From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning

This work develops a methodology for creating a data-driven digital twin from a library of physics-based models representing various asset states. The digital twin is updated using interpretable machine learning. Specifically, we use optimal trees---a recently developed scalable machine learning met...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-04
Hauptverfasser: Kapteyn, Michael G, Willcox, Karen E
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Kapteyn, Michael G
Willcox, Karen E
description This work develops a methodology for creating a data-driven digital twin from a library of physics-based models representing various asset states. The digital twin is updated using interpretable machine learning. Specifically, we use optimal trees---a recently developed scalable machine learning method---to train an interpretable data-driven classifier. Training data for the classifier are generated offline using simulated scenarios solved by the library of physics-based models. These data can be further augmented using experimental or other historical data. In operation, the classifier uses observational data from the asset to infer which physics-based models in the model library are the best candidates for the updated digital twin. The approach is demonstrated through the development of a structural digital twin for a 12ft wingspan unmanned aerial vehicle. This digital twin is built from a library of reduced-order models of the vehicle in a range of structural states. The data-driven digital twin dynamically updates in response to structural damage or degradation and enables the aircraft to replan a safe mission accordingly. Within this context, we study the performance of the optimal tree classifiers and demonstrate how their interpretability enables explainable structural assessments from sparse sensor measurements, and also informs optimal sensor placement.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2394444618</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2394444618</sourcerecordid><originalsourceid>FETCH-proquest_journals_23944446183</originalsourceid><addsrcrecordid>eNqNissKwjAQAIMgKNp_WPBcaBNb69UXChY8ePBWYrvWlZpoNlb8e3vwA5zLHGZ6YiiVisNsKuVABMy3KIpkOpNJoobitHH2Dofrh6nkcKEZK8hthQ2Dt3BwWFHpqUVYUU1eN3B8k2FoScPOeHQPh16fG4Rcl1cyCHvUzpCpx6J_0Q1j8PNITDbr43IbPpx9vpB9cbMvZ7pUSDWfdqRxpv67vl_XQZk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2394444618</pqid></control><display><type>article</type><title>From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning</title><source>Free E- Journals</source><creator>Kapteyn, Michael G ; Willcox, Karen E</creator><creatorcontrib>Kapteyn, Michael G ; Willcox, Karen E</creatorcontrib><description>This work develops a methodology for creating a data-driven digital twin from a library of physics-based models representing various asset states. The digital twin is updated using interpretable machine learning. Specifically, we use optimal trees---a recently developed scalable machine learning method---to train an interpretable data-driven classifier. Training data for the classifier are generated offline using simulated scenarios solved by the library of physics-based models. These data can be further augmented using experimental or other historical data. In operation, the classifier uses observational data from the asset to infer which physics-based models in the model library are the best candidates for the updated digital twin. The approach is demonstrated through the development of a structural digital twin for a 12ft wingspan unmanned aerial vehicle. This digital twin is built from a library of reduced-order models of the vehicle in a range of structural states. The data-driven digital twin dynamically updates in response to structural damage or degradation and enables the aircraft to replan a safe mission accordingly. Within this context, we study the performance of the optimal tree classifiers and demonstrate how their interpretability enables explainable structural assessments from sparse sensor measurements, and also informs optimal sensor placement.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Aging aircraft ; Classifiers ; Digital twins ; Machine learning ; Physics ; Reduced order models ; Structural damage ; Unmanned aerial vehicles ; Wing span</subject><ispartof>arXiv.org, 2020-04</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>776,780</link.rule.ids></links><search><creatorcontrib>Kapteyn, Michael G</creatorcontrib><creatorcontrib>Willcox, Karen E</creatorcontrib><title>From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning</title><title>arXiv.org</title><description>This work develops a methodology for creating a data-driven digital twin from a library of physics-based models representing various asset states. The digital twin is updated using interpretable machine learning. Specifically, we use optimal trees---a recently developed scalable machine learning method---to train an interpretable data-driven classifier. Training data for the classifier are generated offline using simulated scenarios solved by the library of physics-based models. These data can be further augmented using experimental or other historical data. In operation, the classifier uses observational data from the asset to infer which physics-based models in the model library are the best candidates for the updated digital twin. The approach is demonstrated through the development of a structural digital twin for a 12ft wingspan unmanned aerial vehicle. This digital twin is built from a library of reduced-order models of the vehicle in a range of structural states. The data-driven digital twin dynamically updates in response to structural damage or degradation and enables the aircraft to replan a safe mission accordingly. Within this context, we study the performance of the optimal tree classifiers and demonstrate how their interpretability enables explainable structural assessments from sparse sensor measurements, and also informs optimal sensor placement.</description><subject>Aging aircraft</subject><subject>Classifiers</subject><subject>Digital twins</subject><subject>Machine learning</subject><subject>Physics</subject><subject>Reduced order models</subject><subject>Structural damage</subject><subject>Unmanned aerial vehicles</subject><subject>Wing span</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNissKwjAQAIMgKNp_WPBcaBNb69UXChY8ePBWYrvWlZpoNlb8e3vwA5zLHGZ6YiiVisNsKuVABMy3KIpkOpNJoobitHH2Dofrh6nkcKEZK8hthQ2Dt3BwWFHpqUVYUU1eN3B8k2FoScPOeHQPh16fG4Rcl1cyCHvUzpCpx6J_0Q1j8PNITDbr43IbPpx9vpB9cbMvZ7pUSDWfdqRxpv67vl_XQZk</recordid><startdate>20200428</startdate><enddate>20200428</enddate><creator>Kapteyn, Michael G</creator><creator>Willcox, Karen E</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200428</creationdate><title>From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning</title><author>Kapteyn, Michael G ; Willcox, Karen E</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_23944446183</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Aging aircraft</topic><topic>Classifiers</topic><topic>Digital twins</topic><topic>Machine learning</topic><topic>Physics</topic><topic>Reduced order models</topic><topic>Structural damage</topic><topic>Unmanned aerial vehicles</topic><topic>Wing span</topic><toplevel>online_resources</toplevel><creatorcontrib>Kapteyn, Michael G</creatorcontrib><creatorcontrib>Willcox, Karen E</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kapteyn, Michael G</au><au>Willcox, Karen E</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning</atitle><jtitle>arXiv.org</jtitle><date>2020-04-28</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>This work develops a methodology for creating a data-driven digital twin from a library of physics-based models representing various asset states. The digital twin is updated using interpretable machine learning. Specifically, we use optimal trees---a recently developed scalable machine learning method---to train an interpretable data-driven classifier. Training data for the classifier are generated offline using simulated scenarios solved by the library of physics-based models. These data can be further augmented using experimental or other historical data. In operation, the classifier uses observational data from the asset to infer which physics-based models in the model library are the best candidates for the updated digital twin. The approach is demonstrated through the development of a structural digital twin for a 12ft wingspan unmanned aerial vehicle. This digital twin is built from a library of reduced-order models of the vehicle in a range of structural states. The data-driven digital twin dynamically updates in response to structural damage or degradation and enables the aircraft to replan a safe mission accordingly. Within this context, we study the performance of the optimal tree classifiers and demonstrate how their interpretability enables explainable structural assessments from sparse sensor measurements, and also informs optimal sensor placement.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-04
issn 2331-8422
language eng
recordid cdi_proquest_journals_2394444618
source Free E- Journals
subjects Aging aircraft
Classifiers
Digital twins
Machine learning
Physics
Reduced order models
Structural damage
Unmanned aerial vehicles
Wing span
title From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T10%3A25%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=From%20Physics-Based%20Models%20to%20Predictive%20Digital%20Twins%20via%20Interpretable%20Machine%20Learning&rft.jtitle=arXiv.org&rft.au=Kapteyn,%20Michael%20G&rft.date=2020-04-28&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2394444618%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2394444618&rft_id=info:pmid/&rfr_iscdi=true