Publicado:
2022-12-05Edição:
v. 19 n. 2 (2022)Seção:
Entorno SocialKrumbein Roundness Index using Kohonen Self-Organizing Maps
Índice de Redondez de Krumbein mediante Mapas Autoorganizativos de Kohonen
Palavras-chave:
Image analysis, Flexible Pavement, SOM, Krumbein (en).Palavras-chave:
Análisis de imágenes, Pavimentos flexibles, SOM, Krumbein (es).Downloads
Resumo (es)
Dentro de las áreas de conocimiento que abarca la ingeniería, la aplicación de inteligencia artificial y procesamiento digital de imágenes ha permitido automatizar procesos que tradicionalmente se realizaban de forma manual. En el área de pavimentos, diferentes herramientas digitales se han implementado para la parametrización del tipo de fragmentos de roca que se utiliza para la construcción de vías y carreteras, ayudando en el mejoramiento del proceso de diseño de estas estructuras, las cuales, bajo el contexto actual son fundamentales para el trasporte de mercancías esenciales y para la recuperación económica de una región. De esta forma en este trabajo se implementa un algoritmo mediante el análisis de imágenes y redes neuronales para la determinación del índice de redondez de Krumbein del agregado en pavimentos flexibles. Lo anterior con el objetivo de generar una herramienta que permita automatizar un proceso que convencionalmente implica el desplazamiento y tiempo de trabajo de un ingeniero para el desarrollo del diseño de la mezcla.
Resumo (en)
Within the areas of knowledge that engineering encompasses, the application of artificial intelligence and digital image processing has made it possible to automate processes that were traditionally carried out manually. In the area of pavements, different digital tools have been implemented for the parameterization of the type of rock fragments used for the construction of roads and highways. These tools improve the design process of pavement structures, which, under the current context, pavements are essential for the transport of essential goods and the economic recovery of a region. In this work, an algorithm is implemented through the analysis of images and neural networks to determine the Krumbein roundness index of the aggregate in flexible pavements. To generate a tool that allows automating a process that conventionally involves the displacement and work time of an engineer for the development of the mixture design.
Referências
C. Katrakazas, E. Michelaraki, M. Sekadakis, and G. Yannis, “ A descriptive analysis of the effect of the COVID-19 pandemic on driving behavior and road safety,” Transp. Res. Interdiscip. Perspect., vol. 7, 2020, https://doi.org/10.1016/j.trip.2020.100186
P. Pereira and J. Pais, “Main flexible pavement and mix design methods in Europe and challenges for the development of an European method,” J. Traffic Transp. Eng. (English Ed., vol. 4, no. 4, pp. 316–346, 2017, https://doi.org/10.1016/j.jtte.2017.06.001
A. P. Singh, A. Sharma, R. Mishra, M. Wagle, and A. K. Sarkar, “Pavement condition assessment using soft computing techniques,” Int. J. Pavement Res. Technol., 2018.
Z. Zhang, Q. Liu, Q. Wu, H. Xu, P. Liu, and M. Oeser, “Damage evolution of asphalt mixture under freeze-thaw cyclic loading from a mechanical perspective,” Int. J. Fatigue, vol. 142, no. June 2020, pp. 1–9, 2021, doi: 10.1016/j.ijfatigue.2020.105923
K. B. Bai Kamara, E. Ganjian, and M. Khorami, “The effect of quarry waste dust and reclaimed asphalt filler in hydraulically bound mixtures containing plasterboard gypsum and GGBS,” J. Clean. Prod., vol. 279, 2021. doi: 10.1016/j.jclepro.2020.123584
D. M. Kusumawardani and Y. D. Wong, “The influence of aggregate shape properties on aggregate packing in porous asphalt mixture (PAM),” Constr. Build. Mater., vol. 255, 2020.
doi: 10.1016/j.conbuildmat.2020.119379
T. M. Al Rousan, “Characterization of aggregate shape properties using a computer automated system,” Texas A&M University, 2004.
C. García-González, J. Yepes, and M. A. Franesqui, “Geomechanical characterization of volcanic aggregates for paving construction applications and correlation with the rock properties,” Transp. Geotech., vol. 24, January, 2020. doi: 10.1016/j.trgeo.2020.100383
J. Hu and P. Stroeven, “Shape characterization of concrete aggregate,” Image Anal. Stereol, vol. 25, no. 1, pp. 43–53, 2006. doi: 10.5566/ias.v25.p43-53
T. Roussillon, H. Piégay, I. Sivignon, L. Tougne, and F. Lavigne, “Automatic computation of pebble roundness using digital imagery and discrete geometry,” Comput. Geosci., vol. 35, no. 10, pp. 1992–2000, 2009. doi: 10.1016/j.cageo.2009.01.013
J. Zhang, X. Yang, W. Li, S. Zhang, and Y. Jia, “Automatic detection of moisture damages in asphalt pavements from GPR data with deep CNN and IRS method,” Autom. Constr., vol. 113, no. September 2019, 2020. doi: 10.1016/j.autcon.2020.103119
L. Pei et al., “Pavement aggregate shape classification based on extreme gradient boosting,” Constr. Build. Mater., vol. 256, 2020.
K. A. Ghuzlan, M. T. Obaidat, and M. M. Alawneh, “Cellular-phone-based computer vision system to extract shape properties of coarse aggregate for asphalt mixtures,” Eng. Sci. Technol. an Int. J., vol. 22, no. 3, pp. 767–776, 2019. doi: 10.1016/j.jestch.2019.02.003
J. Kim, B. S. Park, S. I. Woo, and Y. T. Choi, “Evaluation of ballasted-track condition based on aggregate-shape characterization,” Constr. Build. Mater., vol. 232, 2020. doi: 10.1016/j.conbuildmat.2019.117082
O. J. Reyes-ortiz, M. Mejía, and J. S. Useche-Castelblanco, “Aggregate segmentation of asphaltic mixes using digital image,” Bull. Polish Acad. Sci. Tech. Sci., vol. 67, no. 2, pp. 279–287, 2019.
S. M. E. Harb, N. Ashidi, M. Isa, and S. A. Salamah, “Improved image magnification algorithm based on Otsu,” Comput. Electr. Eng. J., vol. 46, pp. 338–355, 2015.
J. V. C. I. R, C. Sha, J. Hou, and H. Cui, “A robust 2D Otsu ’ s thresholding method in image segmentation q,” J. Vis. Commun. Image R. J., vol. 41, pp. 339–351, 2016.
O. J. Reyes-Ortiz, M. Mejia, and J. S. Useche-Castelblanco, “Digital image analysis applied in asphalt mixtures for sieve size curve reconstruction and aggregate distribution homogeneity,” Int. J. Pavement Res. Technol., 2020. doi: 10.1007/s42947-020-0315-6
S. Yu, S. Jia, and C. Xu, “Convolutional neural networks for hyperspectral image classification,” Neurocomputing, vol. 219, pp. 88–98, 2017.
V. C. Janoo, “Quantification of shape, angularity, and surface texture of base course materials,” 1998.
E. Masad, T. M. Al Rousan, J. Button, and D. Little, Test Methods for Characterizing Aggregate Shape, Texture, and Angularity. United States of America, 2007.
E. dos S. Silva et al., “Evaluation of macro and micronutrient elements content from soft drinks using principal component analysis and Kohonen self-organizing maps,” Food Chem., vol. 273, May 2018, pp. 9–14, 2019. doi: 10.1016/j.foodchem.2018.06.021
B. Yang, S. Yang, J. Zhang, and D. Li, “Optimizing random searches on three-dimensional lattices,” Phys. A Stat. Mech. its Appl., vol. 501, pp. 120–125, Jul. 2018. doi: 10.1016/J.PHYSA.2018.02.100
Como Citar
IEEE
ACM
ACS
APA
ABNT
Chicago
Harvard
MLA
Turabian
Vancouver
Baixar Citação
Visitas
Downloads
Licença
Copyright (c) 2025 Revista Vínculos
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial 4.0 International License.
4.png)
Este obra está sob uma licença Creative Commons Atribuição 4.0
