Journal
CONSTRUCTION AND BUILDING MATERIALS
Volume 309, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.conbuildmat.2021.125152
Keywords
Polymer concrete; Polyurethane; U-shaped specimens; Drop-weight impact test; Statistical analysis; Artificial intelligent
Ask authors/readers for more resources
The impact resistance of PU-based polymer concrete was significantly enhanced due to the PU binder composition, resulting in improved impact times and energy absorption capacity. Additionally, an AI-based model effectively predicted the failure strength of PU-based polymer concrete samples.
The impact resistance of Polyurethane (PU)-based polymer concrete was investigated using U-shaped specimens tested on a newly designed drop-weight impact test device. The PU-based polymer concrete samples was obtained by mixing natural sand and PU matrix using 85:15 and 90:10 ratios, and normal concrete samples were tested for comparison. The results revealed that the PU binder composition greatly enhanced the impact times and energy absorption capacity. The U-shaped specimen was predetermined the position of the crack and reduced the dispersion of results. The coefficient of variation (COV) of 38.07% is the maximum value obtained in this study, lower than the value obtained in ACI 544 2R impact testing procedure. The AI-based model' result indicates that the prediction skills of the support vector machine (SVM-M3) performed very well with R2 = 0.9575 and 0.9814 in the training and testing stage, respectively. Therefore, the proposed model had high accuracy in predicting the failure strength (blows) of PU-based polymer concrete samples.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available