• DocumentCode
    1753074
  • Title

    Voidage Measurement of Two-Phase Flow Based on Least Squares Support Vector Machine

  • Author

    Peng, Zhenrui ; Mi, Gensuo

  • Author_Institution
    Dept. of Control Sci. & Eng., Zhejiang Univ., Hangzhou
  • Volume
    1
  • fYear
    0
  • fDate
    0-0 0
  • Firstpage
    4900
  • Lastpage
    4903
  • Abstract
    Combining least squares support vector machine (LS-SVM) with electrical capacitance tomography (ECT) technique, a new method for on-line voidage measurement of two-phase flow was proposed. The voidage measurement model was actually a function relationship between voidage and measured capacitance values, which were obtained by ECT sensor. In the measurement process, the normalized capacitance values were fed to the voidage measurement model to calculate the voidage value. This new method implemented the voidage measurement of oil/gas two-phase flow without time-consuming image reconstruction used in traditional ECT technique. Experimental results show that the proposed direct LS-SVM method for voidage measurement is effective. Both the real-time performance and the measurement accuracy can satisfy industrial requirements
  • Keywords
    electric impedance; flow control; flow measurement; least squares approximations; support vector machines; two-phase flow; electrical capacitance tomography; industrial requirements; least squares support vector machine; oil-gas two-phase flow; voidage measurement; Capacitance measurement; Capacitive sensors; Chemical industry; Electric variables measurement; Electrical capacitance tomography; Fluid flow measurement; Image reconstruction; Least squares methods; Petroleum; Support vector machines; Least squares support vector machine; electrical capacitance; two-phase flow; voidage;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on
  • Conference_Location
    Dalian
  • Print_ISBN
    1-4244-0332-4
  • Type

    conf

  • DOI
    10.1109/WCICA.2006.1713316
  • Filename
    1713316