Prediction of load-bearing capacity of FRP-steel composite tubed concrete columns: Using explainable machine learning model with limited data

Simple item page
dc.check.date2025-12-03en
dc.check.infoAccess to this article is restricted until 12 months after publication by request of the publisheren
dc.contributor.authorLiu, Xiaoyangen
dc.contributor.authorSun, Guozhengen
dc.contributor.authorJu, Ruiqingen
dc.contributor.authorLi, Jingen
dc.contributor.authorLi, Zilien
dc.contributor.authorJiang, Yalien
dc.contributor.authorZhao, Kaien
dc.contributor.authorZhang, Yeen
dc.contributor.authorJing, Yucaien
dc.contributor.authorYang, Guotaoen
dc.contributor.funderNatural Science Foundation of Shandong Provinceen
dc.date.accessioned2024-12-18T12:17:54Z
dc.date.available2024-12-18T12:17:54Z
dc.date.issued2024-12-03en
dc.description.abstractThe complex interaction mechanism between the FRP jacket, steel tube, and confined concrete in the FRP-steel composite tubed concrete (F-STC) column makes the prediction of its mechanical behaviour a challenging task. This paper specifically investigates the application of machine learning models to predict the load-bearing capacity of F-STC columns. Since relatively few experimental works are performed on F-STC columns, the database established based on the test results from previous research contains only 69 data samples. In order to circumvent the training difficulties caused by the relatively small database, the application of the Gaussian process regression (GPR) model is trialled in this study. To make the predictions of the GPR model explainable, the Shapley additive explanations (SHAP) approach is incorporated with the GPR model in this study. Besides, four contrasting prediction models based on artificial neural network (ANN), support vector regression (SVR), decision tree (DT), and random forest (RF), are also proposed. The k-fold validation and test results indicate that the GPR model provides strong potential in predicting the load-bearing capacity of F-STC columns with high prediction accuracy and generalisation capability. Besides, 95 % and 99 % confidence intervals obtained by the GPR model are provided to show the uncertainty of the prediction results. Furthermore, the effect of the database size on the prediction performance of GPR, ANN, and SVR models is further examined by gradually reducing the number of data samples, and the comparisons illustrate the superiority of the GPR model.en
dc.description.sponsorshipNatural Science Foundation of Shandong Province, China (No. ZR2021QE235)en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.articleid107890en
dc.identifier.citationLiu, X., Sun, G., Ju, R., Li, J., Li, Z., Jiang, Y., Zhao, K., Zhang, Y., Jing, Y. and Yang, G. (2024) 'Prediction of load-bearing capacity of FRP-steel composite tubed concrete columns: Using explainable machine learning model with limited data', Structures, 71, 107890 (12pp). https://doi.org/10.1016/j.istruc.2024.107890en
dc.identifier.doihttps://doi.org/10.1016/j.istruc.2024.107890en
dc.identifier.endpage12en
dc.identifier.issn2352-0124en
dc.identifier.journaltitleStructuresen
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/16734
dc.identifier.volume71en
dc.language.isoenen
dc.publisherElsevier Ltd.en
dc.relation.ispartofStructuresen
dc.rights© 2024, Institution of Structural Engineers. Published by Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. This manuscript version is made available under the CC BY-NC-ND 4.0 license.en
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectF-STC columnsen
dc.subjectMachine learningen
dc.subjectGaussian process regressionen
dc.subjectShapley additive explanationen
dc.subjectSmall databaseen
dc.titlePrediction of load-bearing capacity of FRP-steel composite tubed concrete columns: Using explainable machine learning model with limited dataen
dc.typeArticle (peer-reviewed)en
oaire.citation.volume71en
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
Manuscript(clean version).docx
Size:
8.18 MB
Format:
Microsoft Word XML
Description:
Authors' original accepted version
Thumbnail Image
Name:
Manuscript(clean version).pdf
Size:
893.8 KB
Format:
Adobe Portable Document Format
Description:
Accepted Version
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Civil and Environmental Engineering - Journal articles