An Improved Neural Network Model for Enhancing Rutting Depth Prediction
DOI:
https://doi.org/10.7250/bjrbe.2022-17.572Keywords:
Mechanistic-Empirical Pavement Design Guide (MEPDG), multiple linear regression (MLR), neural network, nonlinear factors, overfitting, rutting predictionAbstract
Rutting is the main distress form of asphalt pavement, and its prediction accuracy is directly related to the reliability of the designed road. This research developed a neural network model to improve the prediction ability about the rutting of a pavement performance criterion and compared it with the multiple linear regression model and the existing neural network model. The neural network model is developed using the Keras module from the TensorFlow package in Python. Two reports generated by the National Cooperative Highway Research Program project 01-37A and the Long-Term Pavement Performance website records have been used as data sources for training the neural network model, which are reliable data preserved after years of monitoring. The input variables include the pavement thickness, service time, average annual daily traffic of trucks and the deformation of the asphalt concrete layer, granular base layer and subgrade layer. This experiment used 440 samples, of which 352 samples (80%) were used for model training and 88 samples (20%) for testing. The training results of the model reveal that the neural network model is significantly better than the multiple linear regression model, and the newly built neural network model performs better than another similar neural network in predictive performance. For the multiple linear regression model, the correlation coefficient R2 value between the measured and predicted in the testing set increased from 0.265 to 0.712. In contrast, it promotes from 0.867 to 0.902 for the neural network model.
References
American Association of State Highway and Transportation Officials (AASHTO) (2008). Mechanistic-empirical pavement design guide: a manual of practice. AASHTO: Washington, DC, USA.
Ali, Y., Irfan, M., Ahmed, S., & Ahmed, S. (2017). Permanent deformation prediction of asphalt concrete mixtures–a synthesis to explore a rational approach. Construction and Building Materials, 153, 588-597. https://doi.org/10.1016/j.conbuildmat.2017.07.105
Applied Research Associates (ARA) (2004a). Guide for Mechanistic-Empirical Design of New and Rehabilitated Pavement Structures, Final Report Appendix GG-1: NCHRP 1-37A. Transporation Research, Board of the National Academies, Washington D.C.
Applied Research Associates (ARA) (2004b). Guide for Mechanistic-Empirical Design of New and Rehabilitated Pavement Structures, Final Report NCHRP 1-37A. Transporation Research Board of the National Academies, Washington D.C.
Applied Research Associates (ARA) (2004c). Input Data for the Calibration and Validation of the Design Guide for New Constructed Flexible Pavement Sections, Final Report Appendix EE-1: NCHRP 1-37A. Transporation Research Board of the National Academies, Washington D.C.
Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157-166. https://doi.org/10.1109/72.279181
Bennert, T., & Williams, S. G. (2009). Precision of AASHTO TP62-07 for use in mechanistic–empirical pavement design guide for flexible pavements. Transportation Research Record, 2127(1), 115-126. https://doi.org/10.3141/2127-14
Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(2).
Bosurgi, G., Pellegrino, O., & Sollazzo, G. (2019). Optimizing artificial neural networks for the evaluation of asphalt pavement structural performance. The Baltic Journal of Road and Bridge Engineering, 14(1), 58-79. https://doi.org/10.7250/bjrbe.2019-14.433
Darter, M., Titus-Glover, L., & Von Quintus, H. (2009). Draft user’s guide for UDOT mechanistic-empirical pavement design guide. Report No. UT-09.11a, Applied Research Associates, Inc, Champaign, Illinois, USA.
Darter, M. I., Von Quintus, H., Bhattacharya, B. B., & Mallela, J. (2014). Calibration and implementation of the AASHTO mechanistic-empirical pavement design guide in Arizona (No. FHWA-AZ-14-606). Arizona. Dept. of Transportation. Research Center.
Dayhoff, J. E., & DeLeo, J. M. (2001). Artificial neural networks: opening the black box. Cancer: Interdisciplinary International Journal of the American Cancer Society, 91(S8), 1615-1635. https://doi.org/10.1002/1097- 0142(20010415)91:8+<1615::AID-CNCR1175>3.0.CO;2-L
Deng, L., Li, J., Huang, J. T., Yao, K., Yu, D., Seide, F., ... & Acero, A. (2013, May). Recent advances in deep learning for speech research at Microsoft. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 8604-8608). IEEE. https://doi.org/10.1109/ICASSP.2013.6639345
Dietterich, T. (1995). Overfitting and undercomputing in machine learning. ACM Computing Surveys (CSUR), 27(3), 326-327. https://doi.org/10.1145/212094.212114
Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(7).
Esra’a, I. A., & Abo-Qudais, S. A. (2018). Modeling of creep compliance behavior in asphalt mixes using multiple regression and artificial neural networks. Construction and Building Materials, 159, 635-641. https://doi.org/10.1016/j.conbuildmat.2017.10.132
Gong, H., Sun, Y., Mei, Z., & Huang, B. (2018). Improving accuracy of rutting prediction for mechanistic-empirical pavement design guide with deep neural networks. Construction and Building Materials, 190, 710-718. https://doi.org/10.1016/j.conbuildmat.2018.09.087
Haroon, D., & Clustering, I. (2017). Python Machine Learning Case Studies. Apress Berkeley, CA. https://doi.org/10.1007/978-1-4842-2823-4
Hinton, G., Srivastava, N., & Swersky, K. (2012). Neural networks for machine learning lecture 6a overview of mini-batch gradient descent. Cited on, 14(8), 2.
Hopfield, J. J. (1988). Artificial neural networks. IEEE Circuits and Devices Magazine, 4(5), 3-10. https://doi.org/10.1109/101.8118
Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2004, July). Extreme learning machine: a new learning scheme of feed-forward neural networks. In 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541) (Vol. 2, pp. 985-990). Ieee. https://doi.org/10.1109/IJCNN.2004.1380068
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70(1), 489-501. https://doi.org/10.1016/j. neucom.2005.12.126
Jadoun, F. M., & Kim, Y. R. (2012). Calibrating Mechanistic–Empirical Pavement Design Guide for North Carolina: Genetic Algorithm and Generalized Reduced Gradient Optimization Methods. Transportation Research Record, 2305(1), 131-140. https://doi.org/10.3141/2305-14
Jeong, J.-H., Jo, H., & Ditzler, G. (2020). Convolutional neural networks for pavement roughness assessment using calibration-free vehicle dynamics. Computer-Aided Civil and Infrastructure Engineering, 35(11), 1209-1229. https://doi.org/10.1111/mice.12546
Kaya, O. (2015). Investigation Of Aashtoware Pavement ME Design/Darwin-ME TM Performance Prediction Models for Iowa Pavement Analysis and Design (Doctoral dissertation, Iowa State University).
Kingma, D. P., & Ba, J. (2014). Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980. https://doi.org/10.48550/arXiv.1412.6980
Li, B., Wang, K. C. P., Zhang, A., Yang, E., & Wang, G. (2020). Automatic classification of pavement crack using deep convolutional neural network. International Journal of Pavement Engineering, 21(4), 457-463. https://doi.org/10.1080/10298436.2018.1485917
Mallela, J., Glover, L. T., Darter, M. I., Von Quintus, H., Gotlif, A., Stanley, M., & Sadasivam, S. (2009a). Guidelines for Implementing NCHRP 1-37A ME Design Procedures in Ohio: Volume 1 - Summary of Findings, Implementation Plan, and Next Steps (No. FHWA/OH-2009/9A). Ohio. Dept. of Transportation.
Mallela, J., Titus-Glover, L., Von Quintus, H., Darter, M. I., Stanley, M., & Rao, C. (2009b). Implementing the AASHTO Mechanistic-Empirical Pavement Design Guide for Missouri. Vol. II, MEDPG Model Validation and Calibration (No. CM08.01).
Muthadi, N. R., & Kim, Y. R. (2008). Local Calibration of Mechanistic-Empirical Pavement Design Guide for Flexible Pavement Design. Transportation Research Record, 2087(1), 131-141. https://doi.org/10.3141/2087-14
Najafi, S., Flintsch, G. W., & Khaleghian, S. (2019). Pavement friction management – artificial neural network approach. International Journal of Pavement Engineering, 20(2), 125-135. https://doi.org/10.1080/10298436.2016.1264221
Pao, Y.-H., Park, G.-H., & Sobajic, D. J. (1994). Learning and generalization characteristics of the random vector functional-link net. Neurocomputing, 6(2), 163-180. https://doi.org/10.1016/0925-2312(94)90053-1
Pierce, L. M., & McGovern, G. (2014). Implementation of the AASHTO Mechanistic-Empirical Pavement Design Guide and Software (No. Project 20-05, Topic 44-06).
Ramachandran, P., Zoph, B., & Le, Q. V. (2017). Searching for activation functions. arXiv preprint arXiv:1710.05941. https://doi.org/10.48550/arXiv.1710.05941
Schram, S., & Abdelrahman, M. (2006). Improving prediction accuracy in mechanistic–empirical pavement design guide. Transportation Research Record, 1947(1), 59-68. https://doi.org/10.1177/0361198106194700106
Schram, S. A., & Abdelrahman, M. (2010). Integration of Mechanistic– Empirical Pavement Design Guide distresses with local performance indices. Transportation Research Record, 2153(1), 13-23. https://doi.org/10.3141/2153-02
Shafabakhsh, G. H., Ani, O. J., & Talebsafa, M. (2015). Artificial neural network modeling (ANN) for predicting rutting performance of nano-modified hot-mix asphalt mixtures containing steel slag aggregates. Construction and Building Materials, 85, 136-143. https://doi.org/10.1016/j.conbuildmat.2015.03.060
Simpson, A. L., Daleiden, J. F., & Hadley, W. O. (1995). Rutting analysis from a different perspective. Transportation Research Record, 1473, 9-17.
Smith, B., & Nair, H. (2015). Development of Local Calibration Factors and Design Criteria Values for Mechanistic-Empirical Pavement Design (No. FHWA/VCTIR 16-R1). Virginia Center for Transportation Innovation and Research.
Sollazzo, G., Fwa, T. F., & Bosurgi, G. (2017). An ANN model to correlate roughness and structural performance in asphalt pavements. Construction and Building Materials, 134, 684-693. https://doi.org/10.1016/j.conbuildmat.2016.12.186
Souliman, M. I., Mamlouk, M. S., El-Basyouny, M. M., & Zapata, C. E. (2010). Calibration of the AASHTO MEPDG for flexible pavement for arizona conditions. In Proceedings of the Transportation Research Board 89th Annual Meeting (Vol. 22, pp. 243-286). Washington, DC, USA: Transportation Research Board.
Sun, X., Han, J., Parsons, R. L., Misra, A., & Thakur, J. K. (2015). Calibrating the Mechanistic-Empirical Pavement Design Guide for Kansas (No. KS-14-17). Kansas. Dept. of Transportation. Bureau of Materials & Research.
Wang, C., Xu, S., Liu, J., Yang, J., & Liu, C. (2022). Building an improved artificial neural network model based on deeply optimizing the input variables to enhance rutting prediction. Construction and Building Materials, 348, 128658. https://doi.org/10.1016/j.conbuildmat.2022.128658
Wang, C., Xu, S., & Yang, J. (2021). Adaboost Algorithm in Artificial Intelligence for Optimizing the IRI Prediction Accuracy of Asphalt Concrete Pavement. Sensors, 21(17), 5682. https://doi.org/10.3390/s21175682
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Shuzhan Xu, Junxin Yang, Changbai Wang
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
