Yazar "Shahjalal, Md." seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Explainable ensemble learning data-driven modeling of mechanical properties of fiber-reinforced rubberized recycled aggregate concrete
    (Elsevier, 2023) Çakıroğlu, Celal; Shahjalal, Md.; Islam, Kamrul; Mahmood, S.M. Faisal; Billah, A.H.M. Muntasir
    Colossal amounts of construction and demolition waste (C&D) and waste tires have become a considerable global environmental concern. To alleviate this issue, it is proposed to use crumb rubber (CR) derived from waste tires and recycled coarse aggregate (RCA) from C&D as a replacement for natural aggregates in new construction materials. However, the wide variability in the mechanical properties of recycled concrete and the lack of reliable predictive tools in the literature make the wide-scale adoption of these new materials a challenging task. Robust methodologies for predicting the mechanical properties of these materials are needed to advance them as viable alternatives to natural aggregates. Hence, this study compiled a comprehensive experimental database comprising 451, 151, and 102 samples from the literature, including compressive, tensile, and flexural strength values of fiber-reinforced rubberized recycled aggregate concrete (FRRAC). Based on these experimental results, seven data-driven machine learning models were developed. A total of 16 input variables were considered in developing these machine-learning models. It was demonstrated that the CatBoost model performed best for predicting the compressive and tensile strengths, whereas for flexural strength, Random Forest models provided better performance. According to SHapley Additive exPlanations (SHAP) values, the age of concrete, fineness modulus of the natural fine aggregate and the replacement percentage of the RCA were the most impactful input features in the prediction of the compressive, tensile, and flexural strength, respectively. Moreover, it was found that the usage of fiber reinforcement increased the impact of the w/c ratio. Based on the results, it is suggested to limit the replacement level of RCA and CR to 30% and 15%, respectively. Finally, this study highlights the importance of data-driven models in optimizing the mechanical properties of FRRAC, offering a useful tool for industry-scale developments.
  • Küçük Resim
    Öğe
    Explainable ensemble learning graphical user interface for predicting rebar bond strength and failure mode in recycled coarse aggregate concrete
    (Elsevier, 2024) Çakıroğlu, Celal; Tusher, Tanvir Hassan; Shahjalal, Md.; Islam, Kamrul; Billah, A. H. M. Muntasir; Nehdi, Moncef L.
    Novel study deploys robust machine learning algorithms using newly built comprehensive dataset to predict reinforcing rebar-to-recycled coarse aggregate concrete (RCA) bond strength and failure mode. Prior investigations have solely concentrated on bond strength, resulting in a limited comprehension of the bond failure pattern. Considering the increasing significance of sustainable construction methods, it is crucial to examine both the failure pattern and bond strength to expand the versatility of RCA in various reinforced concrete structures. Accordingly, XGBoost, CatBoost, Random Forest, and LightGBM were trained for this purpose. Model performance was appraised using various statistical metrics, while failure classification performance was assessed using accuracy, recall, and precision indicators. Model performance was ranked using Copeland’s algorithm. Feature importance was quantified using SHAP. Coefficient of determination of 0.91 was achieved by XGBoost in predicting bond strength, outperforming other nine analytical models in literature. Failure mode was predicted with accuracy of 94% by CatBoost, XGBoost, and LightGBM. Embedment length and compressive strength features had greatest influence on bond strength and failure mode, respectively. User-friendly graphical interface was developed to harvest ML models in real-world engineering practice. Online free access accurately assigns to any given combination of input features corresponding accurate rebar bond strength and failure mode.