Bond Graph and Bayesian Networks for Reliable Diagnosis
Bond Graph as a unified multidisciplinary tool is widely
used not only for dynamic modelling but also for Fault Detection and
Isolation because of its structural and causal proprieties. A binary
Fault Signature Matrix is systematically generated but to make the
final binary decision is not always feasible because of the problems
revealed by such method. The purpose of this paper is introducing a
methodology for the improvement of the classical binary method of
decision-making, so that the unknown and identical failure signatures
can be treated to improve the robustness. This approach consists of
associating the evaluated residuals and the components reliability data
to build a Hybrid Bayesian Network. This network is used in two
distinct inference procedures: one for the continuous part and the
other for the discrete part. The continuous nodes of the network are
the prior probabilities of the components failures, which are used by
the inference procedure on the discrete part to compute the posterior
probabilities of the failures. The developed methodology is applied
to a real steam generator pilot process.
[1] R. J. Patton and J. Chen, "Observer-based fault detection and isolation
: Robustness and applications," Control Engineering Practice, vol. 5,
no. 5, pp. 671-682, 1997.
[2] J. Gertler, "Fault detection and isolation using parity relations," Control
Engineering Practice, vol. 5, no. 5, pp. 653-661, 1997.
[3] R. Isermann, "Process fault detection based on modelling and estimation
methods : A survey," Automatica, vol. 20, pp. 387-404, 1994.
[4] H. Paynter, Analysis and Design of Engineering Systems. MIT press,
1961.
[5] A. Mukerjee and A. Samantaray, "System modeling through bond graph
objects on symbols 2000," in International Conference on bond graph
Modeling and Simulation (ICBGM01), vol. 33 of Simulation series,
pp. 164-170, 2001.
[6] G. Dauphin-Tanguy, A. Rahmani, and C. Sueur, "Formal determination
of controllability/observability matrices for multivariables systems
modelled by bond graph," in International IMACS/SILE Symposium on
Robotics, Mechatronics and Manufacturing Systems92, pp. 573-578,
1992.
[7] G. Biswas, G. Simon, , N. Mahadevan, N. Narasimhan, S. Raminez, and
G. Karsai, "A robust method for hybrid diagnosis of complex systems,"
in 5th IFAC symposium on Fault Detection, Supervision and Safety for
Technical Processes SAFEPROCESS, pp. 1125-1131, 2003.
[8] A. K. Samantaray and B. Ould-bouamama, Model-based Process Supervision:
A Bond Graph Approach. ISBN 978-1-84800-158-9, Springer-
Verlag, 2008.
[9] B. Ould-bouamama, M. Staroswiecki, and A. Samantaray, "Software for
supervision system design in process engineering industry," in 6th IFAC,
SAFEPROCESS, (Beijing, China), pp. 691-695, 2006.
[10] Z. Shi, F. Gu, B. Lennox, and A. Ball, "The development of an adaptive
threshold for model-based fault detection of a nonlinear electro-hydraulic
system," Control Engineering Practice, vol. 13, pp. 1357-1367, 2005.
[11] J. Armengol, J. Vehi, M. A. Sainz, and P. Herrero, "Fault detection in
a pilot plant using interval models and multiple sliding windows," in
Safeprocess 2003 (e. N. Eva Wu, ed.), pp. 729-734, IFAC, 2003.
[12] M. Basseville and I. V. Nikiforov, Detection of Abrupt Changes: Theory
and Application. ISBN 0-13-126780-9, Prentice Hall, 1993.
[13] R. Wang, Statistical theory. Xian Jiaotong University Press China, 2003.
[14] M. A. Djeziri, B. O. Bouamama, and R. Merzouki, "Modelling and
robust fdi of steam generator using uncertain bond graph model," Journal
of Process Control, vol. 19, pp. 149-162, January 2009.
[15] P. Weber, D. Theilliol, C. Aubrun, and A. Evsukoff, "Increasing effectiveness
of model-based fault diagnosis: a dynamic bayesian network
design for decision making," in 6th IFAC Symposium on Fault Detection
Supervision and Safety for Technical Processes SAFEPROCESS, 2006.
[16] J. Pearl, Probabilistic Reasoning in Intelligent Systems: Networks of
Plausible Inference. Morgan Kaufmann, San Mateo, 1988.
[17] D. Koller and U. Lerner, Sequential Monte Carlo Methods in practice,
ch. Sampling in Factored Dynamic Systems, pp. 445-464. Springer-
Verlag, 2000.
[18] I. Roychoudhury, G. Biswas, and X. Koutsoukos, "A bayesian approach
to efficient diagnosis of incipient faults," in 17th International Workshop
on Principles of Diagnosis (DX 06), (Spain), pp. 243-250, 2006.
[19] P. Mosterman and G. Biswas, "Diagnosis of continuous valued systems
in transient operating regions," IEEE Trans. on Systems, Man and
Cybernetics, vol. 29, no. 6, pp. 554-565, 1999.
[20] P. J. Gawthrop, "Bicausal bond graphs," in ICBGM-95, pp. 83-88, Las
Vegas, USA, 1995.
[21] B. Bregon, B. Belarmino, G. Biswas, and X. Koutsoukos, "Generating
possible conflicts from bond graphs using temporal causal graphs,"
in 23rd European Conference on Modelling and Simulation ECMS09,
pp. 675-682, June 9-12, Madrid, 2009.
[22] N. Mehranbod, M. Soroush, and C. Panjapornpon, "A method of sensor
fault detection and identification," Journal of Process Control, vol. 15,
pp. 321-339, 2005.
[23] M. Anderson, R. Anderson, and K. Wheeler, "Filtering in hybrid
dynamic bayesian networks," in Interntional Conference on Acoustics,
Speech and Signal Processing, vol. 5, pp. 773-776, 2003.
[24] X. Zhang and K. A. Hoo, "Effective fault detection and isolation using
bond graph-based domain decomposition," Computers and Chemical
Engineering, vol. 35, pp. 132-148, 2011.
[25] M. Blanke, M. Kinnaert, J. Lunze, and M. Staroswiecki, Diagnosis and
Fault Tolerant Control. Springer-Verlag, 2003.
[26] P. Declerck, Analyse structurelle et fonctionnelle des grands systmes :
Application une centrale PWR 900 MW. PhD thesis, Universit des
Sciences et Technologies de Lille, France, 1991.
[27] M. Tagina, Application de la Modlisation Bond Graph la Surveillance
Des Systmes Complexes. PhD thesis, Universit des Sciences et Technologies
de Lille, France, 1995.
[28] A. Aitouche and B. Ould-bouamama, "Sensor location with respect
to fault tolerance properties," International Journal of Automation and
Control, vol. 4, no. 3, pp. 298-316, 2010.
[29] C. Andrieu, N. de Freitas, A. Doucet, and M. I. Jordan, "An introduction
to mcmc for machine learning," Kluwer Academic Publishers, vol. 50,
pp. 5-43, 2001.
[30] M. S. Hamada, A. G. Wilson, C. Reese, and H. Martz, Bayesian
reliability. ISBN 978-0-387-77948-5, Springer series in statistics, 2008.
[31] W. R. Gilks and P. Wild, "Adaptive rejection sampling for gibbs
sampling," Applied Statistics, vol. 41, pp. 337-348, 1992.
[32] G. Casella and E. I. George, "Explaining the gibbs sampler," American
Statistician, vol. 46, pp. 167-174, August 1992.
[33] S. Lauritzen and F. Jensen, "Stable local computation with conditional
gaussian distributions," Tech. Rep. R-99-2014, Dept. Math. Sciences,
Aalborg Univ., 1999.
[34] U. Lerner, E. Segal, and D. Koller, "Exact inference in networks with
discrete children of continuous parents," in Uncertainty in Artificial Intelligence
(C. Morgan Kaufmann, San Francisco, ed.), vol. 17, pp. 319-
328, 2001.
[35] D. Koller, U. Lerner, and D. Angelov, "A general algorithm for approximate
inference and its application to hybrid bayes nets," in the
Fifteenth Annual Conf. on Uncertainty in Artificial Intelligence UAI-99,
(Stockholm, Sweden), pp. 324-333, August 1999.
[36] A. V. Kozlov and D. Koller, "Nonuniform dynamic discretization in
hybrid networks," Uncertainty in artificial intelligence, vol. 13, pp. 314-
325, 1997.
[37] S. Moral, R. Rumi, and A. Salmeron, "Mixtures of truncated exponentials
in hybrid bayesian networks," in In Sixth European Conference on
Symbolic and Quantitative Approaches to Reasoning with Uncertainty,
vol. 2143 of Lecture Notes in Artificial Intelligence, pp. 145-167,
Springer-Verlag, 2001.
[38] U. Lerner, R. Parr, D. Koller, and G. Biswas, "Bayesian fault detection
and diagnosis in dynamic systems," in 17th National Conference on
Artificial Intelligence (AAAI), pp. 531-537, 2000.
[39] H. Rinne, The Weibull Distribution: A Handbook. ISBN 978-1-4200-
8743-7, CRC Press, 2008.
[40] B. Ould-bouamama, K. Medjaher, A. Samantaray, and M. Staroswiecki,
"Supervision of an industrial steam generator part i and ii," Control
Engineering Practice, vol. 14, pp. 71-83, 2006.
[41] N. S. Center, Handbook of Reliability Prediction Procedures for Mechanical
equipment. No. NSWC-07, Carderock Division, September 28
2007.
[42] GeNie2.0, "Website , http://genie.sis.pitt.edu," 2011.
[1] R. J. Patton and J. Chen, "Observer-based fault detection and isolation
: Robustness and applications," Control Engineering Practice, vol. 5,
no. 5, pp. 671-682, 1997.
[2] J. Gertler, "Fault detection and isolation using parity relations," Control
Engineering Practice, vol. 5, no. 5, pp. 653-661, 1997.
[3] R. Isermann, "Process fault detection based on modelling and estimation
methods : A survey," Automatica, vol. 20, pp. 387-404, 1994.
[4] H. Paynter, Analysis and Design of Engineering Systems. MIT press,
1961.
[5] A. Mukerjee and A. Samantaray, "System modeling through bond graph
objects on symbols 2000," in International Conference on bond graph
Modeling and Simulation (ICBGM01), vol. 33 of Simulation series,
pp. 164-170, 2001.
[6] G. Dauphin-Tanguy, A. Rahmani, and C. Sueur, "Formal determination
of controllability/observability matrices for multivariables systems
modelled by bond graph," in International IMACS/SILE Symposium on
Robotics, Mechatronics and Manufacturing Systems92, pp. 573-578,
1992.
[7] G. Biswas, G. Simon, , N. Mahadevan, N. Narasimhan, S. Raminez, and
G. Karsai, "A robust method for hybrid diagnosis of complex systems,"
in 5th IFAC symposium on Fault Detection, Supervision and Safety for
Technical Processes SAFEPROCESS, pp. 1125-1131, 2003.
[8] A. K. Samantaray and B. Ould-bouamama, Model-based Process Supervision:
A Bond Graph Approach. ISBN 978-1-84800-158-9, Springer-
Verlag, 2008.
[9] B. Ould-bouamama, M. Staroswiecki, and A. Samantaray, "Software for
supervision system design in process engineering industry," in 6th IFAC,
SAFEPROCESS, (Beijing, China), pp. 691-695, 2006.
[10] Z. Shi, F. Gu, B. Lennox, and A. Ball, "The development of an adaptive
threshold for model-based fault detection of a nonlinear electro-hydraulic
system," Control Engineering Practice, vol. 13, pp. 1357-1367, 2005.
[11] J. Armengol, J. Vehi, M. A. Sainz, and P. Herrero, "Fault detection in
a pilot plant using interval models and multiple sliding windows," in
Safeprocess 2003 (e. N. Eva Wu, ed.), pp. 729-734, IFAC, 2003.
[12] M. Basseville and I. V. Nikiforov, Detection of Abrupt Changes: Theory
and Application. ISBN 0-13-126780-9, Prentice Hall, 1993.
[13] R. Wang, Statistical theory. Xian Jiaotong University Press China, 2003.
[14] M. A. Djeziri, B. O. Bouamama, and R. Merzouki, "Modelling and
robust fdi of steam generator using uncertain bond graph model," Journal
of Process Control, vol. 19, pp. 149-162, January 2009.
[15] P. Weber, D. Theilliol, C. Aubrun, and A. Evsukoff, "Increasing effectiveness
of model-based fault diagnosis: a dynamic bayesian network
design for decision making," in 6th IFAC Symposium on Fault Detection
Supervision and Safety for Technical Processes SAFEPROCESS, 2006.
[16] J. Pearl, Probabilistic Reasoning in Intelligent Systems: Networks of
Plausible Inference. Morgan Kaufmann, San Mateo, 1988.
[17] D. Koller and U. Lerner, Sequential Monte Carlo Methods in practice,
ch. Sampling in Factored Dynamic Systems, pp. 445-464. Springer-
Verlag, 2000.
[18] I. Roychoudhury, G. Biswas, and X. Koutsoukos, "A bayesian approach
to efficient diagnosis of incipient faults," in 17th International Workshop
on Principles of Diagnosis (DX 06), (Spain), pp. 243-250, 2006.
[19] P. Mosterman and G. Biswas, "Diagnosis of continuous valued systems
in transient operating regions," IEEE Trans. on Systems, Man and
Cybernetics, vol. 29, no. 6, pp. 554-565, 1999.
[20] P. J. Gawthrop, "Bicausal bond graphs," in ICBGM-95, pp. 83-88, Las
Vegas, USA, 1995.
[21] B. Bregon, B. Belarmino, G. Biswas, and X. Koutsoukos, "Generating
possible conflicts from bond graphs using temporal causal graphs,"
in 23rd European Conference on Modelling and Simulation ECMS09,
pp. 675-682, June 9-12, Madrid, 2009.
[22] N. Mehranbod, M. Soroush, and C. Panjapornpon, "A method of sensor
fault detection and identification," Journal of Process Control, vol. 15,
pp. 321-339, 2005.
[23] M. Anderson, R. Anderson, and K. Wheeler, "Filtering in hybrid
dynamic bayesian networks," in Interntional Conference on Acoustics,
Speech and Signal Processing, vol. 5, pp. 773-776, 2003.
[24] X. Zhang and K. A. Hoo, "Effective fault detection and isolation using
bond graph-based domain decomposition," Computers and Chemical
Engineering, vol. 35, pp. 132-148, 2011.
[25] M. Blanke, M. Kinnaert, J. Lunze, and M. Staroswiecki, Diagnosis and
Fault Tolerant Control. Springer-Verlag, 2003.
[26] P. Declerck, Analyse structurelle et fonctionnelle des grands systmes :
Application une centrale PWR 900 MW. PhD thesis, Universit des
Sciences et Technologies de Lille, France, 1991.
[27] M. Tagina, Application de la Modlisation Bond Graph la Surveillance
Des Systmes Complexes. PhD thesis, Universit des Sciences et Technologies
de Lille, France, 1995.
[28] A. Aitouche and B. Ould-bouamama, "Sensor location with respect
to fault tolerance properties," International Journal of Automation and
Control, vol. 4, no. 3, pp. 298-316, 2010.
[29] C. Andrieu, N. de Freitas, A. Doucet, and M. I. Jordan, "An introduction
to mcmc for machine learning," Kluwer Academic Publishers, vol. 50,
pp. 5-43, 2001.
[30] M. S. Hamada, A. G. Wilson, C. Reese, and H. Martz, Bayesian
reliability. ISBN 978-0-387-77948-5, Springer series in statistics, 2008.
[31] W. R. Gilks and P. Wild, "Adaptive rejection sampling for gibbs
sampling," Applied Statistics, vol. 41, pp. 337-348, 1992.
[32] G. Casella and E. I. George, "Explaining the gibbs sampler," American
Statistician, vol. 46, pp. 167-174, August 1992.
[33] S. Lauritzen and F. Jensen, "Stable local computation with conditional
gaussian distributions," Tech. Rep. R-99-2014, Dept. Math. Sciences,
Aalborg Univ., 1999.
[34] U. Lerner, E. Segal, and D. Koller, "Exact inference in networks with
discrete children of continuous parents," in Uncertainty in Artificial Intelligence
(C. Morgan Kaufmann, San Francisco, ed.), vol. 17, pp. 319-
328, 2001.
[35] D. Koller, U. Lerner, and D. Angelov, "A general algorithm for approximate
inference and its application to hybrid bayes nets," in the
Fifteenth Annual Conf. on Uncertainty in Artificial Intelligence UAI-99,
(Stockholm, Sweden), pp. 324-333, August 1999.
[36] A. V. Kozlov and D. Koller, "Nonuniform dynamic discretization in
hybrid networks," Uncertainty in artificial intelligence, vol. 13, pp. 314-
325, 1997.
[37] S. Moral, R. Rumi, and A. Salmeron, "Mixtures of truncated exponentials
in hybrid bayesian networks," in In Sixth European Conference on
Symbolic and Quantitative Approaches to Reasoning with Uncertainty,
vol. 2143 of Lecture Notes in Artificial Intelligence, pp. 145-167,
Springer-Verlag, 2001.
[38] U. Lerner, R. Parr, D. Koller, and G. Biswas, "Bayesian fault detection
and diagnosis in dynamic systems," in 17th National Conference on
Artificial Intelligence (AAAI), pp. 531-537, 2000.
[39] H. Rinne, The Weibull Distribution: A Handbook. ISBN 978-1-4200-
8743-7, CRC Press, 2008.
[40] B. Ould-bouamama, K. Medjaher, A. Samantaray, and M. Staroswiecki,
"Supervision of an industrial steam generator part i and ii," Control
Engineering Practice, vol. 14, pp. 71-83, 2006.
[41] N. S. Center, Handbook of Reliability Prediction Procedures for Mechanical
equipment. No. NSWC-07, Carderock Division, September 28
2007.
[42] GeNie2.0, "Website , http://genie.sis.pitt.edu," 2011.
@article{"International Journal of Electrical, Electronic and Communication Sciences:58042", author = "Abdelaziz Zaidi and Belkacem Ould Bouamama and Moncef Tagina", title = "Bond Graph and Bayesian Networks for Reliable Diagnosis", abstract = "Bond Graph as a unified multidisciplinary tool is widely
used not only for dynamic modelling but also for Fault Detection and
Isolation because of its structural and causal proprieties. A binary
Fault Signature Matrix is systematically generated but to make the
final binary decision is not always feasible because of the problems
revealed by such method. The purpose of this paper is introducing a
methodology for the improvement of the classical binary method of
decision-making, so that the unknown and identical failure signatures
can be treated to improve the robustness. This approach consists of
associating the evaluated residuals and the components reliability data
to build a Hybrid Bayesian Network. This network is used in two
distinct inference procedures: one for the continuous part and the
other for the discrete part. The continuous nodes of the network are
the prior probabilities of the components failures, which are used by
the inference procedure on the discrete part to compute the posterior
probabilities of the failures. The developed methodology is applied
to a real steam generator pilot process.", keywords = "Redundancy relations, decision-making, Bond Graph,
reliability, Bayesian Networks.", volume = "5", number = "12", pages = "1776-14", }
