The flow-induced pipeline vibration characteristics of gas-liquid two-phase flow in various flow regimes were u-niquely investigated, and a novel noninvasive approach to the on-line flow regime identification for gas-liquid two-phase flow is proposed. The flow-induced pipeline vibration signals were measured by a vibration transducer installed on outside wall of pipe, and then the normalized energy features from different frequency bands in the vibration signals were extracted though 4-scale wavelet package transform with mother wavelet db7. A probabilistic neural network classifier with the extracted features as inputs was constructed to identify the three typical flow regimes including stratified wavy flow, annular mist flow, and slug flow for wet gas flow. The results show that the proposed method can identify flow regimes effectively and its identification accuracy arrives at above 92. 1%.%通过对不同流型的气液两相流流经管道时诱发的管道振动特性的实验研究,提出了基于流体诱发振动的非接触式在线两相流流型识别新方法.通过安装于测试管道外壁的振动传感器测量不同流型下气液两相流诱发的振动信号；采用小波包分析提取了表征流型变化的振动信号能量特征向量；以能量特征向量作为模型输入,建立了概率神经网络模型用于识别分层流、环/雾状流和弹状流三种水平管气液两相流流型.实验结果表明:气液两相流诱发的振动信号的能量特征向量能有效反映流型的变化;概率神经网络模型对测试样本的准确识别率为92.1％,能有效地识别气液两相流流型.
展开▼
