储层流动单元指数的EBF动态模糊神经网络预测模型

储层流动单元指数(FZI)能够从岩石物理相的角度体现出孔渗关系，可作为孔渗关系分析的辅助性参数。为了在孔隙度、渗透率未知的情况下对逐个采样点求取FZI，本文在分析泌阳凹陷白云岩分布区关键井的岩心数据和多种测井资料的基础上，建立了一种基于椭圆基函数(Ellipse Basis Function)的模糊神经网络FZI预测模型,该预测系统可根据学习样本自行创建或删减模糊规则。测井资料信息量庞大，因此这种具有自学习机制的预测系统更有利于有效信息的提取和利用，特别对于复杂储层而言，减轻了预测过程中对先验信息的依赖程度，因而效率和精度更高。

The application of Dynamic Fuzzy Neural Networks based on EBF in FZI prediction

Flow zone index(FZI) can reflects the relationship between porosity and permeability from the point of view of the petrophysical phase. Therefore, it can be used as a auxiliary analysis parameter of the relationship of porosity and permeability. In order to calculate FZI point-by-point under conditions of unknown porosity and permeability, a fuzzy neural network prediction model based on ellipse basis function was established on the basis of the analysis of the core data and a variety of logging data of Biyang dolostone reservoir. This prediction system can create or delete fuzzy rules by analyzing samples. The information contained in the log data is enormous. By using this prediction system with self-learning mechanism, the extraction and utilization of information is more effective. Practical application shows that the accuracy of identification is high .Especially for complex reservoirs , the application of this Fuzzy Neural Networks on reservoir characteristic parameters prediction improves the precision of prediction results and reduces the dependency on prior informations.