TY - JOUR
T1 - Machine learning prediction of drying shrinkage for alkali-activated materials and multi-objective optimization
AU - Zhang, Lei
AU - Zhu, Dehui
AU - Nehdi, Moncef L.
AU - Marani, Afshin
AU - Wang, Dongmin
AU - Zheng, Dapeng
AU - Tursun, Gulbostan
AU - Pan, Zhu
AU - Zhang, Junfei
N1 - Publisher Copyright:
© 2025 Elsevier Ltd
PY - 2025/4
Y1 - 2025/4
N2 - The aim of this study is to perform multi-objective optimization of alkali activated materials (AAMs) through a machine learning approach, focusing on three key factors: drying shrinkage, cost and CO2 emission. Five machine learning models were trained and evaluated based on 1383 hybrid design data, and the results showed that the gradient boosted regression (GBR) model performed best in terms of prediction accuracy. The main factors affecting the drying shrinkage of AAMs, including curing time, the content of SiO2 and Na2O in sodium silicate, and the ratio of fly ash to slag content, were identified through the Shapley Additive Explanations (SHAP) method and sensitivity analysis. Further, a multi-objective optimization model was constructed by combining the GBR model and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) algorithm while considering drying shrinkage, cost and CO2 emission. The model can help researchers and engineers to quickly design and optimize the ratios of AAMs to meet practical engineering needs.
AB - The aim of this study is to perform multi-objective optimization of alkali activated materials (AAMs) through a machine learning approach, focusing on three key factors: drying shrinkage, cost and CO2 emission. Five machine learning models were trained and evaluated based on 1383 hybrid design data, and the results showed that the gradient boosted regression (GBR) model performed best in terms of prediction accuracy. The main factors affecting the drying shrinkage of AAMs, including curing time, the content of SiO2 and Na2O in sodium silicate, and the ratio of fly ash to slag content, were identified through the Shapley Additive Explanations (SHAP) method and sensitivity analysis. Further, a multi-objective optimization model was constructed by combining the GBR model and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) algorithm while considering drying shrinkage, cost and CO2 emission. The model can help researchers and engineers to quickly design and optimize the ratios of AAMs to meet practical engineering needs.
KW - Alkali-activated materials
KW - Drying shrinkage
KW - Machine learning
KW - Multi-objective optimization
KW - NSGA-II
UR - http://www.scopus.com/inward/record.url?scp=105001410116&partnerID=8YFLogxK
U2 - 10.1016/j.mtcomm.2025.112326
DO - 10.1016/j.mtcomm.2025.112326
M3 - Article
AN - SCOPUS:105001410116
SN - 2352-4928
VL - 45
JO - Materials Today Communications
JF - Materials Today Communications
M1 - 112326
ER -
