期刊文献+

基于深度学习的GPR时频域联合电磁反演方法 被引量:2

GPR time-frequency domain joint electromagnetic inversion method based on deep learning
下载PDF
导出
摘要 对探地雷达(ground penetrating radar,GPR)数据进行电磁反演可以获得探测区域中目标的几何参数和电磁参数.本文针对GPR时域数据与频域数据在图像域的特征差异,首先设计了基于深度学习的GPR维度变换自编码器提取GPR回波数据的时域特征,并对GPR时频域特征进行一致化处理;然后设计了基于时频融合数据的电磁反演处理框架GPR-EInet,并分别使用2000和200个GPR B-Scan数据对GPR-EInet进行训练和测试.仿真实验结果表明,GPR-EInet可以在SNR=-10 dB、目标介电常数与背景介电常数的相对偏差为50%的情况下实现单/双目标的电磁反演,介电常数反演结果与真实值的结构相似性指数(structure similarity index measure,SSIM)达到了0.99564.分别运用GPR-EInet、ünet与PINet对仿真数据进行电磁反演,结果表明:GPREInet的抗噪性能要优于PINet与ünet.对实测的GPR数据也开展了电磁反演实验,获得了探测区域的目标参数信息.与单独的时域或频域数据反演相比,时频融合数据提升了GPR-EInet的电磁反演精度与噪声抑制能力. The electromagnetic inversion process of ground penetrating radar(GPR)data can obtain geometric parameters and electromagnetic parameters of underground targets.Aiming at the feature differences between GPR time domain data and frequency domain data in the image domain,this paper designs a deep learning-based GPR dimensional transformation auto-encoder to extract GPR B-scan time domain features and perform uniform processing on GPR data features in time domain and frequency domain.A GPR-EInet electromagnetic inversion framework based on time-frequency fusion data is designed.GPR-EInet is composed of a multi-scale feature extractor and a feature reconstructor.The multi-scale feature extractor realizes the fusion and feature extraction of time-frequency domain data,and improves the anti-noise ability of the proposed network.The feature reconstructor realizes the nonlinear mapping between time-frequency fusion feature and the permittivity distribution of the detection area.2000 and 200 GPR BScan data are produced to train and test GPR-EInet respectively.Simulation results show that GPR-EInet can realize single/dual target electromagnetic inversion and the SSIM between GPR-EInet predicted value and real value is 0.99564under the conditions of SNR=-10 dB and the deviation between target dielectric constant and background dielectric constant is 50%.These three deep learning network(GPR-EInet,ünet and PINet)are used to conduct electromagnetic inversion of the simulated data respectively.The results show that the anti-noise performance of GPR-EInet is better than that of PINet andünet.Electromagnetic inversion experiments are also carried out on on-site GPR data.Compared with using time domain data and frequency domain data alone,the time-frequency fusion strategy of GPR-EInet improves the electromagnetic inversion quality and anti-noise ability.
作者 罗诗光 任强 王成浩 宋千 雷文太 LUO Shiguang;REN Qiang;WANG Chenghao;SONG Qian;LEI Wentai(School of Computer Science and Engineering,Central South University,Changsha,410083;China Research Institute of Radiowave Propagation,Qingdao,266107)
出处 《电波科学学报》 CSCD 北大核心 2022年第4期555-567,共13页 Chinese Journal of Radio Science
基金 中国电波传播研究所稳定支持科研经费(A131903W13)。
关键词 探地雷达(GPR) 电磁反演 深度学习 卷积神经网络(CNN) 自编码器 ground penetrating radar(GPR) electromagnetic inversion deep learning convolutional neural network(CNN) auto-encoder
  • 相关文献

参考文献4

二级参考文献15

共引文献132

同被引文献4

引证文献2

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部