Multi-objective optimization of ternary geopolymers with multiple solid wastes using machine learning and NSGA-II

Abstract

Abstract The design of the mixtures of the ternary geopolymer is challenging due to the need to balance multiple objectives, including cost, strength, and carbon emissions. In order to address this multi-objective optimization (MOO) problem, machine learning models and the NSGA-II algorithm are employed in this study. To train the machine learning models, namely Artificial Neural Network (ANN), Support Vector Regressor, Extremely Randomized Tree, and Gradient Boosting Regression, 120 uniaxial compressive strength (UCS) values of ternary geopolymers with fly ash (FA), granulated blast furnace slag (GBFS) and steel slag (SS) as precursor materials were obtained from laboratory tests. Results show that the ternary geopolymer with the ratio of FA:GBFS:SS of 2:5:3 has the highest 28-d UCS of 46.8 MPa. The predictive accuracy of the ANN model is the highest with R = 0.949 and RMSE = 3.988MPa on the test set. Furthermore, the Shapley Additive Explanations analysis indicates that precursor materials exhibit the most significant influence on the UCS, particularly the content of GBFS. Based on the ANN model and NSGA-II algorithm, a multi-objective optimization (MOO) model is developed to optimize simultaneously the strength, cost and carbon emission of the ternary geopolymer. The derived MOO model can be used to design mixtures of other cementitious materials with multiple objectives.