EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Compressive Strength Prediction of Alkali-Activated Waste Materials Using Machine Learning

Chien-Hua Hsu iD, Hao-Yu Chan iD, Ming-Hui Chang, Chiung-Fang Liu, Tzu-Yu Liu, Kuo-Chuang Chiu

Materials · 27.06.2024 · 17 (13) · 3141

DOI: 10.3390/ma17133141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 27.06.2024. Verfasst von Chien-Hua Hsu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Material and Chemical Research Laboratories, Industrial Technology Research Institute, Hsinchu 31040, Taiwan. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Resource Circulation Administration Ministry of Environment, Department of Industrial Technology, Ministry of Economic Affairs.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study explores the integration of machine learning (ML) techniques to predict and optimize the compressive strength of alkali-activated materials (AAMs) sourced from four industrial waste streams: blast furnace slag, fly ash, reducing slag, and waste glass. Aimed at mitigating the labor-intensive trial-and-error method in AAM formulation, ML models can predict the compressive strength and then streamline the mixture compositions. By leveraging a dataset of only 42 samples, the Random Forest (RF) model underwent fivefold cross-validation to ensure reliability. Despite challenges posed by the limited datasets, meticulous data processing steps facilitated the identification of pivotal features that influence compressive strength. Substantial enhancement in predicting compressive strength was achieved with the RF model, improving the model accuracy from 0.05 to 0.62. Experimental validation further confirmed the ML model’s efficacy, as the formulations ultimately achieved the desired strength threshold, with a significant 59.65% improvement over the initial experiments. Additionally, the fact that the recommended formulations using ML methods only required about 5 min underscores the transformative potential of ML in reshaping AAM design paradigms and expediting the development process.

Schlagwörter

Stichwörter der Autor:innen

alkali-activated materials (AAMs)component classificationcompressive strengthmachine learningoptimization

Autor:innen und Institutionen

  • Material and Chemical Research Laboratories, Industrial Technology Research Institute, Hsinchu 31040, Taiwan.

ORCID-Profile: Chien-Hua Hsu, Hao-Yu Chan

Förderung

  • Resource Circulation Administration Ministry of Environment
  • Department of Industrial Technology, Ministry of Economic Affairs

Zitieren

APA

Hsu, C. H., Chan, H. Y., Chang, M. H., Liu, C. F., Liu, T. Y., & Chiu, K. C. (2024). Efficient Compressive Strength Prediction of Alkali-Activated Waste Materials Using Machine Learning. Materials, 17(13), 3141. https://doi.org/10.3390/ma17133141

Vancouver

Hsu CH, Chan HY, Chang MH, Liu CF, Liu TY, Chiu KC. Efficient Compressive Strength Prediction of Alkali-Activated Waste Materials Using Machine Learning. Materials. 2024;17(13):3141. doi:10.3390/ma17133141

BibTeX
@article{Hsu2024,
  author = {Hsu, Chien-Hua and Chan, Hao-Yu and Chang, Ming-Hui and Liu, Chiung-Fang and Liu, Tzu-Yu and Chiu, Kuo-Chuang},
  title = {Efficient Compressive Strength Prediction of Alkali-Activated Waste Materials Using Machine Learning},
  journal = {Materials},
  year = {2024},
  volume = {17},
  number = {13},
  pages = {3141},
  doi = {10.3390/ma17133141}
}
Kostenlos starten →