IDENTIFICATION OF GAS LIQUID FLOW REGIMES IN A HORIZONTAL FLOW USING NEURAL NETWORK

查看全文 作　　者：JIAZhi-hai NIUGang [1]WANGJing

机构地区：[1]SchoolofMechanicalandPowerEngineering.ShanghaiJiaotongUniversity.Shanghai200030.China

出　　处：《Journal of Hydrodynamics》索引2005年第17卷第1期,共8页

基　　金：Project supported by the National High Technology and Research Development Program Special Fund of China (GrantNo: 2002AA616050). 摘　　要：The knowledge of flow regimes is very important in the study of a two phase flow system. A new flow regime identification method based on a Probability Density Function (PDF) and a neural network is proposed in this paper. The instantaneous differential pressure signals of a horizontal flow were acquired with a differential pressure sensor. The characters of differential pressure signals for different flow regimes are analyzed with the PDF. Then, four characteristic parameters of the PDF curves are defined, the peak number (K 1 ), the maximum peak value (K 2 ), the peak position (K 3 ) and the PDF variance (K 4 ). The characteristic vectors which consist of the four characteristic parameters as the input vectors train the neural network to classify the flow regimes. Experimental results show that this novel method for identifying air water two phase flow regimes has the advantages with a high accuracy and a fast response. The results clearly demonstrate that this new method could provide an accurate identification of flow regimes. 关键词：流体状态识别二相流人工神经网络概率密度函数

相关文献

参考文献（13）
引证文献（2）
耦合文献（0）

参考文献(13)

引证文献(2)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

IDENTIFICATION OF GAS LIQUID FLOW REGIMES IN A HORIZONTAL FLOW USING NEURAL NETWORK

参考文献(13)

引证文献(2)

用户提示