Compressive strength of geopolymer concrete modified with nano-silica: Experimental and modeling investigations

Since nanotechnology can enhance the performance of materials, significant effort has been expended in recent years to incorporate nanoparticles (NPs) into geopolymer concrete (GPC) to improve performance and produce GPC with improved characteristics. Recent efforts have been made to incorporate various nanomaterials, most notably nano-silica (nS), into GPC to improve the composite's properties. Compressive strength (CS) is an important property of all concrete composites, including geopolymer concrete. Several mix proportion parameters and curing temperature and ages influence the CS of geopolymer concrete. As a result, developing a credible model for forecasting concrete CS is critical for saving time, energy, and money while also providing guidance for scheduling the construction process and removing formworks. This paper consists of three phases; in the first phase, a detailed review on the effect of adding nS on the CS of GPC was provided; then, in the second phase, a large amount of mixed design data were extracted from literature studies to create five different models including artificial neural network, M5P-tree, linear regression, nonlinear regression, and multi logistic regression models for forecasting the CS of GPC incorporated nS. Finally, the developed models were validated in the last phase by carrying out experimental laboratory works. Results revealed that the addition of nS improves the CS of GPC, and the ANN model estimated the CS of GPC incorporated nS more accurately than the other models. On the other hand, the alkaline solution to binder ratio, molarity, NaOH content, curing temperature, and ages were those parameters that significantly influenced the CS of GPC incorporated nS.