摘要
常规测井资料解释应用于非常规储层裂缝识别时,存在裂缝识别率低,储层评价不准确等问题;而成像测井方法(FMI)识别效果好,但成本过高。为了提高常规测井裂缝识别的准确率,首先采用BP(back propagation)神经网络方法,建立常规测井参数与裂缝发育程度之间的非线性关系。在神经网络样本选取上,引入K-means聚类算法,依据不同样本特征对其进行优化分类。最后,利用聚类结果分别建立更为精细的神经网络模型,并用于实际裂缝预测。将该方法应用于塔河油田碳酸盐岩储层A探井,识别结果表明:基于样本优化方法的裂缝密度曲线拟合效果(相关系数R分别为0.84、0.89、0.76)明显优于未考虑样本优化方法(R为0.58),验证了本文方法的优越性,可以将其作为一种识别储层裂缝发育程度的新方法。
When conventional well logging data interpretation methods are applied to unconventional reservoir fractures identification,there are problems such as low fracture identification rate and inaccurate reservoir evaluation.Identification result of formation micro-resistivity scanning imaging logging(FMI)method is better,but the cost of that is too high.In order to improve the accuracy of conventional well logging fracture identification.Firstly,using back propagation(BP)neural network method to establish the nonlinear relationship between conventional well logging parameters and the development degree of fracture.In the selection of neural network samples,K-means clustering algorithm was introduced to optimize and classify according to the characteristics of different samples.Finally,the clustering results were used for establishing more refined neural network models and applied to actual fracture prediction.This method was applied to the prospecting well A of the carbonate reservoir in Tahe oilfield.The identification results show that the fitting effect of the fracture density curves base on the sample optimization method(three classes,correlation coefficients R:0.84,0.89,0.76)is significantly better than that method without considering the sample optimization(correlation coefficient R:0.58).The superiority of the proposed method is verified,and it can be used as a new method to identify the development degree of reservoir fractures.
作者
蓝茜茜
张逸伦
康志宏
LAN Xi-xi;ZHANG Yi-lun;KANG Zhi-hong(School of Energy Resources,China University of Geosciences(Beijing),Beijing 100083,China;School of Earth and Space Sciences,Peking University,Beijing 100871,China)
出处
《科学技术与工程》
北大核心
2020年第21期8530-8536,共7页
Science Technology and Engineering
基金
国家科技重大专项(2017ZX05009-001)。
