改进型粒子群算法及其在GPR全波形反演中的应用  

Improved particle swarm optimization and its application to full-waveform inversion of GPR

作　　者：戴前伟[1,2] 陈威 张彬[1,2] DAI Qian-Wei;CHEN Wei;ZHANG Bin(School of Geosciences and Info-Physics,Central South University,Changsha 410083,China;Key Laboratory of Metallogenic Prediction of Nonferrous Metal and Geological Environment Monitoring,Ministry of Education,Central South University,Changsha 410083,China)

机构地区：[1]中南大学地球科学与信息物理学院,湖南长沙410083 [2]中南大学有色金属成矿预测与地质环境监测教育部重点实验室,湖南长沙410083

出　　处：《物探与化探》2019年第1期90-99,共10页Geophysical and Geochemical Exploration

基　　金：国家自然科学基金项目(41704128;41874148);中国博士后科学基金项目(2018M632992);湖南省自然科学基金项目(2018JJ3636)

摘　　要：探地雷达作为高精度的物探工作方法,其主要目的是反演解释地下结构的物性参数。笔者提出社会学习型粒子群优化反演方法,它以信号均方误差为目标函数,用时域有限差分方法作正演,并且针对反射波信号较弱、反演效果不佳的情况设计了对正演结果进行振幅补偿的方法,对反射波的振幅进行增益,以提高反演精度。通过与经典粒子群优化反演方法的结果对比,说明了该算法在准确度以及效率方面都有相当大的提高。经过分析多层介质仿真数据的一维反演结果,说明了该算法对多参数反演的有效性和良好的抗噪性。Ground penetrating radar (GPR) is a high-precision geophysical exploration method whose main purpose is to invert the physical properties of underground structures.In this paper,an improved particle swarm optimization (PSO) is used to solve GPR inverse problem.The inversion takes the signal mean square error as the objective function and uses the finite-difference time-domain method to do forward modeling.In addition,the inversion accuracy is improved by the amplitude compensation of the forward result.Compared with the results based on classical particle swarm optimization inversion method,the algorithm shows considerable improvement in accuracy and efficiency.An analysis of the one-dimensional inversion results of multi-layer simulation data shows that the inversion method is effective for multi-parameter inversion and has good noise immunity.

关 键 词：粒子群优化 探地雷达 反演 振幅补偿 

分 类 号：P631[天文地球—地质矿产勘探]