Comparative Study on Different Methods to Generate Synthetic Data for the Classification of THT Solder Joints
Automated Optical Inspection (AOI) is still one of the major tools for the quality control of solder joints; especially, if the requirements for the solder joints' mechanical and electrical properties are high. This is the case for products in the automotive sector, e.g. air bags or brake syste...
Saved in:
Published in | 2024 1st International Conference on Production Technologies and Systems for E-Mobility (EPTS) pp. 1 - 6 |
---|---|
Main Authors | , , , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
05.06.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Automated Optical Inspection (AOI) is still one of the major tools for the quality control of solder joints; especially, if the requirements for the solder joints' mechanical and electrical properties are high. This is the case for products in the automotive sector, e.g. air bags or brake systems. Conventional test routines are time-consuming to define and not flexible regarding quality limits and lead to a high amount of manual reinspection. Thus, Artificial Intelligence offers the potential to address these disadvantages. Artificial Intelligence, on the other hand, suffers from highly imbalanced datasets resulting from the low amount of defects on solder joint level. One possibility to face this challenge is the utilization of synthetic data. This work compares different methods to generate data using both conventional data augmentation and deep generative models as well as virtual world rendering in order to enhance dataset quality in general. These are applied to an industrial dataset of THT solder joints. All tested approaches lead to an improvement in model quality. The best results are achieved with synthetic images from a Generative Adversarial Network, relatively increasing performance by around 6 % while minimizing error slip. |
---|---|
AbstractList | Automated Optical Inspection (AOI) is still one of the major tools for the quality control of solder joints; especially, if the requirements for the solder joints' mechanical and electrical properties are high. This is the case for products in the automotive sector, e.g. air bags or brake systems. Conventional test routines are time-consuming to define and not flexible regarding quality limits and lead to a high amount of manual reinspection. Thus, Artificial Intelligence offers the potential to address these disadvantages. Artificial Intelligence, on the other hand, suffers from highly imbalanced datasets resulting from the low amount of defects on solder joint level. One possibility to face this challenge is the utilization of synthetic data. This work compares different methods to generate data using both conventional data augmentation and deep generative models as well as virtual world rendering in order to enhance dataset quality in general. These are applied to an industrial dataset of THT solder joints. All tested approaches lead to an improvement in model quality. The best results are achieved with synthetic images from a Generative Adversarial Network, relatively increasing performance by around 6 % while minimizing error slip. |
Author | Franke, Jorg Seidel, Reinhardt Rachinger, Ben Schroder, Felix Thielen, Nils Preitschaft, Anja Reinhardt, Andreas Meier, Sven |
Author_xml | – sequence: 1 givenname: Nils surname: Thielen fullname: Thielen, Nils email: nils.thielen@faps.fau.de organization: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Insitute for Factory Automation and Production Systems (FAPS),Nuremberg,Germany – sequence: 2 givenname: Ben surname: Rachinger fullname: Rachinger, Ben email: ben.rachinger@faps.fau.de organization: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Insitute for Factory Automation and Production Systems (FAPS),Nuremberg,Germany – sequence: 3 givenname: Felix surname: Schroder fullname: Schroder, Felix email: felix.schroeder@fau.de organization: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Insitute for Factory Automation and Production Systems (FAPS),Nuremberg,Germany – sequence: 4 givenname: Anja surname: Preitschaft fullname: Preitschaft, Anja email: anja.preitschaft@faps.fau.de organization: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Insitute for Factory Automation and Production Systems (FAPS),Nuremberg,Germany – sequence: 5 givenname: Sven surname: Meier fullname: Meier, Sven email: sven.meier@faps.fau.de organization: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Insitute for Factory Automation and Production Systems (FAPS),Nuremberg,Germany – sequence: 6 givenname: Reinhardt surname: Seidel fullname: Seidel, Reinhardt email: reinhardt.seidel@faps.fau.de organization: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Insitute for Factory Automation and Production Systems (FAPS),Nuremberg,Germany – sequence: 7 givenname: Andreas surname: Reinhardt fullname: Reinhardt, Andreas email: andreas.reinhardt@seho.de organization: SEHO Systems GmbH,Kreuzwertheim,Germany – sequence: 8 givenname: Jorg surname: Franke fullname: Franke, Jorg email: joerg.franke@faps.fau.de organization: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Insitute for Factory Automation and Production Systems (FAPS),Nuremberg,Germany |
BookMark | eNo1kMtKw0AYRkfQhda-geD_AomZS-aylLS2SkUhcV2myT90IJkpySj07Q1YV4cPDmfx3ZHrEAMS8kiLnNLCPK0_m1pSoVnOCiZyWpRaKlFckaVRRvOy4FpSxW7JUMXhZEeb_A9Cnb67M8QAK-8cjhgSvGM6xm6CFGGDAWdx1s4hHTH5FlY2WXBxhHlD1dtp8s63c2xuRAfNtoE69h2O8BZ9SNM9uXG2n3B54YJ8vaybapvtPjav1fMu85SLlFGLvDQttooyoUqjWmVU15XMKM2k4lYLTfVBzuxEKTSXxmlOW6cPxqF0fEEe_roeEfen0Q92PO__X-C_bz5XZQ |
ContentType | Conference Proceeding |
DBID | 6IE 6IL CBEJK RIE RIL |
DOI | 10.1109/EPTS61482.2024.10586740 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE IEEE Proceedings Order Plans (POP All) 1998-Present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
EISBN | 9798350386172 |
EndPage | 6 |
ExternalDocumentID | 10586740 |
Genre | orig-research |
GroupedDBID | 6IE 6IL CBEJK RIE RIL |
ID | FETCH-LOGICAL-i134t-1ae359cec71247597c797dd529782673a84818b6a84d4548369f831cf8b9fe6f3 |
IEDL.DBID | RIE |
IngestDate | Wed Jul 17 05:50:34 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-i134t-1ae359cec71247597c797dd529782673a84818b6a84d4548369f831cf8b9fe6f3 |
PageCount | 6 |
ParticipantIDs | ieee_primary_10586740 |
PublicationCentury | 2000 |
PublicationDate | 2024-June-5 |
PublicationDateYYYYMMDD | 2024-06-05 |
PublicationDate_xml | – month: 06 year: 2024 text: 2024-June-5 day: 05 |
PublicationDecade | 2020 |
PublicationTitle | 2024 1st International Conference on Production Technologies and Systems for E-Mobility (EPTS) |
PublicationTitleAbbrev | EPTS |
PublicationYear | 2024 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
Score | 1.9181314 |
Snippet | Automated Optical Inspection (AOI) is still one of the major tools for the quality control of solder joints; especially, if the requirements for the solder... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 1 |
SubjectTerms | Adaptive optics Artificial Intelligence Automated Optical Inspection Electronics Production Mechanical factors Optical imaging Production Quality control Rendering (computer graphics) Safety devices Synthetic Data |
Title | Comparative Study on Different Methods to Generate Synthetic Data for the Classification of THT Solder Joints |
URI | https://ieeexplore.ieee.org/document/10586740 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3LS8MwGA-6kycVJ775Dl5b1yZpkvMejMHGYB3sNto8YIituOww_3qTtHMoCJ76IJCQr-XLl_weCD0rQXWqeyoqifa7VUZGhT8uzLhPt4Yqyj13eDrLxksyWdFVS1YPXBitdQCf6djfhrN8Vcud3ypzfzjlGSOuQj_lvbQha7WYraQnXobzfBF0LV3Zl5L40PqHb0pIG6NzNDt02KBFXuOdLWP5-UuL8d8jukDdI0MP5t-55xKd6OoKvfWPUt7gAYJ7qCsYtBYoFqbBLXoLtoZGbdq6ZvvKLQHd1wODwhbglrDgniF4ZXoUUQgc1AbycQ6L2nt6w6TeVHbbRcvRMO-Po9ZOIdokmNgoKTSmQmrJXE5nrpCQTDClaOoKyTRjuPDK-rzM3FURV8jgTBiOE2l4KYzODL5Gnaqu9A0CyQqpijJhUmBiBOXeAomyHi-owkSJW9T1c7V-bxQz1odpuvvj_T068yELECz6gDr2Y6cfXbK35VMI8hd6z6sz |
link.rule.ids | 310,311,786,790,795,796,802,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1NS8MwGA4yD3pSceK3OXhtXdukSc77oM5tDNbBbiPNBwyxFZcd5q83STuHguCpTQi05G158ibP-zwAPEqGVaw6MiiQcrtVWgTcHRem1MGtxhJTVzs8nqTZHA0XeNEUq_taGKWUJ5-p0N36s3xZiY3bKrN_OKYpQTZDP7RA32F1uVbD2rLtp_40n3llS5v4xSjcjf_hnOKBY3ACJrtH1nyR13BjilB8_lJj_Pc7nYL2vkYPTr_R5wwcqPIcvHX3Yt7QUQS3sCphrzFBMXDs_aLX0FSw1ps2dti2tItA-_3AHjcc2kUstG3o3TIdj8iHDlYa5lkOZ5Vz9YbDalWadRvMB_28mwWNoUKwihJkgoirBDOhBLGoTmwqIQgjUuLYppJxShLutPVpkdqrRDaVSVKmaRIJTQumVaqTC9Aqq1JdAigIF5IXEREsQZph6kyQMOlQjmWCJLsCbTdXy_daM2O5m6brP_ofwFGWj0fL0fPk5QYcu_B5Qha-BS3zsVF3FvpNce8D_gWw6a6J |
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%3Abook&rft.genre=proceeding&rft.title=2024+1st+International+Conference+on+Production+Technologies+and+Systems+for+E-Mobility+%28EPTS%29&rft.atitle=Comparative+Study+on+Different+Methods+to+Generate+Synthetic+Data+for+the+Classification+of+THT+Solder+Joints&rft.au=Thielen%2C+Nils&rft.au=Rachinger%2C+Ben&rft.au=Schroder%2C+Felix&rft.au=Preitschaft%2C+Anja&rft.date=2024-06-05&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FEPTS61482.2024.10586740&rft.externalDocID=10586740 |