Deep learning–based prediction of compressive strength of eco-friendly geopolymer concrete

Abstract

The greenhouse gases cause global warming on Earth. The cement production industry is one of the largest sectors producing greenhouse gases. The geopolymer is produced with synthesized by the reaction of an alkaline solution and the waste materials such as slag and fly ash. The use of eco-friendly geopolymer concrete decreases energy consumption and greenhouse gases. In this study, the fc (compressive strength) of eco-friendly geopolymer concrete was predicted by the deep long short-term memory (LSTM) network model. Moreover, the support vector regression (SVR), least squares boosting ensemble (LSBoost), and multiple linear regression (MLR) models were devised to compare the forecast results of the deep LSTM algorithm. The input variables of the models were used as the mole ratio, the alkaline solution concentration, the curing temperature, the curing days, and the liquid-to-fly ash mass ratio. The output variable of the proposed models was chosen as the compressive strength (fc). Furthermore, the effects of the input variable on the fc of eco-friendly geopolymer concrete were determined by the sensitivity analysis. The fc of eco-friendly geopolymer concrete was predicted by the deep LSTM, LSBoost, SVR, and MLR models with 99.23%, 98.08%, 78.57%, and 88.03% accuracy, respectively. The deep LSTM model forecasted the fc of eco-friendly geopolymer concrete with higher accuracy than the SVR, LSBoost, and MLR models. The sensitivity analysis obtained that the curing temperature was the most important experimental variable that affected the fc of geopolymer concrete.