Utilizing ANFIS for Strength Characteristics Forecasting in Variable Heat-Cured Geopolymer Composites

Reducing cement usage through geopolymer concrete (GPC) can be crucial for resolving environmental concerns. The byproduct of the coal and steel industry, such as fly ash (FA) and ground granulated blast furnace slag (GGBS), is mainly used as a precursor in the production of GPC due to the availability of aluminosilicate products in it. In this work, nano silica is added to the GPC in different percentages and GPC is cured at different temperatures to study the change in the strength of GPC due to change in curing temperature. The compressive strength, flexural strength, and split tensile strength up to 68.99 MPa, 5.89 MPa, 6.82 MPa, respectively was achieved after 28 days of heat curing. However, testing GPC experimentally to anticipate its strength is time-consuming and expensive. Therefore, the ability to precisely forecast concrete strength can be achieved through machine learning. In this study, the correlation for both nano silica (%) and curing temperature towards the strength of concrete is also investigated using adaptive neuro fuzzy interference system (ANFIS) models. ANFIS results showed better compressive, split tensile, and flexural strength prediction with the highest R2 0.9801, 0.9943, and 0.9877, respectively. The performance efficiency of the developed ANFIS model is more significant minimum error for compressive strength prediction (MAE = 0.21375, RMSE = 0.02574, MAPE = 0.42), split tensile strength prediction (MAE = 0.07375, RMSE = 0.0923, MAPE = 1.46) and flexural strength prediction (MAE = 0.04, RMSE = 0.0728, MAPE = 0.78) of GPC cured under different temperature conditions. The results from experiments show that the prediction efficiency of the model is also good, as indicated by the correlation coefficient (R). This model is helpful for further designing the proportion of material for achieving good strength of GPC.