EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Experimental and Machine Learning Analysis of Self‐Compacting Concrete Made With Metalized Waste Plastic Fiber and Clay Brick Powder

Shuvo Dip Datta, Fahmied Sahriea, Jawad Ashraf, Mamunul Karim, Md. Shourav, Mohammad Tarequl Alam, Md. Shahriar Abdullah, Mohtasim Fuad, Md. Zikrullah Hafeez Mona

Journal of Engineering · 2026-01 · 2026 (1)

DOI: 10.1155/je/2822510 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Engineering, online erschienen am 01.07.2026. Verfasst von Shuvo Dip Datta und 8 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Plastic waste disposal and cement production jointly contribute to environmental degradation, making sustainable construction materials a global necessity. This study develops and evaluates self‐compacting concrete (SCC) incorporating clay brick powder (CBP) as a partial cement replacement and metalized waste plastic fibers (MWPFs) as reinforcement, introducing a novel integration of experimental testing with particle swarm optimization (PSO)–tuned machine learning. Ten SCC mixes were prepared with CBP levels of 2.5%–7.5% and MWPF dosages of 0.5%–1.5%, maintaining a water‐to‐binder ratio of 0.38. Fresh properties were assessed using slump‐flow, T 500 , V‐funnel, and J‐ring tests, while compressive and tensile strengths were measured at multiple curing ages. The optimal combination (5% CBP and 1% MWPF) achieved 42.93 MPa at 28 days, surpassing the control mix and showing lower sorptivity. Experimental results were combined with literature data to train PSO‐optimized hybrid ensemble models (RF‐PSO, AB‐PSO, and GB‐PSO) for compressive strength prediction. The GB‐PSO model achieved the highest predictive accuracy ( R 2 = 0.9995 for training and 0.9637 for testing) with minimal errors, demonstrating excellent generalization. Partial dependence analysis confirmed the dominant influence of water/binder ratio and cement content on strength, while excessive CBP or fiber content reduced performance. The novelty of this study lies in its dual valorization of waste resources and application of PSO‐enhanced hybrid models to SCC containing CBP and MWPF, establishing an explainable, data‐driven framework for designing intelligent and eco‐efficient concretes for next‐generation sustainable construction.

Zitieren

APA

Datta, S. D., Sahriea, F., Ashraf, J., Karim, M., Shourav, M., Alam, M. T., Abdullah, M. S., Fuad, M., & Mona, M. Z. H. (2026). Experimental and Machine Learning Analysis of Self‐Compacting Concrete Made With Metalized Waste Plastic Fiber and Clay Brick Powder. Journal of Engineering, 2026(1). https://doi.org/10.1155/je/2822510

Vancouver

Datta SD, Sahriea F, Ashraf J, Karim M, Shourav M, Alam MT, et al. Experimental and Machine Learning Analysis of Self‐Compacting Concrete Made With Metalized Waste Plastic Fiber and Clay Brick Powder. Journal of Engineering. 2026;2026(1). doi:10.1155/je/2822510

BibTeX
@article{Datta2026,
  author = {Datta, Shuvo Dip and Sahriea, Fahmied and Ashraf, Jawad and Karim, Mamunul and Shourav, Md. and Alam, Mohammad Tarequl and Abdullah, Md. Shahriar and Fuad, Mohtasim and Mona, Md. Zikrullah Hafeez},
  title = {Experimental and Machine Learning Analysis of Self‐Compacting Concrete Made With Metalized Waste Plastic Fiber and Clay Brick Powder},
  journal = {Journal of Engineering},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/je/2822510}
}
Kostenlos starten →