Predictive modelling of compressive strength of fly ash and ground granulated blast furnace slag based geopolymer concrete using machine learning techniques

Ordinary Portland cement (OPC) is proving to be hazardous to the environment. To replace the OPC, geopolymers (GPs) are introduced. However, to fully replace the OPC by GPs extensive laboratory tests are required to assess the long-term and short-term properties of GPs in different scenarios. Given the shortage of time for performing such extensive testing, artificial intelligence (AI) is used to analyze the properties of GPs. In this study, different AI techniques such as artificial neuro network (ANN), adaptive neuro-fuzzy inference system (ANFIS), and gene expression programming (GEP) are used to obtain the predictive models for estimating the compressive strength of fly ash and ground granulated blast furnace slag-based GP concrete. Different statistical parameters are used to evaluate the performance of predictive models. Similarly, sensitivity and parametric analysis are also conducted on the input parameters. Additionally, multiple linear regression was also performed on the whole database. After comparing all the results, it was concluded that GEP is the best AI technique to predict the compressive strength of GP-based concrete.