Crack Parameter Characterization by a Neural Network
Date
Authors
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Authors
Research Projects
Organizational Units
Journal Issue
Is Version Of
Versions
Series
Begun in 1973, the Review of Progress in Quantitative Nondestructive Evaluation (QNDE) is the premier international NDE meeting designed to provide an interface between research and early engineering through the presentation of current ideas and results focused on facilitating a rapid transfer to engineering development.
This site provides free, public access to papers presented at the annual QNDE conference between 1983 and 1999, and abstracts for papers presented at the conference since 2001.
Department
Abstract
A neural network with binary outputs is presented to determine the angle and the depth of a surface-breaking crack from ultrasonic backscattering data. The estimation procedure is divided into two steps: (1) The angle of the crack is estimated in the range from 10 to 70 degrees with a precision of 5 degrees. To improve the accuracy of estimation, information on the integral of the backscattered signal is utilized. (2) When the angle of the crack has been estimated, the depth of the crack is determined with a precision of 0.5mm in the range from 2.0mm to 4.0mm. This determination is achieved by employing sets of neural networks corresponding to various angles of the crack.