Deep neural networks for sensitivity assessment of design variables on the structural design parameters of flexible pavements for low-traffic volume roads

Brayan Andres Velasquez Bueno; María José Páez Arenas; Allex Eduardo Alvarez Lugo; Vladimir Ernesto Merchan Jaimes; Carlos Augusto Fajardo Ariza; Gustavo Chio

doi:10.24054/rcta.v2i42.2597

Authors

Brayan Andres Velasquez Bueno Universidad Industrial de Santander https://orcid.org/0000-0002-0697-4979
María José Páez Arenas Universidad Industrial de Santander https://orcid.org/0009-0001-3859-9747
Allex Eduardo Alvarez Lugo Universidad Industrial de Santander https://orcid.org/0000-0001-9010-7642
Vladimir Ernesto Merchan Jaimes Universidad Industrial de Santander https://orcid.org/0000-0002-7430-5451
Carlos Augusto Fajardo Ariza Universidad Industrial de Santander https://orcid.org/0000-0002-8995-4585
Gustavo Chio Universidad Industrial de Santander https://orcid.org/0000-0003-4766-9759

DOI:

https://doi.org/10.24054/rcta.v2i42.2597

Keywords:

Deep neural network, sensitivity analysis, multilayer elastic theory, flexible pavements

Abstract

This study aims to implement deep neural networks (DNNs) to assess the sensitivity level of design parameters in flexible pavements for roads with low traffic volume. One hundred eight structures were modeled using the Pitra Pave® software (i.e., multilayer elastic theory (MET) model for pavement structural analysis) to generate a database to develop the DNN models. The DNN models, through connection weights, allowed the comparison with MET to evaluate the sensitivity of the selected design variables (resilient modulus and layer thickness) on the structural design parameters. The results suggest the significant impact of layer thicknesses. In addition, the predictions of structural design parameters from these initial DNN models showed variations ranging from 0,03% to 10,87% compared to MET. Expanding the database and developing a multi-predictive network is recommended for future research.

Downloads

Download data is not yet available.

References

Instituto Nacional de Vías (2008). Manual de diseño geométrico de carreteras.

Alejandra, M., Ariza, A., Alejandro, P., & Romero, A. (2017). Las vías terciarias en Colombia, una oportunidad para la ingeniería vial y el desarrollo del país. Universidad Católica.

Caro, S., & Caicedo, B. (2017). TECNOLOGÍAS PARA VÍAS TERCIARIAS: PERSPECTIVAS Y EXPERIENCIAS DESDE LA ACADEMIA. Revista de Ingeniería, 45. https://doi.org/10.16924/revinge.45.3

Coria Gutiérrez, C. A., Hernández Domínguez, R. I., & Garnica Anguas, P. (2018). Teorías para calcular esfuerzos, deformaciones y deflexiones en pavimentos flexibles: un enfoque mecanicista. In IMT Instituto Mexicano del Transporte (Issue 72).

Corté, J. F., & Goux, M. T. (1996). Design of pavement structures: The French technical guide. Transportation Research Record, 1539. https://doi.org/10.3141/1539-16

Ghanizadeh, A. R., & Ahadi, M. R. (2015). Application of artificial neural networks for analysis of flexible pavements under static loading of standard axle. International Journal of Transportation Engineering, 3(1).

Ghanizadeh, A. R., Heidarabadizadeh, N., & Jalali, F. (2020). Artificial neural network back-calculation of flexible pavements with sensitivity analysis using Garson's and connection weights algorithms. Innovative Infrastructure Solutions, 5(2). https://doi.org/10.1007/s41062-020-00312-z

Gopalakrishnan, K. (2018). Deep learning in data-driven pavement image analysis and automated distress detection: A review. In Data (Vol. 3, Issue 3).

Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. ArXiv Preprint ArXiv:1412.6980.

Loría-Salazar, L. G., Aguiar-Moya, J. P., Trejos-Castillo, C., & Rojas-Pérez, F. (2017). Solución a la teoría de multicapa elástica y software de cálculo de las respuestas del pavimento PITRA PAVE.

Massenlli, G. S. R., & Paiva, C. E. L. de. (2019). Influencia de la deflexión superficial en pavimentos flexibles con subrasante de baja resistencia. Ingeniare. Revista Chilena de Ingeniería, 27(4).

Pereira, P., & Pais, J. (2017). Main flexible pavement and mix design methods in Europe and challenges for the development of an European method. In Journal of Traffic and Transportation Engineering (English Edition) (Vol. 4, Issue 4). https://doi.org/10.1016/j.jtte.2017.06.001

Plati, C., Georgiou, P., & Papavasiliou, V. (2016). Simulating pavement structural condition using artificial neural networks. Structure and Infrastructure Engineering, 12(9). https://doi.org/10.1080/15732479.2015.1086384

Rondón Quintana, H. A., & Reyes Lizcano, F. A. (2007). Metodologías de diseño de pavimentos flexibles: Tendencias, alcances y limitaciones. Ciencia e Ingeniería Neogranadina, 17(2). https://doi.org/10.18359/rcin.1074

Sandoval, Higuera;Hernando, C. (2006). Análisis de sensibilidad de las variables de diseño de un pavimento rígido y su incidencia en la deflexión. Facultad de Ingeniería, 15(20).

Yang, X., Guan, J., Ding, L., You, Z., Lee, V. C. S., Mohd Hasan, M. R., & Cheng, X. (2021). Research and applications of artificial neural network in pavement engineering: A state-of-the-art review. In Journal of Traffic and Transportation Engineering (English Edition) (Vol. 8, Issue 6).