Application of probabilistic neural network and static test data to the classification of bridge damage patterns

Banfu Yan; Ayaho Miyamoto

doi:10.1117/12.482684

18 August 2003 Application of probabilistic neural network and static test data to the classification of bridge damage patterns

Banfu Yan, Ayaho Miyamoto

Author Affiliations +

Proceedings Volume 5057, Smart Structures and Materials 2003: Smart Systems and Nondestructive Evaluation for Civil Infrastructures; (2003) https://doi.org/10.1117/12.482684
Event: Smart Structures and Materials, 2003, San Diego, California, United States

Abstract

This paper is primarily concerned with the applicaitonof static test data in conjunction withthe probabilistic neural nework (PNN) for the classificationof dmage patterns of a cable-stayed bridge. A total of 11 dmage patterns are considered by combinationof 5 typical dmage regions. Both training and testing data, derived from static analysis via finite element method (FEM), are contaminated with differnt noise level to simula eth eFe model and meausmeent erros. The study of damge pattern identificaitonis conducted by taking into account the change ratios of the deflection of the main beam and the towe runder loading as input neuron sof the pNN. The effects of noise levls, the types of damage patterns, and the number of input neurons on the identification accuracy ae investigated.Base don the classificaiton results some valuable conclusions were obtained.

Citation Download Citation

Banfu Yan and Ayaho Miyamoto "Application of probabilistic neural network and static test data to the classification of bridge damage patterns", Proc. SPIE 5057, Smart Structures and Materials 2003: Smart Systems and Nondestructive Evaluation for Civil Infrastructures, (18 August 2003); https://doi.org/10.1117/12.482684

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