Evaluation and prediction of slag-based geopolymer's compressive strength using design of experiment (DOE) approach and artificial neural network (ANN) algorithms.

Even though the demand for utilizing geopolymers is growing, the need for current standard guidelines to regulate compliance to address the complexity of the mix design could be one of the major hurdles of utilizing geopolymers vastly in construction. There is no straightforward standard that addresses the complexity of the mix design of geopolymers. Thus, this work addresses main factors affecting the compressive strength of slag based geopolymers and provide a tool for predicting it. This article includes experimental work to evaluate the properties of slag-based geopolymer binders and the development of a model using Artificial Neural Network (ANN) algorithms for predicting the performance of these slag-based geopolymer binders. In this paper, we have utilized and developed ANN models for optimizing slag-based geopolymer mixes based on precursor materials' physiochemical properties and activation solutions constituents that can enhance performance compressive strength prediction in construction applications. • A high-accuracy DOE model was developed and used to characterize the Geopolymeric paste. • A developed ANN model was superior in forecasting the compressive strength of AAS systems. • The choice of the alkali activator has minimal impact on the compressive strength. • The optimal water-to-slag ratio is approximately 0.28. • The optimal alkali oxide concentration is 6 %. [ABSTRACT FROM AUTHOR]