基于小波包分析和RBF神经网络的ERT系统流型辨识  

Flow regime identification based on wavelet packet analysis and Radial Basis Function neural network for Electrical Resistance Tomography system

作　　者：陈德运[1] 朱波[1] 张华[1] 

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080

出　　处：《计算机工程与应用》2008年第6期231-233,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of Chinaunder Grant No.60572153);黑龙江省自然科学基金(the Natural Science Foundation of Helongjiang Province of Chinaunder Grant No.F200609);国家教育部重点科技项目(No.204043);黑龙江省重点科技攻关项目(No.GC05A510);哈尔滨市重点科技攻关项目(No.2005AA1CG035)。

摘　　要：两相流体具有复杂性的流动特性,流型的准确辨识是两相流参数准确测量的基础,流型的在线智能辨识成是两相流研究的重点内容之一。以ERT系统和油/水两相流的流型为研究基础,采用小波包分析方法对测量数据进行特征提取,然后以提取后的特征数据作为RBF神经网络的输入,对网络进行建模和仿真。通过实验仿真分析,该方法对流型辨识非常适用,并有效达到流型辨识的目的。Two-phase fluid has complex flow characteristic and the accurate identification of flow regime is the basis of the accurate measurement of two-phase flow＇s parameter, as a result,the on-line intelligent identification of flow regime is an important role of two-phase flow research.Based on electrical resistance tomography system and oil-water two phase flow regime,the feature of measurement data is extracted by the method of wavelet packet analysis,then the extracted data will be taken as input information of radial basis function neural network,both the model and the simulation are made for neural network.Experiment simu- lation analysis shows this method is very suitable for flow regime identification,and can attain a purpose of identification of flow regime effectively.

关 键 词：ERT系统 流型辨识 小波包分析 RBF神经网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]