摘要
两相流体具有复杂的流动特性,流型的准确识别是两相流参数准确测量的基础。针对电阻层析成像(ERT)系统和油/水两相流的流型,先用小波包分析提取ERT系统测量的压差波动信号的特征,然后将特征数据输入构造好的DDAG双支持向量机多类分模型进行识别。仿真实验结果对比证明,DDAG双支持向量机是一种兼顾效率和准确性的流型识别方法。
Two-phase fluid has complex flow characteristics.The exact identification of flow regime is the foundation for measuring twophase flow＇s parameter accurately. According to electrical resistance tomography（ ERT） system and flow regime of oil-water two-phase flow,wavelet packet analysis is adopted to extract the features of the differential pressure fluctuation signal measured by ERT system,then the extracted feature data is input to the prepared DDAG bi- support vector machine to carry out multi-class identification. Experimental results showed that the DDAG bi-support vector machine is an effective and accurate method of regime identification.
出处
《长春大学学报》
2016年第12期33-35,48,共4页
Journal of Changchun University
