Chuanyun Xu1, Heng Wang1, Yang Zhang1This email address is being protected from spambots. You need JavaScript enabled to view it., Song Sun1, and Gang Li2
1Chongqing Normal University, No.37, University City Middle Road, Shapingba District, Chongqing City
2Chongqing University of Technology, No. 69, Hongguang Avenue, Banan District, Chongqing City
Received: December 1, 2024 Accepted: March 27, 2025 Publication Date: May 9, 2025
Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.
Sand gradation is a key factor in concrete mix design, directly affecting its strength and workability. Although traditional vibration sieving methods are highly reliable, they are inefficient. Existing machine learning-based automated detection methods have limited accuracy, and deep learning is hindered by difficulties in image data annotation and the lack of high-quality datasets, which affect its application effectiveness. To address this, this paper proposes a detection method based on the two-dimensional sand particle features in sand images. By extracting these sand particle features to train a network model and combining a threshold division strategy, sand gradation detection is performed. Images of sand particles with a single gradation are captured to extract five sand particle feature parameters, which are then used to train a mature network model. The equivalent volume of the sand particles is calculated by multiplying the equivalent projected area by the equivalent elliptical Feret short diameter, and the Feret short diameter is optimized using an optimization algorithm to enhance the volume calculation. Experimental results show that the sand gradation calculated by this method has an average cumulative error of 8.82% compared to manual sieving results. This method significantly improves detection efficiency, reduces labor input, and holds promising application prospects in the construction industry.
[1] K. K. Poloju, V. Anil, and R. K. Manchiryal, (2017) “Properties of concrete as influenced by shape and texture of fine aggregate" American Journal of Applied scientific research 3(3): 28–36.
[2] K. P. Kumar, P. Ramesh, P. Aravinda, et al., (2022) “Effect of fines on strength and durability of concrete with manufactured sand" Materials Today: Proceedings 66: 2381–2386.
[3] A. Kumar and O. Yadav, (2023) “Concrete Durability Characteristics as a Result of Manufactured Sand" Central Asian Journal of Theoretical and Applied Sciences 4(03):
[4] M. Fang, D. Park, J. L. Singuranayo, H. Chen, and Y. Li, (2019) “Aggregate gradation theory, design and its impact on asphalt pavement performance: a review" Inter national Journal of Pavement Engineering 20(12): 1408–1424.
[5] H. Ying, J. Zhou, Q. Wu, and Y. Liu, (2016) “Variation of the contact form of coarse aggregate particles in skeleton type asphalt mixture" Journal of Building Materials 19(2): 292–298.
[6] M. Budhu. Soil mechanics and foundations. John Wiley and Sons, 2010.
[7] S. Huseynova, (2018) “Determination of particle size distributions of industrial side streams by using laser diffraction and sieving methods":
[8] J. Ke, Z. Shui, X. Gao, X. Qi, Z. Zheng, and S. Zhang, (2023) “Effect of Vibration Procedure on Particle Distribution of Cement Paste" Materials 16(7): 2600.
[9] P. W. Cleary, P. Wilson, and M. D. Sinnott, (2018) “Effect of particle cohesion on flow and separation in industrial vibrating screens" Minerals Engineering 119: 191–204.
[10] G. J. J. Kumara, K. Hayano, and K. Ogiwara, (2012) “Image analysis techniques on evaluation of particle size distribution of gravel" GEOMATE Journal 3(5): 290–297.
[11] J. J. Kumara, K. Hayano, and Y. Kikuchi, (2017) “Evaluation of area-and volume-based gradations of sand crushed stone mixture by 2D images" Ksce Journal of Civil Engineering 21: 774–781.
[12] F.-l. Liu, H.-y. Fang, S.-j. Chen, L. Zhou, and J.-h. Yang, (2019) “Experimental study on manufactured sand shape detection by image method" Journal of Testing and Evaluation 47(5): 3515–3532.
[13] J. Zhou, H. Fang, J. Yang, S. Chen, and M. Luo, (2018) “Study on characterization parameters of aggregate particle size using image analysis" Acta Metrol. Sin 39: 783–790.
[14] D. Su and W. Yan, (2018) “3D characterization of general-shape sand particles using microfocus X-ray computed tomography and spherical harmonic functions, and particle regeneration using multivariate random vector" Powder Technology 323: 8–23.
[15] W. Zheng, X. Hu, D. D. Tannant, K. Zhang, and C. Xu, (2019) “Characterization of two-and three-dimensional morphological properties of fragmented sand grains" Engineering Geology 263: 105358.
[16] W.-Q. Xie, X.-P. Zhang, X.-M. Yang, Q.-S. Liu, S.-H. Tang, and X.-B. Tu, (2020) “3D size and shape characterization of natural sand particles using 2D image analysis" Engineering Geology 279: 105915.
[17] D. Han, J. Zhu, L. Li, and H. Pang, (2016) “Verification and application of two-dimensional slice identification method in three-dimensional me so structure under different aggregate gradations and packing algorithms" Construction and Building Materials 102: 843–851.
[18] L. Bruno, G. Parla, and C. Celauro, (2012) “Image analysis for detecting aggregate gradation in asphalt mixture from planar images" Construction and Building Materials 28(1): 21–30.
[19] S.-l. Zhang, G.-j. Wu, X.-g. Yang, W.-h. Jiang, and J.-w. Zhou, (2018) “Digital image-based identification method for the determination of the particle size distribution of dam granular material" KSCE Journal of Civil Engineering 22: 2820–2833.
[20] W. Fan, Z. Chen, Z. Luo, and B. Guo, (2021) “An aggregate gradation detection method based on multi-view information fusion" Powder Technology 388: 7–16.
[21] S. Shao, K. Mallery, and J. Hong, (2019) “Machine learning holography for measuring 3D particle size distribution" arXiv preprint arXiv:1912.13036:
[22] L. Li and M. Iskander, (2022) “Use of machine learning for classification of sand particles" Acta Geotechnica 17(10): 4739–4759.
[23] J. Qin, J. Wang, T. Lei, G. Sun, J. Yue, W. Wang, J. Chen, and G. Qian, (2023) “Deep learning-based software and hardware framework for a noncontact inspection platform for aggregate grading" Measurement 211: 112634.
[24] D. M.Gay. “The AMPL modeling language: An aid to formulating and solving optimization problems”. In: Numerical Analysis and Optimization: NAO-III, Mus cat, Oman, January 2014. Springer. 2015, 95–116.
[25] Y. Zhang, D. Hou, C. Xu, H. Wang, L. Peng, X. Yuan, X. Zhang, G. Li, and S. Sun, (2024) “Sand gradation detection method based on local sampling" Scientific Reports 14(1): 29464.
[26] A. Nemirko and J. Dulá, (2021) “Machine learning algorithm based on convex hull analysis" Procedia Computer Science 186: 381–386.
[27] P. Soille. Morphological Image Analysis: Principles and Applications. 1999.
[28] S. A. of the People’s Republic of China. Construction Sand (GB/T 14684-2022). English. English Translation of GB/T14684-2022. 2022.
We use cookies on this website to personalize content to improve your user experience and analyze our traffic. By using this site you agree to its use of cookies.
