Kullback-Leibler Divergence Based Kernel SOM for Visualization of Damage Process on Fuel Cells

The present work developed a basis to explore numerous damage events utilizing Self-Organizing Map (SOM) introducing Kullback-Leibler (KL) divergence as an appropriate similarity for frequency spectra of damage events. Firstly, we validated the use of KL divergence to frequency spectra of damage events. The experiment using the datasets of damage related sounds showed that the kernel SOM using KL kernel generates accurate cluster map compared to using general kernel functions and the standard SOM. Afterward, we demonstrated our approach can clarify damage process of Solid Oxide Fuel Cells (SOFC) from acoustic emission (AE) events observed by damage test of SOFC. The damage process was inferred by occurrence frequency of AE events upon the cluster map of SOM, where the occurrence density change was obtained by kernel density estimation (KDE). The presented approach can be a common foundation for the domain experts to clarify fracture mechanism of SOFC and/or to monitor SOFC operation.

[1]  Didier Sornette,et al.  Predictability of catastrophic events: Material rupture, earthquakes, turbulence, financial crashes, and human birth , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[2]  Mario Köppen,et al.  Data Swarm Clustering , 2006, Swarm Intelligence in Data Mining.

[3]  Hajime Omura,et al.  Tracking the Onset of Damage Mechanism in Ceria-based Solid Oxide Fuel Cells under Simulated Operating Conditions , 2006 .

[4]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[5]  Laurence J. Jacobs,et al.  Robust Clustering of Acoustic Emission Signals Using Neural Networks and Signal Subspace Projections , 2003, EURASIP J. Adv. Signal Process..

[6]  Marina Meila,et al.  Comparing Clusterings by the Variation of Information , 2003, COLT.

[7]  Klaus Pawelzik,et al.  Quantifying the neighborhood preservation of self-organizing feature maps , 1992, IEEE Trans. Neural Networks.

[8]  Brian W. Sheldon,et al.  Stresses due to oxygen potential gradients in non-stoichiometric oxides , 2004 .

[9]  Masayuki Numao,et al.  Combining Burst Extraction Method and Sequence-Based SOM for Evaluation of Fracture Dynamics in Solid Oxide Fuel Cell , 2007, 19th IEEE International Conference on Tools with Artificial Intelligence(ICTAI 2007).

[10]  Vangelis Karkaletsis,et al.  Enriching OWL Ontologies with Linguistic and User-Related Annotations: The ELEON System , 2007 .

[11]  Fabrice Rossi,et al.  Batch kernel SOM and related Laplacian methods for social network analysis , 2008, Neurocomputing.

[12]  Jon M. Kleinberg,et al.  Bursty and Hierarchical Structure in Streams , 2002, Data Mining and Knowledge Discovery.

[13]  T. Kohonen,et al.  Bibliography of Self-Organizing Map SOM) Papers: 1998-2001 Addendum , 2003 .

[14]  Masayuki Numao,et al.  Evaluation Method for Mechanical Performance of Solid Oxide Fuel Cell Under Simulated Operating Conditions , 2009 .

[15]  Alan Atkinson,et al.  Chemically-induced stresses in ceramic oxygen ion-conducting membranes , 2000 .

[16]  Hujun Yin,et al.  Kernel self-organising maps for classification , 2006, Neurocomputing.

[17]  Mikael Johnson Waveform based clustering and classification of AE transients in composite laminates using principal component analysis , 2002 .

[18]  Thomas Villmann,et al.  Neural maps and topographic vector quantization , 1999, Neural Networks.

[19]  Ajith Abraham,et al.  Swarm Intelligence in Data Mining , 2009, Swarm Intelligence in Data Mining.

[20]  Nuno Vasconcelos,et al.  A Kullback-Leibler Divergence Based Kernel for SVM Classification in Multimedia Applications , 2003, NIPS.

[21]  Isamu Yasuda,et al.  Lattice Expansion of Acceptor-doped Lanthanum Chromites under High-temperature Reducin'g Atmospheres , 2000 .

[22]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[23]  Péter András Kernel-Kohonen Networks , 2002, Int. J. Neural Syst..

[24]  J. López-Higuera,et al.  Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks , 2007 .

[25]  Masayuki Numao,et al.  Growth Analysis of Neighbor Network for Evaluation of Damage Progress , 2009, PAKDD.

[26]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[27]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .