Health Assessment of Composite Structures in Unconstrained Environments Using Partially Supervised Pattern Recognition Tools
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
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 offers the possibility to use uncertain and imprecise labels on the possible states, and thus covers supervised and unsupervised learning as special cases which makes it suitable for real applications.
How to Cite
##plugins.themes.bootstrap3.article.details##
acoustic emission, composite structure, Belief functions, noisy conditions, partially-supervised learning, clustering
fibre-reinforced polypropylene. Composite Science Technology, 52, 369-376.
Come, E., Oukhellou, L., Denoeux, T., & Aknin, P. (2009). Learning from partially supervised data using mixture models and belief functions. Pattern Recognition, 42(3), 334-348.
Daigle, M., Bregon, A., & Roychoudhury, I. (2011). Dis- tributed damage estimation for prognostics based on structural model decomposition. In Annual conference of the prognostics and health management society (Vol. 2).
Dempster, A. (1967). Upper and lower probabilities induced by multiple valued mappings. Annals of Mathematical Statistics, 38, 325-339.
Denoeux, T. (1995). A k-nearest neighbor classification rule based on Dempster-Shafer theory. IEEE Trans. on Systems, Man and Cybernetics, 5, 804-813.
Denoeux, T. (2011). Maximum likelihood estimation from uncertain data in the belief function framework. IEEE Transactions on Knowledge and Data Engineering.
Ely, T., & Hill, E. (1995). Longitudinal splitting and fiber breakage characterization in graphite epoxy using acoustic emission data. Mater. Eval., 53, 369-376.
Hadzor, T. J., Barnes, R. W., Ziehl, P. H., Xu, J., , & Schindler, A. K. (2011, June). Development of acoustic emission evaluation method for repaired prestressed concrete bridge girders (Tech. Rep. No. FHWA/ALDOT 930-601-1). 238 Harbert Engineering Center, Auburn, AL 36849: Auburn Highway Research Center, Department of Civil Engineering.
Huang, M., Jiang, L., Liaw, P., Brooks, C., Seeley, R., & Klarstrom, D. (1998). Using acoustic emission in fatigue and fracture materials research. Journal of Materials, 50(11), 1-12. (The Minerals, Metals & Materials Society (TMS))
Huguet, S. (2002). Application de classificateurs aux don- nees d’emission acoustique: identification de la sig- nature acoustique des mecanismes d’endommagement dans les composites a matrice polymere. Unpub- lished doctoral dissertation, Institut national des sci- ences appliquees (Lyon), Groupe dEtudes de Metal- lurgie Physique et de Physique des Materiaux. (in French)
Huguet, S., Godin, N., Gaertner, R., Salmon, L., & Villard, D. (2002). Use of acoustic emission to identify damage modes in glass fibre reinforced polyester. Composite Science Technology, 62, 1433-1444.
Kessler, S. S., Flynn, E. B., Dunn, C. T., & Todd, M. D. (2011). A structural health monitoring software tool for optimization, diagnostics and prognostics. In Annual conference of the prognostics and health management society (Vol. 2).
Klir, G., & Wierman, M. (1999). Uncertainty-based in-formation. elements of generalized information theory.In (chap. Studies in fuzzyness and soft computing).
Physica-Verlag.
Momon, S., Godin, N., Reynaud, P., RMili, M., & Fantozzi,G. (2012). Unsupervised and supervised classification of ae data collected during fatigue test on cmc at high temperature. Composites Part A: Applied Science and Manufacturing, 43, 254-260.
Momon, S., Moevus, M., Godin, N., RMili, M., Reynaud, P., Fantozzi, G., et al. (2010). Acoustic emission and lifetime prediction during static fatigue tests on ceramic- matrix composite at high temperature under air. Composites Part A: Applied Science and Manufacturing, 41, 913-918.
Rabiei, M., Modarres, M., & Hoffman, P. (2011). Structural integrity assessment using in-situ acoustic emission monitoring. In Annual conference of the prognostics and health management society.
Rabiner, L. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proc. of the IEEE, 77, 257-285.
Ramasso, E., Denoeux, T., & Zerhouni, N. (2012). Partially- Hidden Markov Models. In International conference on belief functions. Compiegne, France. (Accepted in February 2012)
Ramasso, E., & Jullien, S. (2011). Parameter identification in Choquet integral by the Kullback-Leibler divergence on continuous densities with application to classification fusion. In European society for fuzzy logic and technology (p. 132-139). Aix-Les-Bains, France.
Ramasso, E., Rombaut, M., & Zerhouni, N. (2012). Joint prediction of observations and states in time-series based on belief functions. IEEE Transactions on Systems, Man and Cybernetics - Part B: Cybernetics. (Accepted (http://dx.doi.org/10.1109/TSMCB.2012.2198882))
Serir, L., Ramasso, E., & Zerhouni, N. (2011). Time-sliced temporal evidential networks: the case of evidential hmm with application to dynamical system analysis. In Ieee int. conf. on prognostics and health management
(p. 1-10). Denver, CO, USA.
Serir, L., Ramasso, E., & Zerhouni, N. (2012). Evidential evolving gustafson-kessel algorithm for online data streams partitioning using belief function theory. International Journal of Approximate Reasoning, 5, 747- 768.
Shafer, G. (1976). A mathematical theory of Evidence. Princeton University Press, Princeton, NJ.
Smets, P. (1994). What is Dempster-Shafer’s model ? In I. R. Yager, M. Fedrizzi, & J. Kacprzyk (Eds.), Advances in the dempster-shafer theory of evidence (p. 5- 34). J.Wiley & Sons.
Smets, P., & Kennes, R. (1994). The Transferable Belief Model. Artificial Intelligence, 66(2), 191-234.
Vannoorenberghe, P., & Denoeux, T. (2002). Handling un- certain labels in multiclass problems using belief decision trees. In Information processing and management of uncertainty in knowledge-based systems (p. 1919- 1926).
Vannoorenberghe, P., & Smets, P. (2005). Partially supervised learning by a Credal EM approach. In Europ. conf. on symbolic and quantitative approaches to reasoning with uncertainty (Vol. 3571, p. 956-967).
Wang, Y. (2011). Multiscale uncertainty quantification based on a generalized hidden markov model. Journal of Mechanical Design, 133, 031004(1-10).
Zhou, W., Kovvali, N., Reynolds, W., Papandreou- Suppappola, A., Chattopadhyay, A., & 20, J. . D. Cochran vol., pp. 1271-1288. (2009). On the use of hidden markov modeling and time-frequency features for damage classification in composite structures. Journal of Intelligent Material Systems and Structures, Special Issue on Information Management in
Structural Health Monitoring, 20, 1271-1288.
Zhou, W., Reynolds, W., Moncada, A., Kovvali, N., Chattopadhyay, A., Papandreou-Suppappola, A., et al. (2008). Sensor fusion and damage classification in composite materials. In Proc. spie (Vol. 69260N).
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.