Abstract
We present a new approach for process fault detection based on models generated by machine learning techniques. Our work is based on a residual generation scheme, where the output of a model for process normal behavior is compared against actual process values. The residuals indicate the presence of a fault. The model consists of a general statistical inference engine operating on discrete spaces. This model represents the maximum entropy joint probability mass function (pmf) consistent with arbitrary lower order probabilities. The joint pmf is a rich model that, once learned, allows one to address inference tasks, which can be used for prediction applications. In our case the model allows the one step-ahead prediction of process variable, given its past values. The relevant past values for the forecast model are selected by learning a causal structure with an algorithm to learn a discrete bayesian network. The parameters of the statistical engine are found by an approximate method proposed by Yan and Miller. We show the performance of the prediction models and their application in power systems fault detection.
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.
Similar content being viewed by others
References
Chen, W., Liu, C., Tsai, M.: Online Fault Diagnosis of Distributions Substations Using Hybrid Cause-Effect Network and Fuzzy Rule-based Method. IEEE Transactions on Power Delivery 15(2), 710–717 (2000)
Isermann, R.: On Fuzzy Logic Applications for Automatic Control, Supervision, and Fault Diagnosis. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans 28(2), 221–235 (1997)
Cheng, J., Bell, D., Liu, W.: Learning Bayesian Networks from Data: An Efficient Approach Based on Information Theory, Technical Report, Dept. of Computing Science, University of Alberta, Alberta CA (1998)
Frank, P.: Fault Diagnosis in Dynamic Systems using Analytical and Knowledge Based Redundancy–A Survey and New Results. Automatica 30, 789–804 (1990)
Garza, L., Cantú, F., Acevedo, S.: A Methodology for Multiple-fault Diagnosis based on the Independent Choice Logic. In: Proc. of the IBERAMIA-SBIA, Sao Paulo, Brasil. LNCS (LNAI), pp. 417–426. Springer, Heidelberg (2000)
Gentil, S., Montmain, J., Combastel, C.: Combining FDI and AI Approaches within Causal-Model-Based Diagnosis. IEEE Transactions on Systems, Man and Cybernetics-part B: Cybernetics 34(5) (October 2004)
Grainger, J., Stevenson, W.: Power Systems Analysis. McGraw-Hill, Inc., USA (1994)
Lerner, U., Parr, R., Koller, D., Biswas, G.: Bayesian Fault Detection and Diagnosis in Dynamic Systems. IEEE Transactions on Control Systems 9, 498–503 (1999)
Manders, E., Biswas, G., Mosterman, P., Badford, L., Ram, V., Barnett, J.: Signal Interpretation for Monitoring and Diagnosis, a Cooling System Testbed. IEEE Transactions on Control Systems 9, 498–503 (1999)
Wang, L.: A Course in Fuzzy Systems and Control, Englewood Cliffs, NJ, USA (1997)
Yan, L., Miller, D.: General Statistical Inference for Discrete and Mixed Spaces by an Approximate Application of the Maximum entropy Principle. IEEE trans. On Neural Networks 11(3), 558–573 (2000)
Zhang, D., Dai, S., Zheng, Y., Zhang, R., Mu, P.: Researches and Applications of a Hybrid Fault Diagnosis System. In: Proceedings of the 3r world Congress on Intelligent Control and Automation 2000, Hefei, P.R. China, pp. 215–219 (2000)
Zhirabok, A., Preobrazhenskaya, O.: Robust Fault Detection and Isolation in nonlinear systems. In: Proceedings IFAC Symp. SAFEPROCESS 1994, Finland, June 1994, pp. 244–248 (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Castañon, L.E.G., Ortiz, F.J.C., Morales-Menéndez, R., Ramírez, R. (2005). A Fault Detection Approach Based on Machine Learning Models. In: Gelbukh, A., de Albornoz, Á., Terashima-Marín, H. (eds) MICAI 2005: Advances in Artificial Intelligence. MICAI 2005. Lecture Notes in Computer Science(), vol 3789. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11579427_59
Download citation
DOI: https://doi.org/10.1007/11579427_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29896-0
Online ISBN: 978-3-540-31653-4
eBook Packages: Computer ScienceComputer Science (R0)