All Issue

2024 Vol.26, Issue 6 Preview Page

Research Paper

R-C-D machine learning method to detect joints in 3D point cloud of rock tunnel face

암석 터널 막장의 3차원 포인트 클라우드에서 절리 계측을 위한 R-C-D 기계 학습 방법

Sangmo Moon1
,
Bara Alseid2
,
Hangseok Choi3
,
Jeonghun Yang4
,
Hong Pyo Moon5
,
Hyungjoon Seo6*
문 상모1
,
Alseid Bara2
,
최 항석3
,
양 정훈4
,
문 홍표5
,
서 형준6*
1Ph.D. Candidate, School of Civil, Environmental and Architectural Engineering, Korea University
2Site Engineer, Habash-Deir Contracting Company L.L.C
3Professor, School of Civil, Environmental and Architectural Engineering, Korea University
4Director, EDOGA Consultants
5Manager, DLENC
6Assistant Professor, Dept. of Civil Engineering, Seoul National University of Science and Technology
1비회원, 고려대학교 건축사회환경공학부 박사과정
2비회원, Habash-Deir Contracting Company L.L.C 팀장
3정회원, 고려대학교 건축사회환경공학부 교수
4정회원, (주)이도가컨설턴트 이사
5정회원, 디엘이앤씨 부장
6정회원, 서울과학기술대학교 건설시스템공학과 조교수
*Corresponding Author
30 November 2024. pp. 661-679
PDF XML Citation
Abstract

In rock tunnel excavation, joint is one of the important factors in determining the stability of the tunnel face. This paper proposes the Roughness-CANUPO-Dip Filtration (R-C-D) method to detect joints in tunnel excavation faces. The R-C-D method involves three steps: roughness analysis, CANUPO analysis, and dip filtration. In addition, the study evaluates four different measuring methods for dip angle and direction: plane fitting, normal vector conversion, facet segmentation, and compass measurements. This method is applied to three rock tunnel sites and the results showed that all the measurement tools were able to accurately detect the joints and calculate the dip angle, with an accuracy ranging from 97% to 99.4% for all the applied measurements. Facet segmentation method was identified as the optimal measurement tool due to its automatic nature and ability to provide accurate results without the need for manual intervention. The optimum local neighbour radius (LNR) used to calculate normal vectors was also estimated, with results indicating that a larger LNR value leads to more accurate results but also increases computational time. A verification was performed to estimate the dip angle used to filter and discard additional points that represent joint rock bands, with the optimum value being 45,30,45 degrees respectively, for each site. The R-C-D Method was developed to eliminate joint lines and sustain joint embedment points in order to obtain their dip angle and direction. The R-C-D Method was applied to three site models, and the results showed that the method was successful in detecting joint lines and eliminating them, while the dip angle filtration successfully removed the joint bands. The results showed that the R-C-D Method was effective in obtaining accurate and precise dip angle and direction measurements for geological materials.

Keywords
R-C-D machine learning method
3D point cloud
Rock tunnel face
Dip angle
Dip direction

암석터널 굴착에서 절리는 터널 막장의 안정성을 판단하는데 중요한 요소중 하나이다. 본 연구에서는 지질 암석면의 경사각과 방향을 측정하기 위한 새로운 방법인 Roughness-CANUPO-Dip filtration (R-C-D)을 제시한 후 3개 현장 모델에 의해 평가했다. R-C-D 방법은 거칠기 분석, CANUPO 분석으로 구성된다. 또한 본 연구에서는 경사각 및 방향에 대한 네 가지 다른 측정 방법인 평면 피팅, 법선 벡터 변환, 면 세분화 및 나침반 측정을 평가한다. 결과는 모든 측정 방법에서 97~99.4% 범위의 정확도로 경사각을 정확하게 계산할 수 있음을 보여주었다. 면 세분화 방법은 수동적인 개입 없이 자동으로 정확한 결과를 제공할 수 있어 최적의 측정 방법으로 선택되었다. 법선 벡터를 계산하기 위해 사용되는 최적의 LNR (local neighbor radius)도 산출되었으며, LNR 값이 클수록 더 정확한 결과를 얻을 수 있지만 계산 시간도 증가하는 것으로 나타났다. 절리암대를 나타내는 추가 지점을 필터링하고 삭제하는 데 사용되는 경사각을 추정하기 위한 검증을 수행하였으며, 각 지점에 대해 최적 경사각은 각각 45°, 30°, 45°였다. R-C-D 방법은 절리면을 제거하고 절리 근입점을 유지하여 경사각과 방향을 얻기 위해 개발되었다. R-C-D 방법을 3개 현장 모델에 적용한 결과, 이 방법은 절리면을 감지하여 제거하는 데에 적합한 것으로 나타났으며, 경사각 필터링 방법은 절리대를 성공적으로 제거하였다. R-C-D 방법이 지질 구조를 정확히 구분하고 정밀한 경사각 및 방향 측정을 얻는 데 효과적이라는 것을 보여주었다.

키워드
R-C-D 기계 학습 방법
3D 포인트 클라우드
암석 터널 막장
경사각
경사 방향
References
1

Anders, K., Hämmerle, M., Miernik, G., Drews, T., Escalona, A., Townsend, C., Höfle, B. (2016), "3D geological outcrop characterization: automatic detection of 3D planes (azimuth and dip) using LiDAR point clouds", Proceedings of the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. III-5, XXIII ISPRS Congress, Prague, pp. 105-112.

10.5194/isprsannals-III-5-105-2016
2

Battulwar, R., Zare-Naghadehi, M., Emami, E., Sattarvand, J. (2021), "A state-of-the-art review of automated extraction of rock mass discontinuity characteristics using three-dimensional surface models", Journal of Rock Mechanics and Geotechnical Engineering, Vol. 13, No. 4, pp. 920-936.

10.1016/j.jrmge.2021.01.008
3

Brush, J.A., Pavlis, T.L., Hurtado, J.M., Mason, K.A., Knott, J.R., Williams, K.E. (2019), "Evaluation of field methods for 3-D mapping and 3-D visualization of complex metamorphic structure using multiview stereo terrain models from ground-based photography", Geosphere, Vol. 15, No. 1, pp. 188-221.

10.1130/GES01691.1
4

Collettini, C., De Paola, N., Holdsworth, R.E., Barchi, M.R. (2006), "The development and behaviour of low-angle normal faults during Cenozoic asymmetric extension in the Northern Apennines, Italy", Journal of Structural Geology, Vol. 28, No. 2, pp. 333-352.

10.1016/j.jsg.2005.10.003
5

Compton, R.R. (1985), Geology in the Field, John Wiley & Sons, Stanford, pp. 1-412.

6

Dandois, J.P., Ellis, E.C. (2010), "Remote sensing of vegetation structure using computer vision", Remote Sensing, Vol. 2, No. 4, pp. 1157-1176.

10.3390/rs2041157
7

Deweza, T.J.B., Girardeau-Montaut, D., Allanica, C., Rohmer, J. (2016), "FACETS: A CloudCompare plugin to extract geological planes from unstructured 3D point clouds", Proceedings of the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XLI-B5, XXIII ISPRS Congress, Prague, pp. 799-804.

10.5194/isprsarchives-XLI-B5-799-2016
8

Girardeau-Montaut, D. (2014), CloudCompare, a 3D point cloud and mesh processing free software, EDF R&D, Telecom ParisTech.

9

Hengl, T., Reuter, H.I. (2008), Geomorphometry: Concepts, Software, Applications, Developments in Soil Science, Vol. 33, Elsevier, Amsterdam, 772pp.

10

Jaboyedoff, M., Oppikofer, T., Abellán, A., Derron, M.H., Loye, A., Metzger, R., Pedrazzini, A. (2012), "Use of LIDAR in landslide investigations: a review", Natural Hazards, Vol. 61, pp. 5-28.

10.1007/s11069-010-9634-2
11

Mammoliti, E., Di Stefano, F., Fronzi, D., Mancini, A., Malinverni, E.S., Tazioli, A. (2022), "A machine learning approach to extract rock mass discontinuity orientation and spacing, from laser scanner point clouds", Remote Sensing, Vol. 14, No. 10, 2365.

10.3390/rs14102365
12

Menegoni, N., Giordan, D., Perotti, C., Tannant, D.D. (2019), "Detection and geometric characterization of rock mass discontinuities using a 3D high-resolution digital outcrop model generated from RPAS imagery - Ormea rock slope, Italy", Engineering Geology, Vol. 252, pp. 145-163.

10.1016/j.enggeo.2019.02.028
13

Nagendran, S.K., Mohamad Ismail, M.A.B., Wen, Y.T. (2019), "Photogrammetry approach on geological plane extraction using CloudCompare FACET plugin and scanline survey", Bulletin of the Geological Society of Malaysia, Vol. 68, pp. 151-158.

10.7186/bgsm68201916
14

Ragan, D.M. (2009), Structural Geology: An Introduction to Geometrical Techniques (4th ed.), Cambridge University Press, Cambridge, pp. 1-632.

10.1017/CBO9780511816109
15

Sturzenegger, M., Stead, D. (2009), "Quantifying discontinuity orientation and persistence on high mountain rock slopes and large landslides using terrestrial remote sensing techniques", Natural Hazards and Earth System Sciences, Vol. 9, No. 1, pp. 267-287.

10.5194/nhess-9-267-2009
16

Westoby, M.J., Brasington, J., Glasser, N.F., Hambrey, M.J., Reynolds, J.M. (2012), "'Structure-from-Motion' photogrammetry: a low-cost, effective tool for geoscience applications", Geomorphology, Vol. 179, pp. 300-314.

10.1016/j.geomorph.2012.08.021
17

Yuan, Y., Zhang, N., Han, C., Yang, S., Xie, Z., Wang, J. (2022), "Digital image processing-based automatic detection algorithm of cross joint trace and its application in mining roadway excavation practice", International Journal of Mining Science and Technology, Vol. 32, No. 6, pp. 1219-1231.

10.1016/j.ijmst.2022.09.009
18

Zou, X., Wang, C., Zhang, H., Chen, S. (2021), "A practical method for the automatic recognition of rock structures in panoramic borehole image during deep-hole drilling engineering", Applied Sciences, Vol. 11, No. 21, 10490.

10.3390/app112110490
Information
  • Publisher :Korean Tunneling and Underground Space Association
  • Publisher(Ko) :한국터널지하공간학회
  • Journal Title :Journal of Korean Tunnelling and Underground Space Association
  • Journal Title(Ko) :한국터널지하공간학회 논문집
  • Volume : 26
  • No :6
  • Pages :661-679
  • Received Date : 2024-09-23
  • Revised Date : 2024-10-22
  • Accepted Date : 2024-10-28
  • DOI :https://doi.org/10.9711/KTAJ.2024.26.6.661
Journal Informaiton Journal of Korean Tunnelling and Underground Space Association Journal of Korean Tunnelling and Underground Space Association
Online Submission & Review System
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close