基于支持向量机的浊积扇低渗透储层流动单元研究  

Study on Flow Units of Turbidite Fan Low Permeability Reservoir Based on Support Vector Machine

作　　者：徐守余[1,2] 路研 王亚 Xu Shouyu;Lu Yan;Wang Ya(School of Geosciences,China University of Petroleum(East China),Qingdao 266580,China;Laboratory for Marine Mineral Resources,Qingdao National Laboratory for Marine Science and Technology, Qingdao 266071,Shandong,China)

机构地区：[1]中国石油大学(华东)地球科学与技术学院,山东青岛266580 [2]海洋国家实验室海洋矿产资源评价与探测技术功能实验室,山东青岛266071

出　　处：《吉林大学学报（地球科学版）》2018年第5期1330-1341,共12页Journal of Jilin University：Earth Science Edition

基　　金：国家科技重大专项(2017ZX05009001);国家自然科学基金面上项目(41772138)~~

摘　　要：由于浊积扇储层成因机制的复杂性,本文通过因子分析从反映储层岩石物理特征、微观孔隙结构特征、储层沉积特征及储层非均质特征的13个储层参数中提取了5个主因子,并以此作为预测模型的输入,采用支持向量机的算法来建立流动单元预测模型。应用该模型对大芦湖油田樊29块10口关键井的预测样本进行检验,正判率达90.38%。运用建立的预测模型对研究区441单砂层流动单元进行划分,将预测结果与定性分析结果对比,具有较高的吻合度。平面上,流动单元划分结果与沉积微相展布具有较高的对应关系:Ⅰ类、Ⅱ类流动单元储层质量最好,仅在浊积水道及朵叶体微相发育;Ⅲ类流动单元分布广泛,在浊积水道、水道侧缘及中扇侧缘微相均有分布;Ⅳ类流动单元主要分布在浊积扇外缘的扇缘亚相。结果表明,建立的流动单元模型能够较为系统地反映多种地质因素与流动性能之间的复杂映射规律。Due to the complexity of the formation mechanism of the turbidite reservoir,five principal factors were extracted through analysis on 13 parameters for reflecting the petrophysical,microscopic pore structural,sedimentary and heterogeneity characteristics of the reservoir.Then using the five principal factors as the input,the flow unit prediction model was established based on the support vector machine method.The model was used to test the predicting samples in Fan 29 block of Daluhu oilfield,and the accuracy rate of the results reached 90.38%.With the established prediction model,the flow unit of the single sand bed 4 4 1 in the study area was classified and evaluated,the prediction results were highly consistent with the qualitative analysis results.The flow unit classification well corresponded to the distribution of the sedimentary microfacies as the follows:the I-type and II-type flow-units are the best quality reservoirs,that are developed only in the turbidity channel and lobe;the flow-unit of III-type is widely distributed in the turbidity channel,channel edge,and the edge of middle fan;and the flow-unit IV is distributed in the edge of the fan.The studies suggest that the prediction model of flow units can be more comprehensive in consideration with the complex mapping relationship between the various geological factors and the flow units.

关 键 词：浊积扇 流动单元 因子分析 支持向量机 储层 大芦湖油田 

分 类 号：TE122.2[石油与天然气工程—油气勘探]