EXTRACTION OF INDIVIDUAL ROCK DISCONTINUITIES BASED ON THREE-LAYER CLUSTERING ALGORITHM FROM 3D POINT CLOUDS

АУТОР(И) / AUTHOR(S): Bingyi Pan, Wei Wu, Yong Huang, Baolin Chen, Hehua Zhu

Download Full Pdf   

DOI:  10.46793/ACUUS2025.2.8.105

САЖЕТАК / ABSTRACT:

Accurate characterization of rock discontinuities is essential for tunnel stability analysis, as discontinuities play a fundamental role in governing the mechanical behavior and failure mechanisms of the surrounding rock mass. The advancement of remote surveying methods has enabled the rapid identification of discontinuities and extraction of pertinent geometric information from 3D point clouds of the rock mass. Nevertheless, traditional methods that rely on point features are insufficient in their ability to eliminate fragmented non-structural regions during the process of individual discontinuity extraction. This paper presents a novel three-layer clustering approach that aims to extract individual discontinuities from 3D point clouds automatically. To begin with, the rock mass point cloud is filtered to extract core points and remove non-structural regions. Subsequently, an improved density-based spatial clustering of applications with noise (IDBSCAN) is employed to identify planar units within core points. To merge adjacent fragmented planar units, these units are re-clustered based on their spatial relationships, resulting in the identification of individual discontinuities. A weighted modified k-means++ method is then used to cluster individual discontinuities according to their respective normal vectors. Consequently, the orientation, set, and trace of each individual discontinuity can be obtained respectively through geometric analysis. This method is applied to one tunnel case and compared with previous studies. The results suggest that the proposed method has a high level of reliability and accuracy when it comes to automatically extracting individual discontinuities from 3D point clouds, providing a more robust foundation for tunnel design and construction.

КЉУЧНЕ РЕЧИ / KEYWORDS:

Individual discontinuities, Rock mass, 3D point clouds, Automatic extraction

ПРОЈЕКАТ / ACKNOWLEDGEMENT:

This work was supported by the National Natural Science Foundation of China [42272338, 41827807, 41902275]; Shanghai Sailing Program [18YF1424400]; Joint Fund for Basic Research of High-speed Railway of National Natural Science Foundation of China, China Railway Corporation [U1934212]; China State Railway Group Co., Ltd. [P2019G038]; Department of Transportation of Zhejiang Province [202213]; China Railway First Survey and Design Institute Group Co., Ltd. [19-21-1, 2022KY53ZD(CYH)-10]; China Railway Tunnel Group Co., Ltd. [CZ02-02-08]; PowChina Hebei Transportation Highway Investment Development Co., Ltd. [TH-201908]; Sichuan Railway Investment Group Co., Ltd. [SRIG2019GG0004]; The Science and Technology major program of Guizhou Province [2018]3011.

ЛИТЕРАТУРА / REFERENCES:

• Assali, P., Grussenmeyer, P., Villemin, T., Pollet, N., & Viguier, F. (2016). Solid images for geostructural mapping and key block modeling of rock discontinuities. Computers & Geosciences, 89, 21–31. https://doi.org/10.1016/j.cageo.2016.01.002.
• Chen, J., Huang, H., Zhou, M., & Chaiyasarn, K. (2021). Towards semi-automatic discontinuity characterization in rock tunnel faces using 3D point clouds. Engineering Geology, 291, 106232. https://doi.org/10.1016/j.enggeo.2021.106232.
• Chen, J., Zhu, H., & Li, X. (2016). Automatic extraction of discontinuity orientation from rock mass surface 3D point cloud. Computers & Geosciences, 95, 18–31. https://doi.org/10.1016/j.cageo.2016.06.015.
• Drews, T., Miernik, G., Anders, K., Höfle, B., Profe, J., Emmerich, A., & Bechstädt, T. (2018). Validation of fracture data recognition in rock masses by automated plane detection in 3D point clouds. International Journal of Rock Mechanics and Mining Sciences, 109, 19–31. https://doi.org/10.1016/j.ijrmms.2018.06.023.
• Ester, M., Kriegel, H.-P., Sander, J., & Xu, X. (1996). A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Kdd, 96(34), 226–231.
• Ge, Y., Cao, B., & Tang, H. (2022). Rock Discontinuities Identification from 3D Point Clouds Using Artificial Neural Network. Rock Mechanics and Rock Engineering, 55(3), 1705–1720. https://doi.org/10.1007/s00603-021-02748-w.
• Hu, L., Xiao, J., & Wang, Y. (2020). Efficient and automatic plane detection approach for 3-D rock mass point clouds. Multimedia Tools and Applications, 79(1), Article 1. https://doi.org/10.1007/s11042-019-08189-6.
• Kong, D., Wu, F., & Saroglou, C. (2020). Automatic identification and characterization of discontinuities in rock masses from 3D point clouds. Engineering Geology, 265, 105442. https://doi.org/10.1016/j.enggeo.2019.105442.
• Singh, S. K., Banerjee, B. P., Lato, M. J., Sammut, C., & Raval, S. (2022). Automated rock mass discontinuity set characterisation using amplitude and phase decomposition of point cloud data. International Journal of Rock Mechanics and Mining Sciences, 152, 105072. https://doi.org/10.1016/j.ijrmms.2022.105072.
• Singh, S. K., Banerjee, B. P., & Raval, S. (2023). A review of laser scanning for geological and geotechnical applications in underground mining. International Journal of Mining Science and Technology, 33(2), 133–154. https://doi.org/10.1016/j.ijmst.2022.09.022.
• Singh, S. K., Raval, S., & Banerjee, B. P. (2021). Automated structural discontinuity mapping in a rock face occluded by vegetation using mobile laser scanning. Engineering Geology, 285, 106040. https://doi.org/10.1016/j.enggeo.2021.106040.
• Wu, W., Zhang, K., & Zhu, H. (2020). A fast automatic extraction method for rock mass discontinuity orientation using fast k-means++ and fast silhouette based on 3D point cloud. IOP Conference Series: Earth and Environmental Science, 570(5), 052075. https://doi.org/10.1088/1755-1315/570/5/052075.
• Zhang, K., Wu, W., Zhu, H., Zhang, L., Li, X., & Zhang, H. (2020). A modified method of discontinuity trace mapping using three-dimensional point clouds of rock mass surfaces. Journal of Rock Mechanics and Geotechnical Engineering, 12(03), Article 03.