一种基于经验模式分解的气液两相流流型识别方法  

Identification method of gas-liquid two-phase flow regime based on empirical mode decomposition

作　　者：孙斌[1] 黄胜全[1] 周云龙[1] 关跃波[1] 

机构地区：[1]东北电力大学能源与机械工程学院,吉林132012

出　　处：《仪器仪表学报》2008年第5期1011-1015,共5页Chinese Journal of Scientific Instrument

基　　金：国家自然科学基金项目(50706006);吉林省教育厅重点项目(2006024)资助

摘　　要：提出了一种基于经验模式分解的气液两相流流型识别方法。该方法首先对压差波动信号进行经验模式分解,将其分解为多个平稳的固有模式函数之和,再选取若干个包含主要流型信息的IMF分量,并从中提取时域特征指标—峭度系数作为LVQ神经网络的输入参数,从而实现流型的智能识别。对水平管内空气—水两相流流型的识别结果表明:以EMD为预处理器提取峭度系数的LVQ网络识别方法具有更高的识别率,可以准确、有效地识别流型。A method of flow regime identification based on empirical mode decomposition was proposed. First of all, the collected pressure-difference fluctuation signals were decomposed into a finite number of stationary intrinsic mode function （IMFs） , then a number of IMFs containing main flow regime information were selected, from which time domain feature indicator-kurtosis coefficient that serves as input parameter of LVQ neural network was extracted in order to identify the flow regimes. The successful identification of four typical flow regimes of air-water two-phase flow in horizontal pipe shows that the proposed LVQ neural network identification method based on EMD for extracting time domain features is superior to other methods and can identify flow regimes accurately and effectively.

关 键 词：流型识别 经验模式分解 峭度系数 LVQ网络 

分 类 号：O359.1[理学—流体力学]