Data-driven inverse mix design for sustainable alkali-activated materials DOI
Y.K. Kong, Kiyofumi Kurumisawa, Chiharu Tokoro

et al.

Journal of Sustainable Cement-Based Materials, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 22

Published: Oct. 24, 2024

Language: Английский

Compressive Strength Prediction of Basalt Fiber Reinforced Concrete Based on Interpretive Machine Learning Using SHAP Analysis DOI
Xuewei Wang,

Zhijie Ke,

Wenjun Liu

et al.

Iranian Journal of Science and Technology Transactions of Civil Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 28, 2024

Language: Английский

Citations

4
Assessment of Geopolymer Concrete for Sustainable Construction: A Scientometric-Aided Review DOI
Mohd Asif Ansari, M. Shariq, Fareed Mahdi

et al.

Journal of structural design and construction practice., Journal Year: 2025, Volume and Issue: 30(2)

Published: Feb. 7, 2025

Language: Английский

Citations

0
A Fine-Segmentation Algorithm for XCT Images of Multiphase Composite Building Materials Based on Deep Learning DOI
Shangyu Yang, Lingtao Mao, Mei Zhou

et al.

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 97, P. 110918 - 110918

Published: Oct. 2, 2024

Language: Английский

Citations

3
Assessment of corrosion probability of steel in mortars using machine learning DOI
Haodong Ji, Yuhui Lyu, Zushi Tian

et al.

Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: 253, P. 110535 - 110535

Published: Oct. 6, 2024

Language: Английский

Citations

3
Predictive modeling of compressive strength of geopolymer concrete before and after high temperature applying machine learning algorithms DOI
Haifeng Yang, Hongrui Li,

Jiasheng Jiang

et al.

Structural Concrete, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 22, 2024

Abstract Geopolymer concrete (GPC) is regarded as a more environmentally friendly construction material compared to conventional cement concrete, and its exceptional environmental capabilities are highly favored by the contemporary sector. Studying mechanical properties of GPC upon exposure elevated temperatures crucial aspect evaluating structural damage enhancing fire safety measures. Nevertheless, properly predicting compressive performance high remains formidable task. This study employs various machine learning techniques, such single models, integrated neural network hybrid predict strength from room temperature 1000°C. The results each model summarized, significant factors influencing analyzed evaluate thermal behavior GPC. These findings offer recommendations for future in‐depth applications in field. K‐fold cross‐validation shows that genetic algorithm–random forest has highest prediction accuracy, while performs worst. Other models also provide favorable results. feature importance analysis revealed primarily influenced heating (HT) hydroxide ion concentration, with fly ash ground granulated blast furnace slag content being secondary factors. partial dependence plot‐2D indicates HTs increase, influence other variables on decreases significantly. can inform design mixing ratios high‐temperature exposure. technique proposed this accurately predicts across temperatures, reducing experimental time costs promoting

Language: Английский

Citations

0
Data-driven inverse mix design for sustainable alkali-activated materials DOI
Y.K. Kong, Kiyofumi Kurumisawa, Chiharu Tokoro

et al.

Journal of Sustainable Cement-Based Materials, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 22

Published: Oct. 24, 2024

Language: Английский

Citations

0