Artificial Neural Network Modeling and Prediction of Breakout Strength for Expansion Anchor in Short Carbon Fiber-Reinforced Concrete

Predicting the concrete breakout strength of an expansion anchor embedded in short carbon fiber-reinforced concrete (SCFRC) is challenging due to the nonlinear and heterogeneous nature of fiber–matrix interaction. This study develops an Artificial Neural Network (ANN) model to estimate the breakout capacity of a single expansion anchor installed in SCFRC. Experimental data from 48 cases covering variations in compressive strength, tensile strength, fiber volume fraction, and fiber length were used to train and validate multiple ANN architectures in MATLAB’s Regression Learner. A 4-4-1 trilayered ANN with Rectified Linear Unit (ReLU) activation and 5-fold cross-validation achieved the most reliable performance, yielding R2 values of 0.6726 (validation) and 0.9376 (test), with correspondingly low RMSE, MAE, and scatter index (SI < 0.1). SHAP-based sensitivity analysis identified tensile strength as the dominant predictor, contributing 70.78% to model output influence. ANN predictions were compared with the Concrete Capacity Design (CCD) model adopted by ACI and the National Structural Code of the Philippines (NSCP) and a multiple linear regression (MLR) model, showing that while the ANN is not the most precise model, it provides acceptable accuracy and captures nonlinear concrete breakout behavior more effectively than linear approaches. Results demonstrate that the ANN framework offers a viable data-driven tool for estimating concrete breakout strength in SCFRC anchorage systems.