Case-Based Reasoning for Predicting Bond Strength in Fiber Reinforced Polymer (FRP) and Concrete

¹ Civil and Environnemental Engineering Department, College of Engineering, University of Sharjah, Sharjah, P.O.Box 27272, United Arab Emirates
² Sustainable Construction Materials and Structural System Research Group, Research Institute of Sciences and Engineering, University of Sharjah, Sharjah, United Arab Emirates.
³ Department of Civil Engineering, McMaster University, 1280 Main St W, Hamilton, ON L8S 4L8, Canada

^* Corresponding author: mjunaid@sharjah.ac.ae

Published online: 19 December 2025

Abstract

The increasing adoption of Fiber Reinforced Polymer (FRP) bars in concrete structures necessitates accurate prediction of bond strength to ensure structural integrity and reliability. This study introduces Case-Based Reasoning (CBR) as an interpretable and efficient approach for predicting FRP-concrete bond strength. Utilizing a dataset of 227 experimental results, the CBR model achieves high accuracy, with an R² of 0.98 and a low Mean Squared Error (MSE) of 0.226 MPa. Sensitivity analysis identifies critical parameters such as bar diameter (d_b), concrete compressive strength (fc’), cover-to-bar diameter ratio (c/d_b), and embedment length-to-bar diameter ratio (l_d/d_b), demonstrating their varying influence across different surface types: helical lugged, spiral-wrapped, and sand-coated. The findings emphasize the practical applicability of CBR in tailoring design strategies for FRP-reinforced structures, offering engineers an interpretable and reliable tool to optimize performance while reducing computational complexity.