论文部分内容阅读
本文系统分析ΔLogR技术应用于复杂岩性致密层有机质评价中存在两方面的局限性:参数选取方面,测井曲线选取过于单一,无法有效削弱致密层段复杂岩性和孔隙度等因素对计算有机碳含量的影响;构建模型方面,人为剔除异常点存在随机性与偶然性误差,影响建模准确性.针对上述问题,本文建立了BP神经网络模型,并将其应用于柳河盆地柳参1井下桦皮甸子组烃源岩有机质评价.研究结果表明,在不剔除异常点情况下,BP神经网络模型计算TOC值和实测116组TOC值相关性达到0.886,显示建模效果良好.分别应用BP神经网络和ΔLogR模型,计算研究区致密层纵向上连续的TOC曲线,BP神经网络模型的计算TOC曲线与实测TOC数据基本吻合,而ΔLogR模型的计算TOC曲线吻合度较差.因此在测井资料完善的情况下,本文建议使用BP神经网络评价复杂岩性的致密层有机质.
This paper systematically analyzed the application of ΔLogR in the evaluation of organic matter in complex lithologic tight layers. There are two limitations in the application of ΔLogR to the evaluation of organic matter in complex lithologic tight layers. In terms of parameter selection, the selection of logging curves is too simple to effectively weaken the complex lithology and porosity of the tight intervals. Carbon content.About the model building, there are random and accidental errors in removing abnormal points, which affect the accuracy of modeling.According to the above problems, a BP neural network model is established in this paper and applied to the Betula vulgaris The results show that the correlation between the TOC value of the BP neural network model and the measured TOC value of the 116 groups reaches 0.886 without removing the abnormal point, which shows that the model has a good effect.The BP neural network And ΔLogR model to calculate the continuous TOC curve in the longitudinal direction of the dense layer in the study area.The calculated TOC curve of the BP neural network model is in good agreement with the measured TOC data and the TOC curve of the ΔLogR model is less consistent.Therefore, In this case, we propose to use BP neural network to evaluate the compacted layer organic matter in complex lithology.