Enhancing Predictive Accuracy of Compressive Strength in Recycled Concrete Using Advanced Machine Learning Techniques with K-means Clustering

Authors

Ziaul Haq Doost, Department of Civil and Environmental Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaFollow
Leonardo Goliatt, Computational and Applied Mechanics Department, Federal University of Juiz de Fora, 36036-900, BrazilFollow
Mohammed Suleman Aldlemy, Department of Mechanical Engineering, Collage of Mechanical Engineering Technology, Benghazi, Libya, AND Libyan Center for Solar Energy Research and Studies, Benghazi Branch, Benghazi, LibyaFollow
Mumtaz Ali, UniSQ College, University of Southern Queensland, QLD 4305, Australia; AND Faculty of Sustainable Design Engineering, University of Prince Edward Island, Charlottetown, PE C1A4P3, CanadaFollow
Bruno da S. Macêdo, Department of Systems Engineering and Automation, Federal University of Lavras, Lavras, MG, 37200-000, BrazilFollow

Abstract

The urgent need to mitigate environmental impacts in the construction industry drives the exploration of sustainable practices, such as the use of recycled materials in concrete production. The primary objective of this study was to enhance the predictability of compressive strength in the concrete through the application of advanced machine learning (ML) techniques, specifically Gradient Boosting Regression (GBR) and Random Forest Regression (RFR). Using a comprehensive dataset of 353 eco-friendly concrete samples, the study carefully developed and validated these models to evaluate their performance. The findings exposed that the GBR model outperformed the RFR model, obtained an R² of 0.97 in training phase and 0.96 in testing phase, the findings supported further with root mean squared error (RMSE) of 1.99 and 3.06, and by mean absolute error (MAE) of 1.44 and 2.38 for training and testing phases respectively, where indicating high predictive accuracy. Conclusively, the broader adoption of GBR model for similar applications recommended by the study and points towards future research directions to integrate more diverse datasets and investigate more predictive models to improve sustainable construction practices.

Recommended Citation

Doost, Ziaul Haq; Goliatt, Leonardo; Aldlemy, Mohammed Suleman; Ali, Mumtaz; and Macêdo, Bruno da S. (2024) "Enhancing Predictive Accuracy of Compressive Strength in Recycled Concrete Using Advanced Machine Learning Techniques with K-means Clustering," AUIQ Technical Engineering Science: Vol. 1: Iss. 1, Article 10.
DOI: https://doi.org/10.70645/3078-3437.1009