Abstract
Acoustic Emission (AE) is a non-destructive technique suitable for monitoring structural damages in complex systems. Interpretation of AE data is generally made by an unsupervised learning approach called clustering. A clustering method divides a dataset into different groups called clusters, which are expected to have a physical interpretation in terms of damages. The set of groups, called partition, is then evaluated through an external criterion. Since the number of clusters is a priori unknown, the standard approach for AE clustering consists in running a clustering method for different number of clusters and then to select the partition with the best value of the external criterion. The external criterion can vary across publications and aims at evidencing “natural” clusters. According to the criterion, the selected partition and its interpretation can be subjected to variability. In this publication, we explore a clustering method in which the parameters of clusters are optimised jointly with the number of clusters through an objective function and an optimisation procedure designed for that purpose. To our knowledge, it is the first method of this class in AE literature. Experimental results concern real data from tightening test.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bravo, A., Toubal, L., Koffi, D., Erchiqui, F.: Characterization of tensile damage for a short birch fiber-reinforced polyethylene composite with acoustic emission. Int. J. Mater. Sci. 3(13), 79–89 (2010)
Altschuler, J., Bhaskara, A., Fu, G., Mirrokni, V., Rostamizadeh, A., Zadimoghaddam, M.: Greedy column subset selection: new bounds and distributed algorithms. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning, ICML 2016, vol. 48, pp. 2539–2548. JMLR.org (2016)
Wu, X., et al.: Top 10 algorithms in data mining. Knowl. Inf. Syst. 14(1), 1–37 (2007)
Sause, M., Gribov, A., Unwin, A., Horn, S.: Pattern recognition approach to identify natural clusters of acoustic emission signals. Pattern Recogn. Lett. 33, 17–23 (2012)
Ramasso, E., Placet, V., Boubakar, M.L.: Unsupervised consensus clustering of acoustic emission time-series for robust damage sequence estimation in composites. IEEE Trans. Instrum. Meas. 64(12), 3297–3307 (2015)
Chandarana, N.: Time-dependent acoustic emission data clustering in tubular composite/metal joints, Mechanical Systems and Signal Processing (Submitted)
Fred, A., Jain, A.: Combining multiple clusterings using evidence accumulation. IEEE Trans. Pattern Anal. Mach. Intell. 27(6), 835–850 (2005)
Eaton, M.J., Pullin, R., Hensman, J., Holford, K.M., Worden, K., Evans, S.L.: Principal component analysis of acoustic emission signals from landing gear components: an aid to fatigue fracture detection. Strain 47, e588–e594 (2011)
Bishop, C.: Pattern Recognition and Machine Learning. Information Science and Statistics. Springer, New York (2006)
Beal, M.J.: Variational algorithms for approximate Bayesian inference, Ph.D. thesis, Gatsby Computational Neuroscience Unit, University College London (2003)
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. 39(1), 1–38 (1977)
Bilmes, J.: A gentle tutorial on the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models, Technical Report ICSI-TR-97-02, University of Berkeley, USA (1997)
Sawan, H.A., Walter, M.E., Marquette, B.: Unsupervised learning for classification of acoustic emission events from tensile and bending experiments with open-hole carbon fiber composite samples. Compos. Sci. Technol. 107, 89–97 (2015)
Denoeux, T.: Maximum likelihood estimation from uncertain data in the belief function framework. IEEE Trans. Knowl. Data Eng. 25(1), 119–130 (2013)
Etienne, C., Oukhellou, L., Denoeux, T., Aknin, P.: Mixture model estimation with soft labels, pp. 165–174 (2008)
Ramasso, E., Denoeux, T.: Making use of partial knowledge about hidden states in HMMs: an approach based on belief functions. IEEE Trans. Fuzzy Syst. 22(2), 395–405 (2014)
Tzikas, D.G., Likas, A.C., Galatsanos, N.P.: Life after EM - the variational approximation for Bayesian inference. IEEE Sig. Process. Mag. 25(6), 131–146 (2008)
Blei, D.M., Kucukelbir, A., McAuliffe, J.D.: Variational inference: a review for statisticians. J. Am. Stat. Assoc. 112(518), 859–877 (2017)
Alvares, D., Armero, C., Forte, A., Rubio, L.: Dirichlet-multinomial model: the impact of prior distributions. In: Conference: 11th International Workshop on Objective Bayes Methodology, Valencia, Spain (2015)
Festjens, H., Chevallier, G., Dion, J.-L.: A numerical tool for the design of assembled structures under dynamic loads. Int. J. Mech. Sci. 75, 170–177 (2013)
Kharrat, M., Ramasso, E., Placet, V., Boubakar, M.: A signal processing approach for enhanced acoustic emission data analysis in high activity systems: application to organic matrix composites. Mech. Syst. Sig. Process. 70, 1038–1055 (2016)
Chevallier, G., Ramasso, E., Butaud, P.: Detection and analysis of loosening in jointed structures using acoustic emission sensors and smart bolts. In: 37th Conference and Exposition on Structural Dynamics (IMAC), Orlando, USA (2019)
Acknowledgment
This work has been supported by the EUR EIPHI Graduate school (contract ANR-17-EURE-0002).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mbarga Nkogo, M., Ramasso, E., Le Moal, P., Bourbon, G., Verdin, B., Chevallier, G. (2021). Joint Optimization of the Number of Clusters and Their Parameters in Acoustic Emission Clustering. In: Rizzo, P., Milazzo, A. (eds) European Workshop on Structural Health Monitoring. EWSHM 2020. Lecture Notes in Civil Engineering, vol 128. Springer, Cham. https://doi.org/10.1007/978-3-030-64908-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-64908-1_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64907-4
Online ISBN: 978-3-030-64908-1
eBook Packages: EngineeringEngineering (R0)