自然科学版 英文版
自然科学版 英文版
自然科学版 英文版
自然科学版 英文版
英文版编委
自然科学版 英文版
英文版首届青年编委

您目前所在的位置:首页 - 期刊简介 - 详细页面

中南大学学报(自然科学版)

Journal of Central South University

第51卷    第8期    总第312期    2020年8月

[PDF全文下载]    [Flash在线阅读]

    

文章编号:1672-7207(2020)08-2162-12
基于改进粒子群深度神经网络的频率域航空电磁反演
廖晓龙1,张志厚1,范祥泰1,路润琪1,姚禹1,曹云勇2,徐正宣1, 2

(1. 西南交通大学 地球科学与环境工程学院,四川 成都,611756;
2. 中铁二院成都地勘岩土工程有限责任公司,四川 成都,610000
)

摘 要: 传统的梯度反演方法依赖于初始模型选取,且容易陷入局部极小,在一定程度上影响着反演的求解精度和收敛速度,为此,提出一种基于改进粒子群深度神经网络的频率域航空电磁反演方法。首先,通过频率域航空电磁模型正演获取样本数据集;随后,依据样本数据集建立深度神经网络的基本框架,网络的输入为归一化垂直磁场分量,输出为相应地电模型参数;第三,提出一种惯性权重振荡衰减措施在粒子群优化算法的基础上进行改进,以提高粒子群优化算法的全局寻优能力,并利用改进的粒子群优化算法优化深度神经网络的训练过程,得到连接权值与阈值的最优解;最后,将最优的权值与阈值作为网络的初始值,并利用该网络对未知地电模型进行反演测试。利用层状地质模型测试改进粒子群深度神经网络算法、粒子群神经网络算法和单一的神经网络算法的反演效果,并将此方法运用于实测航空电磁数据反演。研究结果表明:本文提出的改进粒子群神经网络算法充分结合了粒子群优化算法的全局寻优性能和深度神经网络的局部寻优性能,在反演过程中能有效避免反演陷入局部极小,寻找到全局最优解,并能准确地反演出地电模型参数;与粒子群神经网络算法和单一的神经网络算法相比,本文提出的方法具有更高的求解精度和收敛速度。

 

关键词: 航空电磁;频率域;反演;改进粒子群优化算法;深度神经网络

Frequency domain airborne EM inversion based on improved particle swarm depth neural network
LIAO Xiaolong1, ZHANG Zhihou1, FAN Xiangtai1, LU Runqi1, YAO Yu1, CAO Yunyong2, XU Zhengxuan1, 2

1. Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China;
2. Chengdu Geological Survey Geotechnical Engineering Co., Ltd. Chengdu 610000, China

Abstract:The traditional gradient inversion depends on the selection of initial model and is easy to fall into local minimum, which affects the accuracy and convergence speed of inversion to a certain extent. To solve the problems, a frequency domain airborne EM inversion method based on an improved particle swarm deep neural network was proposed. Firstly, a large number of sample data sets were obtained through model forward modeling. Secondly, the basic framework of the deep neural network was established based on the data sets. The network input was the normalized vertical magnetic field component and the output was the corresponding electrical model parameters. Thirdly, an inertial weight oscillation attenuation method was proposed to improve the global optimization ability of particle swarm optimization algorithm, and the swarm algorithm optimizes the training process of the deep neural network to obtain the optimal solution of the connection weights and thresholds. Finally, the optimal weights and thresholds were used as the initial values of the network which were used to perform inversion tests on the unknown geoelectric model. In this paper, the inversion results of the improved particle swarm deep neural network algorithm(IPSO-DNN), the particle swarm deep neural network algorithm(PSO-DNN) and the single deep neural network algorithm(DNN) were tested by layered geological model, and this method was applied to inversion of measured aeromagnetic data. The results show that the improved particle swarm neural network algorithm can make full use of the global searching capability of particle swarm optimization and the local optimization of deep neural network. In the process of inversion, it can effectively prevent the inversion from falling into the local minimum, find the global optimal solution and accurately reverse the parameters of geoelectric model. Compared with the particle swarm neural network and a single neural network inversion method, this method has higher accuracy and convergence speed.

 

Key words: airborne EM; frequency domain; inversion; improved particle swarm algorithm; deep neural network(DNN)

中南大学学报(自然科学版)
  ISSN 1672-7207
CN 43-1426/N
ZDXZAC
中南大学学报(英文版)
  ISSN 2095-2899
CN 43-1516/TB
JCSTFT
版权所有:《中南大学学报(自然科学版、英文版)》编辑部
地 址:湖南省长沙市中南大学 邮编: 410083
电 话: 0731-88879765(中) 88836963(英) 传真: 0731-88877727
电子邮箱:zngdxb@csu.edu.cn 湘ICP备09001153号