Using Fault Augmented Modelica Models for Diagnostics

Raj Minhas
Palo Alto Research Center, Palo Alto, CA, USA

Johan de Kleer
Palo Alto Research Center, Palo Alto, CA, USA

Ion Matei
Palo Alto Research Center, Palo Alto, CA, USA

Bhaskar Saha
Palo Alto Research Center, Palo Alto, CA, USA

Bill Janssen
Palo Alto Research Center, Palo Alto, CA, USA

Daniel G. Bobrow
Palo Alto Research Center, Palo Alto, CA, USA

Tolga Kurtoglu
Palo Alto Research Center, Palo Alto, CA, USA

Ladda ner artikelhttp://dx.doi.org/10.3384/ecp14096437

Ingår i: Proceedings of the 10th International Modelica Conference; March 10-12; 2014; Lund; Sweden

Linköping Electronic Conference Proceedings 96:46, s. 437-445

Visa mer +

Publicerad: 2014-03-10

ISBN: 978-91-7519-380-9

ISSN: 1650-3686 (tryckt), 1650-3740 (online)


We propose a model-based diagnosis framework in which Modelica models of faulted behavior are used in combination with a Bayesian approach. The fault augmented models are automatically generated through a process developed as part of our Fault Augmented Model Extension (FAME) work. Fault diagnosis using a Bayesian approach is based on computing a set of probability density functions; a process that is usually intractable for any reasonably complex system.We use Approximate Bayesian Computation (ABC) to bound the numerical and computational complexity. The basic idea is to use fault augmented Modelica models to create probability distributions of possible outcomes and then compare those distributions against actual observations to perform parameter estimation. The detection of faults is treated as a model selection problem and the inference of their severity levels is treated as parameter estimation. The diagnostic precision of this approach is evaluated on a Modelica vehicle drive line model.


Fault models; diagnosis; machine learning; model translation;bayesian methods


[1] M. G. B. Blum and O. Franscois. Non-linear regression models for approximate bayesian computation. Statistics and Computing, 20(20):63–73, 2010.

[2] Peter Bunus and Karin Lunde. Supporting model-based diagnostics with equation-based object oriented languages. In Proceedings of the 2nd International Workshop on Equation-Based Object-Oriented Languages and Tools, Paphos, Cyprus, July 2008.

[3] Wen Chen, M. Saif, and B. Shafai. Fault diagnosis in a class of differential-algebraic systems. In American Control Conference, 2004. Proceedings of the 2004, volume 5, pages 4398–4402 vol.5, 2004.

[4] J. de Kleer and B. C. Williams. Diagnosing multiple faults. Artificial Intelligence, 32(1):97–130, April 1987. Also in: Readings in NonMonotonic Reasoning, edited by Matthew L. Ginsberg, (Morgan Kaufmann, 1987), 280–297.

[5] Johan de Kleer, Bill Janssen, Daniel G. Bobrow, Tolga Kurtoglu, Bhaskar Saha, Nicholas R. Moore, and Saravan Sutharshana. Fault augmented modelica models. In 24th International Workshop on Principles of Diagnosis, pages 71–78, Jerusalem, Israel, 2013.

[6] P. Fritzson. Principles of Object-Oriented Modeling and Simulation with Modelica 2.1. Wiley-IEEE Press, Piscataway, NJ, 2004.

[7] Mattias Krysander and Mattias Nyberg. xstructural analysis for fault diagnosis of dae systems utilizing graph theory and mss sets. Technical Report LiTH-ISY-R-2410, Department of Electrical Engineering, Linkoping University, 2002.

[8] Zsolt Lattmann, Adrian Pop, Johan de Kleer, Peter Fritzson, Bill Janssen, Sandeep Neema, Ted Bapty, Xenofon Koutsoukos, Matthew Klenk, Daniel Bobrow, Bhaskar Saha, and Tolga Kurtoglu. Verification and design exploration through meta tool integration with openmodelica. In Proceedings of the 10th International Modelica Conference, Lunde, Sweden, 2014.

[9] J. K. Pritchard, M. T. Seielstad, A. Perez-Lezaun, and M. W. Feldman. Population growth of human y chromosomes: a study of y chromosome microsatellites. Molecular Biology and Evolution, 16:1791–1798, 1991.

[10] R. Reiter. A theory of diagnosis from first principles. Artificial Intelligence, 32(1):57–96, 1987.

[11] D. Wegmann, C. Leuenberger, S. Neuenschwander, and L. Excoffier. Abctoolbox: a versatile for approximate bayesian algorithms. BMC Bioinformatics, 2(11):116, 1990.

[12] W. Zhang and D. J. Balding. Approximate bayesian computation in population genetics. Genetics, 27:2025–2035, 2002.

Citeringar i Crossref