Abstract
This paper proposes a diagnosis architecture that integrates consistency based diagnosis with induced time series classifiers, trying to combine the advantages of both methods. Consistency based diagnosis allows fault detection and localization without prior knowledge of the device fault modes. Machine learning techniques are able to induce time series classifiers that may be used to identify fault modes of a dynamic systems. The diagnostician performs fault detection and localization resorting to consistency based diagnosis through possible conflicts. Then, a time series classifier, induced from simulated examples, generates a sequence of faults modes, coherent with the result of the fault localization stage, and ordered by fault modes confidence. Finally, to simplify the diagnosis task, it is considered as a subtask of a supervisory system, who is in charge of identifying the working conditions for the physical system.
This work has been supported by the Spanish MCyT project DPI2001-4404-E and the “Junta de Castilla y León” project VA101/01.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Acosta Lazo, G., Alonso González, C.J., Pulido Junquera, B.: Basic tasks for knowledge based supervisin in process control. Engineering Application of Artificial Intelligence 14, 441–455 (2002)
Balakrishnan, K., Honavar, V.: Intelligent diagnosis systems. Journal of Intelligent Systems 8 (1998)
Cauvin, S., Cordier, M.-O., Dousson, C., Laboire, P., Levy, F., Montmain, J., Pocheron, M., Servet, I., Travé-Massuyès, L.: Monitoring and alarm interpretation in industrial environments. AI Comunications 11(3–4), 139–173 (1998)
Feng, C.: Inducting temporal fault diagnostic rules from a qualitative model. In: Muggleton, S. (ed.) Inductive Logic Programming, Academic Press, London (1992)
Pulido, B., Alonso, C.: An alternative approach to dependency-recording engines in consistency-based diagnosis. In: Cerri, S.A., Dochev, D. (eds.) AIMSA 2000. LNCS (LNAI), vol. 1904, pp. 111–120. Springer, Heidelberg (2000)
Pulido, B., Alonso, C.: Possible conflicts, ARRs, and conflicts. In: 13th International Workshop on Principles of Diagnosis (DX 2002), Semmering, Austria, pp. 122–128 (2002)
Pulido, B., Alonso, C., Acebes, F.: Lessons learned from diagnosing dynamic systems using possible conflicts and quantitative models. In: Monostori, L., Váncza, J., Ali, M. (eds.) IEA/AIE 2001. LNCS (LNAI), vol. 2070, pp. 135–144. Springer, Heidelberg (2001)
Quinlan, J.R.: C4.5: programs for machine learning. Morgan Kaufmann, San Francisco (1993)
Rodríguez, J.J., Alonso, C.J., Boström, H.: Boosting interval based literals. Intelligent Data Analysis 5(3), 245–262 (2001)
Roverso, D.: Multivariate temporal classification by windowed wavelet decomposition and recurrent neural networks. In: 3rd ANS International Topical Meeting on Nuclear Plant Instrumentation, Control and Human-Machine Interface (2000)
Schapire, R.E.: A brief introduction to boosting. In: 16th International Joint Conference on Artificial Intelligence (1999)
Travé-Massuyès, L., Milne, R.: Gas turbine condition monitoring using qualitative model based diagnosis. IEEE Expert, 22–31 (1997)
Venkatusugramanian, V., Chan, K.: A neural network methodology for process fault diagnosis. AIChE J. 35, 1993–2001 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Alonso, C.J., Rodríguez, J.J., Pulido, B. (2004). Enhancing Consistency Based Diagnosis with Machine Learning Techniques. In: Conejo, R., Urretavizcaya, M., Pérez-de-la-Cruz, JL. (eds) Current Topics in Artificial Intelligence. TTIA 2003. Lecture Notes in Computer Science(), vol 3040. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25945-9_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-25945-9_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22218-7
Online ISBN: 978-3-540-25945-9
eBook Packages: Springer Book Archive