Accession Number : ADA138142

Title :   Employment of Adaptive Learning Techniques for the Discrimination of Acoustic Emissions.

Descriptive Note : Final rept. Nov 81-Dec 82 on Phase 1,

Corporate Author : GENERAL ELECTRIC CORPORATE RESEARCH AND DEVELOPMENT SCHENECTADY NY

Personal Author(s) : Erkes,J W ; McDonald,J F ; Scarton,H A ; Tam,K C ; Kraft,R P

PDF Url : ADA138142

Report Date : Nov 1983

Pagination or Media Count : 286

Abstract : The following aspects of this study on the discrimination of acoustic emissions (AE) were examined: (1) The analytical development and assessment of digital signal processing techniques for AE signal dereverberation, noise reduction, and source characterization; (2) The modeling and verification of some aspects of key selected techniques through a computer-based simulation; and (3) The study of signal propagation physics and their effect on received signal characteristics for relevant physical situations.

Descriptors :   *Acoustic emissions, *Signal processing, *Adaptive systems, Learning machines, Digital systems, Adaptive filters, Optimization, Acoustic signals, Discrimination, Sound transmission, Cepstrum technique, Amplitude, Arrival, Time, Correlation, Noise reduction, Statistical distributions, Two dimensional, Acoustic signatures, Pattern recognition, Phased arrays, Computerized simulation, Volterra equations, Recursive filters, Computer programs

Subject Categories : Electrical and Electronic Equipment
      Cybernetics
      Acoustics

Distribution Statement : APPROVED FOR PUBLIC RELEASE