Author Login Editor-in-Chief Peer Review Editor Work Office Work

Computer Engineering ›› 2020, Vol. 46 ›› Issue (9): 292-297. doi: 10.19678/j.issn.1000-3428.0056088

• Development Research and Engineering Application • Previous Articles     Next Articles

Method for Positioning of Underground Shallow Hypocenter Based on Deep Learning

XIN Weiyao, LI Jian, WANG Xiaoliang, LI Yujian   

  1. Key Laboratory of Information Detection and Processing of Shanxi Province, North University of China, Taiyuan 030051, China
  • Received:2019-09-23 Revised:2019-11-04 Published:2019-11-12

基于深度学习的地下浅层震源定位方法

辛伟瑶, 李剑, 王小亮, 李禹剑   

  1. 中北大学 信息探测与处理山西省重点实验室, 太原 030051
  • 作者简介:辛伟瑶(1995-),女,硕士研究生,主研方向为信号处理、定位算法;李剑,副教授;王小亮、李禹剑,硕士研究生。
  • 基金资助:
    国家自然科学基金青年科学基金(61901419);山西省面上青年科学基金(201801D221205);山西省高校创新项目(201802083)。

Abstract: To address the problem that the energy focus in the underground energy field focusing model cannot be effectively identified,this paper proposes a method for positioning of underground shallow hypocenter on the basis of deep learning.The method uses inverse time amplitude superposition to reconstruct the vibration data obtained by the sensor array into a sample sequence of massive three-dimensional energy field images,which is then used as the input data of the deep learning network.The 3D-CNN model is used to build a deep learning network framework.The coordinates of known hypocenters are used as input labels during the preliminary training,and the above obtained data and labels are input into the network for training and testing,so as to form a learning model that maps the three-dimensional energy field to the hypocenter coordinates.Then the model outputs the coordinates of focal points,that is,the hypocenter coordinates.Results of the experiments show that the proposed method can effectively identify the focal points of the energy field,and can be applied to the field of positioning of underground shallow hypocenter.

Key words: positioning of underground shallow, inverse time focusing, amplitude superposition, image sequence of three-dimensional energy field, deep learning

摘要: 针对地下能量场聚焦模型中能量聚焦点无法有效识别的问题,在深度学习的基础上,提出一种地下浅层震源定位方法。利用逆时振幅叠加的方法将传感器阵列获取的震动数据逆时重建为三维能量场图像样本序列,并将其作为深度学习网络的输入数据。采用3D-CNN模型搭建深度学习网络框架,在前期训练时将已知震源坐标作为输入标签,且将获取的数据和标签输入到网络中进行训练测试,形成三维能量场到震源坐标的端到端学习模型,并输出聚焦点坐标,即震源坐标。实验结果表明,该方法能够有效识别能量场聚焦点,适用于地下浅层震源定位领域。

关键词: 地下浅层定位, 逆时聚焦, 振幅叠加, 三维能量场图像序列, 深度学习

CLC Number: