Hidden Markov model based classification of structural damage

Wenfan Zhou; Narayan Kovvali; Antonia Papandreou-Suppappola; Douglas Cochran; Aditi Chattopadhyay

doi:10.1117/12.716132

18 April 2007 Hidden Markov model based classification of structural damage

Wenfan Zhou, Narayan Kovvali, Antonia Papandreou-Suppappola, Douglas Cochran, Aditi Chattopadhyay

Proceedings Volume 6523, Modeling, Signal Processing, and Control for Smart Structures 2007; 652311 (2007) https://doi.org/10.1117/12.716132
Event: SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring, 2007, San Diego, California, United States

Abstract

The ability to detect and classify damages in complex materials and structures is an important problem from both safety and economical perspectives. This paper develops a novel approach based on Hidden Markov Models (HMMs) for the classification of structural damage. Our approach here is based on using HMMs for modeling the time-frequency features extracted from time-varying structural data. Unlike conventional deterministic methods, the HMM is a stochastic approach which better accounts for the uncertainties encountered in the structural problem and leads to a more robust health monitoring system. The utility of the proposed approach is demonstrated via example results for the classification of fastener damage in an aluminum plate.

Citation Download Citation

Wenfan Zhou, Narayan Kovvali, Antonia Papandreou-Suppappola, Douglas Cochran, and Aditi Chattopadhyay "Hidden Markov model based classification of structural damage", Proc. SPIE 6523, Modeling, Signal Processing, and Control for Smart Structures 2007, 652311 (18 April 2007); https://doi.org/10.1117/12.716132

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