GA-based hybrid ANN optimization approach for the prediction of compressive strength of high-volume fly ash concrete mixes

The present study employs the artificial neural network (ANN) analysis to predict concrete strength containing different fly ash percentages. Based on the parameters such as water-to-binder ratio (w/b), coarse aggregate to the total aggregate ratio (CA/TA), and fly ash content, a Genetic Algorithm (GA) based hybrid ANN optimization model has also been devised. These variables were chosen to effectuate the best fly ash concrete mix in the feasible compressive strength range. A total of 64 concrete mixes were taken by considering the above parameters for strength determination, optimization, and verification through the ANN model. The data obtained experimentally was trained to propose ANN model to determine the strength of concrete for various combinations of w/b, CA/TA, and fly ash content. The data was carefully assessed and analyzed to provide a statistically significant model that may be used to predict the strength of fly ash concrete. The actual values are compared to the ANN-predicted strengths. The measured compressive strength values are quite similar to those derived using the suggested model. Thus, it can be inferred that the model based on ANN analysis is an effective method for predicting the compressive strength of fly ash concrete. © 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.