Modelling the mechanical properties of concrete produced with polycarbonate waste ash by machine learning

Abstract

Abstract India’s cement industry is the second largest in the world, generating 6.9% of the global cement output. Polycarbonate waste ash is a major problem in India and around the globe. Approximately 370,000 tons of scientific waste are generated annually from fitness care facilities in India. Polycarbonate waste helps reduce the environmental burden associated with disposal and decreases the need for new raw materials. The primary variable in this study is the quantity of polycarbonate waste ash (5, 10, 15, 20 and 25% of the weight of cement), partial replacement of cement, water-cement ratio and aggregates. The mechanical properties, such as compressive strength, split tensile strength and flexural test results, of the mixtures with the polycarbonate waste ash were superior at 7, 14 and 28 days compared to those of the control mix. The water absorption rate is less than that of standard concrete. Compared with those of conventional concrete, polycarbonate waste concrete mixtures undergo minimal weight loss under acid curing conditions. Polycarbonate waste is utilized in the construction industry to reduce pollution and improve the economy. This study further simulated the strength characteristics of concrete made with waste polycarbonate ash using least absolute shrinkage and selection operator regression and decision trees. Cement, polycarbonate waste, slump, water absorption, and the ratio of water to cement were the main components that were considered input variables. The suggested decision tree model was successful with unparalleled predictive accuracy across important metrics. Its outstanding predictive ability for split tensile strength (R2 = 0.879403), flexural strength (R2 = 0.91197), and compressive strength (R2 = 0.853683) confirmed that this method was the preferred choice for these strength predictions.

Keywords

• Polycarbonate waste
• Mechanical properties
• Durability properties
• Microstructural study
• Machine learning
• Cost analysis