Accession Number : ADA292440
Title : Spectral Characterization of Pulsed Ultrasound Using Neural Networks.
Descriptive Note : Final technical rept.,
Corporate Author : ARMY ARMAMENT RESEARCH DEVELOPMENT AND ENGINEERING CENTER WATERVLIET NY BENET LABS
Personal Author(s) : Johnson, Mark A. ; Cipollo, Michael A. ; Scanlon, R. D.
PDF Url : ADA292440
Report Date : DEC 1994
Pagination or Media Count : 17
Abstract : A novel nondestructive evaluation technique that uses the spectral signature of a pulsed ultrasound signal to identify metals had recently been abandoned because of the difficulty in interpreting the results. Traditional analysis is inconvienent to apply to this type of problem because of the complicated, noisy and incomplete nature of the data. Neural networks provide a radically different approach to computation. These massively parallel systems provide a mechanism to extract pertinent information from input data while maintaining a high degree of fault tolerance. This report discusses design of a neural network system capable of accepting data from nondestructive test equipment and producing output relative to the quality of the sample being tested.
Descriptors : *NEURAL NETS, *NONDESTRUCTIVE TESTING, *IDENTIFICATION SYSTEMS, *ULTRASONIC TESTS, *SPECTRUM SIGNATURES, INPUT, METALS, COMPUTATIONS, TEST EQUIPMENT, PULSES, ULTRASONICS, SIGNALS, PARALLEL ORIENTATION, FAULT TOLERANCE.
Subject Categories : Test Facilities, Equipment and Methods
Properties of Metals and Alloys
Distribution Statement : APPROVED FOR PUBLIC RELEASE