Investigation of the Extrapolation Capability of an Artificial Neural Network Algorithm in Combination with Process Signals in Resistance Spot Welding of Advanced High-Strength Steels

dc.contributor.authorEl-Sari, Bassel
dc.contributor.authorBiegler, Max
dc.contributor.authorRethmeier, Michael
dc.date.accessioned2021-12-13T12:00:38Z
dc.date.available2021-12-13T12:00:38Z
dc.date.issued2021-11-22
dc.date.updated2021-12-02T16:49:37Z
dc.description.abstractResistance spot welding is an established joining process for the production of safety-relevant components in the automotive industry. Therefore, consecutive process monitoring is essential to meet the high quality requirements. Artificial neural networks can be used to evaluate the process parameters and signals, to ensure individual spot weld quality. The predictive accuracy of such algorithms depends on the provided training data set, and the prediction of untrained data is challenging. The aim of this paper was to investigate the extrapolation capability of a multi-layer perceptron model. That means, the predictive performance of the model was tested with data that clearly differed from the training data in terms of material and coating composition. Therefore, three multi-layer perceptron regression models were implemented to predict the nugget diameter from process data. The three models were able to predict the training datasets very well. The models, which were provided with features from the dynamic resistance curve predicted the new dataset better than the model with only process parameters. This study shows the beneficial influence of process signals on the predictive accuracy and robustness of artificial neural network algorithms. Especially, when predicting a data set from outside of the training space.en
dc.identifier.eissn2075-4701
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/14042
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-12815
dc.language.isoenen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subject.ddc530 Physikde
dc.subject.otherautomotiveen
dc.subject.otherresistance spot weldingen
dc.subject.otherquality assuranceen
dc.subject.otherquality monitoringen
dc.subject.otherartificial intelligenceen
dc.titleInvestigation of the Extrapolation Capability of an Artificial Neural Network Algorithm in Combination with Process Signals in Resistance Spot Welding of Advanced High-Strength Steelsen
dc.typeArticleen
dc.type.versionpublishedVersionen
dcterms.bibliographicCitation.articlenumber1874en
dcterms.bibliographicCitation.doi10.3390/met11111874en
dcterms.bibliographicCitation.issue11en
dcterms.bibliographicCitation.journaltitleMetalsen
dcterms.bibliographicCitation.originalpublishernameMDPIen
dcterms.bibliographicCitation.originalpublisherplaceBaselen
dcterms.bibliographicCitation.volume11en
tub.accessrights.dnbfreeen
tub.affiliationFak. 5 Verkehrs- und Maschinensysteme::Inst. Werkzeugmaschinen und Fabrikbetrieb::FG Fügetechnikde
tub.affiliation.facultyFak. 5 Verkehrs- und Maschinensystemede
tub.affiliation.groupFG Fügetechnikde
tub.affiliation.instituteInst. Werkzeugmaschinen und Fabrikbetriebde
tub.publisher.universityorinstitutionTechnische Universität Berlinen

Files

Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
metals-11-01874.pdf
Size:
2.82 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.86 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections