时域与频域自适应SVD融合去噪算法  

An Adaptive SVD Fusion Denoising Algorithm in Time and Frequency Domain

作　　者：高磊[1] 夏星 闵帆[1] GAO Lei;XIA Xing;MIN Fan(School of Computer Science,Southwest Petroleum University,Chengdu 610500,China)

机构地区：[1]西南石油大学计算机科学学院,四川成都610500

出　　处：《郑州大学学报（理学版）》2023年第6期48-54,共7页Journal of Zhengzhou University:Natural Science Edition

基　　金：国家自然科学基金项目(41604114)。

摘　　要：时域方法在地震同相轴倾斜或弯曲时,难以保证去噪的有效性;频域方法在信号频带较宽时,会衰减过多信号。基于此,提出一种时域与频域自适应奇异值分解(singular value decomposition,SVD)融合去噪算法。该算法包含分解与融合技术:在分解技术中,根据奇异值二阶差分谱,在时域与频域中分别进行自适应去噪,得到两个分解矩阵;在融合技术中,提出了用于评估分解矩阵的一致度,利用融合策略得到融合矩阵,最后根据局部相似性调整得到去噪矩阵。在合成与野外数据集上与一些算法进行了对比实验,结果表明,所提算法能够更有效地压制噪声。Time-domain methods were difficult to ensure the effectiveness of denoising when the seismic event was tilted or curved,and frequency-domain methods attenuated too much signal when the signal frequency band was wide.Based on this,an adaptive singular value decomposition(SVD)fusion denoising algorithm in time and frequency domain was proposed.The algorithm included both decomposition and fusion techniques.In the decomposition technique,adaptive denoising was performed in the time and frequency domain respectively according to the second-order difference spectrum of singular values,and two decomposition matrices were obtained.In the fusion technique,the degree of consistency for evaluating the decomposition matrix was proposed,and then the fusion matrix was obtained by using the fusion strategy.Finally,the denoising matrix was obtained,which was adjusted according to the local similarity.Compared with some algorithms on synthetic and field datasets,the results showed that the proposed algorithm could suppress noise more effectively.

关 键 词：地震数据 去噪 融合算法 奇异值分解 自适应 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]