Show simple item record

AuthorWakjira, Tadesse G.
AuthorIbrahim, Mohamed
AuthorEbead, Usama
AuthorAlam, M. Shahria
Available date2023-01-29T09:23:41Z
Publication Date2022
Publication NameEngineering Structures
ResourceScopus
URIhttp://dx.doi.org/10.1016/j.engstruct.2022.113903
URIhttp://hdl.handle.net/10576/39122
AbstractThis paper presents a data-driven approach to determine the load and flexural capacities of reinforced concrete (RC) beams strengthened with fabric reinforced cementitious matrix (FRCM) composites in flexure. A total of seven machine learning (ML) models such as kernel ridge regression, K-nearest neighbors, support vector regression, classification and regression trees, random forest, gradient boosted trees, and extreme gradient boosting (xgBoost) are evaluated to propose the best predictive model for FRCM-strengthened beams. Beam geometry, internal steel reinforcement area, FRCM reinforcement area, and mechanical characteristics of concrete, steel, and FRCM are the main input parameters included in the database. Among the studied ML models, the xgBoost model is the most accurate model with the highest coefficient of determination (R2=99.3%) and least root mean square (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). A comparative study of the performance of the proposed and existing analytical models revealed the superior predictive capability and robustness of the proposed model. The predicted flexural and load capacities of the beams based on the existing analytical models are highly scattered and either over-conservative or unsafe. A unified SHapley Additive exPlanations approach is employed to explain the output of the best ML model and identify the most significant input features and interactions that influence the capacity of FRCM-strengthened RC beams in flexure. Furthermore, a reliability analysis is performed to calibrate the resistance reduction factor (ϕ) to achieve a specified target reliability index (βT=3.5).
SponsorThis paper was made possible by NPRP grant # NPRP 13S-0209-200311 from the Qatar National Research Fund (a member of Qatar Foundation) and financial support of the Natural Sciences and Engineering Research Council (NSERC) of Canada . Open Access funding provided by the Qatar National Library. The findings achieved herein are solely the responsibility of the authors.
Languageen
PublisherElsevier
SubjectFRCM
Machine learning
Reliability analysis
SHAP
Strengthening
TitleExplainable machine learning model and reliability analysis for flexural capacity prediction of RC beams strengthened in flexure with FRCM
TypeArticle
Volume Number255
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record