EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimization of Mix Proportions and Random-Forest-Assisted Exploratory Modeling for Alkali-Activated Fly Ash Geopolymer

Yawei Ma, Xianyang Wang, Ying Zhang, Binsheng Zhang, Guihong Guo

Buildings · 16.07.2026 · 16 (14) · 2843

DOI: 10.3390/buildings16142843 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 16.07.2026. Verfasst von Yawei Ma und 4 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Alkali-activated fly ash geopolymers are promising low-carbon binders, but their performance depends strongly on mix proportion design. This study investigated the effects of water-to-binder ratio, sand content, and NaOH concentration on fly ash-based geopolymer using an L25(56) orthogonal design. Flexural and compressive strengths were evaluated through range analysis and Analysis of Variance (ANOVA), while Random Forest was used as an exploratory tool for factor-response interpretation. Scanning electron microscopy (SEM), Fourier transform infrared spectroscopy (FTIR), and X-ray diffraction (XRD) were conducted to relate mechanical behavior to microstructural evolution. The optimal combination within the tested levels was a water-to-binder ratio of 0.30, sand content of 40%, and NaOH concentration of 12 mol/L. The maximum flexural and compressive strengths reached 3.65 MPa and 17.98 MPa, respectively. NaOH concentration dominated flexural strength, whereas water-to-binder ratio primarily controlled compressive strength. Model benchmarking and cross-validation showed that the machine-learning results had limited generalization capability under the small-sample condition and should be interpreted as candidate screening rather than independent predictive validation. Microstructural analyses indicated that strength development was associated with matrix densification, aluminosilicate network reorganization, and amorphous geopolymeric gel formation.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Ma, Y., Wang, X., Zhang, Y., Zhang, B., & Guo, G. (2026). Optimization of Mix Proportions and Random-Forest-Assisted Exploratory Modeling for Alkali-Activated Fly Ash Geopolymer. Buildings, 16(14), 2843. https://doi.org/10.3390/buildings16142843

Vancouver

Ma Y, Wang X, Zhang Y, Zhang B, Guo G. Optimization of Mix Proportions and Random-Forest-Assisted Exploratory Modeling for Alkali-Activated Fly Ash Geopolymer. Buildings. 2026;16(14):2843. doi:10.3390/buildings16142843

BibTeX
@article{Ma2026,
  author = {Ma, Yawei and Wang, Xianyang and Zhang, Ying and Zhang, Binsheng and Guo, Guihong},
  title = {Optimization of Mix Proportions and Random-Forest-Assisted Exploratory Modeling for Alkali-Activated Fly Ash Geopolymer},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {14},
  pages = {2843},
  doi = {10.3390/buildings16142843}
}
Kostenlos starten →