利用测井曲线反褶积方法提高薄层识别能力

Improve thin beds discrimination using the log curves deconvolution method

针对老油田早期测井曲线垂向分辨率难以满足地质精细研究需要的问题,将信号反褶积原理应用于测井曲线处理。通过将反褶积问题转化为期望输出与实际输出的误差极值问题构造线性方程组,求解方程组得到反褶积因子,从而实现测井曲线的盲反褶积处理。通过处理,消除了围岩等因素的影响,对测井曲线上低幅度的细微变化产生了"放大"效应,这种效应在单层厚度0.5 m左右的砂泥岩薄互层地层中体现最为明显,同时该处理对测井曲线斜率的微小变化反映更加灵敏。实际测井资料处理前后的频谱对比表明,该方法增强了测井曲线高频段能量,提高了测井曲线对沉积界面,尤其是薄互层界面的识别能力,通过取心井资料检验,验证了反褶积处理结果的地质意义合理性。

In mature oil fields,vertical resolution of early log curves is not high enough for the characterization of thin beds and doesn＇t meet the demand of delicate geologic research.Aimed at this problem,the process of blind deconvolution for log curves is developed.The algorithm of this method is： form linear equations by transforming the problem of deconvolution into an extreme value problem between the expected and actual output signals,and then get the deconvolution factor by solving the equations.By this process,the influences of surrounding rocks are wiped,the energy of high frequency band in frequency spectrum is improved,the new curve is more sensitive to the variance of curve slope,low amplitude variances of curves are zoomed in and the characteristics of sedimentary surfaces are more distinct.The identification ability of processed log curves in thin beds interpretation,especially in alternating beds with single beds about 0.5 m thick,is improved after the deconvolution process.The geological rationality of deconvolution process is verified by research with cored well data.