Unsupervised process monitoring and fault diagnoses with machine learning methods

Although this book is focused on the process industries, the methodologies discussed in the following chapters are generic and can in many instances be applied with little modification in other monitoring systems, including some of those concerned with structural health monitoring, biomedicine, envi...

Full description

Bibliographic Details
Main Authors: Aldrich, Chris, Auret, Lidia
Other Authors: Sameer Singh
Format: Book
Published: Springer 2013
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/44434
_version_ 1848757000117157888
author Aldrich, Chris
Auret, Lidia
author2 Sameer Singh
author_facet Sameer Singh
Aldrich, Chris
Auret, Lidia
author_sort Aldrich, Chris
building Curtin Institutional Repository
collection Online Access
description Although this book is focused on the process industries, the methodologies discussed in the following chapters are generic and can in many instances be applied with little modification in other monitoring systems, including some of those concerned with structural health monitoring, biomedicine, environmental monitoring, the monitoring systems found in vehicles and aircraft and monitoring of computer security systems. Of course, the emphasis would differ in these other areas of interest, e.g. dynamic process monitoring and nonlinear signal processing would be more relevant to structural health analysis and brain–machine interfaces than techniques designed for steady-state systems, but the basic ideas remain intact. As a consequence, the book should also be of interest to readers outside the process engineering community, and indeed, advances in one area are often driven by application or modification of related ideas in a similar field.
first_indexed 2025-11-14T09:21:08Z
format Book
id curtin-20.500.11937-44434
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:21:08Z
publishDate 2013
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-444342023-02-13T08:01:35Z Unsupervised process monitoring and fault diagnoses with machine learning methods Aldrich, Chris Auret, Lidia Sameer Singh Sing Bing Kang classification trees regression trees neural networks fault identification kernel-based methods fault detection Although this book is focused on the process industries, the methodologies discussed in the following chapters are generic and can in many instances be applied with little modification in other monitoring systems, including some of those concerned with structural health monitoring, biomedicine, environmental monitoring, the monitoring systems found in vehicles and aircraft and monitoring of computer security systems. Of course, the emphasis would differ in these other areas of interest, e.g. dynamic process monitoring and nonlinear signal processing would be more relevant to structural health analysis and brain–machine interfaces than techniques designed for steady-state systems, but the basic ideas remain intact. As a consequence, the book should also be of interest to readers outside the process engineering community, and indeed, advances in one area are often driven by application or modification of related ideas in a similar field. 2013 Book http://hdl.handle.net/20.500.11937/44434 10.1007/978-1-4471-5185-2 Springer restricted
spellingShingle classification trees
regression trees
neural networks
fault identification
kernel-based methods
fault detection
Aldrich, Chris
Auret, Lidia
Unsupervised process monitoring and fault diagnoses with machine learning methods
title Unsupervised process monitoring and fault diagnoses with machine learning methods
title_full Unsupervised process monitoring and fault diagnoses with machine learning methods
title_fullStr Unsupervised process monitoring and fault diagnoses with machine learning methods
title_full_unstemmed Unsupervised process monitoring and fault diagnoses with machine learning methods
title_short Unsupervised process monitoring and fault diagnoses with machine learning methods
title_sort unsupervised process monitoring and fault diagnoses with machine learning methods
topic classification trees
regression trees
neural networks
fault identification
kernel-based methods
fault detection
url http://hdl.handle.net/20.500.11937/44434