主成分分析法在泥页岩地层岩性识别中的应用

Application of principal component analysis method in lithology identification for shale formation

 刘毅 陆正元 吕晶 谢润成

 （成都理工大学油气藏地质及开发国家重点实验室，四川 成都 610059）

 (State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu University of Technology, Chengdu 610059, China)

 泥页岩地层岩性复杂，非均质性强，利用常规测井交会图法识别岩性往往具有多解性和不确定性。依据主成分分析理论，建立多条测井曲线的主成分计算模型，主成分Y1，Y2，Y3的累积方差贡献率可达91.39%，能够准确反映原测井曲线的全部有效信息。研究结果表明，主成分分析法能够有效识别泥页岩地层的浅灰色泥岩、黑色泥岩、灰色粉砂岩及细砂岩等多种岩性，回判率达90.37%。与常规测井交会图法相比，主成分分析法可靠性更高，在泥页岩储层研究领域具有较广泛的应用前景。

 With the complex and strong anisotropy lithology of shale, conventional log crossplot method to identify lithology tends to have multiple solutions and uncertainty. According to principal component analysis theory, the principal component calculation model of multi?-well logging was set up. The cumulative variance contribution rate of Y1，Y2，Y3 is 91.39%, the total effective information of 6 logging curves can be responded. The results show that principal component analysis method can effectively identify black mudstone, black carbonaceous mudstone, grey siltstone and fine sandstone. The recognition rate is 90.37%. Comparing with the conventional logging crossplot method, the principal component analysis method has a higher reliability, which can widely be used for shale reservoir research.

10.6056/dkyqt201703014