Credibility Assessment of Machine Learning in a Manufacturing Process Application

Credibility Assessment of Machine Learning in a Manufacturing Process Application

We present a framework for establishing credibility of a machine learning (ML) model used to predict a key process control variable setting to maximize product quality in a component manufacturing application. Our model coupled a purely data-based ML model with a physics-based adjustment that encode...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of verification, validation, and uncertainty quantification validation, and uncertainty quantification, 2021-09, Vol.6 (3)
Hauptverfasser: Banyay, Gregory A, Worrell, Clarence L, Sidener, Scott E, Kaizer, Joshua S
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 3
container_start_page
container_title Journal of verification, validation, and uncertainty quantification
container_volume 6
creator Banyay, Gregory A
Worrell, Clarence L
Sidener, Scott E
Kaizer, Joshua S
description We present a framework for establishing credibility of a machine learning (ML) model used to predict a key process control variable setting to maximize product quality in a component manufacturing application. Our model coupled a purely data-based ML model with a physics-based adjustment that encoded subject matter expertise of the physical process. Establishing credibility of the resulting model provided the basis for eliminating a costly intermediate testing process that was previously used to determine the control variable setting.
doi_str_mv 10.1115/1.4051717
format Article
fullrecord <record><control><sourceid>asme_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1115_1_4051717</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1114498</sourcerecordid><originalsourceid>FETCH-LOGICAL-a180t-2b80339efa105d2546d515ba984b835fc44e2782bcd92ebe33e25535fa7334d53</originalsourceid><addsrcrecordid>eNo9kL1PwzAQxS0EElXpwM7glSHF54_EGaOILykIkGCObMcBV60T2cnQ_x5HrZju9O53p3cPoVsgWwAQD7DlREABxQVaUVYUGYU8v_zvhbxGmxh3hBDIATiFFfqsg-2cdns3HXEVo43xYP2Ehx6_KfPrvMWNVcE7_4Odxyqpfu6VmeawSB9hMGkFV-O4d0ZNbvA36KpX-2g357pG30-PX_VL1rw_v9ZVkymQZMqoloSx0vYKiOio4HknQGhVSq4lE73h3NJCUm26klptGbNUiDRQBWO8E2yN7k93TRhiDLZvx-AOKhxbIO0SRwvtOY7E3p1Ylb5rd8McfLK2UJyXkv0BE3tamQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Credibility Assessment of Machine Learning in a Manufacturing Process Application</title><source>ASME Transactions Journals (Current)</source><creator>Banyay, Gregory A ; Worrell, Clarence L ; Sidener, Scott E ; Kaizer, Joshua S</creator><creatorcontrib>Banyay, Gregory A ; Worrell, Clarence L ; Sidener, Scott E ; Kaizer, Joshua S</creatorcontrib><description>We present a framework for establishing credibility of a machine learning (ML) model used to predict a key process control variable setting to maximize product quality in a component manufacturing application. Our model coupled a purely data-based ML model with a physics-based adjustment that encoded subject matter expertise of the physical process. Establishing credibility of the resulting model provided the basis for eliminating a costly intermediate testing process that was previously used to determine the control variable setting.</description><identifier>ISSN: 2377-2158</identifier><identifier>EISSN: 2377-2166</identifier><identifier>DOI: 10.1115/1.4051717</identifier><language>eng</language><publisher>ASME</publisher><ispartof>Journal of verification, validation, and uncertainty quantification, 2021-09, Vol.6 (3)</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a180t-2b80339efa105d2546d515ba984b835fc44e2782bcd92ebe33e25535fa7334d53</citedby><cites>FETCH-LOGICAL-a180t-2b80339efa105d2546d515ba984b835fc44e2782bcd92ebe33e25535fa7334d53</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27923,27924,38519</link.rule.ids></links><search><creatorcontrib>Banyay, Gregory A</creatorcontrib><creatorcontrib>Worrell, Clarence L</creatorcontrib><creatorcontrib>Sidener, Scott E</creatorcontrib><creatorcontrib>Kaizer, Joshua S</creatorcontrib><title>Credibility Assessment of Machine Learning in a Manufacturing Process Application</title><title>Journal of verification, validation, and uncertainty quantification</title><addtitle>J. Verif. Valid. Uncert</addtitle><description>We present a framework for establishing credibility of a machine learning (ML) model used to predict a key process control variable setting to maximize product quality in a component manufacturing application. Our model coupled a purely data-based ML model with a physics-based adjustment that encoded subject matter expertise of the physical process. Establishing credibility of the resulting model provided the basis for eliminating a costly intermediate testing process that was previously used to determine the control variable setting.</description><issn>2377-2158</issn><issn>2377-2166</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNo9kL1PwzAQxS0EElXpwM7glSHF54_EGaOILykIkGCObMcBV60T2cnQ_x5HrZju9O53p3cPoVsgWwAQD7DlREABxQVaUVYUGYU8v_zvhbxGmxh3hBDIATiFFfqsg-2cdns3HXEVo43xYP2Ehx6_KfPrvMWNVcE7_4Odxyqpfu6VmeawSB9hMGkFV-O4d0ZNbvA36KpX-2g357pG30-PX_VL1rw_v9ZVkymQZMqoloSx0vYKiOio4HknQGhVSq4lE73h3NJCUm26klptGbNUiDRQBWO8E2yN7k93TRhiDLZvx-AOKhxbIO0SRwvtOY7E3p1Ylb5rd8McfLK2UJyXkv0BE3tamQ</recordid><startdate>20210901</startdate><enddate>20210901</enddate><creator>Banyay, Gregory A</creator><creator>Worrell, Clarence L</creator><creator>Sidener, Scott E</creator><creator>Kaizer, Joshua S</creator><general>ASME</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20210901</creationdate><title>Credibility Assessment of Machine Learning in a Manufacturing Process Application</title><author>Banyay, Gregory A ; Worrell, Clarence L ; Sidener, Scott E ; Kaizer, Joshua S</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a180t-2b80339efa105d2546d515ba984b835fc44e2782bcd92ebe33e25535fa7334d53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Banyay, Gregory A</creatorcontrib><creatorcontrib>Worrell, Clarence L</creatorcontrib><creatorcontrib>Sidener, Scott E</creatorcontrib><creatorcontrib>Kaizer, Joshua S</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of verification, validation, and uncertainty quantification</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Banyay, Gregory A</au><au>Worrell, Clarence L</au><au>Sidener, Scott E</au><au>Kaizer, Joshua S</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Credibility Assessment of Machine Learning in a Manufacturing Process Application</atitle><jtitle>Journal of verification, validation, and uncertainty quantification</jtitle><stitle>J. Verif. Valid. Uncert</stitle><date>2021-09-01</date><risdate>2021</risdate><volume>6</volume><issue>3</issue><issn>2377-2158</issn><eissn>2377-2166</eissn><abstract>We present a framework for establishing credibility of a machine learning (ML) model used to predict a key process control variable setting to maximize product quality in a component manufacturing application. Our model coupled a purely data-based ML model with a physics-based adjustment that encoded subject matter expertise of the physical process. Establishing credibility of the resulting model provided the basis for eliminating a costly intermediate testing process that was previously used to determine the control variable setting.</abstract><pub>ASME</pub><doi>10.1115/1.4051717</doi></addata></record>
fulltext fulltext
identifier ISSN: 2377-2158
ispartof Journal of verification, validation, and uncertainty quantification, 2021-09, Vol.6 (3)
issn 2377-2158
2377-2166
language eng
recordid cdi_crossref_primary_10_1115_1_4051717
source ASME Transactions Journals (Current)
title Credibility Assessment of Machine Learning in a Manufacturing Process Application
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T20%3A41%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-asme_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Credibility%20Assessment%20of%20Machine%20Learning%20in%20a%20Manufacturing%20Process%20Application&rft.jtitle=Journal%20of%20verification,%20validation,%20and%20uncertainty%20quantification&rft.au=Banyay,%20Gregory%20A&rft.date=2021-09-01&rft.volume=6&rft.issue=3&rft.issn=2377-2158&rft.eissn=2377-2166&rft_id=info:doi/10.1115/1.4051717&rft_dat=%3Casme_cross%3E1114498%3C/asme_cross%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