Prediction and validation of constituent materials for concrete manufacturing using artificial neural network

The development of high-strength concrete is based on the mix proportion determined through mix design. After conducting multiple trials on the mix proportions, a typical concrete mix with the requisite strength can be achieved. As a result, the procedure takes far too long to complete a large number of mix design trials. Therefore, the requirement of advanced technology to save time, manpower, and material is required. This work is mainly focused on the creation of a MATLAB-based artificial neural network (ANN) model for predicting concrete's compressive strength, determining the projected values of concrete's mechanical characteristics, and conducting a correlation between the results of the experiment and the predicted values. A total of 1030 pieces of mixed proportional data were collected from various researchers to train the neural network. And to validate the trained data, a total of five mix proportions were prepared as per the Indian standard code for mix design. From the results, there is a good correlation between the trained and experimental data. Furthermore, the error values are found to be minimal, and the test and experimental data are well correlated (R2 = 0.95).