Employment of Adaptive Learning Techniques for the Discrimination of Acoustic Emissions.
Abstract
Under Phase I of this contract, several new acoustic emission techniques were developed. These techniques showed a promise as a means of adaptively learning and removing multimode and multipath effects from acoustic emission signals in a preprocessing step prior to source characterization. In this Phase II effort, software was developed to implement the techniques, and a series of experiments was carried out to assess the effectiveness and practicality of these techniques on real signals. Analysis of the data revealed that reasonably accurate transfer functions could be determined adaptively, when a flat response wide-band transducer was employed, and when relatively short record lengths were used. Available commercial transducers with the requisite frequency response are quite fragile, however, and far too insensitive for practical use. Pattern recognition techniques were also explored as a means of characterizing acoustic emission sources; specifically, details of the pulse microstructure were examined for evidence of characterizable features. No such evidence was found in either raw (reverberation dominated) or processed data. Originator-supplied keywords include: Acoustic emission, Digital signal processing, Adaptive learning, Homomorphic deconvolution. (Author).
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 1984
- Accession Number
- ADA150170
Entities
People
- H. A. Scarton
- J. F. Macdonald
- J. W. Erkes
- K. C. Tam
- S. R. Mannava
Organizations
- General Electric