Premium
Application of Pattern Recognition to Damage Localization
Author(s) -
Stubbs Norris,
Garcia Gabe
Publication year - 1996
Publication title -
computer‐aided civil and infrastructure engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.773
H-Index - 82
eISSN - 1467-8667
pISSN - 1093-9687
DOI - 10.1111/j.1467-8667.1996.tb00352.x
Subject(s) - pattern recognition (psychology) , feature (linguistics) , basis (linear algebra) , feature vector , bridge (graph theory) , artificial intelligence , finite element method , space (punctuation) , mode (computer interface) , computer science , structural engineering , element (criminal law) , engineering , mathematics , geometry , biology , philosophy , linguistics , law , political science , anatomy , operating system
Pattern recognition is used as a basis to localize damage in structures. Feature vectors that depend on the predamaged and postdamaged mode shapes are developed. Classification criteria are developed to classify elements in the feature space into damaged and undamaged classes. The formulation is applied to a three‐dimensional finite element model of a bridge girder. The accuracy of the localization results is then evaluated.