Skip to main content

Research Repository

Advanced Search

Prediction of ultimate strain in anchored CFRP laminates using machine learning

Amer, Sabreen Dar; Assad, Maha; Hawileh, Rami A.; Karaki, Ghada; Safieh, Hussam; Abdalla, Jamal

Prediction of ultimate strain in anchored CFRP laminates using machine learning Thumbnail


Authors

Sabreen Dar Amer

Maha Assad

Rami A. Hawileh

Ghada Karaki

Hussam Safieh

Jamal Abdalla



Abstract

Anchorage of carbon fibre-reinforced polymers (CFRP) laminates externally bonded to concrete by CFRP spike anchors effectively prevents the unfavourable debonding failure mode in strengthened concrete beams. However, the strain and strength enhancement resulting from the anchorage have not been thoroughly quantified in the literature and existing practice codes. This study investigates the prediction of ultimate strain in anchored CFRP laminates, which is crucial for assessing the flexural strength of strengthened concrete beams. Statistical regression analysis and machine learning models are employed to develop a predictive equation for the ultimate strain in CFRP laminates induced by anchorage by collecting and analysing data from previous flexural tests on concrete prisms. The study examines various parameters, including CFRP sheet width, anchor design details (such as diameter and embedment depth), number of CFRP layers and anchor-to-sheet material ratio. Linear regression models, Linear SVR and Decision Trees were tested and compared for prediction accuracy of ultimate strain in CFRP laminates. Due to its highest coefficient of determination, the linear regression model is selected for its superior predictive performance. Furthermore, the study provides derived predictive equations, offering a practical implication for design optimization. Finally, sets of design charts were proposed to achieve specific values of ultimate strain in CFRP-strengthened and anchored concrete beams.

Journal Article Type Article
Acceptance Date Aug 21, 2024
Online Publication Date Oct 31, 2024
Deposit Date Oct 28, 2024
Publicly Available Date Dec 1, 2024
Journal Engineered Science
Print ISSN 2576-988X
Electronic ISSN 2576-9898
Peer Reviewed Peer Reviewed
Volume 31
Article Number 1251
DOI https://doi.org/10.30919/es1251
Public URL https://uwe-repository.worktribe.com/output/13321808

Files






You might also like



Downloadable Citations