Relative performance evaluation of pattern recognition models for nondestructive damage detection

Gabriel V. Garcia; Norris Stubbs; Karen Butler

doi:10.1117/12.238846

22 April 1996 Relative performance evaluation of pattern recognition models for nondestructive damage detection

Gabriel V. Garcia, Norris Stubbs, Karen Butler

Proceedings Volume 2719, Smart Structures and Materials 1996: Smart Systems for Bridges, Structures, and Highways; (1996) https://doi.org/10.1117/12.238846
Event: 1996 Symposium on Smart Structures and Materials, 1996, San Diego, CA, United States

Abstract

The objective of this paper is to evaluate the relative performance of several Bayesian distance-based pattern recognition models and two non-Bayesian models for non-destructive damage detection (NDD). A theory of damage localization, which yields information on the location of the damage directly from changes in mode shapes, is formulated. Next, the application of pattern recognition for NDD is established. Expressions for pattern classification using discriminate functions based on Bayes' Rule, Neyman-Pearson criteria, and neural networks are generated. A set of criteria for the evaluation of the pattern recognition models is then established. Damage localization is applied to a finite element mode of a structure which contains simulated damage at various locations using the pattern recognition and neural network models. Finally, the evaluation of the pattern recognition models is carried out using the established criteria.

Citation Download Citation

Gabriel V. Garcia, Norris Stubbs, and Karen Butler "Relative performance evaluation of pattern recognition models for nondestructive damage detection", Proc. SPIE 2719, Smart Structures and Materials 1996: Smart Systems for Bridges, Structures, and Highways, (22 April 1996); https://doi.org/10.1117/12.238846

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available