吉林大学学报(工学版) ›› 2015, Vol. 45 ›› Issue (6): 2026-2033.doi: 10.13229/j.cnki.jdxbgxb201506042

• • 上一篇    下一篇

PSBP在高密度电阻率法二维反演中的应用

高明亮, 于生宝, 郑建波, 徐畅, 张堃, 栾卉   

  1. 吉林大学 仪器科学与电气工程学院,长春 130026
  • 收稿日期:2014-08-28 出版日期:2015-11-01 发布日期:2015-11-01
  • 通讯作者: 栾卉(1979-),女,副教授,博士.研究方向:高密度电法勘探反演.E-mail:luanhui@jlu.edu.cn
  • 作者简介:高明亮(1987-),男,博士研究生.研究方向:高密度电法勘探非线性反演.E-mail:mlgao13@mails.jlu.edu.cn
  • 基金资助:
    公益性行业科研专项项目(201011079-05)

Application of PSBP method in high-density two-dimensional resistivity inversion

GAO Ming-liang, YU Sheng-bao, ZHENG Jian-bo, XU Chang, ZHANG Kun, LUAN Hui   

  1. College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130026, China
  • Received:2014-08-28 Online:2015-11-01 Published:2015-11-01

摘要: 针对神经网络算法在非线性反演中容易陷入局部极小、收敛慢、反演精度差等问题,提出了将粒子群优化(Particle swarm optimization)算法与BP神经网络(Back propagation neural networks)进行混合反演(简称PSBP)。最后,通过经典的地电模型对本文方法的有效性进行验证,结果表明,本文方法与线性反演方法、BP神经网络反演方法对比,具有明显的优势,并取得了很好的反演结果。

关键词: 固体地球物理学, 粒子群算法, BP神经网络, 高密度电阻率法, 反演精度

Abstract: In nonlinear inversion, neural network algorithm has the shortcomings of easy to fall into local minimum, slow convergence and poor inversion accuracy. To overcome these shortcomings, the Particle Swarm Optimization (PSO) is combined with Back Propagation (BP) neural network to achieve inversion (referred as PSBP). The effectiveness of the PSBP is verified by the classical geoelectric model. Compared with the linear inversion and BP neural network inversion methods, the proposed PSBP method has obvious advantages with good inversion result.

Key words: solid geophysics, particle swarm optimization, BP neural networks, high-density resistivity method, inversion accuracy

中图分类号: 

  • P319.3
[1] 徐海浪,吴小平. 电阻率二维神经网络反演[J].地球物理学报,2006,49(2):584-589.
Xu Hai-lang,Wu Xiao-ping. 2D resistivity inversion using the neural network method[J]. Chinese Journal of Geophysics,2006,49(2):584-589.
[2] Singh U K,Tiwari R K,Singh S B. One-dimensional inversion of geo-electrical resistivity sounding data using artificial neural networks-a case study[J]. Computers & Geosciences,2005,31(1): 99-108.
[3] 赵丁选,崔功杰,陈宁,等. 基于BP神经网络的工程车辆四参数自动变速控制[J]. 吉林大学学报:工学版,2008,38(5):1091-1094.
Zhao Ding-xuan,Cui Gong-jie,Chen Ning,et al. Engineering vehicle four parameters automatic speed control based on BP neural network[J]. Journal of Jilin University (Engineering and Technology Edition),2008,38(5):1091-1094.
[4] 司建波,杨芳,郭蔚莹,等. 基于BP神经网络两阶段疾病预测模型[J]. 吉林大学学报:工学版,2013,43(Sup.1):481-484.
Si Jian-bo,Yang Fang,Guo Wei-ying,et al. The two stage of the disease prediction model based on BP neural network[J]. Journal of Jilin University(Engineering and Technology Edition),2013,43(Sup.1):481-484.
[5] 刘杰,孙吉贵,李红建,等.基于BP神经网络的气囊点火算法模型[J]. 吉林大学学报:工学版,2008,38(2):414-418.
Liu Jie,Sun Ji-gui,Li Hong-jian,et al. Airbag ignition algorithm model based on BP neural network[J]. Journal of Jilin University (Engineering and Technology Edition),2008,38(2):414-418.
[6] 王家映. 地球物理资料非线性反演方法讲座(五)——人工神经网络反演法[J].工程地球物理学报,2008,5(3):255-265.
Wang Jia-ying. The lecture of nonlinear inversion methods in geophysics (the fifth)-artificial neural network inversion method[J]. Chinese Journal of Engineering Geophysics,2008,5(3):255-265.
[7] 齐龙,马旭,张小超. 基于BP神经网络的植物病害彩色图像的分割技术[J]. 吉林大学学报:工学版,2006,36(Sup.2):126-129.
Qi long,Ma Xu,Zhang Xiao-chao. Plant disease image segmentation technology based on BP neural network[J]. Journal of Jilin University (Engineering and Technology Edition),2006,36(Sup.2):126-129.
[8] 冷欣,朱齐丹. 基于径向基函数神经网络动态补偿的船用增压锅炉汽包水位多模型预测控制[J]. 吉林大学学报:工学版,2011,41(5):1450-1455.
Leng xin,Zhu Qi-dan. Prediction and control of ship model with the water level of the steam drum boiler based on radial basis function neural network dynamic compensation[J].Journal of Jilin University (Engineering and Technology Edition),2011,41(5):1450-1455.
[9] Stephen J, Manoj C,Singh S B. A direct inversion seheme for deep resistivity Sounding data using artificial neural networks[J]. Journal of Earth System Science,2004,113(1):49-66.
[10] Neyamadpour A,Taib S,Abdullah W A T W. Using artificial neural networks to invert 2D DC resistivity imaging data for high resistivity contrast regions: A MATLAB application[J]. Computers & Geosciences,2009,35(11):2268-2274.
[11] El-Qady G,Ushijima K. Inversion of DC resistivity data using neural networks[J]. Geophysical Prospecting,2001,49(1):417-430.
[12] 张凌云,刘鸿福.ABP法在高密度电阻率法反演中的应用[J].地球物理学报,2011,54(1):227-233.
Zhang Ling-yun,Liu Hong-fu. The application of ABP method in high-density resistivity method inversion[J]. Chinese Journal of Geophysics,2011,54(1):227-233.
[13] 巩明德,赵丁选,宫文斌,等. 基于神经网络的电液伺服机械手位置控制[J]. 吉林大学学报:工学版,2002,32(3):15-19.
Kong Ming-de,Zhao Ding-xuan,Gong Wen-bin,et al. Position control of electro mechanical manipulator based on neural network[J]. Journal of Jilin University (Engineering and Technology Edition),2002,32(3):15-19.
[14] 逢泽芳,韩红桂,乔俊飞. 基于神经网络的污水处理预测控制[J]. 吉林大学学报:工学版,2011,41(Sup.1):280-284.
Feng Ze-fang,Han Hong-gui,Qiao Jun-fei. Sewage treatment predictive control based on neural network[J]. Journal of Jilin University (Engineering and Technology Edition),2011,41(Sup.1):280-284.
[15] 贾鹤鸣,宋文龙,郭婧. 基于神经网络滑膜的采摘机械臂控制设计[J]. 吉林大学学报:工学版,2012,42(3):709-713.
Jia He-ming,Song Wen-long,Guo Jing. The design of picking manipulator control based on neural network synovial[J]. Journal of Jilin University(Engineering and Technology Edition),2012,42(3):709-713.
[16] 吴清佳. 基于神经网络集成的旋转人脸快速检测系统[J]. 吉林大学学报:工学版,2013,43(Sup.1):424-429.
Wu Qing-jia. Rotating face fast detection system based on neural network ensemble[J]. Journal of Jilin University(Engineering and Technology Edition),2013,43(Sup.1):424-429.
[17] 王改革,郭立红,段红,等. 基于萤火虫算法优化BP神经网络的目标威胁估计[J]. 吉林大学学报:工学版,2013,43(4):1064-1069.
Wang Gai-ge,Guo Li-hong,Duan Hong,et al. Target threat estimation based on the firefly algorithm optimizing BP neural network[J]. Journal of Jilin University (Engineering and Technology Edition),2013,43(4):1064-1069.
[18] 侯阿临,廖庆,靳志娟,等.计算全息图的人工神经网络压缩算法[J]. 吉林大学学报:工学版,2013,43(Sup.1):21-24.
Hou A-lin,Liao Qing,Jin Zhi-juan,et al. Artificial neural network compression algorithm calculating hologram[J]. Journal of Jilin University (Engineering and Technology Edition),2013,43(Sup.1):21-24.
[19] 戴逸松,陈贺新,郭殿龙,等. 人工神经网络的研究及在计算机视觉中的应用[J]. 吉林工业大学学报,1991(2):102-110.
Dai Yi-song,Chen He-xin,Guo Dian-long,et al. The research of artificial neural network and its application in computer vision[J]. Journal of Jilin University of Technology,1991(2):102-110.
[20] 王芳荣,阚如文,王昕,等. 无人水下航行器PID神经网络解耦控制[J]. 吉林大学学报:工学版,2012,42(Sup.1):387-391.
Wang Fang-rong,Kan Ru-wen,Wang Xin,et al. PID neural network decoupling control of unmanned underwater vehicle[J]. Journal of Jilin University(Engineering and Technology Edition),2012,42(Sup.1):387-391.
[21] Kennedy J,Eberhart R. Particle swarm optimization[C]∥Proceeding of IEEE International Conference on Neural Networks, Perth,Australia,1995:1942-1948.
[22] Eberhart R,Kennedy J. A new optimizer using particle swarm theory[C]∥Proceedings of the Sixth International Symposium on Source,1995:39-43.
[23] Kennedy J,Eberhart R C. A discrete binary version of the particle swarm algorithm[C]∥1997 IEEE International Conference on Systems, Man, and Cybernetics, Orlando, FL,1997:4104-4109.
[24] Clerc M. Discrete particle swarm optimization illustrated by the travelling salesman problem[EB/OL].[2014-07-03].http://www.mauriceclerc.net,2000.
[25] 张大莲,刘天佑,陈石羡,等. 粒子群算法在磁测资料井地联合反演中的应用[J].物探与化探,2009,33(5):571-575.
Zhang Da-lian,Liu Tian-you,Chen Shi-xian,et al. The application of particle swarm algorithm in joint inversion of Borehole magnetic data[J]. Geophysical and Geochemical Exploration,2009,33(5):571-575.
[26] 刘顺安,胡庆玉. PSO-BP网络算法在汽车悬架优化中的应用[J]. 吉林大学学报:工学版,2009,39(3):571-575.
Liu Shun-an,Hu Qing-yu. Application of PSO-BP network algorithm in optimization of automotive suspension[J]. Journal of Jilin University (Engineering and Technology Edition),2009,39(3):571-575.
[27] 周立军,王殿海,李卫青. 人工神经网络及粒子群优化算法在跟驰模型中的应用[J]. 吉林大学学报:工学版,2009,39(4):896-899.
Zhou Li-jun,Wang Dian-hai,Li Wei-qing. The application of artificial neural network and particle swarm optimization algorithm in the following model[J]. Journal of Jilin University (Engineering and Technology Edition),2009,39(4):896-899.
[1] 臧国帅, 孙立军. 基于惰性弯沉点的刚性下卧层深度设置方法[J]. 吉林大学学报(工学版), 2018, 48(4): 1037-1044.
[2] 刘东亮, 王秋爽. 基于NGSIM数据的车辆瞬时速度获取方法[J]. 吉林大学学报(工学版), 2018, 48(1): 330-335.
[3] 于繁华, 刘仁云, 张义民, 张晓丽, 孙秋成. 机械零部件动态可靠性稳健优化设计的群智能算法[J]. 吉林大学学报(工学版), 2017, 47(6): 1903-1908.
[4] 江海宇, 刘玉海, 孙海林, 徐克彬, 白田增, 陈祖斌. 微地震地面监测层状起伏速度模型校正算法[J]. 吉林大学学报(工学版), 2017, 47(6): 1969-1975.
[5] 王德军, 吕志超, 王启明, 张贤达, 王子健. 基于汽缸压力辨识的发动机失火故障诊断[J]. 吉林大学学报(工学版), 2017, 47(3): 917-923.
[6] 黄璇, 郭立红, 李姜, 于洋. 改进粒子群优化BP神经网络的目标威胁估计[J]. 吉林大学学报(工学版), 2017, 47(3): 996-1002.
[7] 孙亮, 徐海浪, 葛宏伟. 保证全局收敛的随机粒子群新算法[J]. 吉林大学学报(工学版), 2017, 47(2): 615-623.
[8] 郭应时, 付锐, 赵凯, 马勇, 袁伟. 驾驶人换道意图实时识别模型评价及测试[J]. 吉林大学学报(工学版), 2016, 46(6): 1836-1844.
[9] 张静, 刘向东. 混沌粒子群算法优化最小二乘支持向量机的混凝土强度预测[J]. 吉林大学学报(工学版), 2016, 46(4): 1097-1102.
[10] 于繁华, 刘仁云, 张义民, 孙秋成, 张晓丽. 机械结构动态可靠性设计的智能计算方法[J]. 吉林大学学报(工学版), 2016, 46(4): 1269-1275.
[11] 季彦婕, 陈晓实, 王炜, 胡波. 基于小波变换和粒子群小波神经网络组合模型的有效停车泊位短时预测[J]. 吉林大学学报(工学版), 2016, 46(2): 399-405.
[12] 李寿涛, 田微, 郭鹏程, 马用学, 张浩, 王楠. 基于模糊自适应的BP神经网络动态行驶车辆车长测算[J]. 吉林大学学报(工学版), 2015, 45(6): 1881-1886.
[13] 刘红,孙爽滋,王庆元,李延忠. 基于PSO的模拟电路故障信息特征提取[J]. 吉林大学学报(工学版), 2015, 45(2): 675-680.
[14] 闫楚良, 郝云霄, 刘克格. 基于遗传算法优化的BP神经网络的材料疲劳寿命预测[J]. 吉林大学学报(工学版), 2014, 44(6): 1710-1715.
[15] 陈莉, 孙永海, 付天宇, 丁健峰. 羊肚菌胞外多糖快速估测方法[J]. 吉林大学学报(工学版), 2014, 44(2): 567-572.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!