改进的神经网络反演微动面波频散曲线

J4 ›› 2011, Vol. 41 ›› Issue (3): 900-906.

改进的神经网络反演微动面波频散曲线

周晓华¹|林君¹|陈祖斌¹|焦健¹|郭同健²

1.吉林大学仪器科学与电气工程学院|长春130026;2.中国科学院长春光学精密机械与物理研究所|长春130033

收稿日期:2010-07-01 出版日期:2011-05-26 发布日期:2011-05-26
作者简介:周晓华(1981-)|女|内蒙古集宁人,讲师,博士,主要从事微动勘探技术等方面的研究|E-mail:zhouxiaohua@jlu.edu.cn
基金资助:
中央高校基本科研业务费专项基金项目（421033784537）

Iterative Inversion of Microtremor Surface Wave Dispersion Curves by Improved Neural Network

ZHOU Xiao-hua¹|LIN Jun¹|CHEN Zu-bin¹|JIAO Jian¹|GUO Tong-jian²

1.College of Instrumentation and Electrical Engineering, Jilin University, Changchun130026,China;
2.Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun130033, China

Received:2010-07-01 Online:2011-05-26 Published:2011-05-26

摘要/Abstract

摘要：

通过分析微动探查方法和改进神经网络迭代反演算法，提出采用改进的神经网络迭代反演微动面波频散曲线。该方法在网络训练学习阶段通过批处理学习和优化网络结构提高网络学习速度；在迭代反演阶段通过v_R/λ_R-f曲线极值点的变化来调整输入模型以减少迭代反演次数；最后设计反演方案，并对6层介质模型进行频散曲线的网络训练和迭代反演，验证了方法的有效性。对比分析结果表明：该方法明显减少了迭代反演次数，提高了收敛速度，而且具有良好的抗干扰能力。

关键词: 改进BP神经网络, 微动, 频散曲线, 面波, 迭代反演

Abstract:

An iterative inversion of microtremor surface wave dispersion curves by improved neural network is proposed. The learning speed is improved by batch processing and optimizing the network structure in network training. In order to reduce the iteration number of the inversion, the input model is adjusted according to the changes of the extreme points of v_R/λ_R-f curve during the inversion. The inversion program is designed and applied to the inversion of dispersion curve from a six-layer model to validate the method. The results show that the method can reduce the iteration number significantly and improve the convergence rate, while is of good anti-noise capability.

Key words: improved BP neural networks, microtremor, dispersion curve, surface waves, iterative inversion

中图分类号:

P315.4

周晓华, 林君, 陈祖斌, 焦健, 郭同健. 改进的神经网络反演微动面波频散曲线[J]. J4, 2011, 41(3): 900-906.

ZHOU Xiao-hua, LIN Jun, CHEN Zu-bin, JIAO Jian, GUO Tong-jian. Iterative Inversion of Microtremor Surface Wave Dispersion Curves by Improved Neural Network[J]. J4, 2011, 41(3): 900-906.

参考文献

相关文章 7

[1]	崔永福, 李国发, 吴国忱, 尚帅, 赵锐锐, 罗莉莉. 基于面波模拟和曲波变换的去噪技术[J]. 吉林大学学报(地球科学版), 2016, 46(3): 911-919.
[2]	高成, 孙建国. 不同域的局部平面波分解应用与对比[J]. 吉林大学学报(地球科学版), 2015, 45(5): 1523-1529.
[3]	李庆春，吴华，周学明. 路基下伏地质缺陷弹性波数值模拟[J]. 吉林大学学报(地球科学版), 2014, 44(6): 2016-2025.
[4]	周晓华, 陈祖斌, 曾晓献, 焦健. 交错网格有限差分法模拟微动信号[J]. J4, 2012, 42(3): 852-857.
[5]	马见青, 李庆春. 面波压制的TT变换法[J]. J4, 2011, 41(2): 565-571.
[6]	郝奇, 何樵登, 王德利. 用改进的摄动理论研究各向异性弱粘弹性介质中的非均匀平面波[J]. J4, 2010, 40(1): 195-202.
[7]	张晨，陈剑平,肖云华. 基于神经网络对有限元强度折减法分析[J]. J4, 2009, 39(1): 114-0118.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed