Evaluating Concrete Strength Under Various Curing Conditions Using Artificial Neural Networks

Abstract This study examines the impact of different curing methods on the compressive strength of concrete. It investigates techniques such as air curing, periodic water spraying, full water submersion, and polyethylene encasement. Artificial neural network models were employed to evaluate the compressive strength under each curing condition. A model for calculating compressive strength that considers surrounding conditions was created using an artificial neural network. The current study’s figures were generated using this model. The research thoroughly examined the impact of curing environments and concrete mix components on strength properties, taking into account factors such as temperature, the inclusion of additives such as fly ash and silica fume, adjustments in water-to-cement ratio, selection of aggregates, and the integration of various admixtures. One important discovery is that models that predict compressive strength based on 28-day water immersion do not accurately represent the actual strength because of the substantial impact of local curing conditions. Furthermore, concrete that was cured in polyethylene bags exhibited noticeable differences in moisture retention and temperature properties when compared to alternative methods. Understanding and evaluating curing conditions is crucial for accurate strength predictions. The study also found that compressive strength decreases with temperatures above 30°C and below 15°C.