首页 | 本学科首页   官方微博 | 高级检索  
     

基于RBF神经网络的地震与爆破识别技术
引用本文:毛世榕,史水平,苏梅艳,蒋志峰,玉壮基. 基于RBF神经网络的地震与爆破识别技术[J]. 地震地磁观测与研究, 2020, 41(3): 59-66. DOI: 10.3969/j.issn.1003-3246.2020.03.008
作者姓名:毛世榕  史水平  苏梅艳  蒋志峰  玉壮基
作者单位:中国广西 541004 广西壮族自治区地震局桂林地震台
基金项目:广西科学研究与技术开发计划(项目编号:桂科AB1850042);红水河流域水库地震特征的精细研究——以天峨至大化段为例;广西壮族自治区地震局科研课题(项目编号:2017002);人工神经网络技术在爆破识别中的应用
摘    要:利用天然地震震源和人工爆破震源之间信号能量分布的差异,结合RBF神经网络技术,对2类事件进行分类,具体步骤如下:使用8个带通滤波器对事件波形进行滤波,并划分为4个波形段:P波、P波尾波、S波和S波尾波,分别计算每个滤波器信道和波形段的能量特征值,以所得32个特征参数作为输入向量,利用RBF神经网络,对地震和爆破事件进行分类识别。结果表明,基于RBF神经网络的地震事件识别方法,识别率为88.1%,具有较高的准确性,可作为地震与爆破事件识别的一个重要依据。

关 键 词:地震识别  能量特征  RBF神经网络

A technique for earthquake and explosion discrimination based on RBF neural network
MAO Shirong,SHI Shuiping,SU Meiyan,JIANG Zhifeng,YU Zhuangji. A technique for earthquake and explosion discrimination based on RBF neural network[J]. Seismological and Geomagnetic Observation and Research, 2020, 41(3): 59-66. DOI: 10.3969/j.issn.1003-3246.2020.03.008
Authors:MAO Shirong  SHI Shuiping  SU Meiyan  JIANG Zhifeng  YU Zhuangji
Affiliation:Guilin Seismic Station, Earthquake Agency of Guangxi Zhuang Autonomous Region, Guangxi Zhuang Autonomous Region 541004, China
Abstract:In this paper, eight band-pass filters are used to filter the events waveform, which are divided into four waveform segments including P, P coda, S, and S coda. Then, the energy eigenvalues of each filter channel and waveform segment are calculated respectively. Finally, taking the 32 characteristic parameters as input vectors, the RBF neural network is used to classify and identify earthquake and explosion events. The results show that the recognition rate of the method based on the RBF neural network is 88.1%, which has high accuracy and can be used as an important basis for earthquake and blasting event identification.
Keywords:earthquake discrimination   energy characteristics   RBF neural network
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《地震地磁观测与研究》浏览原始摘要信息
点击此处可从《地震地磁观测与研究》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号