Prediction of Multi-layered Pavement Moduli Based on Falling Weight Deflectometer Test Using Soft Computing Approaches

被引:4
作者
Phulsawat, Barami [1 ]
Senjuntichai, Angsumalin [2 ]
Senjuntichai, Teerapong [1 ]
机构
[1] Chulalongkorn Univ, Fac Engn, Ctr Excellence Appl Mech & Struct, Dept Civil Engn, Bangkok 10330, Thailand
[2] Chulalongkorn Univ, Fac Engn, Dept Ind Engn, Bangkok 10330, Thailand
关键词
Artificial neural networks; Falling weight deflectometer; Multi-layered medium; Pavement performance prediction; Random forest regression; Sensitivity analysis; FLEXIBLE PAVEMENTS;
D O I
10.1007/s40515-024-00370-1
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The application of supervised machine learning algorithms to provide solutions for various civil engineering problems is an emerging trend. This paper presents the utilization of artificial neural network (ANN) and random forest regression (RFR) for the prediction of the elastic moduli of multi-layered pavement based on the falling weight deflectometer (FWD) test. The establishment of ML models includes data preprocessing, hyperparameter optimization, and performance evaluations. The ML models are created from both ANN and RFR techniques using 122,500 datasets from a theoretical model of the FWD test, generated by employing an exact stiffness matrix method for the analysis of multi-layered flexible pavement. The performance measures of both ML models, developed from the synthetic dataset, indicate that the output variables (the predicted pavement moduli) are precisely explained by the input parameters (the measured surface displacements). Both ML solutions are then compared with the FWD test results performed on the road infrastructures in Thailand, showing good agreement with the predicted moduli from the FWD tests. Between the two ML solutions, RFR displays better accuracy in predicting the pavement moduli from the FWD tests with the R2 values of the predicted elastic moduli exceeding 90%. Besides, a sensitivity analysis is carried out to illustrate the impact of surface deflections recorded at each geophone on the predicted pavement moduli. The present study demonstrates the efficacy of ML techniques in assessing road infrastructures and highlights the significance of sensitivity analysis in enhancing the accuracy of pavement performance prediction.
引用
收藏
页码:2348 / 2381
页数:34
相关论文
共 44 条
  • [1] Artificial Neural Network-Based Inversion for Leaky Rayleigh Wave Dispersion Curve from Non-contact SASW Testing of Multi-layer Pavements
    Al-Adhami, Hiba
    Gucunski, Nenad
    [J]. TRANSPORTATION INFRASTRUCTURE GEOTECHNOLOGY, 2021, 8 (01) : 1 - 11
  • [2] Ameri M., 2009, Asian Journal of Applied Sciences, V2, P197
  • [3] Recycled Aggregates Concrete Compressive Strength Prediction Using Artificial Neural Networks (ANNs)
    B K A, Mohamad Ali Ridho
    Ngamkhanong, Chayut
    Wu, Yubin
    Kaewunruen, Sakdirat
    [J]. INFRASTRUCTURES, 2021, 6 (02) : 1 - 20
  • [4] Progressive Machine Learning Approaches for Predicting the Soil Compaction Parameters
    Benbouras, Mohammed Amin
    Lefilef, Lina
    [J]. TRANSPORTATION INFRASTRUCTURE GEOTECHNOLOGY, 2023, 10 (02) : 211 - 238
  • [5] Random forests
    Breiman, L
    [J]. MACHINE LEARNING, 2001, 45 (01) : 5 - 32
  • [6] Evaluation and Prediction of Pavement Deflection Parameters Based on Machine Learning Methods
    Chen, Xueqin
    Dong, Qiao
    Dong, Shi
    [J]. BUILDINGS, 2022, 12 (11)
  • [7] Determination of complex modulus gradients of flexible pavements using falling weight deflectometer and artificial intelligence
    Deng, Yong
    Luo, Xue
    Zhang, Yazhou
    Lytton, Robert L.
    [J]. MATERIALS AND STRUCTURES, 2020, 53 (04)
  • [8] Development of the pavement structural health index based on falling weight deflectometer testing
    Elbagalati, Omar
    Elseifi, Mostafa
    Gaspard, Kevin
    Zhang, Zhongjie
    [J]. INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING, 2018, 19 (01) : 1 - 8
  • [9] USING APPLICATION OF AN ARTIFICIAL NEURAL NETWORK SYSTEM TO BACKCALCULATE PAVEMENT ELASTIC MODULUS
    Elshamy, M. M. M.
    Tiraturyan, A. N.
    [J]. RUSSIAN JOURNAL OF BUILDING CONSTRUCTION AND ARCHITECTURE, 2020, (02): : 84 - 93
  • [10] Artificial neural network back-calculation of flexible pavements with sensitivity analysis using Garson's and connection weights algorithms
    Ghanizadeh, Ali Reza
    Heidarabadizadeh, Nasrin
    Jalali, Farhang
    [J]. INNOVATIVE INFRASTRUCTURE SOLUTIONS, 2020, 5 (02)