Data-driven process characterization and adaptive control in robotic arc welding

Robotic arc welding (RAW) has been an essential process in various assembly systems, such as automotive manufacturing. However, its implementations lack adaptivity to compensate for process variations. This paper presents a data-driven process characterization and online adaptive control framework f...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:CIRP annals Ročník 71; číslo 1; s. 45 - 48
Hlavní autoři: Wang, Peng, Kershaw, Joseph, Russell, Matthew, Zhang, Jianjing, Zhang, Yuming, Gao, Robert X.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 2022
Témata:
ISSN:0007-8506
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Robotic arc welding (RAW) has been an essential process in various assembly systems, such as automotive manufacturing. However, its implementations lack adaptivity to compensate for process variations. This paper presents a data-driven process characterization and online adaptive control framework for RAW to automatically and efficiently achieve desired weld pool condition, given any initial conditions. Based on optical imaging, pool width is characterized through a pixel-level image segmentation network and then used for determining the parameter adjustment for robotic execution through a gradient-based controller. Experiments demonstrate quick process convergence within 7 adjustment periods and an error band within 10.9%.
AbstractList Robotic arc welding (RAW) has been an essential process in various assembly systems, such as automotive manufacturing. However, its implementations lack adaptivity to compensate for process variations. This paper presents a data-driven process characterization and online adaptive control framework for RAW to automatically and efficiently achieve desired weld pool condition, given any initial conditions. Based on optical imaging, pool width is characterized through a pixel-level image segmentation network and then used for determining the parameter adjustment for robotic execution through a gradient-based controller. Experiments demonstrate quick process convergence within 7 adjustment periods and an error band within 10.9%.
Author Zhang, Jianjing
Kershaw, Joseph
Wang, Peng
Zhang, Yuming
Gao, Robert X.
Russell, Matthew
Author_xml – sequence: 1
  givenname: Peng
  orcidid: 0000-0003-3098-009X
  surname: Wang
  fullname: Wang, Peng
  email: Edward.Wang@uky.edu
  organization: Department of Electrical and Computer Engineering University of Kentucky, Lexington, KY, United States of America
– sequence: 2
  givenname: Joseph
  orcidid: 0000-0001-8324-8658
  surname: Kershaw
  fullname: Kershaw, Joseph
  organization: Department of Mechanical Engineering, University of Kentucky, Lexington, KY, United States of America
– sequence: 3
  givenname: Matthew
  surname: Russell
  fullname: Russell, Matthew
  organization: Department of Electrical and Computer Engineering University of Kentucky, Lexington, KY, United States of America
– sequence: 4
  givenname: Jianjing
  orcidid: 0000-0002-5760-6893
  surname: Zhang
  fullname: Zhang, Jianjing
  organization: Department of Mechanical and Aerospace Engineering, Case Western Reserve University, Cleveland, OH, United States of America
– sequence: 5
  givenname: Yuming
  surname: Zhang
  fullname: Zhang, Yuming
  organization: Department of Electrical and Computer Engineering University of Kentucky, Lexington, KY, United States of America
– sequence: 6
  givenname: Robert X.
  orcidid: 0000-0003-3595-3728
  surname: Gao
  fullname: Gao, Robert X.
  organization: Department of Mechanical and Aerospace Engineering, Case Western Reserve University, Cleveland, OH, United States of America
BookMark eNp9kM1KAzEUhbOoYFt9AVd5gRmTTDOTghupv1DQha7DnZuMpozJkISKPr0z1pWLwoGzud-F8y3IzAdvCbngrOSM15e7El0cSsGEKNlqTD0jc8ZYUyjJ6lOySGnHmJSsEXPyfAMZChPd3no6xIA2JYrvEAGzje4bsguegjcUDAx5PKMYfI6hp87TGNqQHVKISD9tb5x_OyMnHfTJnv_1krze3b5sHort0_3j5npboOAyFxKRGdV0qmWGdwp42_C2QiuVUaAApRLr2poOANcNqraaeqxOWiOrTlRLIg5_MYaUou30EN0HxC_NmZ486J2ePOjJg2arMfUIqX8Quvw7MUdw_XH06oDacdTe2agTOuvRGhctZm2CO4b_AHp1gAs
CitedBy_id crossref_primary_10_1109_TIM_2025_3563002
crossref_primary_10_3390_jmmp6060135
crossref_primary_10_1007_s40194_025_02020_7
crossref_primary_10_1016_j_rcim_2025_102992
crossref_primary_10_1126_sciadv_adw7071
crossref_primary_10_1016_j_jmapro_2023_11_025
crossref_primary_10_1016_j_jmapro_2024_07_142
crossref_primary_10_1038_s41467_025_60164_y
crossref_primary_10_1016_j_oceaneng_2024_119294
Cites_doi 10.1109/ACCESS.2020.2998052
10.1016/j.jmapro.2020.04.044
10.1016/S0007-8506(07)62060-5
10.1016/j.matdes.2008.04.052
10.1016/j.cirp.2015.04.119
10.1016/j.cirp.2008.03.120
10.1016/j.cirp.2020.04.110
10.1016/j.cirp.2016.04.024
10.1016/j.jmapro.2018.10.042
10.1016/j.jmapro.2021.09.023
10.1016/j.cirp.2019.04.095
ContentType Journal Article
Copyright 2022 CIRP
Copyright_xml – notice: 2022 CIRP
DBID AAYXX
CITATION
DOI 10.1016/j.cirp.2022.04.046
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EndPage 48
ExternalDocumentID 10_1016_j_cirp_2022_04_046
S0007850622000920
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
29B
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AABNK
AABXZ
AACTN
AAEDT
AAEDW
AAEPC
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
ABDEX
ABMAC
ABXDB
ABXRA
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ADBBV
ADEZE
ADIYS
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AEZYN
AFKWA
AFRZQ
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
GBLVA
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LY7
M41
MAGPM
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RNS
ROL
RPZ
SDF
SDG
SES
SET
SPC
SSM
SST
SSZ
T5K
WUQ
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c215t-5cc0d87f8b0d1f8a1b71b3ce58d8a8ac58296edfaac97c8b3ac978b3f5ed53f23
ISSN 0007-8506
IngestDate Tue Nov 18 21:09:38 EST 2025
Sat Nov 29 07:30:15 EST 2025
Fri Feb 23 02:38:26 EST 2024
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Welding
Robot
Adaptive control
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c215t-5cc0d87f8b0d1f8a1b71b3ce58d8a8ac58296edfaac97c8b3ac978b3f5ed53f23
ORCID 0000-0003-3098-009X
0000-0003-3595-3728
0000-0002-5760-6893
0000-0001-8324-8658
PageCount 4
ParticipantIDs crossref_primary_10_1016_j_cirp_2022_04_046
crossref_citationtrail_10_1016_j_cirp_2022_04_046
elsevier_sciencedirect_doi_10_1016_j_cirp_2022_04_046
PublicationCentury 2000
PublicationDate 2022
2022-00-00
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – year: 2022
  text: 2022
PublicationDecade 2020
PublicationTitle CIRP annals
PublicationYear 2022
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Kershaw, Y, Zhang, Wang (bib0007) 2021; 71
Deng (bib0010) 2009; 30
Krueger, Lehr, Schlueter, Bischoff (bib0012) 2019; 68
Zhang, Li, Gui, Li (bib0006) 2018; 36
Lanzett, Santochi, Tantussi (bib0004) 2001; 50
Masinelli, Le-Quang, Zanoli, Wasmer, Shevchik (bib0008) 2020; 8
Ceglarek, Colledan, Váncza, Kim, Marine, Kogel-Hollacher, Mistry, Bolognese (bib0003) 2015; 64
Reinhart, Munzert, Vogl (bib0001) 2008; 57
Ozcelik, Moore (bib0011) 2003
Ruder (bib0013) 2016
Erdős, Kovács, Váncza (bib0002) 2016; 65
Wang, Jiao, Wang, Zhang (bib0009) 2021; 63
Franciosa, Sokolov, Sinha, Sun, Ceglarek (bib0005) 2020; 69
Erdős (10.1016/j.cirp.2022.04.046_bib0002) 2016; 65
Kershaw (10.1016/j.cirp.2022.04.046_bib0007) 2021; 71
Deng (10.1016/j.cirp.2022.04.046_bib0010) 2009; 30
Wang (10.1016/j.cirp.2022.04.046_bib0009) 2021; 63
Ruder (10.1016/j.cirp.2022.04.046_bib0013) 2016
Ozcelik (10.1016/j.cirp.2022.04.046_bib0011) 2003
Krueger (10.1016/j.cirp.2022.04.046_bib0012) 2019; 68
Lanzett (10.1016/j.cirp.2022.04.046_bib0004) 2001; 50
Masinelli (10.1016/j.cirp.2022.04.046_bib0008) 2020; 8
Reinhart (10.1016/j.cirp.2022.04.046_bib0001) 2008; 57
Zhang (10.1016/j.cirp.2022.04.046_bib0006) 2018; 36
Franciosa (10.1016/j.cirp.2022.04.046_bib0005) 2020; 69
Ceglarek (10.1016/j.cirp.2022.04.046_bib0003) 2015; 64
References_xml – year: 2016
  ident: bib0013
  article-title: An Overview of Gradient Descent Optimization Algorithms
– volume: 68
  start-page: 9
  year: 2019
  end-page: 12
  ident: bib0012
  article-title: Deep learning for part identification based on inherent features
  publication-title: CIRP Annals
– volume: 50
  start-page: 13
  year: 2001
  end-page: 16
  ident: bib0004
  article-title: On-line control of robotized Gas Metal Arc Welding
  publication-title: CIRP Annals
– volume: 65
  start-page: 451
  year: 2016
  end-page: 454
  ident: bib0002
  article-title: Optimized joint motion planning for redundant industrial robots
  publication-title: CIRP Annals
– volume: 69
  start-page: 369
  year: 2020
  end-page: 372
  ident: bib0005
  article-title: Deep learning enhanced digital twin for closed-loop in-process quality improvement
  publication-title: CIRP Annals
– volume: 30
  start-page: 359
  year: 2009
  end-page: 366
  ident: bib0010
  article-title: FEM prediction of welding residual stress & distortion in carbon steel considering phase transformation effects
  publication-title: Mater. Des.
– volume: 71
  start-page: 374
  year: 2021
  end-page: 383
  ident: bib0007
  article-title: Hybrid machine learning-enabled adaptive welding speed control
  publication-title: J. Manuf. Proc.
– volume: 36
  start-page: 434
  year: 2018
  end-page: 441
  ident: bib0006
  article-title: Adaptive control for laser welding with filler wire of marine high strength steel with tight butt joints for large structures
  publication-title: J. Manuf. Proc.
– volume: 57
  start-page: 37
  year: 2008
  end-page: 40
  ident: bib0001
  article-title: A programming system for robot-based remote-laser-welding with conventional optics
  publication-title: CIRP Annals
– volume: 64
  start-page: 389
  year: 2015
  end-page: 394
  ident: bib0003
  article-title: Rapid deployment of remote laser welding processes in automotive assembly systems
  publication-title: CIRP Annals
– volume: 8
  start-page: 103803
  year: 2020
  end-page: 103814
  ident: bib0008
  article-title: Adaptive laser welding control: a reinforcement learning approach
  publication-title: IEEE Access
– volume: 63
  start-page: 2
  year: 2021
  end-page: 13
  ident: bib0009
  article-title: A tutorial on deep learning-based data analytics in manufacturing through a welding case study
  publication-title: J. Manuf. Proc.
– year: 2003
  ident: bib0011
  article-title: Modeling, Sensing and Control of Gas Metal Arc Welding
– volume: 8
  start-page: 103803
  year: 2020
  ident: 10.1016/j.cirp.2022.04.046_bib0008
  article-title: Adaptive laser welding control: a reinforcement learning approach
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2998052
– volume: 63
  start-page: 2
  year: 2021
  ident: 10.1016/j.cirp.2022.04.046_bib0009
  article-title: A tutorial on deep learning-based data analytics in manufacturing through a welding case study
  publication-title: J. Manuf. Proc.
  doi: 10.1016/j.jmapro.2020.04.044
– volume: 50
  start-page: 13
  issue: 1
  year: 2001
  ident: 10.1016/j.cirp.2022.04.046_bib0004
  article-title: On-line control of robotized Gas Metal Arc Welding
  publication-title: CIRP Annals
  doi: 10.1016/S0007-8506(07)62060-5
– year: 2003
  ident: 10.1016/j.cirp.2022.04.046_bib0011
– volume: 30
  start-page: 359
  year: 2009
  ident: 10.1016/j.cirp.2022.04.046_bib0010
  article-title: FEM prediction of welding residual stress & distortion in carbon steel considering phase transformation effects
  publication-title: Mater. Des.
  doi: 10.1016/j.matdes.2008.04.052
– volume: 64
  start-page: 389
  issue: 1
  year: 2015
  ident: 10.1016/j.cirp.2022.04.046_bib0003
  article-title: Rapid deployment of remote laser welding processes in automotive assembly systems
  publication-title: CIRP Annals
  doi: 10.1016/j.cirp.2015.04.119
– year: 2016
  ident: 10.1016/j.cirp.2022.04.046_bib0013
– volume: 57
  start-page: 37
  issue: 1
  year: 2008
  ident: 10.1016/j.cirp.2022.04.046_bib0001
  article-title: A programming system for robot-based remote-laser-welding with conventional optics
  publication-title: CIRP Annals
  doi: 10.1016/j.cirp.2008.03.120
– volume: 69
  start-page: 369
  issue: 1
  year: 2020
  ident: 10.1016/j.cirp.2022.04.046_bib0005
  article-title: Deep learning enhanced digital twin for closed-loop in-process quality improvement
  publication-title: CIRP Annals
  doi: 10.1016/j.cirp.2020.04.110
– volume: 65
  start-page: 451
  issue: 1
  year: 2016
  ident: 10.1016/j.cirp.2022.04.046_bib0002
  article-title: Optimized joint motion planning for redundant industrial robots
  publication-title: CIRP Annals
  doi: 10.1016/j.cirp.2016.04.024
– volume: 36
  start-page: 434
  year: 2018
  ident: 10.1016/j.cirp.2022.04.046_bib0006
  article-title: Adaptive control for laser welding with filler wire of marine high strength steel with tight butt joints for large structures
  publication-title: J. Manuf. Proc.
  doi: 10.1016/j.jmapro.2018.10.042
– volume: 71
  start-page: 374
  year: 2021
  ident: 10.1016/j.cirp.2022.04.046_bib0007
  article-title: Hybrid machine learning-enabled adaptive welding speed control
  publication-title: J. Manuf. Proc.
  doi: 10.1016/j.jmapro.2021.09.023
– volume: 68
  start-page: 9
  issue: 1
  year: 2019
  ident: 10.1016/j.cirp.2022.04.046_bib0012
  article-title: Deep learning for part identification based on inherent features
  publication-title: CIRP Annals
  doi: 10.1016/j.cirp.2019.04.095
SSID ssj0055072
Score 2.4326646
Snippet Robotic arc welding (RAW) has been an essential process in various assembly systems, such as automotive manufacturing. However, its implementations lack...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 45
SubjectTerms Adaptive control
Robot
Welding
Title Data-driven process characterization and adaptive control in robotic arc welding
URI https://dx.doi.org/10.1016/j.cirp.2022.04.046
Volume 71
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0007-8506
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0055072
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Li9swEBZptof2UPqk2xc69BZcHHllScel3dLdwxLaLeRmJFmiCcEJTvbx8zuyRombLUtbKBg7NpYVNB8znx7ziZD3THProd-VcSDzGYQAkalCF5njuS1K4BPcm26zCXF-LqdTNRkMfMqFuVqIppE3N2r1X00Nz8DYIXX2L8y9_Sg8gN9gdDiD2eH8R4b_pDc6q9vgxUarmAYQ0ntRljlmXUaJ1lqvuoVDabl6SG1ZmmUn4dra0bVbbANb0jI4_TqBskFzeTcSH73FxOGrnfdu1z_0dW-GIU3rXK7XONGBG43fGrg-A7zOU7U4HMF23dZthsxuOVL0uBAFeV72PW7cdOUXZEX3GZUlMRBHBc5bLj6ONsw_2FmnN8pYJ1V7tKen3UXobx0DgspZSEhSLL9HDpjgSg7JwfHpyfQsxewg6hZ15fHfYnpVXAm4X9PvKUyPllw8Jo-wP0GPIw6ekIFrnpKHPZXJZ2TSQwRFRNB9RFBABE2IoIgIOmsoIoICIigi4jn5_vnk4uOXDDfSyCwwuk3Grc1rKbw0eT32Uo-NGJvCOi5rqaW2XDJVutprbZWw0hThChfPXc0Lz4oXZNgsG_eSUM0ZkFpmvBclcD9lnCpsLrQFHuiYNodknNqmsqgyHzY7WVRpOeG8Cu1Zhfas8iM4ykMy2pZZRY2VO9_mqckrZImR_VWAkDvKvfrHcq_Jg3AXh93ekOGmvXRvyX17tZmt23cIpJ82GI-5
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Data-driven+process+characterization+and+adaptive+control+in+robotic+arc+welding&rft.jtitle=CIRP+annals&rft.au=Wang%2C+Peng&rft.au=Kershaw%2C+Joseph&rft.au=Russell%2C+Matthew&rft.au=Zhang%2C+Jianjing&rft.date=2022&rft.pub=Elsevier+Ltd&rft.issn=0007-8506&rft.volume=71&rft.issue=1&rft.spage=45&rft.epage=48&rft_id=info:doi/10.1016%2Fj.cirp.2022.04.046&rft.externalDocID=S0007850622000920
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0007-8506&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0007-8506&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0007-8506&client=summon