基于神经网络的两相流流型识别方法研究Flow Regime Identification in Two-phase Flow by Using Neural Network
贾志海,牛刚,王经
摘要(Abstract)：
采集了水平管内气水两相流动的差压信号,利用概率密度函数(PDF)对差压信号特征进行了分析;定义了PDF的四个特征参数,即PDF波峰个数K1、波峰峰值K2、波峰位置K3、以及PDF的方差K4来反映流型的特征。运用四个参数构成的特征向量对径向基函数(RBF)神经网络进行训练并识别流型,结果表明,该方法具有识别速度快、准确率高的特点,从而为两相流的流型识别提供了一种有效的手段。
关键词(KeyWords)： 两相流;流型识别;概率密度函数(PDF);神经网络
基金项目(Foundation): 国家高技术研究发展专项经费资助项目(2002AA616050)
作者(Author): 贾志海,牛刚,王经
参考文献(References)：
- [1]Lowe D C,Rezkallah K S.Flow regime identification in microgravity two-phase flows using void fraction signals[J].International Journal of Multiphase Flow,1999,25:433-457.
- [2]Mi Y,Ishii M,Tsoukalas L H.Investigation of vertical slug flow with advanced two-phase flow instrumentation[J].Nuclear Engineering and Design,2001,204:69-85.
- [3]Tsoukalas L H,Ishii Ma,Mi Y.A neurofuzzy methodology for impedance-based multiphase flow identification[J].Engineering Applications of Artificial Intelligence,1997,10:545-555.
- [4]Mi Y,Ishii M,Tsoukalas L H.Flow regime identification methodology with neural network and two-phase flow models[J].Nuclear Engineering and Design,2001,204:87-100.
- [5]Wu Hao-jiang,Zhou Fang-de,Wu Yu-yuan.Intelligent identification system of flow regime of oil-gas-water multiphase flow[J].International Journal of Multiphase Flow,2001,27:459-475.
- [6]Cai Y,Wambsganss M W,Jendrzejczyk J A.Application of chaos theory in identification of two-phase flow patterns and transitions in a small,horizontal,rectangular channel[J].J Fluids Eng,1996,118:383-390.
- [7]Elperin T,Klochko M.Flow regime identification in a two-phase flow using wavelet transform[J].Experiments in Fluids,2002,32:674-682.
- [8]CHEN Gong(陈珙),WANG Bao-liang(王保良),YANG Jiang(杨江),LI Hai-qing(李海青).Application of wavelets transform to the fuzzy identification gas-liquid two-phase flow regimes(基于小波分析的气液两相流流型模糊辨识)[J].J Chem Eng of Chinese Univ(高校化学工程学报),1999,13(4):303-308.