In this research, two different machine learning approaches are proposed for predicting the compressive strength of fly ash based geopolymer concrete. Experimental work with a total of 335 mix proportions were conducted to produce the data for training and validating processes. In the proposed models, the amount of fly ash, water glass solution, sodium hydroxide solution, coarse aggregate, fine aggregate, water, concentration of sodium hydroxide solution, curing time, and curing temperature were considered as nine input variables, while compressive strength was the output feature. The performance of the machine learning approaches was evaluated using a set of three metrics, including correlation coefficient (R), mean absolute error (MAE) and root mean square error (RMSE). Good correlation between machine learning models and experimental results was obtained. The proposed models can be employed to build a standard mix, and for designing the mix proportions of fly ash based geopolymer concrete.
Read full abstract