[1]蔡杏辉,廖诗荣,张燕明,等.基于支持向量机的地震事件类型自动识别及应用[J].华南地震,2021,41(02):27-35.[doi:10.13512/j.hndz.2021.02.04 ]
 CAI Xinghui,LIAO Shirong,ZHANG Yanming,et al.Automatic Identification of Earthquake Event Types Based on Support Vector Machine and Its Application[J].,2021,41(02):27-35.[doi:10.13512/j.hndz.2021.02.04 ]
点击复制

基于支持向量机的地震事件类型自动识别及应用()
分享到:

华南地震[ISSN:1006-6977/CN:61-1281/TN]

卷:
41
期数:
2021年02期
页码:
27-35
栏目:
地震科学研究
出版日期:
2021-06-20

文章信息/Info

Title:
Automatic Identification of Earthquake Event Types Based on Support Vector Machine and Its Application
文章编号:
1001-8662(2021)02-0027-09
作者:
蔡杏辉廖诗荣张燕明陈惠芳林彬华
(福建省地震局,福州 350003)
Author(s):
CAI XinghuiLIAO ShirongZHANG YanmingCHENG HuifangLIN Binhua
(Fujian Earthquake Agency,Fuzhou 350003,China)
关键词:
事件类型特征组合自动识别模块支持向量机
Keywords:
Event typeFeature combination Automatic recognition moduleSupport Vector Machine
分类号:
P315
DOI:
10.13512/j.hndz.2021.02.04
文献标志码:
A
摘要:
天然地震与非天然地震自动识别是地震自动编目系统的重要功能之一,是监测数据产出智能化的基础应用。从福建天然地震和人工爆破事件中,提取小波分析特征、P/S震相振幅比、波形能量分布特征,对以上特征组合联合支持向量机进行大批量数据测试分析,研究得出识别效果较好的事件类型判别算法,最优测试识别率为94.5%;采用最优算法研发基于支持向量机事件类型自动识别模块,将研制的自动识别软件模块应用于福建台网的日常地震编目工作,对2019年8月1日至2020年2月29日共计1531个日常触发事件进行准实时分类,自动识别软件模块分类的正确率为93.9%。另外,采用AMQ消息中间件为信息中介,从redis波形共享内存中获取事件波形,实现自动识别模块与自动编目系统对接。
Abstract:
Automatic identification of natural and non-natural earthquakes is one of the important functions of earthquake automatic cataloging system,and it is the basic application of intelligent monitoring data output. The wavelet analysis features,P/S phase amplitude ratio,waveform energy distribution features and spectrum features were extracted from the natural earthquake and artificial blasting events in Fujian province to carry out large-scale data test and analysis on the combination of the above features and the Support Vector Machine,the algorithm of event type identification is proved to effective,and the optimal test recognition rate is 94.5%. An automatic event recognition module based on Support Vector Machine is developed by using the optimal algorithm,the automatic identification software module was applied to the daily earthquake cataloging work of Fujian Seismic Network,and a total of 1531 daily triggered events were quasi real time classified from August 1st,2019 to February 29th,2020,the correct rate of automatic recognition software module classification was 93.9%. Using Amq message middleware as the information medium,the event waveform is obtained in Redis waveform shared memory,and the automatic recognition module is connected with automatic cataloging system.

参考文献/References:

[1] 边银菊. 遗传BP网络在地震和爆破识别中的应用[J]. 地震学报,2002,24(5):516-524.
[2] 卢世军,黄汉明. 基于能量比的天然地震与人工爆破自动识别算法研究[J]. 华南地震,2010,30(1):34-39.
[3] 黄汉明,边银菊,卢世军,等. 天然地震与人工爆破的波形小波特征研究[J]. 地震学报,2010,32(3):270-276.
[4] 赵明,陈石,Dave Yuen. 基于深度学习卷积神经网络的地震波形自动分类与研究[J]. 地球物理学报,2019,62(1):374-382.
[5] 王军. 支持向量机在地震和爆破识别中的应用[J]. 地震地磁观测与研究,2018,39(3):181:188.
[6] 刘方斌,曲军浩,张志慧. 基于BP神经网络的天然与非天然地震识别[J]. 计算机应用与软件,2020,37(1):109.
[7] Jari Kortstrom. Automatic classification of seismic events within a regional seismograph network[J]. Computers Geos-ciences,2016,87:22-30.
[8] N. Rabin. Earthquake-explosion discrimination using diffusion maps[J]. Geophysical Journal International,2016,(207):1484-1492.
[9] Omar M. Saad. Automatic discrimination of earthquakes and quarry blasts using wavelet filter bank and support vector machine[J]. Journal of Seismology,2019(23):357-371.
[10] 郝红艳. 基于支持向量机的可靠性优化设计方法研究[D]. 武汉:华中科技大学,2013.
[11] Cristianini N. 支持向量机导论[M]. 北京:机械工业出版社,2005.
[12] Pai-Hsuen Chen,Chih-jen lin,Bernhard Scholkopf.A tutorial on v-Support Vector Machines[J]. Applied Stochastic Models in Business and Industry,2005,2(2):111-136.
[13] 倪炜. 分布式消息中间件实践[M]. 北京:电子工业出版社,2018.
[14] Colin T O,G. Eli Baker,Anne F.Sheehan.Using P/S amplitude ratios for seismic discrimination at local distances[J]. Bulletin of the Seismological Society of Am-erica,2016,106(5):1-12.
[15] 付磊,张益军. Redis开发与运维[M]. 北京:机械工业出版社,2017.

备注/Memo

备注/Memo:
收稿日期:2020-08-10
基金项目:监测预报科研三结合(3JH20200105);中国地震局监测预报业务专项;地震科技星火计划项目(XH20029)联合资助
作者简介:蔡杏辉(1976-),男,高级工程师,主要从事地震监测工作。E-mail:13870511@sina.com
更新日期/Last Update: 2021-06-20