An intelligent signal processing and pattern recognition technique for defect identification using an active sensor network

Zhongqing Su, Lin Ye

Research output: Journal article publicationJournal articleAcademic researchpeer-review

50 Citations (Scopus)

Abstract

The practical utilization of elastic waves, e.g. Rayleigh-Lamb waves, in high-performance structural health monitoring techniques is somewhat impeded due to the complicated wave dispersion phenomena, the existence of multiple wave modes, the high susceptibility to diverse interferences, the bulky sampled data and the difficulty in signal interpretation. An intelligent signal processing and pattern recognition (ISPPR) approach using the wavelet transform and artificial neural network algorithms was developed; this was actualized in a signal processing package (SPP). The ISPPR technique comprehensively functions as signal filtration, data compression, characteristic extraction, information mapping and pattern recognition, capable of extracting essential yet concise features from acquired raw wave signals and further assisting in structural health evaluation. For validation, the SPP was applied to the prediction of crack growth in an alloy structural beam and construction of a damage parameter database for defect identification in CF/EP composite structures. It was clearly apparent that the elastic wave propagation-based damage assessment could be dramatically streamlined by introduction of the ISPPR technique.
Original languageEnglish
Pages (from-to)957-969
Number of pages13
JournalSmart Materials and Structures
Volume13
Issue number4
DOIs
Publication statusPublished - 1 Aug 2004
Externally publishedYes

ASJC Scopus subject areas

  • Materials Science(all)

Cite this