• DocumentCode
    538869
  • Title

    Application of Genetic Algorithm in Combination with Least Squares Method for Particle Inversion

  • Author

    Jiang Haiying ; Li Jie ; Qi, Wang

  • Author_Institution
    Sch. of Electr. Eng. & Autom., Harbin Inst. of Technol., Harbin, China
  • Volume
    1
  • fYear
    2010
  • fDate
    16-17 Dec. 2010
  • Firstpage
    263
  • Lastpage
    266
  • Abstract
    Based on light intensity distribution, utilizing relationship between the diffraction angle and particle diameter, this paper introduces a direction operator in the particle inversion. Combination of the least squares method and genetic algorithm is proposed, which is a more effective method and reduces errors. The introduction of direction operator reduces the number of iterations, so the calculating time is shorted. The experimental results show that the time used in improved algorithm is less than 5s, and if the request is not very strict, 2s is sufficient. We can select the number of iterations according to the real-time requirements. The calculated root mean square error and maximum error also overall decline.
  • Keywords
    genetic algorithms; inverse problems; least mean squares methods; light scattering; particle size; genetic algorithm; least squares method; light intensity distribution; particle inversion; root mean square error; Artificial neural networks; Atmospheric measurements; Diffraction; Gallium; Particle measurements; Real time systems; Size measurement; direction operator; genetic algorithm; nonnegative least squares; particle inversion;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Systems (GCIS), 2010 Second WRI Global Congress on
  • Conference_Location
    Wuhan
  • Print_ISBN
    978-1-4244-9247-3
  • Type

    conf

  • DOI
    10.1109/GCIS.2010.93
  • Filename
    5708757