基于独立分量分析的多次波自适应相减技术

ADAPTIVE MULTIPLE WAVE SUBTRACTION USING INDEPENDENT COMPONENT ANALYSIS

针对多次波自适应相减这个关键问题 ,文中首次提出利用独立分量分析技术来实现多次波和一次波的分离 (简称ICAAMS) .现有的多次波自适应相减技术大都是采用输出信号 (一次波 )能量最小准则 ,基于二阶统计量的技术 .本文提出的ICAAMS采用了输出信号非高斯性最大准则 ,并利用高阶统计量来表征非高斯性 .简单的褶积模型和复杂的有限差分模型资料处理结果表明 ,本文提出的方法可以有效地分离一次波和多次波 .

We present a new adaptive multiple subtraction algorithm based on independent component analysis (ICAAMS). The output energy minimum criterion, which is adopted by almost all the existing adaptive multiple subtraction methods, is based on second order statistics. The method proposed in this paper maximizes the nongaussianity of the output signal, which can be measured by higher order statistics. The method has been applied to several synthetic datasets generated by simple convolution and finite-difference model (FDM) technique, and the results show that our method can separate primary wave and multiple wave effectively.