Predicting the impact strength and chloride permeability of concrete made with industrial waste and artificial sand using ANN

Large-scale cement and natural fine aggregate use in construction has negative environmental effects. Considering this issue in this study crushed sand, and wastes from industries such as metakaolin, Fly ash, blast furnace slag and micro silica used as replacement for cement. To estimate the impact strength and chloride permeability of concrete made by cementitious waste ingredients and in which the natural fine aggregate is partially replaced by artificial sand. Matlab software model was created, 150 mm diameter and 65 mm thick cylinder was tested for impact strength and chloride permeability 50 mm thick and 100 mm diameter samples were cast. An artificial neural network model was developed using the experimental values. For design of model 400 result values whre used, 20% results used for testing purpose and 80% results used for artificial neural network model training. The 28-day impact strength and chloride permeability of concrete mixed by partially substituting cement with pozzolan and partially substituting natural fine aggregate with artificial sand were calculated using the product of 25 input data. The artificial neural network model's results offer a precise elastic prediction of the impact strength and chloride iron pass ability of concrete mixed with substituting industrial cementitious waste for cement and artificial sand with naturally occurring fine aggregate. Percentage error provided by model is in between 0 to 5% with acceptable range. Statistical parameters are with in range. The findings of this study help to reduce the extraction of non-renewable natural recourses and the environmental impact of industrial waste by preparing more sustainable concrete.