• DocumentCode
    2012884
  • Title

    Gas-water two-phase flow regime identification with feature fusion from an ERT system and a V-cone meter

  • Author

    Tan, Chao ; Dong, Feng

  • Author_Institution
    Tianjin Key Lab. of Process Meas. & Control, Tianjin Univ., Tianjin
  • fYear
    2009
  • fDate
    11-12 May 2009
  • Firstpage
    307
  • Lastpage
    312
  • Abstract
    Gas-water two-phase flow is of significance in industrial process and scientific research field. Its flow regime determines the flow parameters and the method of flow measurement. Precise identification of flow regime has been a popular subject for a long time. In this work, a series of experiments on gas-water two-phase flows were conducted in a 50 mm diameter horizontal pipe, the flow parameters were measured with an Electrical Resistance Tomography (ERT) system and a V-cone meter. A method of feature extraction from the above two instruments is presented and the flow regime was recognized by using a Support Vector Machine (SVM) method. Additionally, the feature fusion methods are selected and compared to discuss the method of improving the flow regime recognition performance.
  • Keywords
    electric impedance imaging; flow measurement; pipe flow; pressure measurement; support vector machines; two-phase flow; ERT system; V cone meter; electrical resistance tomography system; flow measurement method; flow parameters; gas-water two phase flow; size 50 mm; support vector machine method; two phase flow regime identification; Conductivity; Electric resistance; Electric variables measurement; Electrical resistance measurement; Fluid flow; Fluid flow measurement; Gas industry; Plugs; Support vector machines; Tomography; electrical resistance tomgoraphy; flow regime; support vector machine; two-phase flow; v-cone;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Imaging Systems and Techniques, 2009. IST '09. IEEE International Workshop on
  • Conference_Location
    Shenzhen
  • Print_ISBN
    978-1-4244-3482-4
  • Electronic_ISBN
    978-1-4244-3483-1
  • Type

    conf

  • DOI
    10.1109/IST.2009.5071655
  • Filename
    5071655