鄂尔多斯盆地长7地层油页岩含油率预测

油页岩的含油率是油页岩工业品质评价中最重要的参数之一,其计算的准确与否直接关系到炼油适宜性的有效确定。鉴于岩心测试成本较高、且不连续等因素,本文充分利用测井资料和含油率室内化验分析资料,在含油率化验分析资料归位的基础上利用现代数理统计方法优选了含油率的敏感性测井参数,采用BP非线性神经网络技术构建了研究区的含油率多测井参数预测模型。含油率预测结果表明,该法能够较好地对研究区内的油页岩含油率进行有效预测,可有效弥补实验室测样的不足,并为利用研究区测井资料进行油页岩工业评价提供了依据。

Predicting Oil Content of Oil Shale in Chang 7 Formation of Ordos Basin

Oil content of oil shale is one of the most important it is directly related to effectively formulating the oil refining parameters in quality evaluation of oil shale industry, suitability that whether the calculation of shale＇s oil content is or not accurate. In view of the high cost of core test, and discontinuous, based on the analysis of log in- formation and laboratory analysis data of oil content, after the laboratory analysis data of oil content are placed the true depth of core, then the sensitivity logging parameters of oil content are optimized adopting modem mathematical statistical methods. The nonlinear BP neural network technology was used to establish the more logging parameter prediction model in the study area. Prediction results of oil content show that the method can effectively predict the oil content of research area, which can effectively make up for the deficiency of the lab test samples, and provide the basis of evaluating oil shale industry in the study area using logging data.