• DocumentCode
    2808990
  • Title

    Application of projection pursuit regression method in the confirmation of liquefaction grade of sand soil

  • Author

    Jianping, Jiang

  • Author_Institution
    Coll. of Ocean Environ. & Eng., Shanghai Maritime Univ., Shanghai, China
  • fYear
    2011
  • fDate
    15-17 July 2011
  • Firstpage
    3928
  • Lastpage
    3931
  • Abstract
    Based on projection pursuit regression method, this paper had a analysis on liquefaction grade of sand soil. Taking epicenter distance, effective pressure overlaying, standard penetration test, water table, circular shearing strength ratio as independent variables, and liquefaction grade of sand soil as dependent variable, the confirmation model of liquefaction grade of sand soil was obtained. It was found that, the confirmation value of liquefaction grade of sand soil was consistent with actual measurement value of liquefaction grade of sand soil for 32 groups of independent variables training model and 4 groups of independent variables validating model. The following conclusion can be drawn that, the prediction model is accurate and credible, and the projection pursuit regression method is a eximious method, and it is worthy to spread its application in the prediction of liquefaction grade of sand soil.
  • Keywords
    groundwater; liquefaction; sand; soil; circular shearing strength ratio; confirmation value; epicenter distance; eximious method; independent variable training model; independent variable validating model; liquefaction grade; prediction model; projection pursuit regression method; sand soil; standard penetration test; water table; Cities and towns; Earthquake engineering; Electric shock; Helium; Predictive models; Soil; Vibrations; application; liquefaction; projection pursuit regression method; sand soil;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Mechanic Automation and Control Engineering (MACE), 2011 Second International Conference on
  • Conference_Location
    Hohhot
  • Print_ISBN
    978-1-4244-9436-1
  • Type

    conf

  • DOI
    10.1109/MACE.2011.5987859
  • Filename
    5987859