JOURNAL OF YANGTZE RIVER SCIENTIFIC RESEARCH INSTI ›› 2013, Vol. 30 ›› Issue (11): 113-118.DOI: 10.3969/j.issn.1001-5485.2013.11.0232013,30(11):113-118

• Orignal Article • Previous Articles     Next Articles

Damage Identification of Concrete Arch Dam Using Mean Curvature Mode and Least Squares Support Vector Machine

LI Bo1,LIU Ming-jun2,MA Yi-ren3,CAO Hao1,GUO Fa-wang4   

  1. 1.Yangtze River Scientific Research Institute, Wuhan 430010, China;
    2.South Branch of China Power Investment Corporation, Guangzhou 510130, China;
    3. Changjiang Project Supervision Consultant Company, Ltd., Wuhan 430010,China;
    4.Hydrochina Guiyang Survey and Design Institute,Guiyang 550081, China
  • Received:2013-09-10 Revised:2013-11-07 Online:2013-11-30 Published:2013-11-07

Abstract: Affected by many external factors, the relation between concrete arch dam damage and modal information is apparently nonlinear, which makes it difficult to accurately identify the degree of structural damage by traditional modal analysis. Aimed at these problems, a method of identifying the damage of concrete arch dam by using mean curvature mode and least squares support vector machine is proposed. On the basis of numerical simulation, the damage location is firstly identified using mean curvature mode, then the non-linear relationship between mean curvature mode and damage degree is established using least squares support vector machine to identify the damage degree. Engineering example shows that by using this method, the location and degree of various damages occurring simultaneously can be effectively identified.

Key words: mean curvature mode, least squares support vector machine, concrete arch dam, damage identification

CLC Number: