A machine learning-based structural load estimation model for shear-critical RC beams and slabs using multifractal analysis

Osei, Jack Banahene; Adom-Asamoah, Mark; Owusu Twumasi, Jones; Andras, Peter; Zhang, Hexin

doi:10.1016/j.conbuildmat.2023.132250

A machine learning-based structural load estimation model for shear-critical RC beams and slabs using multifractal analysis

Osei, Jack Banahene; Adom-Asamoah, Mark; Owusu Twumasi, Jones; Andras, Peter; Zhang, Hexin

Authors

Jack Banahene Osei

Mark Adom-Asamoah

Jones Owusu Twumasi

Prof Peter Andras P.Andras@napier.ac.uk
Dean of School of Computing Engineering and the Built Environment

Prof Johnson Zhang j.zhang@napier.ac.uk
Professor

Abstract

This paper presents a machine learning model for load-level estimation for shear-critical reinforced concrete (RC) beams and slabs using multifractal features of their characteristic crack patterns to automate and provide well-informed decisions for RC damage assessment. Multifractal analysis was conducted on a database of 508 images, of which critical features were extracted from the singularity and generalized dimension spectra. These features are used as predictors for the load-level estimation model. The extreme gradient boosting algorithm yielded the best performance among the four machine learning models considered. The mean of the predicted-to-true ratio for the developed model was 1.04 with a coefficient of variation of 0.27. Upon applying Shapley additive explanations, the fractal dimension, information dimension, correlation dimension and the area under the left branch of the singularity spectrum were the critical features influencing load-level estimation. The proposed model can be useful to RC building inspectors.

Citation

Osei, J. B., Adom-Asamoah, M., Owusu Twumasi, J., Andras, P., & Zhang, H. (2023). A machine learning-based structural load estimation model for shear-critical RC beams and slabs using multifractal analysis. Construction and Building Materials, 394, Article 132250. https://doi.org/10.1016/j.conbuildmat.2023.132250

Journal Article Type	Article
Acceptance Date	Jun 21, 2023
Online Publication Date	Jun 28, 2023
Publication Date	2023-08
Deposit Date	Aug 18, 2023
Publicly Available Date	Jun 29, 2024
Print ISSN	0950-0618
Publisher	Elsevier
Peer Reviewed	Peer Reviewed
Volume	394
Article Number	132250
DOI	https://doi.org/10.1016/j.conbuildmat.2023.132250
Keywords	Multifractal analysis, Load-level assessment, Beams and slabs, Machine learning, Score analysis