Database on ANN-Based Performance Evaluation of Composite Recycled Mortar

The recycling of construction waste is crucial for environmental preservation and sustainable progress. By integrating construction waste into mortar production, substantial reductions in carbon emissions can be achieved. However, there is currently no dependable method for estimating mortar strength based on its composition. This paper explores the utilization of artificial intelligence technology to forecast the compressive strength of composite recycled mortar. Three artificial neural network (ANN) models are developed for this purpose. A comparison between predicted results and experimental findings demonstrates the ANN models' ability to reliably and robustly approximate mortar strength. Furthermore, utilizing extremum optimization through ANN's genetic algorithm function, the paper forecasts optimal compressive strength and corresponding mix proportions. Because of its high predictive accuracy, ANN can efficiently supplement conventional destructive tests, thereby conserving valuable time, resources, and capital within the construction industry. This research could significantly advance civil engineering by providing an optimal ANN model for predicting the compressive strength of composite recycled mortar, ultimately contributing to the reduction of carbon dioxide emissions and promoting environmental protection and sustainable development.