An enriched K-means clustering method for grouping fractures with meliorated initial centers

详细信息    查看全文

• 作者：G. W. Ma (3)
  Z. H. Xu (1) (2)
  W. Zhang (3)
  S. C. Li (1)
  
  3. School of Civil and Resource Engineering ; The University of Western Australia ; Perth ; WA ; 6009 ; Australia
  1. Geotechnical and Structural Engineering Research Center ; Shandong University ; Jinan ; Shandong ; 250061 ; China
  2. State Key Laboratory for GeoMechanics and Deep Underground Engineering ; China ; University of Mining & Technology ; Xuzhou ; Jiangsu ; 221008 ; China
  
• 关键词：Enriched K ; means聽clustering method聽 ; Meliorated initial center ; Gathering degree ; Hierarchical clustering ; Fracture grouping
• 刊名：Arabian Journal of Geosciences
• 出版年：2015
• 出版时间：April 2015
• 年：2015
• 卷：8
• 期：4
• 页码：1881-1893
• 全文大小：4,397 KB
• 参考文献：1. Behzad, T, Memarian, H, Moshiri, B, Rasouli, V, Noubari, HA (2011) Investigating the validity of conventional joint set clustering methods. Eng Geol 118: pp. 75-81 CrossRef
  2. Cai, MF, Wang, P, Zhao, K, Zhang, D (2005) Fuzzy C-means cluster analysis based on genetic algorithm for automatic identification of joint sets. Chin J Rock Mech Eng 24: pp. 371-376
  3. Fan, L, Wang, LQ, Tang, HM (2007) Dynamic cluster analysis of discontinuity orientations of jointed rock mass. Rock Soil Mech 28: pp. 2405-2408
  4. Hammah, RE, Curran, JH (1998) Fuzzy cluster algorithm for the automatic identification of joint sets. Int. J. Rock Mech. Min. Sci. 35: pp. 889-905 CrossRef
  5. Hammah, RE, Curran, JH (1999) On distance measures for the fuzzy K-means algorithm for joint data. Rock Mech Rock Eng 32: pp. 1-27 CrossRef
  6. Hammah, RE, Curran, JH (2000) Validity measures for the fuzzy cluster analysis of orientations. IEEE T. Pattern Anal. 22: pp. 1467-1472 CrossRef
  7. Huh, M-H Setting the number of clusters in K-means clustering. In: Baba, Y, Hayter, A, Kanefuji, K, Kuriki, S eds. (2002) Recent advances in statistical research and data analysis. Springer, Japan, pp. 115-124 CrossRef
  8. Jia, HB, Tang, HM, Liu, YR, Ma, SZ (2008) Theory and engineering application of 3-d network modeling of discontinuities in rockmass. Science Publishing house, Beijing
  9. Jimenez, R (2008) Fuzzy spectral clustering for identification of rock discontinuity sets. Rock Mech Rock Eng 41: pp. 929-939 CrossRef
  10. Jimenez-Rodriguez, R, Sitar, N (2006) A spectral method for clustering of rock discontinuity sets. Int. J. Rock Mech. Min. Sci. 43: pp. 1052-1061 CrossRef
  11. Johnson, S (1967) Hierarchical clustering schemes. Psychometrika 32: pp. 241-254 CrossRef
  12. Klose, CD, Seo, S, Obermayer, K (2005) A new clustering approach for partitioning directional data. Int. J. Rock Mech. Min. Sci. 42: pp. 315-321 CrossRef
  13. Lisle RJ, Leyshon PR (2004) Stereographic projection techniques for geologists and civil engineers. Cambridge University Press.
  14. MacQueen, J., 1967. Some methods for classification and analysis of multivariate observations, Proceedings of the fifth Berkeley symposium on mathematical statistics and probability. California, USA, p. 14.
  15. Moomivand H (2013) Effects of orientation, frequency, and number of sets of discontinuities on rock strength under triaxial stresses. Arab J Geosci 1鈥?
  16. Pecher, A (1989) SCHMIDTMAC鈥攁 program to display and analyze directional data. Comput. Geosci-UK 15: pp. 1315-1326 CrossRef
  17. Priest, SD (1993) Discontinuity analysis for rock engineering, 1st ed. Chapman&Hall, London, New York CrossRef
  18. Scesi L, Gattinoni P (2009) Water circulation in rocks. Springer.
  19. Shanley, RJ, Mahtab, MA (1976) Delineation and analysis of clusters in orientation data. J Int Assoc Math Geol 8: pp. 9-23 CrossRef
  20. Terzaghi RD (1965) Sources of error in joint surveys. Geotechnique 4
  21. Theodoridis S, Koutroumbas K (2008) Pattern recognition. Elsevier Science.
  22. Verma, A, Singh, TN (2010) Modeling of a jointed rock mass under triaxial conditions. Arab J Geosci 3: pp. 91-103 CrossRef
  23. Wang, JH (1999) A new statistical grouping method of orientation data of fractures. Express Water Res. Hydropower Inform. (EWRHI) 20: pp. 27-28
  24. Wong LNY, Liu G (2010) An improved K-means clustering method for the automatic grouping of discontinuity sets, 44th US Rock Mechanics Symposium and 5th US-Canada Rock Mechanics Symposium.
  25. Xie, X l, Beni, G (1991) A validity measure for fuzzy clustering. IEEE T. Pattern Anal. 13: pp. 841-847 CrossRef
  26. Xie JW, Zhang YB, Jiang WG (2008) A K-means clustering algorithm with meliorated initial centers and its application to partition of diet structures, International Symposium on Intelligent Information Technology Application Workshops, 2008. IITAW '08., pp. 98鈥?02.
  27. Xu ZH (2013) Topological pipe network method for underground water flow simulation and engineering applications. School of Civil Engineering, Shandong University, China
  28. Zhang, YJ, Cheng, EX An optimized method for selection of the initial centers of K-means clustering. In: Qin, Z, Huynh, V-N eds. (2013) Integrated Uncertainty in Knowledge Modelling and Decision Making. Springer, Berlin Heidelberg, pp. 149-156 CrossRef
  29. Zhou, W, Maerz, NH (2002) Implementation of multivariate clustering methods for characterizing discontinuities data from scanlines and oriented boreholes. Comput. Geosci-UK 28: pp. 827-839 CrossRef
  30. Zhou, YX, Zhou, ZF, Sun, QG (2005) Synthetical fuzzy clustering analysis for joints occurrence of rock mass. Chinese J. Rock Mech. Eng. 24: pp. 2283-2287
  
• 刊物类别：Earth and Environmental Science
• 出版者：Springer Berlin Heidelberg
• ISSN：1866-7538

文摘

An enriched K-means clustering method for grouping fractures with meliorated initial cluster centers is proposed. Selection of the initial cluster centers is based on a gathering degree function and a hierarchical clustering method. A simplified Xie-Beni cluster validity index is applied to determine the optimal number of clusters automatically. The effectiveness of the proposed clustering method is demonstrated by using synthetic data and field data compiled from literatures. The gathering degree concept used in the density-based method is helpful in seeking suitable initial cluster centers. It alleviates the influence from the selected arbitrary threshold to get a more stable clustering result. The procedure to automatically remove fractures belonging to the obtained cluster center with the hierarchical clustering method is more natural than using the pre-defined radius. Additional advantage of the algorithm is that its convergence is fast, and it can be easily implemented for geological mapping result analysis.