Abstract:
The purpose of present study is to examine how the UPV of pervious concrete changes with three parameters: compaction energy, aggregate size and aggregate-to-cement ratio. The pervious concrete specimens were casted using five levels of compaction energy (0, 15, 30, 45, and 60 blows) and five A/C ratios (3.5, 4.0, 4.5, and 5.0) to test the effects of these factors on UPV. The aggregate sizes were 5–12 mm, 12–18 mm, and 18–25 mm. The study produced 225 pervious concrete cubes with 15 different mix designs and measured their UPV. The study analyzed the test data and developed a mathematical model using machine learning (ML) techniques to establish the associations between the three parameters and the UPV. The study proposed six ML models, such as boosted tree regression (BTR), random forest regression (RFR), and XG boost (XG), to predict the UPV based on compaction energy, aggregate size, aggregate-to-cement ratio. Researchers and professionals may use these models to improve mix design for pervious concrete for a variety of applications.
