Application of neural networks in vibrational signature analysis

M. F. Elkordy, K. C. Chang, G. C. Lee

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

To identify the pattern of changes in vibrational signatures of a structure is a promising approach for on-line structure monitoring. Artificial neural networks, developed by researchers in cognitive sciences and artificial intelligence, can be used for this purpose. The main benefit of using artificial neural networks is their ability to diagnose signals that are fuzzy or imprecise. In this paper, neural networks were used to analyze the changes in vibrational signatures of a five-story, three dimensional, steel frame. The neural networks were first trained with a set of experimental data obtained from shake-table test results of the model. The capability of the neural networks to diagnose new signals was then tested against a separate set of experimental data. The results show that application of artificial neural networks in analyzing the changes in vibrational signatures of structures has considerable potential to structural damage diagnosis and condition monitoring.

Original languageEnglish
Pages (from-to)250-265
Number of pages16
JournalJournal of Engineering Mechanics
Volume120
Issue number2
DOIs
Publication statusPublished - 1994 Feb

All Science Journal Classification (ASJC) codes

  • Mechanics of Materials
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Application of neural networks in vibrational signature analysis'. Together they form a unique fingerprint.

  • Cite this