Abstract
Condition monitoring is an important and challenging task actual for many areas of industry, medicine and economics. Nowadays it is necessary to provide on-line monitoring of the complex systems status, e.g. the steel production, in order to avoid faults, breakdowns or wrong diagnostics. In the present paper a novel machine learning method for the automated condition monitoring is presented. Neural Clouds (NC) is a novel data encapsulation method, which provides a confidence measure regarding classification of the complex system conditions. The presented adaptive algorithm requires only the data which corresponds to the normal system conditions, which is typically available. At the same time the fault related data acquisition is expensive and fault modeling is not always possible, especially in case one is dealing with steel production, power stations operation, human health condition or critical phenomena in financial markets. These real word applications are also presented in the paper.
Similar content being viewed by others
References
Sergeev, A., Pavlova, L., and Romanenko, A., Statistical Methods of Human EEG Study, Leningrad: Nauka, 1968.
Evans, J. and Abarbanel, A., Introduction to Quantitative EEG and Neurofeedback, New York: Academic Press, 1999.
Schlang, M., Lang, B., Poppe, T., Runkler, T., and Weinzierl, K., Current and Future Development in Neural Computation in Steel Processing, Control Engineering Practice, 2001, vol. 9, pp. 975–986.
Mokhov, I. and Minin, A., Advanced Forecasting and Classification Technique for Condition Monitoring of Rotating Machinery, Proceedings of the 8th International Conference On Intelligent Data Engineering and Automated Learning (IDEAL’07), Birmingham, UK, December 16–19, 2007 (Springer), pp. 37–46.
Sinha, K., Artificial Neural Network Detects Changes in Electro-Encephalogram Power Spectrum of Different Sleep-Wake States in an Animal Model of Heat Stress, Medical and Biological Engineering and Computing, 2003, vol. 41, no. 5,, pp. 595–600.
Duta, M., Alford, C., Wilson, S., and Tarassenko, L., Neural Network Analysis of the Mastoid EEG for the Assessment of Vigilance, International Journal of Human-Computer Interaction, 2004, vol. 17, no. 2, pp. 171–199.
Karayiannis, N., Mukherjee, A., Glover, J., Ktonas, P., Frost, J.Jr., Hrachovy, R., and Mizrahi, E., Detection of Pseudosinusoidal Epileptic Seizure Segments in the Neonatal EEG by Cascading a Rule-Based Algorithm with a Neural Network, IEEE Transactions on Biomedical Engineering, 2006, vol. 53, no. 4, pp. 633–641.
James, J., Jones, D., Bones, J., and Carroll, J., Detection of Epileptiform Discharges in the EEG by a Hybrid System Comprising Mimetic, Self-Organized Artificial Neural Network, and Fuzzy Logic Stages, Clinical Neurophysiology, 1, December 1999, vol. 110, no. 12, pp. 2049–2063.
Tsuji, Y., Usui, T., Sato, Y., and Nagasawa, K., Development of Automatic Scoring System for Sleep EEG Using Fuzzy Logic, Journal of Robotics and Mechatronics, 1993, vol. 5, no. 3, pp. 204–208.
Bishop, C., Pattern Recognition and Machine Learning, Springer, 2006.
Barkova, N.A., The Current State of Vibroacoustical Machine Diagnostics, http://www.vibrotek.com/articles.php.
Barkov, A.V., Barkova, N.A., and Mitchell, J.S., Condition Assessment and Life Prediction of Rolling Element Bearings, Sound and Vibration, June 1995, pp. 10–17; September, pp. 27–31.
CASTOMAT Diagnostic Systems, http://www.siemens.com/castomat
Jasper, H., Report of the Committee on Methods of Clinical Examination in Electroencephalography, EEG Clin. Neurophysiol, 1958, vol. 10, pp. 370–375.
Lagerlund, T.D., Cascino, G.D., Cicora, K.M., and Sharbrough, F.W., Long-Term Electroencephalographic Monitoring for Diagnosis and Management of Seizures, Mayo Clin. Proc., 1996, pp. 1001–1006.
Legatt, A.D. and Ebersole, J.S., Options for Long-Term Monitoring, in Epilepsy: A Comprehensive Textbook, Engel, J., Pedley, T.A., Eds., Philadelphia: Lippincott Williams and Wilkins; 1998, vol. 1, pp. 1001–1020.
Dericioğlu, N., Albakir, M., and Saygi, S., The Role of Patient Companions in Long-Term Video-EEG Monitoring, Seizure, 2000, vol. 9, no. 2, pp. 124–127.
Wikipedia Internet Portal, http://en.wikipedia.org/wiki/Parzen_window
Wikipedia Internet Portal, http://en.wikipedia.org/wiki/Mixture_model
Sornette, D., Why Stock Markets Crash, Princeton and Oxford: Princeton University Press, 2003.
Johansen, A., Sornette, D., and Ledoit, O., Crashes as Critical Points, Int. J. Theor. and Appl. Finance, 2000, vol. 3, no. 2, pp. 219–255.
Sornette, D., Critical Market Crashes, Physics Reports, 2003, vol. 378, pp. 1–98.
Agaev, I.A. and Kuperin, Yu.A., Multifractal Analysis and Local Hoelder Exponents Approach to Detecting Stock Markets Crashes, http://xxx.lanl.gov/ftp/cond-mat/papers/0407/0407603.pdf, 2004.
Sornette, D., Johansen, A., and Bouchaud, J.-P., Stock Market Crashes, Precursors and Replicas, J. Phys. I France, January, 1996, vol. 6, pp. 167–175.
Kuperin, Yu.A. and Schastlivtsev, R.R., Modified Holder Exponents Approach to Prediction of the USA Stock Market Critical Points and Crashes, 15p., arXiv: 0802.4460, physics. soc-ph, 2008, http://xxx.lanl.gov
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Lang, B., Poppe, T., Minin, A. et al. Neural clouds for monitoring of complex systems. Opt. Mem. Neural Networks 17, 183–192 (2008). https://doi.org/10.3103/S1060992X08030016
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X08030016