Developing a comprehensive prediction model for the compressive strength of slag-based alkali-activated concrete

Abstract

AbstractThis study aims to evaluate the effects of mix design parameters of ambient-cured slag-based alkali-activated concrete (GAAC) and develop a prediction model for its compressive strength (CS) by emphasizing the chemical compositions of alkaline solutions. A test setup including 625 specimens, in 125 mixes, was designed. A comprehensive parametric study and statistical evaluation were performed. Findings revealed the effectiveness of Na2O, SiO2, H2O, and GGBFS contents compared to the dosage of alkaline solutions and highlighted their disadvantages. The results also discovered the efficiency of the Bayesian linear regression in the simulation compared to the artificial neural network. Two models for estimating the CS of GAAC with reasonable accuracy were also proposed. Carbon footprint evaluation revealed that the carbon dioxide reduction of substituting ordinary concrete with GAAC depended on the desired properties of the concrete and was equal to 33% for grade 35 MPa concrete.Keywords: Alkali-activated concreteprediction modelcompressive strengthparametric studystatistical evaluationMachine learning Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementSome or all data, models, or codes that support the findings of this study are available from the corresponding author upon reasonable request.Notes1 The difference in H2O and water in the mixtures is due to the water-sodium hydroxide flakes reaction in SH. (2NaOH+H2O→Na2O+2H2O).