Abstract
The paper focuses on designing an active fault detector (AFD) for a non-linear stochastic system subject to abrupt faults. The neural network (NN) based models of the monitored system and their prediction error uncertainties are identified using historical input-output data obtained from the system under fault-free and all considered faulty conditions. The fault detector is based on a multiple hypothesis CUSUM-like statistical test that uses the identified NN models. The quality of decisions provided by such a detector is improved by a closed loop input signal generator. The input signal generator is represented by another NN and it is designed using a reinforcement learning method. The proposed AFD is illustrated by means of a numerical example.
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
Similar content being viewed by others
Notes
- 1.
Note that \(\textbf{y}_{i:j}\) denotes the sequence of \(\textbf{y}_{k}\) from the time step i up to the time step j.
References
Blanke, M., Kinnaert, M., Lunze, J., Staroswiecki, M.: Diagnosis and Fault-Tolerant Control. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-662-47943-8
Campbell, S.L., Nikoukhah, R.: Auxiliary Signal Design for Failure Detection. Princeton University Press, Princeton, NJ, USA (2004)
Golubev, G., Safarian, M.: A multiple hypothesis testing approach to detection changes in distribution. Math. Methods Statist. 28(2), 155–167 (2019)
Haroutunian, E.A., Hakobyan, P.M.: Most powerful test for multiple hypotheses. In: Proceedings of the 10th International Conference on Computer Science and Information Technology, pp. 1–3. Yerevan, Armenia (2015)
Haykin, S.: Neural networks: a comprehensive foundation. Prentice Hall (1999)
Isermann, R.: Fault-Diagnosis Applications. Springer, Heidelberg, Germany (2011). https://doi.org/10.1007/978-3-642-12767-0
Kerestecioğlu, F.: Change Detection and Input Design in Dynamical Systems. Research Studies Press, Taunton, England (1993)
Král, L., Punčochář, I.: Policy search for active fault diagnosis with partially observable state. Adapt. Control Signal Process. 36(9), 2190–2216 (2022)
Marseglia, G.R., Scott, J.K., Magni, L., Braatz, R.D., Raimondo, D.M.: A hybrid stochastic-deterministic approach for active fault diagnosis using scenario optimization. In: Proceedings of the 19th IFAC World Congress, pp. 1102–1107. Cape Town, South Africa (2014)
Niemann, H.H.: A model-based approach to fault-tolerant control. Int. J. Appl. Math. Comput. Sci. 22(1), 67–86 (2012)
Nørgaard, M., Ravn, O., Poulsen, N.K., Hansen, L.K.: Neural Networks For Modelling And Control Of Dynamic Systems: A Practitioner’s Handbook (2000)
Oskiper, T., Poor, H.V.: Matrix CUSUM: a recursive multi-hypothesis change detection algorithm. In: Proceedings of the 2001 IEEE International Symposium on Information Theory, p. 19. Washington, DC, USA (2001)
Patton, R.J., Frank, P.M., Clark, R.N.: Issues of Fault Diagnosis for Dynamic Systems, 1st edn. Springer-Verlag, London, London, United Kingdom (2000). https://doi.org/10.1007/978-1-4471-3644-6
Poulsen, N.K., Niemann, H.H.: Active fault diagnosis based on stochastic tests. Int. J. Appl. Math. Comput. Sci. 18(4), 487–496 (2008)
Punčochář, I., Šimandl, M.: On infinite horizon active fault diagnosis for a class of non-linear non-Gaussian systems. Int. J. Appl. Math. Comput. Sci. 24(4), 795–807 (2014)
Raimondo, D.M., Marseglia, G.R., Braatz, R.D., Scott, J.K.: Closed-loop input design for guaranteed fault diagnosis using set-valued observers. Automatica 74, 107–117 (2016)
Zhang, X.J.: Auxiliary Signal Design in Fault Detection and Diagnosis. Springer-Verlag, Berlin, Germany (1989). https://doi.org/10.1007/BFb0009313
The work was supported by the Czech Science Foundation under grant 22-11101S.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Punčochář, I., Král, L. (2023). Neural Network Based Active Fault Diagnosis with a Statistical Test. In: Pawelczyk, M., Bismor, D., Ogonowski, S., Kacprzyk, J. (eds) Advanced, Contemporary Control. PCC 2023. Lecture Notes in Networks and Systems, vol 708. Springer, Cham. https://doi.org/10.1007/978-3-031-35170-9_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-35170-9_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35169-3
Online ISBN: 978-3-031-35170-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)