Study of retroanalysis of asphaltic pavements resilience modules with the use of artificial neural networks

Authors

  • Alcidney Batista Celeste Superintendência Regional da Paraíba - UL de Patos
  • Francisco Heber Lacerda de Oliveira Universidade Federal do Ceará

DOI:

https://doi.org/10.14295/transportes.v27i4.1781

Keywords:

Asphalt pavements, Resilience module, Retroanalysis, Artificial neural networks.

Abstract

Knowledge of pavement Resilience Modules (RM) is an important element for the structural assessment of existing infrastructures. One way to determine them is through dynamic repeated load testing in the laboratory; another way is to use the technique of retroanalysis, which consists in obtaining the RM from the thickness of the layers and the deflections measured on the pavement surface. In this sense, this paper aims to present the RM retroanalysis through the technique of Artificial Neural Networks (ANN) as an alternative to the traditional retroanalysis. The results demonstrate that the ANN could predict the RM with results of coefficients of determination (R²) above 99.9% between the reference and predicted values. Thus, ANN are a potential alternative to obtain this important mechanical property of paving materials compared to traditional methods.

Downloads

Download data is not yet available.

Author Biographies

Alcidney Batista Celeste, Superintendência Regional da Paraíba - UL de Patos

Mestre em Engenharia Civil

Analista em Infraestrutura de Transportes


Francisco Heber Lacerda de Oliveira, Universidade Federal do Ceará

Doutor em Engenharia de Transportes pelo Programa de Pós-Graduação em Engenharia de Transportes, da Universidade Federal do Ceará. Professor Adjunto do Departamento de Engenharia de Transportes, da Universidade Federal do Ceará. Affiliate Member in the American Society of Civil Engineers - ASCE. Tem experiência em Planejamento do Transporte Aéreo, Operação, Manutenção e Reabilitação de Infraestruturas Aeroportuárias, especialmente em pavimentos de pátios e de pistas de pouso e decolagem.

References

Albernaz, C. A. V. (1997) Simplified Method of Retrofitting Flexible Pavement Resilience Modules from the Deflection Basin. Mas-ter's Thesis, Coppe – The Alberto Luiz Coimbra Institute for Graduate Studies and Research in Engineering, Federal Uni-versity of Rio de Janeiro, Rio de Janeiro.

Albernaz, C. A. V.; L. M. G. Motta and J. Medina (1995) Retroanalysis: A Useful Tool in Structural Pavement Evalua-tion. Proceedings of the 29th Annual Paving Meeting. Cuiabá, v. 1, p. 399 - 417.

Bernucci, L. B.; L. M. G. Motta; J. A. P. Ceratti and J. B. Soares (2006) Asphalt Paving: basic training for engineers. 1st ed. Petro-bras: Abeda, Rio de Janeiro.

Coutinho Neto, B. (2000) Artificial neural networks as a procedure for flexible pavement retroanalysis. Master's Thesis. São Carlos School of Engineering. University of Sao Paulo, Sao Carlos. Available in: https://www.teses.usp.br/teses/disponiveis/18/18137/tde-01022018-122501/pt-br.php (access in 23/12/2019).

Franco, F. A. C. P. (2007) Method of Mechanical-Empirical Dimensioning of Asphalt Pavements - SisPav. Doctoral Thesis. Coppe – The Alberto Luiz Coimbra Institute for Graduate Studies and Research in Engineering, Federal University of Rio de Janei-ro, Rio de Janeiro. Available in: http://www.coc.ufrj.br/pt/teses-de-doutorado/151-2007/1107-filipe-augusto-cinque-de-proenca-franco (access in 23/12/2019).

Godoy, W. F.; I. N. Silva; W. S. Gongora; A. Goedtel and R. H. C. Palaces (2013) Failure Classification in Three-Phase Induction Motor Bearings using Artificial Neural Networks. Proceedings of the XI Brazilian Symposium on Intelligent Automation, For-taleza. Available in: http://www.sbai2013.ufc.br/pdfs/4788.pdf (access in 23/12/2019).

Hagan, M.T. and M. B. Menhaj (1994) Training Feedforward Networks with the Marquardt Algorithm. IEEE Transactions on Neural Networks, v. 5, n. 6, p. 989 - 993. DOI: 10.1109/72.329697.

Haykin, S. (2001). Neural Networks: Principles and Practices. 2nd edition. Bookman, Porto Alegre.

Macedo, F. N. (2003) Retroanalysis of real and theoretical deflection basins obtained by static and dynamic methods. Master's Thesis. University of Brasília, Brasília, DF.

Nóbrega, E. S. (2003) Comparison Between Asphalt Pavement Retroanalysis Method. Master's Thesis. Coppe – The Alberto Luiz Coimbra Institute for Graduate Studies and Research in Engineering, Federal University of Rio de Janeiro, Rio de Janeiro. Available in:

http://www.coc.ufrj.br/pt/dissertacoes-de-mestrado/103-msc-pt-2003/1835-eduardo-suassuna-nobrega (access in 23/12/2019).

Ribeiro, A. J. A. (2016) A prediction model of resilient modulus of soils in the state of Ceará for the purpose of paving. Doctoral Dissertation, Federal University of Ceará, Fortaleza. Available in: http://www.repositorio.ufc.br/handle/riufc/18958 (access in 23/12/2019).

Rocha Filho, N. R. and R. M. Rodrigues (1996) Structural Evaluation of Pavements through Deflectometric Surveys. Proceedings of the

th Annual Paving Meeting. Salvador, v. 3, p. 1119 - 1146.

Rosenblatt, F. (1958). The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain. Physiological Reviews, v. 65 (3), p. 386-408. DOI: 10.1037/h0042519.

Silva, I. N.; D. H. Spatti and R. A. Flauzino (2010) Artificial neural networks for engineering and applied sciences, Artliber, 1st edition, São Paulo, SP.

Zanetti, F. S. (2008) The Use of Artificial Neural Networks as a Tool to Assist in Determining the Life of Flexible Pavements. Master's Thesis. São Carlos School of Engineering. University of São Paulo, São Carlos, SP. Available in: https://teses.usp.br/teses/disponiveis/18/18143/tde-28042009-091916/en.php (access in 23/12/2019).

Downloads

Published

2019-12-28

How to Cite

Celeste, A. B., & Oliveira, F. H. L. de. (2019). Study of retroanalysis of asphaltic pavements resilience modules with the use of artificial neural networks. Transportes, 27(4), 123–133. https://doi.org/10.14295/transportes.v27i4.1781

Issue

Vol. 27 No. 4 (2019)

Section

Articles

License

Authors who submit papers for publication by TRANSPORTES agree to the following terms:

  1. The authors retain the copyright and grant Transportes the right of first publication of the manuscript, without any financial charge, and waive any other remuneration for its publication by ANPET.
  2. Upon publication by Transportes, the manuscript is automatically licensed under the Creative Commons License CC BY 4.0 license. This license permits the work to be shared with proper attribution to the authors and its original publication in this journal.
  3. Authors are authorized to enter into additional separate contracts for the non-exclusive distribution of the version of the manuscript published in this journal (e.g., publishing in an institutional repository or as a book chapter), with recognition of the initial publication in this journal, provided that such a contract does not imply an endorsement of the content of the manuscript or the new medium by ANPET.
  4. Authors are permitted and encouraged to publish and distribute their work online (e.g., in institutional repositories or on their personal websites) after the editorial process is complete. As Transportes provides open access to all published issues, authors are encouraged to use links to the DOI of their article in these cases.
  5. Authors guarantee that they have obtained the necessary authorization from their employers for the transfer of rights under this agreement, if these employers hold any copyright over the manuscript. Additionally, authors assume all responsibility for any copyright infringements by these employers, releasing ANPET and Transportes from any responsibility in this regard.
  6. Authors assume full responsibility for the content of the manuscript, including the necessary and appropriate authorizations for the disclosure of collected data and obtained results, releasing ANPET and Transportes from any responsibility in this regard.