Empirical Models with Self-Assessment Capabilities for On-Line Industrial Applications
Self-assessment capabilities are critical for the longevity of online empirical models in industrial settings. A generic structure of an on-line model supervisor, consisting of within-the-range indicator, confidence of prediction, performance indicator, novelty/outlier detector, and model fault dete...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Tagungsbericht |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 3113 |
---|---|
container_issue | |
container_start_page | 3106 |
container_title | |
container_volume | |
creator | Kordon, A.K. Smits, G.F. Jordaan, E.M. Kalos, A.N. Castillo, F.A. Chiang, L.H. |
description | Self-assessment capabilities are critical for the longevity of online empirical models in industrial settings. A generic structure of an on-line model supervisor, consisting of within-the-range indicator, confidence of prediction, performance indicator, novelty/outlier detector, and model fault detector, is proposed in the paper. Several methods for confidence limits calculations, such as ensembles of analytic neural networks and symbolic regression models generated by genetic programming, linearized models based on transforms, derived by genetic programming, and a strangeness measure, based on support vector machines for regression, have been explored and their performance was compared in a case study for emission estimation on-line model. Some of the self-assessment capabilities for detection of unacceptable on-line performance and model and process faults are illustrated with industrial applications in the chemical industry. |
doi_str_mv | 10.1109/CEC.2006.1688702 |
format | Conference Proceeding |
fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1688702</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1688702</ieee_id><sourcerecordid>1688702</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-5f18d58114c96b28e4bbb0b98860c30de9a1ee5d1fa79f1998161009e956bf533</originalsourceid><addsrcrecordid>eNotkEtLw0AUhQcfYK3dC27mD0y8N4_J3GUJVQuRLizirswkd3AkTUMmIv57AxYOnMXh-xZHiHuEBBHosdpUSQqgE9TGlJBeiAVSjgog1ZdiRaWBORnlpkyv5g0MqbI0HzfiNsYvAMwLpIV43xyHMIbGdvL11HIX5U-YPuUbd16tY-QYj9xPsrKDdaELU-Ao_WmUu17VoWe57dvvOI1h5tfD0M2iKZz6eCeuve0ir869FPunzb56UfXueVutaxUIJlV4NG1hEPOGtEsN5845cGSMhiaDlskic9GityV5JDKoEYCYCu18kWVL8fCvDcx8GMZwtOPv4fxI9gdA6FLT</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Empirical Models with Self-Assessment Capabilities for On-Line Industrial Applications</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Kordon, A.K. ; Smits, G.F. ; Jordaan, E.M. ; Kalos, A.N. ; Castillo, F.A. ; Chiang, L.H.</creator><creatorcontrib>Kordon, A.K. ; Smits, G.F. ; Jordaan, E.M. ; Kalos, A.N. ; Castillo, F.A. ; Chiang, L.H.</creatorcontrib><description>Self-assessment capabilities are critical for the longevity of online empirical models in industrial settings. A generic structure of an on-line model supervisor, consisting of within-the-range indicator, confidence of prediction, performance indicator, novelty/outlier detector, and model fault detector, is proposed in the paper. Several methods for confidence limits calculations, such as ensembles of analytic neural networks and symbolic regression models generated by genetic programming, linearized models based on transforms, derived by genetic programming, and a strangeness measure, based on support vector machines for regression, have been explored and their performance was compared in a case study for emission estimation on-line model. Some of the self-assessment capabilities for detection of unacceptable on-line performance and model and process faults are illustrated with industrial applications in the chemical industry.</description><identifier>ISSN: 1089-778X</identifier><identifier>ISBN: 9780780394872</identifier><identifier>ISBN: 0780394879</identifier><identifier>EISSN: 1941-0026</identifier><identifier>DOI: 10.1109/CEC.2006.1688702</identifier><language>eng</language><publisher>IEEE</publisher><subject>Chemical industry ; Detectors ; Fault detection ; Genetic programming ; Maintenance ; Manufacturing industries ; Neural networks ; Predictive models ; Robustness ; Support vector machines</subject><ispartof>2006 IEEE International Conference on Evolutionary Computation, 2006, p.3106-3113</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1688702$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,796,2058,4050,4051,27925,54758,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1688702$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kordon, A.K.</creatorcontrib><creatorcontrib>Smits, G.F.</creatorcontrib><creatorcontrib>Jordaan, E.M.</creatorcontrib><creatorcontrib>Kalos, A.N.</creatorcontrib><creatorcontrib>Castillo, F.A.</creatorcontrib><creatorcontrib>Chiang, L.H.</creatorcontrib><title>Empirical Models with Self-Assessment Capabilities for On-Line Industrial Applications</title><title>2006 IEEE International Conference on Evolutionary Computation</title><addtitle>CEC</addtitle><description>Self-assessment capabilities are critical for the longevity of online empirical models in industrial settings. A generic structure of an on-line model supervisor, consisting of within-the-range indicator, confidence of prediction, performance indicator, novelty/outlier detector, and model fault detector, is proposed in the paper. Several methods for confidence limits calculations, such as ensembles of analytic neural networks and symbolic regression models generated by genetic programming, linearized models based on transforms, derived by genetic programming, and a strangeness measure, based on support vector machines for regression, have been explored and their performance was compared in a case study for emission estimation on-line model. Some of the self-assessment capabilities for detection of unacceptable on-line performance and model and process faults are illustrated with industrial applications in the chemical industry.</description><subject>Chemical industry</subject><subject>Detectors</subject><subject>Fault detection</subject><subject>Genetic programming</subject><subject>Maintenance</subject><subject>Manufacturing industries</subject><subject>Neural networks</subject><subject>Predictive models</subject><subject>Robustness</subject><subject>Support vector machines</subject><issn>1089-778X</issn><issn>1941-0026</issn><isbn>9780780394872</isbn><isbn>0780394879</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotkEtLw0AUhQcfYK3dC27mD0y8N4_J3GUJVQuRLizirswkd3AkTUMmIv57AxYOnMXh-xZHiHuEBBHosdpUSQqgE9TGlJBeiAVSjgog1ZdiRaWBORnlpkyv5g0MqbI0HzfiNsYvAMwLpIV43xyHMIbGdvL11HIX5U-YPuUbd16tY-QYj9xPsrKDdaELU-Ao_WmUu17VoWe57dvvOI1h5tfD0M2iKZz6eCeuve0ir869FPunzb56UfXueVutaxUIJlV4NG1hEPOGtEsN5845cGSMhiaDlskic9GityV5JDKoEYCYCu18kWVL8fCvDcx8GMZwtOPv4fxI9gdA6FLT</recordid><startdate>2006</startdate><enddate>2006</enddate><creator>Kordon, A.K.</creator><creator>Smits, G.F.</creator><creator>Jordaan, E.M.</creator><creator>Kalos, A.N.</creator><creator>Castillo, F.A.</creator><creator>Chiang, L.H.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2006</creationdate><title>Empirical Models with Self-Assessment Capabilities for On-Line Industrial Applications</title><author>Kordon, A.K. ; Smits, G.F. ; Jordaan, E.M. ; Kalos, A.N. ; Castillo, F.A. ; Chiang, L.H.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-5f18d58114c96b28e4bbb0b98860c30de9a1ee5d1fa79f1998161009e956bf533</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Chemical industry</topic><topic>Detectors</topic><topic>Fault detection</topic><topic>Genetic programming</topic><topic>Maintenance</topic><topic>Manufacturing industries</topic><topic>Neural networks</topic><topic>Predictive models</topic><topic>Robustness</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kordon, A.K.</creatorcontrib><creatorcontrib>Smits, G.F.</creatorcontrib><creatorcontrib>Jordaan, E.M.</creatorcontrib><creatorcontrib>Kalos, A.N.</creatorcontrib><creatorcontrib>Castillo, F.A.</creatorcontrib><creatorcontrib>Chiang, L.H.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kordon, A.K.</au><au>Smits, G.F.</au><au>Jordaan, E.M.</au><au>Kalos, A.N.</au><au>Castillo, F.A.</au><au>Chiang, L.H.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Empirical Models with Self-Assessment Capabilities for On-Line Industrial Applications</atitle><btitle>2006 IEEE International Conference on Evolutionary Computation</btitle><stitle>CEC</stitle><date>2006</date><risdate>2006</risdate><spage>3106</spage><epage>3113</epage><pages>3106-3113</pages><issn>1089-778X</issn><eissn>1941-0026</eissn><isbn>9780780394872</isbn><isbn>0780394879</isbn><abstract>Self-assessment capabilities are critical for the longevity of online empirical models in industrial settings. A generic structure of an on-line model supervisor, consisting of within-the-range indicator, confidence of prediction, performance indicator, novelty/outlier detector, and model fault detector, is proposed in the paper. Several methods for confidence limits calculations, such as ensembles of analytic neural networks and symbolic regression models generated by genetic programming, linearized models based on transforms, derived by genetic programming, and a strangeness measure, based on support vector machines for regression, have been explored and their performance was compared in a case study for emission estimation on-line model. Some of the self-assessment capabilities for detection of unacceptable on-line performance and model and process faults are illustrated with industrial applications in the chemical industry.</abstract><pub>IEEE</pub><doi>10.1109/CEC.2006.1688702</doi><tpages>8</tpages></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1089-778X |
ispartof | 2006 IEEE International Conference on Evolutionary Computation, 2006, p.3106-3113 |
issn | 1089-778X 1941-0026 |
language | eng |
recordid | cdi_ieee_primary_1688702 |
source | IEEE Electronic Library (IEL) Conference Proceedings |
subjects | Chemical industry Detectors Fault detection Genetic programming Maintenance Manufacturing industries Neural networks Predictive models Robustness Support vector machines |
title | Empirical Models with Self-Assessment Capabilities for On-Line Industrial Applications |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T04%3A51%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Empirical%20Models%20with%20Self-Assessment%20Capabilities%20for%20On-Line%20Industrial%20Applications&rft.btitle=2006%20IEEE%20International%20Conference%20on%20Evolutionary%20Computation&rft.au=Kordon,%20A.K.&rft.date=2006&rft.spage=3106&rft.epage=3113&rft.pages=3106-3113&rft.issn=1089-778X&rft.eissn=1941-0026&rft.isbn=9780780394872&rft.isbn_list=0780394879&rft_id=info:doi/10.1109/CEC.2006.1688702&rft_dat=%3Cieee_6IE%3E1688702%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1688702&rfr_iscdi=true |