Abstract
A new supervision system consisting of three modules is presented. The main novelty is the first module that corresponds to a modelling task. This module, which uses the auto-adaptive and dynamical clustering (AUDyC) neural network, allows us to continuously analyse and classify the functioning state of the monitored system using a dynamical modelling of all known modes (good/bad functioning modes represent different classes). The second module exploits these models of the functioning modes in order to detect “fast” and “slow” deviations. From membership degrees and from the information extracted by the monitoring module, the third module, dedicated to the diagnostics, informs the user about the functioning conditions of the system. In this paper, the main characteristics of the AUDyC and its abilities to model on-line non-stationary data are presented. Then, the description of the supervision system is given and some experimental results stemmed from a supervision application of a hydraulic system are discussed.
Similar content being viewed by others
References
Platt J (1991) A resource-allocating network for function interpolation. Neural Comput 3:213–225
Gomm J (1995) Process fault diagnostic using self-adaptive neural network with on-line learning capabilities. In: Proceedings of the IFAC workshop on on-line fault detection and supervision in the chemical process industries, vol 1, Newcastle, United Kingdom, January 1995, pp 69–74
Fritzke B (1997) A self-organizing network that can follow non-stationary distributions. In: Proceedings of the 7th international conference on artificial neural networks (ICANN’97), Lausanne, Switzerland, October 1997, pp 613–618
Kasabov N (1999) Evolving connectionist systems for on-line, knowledge-based learning: principles and applications. Technical report, Department of Information Science, University of Otago, New Zealand
Hassibi B, Stork D (1993) Second order derivatives for network pruning: optimal brain surgeon. Adv Neural Inf Processing Syst 5:164–171
Castellano G, Fanelli AM, Pelillo M (1997) An iterative pruning algorithm for feedforward neural networks. IEEE Trans Neural Netw 8:519–531
Polikar R, Udpa L, Udpa S, Honavar V (2001) Learn ++: an incremental learning algorithm for supervised neural networks. IEEE Trans Sys Mans Cybern 31:497–508
Engelbrecht A, Brits R (2002) Supervised training using an unsupervised approach to active learning. Neural Processing Lett 15:247–260
Mouchaweh M, Devillez A, Villermain G, Billaudel P (2002) Incremental learning in fuzzy pattern matching. Fuzzy Sets Sys 132:49–62
Eltoft T, de Figueiredo R (1998) A new neural network for cluster detection and labeling. IEEE Trans Neural Netw 9:1021–1035
Lurette C, Lecoeuche S (2001) Improvement of cluster detection and labeling neural network by introducing elliptical basis functions. In: Dorffner G, Bischof H, Hornik K (eds) Proceedings of the international conference on artificial neural networks (ICANN 2001), Vienna, Austria, August 2001, pp 196–202
Deng D, Kasabov N (2003) On-line pattern analysis by evolving self-organizing maps. Neurocomputing 51:87–103
Lecoeuche S, Lurette C (2003) Auto-adaptive and dynamical clustering neural network. In: Proceedings of the 13th international conference on neural networks (ICANN 2003), Istanbul, Turkey, June 2003, pp 350–358
Lurette C (2003) Développement d’une technique neuronale auto-adaptative pour la classification dynamique de données évolutives. Application à la supervision d’une presse hydraulique. PhD thesis, Université des Sciences et Technologies de Lille, Lille, France
Basseville M, Nikiforov IV (1993) Detection of abrupt change: theory and application. Prentice Hall, Englewood Cliffs, New Jersey
Amadou Boubacar H (2002) Outils pour la détection de changements de comportement d’un système. Rapport de DEA de l’université de Sciences et Technologies de Lille, Lille, France
Lecoeuche S (2002) Unsupervised classifier for monitoring and diagnostic of time series. In: Proceedings of the 12th European symposium on artificial neural networks (ESANN 2002) Bruges, Belgium, April 2002, 419–424
Lurette C, Lecoeuche S (2003) An unsupervised and auto-adaptive neural architecture for on-line monitoring of an hydraulic process. Eng Appl Artif Intell 16(5–6):441–451
Pham DT, Chan AB (1998) Control chart pattern recognition using a new type of self organizing neural networks. Proc Instn Mech Engrs 212:115–127
Ljung L (1999) System identification: theory for the user, 2nd edn. Prentice Hall, Upper Saddle River, New Jersey
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lecoeuche, S., Lurette, C. & Lalot, S. New supervision architecture based on on-line modelling of non-stationary data. Neural Comput & Applic 13, 323–338 (2004). https://doi.org/10.1007/s00521-004-0427-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-004-0427-y