Revista 27 - 2

Published

2007-05-01

Neural network fault diagnosis. Part II: flow recognition

Diagnóstico de fallas con redes neuronales. Parte II: Reconocimiento de flujos

Keywords:

fault diagnosis, artificial neural network, flow recognition, optimisation, noise tolerance (en)
diagnóstico de fallas, redes neuronales, reconocimiento de flujos, optimización, tolerancia al ruido (es)

Downloads

Authors

  • Enrique Eduardo Tarifa Universidad Nacional de Jujuy
  • Sergio Luis Martínez Universidad Nacional de Jujuy

The diagnostic system introduced in Part I is modified in this work for supervising complex processes when faults present themselves. As in Part I, it is supposed that when a fault affects a process, then each variable evolves following a trajectory. However, this time the aforementioned trajectory is not unique but belongs to a set of infinite possible trajectories named flow. Each fault in a particular flow is associated with each variable. Faults affecting a process can then be diagnosed by recognising which flow the trajectory being observed belongs to for every variable in turn. Once flows have been identified, then the fault causing them is also identified. Theory was developed after modelling fault diagnosis as being a flow recognition problem, definitions being yielded for both structure and training method for the artificial neural networks used by the new diagnostic system. The diagnostic system performed well in tests, diagnosis being exact, having high, stable resolution in the presence of noise. The theory so developed recommends networks being scaled-up for supervising more complex processes.

En el presente trabajo el sistema de diagnóstico presentado en la parte I es modificado para supervisar procesos que evolucionan en forma compleja ante la presencia de fallas. Al igual que en la Parte I, se considera que cuando una falla afecta a un proceso, cada variable evoluciona siguiendo una trayectoria. Sin embargo, esta vez dicha trayectoria no es única, sino que pertenece a un conjunto de infinitas trayectorias posibles denominado flujo. Cada falla tiene asociado un flujo particular para cada variable. Entonces, en un proceso afectado por una falla, el problema del diagnóstico de fallas se traduce a reconocer, para todas las variables, a cuál flujo pertenece la trayectoria que está siendo observada. Al identificar los flujos se habrá identificado la falla que los provoca. Modelado el diagnóstico de fallas como un problema de reconocimiento de flujos, se realizó un desarrollo teórico que culminó con la definición tanto de la estructura como del método de entrenamiento de las redes neuronales empleadas por el nuevo sistema de diagnóstico. En las pruebas hechas, el nuevo sistema de diagnóstico presentó muy buen comportamiento, siendo el diagnóstico exacto, de alta resolución y estable frente al ruido. Finalmente, la teoría desarrollada también indica cómo deben ser escaladas las redes para supervisar procesos de mayor complejidad.

Downloads

Download data is not yet available.

References

Ferrer-Nadal, S., Yélamos-Ruiz, I., Graells, M. and Puigjaner, L., An integrated framework for on-line supervised optimization, Computers & Chemical Engineering, Vol. 31, Issues 5-6, 2007, pp. 401-409.

Levy, A.V. and Montalvo, A., The tunneling algorithm for the global minimization of functions., SIAM Journal on Scientific and Statistical Computing, Vol. 6, No. 1, 1985, pp. 15-29.

Lin, C.T. and Lee, C.S., Neural Fuzzy Systems, A Neuro-Fuzzy Synergism to Intelligent Systems., Prentice Hall, New York, 1996, pp. 346-349.

Looney, C.G., Pattern Recognition Using Neural Networks: Theory and Algorithms for Engineers and Scientists., Oxford University Press, New York, 1997.

Power, Y. and Bahri, P.A., A two-step supervisory fault diagnosis framework., Computers & Chemical Engineering, Vol. 28, Issue 11, 2004, pp. 2131-2140.

Russell, S.J. and Norvig, P., Artificial Intelligence - A Modern approach., Prentice Hall, New Jersey, 1995.

Srinivasan, R., Wang, C., Ho, W.K. and Lim, K.W., Neural network systems for multi-dimensional temporal pattern classification., Computers & Chemical Engineering, Vol. 29, Issue 5, 2005a, pp. 965-981.

Srinivasan, R., Wang, C., Ho, W.K., Lim, K.W., Context-based recognition of process states using neural networks., Chemical Engineering Science, Vol. 60, Issue 4, 2005b, pp. 935-949.

Tarifa, E.E. y Martínez, S.L., Diagnóstico de fallas con redes neuronales. Parte I: Reconocimiento de trayectorias., Ing. Investig., Vol 27, No. 1, abril, 2007, pp. 68-76.

Tarifa, E.E., Humana, D., Franco, S., Martínez, S., Nuñez, A., and Scenna, N., Fault diagnosis for a MSF using neural networks., Desalination, 152, 2002, pp. 215-222.

License

Copyright (c) 2007 Enrique Eduardo Tarifa, Sergio Luis Martínez

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The authors or holders of the copyright for each article hereby confer exclusive, limited and free authorization on the Universidad Nacional de Colombia's journal Ingeniería e Investigación concerning the aforementioned article which, once it has been evaluated and approved, will be submitted for publication, in line with the following items:

1.    The version which has been corrected according to the evaluators' suggestions will be remitted and it will be made clear whether the aforementioned article is an unedited document regarding which the rights to be authorized are held and total responsibility will be assumed by the authors for the content of the work being submitted to Ingeniería e Investigación, the Universidad Nacional de Colombia and third-parties;

2.    The authorization conferred on the journal will come into force from the date on which it is included in the respective volume and issue of Ingeniería e Investigación in the Open Journal Systems and on the journal's main page (https://revistas.unal.edu.co/index.php/ingeinv), as well as in different databases and indices in which the publication is indexed;

3.    The authors authorize the Universidad Nacional de Colombia's journal Ingeniería e Investigación to publish the document in whatever required format (printed, digital, electronic or whatsoever known or yet to be discovered form) and authorize Ingeniería e Investigación to include the work in any indices and/or search engines deemed necessary for promoting its diffusion;

4.    The authors accept that such authorization is given free of charge and they, therefore, waive any right to receive remuneration from the publication, distribution, public communication and any use whatsoever referred to in the terms of this authorization.