Prediction of Multi-layered Pavement Moduli Based on Falling Weight Deflectometer Test Using Soft Computing Approaches
Transportation Infrastructure Geotechnology - Trang 1-34 - 2024
Tóm tắt
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.
Tài liệu tham khảo
Al-Adhami, H., Gucunski, N.: Artificial neural network–based inversion for leaky rayleigh wave dispersion curve from non-contact SASW testing of multi-layer pavements. Transport Infrast Geotechnol. 8, 1–11 (2021). https://doi.org/10.1007/s40515-020-00117-8
Ameri, M., Yavari, N., Scullion, T.: Comparison of static and dynamic backcalculation of flexible pavement layers moduli, using four softwares. Asian J Appl Sci. 2(3), 197–210 (2009). https://doi.org/10.3923/ajaps.2009.197.210
Benbouras, M.A., Lefilef, L.: Progressive machine learning approaches for predicting the soil compaction parameters. Transport Infrast Geotechnol. 10, 211–238 (2023). https://doi.org/10.1007/s40515-021-00212-4
Breiman, L.: Random forests. Mach Learn. 45, 5–32 (2001)
Chen, X., Dong, Q., Dong, S.: Evaluation and prediction of pavement deflection parameters based on machine learning methods. Buildings. 12(11), 1928 (2022). https://doi.org/10.3390/buildings12111928
Deng, Y., Luo, X., Zhang, Y., Lytton, R.L.: Determination of complex modulus gradients of flexible pavements using falling weight deflectometer and artificial intelligence. Mater Struct. 53, 100 (2020). https://doi.org/10.1617/s11527-020-01528-2
Elbagalati, O., Elseifi, M., Gaspard, K., Zhang, Z.: Development of the pavement structural health index based on falling weight deflectometer testing. Int. J. Pavem. Eng. 19(1), 1–8 (2018). https://doi.org/10.1080/10298436.2016.1149838
Elshamy, M., Tiraturyan, A.N.: Using application of an artificial neural network system to backcalculate pavement elastic modulus. Russian J Build Const Architectur. 2(46), 84–93 (2020)
Ghanizadeh, A.R., Heidarabadizadeh, N., Jalali, F.: Artificial neural network back-calculation of flexible pavements with sensitivity analysis using Garson’s and connection weights algorithms. Innov Infrast Solut. 5, 63 (2020). https://doi.org/10.1007/s41062-020-00312-z
Gopalakrishnan, K., Thompson, M.R.: Backcalculation of airport flexible pavement non-linear moduli using artificial neural networks. The Florida AI Research Society (2004)
Guzina, B.B., Osburn, R.H.: Effective tool for enhancing elastostatic pavement diagnosis. Transpor Res Rec. 1806(1), 30–37 (2002). https://doi.org/10.3141/1806-04
HasanuddinSetyawan, A., Yulianto, B.: Evaluation of road performance based on international roughness index and falling weight deflectometer. IOP Conf.Series: Mater. Sci. Eng.. 333, 012090 (2018). https://doi.org/10.1088/1757-899X/333/1/012090
Hosseini, S., Khatti, J., Taiwo, B.O., Fissha, Y., Grover, K.S., Ikeda, H., Pushkarna, M., Berhanu, M., Ali, M.: Assessment of the ground vibration during blasting in mining projects using different computational approaches. Sci Rep. 13, 18582 (2023). https://doi.org/10.1038/s41598-023-46064-5
Karasudhi, P.: Foundations of solid mechanics. Kluwer Academic Publishers, The Netherlands (1990)
Khatti, J., Grover, K.S.: A scientometrics review of soil properties prediction using soft computing approaches. Arch Comp Methods Eng (2023). https://doi.org/10.1007/s11831-023-10024-z
Khatti, J., Grover, K.S.: Prediction of UCS of fine-grained soil based on machine learning part 1: multivariable regression analysis, gaussian process regression, and gene expression programming. Multiscale Multidiscip Mod Exp Des. 6, 199–222 (2023). https://doi.org/10.1007/s41939-022-00137-6
Khatti, J., Grover, K.S.: Assessment of fine-grained soil compaction parameters using advanced soft computing techniques. Arab J Geosci. 16, 208 (2023). https://doi.org/10.1007/s12517-023-11268-6
Khatti, J., Grover, K.S.: Prediction of compaction parameters for fine-grained soil: critical comparison of the deep learning and standalone models. J Rock Mech Geotech Eng. 15(11), 3010–3038 (2023). https://doi.org/10.1016/j.jrmge.2022.12.034
Khatti, J., Grover, K.S.: CBR prediction of pavement materials in unsoaked condition using LSSVM, LSTM-RNN, and ANN approaches. Int J Pavement Res Technol. (2023). https://doi.org/10.1007/s42947-022-00268-6
Khatti, J., Samadi, H., Grover, K.S.: Estimation of settlement of pile group in clay using soft computing techniques. Geotech Geol Eng. (2023). https://doi.org/10.1007/s10706-023-02643-x
Khatti, J., Grover, K.S., Kim, H.J., Mawuntu, K.B.A., Park, T.W.: Prediction of ultimate bearing capacity of shallow foundations on cohesionless soil using hybrid LSTM and RVM approaches: an extended investigation of multicollinearity. Comp Geotech. 165, 105912 (2024). https://doi.org/10.1016/j.compgeo.2023.105912
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. Proc. Int. Conf. Learn. Representations. 1–15 (2015)
Lav, A.H., Goktepe, A.B., Lav, M.A.: Backcalculation of flexible pavements using soft computing. In: Gopalakrishnan, K., Ceylan, H., Attoh-Okine, N.O. (eds.) Intelligent and soft computing in infrastructure systems engineering. Stud. Comput. Intell. 259, 67–106 (2009). https://doi.org/10.1007/978-3-642-04586-8_4
Liu, T., Wang, Z., Zeng, J., Wang, J.: Machine-learning-based models to predict shear transfer strength of concrete joints. Eng Struct. 249, 16 (2021). https://doi.org/10.1016/j.engstruct.2021.113253
Meier, R.W., Rix, G.J.: Backcalculation of flexible pavement moduli using artificial neural networks, pp. 75–82. Transportation Research Record. TRB, National Research Council, Washington, D.C. (1994)
Meier, R.W., Rix, G.J.: Backcalculation of flexible pavement moduli from dynamic deflection basins using artificial neural networks, pp. 72–81. Transportation Research Record. TRB, National Research Council, Washington, D.C. (1995)
Meier, R.W., Alexander, D.R., Freeman, R.B.: Using artificial neural networks as a forward approach to backculculation. Transport Res Rec. 1570, 126–133 (1997). https://doi.org/10.3141/1570-15
Miah, M.I., Ahmed, S., Zendehboudi, S., Butt, S.: Machine learning approach to model rock strength: prediction and variable selection with aid of log data. Rock Mech Rock Eng. 53, 4691–4715 (2020). https://doi.org/10.1007/s00603-020-02184-2
Mohamad Ali Ridho, B.K.A., Ngamkhanong, C., Wu, Y., Kaewunruen, S.: Recycled aggregates concrete compressive strength prediction using artificial neural networks (ANNs). Infrastructures. 6(2), 17 (2021)
Nam, B.H., An, J., Kim, M., Murphy, M.R., Zhang, Z.: Improvements to the structural condition index (SCI) for pavement structural evaluation at network level. Int J Pavem Eng. 17(8), 680–697 (2016). https://doi.org/10.1080/10298436.2015.1014369
Nguyen, D.K., Nguyen, T.P., Ngamkhanong, C., Keawsawasvong, S., Nguyen, T.K., Lai, V.Q.: Prediction of uplift resistance of circular anchors in anisotropic clays using MLR, ANN, and MARS. Appl Ocean Res. 136, 103584 (2023). https://doi.org/10.1016/j.apor.2023.103584
Park, B., Cho, S., Rahbar-Rastegar, R., Nantung, T.E., Haddock, J.E.: Prediction of critical responses in full-depth asphalt pavements using the falling weight deflectometer deflection basin parameters. Const. Build. Mater. 318 (2022). https://doi.org/10.1016/j.conbuildmat.2021.126019
Plati, C., Georgiou, P., Papavasiliou, V.: Simulating pavement structural condition using artificial neural networks. Struct. Infrastr. Eng. 12(9), 1127–1136 (2016). https://doi.org/10.1080/15732479.2015.1086384
Plischke, E.: An effective algorithm for computing global sensitivity indices (EASI). Reliab Eng Syst Safety. 95(4), 354–360 (2010). https://doi.org/10.1016/j.ress.2009.11.005
Rahim, A., George, K.P.: Falling weight deflectometer for estimating subgrade elastic modulus. J Transport Eng. 129(1), 100–107 (2003). https://doi.org/10.1061/(ASCE)0733-947X(2003)129:1(100)
Saleh, M.: A mechanistic empirical approach for the evaluation of the structural capacity and remaining service life of flexible pavements at the network level. Canad. J.Civil. Eng. 43(8), 749–758 (2016). https://doi.org/10.1139/CJCE-2016-0060
Senjuntichai, T., Sornpakdee, N., Teerawong, J., Rajapakse, R.K.N.D.: Time-dependent response of an axially loaded elastic bar in a multilayered poroelastic medium. J Eng Mech. 133(5), 578–587 (2007)
Senjuntichai, T., Keawsawasvong, S., Yooyao, B.: Exact stiffness method for multi-layered saturated soils under moving dynamic loads. J GeoEng. 15, 59–171 (2020)
Senjuntichai, T., Sornpakdee, N., Keawsawasvong, S., Phulsawat, B., Rajapakse, R.K.N.D.: Consolidation settlement of vertically loaded pile groups in multilayered poroelastic soils. Transp Geotech. 38, 100904 (2023). https://doi.org/10.1016/j.trgeo.2022.100904
Singh, V.P.: Uniform distribution. In: Singh, V.P. (eds.) Entropy-based parameter estimation in hydrology, pp. 10–13. Water Science and Technology Library, Springer, Dordrecht (1998)
Tissot, J.Y., Prieur, C.: Bias correction method for the estimation of sensitivity indices based on random balance designs. Reliab Eng Syst Safety. 107, 205–213 (2012). https://doi.org/10.1016/j.ress.2012.06.010
Van Rossum, G., Drake, F.L.: Python tutorial. Centrum voor Wiskunde en Informatica Amsterdam, The Netherlands (1995)
Yin, D., Mrawira, D.M.: Comparison between laboratory investigation and non-destructive testing methods for mechanistic characterization of asphalt pavement. 88th Annual Meeting of Transportation Research Board. 9, 3339 (2009)
Yoonirundorn, K., Senjuntichai, T., Keawsawasvong, S., Ngamkhanong, C., Wijeyewickrema, A.C.: Stability analysis of multiple unsupported excavations in cohesive-frictional soils using finite element limit analysis (FELA) and an artificial neural network (ANN). Modeling. Earth. Syst. Environ. (2023). https://doi.org/10.1007/s40808-023-01857-5