稀疏短时傅里叶变换谱分解方法及应用  

Sparse short-time Fourier transform spectral decomposition method and its application

作　　者：田琳 胡津健 TIAN Lin;HU JinJian(School of Electronic Engineering,Yili Normal University,Yining 835000,China)

机构地区：[1]伊犁师范大学电子与工程学院,伊宁835000

出　　处：《地球物理学进展》2021年第6期2581-2587,共7页Progress in Geophysics

基　　金：国家自然科学基金(61761043);新疆自然科学基金(2016D01C384)和伊犁师范大学博士启动基金项目(2017YSBS07)联合资助。

摘　　要：谱分解是地震资料处理非常重要的方法,传统的谱分解方法具有时频分辨率低等缺点,为了提高谱分解方法的性能,本文提出了基于稀疏约束的短时傅里叶变换时频分析方法.该方法利用地震信号时频域表示的冗余特性,建立地震信号稀疏约束的时频域分析模型,并利用快速投影迭代软阈值投影算法(Projected Fast Iterative Soft-Thresholding Algorithm,pFISTA)求模型的优化解,得到地震信号的稀疏谱分解.本文将pFISTA求解方法引入稀疏时频分析求解方法,并用于实际地震信号谱分解,与传统时频分析方法比较,本文所提方法具有更高的时频分辨率,能给出更准确的频谱信息;本文所提方法能够有效压制地滚噪声;与交错分裂Bregman方法稀疏谱分解方法比较,本文方法运算速度更快.Spectral decomposition is a very important processing technique for seismic data,and the traditional time-frequency analysis method has the disadvantages of low time-frequency resolution and other shortcomings.In order to improve the performance of the spectral decomposition method,this paper proposes a short-time Fourier transform time-frequency analysis method based on the sparse constraints,this method uses redundant characteristics of seismic signal in time-frequency domain,the model is established by the sparse constraint in the time-frequency domain,and use a Projected Fast Iterative Soft-Thresholding Algorithm(pFISTA)to find the optimal solution of the model,the sparse time-frequency distribution of seismic signals is obtained.The sparse time-frequency analysis method proposed in this paper is used for spectral decomposition of real seismic signals,compared with traditional time-frequency analysis methods,this method has the ability to significantly improve the time-frequency resolution,can more accurately descript the reservoir and can also reconstruct the original signal;The method in this paper is applied to suppress the ground roll noise,and the suppressing effect is better,and can achieve better noise suppression effect.Compared with sparse constraints spectral decomposition method based on alternating split Bregman method,the method in this paper is easy and fast to implement.

关 键 词：稀疏约束 谱分解 时频分辨率 噪声压制 

分 类 号：P631[天文地球—地质矿产勘探]