基于ERT技术的垂直管道两相流流型识别

在两相流测量问题的研究中 ,流型的准确识别是其它流动参数准确测量的基础。基于电学敏感原理的电阻层析成像技术 (ERT) ,由于可视化、无辐射、低成本等优点 ,在两相流动参数的检测中具有很广阔的发展前景。研究中以 ERT系统样机为测量工具 ,以垂直管道气 /液两相管流为研究对象。通过对模拟流动状态实验下几种典型流型的测量数据的采集、处理 ,采用模式识别中的特征提取方法降低数据维数 ,并利用数理统计和神经网络方法识别流型。研究结果表明采用距离判别法和径向基神经网络技术均得到较高的识别率

Identification of Two-phase Flow Regime Based on ERT in Vertical Pipes

In the investigation of the two-phase flow measurement,the exact identification of flow regime is the foundation of other parameter exact measurement.Electrical resistance tomography (ERT) is a kind of process tomography technique based on the principle of electrical sensitivity.The technique has an expansive developing foreground in two-phase flow parameter measurement because of its advantages such as visualization,non-radiation, and low cost.The research object is gas/liquid two-phase flow in vertical pipes while the ERT system is used for the measuring tool.Based on the source data of several kinds of typical flow regime in vertical pipes,this research reduces the dimension of data using the extracted characteristic method in pattern recognition,and identifies the flow regime with statistics and neural network.The results show that both distance discriminance and radial basis function neural network have higher distinguishability.