Application of adaptive probabilistic neural network to damage detection of Tsing Ma suspension bridge

Yi-Qing Ni; S. F. Jiang; Jan Ming Ko

doi:10.1117/12.435610

3 August 2001 Application of adaptive probabilistic neural network to damage detection of Tsing Ma suspension bridge

Yi-Qing Ni, S. F. Jiang, Jan Ming Ko

Proceedings Volume 4337, Health Monitoring and Management of Civil Infrastructure Systems; (2001) https://doi.org/10.1117/12.435610
Event: 6th Annual International Symposium on NDE for Health Monitoring and Diagnostics, 2001, Newport Beach, CA, United States

Abstract

Since the probabilistic neural network (PNN) describes measurement data in a Bayesian probabilistic approach, it shows great promise for structural damage detection in noisy conditions. In the traditional PNN, the smoothing parameter is unique to all pattern classes and is specified artificially, which may result in inaccuracy of identification results and computational inefficiency. In this study, we explore the damage localization of the Tsing Ma suspension bridge by use of an adaptive PNN that optimally determines different smoothing parameters for different pattern classes through an iteration scheme. A series of pattern classes are defined for the Tsing Ma Bridge to depict different damage locations.

Citation Download Citation

Yi-Qing Ni, S. F. Jiang, and Jan Ming Ko "Application of adaptive probabilistic neural network to damage detection of Tsing Ma suspension bridge", Proc. SPIE 4337, Health Monitoring and Management of Civil Infrastructure Systems, (3 August 2001); https://doi.org/10.1117/12.435610

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