Data-Based Design of Multi-Model Inferential Sensors

This paper deals with the problem of inferential (soft) sensor design. The nonlinear character of industrial processes is usually the main limitation to designing simple linear inferential sensors with sufficient accuracy. In order to increase the inferential sensor predictive performance and yet to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mojto, Martin, Lubušký, Karol, Fikar, Miroslav, Paulen, Radoslav
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Mojto, Martin
Lubušký, Karol
Fikar, Miroslav
Paulen, Radoslav
description This paper deals with the problem of inferential (soft) sensor design. The nonlinear character of industrial processes is usually the main limitation to designing simple linear inferential sensors with sufficient accuracy. In order to increase the inferential sensor predictive performance and yet to maintain its linear structure, multi-model inferential sensors represent a straightforward option. In this contribution, we propose two novel approaches for the design of multi-model inferential sensors aiming to mitigate some drawbacks of the state-of-the-art approaches. For a demonstration of the developed techniques, we design inferential sensors for a Vacuum Gasoil Hydrogenation unit, which is a real-world petrochemical refinery unit. The performance of the multi-model inferential sensor is compared against various single-model inferential sensors and the current (referential) inferential sensor used in the refinery. The results show substantial improvements over the state-of-the-art design techniques for single-/multi-model inferential sensors.
doi_str_mv 10.48550/arxiv.2308.02872
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2308_02872</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2308_02872</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-484cd7d85ad4e92a553b5b4cc550fe7a54e38337e8fae2a8b4b360aa7759490b3</originalsourceid><addsrcrecordid>eNotzr1OwzAUQGEvDKjwAEz4BZwa-7p2xtJSWqkVA92j6_gaWUoTZKeIvj30Zzrb0cfY04uswBkjp5h_00-ltHSVVM6qewZLHFG8YqHAl1TSV8-HyHfHbkxiNwTq-KaPlKkfE3b8k_oy5PLA7iJ2hR5vnbD96m2_WIvtx_tmMd8KnFklwEEbbHAGA1Ct0BjtjYe2_ZdEsmiAtNPakotICp0Hr2cS0VpTQy29nrDn6_bCbr5zOmA-NWd-c-HrP_GMPtE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Data-Based Design of Multi-Model Inferential Sensors</title><source>arXiv.org</source><creator>Mojto, Martin ; Lubušký, Karol ; Fikar, Miroslav ; Paulen, Radoslav</creator><creatorcontrib>Mojto, Martin ; Lubušký, Karol ; Fikar, Miroslav ; Paulen, Radoslav</creatorcontrib><description>This paper deals with the problem of inferential (soft) sensor design. The nonlinear character of industrial processes is usually the main limitation to designing simple linear inferential sensors with sufficient accuracy. In order to increase the inferential sensor predictive performance and yet to maintain its linear structure, multi-model inferential sensors represent a straightforward option. In this contribution, we propose two novel approaches for the design of multi-model inferential sensors aiming to mitigate some drawbacks of the state-of-the-art approaches. For a demonstration of the developed techniques, we design inferential sensors for a Vacuum Gasoil Hydrogenation unit, which is a real-world petrochemical refinery unit. The performance of the multi-model inferential sensor is compared against various single-model inferential sensors and the current (referential) inferential sensor used in the refinery. The results show substantial improvements over the state-of-the-art design techniques for single-/multi-model inferential sensors.</description><identifier>DOI: 10.48550/arxiv.2308.02872</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2023-08</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2308.02872$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2308.02872$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Mojto, Martin</creatorcontrib><creatorcontrib>Lubušký, Karol</creatorcontrib><creatorcontrib>Fikar, Miroslav</creatorcontrib><creatorcontrib>Paulen, Radoslav</creatorcontrib><title>Data-Based Design of Multi-Model Inferential Sensors</title><description>This paper deals with the problem of inferential (soft) sensor design. The nonlinear character of industrial processes is usually the main limitation to designing simple linear inferential sensors with sufficient accuracy. In order to increase the inferential sensor predictive performance and yet to maintain its linear structure, multi-model inferential sensors represent a straightforward option. In this contribution, we propose two novel approaches for the design of multi-model inferential sensors aiming to mitigate some drawbacks of the state-of-the-art approaches. For a demonstration of the developed techniques, we design inferential sensors for a Vacuum Gasoil Hydrogenation unit, which is a real-world petrochemical refinery unit. The performance of the multi-model inferential sensor is compared against various single-model inferential sensors and the current (referential) inferential sensor used in the refinery. The results show substantial improvements over the state-of-the-art design techniques for single-/multi-model inferential sensors.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzr1OwzAUQGEvDKjwAEz4BZwa-7p2xtJSWqkVA92j6_gaWUoTZKeIvj30Zzrb0cfY04uswBkjp5h_00-ltHSVVM6qewZLHFG8YqHAl1TSV8-HyHfHbkxiNwTq-KaPlKkfE3b8k_oy5PLA7iJ2hR5vnbD96m2_WIvtx_tmMd8KnFklwEEbbHAGA1Ct0BjtjYe2_ZdEsmiAtNPakotICp0Hr2cS0VpTQy29nrDn6_bCbr5zOmA-NWd-c-HrP_GMPtE</recordid><startdate>20230805</startdate><enddate>20230805</enddate><creator>Mojto, Martin</creator><creator>Lubušký, Karol</creator><creator>Fikar, Miroslav</creator><creator>Paulen, Radoslav</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230805</creationdate><title>Data-Based Design of Multi-Model Inferential Sensors</title><author>Mojto, Martin ; Lubušký, Karol ; Fikar, Miroslav ; Paulen, Radoslav</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-484cd7d85ad4e92a553b5b4cc550fe7a54e38337e8fae2a8b4b360aa7759490b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Mojto, Martin</creatorcontrib><creatorcontrib>Lubušký, Karol</creatorcontrib><creatorcontrib>Fikar, Miroslav</creatorcontrib><creatorcontrib>Paulen, Radoslav</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Mojto, Martin</au><au>Lubušký, Karol</au><au>Fikar, Miroslav</au><au>Paulen, Radoslav</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Data-Based Design of Multi-Model Inferential Sensors</atitle><date>2023-08-05</date><risdate>2023</risdate><abstract>This paper deals with the problem of inferential (soft) sensor design. The nonlinear character of industrial processes is usually the main limitation to designing simple linear inferential sensors with sufficient accuracy. In order to increase the inferential sensor predictive performance and yet to maintain its linear structure, multi-model inferential sensors represent a straightforward option. In this contribution, we propose two novel approaches for the design of multi-model inferential sensors aiming to mitigate some drawbacks of the state-of-the-art approaches. For a demonstration of the developed techniques, we design inferential sensors for a Vacuum Gasoil Hydrogenation unit, which is a real-world petrochemical refinery unit. The performance of the multi-model inferential sensor is compared against various single-model inferential sensors and the current (referential) inferential sensor used in the refinery. The results show substantial improvements over the state-of-the-art design techniques for single-/multi-model inferential sensors.</abstract><doi>10.48550/arxiv.2308.02872</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2308.02872
ispartof
issn
language eng
recordid cdi_arxiv_primary_2308_02872
source arXiv.org
subjects Computer Science - Learning
title Data-Based Design of Multi-Model Inferential Sensors
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T08%3A53%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Data-Based%20Design%20of%20Multi-Model%20Inferential%20Sensors&rft.au=Mojto,%20Martin&rft.date=2023-08-05&rft_id=info:doi/10.48550/arxiv.2308.02872&rft_dat=%3Carxiv_GOX%3E2308_02872%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true