Abstract
Knowledge discovery consists of finding new knowledge from databases where dimension, complexity, or amount of data is prohibitively large for human observation alone. The need for efficient data visualization and clustering is often faced, for instance, in the analysis, monitoring, fault detection, or prediction of various engineering plants. In this paper, two clustering techniques, K-means and Self-Organizing Maps, are used for the identification of characteristic regions for plasma scenario in nuclear fusion experimental devices. The choice of the number of clusters, which heavily affects the performance of the mapping, is firstly faced. Then, the ASDEX Upgrade Tokamak high-dimensional operational space is mapped into lower-dimensional maps, allowing to detect the regions with high risk of disruption, and, finally, the current process state and its history in time are visualized as a trajectory on the Self-Organizing Map, in order to predict the safe or disruptive state of the plasma.
Similar content being viewed by others
References
Murakami M, Callen JD, Berry LA (1976) Some observation on maximum density in Tokamaks experiments. Nucl Fusion 16:347–348
Fielding SJ, Hugill J, McCracken GM, Paul JWM, Prentice R, Stott PE (1977) High-density discharges with gettered Torus walls in DITE. Nucl Fusion 17:1382–1385
Lloyd SP (1982) Least squares quantization in PCM. IEEE Trans Inf Theory 2:129–137
Kohonen MT (1989) Self-organization and associative memory. Springer, New York
Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv 31:264–323
MacQueen JB (1967) Some methods for classification and analysis of multivariate observations. In: 5th Berkeley symposium on mathematical statistics and probability proceedings, Berkeley, University of California Press, vol 1, pp 281–297
Vesanto J, Himberg J, Alhoniemi E, Parhankangas J (2000) SOM toolbox for Matlab 5. Helsinki University of Technology, Finland. http://www.cis.hut.fi/somtoolbox/package/papers/techrep.pdf
Alhoniemi E (2002) Unsupervised pattern recognition methods for exploratory analysis of industrial process data. Doctoral Dissertation, Lab. of Computer and Information Science. Helsinki University of Technology, Finland
Laine S (2003) Using visualization, variable selection and feature extraction to learn from industrial data. Doctoral Dissertation, Laboratory of Computer and Information Science, University of Technology, Helsinki, Finland
Oja M, Kaski S, Kohonen T (2003) Bibliography of self-organizing map (SOM) papers: 1998–2001 addendum. Neural Comput Surv (3):1–156
Corona F, Mulas M, Baratti R, Romagnoli J (2009) Data derived analysis and inference for an industrial deethanizer. In: IFAC-ADCHEM09 conference proceedings, vol 2, pp 717–723
Ratta GA, Vega J, Murari A, Vagliasindi G (2009) Inspection of disruptive behaviours at JET using Generative Topographic mapping. In: PHYSCON 2009 proceedings, Catania, Italy
Sias G (2007) A disruption prediction system for ASDEX upgrade based on neural networks. PhD dissertation, University of Padova, Italy
Cannas B, Fanni A, Pautasso G, Sias G, Sonato P, Zedda MK, The ASDEX-Upgrade Team (2006) Disruption prediction at ASDEX upgrade using neural networks. In: 33th EPS conference on controlled fusion and plasma physics proceedings, Rome, Italy. http://epsppd.epfl.ch/Roma/pdf/P2_143.pdf
Salvador S, Philip Chan P (2004) Determining the number of clusters/segments in hierarchical clustering/segmentation algorithms. In: 16th IEEE international conference on tools with AI proceedings, pp 576–584
Dubes RC (1987) How many clusters are best? An experiment. Pattern Recognit 20(6):645–663
SOMtoolbox (2005) Adaptive Informatics Research Centre, Helsinky University of Technology, Finland. http://www.cis.hut.fi/projects/somtoolbox/
Davies DL, Bouldin DW (1979) A cluster separation measure. IEEE Trans Pattern Recognit Mach Intell (1):224–227
Dunn J (1974) Well separated clusters and optimal fuzzy partitions. J Cybern (4):95–104
Camplani M, Cannas B, Fanni A, Pautasso G, Sias G, Sonato P, Zedda MK, The ASDEX Upgrade Team (2007) Mapping of the ASDEX upgrade operational space using clustering techniques. In: 34th EPS conference on plasma physics and controlled fusion, Warsaw, Poland
Jolliffe IT (1986) Principal component analysis. Springer, New York
Version 5.2 R (2006) Statistics toolbox software for Matlab5.2. User’s guide: http://www.mathworks.com/access/helpdesk/help/pdf_doc/stats/stats.pdf
Acknowledgments
This work was supported by the Euratom Communities under the contract of Association between EURATOM/ENEA. The views and opinions expressed herein do not necessarily reflect those of the European Commission.
Author information
Authors and Affiliations
Consortia
Corresponding author
Rights and permissions
About this article
Cite this article
Camplani, M., Cannas, B., Fanni, A. et al. Tracking of the plasma states in a nuclear fusion device using SOMs. Neural Comput & Applic 20, 851–863 (2011). https://doi.org/10.1007/s00521-011-0529-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0529-2