Fly ash-based geopolymer concrete's compressive strength estimation by applying artificial intelligence methods

Abstract

Geopolymer concrete is a kind of eco-friendly concrete and its important characteristic is that the cement is completely or partially removed from its mixture and other materials such as industrial waste have replaced it. Using industrial waste materials, in particular fly ash, as full or partial replacement of cement in this type of concrete can provide advantages like improving concrete's fresh and hardened traits, decreasing the amounts of released waste materials in the environment, reducing CO2 footprint and alleviate the pressure on natural resources. According to the acceptable performance of Artificial Intelligence (AI) methods in the various fields, as well as in the issues related to the properties of cementitious materials, in this research three developed AI methods including radial basis function neural network (RBFNN) aided by ant colony optimization algorithm (ACO), group method of data handling (GMDH), and artificial neural network (ANN) was proposed for estimating the compressive strength (that is a notable mechanical character of every type of concrete) of fly ash-based geopolymer concrete (FAGC). To achieve this goal, the information from 360 samples of FAGC was collected from the previous studies. Models' accuracy and predictive capacity have been appraised via Statistical formulas as well as comparing models' outputs with experimental test results. The assessment showed that the performance of all three models for forecasting this mechanical feature of FAGC is acceptable but the RBFNN has the best performance among these proposed models.