Metodologia de baixo custo para mapeamento geotécnico aplicado à pavimentação

Authors

  • Antonio Júnior Alves Ribeiro IFCE
  • Carlos Augusto Uchôa da Silva UFC/PETRAN
  • Suelly Helena de Araújo Barroso UFC/PETRAN

DOI:

https://doi.org/10.14295/transportes.v26i2.1491

Keywords:

Geotechnics, Neural Modeling, Geoprocessing.

Abstract

This paper presents a low-cost methodology for forecasting and mapping of CBR values (California Bearing Ratio) of soils in the energies normal compression (CBR-N) and intermediate (CBR-I), which contribute to the decision-making process as to their use for paving purposes. GIS, Artificial Neural Networks (ANN) and modeling techniques as well as biophysical and spatial variables were used as explanatory of the modeled phenomenon. The researched characteristics (pedology, geology, geomorphology, vegetation, hypsometry and position) correlated with CBR values of soils in both energy compaction. CBR data were extracted from pre-existing projects and studies in the study area, in this case, the metropolitan area of Fortaleza (MAF). Thus, they were calibrated, validated and tested in many different ANN to find the two models best fit, for the generation of CBR-N estimates and CBR-I, of the soil MAF from the studied biophysical variables. The geotechnical characteristics estimated by these models enabled the development of two Neural Geotechnical Maps stratified to predict the values, CBR-N and CBR-I. The results show that ANN technique is promising to predict the mechanical properties of soils and can assist in making decisions regarding the use of these in road projects.

Downloads

Download data is not yet available.

References

Almeida, Márcio. S. S.; M. E. S. Marques; T. C. Miranda (2008) Lowland Reclamation in Urban Areas. In: Geotechnical Infra-structure for Mega Cities and New Capitals, XIV COBRAMSEG , Búzios.

Anderson, D.A. e R. Dongre (1995) The SHRP Direct Tension Specification Test – Its Development and Use. Physical Properties of Asphalt Cement Binders. In: J.C. Hardin, Ed. ASTM Special Technical Publication 1241. American Society for Testing and Materials, Philadelphia, PA, p. 51-66.

Beale, M. H.; M. T. Hagan e H. B. Demuth (2010). Neural Network Toolbox™ 7 - User’s Guide.

Bockheim, J. G.; A. N. Gennadiyev; R. D. Hammer e J. P. Tandarich (2005). The Historical development of key concepts in Pedol-ogy. Geoderma, v. 124, n. 1-2, p. 23–36. DOI:10.1016/j.geoderma.2004.03.004

Bui, D.; H. Tien; C. Tien; I. Revhaug; B. Pradhan e D. B. Nguyen (2014) Landslide susceptibility mapping along the national road 32 of Vietnam using GIS-based j48 decision tree classifier and its ensembles. Cartography from pole to pole, pag. 303-317. Editora Springer Berlin Heidelberg. DOI:10.1007/978-3-642-32618-9_22

Câmara, G.; C. B. Medeiros; M. A. Casa Nova; A. Hemerly e G. Magalhães (2004) Anatomia de sistemas de informação geográfica. Escola de Computação, SBC.

Câmara, A. S. (1996). Spatial Simulation Modelling. Spatial Analytical Perspectives on GIS. M. Fisher. London, Taylor & Francis: 213-218.

Caten, A. ten; R. S. D. Dalmolin; F. de A. Pedron e M. de L. Mendonça‑Santos (2011b) Regressões logísticas múltiplas: fatores que influenciam sua aplicação na predição de classes de solos. Revista Brasileira de Ciência do Solo, v.35, p.53‑62. DOI:10.1590/S0100-06832011000100005

Debella-Gilo, M. e B. Etzelmüller (2009) Spatial prediction of soil classes using digital terrain analysis and multinomial logistic regression modeling integrated in GIS: Examples from Vestfold County, Norway, Catena, v. 77, p. 8-18, 2009. DOI:10.1016/j.catena.2008.12.001

DNIT (2006) Manual De Pavimentação, 2006.

Franco, F.A.C.P. (2007) Método de Dimensionamento Mecanístico-Empírico de Pavimentos Asfálticos – SISPAV. 294p. Tese (Doutorado em Engenharia Civil) - Universidade Federal do Rio de Janeiro, Rio de Janeiro.

Fritzen, M. A. (2016) Desenvolvimento e Validação de Função de Transferência para Previsão do Dano por Fadiga em Pavimentos Asfálticos – Rio de Janeiro: UFRJ/COPPE.

Guilherme, A. T. P.; A. J. A. Ribeiro; W. S. Cabral; C. A. U. Silva; S. H. A. Barroso e I. W. Castro (2016) Um Método para Construção de um Banco de Dados com fins de Modelagem Geotécnica para Pavimentação dos Solos da Microrregião de Mossoró-RN. In: XXX Congresso Nacional de Pesquisa em Transporte da ANPET. Rio de Janeiro. Anais, p. 85-96.

Gunaydin O.; A. Gokoglu e M. Fener (2010). Prediction of artificial soil’s unconfined compression strength test using statisti-cal analyses and artificial neural networks. Advances in Engineering Software, v. 41, p. 1115-1123, 2010. DOI:10.1016/j.advengsoft.2010.06.008

Hartemink, A. E. e A. B. McBratney (2008). A soil science renaissance. Geoderma, v. 148, p. 123-129. DOI:10.1016/j.geoderma.2008.10.006

Haykin (2001) Neural Networks, A Comprehensive Foundation. Second Edition, Pearson Education, McMaster University, Ham-ilton, Ontario, Canada.

Johari A.; A. A. Javadi e G. Habibagahi (2011) Modelling the mechanical behaviour of unsaturated soils using a genetic algo-rithm-based neural network. Computers and Geotechnics, v 38, p. 2-13, 2011. DOI: 10.1016/j.compgeo.2010.08.011

Juang, C. H.; P. C. Lu e C. J. Chen (2002), Predicting Geotechnical Parameters of Sands from CPT Measurements Using Neural Networks. Computer-Aided Civil and Infrastructure Engineering, v. 17, p. 31–42. DOI: 10.1111/1467-8667.00250

Kempen B.; D. J. Brus; G. B. M. Heuvelink e J. J. Stoorvogel (2009) Updating the 1:50,000 Dutch soil map using legacy soil data: A multinomial logistic regression approach. Geoderma, Amsterdam, v 151, p. 311-326, 2009. DOI: 10.1016/j.geoderma.2009.04.023

Lagacherie, P. e A. B. McBratney (2007) Spatial soil information systems and spatial soil inference systems: Perspectives for digi-tal soil mapping. Digital soil mapping: An introductory perspective. Amsterdam, Elsevier, p.3-22.

McBratney, A. B.; S. M. L. Mendonca e B. Minasny (2003) On digital soil mapping. Geoderma, Amsterdam, v. 117, n. 1-2, p. 3-52, 2003. DOI: 10.1016/S0016-7061(03)00223-4

McCulloch, W. S. e W. H. Pitts (1943) ‘A Logical Calculus of the Ideas Immanent in Nervous Activity’, Bulletin of Mathematical Biophysics 7, 115–133. Reprinted in McCulloch 1964, pp. 16–39.

Oh, T. C. e B. Pradhan (2011) Application of a neuro-fuzzy model to landslide-susceptibility mapping for shallow landslides in a tropical hilly area. Computers & Geosciences, v. 37, n.9, pag. 1264 - 1276, 2011. DOI: 10.1016/j.cageo.2010.10.012

Ribeiro, A. J. A.; C. A. U. da Silva e S. H. A Barroso (2015). Neural Estimation of Localization and Classification of Soils for Use in Low-Traffic-Volume Roads. Transportation Research Record, v. 2473, p. 98-106, 2015. DOI: 10.3141/2473-12

Ribeiro, A. J. A.; C. A. U. da Silva e S. H. A. Barroso (2016) Metodologia Para Criação De Um Banco De Dados Georeferenciado a Partir de Dados Geotécnicos Obtidos Em -As Built- e Projetos Rodoviários. REEC - Revista Eletrônica de Engenharia Civil, v. 12, p. 1-13, 2016. DOI: 10.5216/reec.v12i2.39413

Ribeiro, A. J. A.; M.E. R. Rosa e G. A. Reis (2016) Comparação entre Diferentes Bases Altimétricas para Delimitação de Bacias e Extração de Drenagens. Revista Eletrônica de Gestão e Tecnologias Ambientais, v. 4, p. 193, 2016. DOI: 10.9771/gesta.v4i2.14992

Rosenblatt, F. (1958) The perceptron: A probabilistic model for information storage and organization in the brain. Psycholog-ical Review. v. 6, p. 386–408.

Scull, P.; J. Franklin; O. A. Chadwick e D. McArthur (2003), Predictive soil mapping a review. Progress in Physical Geography, v. 27, p. 171-197, 2003.

Souza, M. L. (1979) Método de projeto de pavimentos flexíveis. 2. ed. Rio de Janeiro: DNER, 1979.

Taskiran, T. (2010) Prediction of California bearing ratio (CBR) of fine grained soils by AI methods. Advances in Engineering Software n. 41, p. 886–892. DOI: 10.1016/j.advengsoft.2010.01.003

Yildirim, B. e O. Gunaydin (2011) Estimation of California bearing ratio by using soft computing systems. Expert Systems with Applications v. 38, p. 6381–6391. DOI: 10.1016/j.eswa.2010.12.054

Zeghal, M. e W. Khogali (2005) Predicting the resilient modulus of unbound granular materials by neural networks. National Research Council Canada (NRCC-47704). BCRA 2005, Trondheim, Norway, June 27-29, 2005, pp. 1-9.

Published

2018-08-31

How to Cite

Ribeiro, A. J. A., da Silva, C. A. U., & Barroso, S. H. de A. (2018). Metodologia de baixo custo para mapeamento geotécnico aplicado à pavimentação. TRANSPORTES, 26(2), 84–100. https://doi.org/10.14295/transportes.v26i2.1491

Issue

Section

Artigos