Semi-mechanistic Models for State-Estimation – Soft Sensor for Polymer Melt Index Prediction
Nonlinear state estimation is a useful approach to the monitoring of industrial (polymerization) processes. This paper investigates how this approach can be followed to the development of a soft sensor of the product quality (melt index). The bottleneck of the successful application of advanced stat...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Buchkapitel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1117 |
|---|---|
| container_issue | |
| container_start_page | 1111 |
| container_title | |
| container_volume | 3070 |
| creator | Feil, Balazs Abonyi, Janos Pach, Peter Nemeth, Sandor Arva, Peter Nemeth, Miklos Nagy, Gabor |
| description | Nonlinear state estimation is a useful approach to the monitoring of industrial (polymerization) processes. This paper investigates how this approach can be followed to the development of a soft sensor of the product quality (melt index). The bottleneck of the successful application of advanced state estimation algorithms is the identification of models that can accurately describe the process. This paper presents a semi-mechanistic modeling approach where neural networks describe the unknown phenomena of the system that cannot be formulated by prior knowledge based differential equations. Since in the presented semi-mechanistic model structure the neural network is a part of a nonlinear algebraic-differential equation set, there are no available direct input-output data to train the weights of the network. To handle this problem in this paper a simple, yet practically useful spline-smoothing based technique has been used. The results show that the developed semi-mechanistic model can be efficiently used for on-line state estimation. |
| doi_str_mv | 10.1007/978-3-540-24844-6_174 |
| format | Book Chapter |
| fullrecord | <record><control><sourceid>proquest_pasca</sourceid><recordid>TN_cdi_pascalfrancis_primary_15852342</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EBC3088629_180_1135</sourcerecordid><originalsourceid>FETCH-LOGICAL-p273t-b16803f2b62ef3679ea05b069ae72df7169d924e597db5183b773d837529d2753</originalsourceid><addsrcrecordid>eNpFkE1OHDEQhU2AKCOYIyB5k6WD7fLvEiFIkEAgTbKN5e6uhoae7ontSLDLHXLDnCSeAYnalPTqvafSR8iJ4F8E5_bUW8eAacWZVE4pZoKwao8sqw5V3YnmA1kIIwQDUH7__SaFBHVAFhy4ZN4q-EgWvloc98p_IsucH3kdwWsWFuTnCtcDW2P7EKchl6GlN3OHY6b9nOiqxILsosrrWIZ5ov_-_KWruS90hVOuhq3pbh5f1pjoDY6FXk0dPtO7hN3QbhPH5LCPY8bl2z4iPy4vvp9_Y9e3X6_Oz67ZRloorBHGcehlYyT2YKzHyHXDjY9oZddbYXznpULtbddo4aCxFjoHVkvfSavhiHx-7d3E3MaxT3Fqhxw2qX6eXoLQTlcssvrg1ZfrabrHFJp5fspB8LAlHyrFAKFyDDvIYUe-pvRbe5p__cZcAm5jLU4lxbGi2xRMOQB3zkgfhKttAjT8B8glgWk</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>book_chapter</recordtype><pqid>EBC3088629_180_1135</pqid></control><display><type>book_chapter</type><title>Semi-mechanistic Models for State-Estimation – Soft Sensor for Polymer Melt Index Prediction</title><source>Springer Books</source><creator>Feil, Balazs ; Abonyi, Janos ; Pach, Peter ; Nemeth, Sandor ; Arva, Peter ; Nemeth, Miklos ; Nagy, Gabor</creator><contributor>Tadeusiewicz, Ryszard ; Siekmann, Jörg ; Rutkowski, Leszek ; Zadeh, Lotfi A ; Rutkowski, Leszek ; Siekmann, Jörg H. ; Zadeh, Lotfi A. ; Tadeusiewicz, Ryszard</contributor><creatorcontrib>Feil, Balazs ; Abonyi, Janos ; Pach, Peter ; Nemeth, Sandor ; Arva, Peter ; Nemeth, Miklos ; Nagy, Gabor ; Tadeusiewicz, Ryszard ; Siekmann, Jörg ; Rutkowski, Leszek ; Zadeh, Lotfi A ; Rutkowski, Leszek ; Siekmann, Jörg H. ; Zadeh, Lotfi A. ; Tadeusiewicz, Ryszard</creatorcontrib><description>Nonlinear state estimation is a useful approach to the monitoring of industrial (polymerization) processes. This paper investigates how this approach can be followed to the development of a soft sensor of the product quality (melt index). The bottleneck of the successful application of advanced state estimation algorithms is the identification of models that can accurately describe the process. This paper presents a semi-mechanistic modeling approach where neural networks describe the unknown phenomena of the system that cannot be formulated by prior knowledge based differential equations. Since in the presented semi-mechanistic model structure the neural network is a part of a nonlinear algebraic-differential equation set, there are no available direct input-output data to train the weights of the network. To handle this problem in this paper a simple, yet practically useful spline-smoothing based technique has been used. The results show that the developed semi-mechanistic model can be efficiently used for on-line state estimation.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 9783540221234</identifier><identifier>ISBN: 3540221239</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 9783540248446</identifier><identifier>EISBN: 3540248447</identifier><identifier>DOI: 10.1007/978-3-540-24844-6_174</identifier><identifier>OCLC: 934980949</identifier><identifier>LCCallNum: Q334-342</identifier><language>eng</language><publisher>Germany: Springer Berlin / Heidelberg</publisher><subject>Advance Process Control ; Applied sciences ; Artificial intelligence ; Chain Transfer Agent ; Computer science; control theory; systems ; Exact sciences and technology ; Extend Kalman Filter ; Learning and adaptive systems ; Soft Sensor ; State Estimation</subject><ispartof>Artificial Intelligence and Soft Computing - ICAISC 2004, 2004, Vol.3070, p.1111-1117</ispartof><rights>Springer-Verlag Berlin Heidelberg 2004</rights><rights>2004 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><relation>Lecture Notes in Computer Science</relation></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttps://ebookcentral.proquest.com/covers/3088629-l.jpg</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/978-3-540-24844-6_174$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/978-3-540-24844-6_174$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,779,780,784,789,790,793,4050,4051,27925,38255,41442,42511</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=15852342$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Tadeusiewicz, Ryszard</contributor><contributor>Siekmann, Jörg</contributor><contributor>Rutkowski, Leszek</contributor><contributor>Zadeh, Lotfi A</contributor><contributor>Rutkowski, Leszek</contributor><contributor>Siekmann, Jörg H.</contributor><contributor>Zadeh, Lotfi A.</contributor><contributor>Tadeusiewicz, Ryszard</contributor><creatorcontrib>Feil, Balazs</creatorcontrib><creatorcontrib>Abonyi, Janos</creatorcontrib><creatorcontrib>Pach, Peter</creatorcontrib><creatorcontrib>Nemeth, Sandor</creatorcontrib><creatorcontrib>Arva, Peter</creatorcontrib><creatorcontrib>Nemeth, Miklos</creatorcontrib><creatorcontrib>Nagy, Gabor</creatorcontrib><title>Semi-mechanistic Models for State-Estimation – Soft Sensor for Polymer Melt Index Prediction</title><title>Artificial Intelligence and Soft Computing - ICAISC 2004</title><description>Nonlinear state estimation is a useful approach to the monitoring of industrial (polymerization) processes. This paper investigates how this approach can be followed to the development of a soft sensor of the product quality (melt index). The bottleneck of the successful application of advanced state estimation algorithms is the identification of models that can accurately describe the process. This paper presents a semi-mechanistic modeling approach where neural networks describe the unknown phenomena of the system that cannot be formulated by prior knowledge based differential equations. Since in the presented semi-mechanistic model structure the neural network is a part of a nonlinear algebraic-differential equation set, there are no available direct input-output data to train the weights of the network. To handle this problem in this paper a simple, yet practically useful spline-smoothing based technique has been used. The results show that the developed semi-mechanistic model can be efficiently used for on-line state estimation.</description><subject>Advance Process Control</subject><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Chain Transfer Agent</subject><subject>Computer science; control theory; systems</subject><subject>Exact sciences and technology</subject><subject>Extend Kalman Filter</subject><subject>Learning and adaptive systems</subject><subject>Soft Sensor</subject><subject>State Estimation</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>9783540221234</isbn><isbn>3540221239</isbn><isbn>9783540248446</isbn><isbn>3540248447</isbn><fulltext>true</fulltext><rsrctype>book_chapter</rsrctype><creationdate>2004</creationdate><recordtype>book_chapter</recordtype><recordid>eNpFkE1OHDEQhU2AKCOYIyB5k6WD7fLvEiFIkEAgTbKN5e6uhoae7ontSLDLHXLDnCSeAYnalPTqvafSR8iJ4F8E5_bUW8eAacWZVE4pZoKwao8sqw5V3YnmA1kIIwQDUH7__SaFBHVAFhy4ZN4q-EgWvloc98p_IsucH3kdwWsWFuTnCtcDW2P7EKchl6GlN3OHY6b9nOiqxILsosrrWIZ5ov_-_KWruS90hVOuhq3pbh5f1pjoDY6FXk0dPtO7hN3QbhPH5LCPY8bl2z4iPy4vvp9_Y9e3X6_Oz67ZRloorBHGcehlYyT2YKzHyHXDjY9oZddbYXznpULtbddo4aCxFjoHVkvfSavhiHx-7d3E3MaxT3Fqhxw2qX6eXoLQTlcssvrg1ZfrabrHFJp5fspB8LAlHyrFAKFyDDvIYUe-pvRbe5p__cZcAm5jLU4lxbGi2xRMOQB3zkgfhKttAjT8B8glgWk</recordid><startdate>2004</startdate><enddate>2004</enddate><creator>Feil, Balazs</creator><creator>Abonyi, Janos</creator><creator>Pach, Peter</creator><creator>Nemeth, Sandor</creator><creator>Arva, Peter</creator><creator>Nemeth, Miklos</creator><creator>Nagy, Gabor</creator><general>Springer Berlin / Heidelberg</general><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>FFUUA</scope><scope>IQODW</scope></search><sort><creationdate>2004</creationdate><title>Semi-mechanistic Models for State-Estimation – Soft Sensor for Polymer Melt Index Prediction</title><author>Feil, Balazs ; Abonyi, Janos ; Pach, Peter ; Nemeth, Sandor ; Arva, Peter ; Nemeth, Miklos ; Nagy, Gabor</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p273t-b16803f2b62ef3679ea05b069ae72df7169d924e597db5183b773d837529d2753</frbrgroupid><rsrctype>book_chapters</rsrctype><prefilter>book_chapters</prefilter><language>eng</language><creationdate>2004</creationdate><topic>Advance Process Control</topic><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Chain Transfer Agent</topic><topic>Computer science; control theory; systems</topic><topic>Exact sciences and technology</topic><topic>Extend Kalman Filter</topic><topic>Learning and adaptive systems</topic><topic>Soft Sensor</topic><topic>State Estimation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Feil, Balazs</creatorcontrib><creatorcontrib>Abonyi, Janos</creatorcontrib><creatorcontrib>Pach, Peter</creatorcontrib><creatorcontrib>Nemeth, Sandor</creatorcontrib><creatorcontrib>Arva, Peter</creatorcontrib><creatorcontrib>Nemeth, Miklos</creatorcontrib><creatorcontrib>Nagy, Gabor</creatorcontrib><collection>ProQuest Ebook Central - Book Chapters - Demo use only</collection><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Feil, Balazs</au><au>Abonyi, Janos</au><au>Pach, Peter</au><au>Nemeth, Sandor</au><au>Arva, Peter</au><au>Nemeth, Miklos</au><au>Nagy, Gabor</au><au>Tadeusiewicz, Ryszard</au><au>Siekmann, Jörg</au><au>Rutkowski, Leszek</au><au>Zadeh, Lotfi A</au><au>Rutkowski, Leszek</au><au>Siekmann, Jörg H.</au><au>Zadeh, Lotfi A.</au><au>Tadeusiewicz, Ryszard</au><format>book</format><genre>bookitem</genre><ristype>CHAP</ristype><atitle>Semi-mechanistic Models for State-Estimation – Soft Sensor for Polymer Melt Index Prediction</atitle><btitle>Artificial Intelligence and Soft Computing - ICAISC 2004</btitle><seriestitle>Lecture Notes in Computer Science</seriestitle><date>2004</date><risdate>2004</risdate><volume>3070</volume><spage>1111</spage><epage>1117</epage><pages>1111-1117</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>9783540221234</isbn><isbn>3540221239</isbn><eisbn>9783540248446</eisbn><eisbn>3540248447</eisbn><abstract>Nonlinear state estimation is a useful approach to the monitoring of industrial (polymerization) processes. This paper investigates how this approach can be followed to the development of a soft sensor of the product quality (melt index). The bottleneck of the successful application of advanced state estimation algorithms is the identification of models that can accurately describe the process. This paper presents a semi-mechanistic modeling approach where neural networks describe the unknown phenomena of the system that cannot be formulated by prior knowledge based differential equations. Since in the presented semi-mechanistic model structure the neural network is a part of a nonlinear algebraic-differential equation set, there are no available direct input-output data to train the weights of the network. To handle this problem in this paper a simple, yet practically useful spline-smoothing based technique has been used. The results show that the developed semi-mechanistic model can be efficiently used for on-line state estimation.</abstract><cop>Germany</cop><pub>Springer Berlin / Heidelberg</pub><doi>10.1007/978-3-540-24844-6_174</doi><oclcid>934980949</oclcid><tpages>7</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Artificial Intelligence and Soft Computing - ICAISC 2004, 2004, Vol.3070, p.1111-1117 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_pascalfrancis_primary_15852342 |
| source | Springer Books |
| subjects | Advance Process Control Applied sciences Artificial intelligence Chain Transfer Agent Computer science control theory systems Exact sciences and technology Extend Kalman Filter Learning and adaptive systems Soft Sensor State Estimation |
| title | Semi-mechanistic Models for State-Estimation – Soft Sensor for Polymer Melt Index Prediction |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T10%3A53%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pasca&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=bookitem&rft.atitle=Semi-mechanistic%20Models%20for%20State-Estimation%20%E2%80%93%20Soft%20Sensor%20for%20Polymer%20Melt%20Index%20Prediction&rft.btitle=Artificial%20Intelligence%20and%20Soft%20Computing%20-%20ICAISC%202004&rft.au=Feil,%20Balazs&rft.date=2004&rft.volume=3070&rft.spage=1111&rft.epage=1117&rft.pages=1111-1117&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=9783540221234&rft.isbn_list=3540221239&rft_id=info:doi/10.1007/978-3-540-24844-6_174&rft_dat=%3Cproquest_pasca%3EEBC3088629_180_1135%3C/proquest_pasca%3E%3Curl%3E%3C/url%3E&rft.eisbn=9783540248446&rft.eisbn_list=3540248447&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=EBC3088629_180_1135&rft_id=info:pmid/&rfr_iscdi=true |