摘要
对层状介质中各弹性参数对频散曲线的影响进行了探讨,研究了vR-λR频散曲线拐点的变化情况,提出了应用人工神经网络反演瑞利波频散曲线的问题.针对3层固体介质模型进行了频散曲线的网络训练和网络反演,验证了方法的有效性.研究发现:介质的横波速度和介质层的厚度对频散曲线的影响较大,用拐点法对地层进行分层缺乏理论依据,利用人工神经网络的方法可对瑞利波频散曲线进行反演,但反演训练费时,精度也需进一步研究.
Studied the influence of elastic parameters on Rayleigh dispersion curves, and also studied the inflexion movement of VR - A R dispersion curves with parameters＇ change. And then, the inversion method of artificial neural network was put forward for dispersion curves＇ inversion, and practical application was used to test the validity of the inversion method. According to the studied results, influence of velocities of transverse waves and thicknesses of media on dispersion curves is bigger. It has not a theoretic gist to delaminate by inflexions in Rayleigh waves＇ inversion. The artificial network method can interpret the dispersion curves, but it consumes time and the precision is low, and this method must be further studied in the future.
出处
《煤炭学报》
EI
CAS
CSCD
北大核心
2008年第10期1097-1101,共5页
Journal of China Coal Society
基金
国家自然科学基金重点基金资助项目(50534080)
国家重点基础研究发展计划(973)资助项目(2005CB221505)
关键词
瑞利波
频散曲线
反演
人工神经网络
拐点法
Rayleigh waves
dispersion curves
inversion
artificial neural network
inflexion method
