|本期目录/Table of Contents|

[1]刘德彪,李夕兵,李响,等.基于LOF的K-means聚类方法及其在微震监测中的应用[J].中国安全生产科学技术,2019,15(6):81-87.[doi:10.11731/j.issn.1673-193x.2019.06.013]
　LIU Debiao,LI Xibing,LI Xiang,et al.K-means clustering method based on LOF and its application in microseismic monitoring[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(6):81-87.[doi:10.11731/j.issn.1673-193x.2019.06.013]
点击复制

基于LOF的K-means聚类方法及其在微震监测中的应用
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
15
期数:
2019年6期
页码:
81-87
栏目:
职业安全卫生管理与技术
出版日期:
2019-06-30

文章信息/Info

Title:
K-means clustering method based on LOF and its application in microseismic monitoring
文章编号:
1673-193X(2019)-06-0081-07
作者:
刘德彪; 李夕兵; 李响; 尚雪义
(中南大学 资源与安全工程学院，湖南 长沙 410083)
Author(s):
LIU Debiao;  LI Xibing;  LI Xiang;  SHANG Xueyi
(School of Resource and Safety Engineering, Central South University, Changsha Hunan 410083, China)
关键词:
矿山微震; 局部离群因子; K-means聚类; 微震活动性
Keywords:
mine microseismic;  local outlier factor (LOF);  Kmeans clustering;  microseismicity
分类号:
X936
DOI:
10.11731/j.issn.1673-193x.2019.06.013
文献标志码:
A
摘要:
矿山微震事件集群是分析矿震的重要参考之一，其准确的划分对矿山微震分布特征和微震活动分析具有重要作用。提出了1种基于局部离群因子(Local Outlier Factor, LOF)的K-means聚类算法并构建了综合SSE评价指标和模型，通过LOF算法检测异常微震事件和选取初始聚类中心，利用Krzanowski-Lai指数确定最佳聚类分组数；采用模拟计算比较了不同数据集大小的聚类效果。结果表明：基于LOF的K-means聚类方法评分最高，聚类结果最好；并利用该聚类方法分析用沙坝矿1 649个微震事件的分布特征与微震活动性。实例表明，K=7为最佳聚类分组数，聚类簇的划分受断层滑移和矿山生产活动的影响。
Abstract:
The microseismic event cluster in mines is a primary reference of mine earthquake analysis, and its accurate division plays an important role for the analysis on microseismic distribution characteristics and microseismicity of mine. A Kmeans clustering algorithm based on local outlier factor (LOF) was proposed, and the comprehensive SSE evaluation indexes and model were constructed. The abnormal microseismic events were detected and the initial clustering centers were selected by using LOF algorithm, and the optimal clustering number was determined by using the KrzanowskiLai index. The clustering effect of this method was compared with those of the Kmeans clustering in literature ［14］ and the traditional Kmeans clustering by using the simulated calculation. The results showed that the score of Kmeans clustering method based on LOF was the highest, with the best clustering results. The distribution characteristics and microseismicity of 1 649 microseismic events in Yongshaba mine were analyzed by using this clustering method, which showed that K=7 was the optimal clustering number, and the division of cluster was affected by the fault slip and the mine production.

参考文献/References:

［1］冯夏庭, 王泳嘉. 深部开采诱发的岩爆及其防治策略的研究进展［J］. 中国矿业, 1998, 7(5):42-45. FENG Xiating, WANG Yongjia. New development in researching rockburst induced by mining at great depth aand its control strategies ［J］. China Mining Magazine, 1998, 7(5):42-45.
［2］姜福兴. 微震监测技术在矿井岩层破裂监测中的应用［J］.岩土工程学报, 2002, 24(2):147-149. JIANG Fuxing. Application of microseismic monitoring technology of strata fracturing in underground coal mine ［J］. Chinese Journal of Geotechnical Engineering, 2002, 24(2):147-149.
［3］徐顺强,刘巧霞,李怡青,等.密集台网微震定位技术在矿山开采动态监测中的应用研究［J］.地震工程学报, 2015, 37(1):266-270. XU Shunqiang, LIU Qiaoxia, LI Yiqing, et al. Application of the dense network micro-seismic location method to dynamic mining monitoring ［J］. China Earthquake Engineering Journal, 2015, 37(1):266-270.
［4］高见,张元生,郭飚,等. 甘东南流动台阵微震监测结果［J］.地震工程学报, 2013, 35(1):177-182. GAO Jian, ZHYANG Yuansheng, GUO Biao, et al. Microearthquake location determined by portable seismic array data in southeast gansu province ［J］. China Earthquake Engineering Journal, 2013, 35(1):177-182.
［5］ZALIAPIN I, BEN-ZION Y. Discriminating characteristics of tectonic and human-induced seismicity ［J］. Bulletin of the Seismological Society of America, 2016, 106(3): 846-859.
［6］WEATHERILL G, BURTON P W. Delineation of shallow seismic source zones using K-means cluster analysis, with application to the Aegean region ［J］. Geophysical Journal International, 2009, 176(2): 565-588.
［7］MORALES-ESTEBAN A, MARTNEZ-LVAREZ F, SCITOVSKI S, et al. A fast partitioning algorithm using adaptive Mahalanobis clustering with application to seismic zoning ［J］. Computersand geosciences, 2014, 73(9): 132-141.
［8］RAMDANI F, KETTANI O, TADILI B. Evidence for subduction beneathGibraltar Arc and Andean regions from K-means earthquake centroids ［J］. Journal of Seismology, 2015, 19(1): 41-53.
［9］吴爱祥, 武力聪, 刘晓辉, 等. 矿山微地震活动时空分布［J］. 北京科技大学学报, 2012, 34(6):609-613. WU Aixiang, WU Licong, LIU Xiaohui, et al. Space-time distribution of microseismic activities in mines ［J］. Journal of University of Science and Technology Beijing, 2012, 34(6):609-613.
［10］WANG Z, LI X, SHANG X. Distribution characteristics of mining-induced seismicity revealed by 3-D ray-tracing relocation and the FCM clustering method［J］. Rock Mechanics and Rock Engineering, 2019, 52(1): 183-197.
［11］SHANG X, LI X, MORALES-ESTEBAN A, et al. K-means cluster for seismicity partitioning and geological structure interpretation, with application to the Yongshaba mine (China)［J］. Shock and Vibration, 2017.
［12］刘栋, 李夕兵, 刘志祥, 等. 基于STSNN聚类算法的用沙坝矿微震事件活动特征研究［J］. 中国安全生产科学技术, 2017, 13(2):74-78. LIU dong, LI Xibing, LIU Zhixiang, et al. Study on activity characteristics of micro-seismic events in Yongshaba mine based on STSNN clustering algorithm ［J］. Journal of Safety Science and Technology, 2017, 13(2):74-78.
［13］刘栋, 李夕兵, 刘志祥, 等. 用沙坝断层滑移型微震事件群活动特征分析［J］. 安全与环境学报, 2018, 18(3):1036-1040. LIU dong, LI Xibing, LIU Zhixiang, et al. Characteristic analysis for the micro-seismic event group activities in a fault-slip form at the Yongshaba Mine ［J］. Journal of Safety and Enviroment, 2018, 18(3):1036-1040.
［14］WANG J, SU X. An improved K-means clustering algorithm ［C］// 2011 IEEE 3rd International Conference on Communication Software and Networks. 2011, 44-46.
［15］BREUNIG M M, KRIEGEL H P, NG R T, et al. LOF: identifying density-based local outliers ［J］. ACM Sigmod Record, 2000, 29(2): 93-104.
［16］GAO J, TAN P N. Converting output scores from outlier detection algorithms into probability estimates ［C］//Sixth International Conference on Data Mining . 2006, 212-221.
［17］KRIEGEL H P, KROGER P, SCHUBERT E, et al.Interpreting and unifying outlier scores ［C］//Proceedings of the 2011 SIAM International Conference on Data Mining. 2011, 13-24.
［18］KRZANOWSKI W J, LAI Y T. A criterion for determining the number of groups in a data set using sum-of-squares clustering ［J］. Biometrics, 1988, 44(1): 23-34.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期： 2019-03-31
* 基金项目： 国家重点研发计划项目(2016YFC0600706);中南大学中央高校基本科研业务费专项资金项目(2018zzts718)
作者简介： 刘德彪 ，硕士研究生，主要研究方向为微震监测数据分析。
通信作者： 李夕兵 ，博士，教授，主要研究方向为采矿与岩土工程。
更新日期/Last Update: 2019-07-09