img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2017, Vol. 25 ›› Issue (4): 46-51.doi: 10.11872/j.issn.1005-2518.2017.04.046

• 采选技术与矿山管理 • 上一篇    下一篇

基于谱聚类算法的岩体结构面产状优势分组

何顺斌1,刘杰2   

  1. 1.山东黄金矿业(莱州)有限公司三山岛金矿,山东  莱州   261442;
    2.东北大学资源与土木工程学院,辽宁  沈阳   110819
  • 收稿日期:2017-04-21 修回日期:2017-07-15 出版日期:2017-08-30 发布日期:2017-10-30
  • 通讯作者: 刘杰(1986-),男,河南沈丘人,博士研究生,从事岩石破裂与失稳方面的研究工作。413246694@qq.com
  • 作者简介:何顺斌(1973-),男,河南南阳人,高级工程师,从事金属矿山开采技术和管理工作。heshunbin123@163.com
  • 基金资助:

    国家自然科学基金项目“基于岩体动力响应特征的岩爆控制方法研究”(编号:51474052)、中央高校基本科研业务费专项资金“深部复杂应力环境下巷道围岩变异性破坏机理研究”(编号:N150102001)和国家重点研发计划“深部金属矿建井与提升关键技术”(编号:2016YFC0600803)联合资助。

Dominant Grouping of Rock Mass Structural Space Orientation Based on Spectral Clustering Algorithm 

HE Shunbin1,LIU Jie2   

  1. 1.Sanshandao Gold Mine,Shandong Gold Mining (Laizhou) Co.,Ltd.,Laizhou   261442,Shandong,China;
    2.School of Resources and Civil Engineering,Northeastern University,Shenyang   110819,Liaoning,China
  • Received:2017-04-21 Revised:2017-07-15 Online:2017-08-30 Published:2017-10-30

摘要:

结构面分组是开展岩体工程稳定性分析的基础,为此,采用谱聚类算法根据岩体结构面产状信息将结构面进行优势组划分。与目前广泛使用的K均值聚类相比,该算法能够收敛到全局最优。选取结构面法向量所夹锐角的正弦值平方作为结构面间的相似度量准则,应用谱聚类算法进行优化求解;同时,引入Silhouette指标对聚类有效性进行评价,以确定最佳分类数目。利用谱聚类方法对人工生成结构面数据进行计算的结果验证了该方法的可靠性。最后,将该算法应用于三山岛金矿岩体结构面的优势组划分,取得了理想的分类效果,为进一步岩体稳定性分析提供了可靠的数据基础。

关键词: 岩体结构面, 聚类分析, 谱聚类算法, 优势产状

Abstract:

The identification of rock discontinuity sets is the foundation of stability analysis of rock masses in engineering practices.Therefore,a spectral clustering algorithm was used in this paper to classify the discontinuity data sets based on discontinuity orientations.Compared with the K-means clustering algorithm widely used at present,this algorithm can converge to the global optimum.The square value of the sine of acute angle between normal unit vectors of structural planes was selected as similarity criterion and then the spectral method was used to group discontinuity data.Meanwhile,the Silhouette index was introduced to evaluate the clustering validity to determine the optimal clustering number.The test of artificial discontinuity data shows that the method is reliable. Finally,the algorithm was applied to group the discontinuity data in Sanshandao gold mine.The results show that the algorithm can achieve ideal classification results,which provides reliable data base for further analysis of rock mass stability.

Key words:  rockmass structural plane, cluster analysis, spectral clustering method, dominant orientation

中图分类号: 

  • TD163+2

[1] Park H J,West T R,Woo I.Probabilistic analysis of rock slope stability and random properties of discontinuity parameters,Interstate Highway 40,Western North Carolina,USA[J]. Engineering Geology,2005,79(3/4):230-250.
[2] Maffuccia R,Bigi S,Corrado S,et al.Quality assessment of reservoirs by means of outcrop data and“discrete fracture network” models:The case history of Rosario de La Frontera (NW Argentina) geothermal system[J].Tectonophysics,2015,647-648:112-131.
[3] Xu C S,Peter D.A new computer code for discrete fracture network modeling[J].Computers and Geosciences,2010,36(3):292-301.
[4] Lu Bo,Ding Xiuli,Wu Aiqing. Study on method of orientation data partitioning of randomly distributed discontinuities of rocks[J].Chinese Journal of Rock Mechanics and Enginee- ring,2007,26(9):1809-1816.[卢波,丁秀丽,邬爱清.岩体随机不连续面产状数据划分方法研究[J].岩石力学与工程学报,2007,26(9):1809-1816.]
[5] Shanley R J,Mahtab M A.Delineation and analysis of clusters in orientation data[J].Journal of the International Association for Mathematical Geology,1976,8(1):9-23.
[6] Hammah R E,Curran J H.Fuzzy cluster algorithm for the auto-matic identification of joint sets[J].International Journal of Rock Mechanics and Mining Sciences,1998,35(7):889-905.
[7] Hammah R E,Curran J H.On distance measures for the fuzzy K-means algorithm for joint data[J].Rock Mechanics and Rock Engineering,1999,32(1):1-27.
[8] Zhou Yuxin,Zhou Zhifang,Sun Qiguo.Synthetical fuzzy clustering analysis for occurrence of rock mass[J].Chinese Jour- nal of Rock Mechanics and Engineering,2005,24(13):2283-2287.[周玉新,周志芳,孙其国.岩体结构面产状的综合模糊聚类分析[J].岩石力学与工程学报,2005,24(13):2283-2287.]
[9] Zhou W,Maerz N H.Implementation of multivariate clustering methods for characterizing discontinuities data from scanlines and oriented boreholes[J].Computers and Geoscie- nces,2002,28(7):827-839.
[10] Xiang Jie,Zhao Dongqin.Improved spectral clustering algorithm and its application in MCI detection[J]. Journal on Communication,2015,36(4):887-890.[相洁,赵冬琴.改进谱聚类算法在MCI 患者检测中的应用研究[J].通信学报,2015,36(4):887-890.]
[11] Li X B,Wang Z W,Peng K,et al.Ant colony ATTA clustering algorithm of rock mass structural plane in groups[J]. Journal of Central South University,2014,21(2):709-714.
[12] Li Ning,Wang Liguan,Jia Mingtao,et al.Application of improved genetic algorithm and support vector machine to clustering analysis of rock mass structural plane[J].Rock and Soil Mechanics,2014,35(S2):405-411.[李宁,王李管,贾明涛,等.改进遗传算法和支持向量机的岩体结构面聚类分析[J].岩土力学,2014,35(增2):405-411.]
[13] Du Furui,Xie Yuling,Hu Nailian,et al.Design and application of microseismic system in Xinli mining area of Sanshandao gold mine[J]. Metal Mine,2013(9):148-151.[杜富瑞,谢玉玲,胡乃联,等.三山岛金矿新立矿区微震系统设计及应用[J].金属矿山,2013(9):148-151.]
[14] Chen Yumin,Li Xibing.Safety and Efficient Mining Technology for Large Submarine Metal Deposits[M].Beijing:Metallurgical Industry Press,2013.[陈玉民,李夕兵. 海底大型金属矿床安全高效开采技术[M]. 北京:冶金工业出版社,2013.]
[15] He Shunbin,Wang Hongwei,Guo Yao,et al.Analysis of characteristics of seepage field in Sanshandao gold mine under the action of water chemical damage[J].Metal Mine,2016(6):167-172.[何顺斌,王宏伟,郭遥,等.水化学损伤作用下三山岛金矿渗流场特征分析[J].金属矿山,2016(6):167-172.]

[1] 何金霖, 李俊, 许慧玲, 曹李慧, 孙德华. 山东曹家洼金矿石头顶矿段土壤地球化学特征及找矿预测[J]. 黄金科学技术, 2022, 30(2): 179-195.
[2] 刘国伟,马凤山,郭捷,杜云龙,侯成录,李威. 多元统计分析在滨海矿区水源识别中的应用——以三山岛金矿为例[J]. 黄金科学技术, 2019, 27(2): 207-215.
[3] 韩珂,安乐,杨兴科,刘淑文. 数学地质方法在南秦岭汉阴黄龙金矿中的应用[J]. 黄金科学技术, 2019, 27(1): 1-14.
[4] 邓高,杨珊 . 基于灰色聚类与灰色预测组合模型的矿产资源利用情况分析[J]. 黄金科学技术, 2017, 25(5): 85-92.
[5] 孙保花,牛树银,王杏村,孙爱群,丁培超,李强峰,侯江龙. 小秦岭大湖金矿矿体原生晕特征研究[J]. 黄金科学技术, 2014, 22(4): 55-60.
[6] 祁民,张宝林,宋保昌,王杰,于立臣. 河北水晶屯金矿隐伏找矿靶区钻孔岩芯地球化学特征及成矿预测[J]. J4, 2004, 12(5): 6-14.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!