多资料水淹层识别的模糊神经网络模型研究  

A Study of Multiple Data Recognition for Water Flooding Layer by Fuzzy Neural Network Model

作　　者：朱华艳[1] 王树明[1] 郭万奎[2] 牛彦良[2] 魏国章[2] 

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]大庆油田有限责任公司,黑龙江大庆163453

出　　处：《计算机工程与应用》2006年第2期226-229,共4页Computer Engineering and Applications

基　　金：大庆油田有限公司科学技术攻关项目(编号:2004220100001255)

摘　　要：该文研究了利用多资料识别水淹层水淹等级的模糊神经元网络自适应模型,模型由若干个规则网络和适用度网络组成,汇合了神经网络与模糊逻辑的优点,具有非线性系统的逼近能力。通过相关性分析和反复测试,最终选择13个参数作为输入参数,水淹层的含水饱和度作为输出参数,实际资料的检验证明该算法明显改进了识别效果。This article studies a self-adaptive fuzzy neural network model applied to the multiple data recognition of water flooding grade,This model is the combination of regulation network and fitness value network,so it adopts the advantages of neural network and fuzzy logic,and can approximate the complex nonlinear system adequately.After analysing the relativity and repeatedly testing,we chose 13 parameters to be the input parameters,and water-bearing saturation to be the output parameter.The practical data processing results show that this arithmetic can improve the recognition effect obviously.

关 键 词：模糊神经网络 水淹层 多资料识别 多规则 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]