Forecasting strength characteristics of concrete incorporating nano-silica, alccofine and fly ash as partial replacement of cement using artificial neural network

Concrete is a fundamental building material, and efforts are continually made to enhance its properties, sustainability, and performance. This study investigates the influence of incorporating nano-silica (1-5%), alccofine (10%), and fly ash (20%) as partial replacements of cement on the strength characteristics (compressive strength, tensile strength, and flexural strength) of concrete by performing experiments at various curing periods in the laboratory. The objective of the current study is to develop a predictive model using Artificial Neural Network (ANN) to forecast the compressive strength of concrete with varying combinations of these supplementary cementitious materials. Subsequently, an ANN-based predictive model was trained using the collected data to establish a relationship between the composition of the concrete mix and its strength characteristics. The ANN model takes into account various input parameters, including the percentage replacements of nano-silica, alccofine, and fly ash, as well as other relevant mix design parameters. The trained model aims to provide accurate predictions of compressive strength based on the selected input variables. The findings of this research contribute to a better understanding of the synergistic effects of nano-silica, alccofine, and fly ash on the strength properties of concrete. Moreover, the co-efficient of the correlation value comes out to be 0.924, revealing that observed and predicted values are in agreement with each other. Additionally, the developed ANN model serves as a valuable tool for engineers and researchers to efficiently forecast the strength characteristics of concrete with different combinations of these supplementary materials, facilitating more informed decision-making in concrete mix design and optimization.