/7250