Mechanical and Impact Strength Properties of Polymer-Modified Concrete Supported with Machine Learning Method: Microstructure Analysis (SEM) Coupled with EDS

This study investigated the mechanical and impact resistance properties of U-shaped polymer-modified concrete (PMC) incorporated with epoxy (EP) and polyacrylate (PA) binders. The polymer-modified concrete mixtures were prepared with varying binder contents (0 to 30%) at intervals of 10% for each EP and PA binder. Moreover, scanning electron microscopy (SEM) analysis coupled with energy-dispersive X-ray spectroscopy (EDS) was used to study the microstructure of the polymer-modified concrete mixtures. An Artificial Neural Network (ANN) model was developed to predict failure crack strength (N2). The results indicate that EP binders enhance impact resistance but decrease compressive strength, whereas PA binders slightly improve both mechanical and impact properties. Introducing the EP binder into the PCM mixtures reduces the compressive strength by 4.91%, 15.09%, and 33.02% for EP10, EP20, and EP30, respectively, compared to the reference specimen, whereas the impact strength at the initial crack strength was improved by 127.64%, 221.95%, and 17.07% for EP 10, EP 20, and EP 30, respectively. The ANN model demonstrated high accuracy in predicting N2, achieving R² values of 0.9892 and 0.9664 during training and testing, respectively.