Health Assessment of Composite Structures in Unconstrained Environments Using Partially Supervised Pattern Recognition Tools

Emmanuel Ramasso, Vincent Placet, Rafael Gouriveau, Lamine Boubakar, and Noureddine Zerhouni
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmc_12_104.pdf2.39 MBSeptember 20, 2012 - 12:13am

The health assessment of composite structures from acoustic emission data is generally tackled by the use of clustering techniques. In this paper, the K-means clustering and the newly proposed Partially-Hidden Markov Model (PHMM) are exploited to analyse the data collected during mechanical tests on composite structures. The health assessment considered in this paper is made difficult by working in unconstrained environments. The presence of the noise is illustrated in several examples and is shown to distort strongly the results of clustering. A solution is proposed to filter out the noisy partition provided by the clustering methods. After filtering, the PHMM provides results which appeared closer to the expectations than the K-means. The PHMM also enables one to use uncertain and imprecise labels on the possible states, which makes it different from HMM. The formulation of the PHMM also enables one to cover supervised and unsupervised learning.

Publication Year: 
2012
Publication Volume: 
3
Publication Control Number: 
104
Page Count: 
11
Submission Keywords: 
composite structure
acoustic emission
noisy conditions
partially-supervised learning
clustering
Belief functions
Submission Topic Areas: 
Data-driven methods for fault detection, diagnosis, and prognosis
Structural health monitoring
Submitted by: 
  
 
 
 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed