International Journal of Highway Engineering (한국도로학회논문집)

Korean Society of Road Engineers (한국도로학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Asphalt Pavement Service Life using Deep Learning

딥러닝을 활용한 일반국도 아스팔트포장의 공용수명 예측

  • Received : 2018.02.19
  • Accepted : 2018.04.01
  • Published : 2018.04.16
Download PDF
⟨ Previous Next ⟩

Abstract

PURPOSES : The study aims to predict the service life of national highway asphalt pavements through deep learning methods by using maintenance history data of the National Highway Pavement Management System. METHODS : For the configuration of a deep learning network, this study used Tensorflow 1.5, an open source program which has excellent usability among deep learning frameworks. For the analysis, nine variables of cumulative annual average daily traffic, cumulative equivalent single axle loads, maintenance layer, surface, base, subbase, anti-frost layer, structural number of pavement, and region were selected as input data, while service life was chosen to construct the input layer and output layers as output data. Additionally, for scenario analysis, in this study, a model was formed with four different numbers of 1, 2, 4, and 8 hidden layers and a simulation analysis was performed according to the applicability of the over fitting resolution algorithm. RESULTS : The results of the analysis have shown that regardless of the number of hidden layers, when an over fitting resolution algorithm, such as dropout, is applied, the prediction capability is improved as the coefficient of determination ($R^2$) of the test data increases. Furthermore, the result of the sensitivity analysis of the applicability of region variables demonstrates that estimating service life requires sufficient consideration of regional characteristics as $R^2$ had a maximum of between 0.73 and 0.84, when regional variables where taken into consideration. CONCLUSIONS : As a result, this study proposes that it is possible to precisely predict the service life of national highway pavement sections with the consideration of traffic, pavement thickness, and regional factors and concludes that the use of the prediction of service life is fundamental data in decision making within pavement management systems.

Keywords

References

  1. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., and Ghemawat, S. (2016). "Tensorflow: Large-scale machine learning on heterogeneous distributed systems."arXiv preprint arXiv:1603.04467.
  2. Attoh-Okine, N. O. (1999). "Analysis of learning rate and momentum term in backpropagation neural network algorithm trained to predict pavement performance."Advances in Engineering Software, Vol.30, No.4, pp.291-302. https://doi.org/10.1016/S0965-9978(98)00071-4
  3. Baek, J., Lim, J., Kwon, S., and Kwon, B. (2015). "Performance Evaluation of Long-Life Asphalt Concrete Overlays Based on Field Survey Monitoring in National Highways."Intl. Journal of the Highway Engineers, Vol. 17, No. 3, pp.69-76.
  4. Bowden, G.J., Dandy, G.C., Maier, H.R. (2005). " Input determination for neural network models in water resources applications. Part 1-background and methodology."Journal of Hydrology, Vol.301, No.1-4, pp.75-92. https://doi.org/10.1016/j.jhydrol.2004.06.021
  5. Clevert, D. A., Unterthiner, T., Hochreiter, S. (2015). "Fast and accurate deep network learning by exponential linear units (elus)."arXiv preprint arXiv:1511.07289.
  6. Dahl, G. E., Sainath, T. N., Hinton, G. E. (2013). "Improving deep neural networks for LVCSR using rectified linear units and dropout."IEEE International Confedence Acoustics on Speech and Signal Processing(ICASSP), pp.8609-8613.
  7. Do, M. and Kwon, S. (2010). "Selection of Probability Distribution of Pavement Life Based on Reliability Method."Intl. Journal of the Highway Engineers, Vol.12, No.1. pp.61-69.
  8. Gopalakrishnan, K., Khaitan, S. K., Choudhary, A., Agrawal, A. (2017). "Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection."Construction and Building Materials, Vol.157, pp.322-330. https://doi.org/10.1016/j.conbuildmat.2017.09.110
  9. Han, D., Yoo, I., Lee, S. (2017a). "Improvement of Multivariable, Nonlinear, and Overdispersion Modeling with Deep Learning: A Case Study on Prediction of Vehicle Fuel Consumption Rate."Intl. Journal of the Highway Engineers, Vol.19, No.4, pp.1-7.
  10. Han, D., Do, M., Kim, B. (2017b). "Internal Property and Stochastic Deterioration Modeling of Total Pavement Condition Index for Transportation Asset Management."Intl. Journal of the Highway Engineers, Vol.19, No.5, pp.1-11.
  11. Han, D. (2013). "Stochastic Disaggregation and Aggregation of Localized Uncertainty in Pavement Deterioration Process." Journal Of The Korean Society Of Civil Engineers, Vol.33, No.4. pp.1651-1664. https://doi.org/10.12652/Ksce.2013.33.4.1651
  12. Han, D. and Do, M. (2012). "Estimation of Life Expectancy and Budget Demands based on Maintenance Strategy."Journal Of The Korean Society Of Civil Engineers, Vol.32, No.4D, pp.345-356. https://doi.org/10.12652/Ksce.2012.32.4D.345
  13. Hinton, G. E., Osindero, S., Tech, Y. W. (2006). "A fast learning algorithm for deep belief nets."Neural computation, Vol.18, No.7, pp.1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
  14. Kim, H., and Lim, H. (2016). "A Basic Study on the Prediction of Collapse of Tunnels Using Artificial Neural Network."Journal of The Korean Geotechnical Society, Vol.32, No.2, pp.5-17 https://doi.org/10.7843/KGS.2016.32.2.5
  15. Kobayashi, K., Kaito, K., Nam, L. (2012). "A statistical deterioration forecasting method using hidden Markov model with measurement error."Transportation Research-Part B, Vol.46, pp.544-561. https://doi.org/10.1016/j.trb.2011.11.008
  16. Kobayashi, K., Do, M., Han, D. (2010). "Estimation of Markovian transition probabilities for pavement deterioration forecasting." KSCE J. of Civil Engineering, Vol.14, No.3, pp.341-351.
  17. Ministry of Land, Infrastructure, and Transport (MOLIT) (2016). Development of Road Asset Management System Focus on Road Pavement.
  18. May, R., Dandy, G., and Maier, H. (2011). "Review of Input Variable Selection Methods for Artificial Neural Networks." Artificial Neural Networks-Methodological Advances and Biomedical Applications, Edited by Suzuki, K., InTech, India, pp.19-44.
  19. May, R.J., Maier, H.R., Dandy, G.C., Fernando, T.M.K.G. (2008). "Non-linear variable selection for artificial neural networks using partial mutual information."Environmental Modelling & Software, Vol.23, No.10-11, pp. 1312-1326. https://doi.org/10.1016/j.envsoft.2008.03.007
  20. Mishalani, R.G., and Madanat, S.M. (2002). "Computation of infrastructure transition probabilities using stochastic duration models."J. of Infrastructure Systems, Vol.8, No.4, pp.139-148. https://doi.org/10.1061/(ASCE)1076-0342(2002)8:4(139)
  21. Minsky M.L., Papert, S. A. (1969). "Perceptrons."Cambridge, MA: MIT Press.
  22. Nair, V., Hinton, G. E. (2010). "Rectified linear units improve restricted boltzmann machines."In Proceedings of the 27th International on Machine Learning (ICML-10), pp.809-814.
  23. Srivastava N., Hinton, G. E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. (2014)."Dropout: A simple way to prevent neural networks from overfitting."The Journal of Machine Learning Research, Vol.15, No.1, pp.1929-1958.
  24. Tan, P.N., Steinbach, M., Kumar, V. (2006). "Introduction to Data Mining", Pearson Education, Addison Wesely.
  25. Terzi, S. (2007). "Modeling the pavement serviceability ratio of flexible highway pavements by artificial neural networks." Construction and Building Materials, Vol.21, No.3, pp.590-593. https://doi.org/10.1016/j.conbuildmat.2005.11.001
  26. Werbos, P.J. (1974). "Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences."PhD thesis, Harvard University.