塔河油田碳酸盐岩储层水力压裂选井选层定量研究  

Research on target wells and layers selection for hydraulic fracturing in carbonate reservoir

作　　者：李林地[1,2] 张士诚[2] 庚勐[3] 王富来[4] 

机构地区：[1]中国石化石油勘探开发研究院,北京100083 [2]中国石油大学(北京)石油工程教育部重点实验室,北京102249 [3]中国石油勘探开发研究院廊坊分院,河北廊坊065007 [4]中国石化河南油田分公司新疆勘探开发中心,河南南阳473132

出　　处：《油气地质与采收率》2010年第5期99-101,共3页Petroleum Geology and Recovery Efficiency

基　　金：中国石油化工集团公司科技攻关项目"碳酸盐岩水力压裂机理研究及应用"(2007110001002285)

摘　　要：塔河油田碳酸盐岩储层水力压裂工艺起步较晚,选井选层工作还处于定性阶段。从储层地质条件出发,以酸压井的地质动静态资料为基础,利用人工神经网络原理建立的人工智能专家系统,对影响储层改造效果的地质因素进行数据处理和分析,实现了选井选层的定量研究。研究了提高神经网络泛化能力的方法,利用筛选出的数据对网络结构进行训练和测试,应用结果表明,优选出的神经网络预测结果与实际符合率为87.50%,能够满足工程需要,该方法能够快速、准确地进行水力压裂选井选层。Hydraulic fracturing for carbonate reservoir was implemented late in Tahe oilfield. And,target wells and layers selection are still in the qualitative stage. Based on the reservoir geological conditions and the analysis on static and dynamic geologic data, artificial intelligence and expert system has been established for the quantitative analysis on wells and layers selection for hydraulic fracturing in carbonate reservoir by means of application of artificial neural network theory. The method to improve the forecast ability of the network is studied and the network is trained and tested by valid data. The coincidence rate of the optimized nerve network and the reality was 87. 50 % which is qualified for the project demand. The method is helpful for selecting target wells and layers quickly and accurately in Tahe oilfield.

关 键 词：碳酸盐岩 水力压裂 选井选层 神经网络 塔河油田 

分 类 号：TE257.1[石油与天然气工程—油气井工程]