Using structural decomposition methods to design gray-box models for fault diagnosis of complex industrial systems: a beet sugar factory case study

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jul 3, 2012
Belarmino Pulido Jesus Maria Zamarreño Alejandro Merino Anibal Bregon

Abstract

Reliable and timely fault detection and isolation are necessary tasks to guarantee continuous performance in complex industrial systems, avoiding failure propagation in the system and helping to minimize downtime. Model-based diagnosis fulfils those requirements, and has the additional advantage of using reusable models. However, reusing existing complex non-linear models for diagnosis in large industrial systems is not straightforward. Most of the times the models have been created for other purposes different from diagnosis, and many times the required analytical redundancy is small. In this work we propose to use Possible Conflicts, which is a model decomposition technique, to provide the structure (equations, inputs, outputs, and state variables) of minimal models able to perform fault detection and isolation. Such structural information can be used to design a gray box model by means of state space neural networks. We demonstrate the feasibility of the approach in an evaporator for a beet sugar factory using real data.

How to Cite

Pulido, B., Zamarreño, J. M., Merino, A., & Bregon, A. (2012). Using structural decomposition methods to design gray-box models for fault diagnosis of complex industrial systems: a beet sugar factory case study. PHM Society European Conference, 1(1). https://doi.org/10.36001/phme.2012.v1i1.1445
Abstract 113 | PDF Downloads 111

##plugins.themes.bootstrap3.article.details##

Keywords

applications, industrial, Diagnosis and fault isolation methods

References
Acebes, L., Merino, A., Alves, R., & Prada, C. de. (2009). Online energy diagnosis of sugar plants (in Spanish in the original). RIAI - Revista Iberoamericana de Automatica e Informatica Industrial, 6(3), 68-75.
Alves, R., Normey-Rico, J., A., M., Acebes, L., & Prada, C. de. (2008, June). Distributed Continuous Process Simulation: An Industrial Case Study. Computers and Chemical Engineering, 32(6), 1203-1213.
Armengol, J., Bregon, A., Escobet, T., Gelso, E., Krysander, M., Nyberg, M., et al. (2009). Minimal Structurally Overdetermined sets for residual generation: A comparison of alternative approaches. In Proceedings of the 7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, SAFEPROCESS09 (p. 1480-1485). Barcelona, Spain.
Blanke, M., Kinnaert, M., Lunze, J., & Staroswiecki, M. (2006). Diagnosis and Fault-Tolerant Control. Springer.
Chantler, M., Daus, S., Vikatos, T., & Coghill, G. (1996). The use of quantitative dynamic models and dependency recording engines. In Proceedings of the Seventh International Workshop on Principles of Diagnosis, DX96 (p. 59-68). Val Morin, Quebec, Canada.
Cordier, M., Dague, P., Lévy, F., Montmain, J., & Travé-Massuy`es, M. S. L. (2004). Conflicts versus Analytical Redundancy Relations: a comparativeanalysis of the Model-based Diagnosis approach from the Artificial Intelligence and Automatic Control perspectives. IEEE Trans. on Systems, Man, and Cybernetics. Part B: Cybernetics, 34(5), 2163-2177.
Daigle, M., Bregon, A., & Roychoudhury, I. (2011, September). Distributed Damage Estimation for Prognostics Based on Structural Model Decomposition. In Proceedings of the Annual Conference of the Prognostics and Health Management Society 2011 (p. 198-208).
Dressler, O. (1994). Model-based Diagnosis on Board: Magellan-MT Inside. In Working Notes of the International Workshop on Principles of Diagnosis, DX94. Goslar, Germany.
Dressler, O. (1996). On-line diagnosis and monitoring of dynamic systems based on qualitativemodels and dependency-recording diagnosis engines. In Proceedings of the Twelfth European Conference on Artificial Intelligence, ECAI-96 (p. 461-465). John Wiley and Sons, New York.
Dressler, O., & Struss, P. (1996). The Consistencybased approach to automated diagnosis of devices. In G. Brewka (Ed.), Principles of Knowledge Representation (p. 269-314). CSLI Publications, Standford.
Empresarios Agrupados Internacional. (2012). EcosimPro. http://www.ecosimpro.com/. Madrid, Spain.
Gertler, J. (1998). Fault detection and diagnosis in Engineering Systems. Marcel Dekker, Inc., Basel.
González-Lanza, P., & Zamarreño, J. (2002, january). A hybrid method for training a feedback neural network. In First International ICSC-NAISO Congress on Neuro Fuzzy Technologies NF 2002. Havana - Cuba.
González Lanza, P., & Zamarreño, J. (2002). A short-term temperature forecaster based on a state space neural network. Engineering Applications of Artificial Intelligence, 15(5), 459 - 464.
Hamscher, W., Console, L., & Kleer (Eds.), J. de. (1992). Readings in Model based Diagnosis. Morgan-Kaufmann Pub., San Mateo.
Kleer, J. de, & Williams, B. (1987). Diagnosing multiple faults. Artificial Intelligente, 32, 97-130.
Luyben, W. (1990). Process modeling, simulation, and control for chemical engineers. McGraw-Hill.
Merino, A. (2008). Librería de modelos del cuarto de remolacha de una industria azucarera para un simulador de entrenamiento de operarios. Unpublished doctoral dissertation, Universidad de Valladolid.
Merino, A., Alves, R., & Acebes, L. (2005). A training simulator for the evaporation section of a beet sugar production process. In Proceedings of the 2005 European Simulation and Modelling conference.
Patton, R. J., Frank, P. M., & Clark, R. N. (2000). Issues in fault diagnosis for dynamic systems. Springer Verlag, New York.
Pulido, B., & Alonso-González, C. (2004). Possible conflicts: a compilation technique for consistency-based diagnosis. ”IEEE Trans. on Systems, Man, and Cybernetics. Part B: Cybernetics”, 34(5), 2192-2206.
Pulido, B., Alonso-González, C., & Acebes, F. (2001). Consistency-based diagnosis of dynamic systems using quantitative models and off-line dependencyrecording. In 12th International Workshop on Principles of Diagnosis (DX-01) (p. 175-182). Sansicario, Italy.
Pulido, B., Bregon, A., & Alonso-González, C. (2010). Analyzing the influence of differential constraints in Possible Conflict and ARR computation. In Current Topics in Artficial Intelligence, CAEPIA 2009 Selected Papers. P. Meseguer, L. Mandow, R. M. Gasca Eds. Springer-Verlag Berlin.
Reiter, R. (1987). A Theory of Diagnosis from First Principles. Artificial Intelligence, 32, 57-95. Solis, F., & Wets, R. J.-B. (1981). Minimization by Random Search Techniques. Mathematics of Operations
Research, 6, 19–30.
Zamarreño, J., & Vega, P. (1997). Identification and predictive control of a melter unit used in the sugar industry. Artificial Intelligence in Engineering, 11(4), 365 - 373.
Zamarreño, J., & Vega, P. (1998). State space neural network.
Properties and application. Neural Networks, 11(6),
1099–1112.
Zamarreño, J., Vega, P., García, L., & Francisco, M. (2000).
State-space neural network for modelling, prediction
and control. Control Engineering Practice, 8(9), 1063
- 1075.
Section
Technical Papers