Demir Şahin, DemetIsik, EsmeIsik, IbrahimCullu, Mustafa2022-03-222022-03-222021Demir Sahin, D., Isik, E., Isik, I., & Cullu, M. (2021). Artificial neural network modeling for the effect of fly ash fineness on compressive strength. Arabian Journal of Geosciences, 14(23), 1-14.https://doi.org/10.1007/s12517-021-09120-whttps://hdl.handle.net/20.500.12899/808In the literature, there has been a lot of discussion over the compressive strength of concrete made with high-calcium fly ash instead of cement. However, no research has been done to determine the influence of ground fly ash on compressive strength using experimental and artificial neural network (ANN) models when they are used in place of cement at various replacement ratios. The size and replacement ratio of fly ash give maximum durability of the concrete when utilized in the cement composition, according to the ANN model employed in this study, allowing to forecast the result without using a high-cost and energy-intensive operation like grinding. In this study, short and long-term compressive strength of concrete of class C fly ash is analyzed at six different Blaine fineness values (1834, 1852, 1930, 1992, 1995, and 2018 cm2/g) and three different fly ash substitution rates (10, 30, and 50%) for 270 supplemental concrete samples. In addition, based on the experimental results, an ANN model was proposed to simulate and predict the compressive strength of concrete. In this proposed model, substitution rate, Blaine fineness, and curing time (day) were used as input to simulate the value of compressive strength for 3, 7, 28, 56, and 90 curing times with 99% accuracy. Also, the value of compressive strength was predicted for 120 curing days. The predicted target values were compared with the experiment resulted in a better correlation coefficient of 0.99. Thus, the results attained from this ANN model were found to be effective in predicting the relationship between fly ash fineness and compressive strength at any given operating condition.eninfo:eu-repo/semantics/closedAccessCompressive strengthFly ashArtifcial neural networkBlaine fnenessArticle10.1007/s12517-021-09120-w14