ASSESSMENT OF SUSTAINABLE GREEN CONCRETE PROPERTIES USING RECYCLED PLASTIC WASTE AS REPLACEMENT FOR FINE AGGREGATE USING MACHINE LEARNING TECHNIQUE

Abstract

The use of waste plastic as a replacement for natural aggregates in cement composites can solve the problem of the disposal of waste plastics sustainably. This study aims to investigate and compare the impact of replacing fine natural aggregate with recycled aggregates made up of polyethylene (PE) in M30 grade of concrete by analyzing the physical and mechanical properties of both fresh and hardened concrete in terms of workability, dry and fresh unit weight, 28-day compressive strength, flexural strength, split tensile strength, and ultrasonic pulse velocity. Nine concrete mixtures containing PE was prepared as a partial volumetric replacement for fine aggregate with substitution levels of 0%, 5%, 10%, 15%, 20%, 25%, 30%, 35% and 40%. Due to the application of superplasticizers, the workability of concrete containing recycled plastic has improved. The fresh and dry unit weight values of the PE-based concrete decreased by 8.16% and 8.6%, respectively, with the increase in PE aggregate and can therefore be considered lightweight concrete. The compressive strength of concrete at various ages is reduced as the quantity of plastic in concrete increases. As the PE replacement ratio in concrete increased, the flexural strength and split tensile strength also declined. Up to 10% replacement gives acceptable physical and mechanical properties of concrete for structural purposes. In this study, artificial neural network (ANN) was used to predict the fresh and hardened properties of waste plastic aggregate-based concrete, and it was discovered that it can predict concrete qualities with good accuracy (R² = 0.99).