A comparative analysis of tree-based machine learning algorithms for predicting the mechanical properties of fibre-reinforced GGBS geopolymer concrete

被引:4
作者
Philip, Shimol [1 ]
Nidhi, M. [1 ]
Ahmed, Hemn Unis [2 ,3 ,4 ]
机构
[1] Natl Inst Technol Puducherry, Dept Civil Engn, Karaikal 609609, Puducherry, India
[2] Univ Sulaimani, Coll Engn, Civil Engn Dept, Sulaimani, Kurdistan Regio, Iraq
[3] Komar Univ Sci & Technol, Civil Engn Dept, Sulaimani, Kurdistan Regio, Iraq
[4] Univ Halabja, Civil Engn Dept, Halabja, Kurdistan Regio, Iraq
关键词
Fibre-reinforced geopolymer concrete; Statistical analysis; k-fold cross-validation; Tree-based prediction model; Sensitivity analysis; BLAST-FURNACE SLAG; MIX DESIGN; FLY-ASH; STEEL; MICROSTRUCTURE; STRENGTH;
D O I
10.1007/s41939-023-00355-6
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The advancement of strength prediction techniques for fibre-reinforced ground granulated blast furnace slag (GGBS)-based geopolymer concrete (GPC) is still in its early stages, especially compared to conventional GPC, primarily due to its complexity and the scarcity of available data. Therefore, this study evaluates five tree-based machine learning techniques, including decision tree, random forest, XGBoost (XGB), gradient boost and AdaBoost, to determine the optimal algorithm for forecasting the mechanical strength properties of fibre-reinforced GGBS-based GPC. The input parameters included the mix proportions, curing conditions and properties of fibres; while the output parameters were compressive strength, split tensile strength and flexural strength. The models were trained, tested and validated using a comprehensive dataset obtained from the published literature. The performance and accuracy of the models were compared based on statistical evaluation metrics such as the coefficient of determination (R2), mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). k-fold validation was performed to mitigate overfitting and the algorithms were fine-tuned for optimal performance. The results demonstrated that the XGBoost model outperformed other models, achieving high predictive accuracy with R2 values of 0.938, 0.957 and 0.909 for compressive, split tensile and flexural strength, respectively, along with significantly lower RMSE and MAE values. XGBoost continued to outperform other techniques and showed consistency of high accuracy in performance for the testing dataset even after k-fold cross-validation. The sensitivity analysis results indicate that the prediction of compressive strength in fibre-reinforced GGBS-based GPC was most significantly influenced by specimen age and curing temperature. However, the fibre volume and curing temperature strongly influenced split tensile and flexural strength.
引用
收藏
页码:2555 / 2583
页数:29
相关论文
共 69 条
  • [1] Impact Behaviour of Steel-Fibre-Reinforced Alkali-Activated Slag Concrete Exposed to Elevated Temperatures
    Abubakr, Ahmed
    Soliman, Ahmed
    [J]. MATERIALS, 2023, 16 (11)
  • [2] Compressive strength prediction of fly ash-based geopolymer concrete via advanced machine learning techniques
    Ahmad, Ayaz
    Ahmad, Waqas
    Aslam, Fahid
    Joyklad, Panuwat
    [J]. CASE STUDIES IN CONSTRUCTION MATERIALS, 2022, 16
  • [3] Prediction of Geopolymer Concrete Compressive Strength Using Novel Machine Learning Algorithms
    Ahmad, Ayaz
    Ahmad, Waqas
    Chaiyasarn, Krisada
    Ostrowski, Krzysztof Adam
    Aslam, Fahid
    Zajdel, Paulina
    Joyklad, Panuwat
    [J]. POLYMERS, 2021, 13 (19)
  • [4] Support vector regression (SVR) and grey wolf optimization (GWO) to predict the compressive strength of GGBFS-based geopolymer concrete
    Ahmed, Hemn Unis
    Mostafa, Reham R.
    Mohammed, Ahmed
    Sihag, Parveen
    Qadir, Azad
    [J]. NEURAL COMPUTING & APPLICATIONS, 2023, 35 (03) : 2909 - 2926
  • [5] Multivariable models including artificial neural network and M5P-tree to forecast the stress at the failure of alkali-activated concrete at ambient curing condition and various mixture proportions
    Ahmed, Hemn Unis
    Mohammed, Ahmed S.
    Mohammed, Azad A.
    [J]. NEURAL COMPUTING & APPLICATIONS, 2022, 34 (20) : 17853 - 17876
  • [6] Compressive strength of geopolymer concrete modified with nano-silica: Experimental and modeling investigations
    Ahmed, Hemn Unis
    Mohammed, Ahmed S.
    Faraj, Rabar H.
    Qaidi, Shaker M. A.
    Mohammed, Azad A.
    [J]. CASE STUDIES IN CONSTRUCTION MATERIALS, 2022, 16
  • [7] Steel fibre reinforced geopolymer concrete (SFRGC) with improved microstructure and enhanced fibre-matrix interfacial properties
    Al-Majidi, Mohammed Haloob
    Lampropoulos, Andreas
    Cundy, Andrew B.
    [J]. CONSTRUCTION AND BUILDING MATERIALS, 2017, 139 : 286 - 307
  • [8] Characteristics of metakaolin-based geopolymer concrete for different mix design parameters
    Albidah, Abdulrahman
    Alghannam, Mohammed
    Abbas, Husain
    Almusallam, Tarek
    Al-Salloum, Yousef
    [J]. JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T, 2021, 10 : 84 - 98
  • [9] Compressive Strength Estimation of Geopolymer Composites through Novel Computational Approaches
    Amin, Muhammad Nasir
    Khan, Kaffayatullah
    Ahmad, Waqas
    Javed, Muhammad Faisal
    Qureshi, Hisham Jahangir
    Saleem, Muhammad Umair
    Qadir, Muhammad Ghulam
    Faraz, Muhammad Iftikhar
    [J]. POLYMERS, 2022, 14 (10)
  • [10] Exploration of mechanical and durability characteristics of fly ash-GGBFS based green geopolymer concrete
    Bellum, Ramamohana Reddy
    Muniraj, Karthikeyan
    Madduru, Sri Rama Chand
    [J]. SN APPLIED SCIENCES, 2020, 2 (05):