Structural damage detection in the frequency domain using neural networks

Jungwhee Lee, Sungkon Kim

Research output: Contribution to journalArticlepeer-review

71 Scopus citations

Abstract

A bi-level damage detection algorithm that utilizes dynamic responses of the structure as input and neural network (NN) as a pattern classifier is presented. The signal anomaly index (SAI) is proposed to express the amount of changes in the shape of frequency response functions (FRFs) or strain frequency response function (SFRF). SAI is calculated by using the acceleration and dynamic strain responses acquired from intact and damaged states of the structure. In a bi-level damage identification algorithm, first the presence of damage is identified from the magnitude of the SAI value. Then the location of the damage is identified using the pattern recognition capability of the NN. The proposed algorithm is applied to an experimental model bridge to demonstrate the feasibility of the algorithm. Numerically simulated signals are used for training the NN, and experimentally acquired signals are used to test the NN. The results of this example application suggest that the SAI based pattern recognition approach may be applied to the structural health monitoring system for a real bridge.

Original languageEnglish
Pages (from-to)785-792
Number of pages8
JournalJournal of Intelligent Material Systems and Structures
Volume18
Issue number8
DOIs
StatePublished - Aug 2007

Keywords

  • Damage detection
  • Frequency response function (FRF)
  • Neural network (NN).
  • Pattern recognition
  • Signal anomaly index (SAI)
  • Strain frequency response function (SFRF)

Fingerprint

Dive into the research topics of 'Structural damage detection in the frequency domain using neural networks'. Together they form a unique fingerprint.

Cite this