A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System

Mohammed Said Achbi; Sihem Kechida; Lotfi Mhamdi; Hedi Dhouibi

doi:10.2478/ama-2021-0001

.blurhash-client-img { display: none !important; }

A Neural-Fuzzy Approach for Fault Diagnosis of Hybrid Dynamical Systems: Demonstration on Three-Tank System

Acta Mechanica et Automatica

Volume 15 (2021): Issue 1 (March 2021)

By: Mohammed Said Achbi, Sihem Kechida, Lotfi Mhamdi and Hedi Dhouibi

Open Access

|May 2021

Abstract

This work is part of the diagnostic field of hybrid dynamic systems (HDS) whose objective is to ensure proper operation of industrial facilities. The study is initially oriented to the modelling approach dedicated to hybrid dynamical systems (HDS). The objective is to look for an adequate model encompassing both aspects (continuous and event). Then, fault diagnosis technique is synthesised using artificial intelligence (AI) techniques. The idea is to introduce a hybrid version combining neural networks and fuzzy logic for residual generation and evaluation. The proposed approach is then validated on three tank system. The modelling and diagnosis approaches are developed using MATLAB/Simulink environment.

References

1. Abdallah I., Gehin A.-L., Bouamama B. O. (2016), Event driven hybrid bond graph for diagnosis, 2016 European Control Conference (ECC), 2353–2358.10.1109/ECC.2016.7810642
Search in Google Scholar Back to article
2. Abid A., Khan M.T., Lang H., de Silva C.W. (2019), Adaptive system identification and severity index-based fault diagnosis in motors, IEEE/ASME Transactions on Mechatronics, 24(4), 1628–1639.10.1109/TMECH.2019.2917749
Search in Google Scholar Back to article
3. Achbi M.S., Kechida S. (2017), Hybrid dynamic systems fault diagnosis approach based on hybrid automata and ANFIS, The 2 Nd International Conference on Applied Automation and Industrial Diagnostics, ICAAID2017.
Search in Google Scholar Back to article
4. Achbi M.S., Kechida S. (2017a), Fault diagnosis of a reverse osmosis water desalination plant through a hybrid approach, ICENT2017.
Search in Google Scholar Back to article
5. Achbi M.S., Kechida S. (2017b), Fault tolerant control of Reverse Osmosis Desalination Plant with the application of SCADA system, The 2nd International Conference on Applied Automation and Industrial Diagnostics, ICAAID2017.
Search in Google Scholar Back to article
6. Achbi M.S., Kechida S. (2020), Methodology for monitoring and diagnosing faults of hybrid dynamic systems: A case study on a desalination plant, Diagnostyka, 21(1), 1641–6414.10.29354/diag/116076
Search in Google Scholar Back to article
7. Achbi M.S., Mhamdi L., Kechida S., Dhouibi H. (2020), Methodology to knowledge discovery for fault diagnosis of hybrid dynamical systems: demonstration on two tanks system, Diagnostyka, 21.10.29354/diag/130617
Search in Google Scholar Back to article
8. Alur R., Courcoubetis C., Henzinger T.A., Ho P.-H. (1992), Hybrid automata: An algorithmic approach to the specification and verification of hybrid systems, Hybrid systems, 209–229, Springer.10.1007/3-540-57318-6_30
Search in Google Scholar Back to article
9. Antsaklis P., Koutsoukos X. (1997), On hybrid control of complex systems: A survey, ISIS, 97, 017.
Search in Google Scholar Back to article
10. Asma T., Islem L., Zanzouri N., Ksouri M. (2015), Robust diagnosis for hybrid dynamical systems, 2015 IEEE 12th International Multi-Conference on Systems, Signals Devices (SSD15), 1–6.10.1109/SSD.2015.7348222
Search in Google Scholar Back to article
11. Belkacem L., Mhamdi L., Simeu-Abazi Z., Messaoud H., Gascard E. (2016), Diagnosis of Hybrid Dynamical Systems through Hybrid Automata, IFAC-PapersOnLine, 49(12), 990–995.10.1016/j.ifacol.2016.07.571
Search in Google Scholar Back to article
12. Belkhiat D E.C., Manamanni N., Messai N., Djemai M. (2012), Fault detection isolation for a class of hybrid systems: A dedicated switched robust observer scheme, 2012 20th Mediterranean Conference on Control Automation (MED), 984–989.10.1109/MED.2012.6265766
Search in Google Scholar Back to article
13. Belkhiat D.E.C., Messai N., Manamanni N. (2011), Design of a robust fault detection based observer for linear switched systems with external disturbances, Nonlinear Analysis: Hybrid Systems, 5(2), 206–219.10.1016/j.nahs.2010.10.009
Search in Google Scholar Back to article
14. Branicky M. S. (1995), Studies in hybrid systems: Modeling, analysis, and control, Massachusetts Inst Of Tech Cambridge Lab For Information And Decision Systems.
Search in Google Scholar Back to article
15. Chanthery E., Pencolé Y., Ribot P., Travé-Massuyès L. (2015), HYDIAG: Extended diagnosis and prognosis for hybrid systems.
Search in Google Scholar Back to article
16. Chanthery E., Sztyber A., Travé-Massuyès L., Pérez-Zuñiga C.G. (2020), Process decomposition and test selection for distributed fault diagnosis, International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 914-925, Springer, Cham.10.1007/978-3-030-55789-8_78
Search in Google Scholar Back to article
17. Cocquempot V., El Mezyani T., Staroswiecki M. (2004), Fault detection and isolation for hybrid systems using structured parity residuals, 2004 5th Asian Control Conference (IEEE Cat. No. 04EX904), 2, 1204–1212.
Search in Google Scholar Back to article
18. Daher A. (2018), Default diagnosis and prognosis for a preventive and predictive maintenance, Application to a distillation column [PhD Thesis].
Search in Google Scholar Back to article
19. Deng Y., D’Innocenzo, A., Julius A.A. (2015), Trajectory-based observer for hybrid automata fault diagnosis, 2015 54th IEEE Conference on Decision and Control (CDC), 942–947.10.1109/CDC.2015.7401994
Search in Google Scholar Back to article
20. Derbel H. (2009), Diagnostic à base de modèles des systèmes temporisés et d’une sous-classe de systèmes dynamiques hybrides [PhD Thesis].
Search in Google Scholar Back to article
21. Ekanayake T., Dewasurendra D., Abeyratne S., Ma L., Yarlagadda P. (2019), Model-based fault diagnosis and prognosis of dynamic systems: A review, Procedia Manufacturing, 30, 435–442.10.1016/j.promfg.2019.02.060
Search in Google Scholar Back to article
22. Favela Contreras A. (1999), Modélisation et analyse du comportement dynamique des systèmes hybrides: Une approche basée sur le modèle d’automate hybride [PhD Thesis], Grenoble INPG.
Search in Google Scholar Back to article
23. Gara H., Saad K.B. (2020), Fault diagnosis for hybrid systems based on a bank of linear observers and a discrete automaton, SN Applied Sciences, 2(11), 1-9.10.1007/s42452-020-03564-7
Search in Google Scholar Back to article
24. Guo D., Zhong M., Ji H., Liu Y., Yang R. (2018), A hybrid feature model and deep learning based fault diagnosis for unmanned aerial vehicle sensors, Neurocomputing, 319, 155-163.10.1016/j.neucom.2018.08.046
Search in Google Scholar Back to article
25. Jang J.-S. (1992), Neuro-fuzzy modeling: Architectures, analyses, and applications, University of California, Berkeley.
Search in Google Scholar Back to article
26. Karsai G., Abdelwahed, S., Biswas, G. (2003), Integrated diagnosis and control for hybrid dynamic systems, AIAA Guidance, Navigation, and Control Conference and Exhibit, 5673.10.2514/6.2003-5673
Search in Google Scholar Back to article
27. Kechida S. (2007), Synthèse des générateurs de résidus robustes pour la détection de défauts [PhD Thesis], Université de Annaba-Badji Mokhtar.
Search in Google Scholar Back to article
28. Mahmoud M.S. (2018), Fuzzy control, estimation and diagnosis, Saudi Arabia: Springer International.10.1007/978-3-319-54954-5
Search in Google Scholar Back to article
29. Mhamdi L., Achbi M. S., Dhouibi H., Kechida S. (2020), Diagnosis of hybrid systems through bond graph, observers and timed automata, Diagnostyka, 21.10.29354/diag/126444
Search in Google Scholar Back to article
30. MI Rahal B. (2018), Modeling and robust fault diagnosis of hybrid system based on hybrid bond graph approach, Int Rob Auto J, 4(4), 266–272.10.15406/iratj.2018.04.00135
Search in Google Scholar Back to article
31. Olivier-Maget N., Hétreux G., Le Lann J.-M., Le Lann M.-V. (2008), Fault detection and isolation based on the model-based approach: Application on chemical processes, Computer Aided Chemical Engineering, 25, 411–416, Elsevier.10.1016/S1570-7946(08)80073-9
Search in Google Scholar Back to article
32. Patel H.R., Raval S.K., Shah V.A. (2021), A novel design of optimal intelligent fuzzy TID controller employing GA for nonlinear level control problem subject to actuator and system component fault, International Journal of Intelligent Computing and Cybernetics.10.1108/IJICC-11-2020-0174
Search in Google Scholar Back to article
33. Pérez-Zuñiga G., Rivas-Perez R., Sotomayor-Moriano J., Sánchez-Zurita V. (2020), Fault Detection and Isolation System Based on Structural Analysis of an Industrial Seawater Reverse Osmosis Desalination Plant, Processes, 8(9), 1100.10.3390/pr8091100
Search in Google Scholar Back to article
34. Pisano A., Rapaić M. R., Usai E. (2014), Discontinuous dynamical systems for fault detection, A unified approach including fractional and integer order dynamics, Mathematics and Computers in Simulation, 95, 111–125.10.1016/j.matcom.2012.09.007
Search in Google Scholar Back to article
35. Pislaru M., Trandabat A.F., Schreiner C. (2006), Neuro-fuzzy surveillance for industrial process fault detection.
Search in Google Scholar Back to article
36. Rivas-Perez R., Sotomayor-Moriano J., Pérez-Zuñiga G., Soto-Angles M.E. (2019), Real-time implementation of an expert model predictive controller in a pilot-scale reverse osmosis plant for brackish and seawater desalination, Applied Sciences, 9(14), 2932.10.3390/app9142932
Search in Google Scholar Back to article
37. Sadhukhan C., Mitra S.K., Naskar M.K., Sharifpur M. (2021), Fault diagnosis of a nonlinear hybrid system using adaptive unscented Kalman filter bank, Engineering with Computers, 1-12.10.1007/s00366-020-01235-0
Search in Google Scholar Back to article
38. Sayed-Mouchaweh M. (2018), Fault diagnosis of hybrid dynamic and complex systems, Springer.10.1007/978-3-319-74014-0
Search in Google Scholar Back to article
39. Sengupta S., Mukhopadhyay S., Deb A., Pattada K., De S. (2012), Hybrid automata modeling of SI gasoline engines towards state estimation for fault diagnosis, SAE International Journal of Engines, 5(3), 759–781.10.4271/2011-01-2434
Search in Google Scholar Back to article
40. Subbaraj P., Kannapiran B. (2011), Adaptive neuro-fuzzy inference system approach for fault detection and diagnosis of pneumatic valve in cement industry, International Journal of Computational Intelligence and Applications, 10(04), 399–423.10.1142/S1469026811003161
Search in Google Scholar Back to article
41. Sun S., Cui Z., Zhang X., Tian W. (2020), A hybrid inverse problem approach to model-based fault diagnosis of a distillation column, Processes, 8(1), 55.10.3390/pr8010055
Search in Google Scholar Back to article
42. Tabatabaeipour S., Ravn A.P., Izadi-zamabadi R., Bak T. (2009), Active diagnosis of hybrid systems—A model predictive approach, 2009 IEEE International Conference on Control and Automation, 465–470.10.1109/ICCA.2009.5410420
Search in Google Scholar Back to article
43. Tsuda K., Mignone D., Ferrari-Trecate G., Morari M. (2001), Reconfiguration strategies for hybrid systems, Proceedings of the 2001 American Control Conference (Cat. No. 01CH37148), 2, 868–873.10.1109/ACC.2001.945826
Search in Google Scholar Back to article
44. Uppal F. J., Patton R. J., Palade V. (2002), Neuro-fuzzy based fault diagnosis applied to an electro-pneumatic valve, IFAC Proceedings Volumes, 35(1), 477–482.10.3182/20020721-6-ES-1901.01633
Search in Google Scholar Back to article
45. Van Gorp J. (2013), Diagnostic et observation d’une classe de systèmes dynamiques hybrids, Application au convertisseur multicellulaire série [PhD Thesis].
Search in Google Scholar Back to article
46. Vento Maldonado J., Travé-Massuyès L., Sarrate Estruch R., Puig Cayuela V. (2013), Hybrid automaton incremental construction for online diagnosis, Proceedings DX’13, 186–191.
Search in Google Scholar Back to article
47. Viharos Z. J., Kis K. B. (2015), Survey on neuro-fuzzy systems and their applications in technical diagnostics and measurement, Measurement, 67, 126–136.10.1016/j.measurement.2015.02.001
Search in Google Scholar Back to article
48. Zhirabok A., Shumsky A. (2018), Fault diagnosis in nonlinear hybrid systems, International Journal of Applied Mathematics and Computer Science, 28(4), 635–648.10.2478/amcs-2018-0049
Search in Google Scholar Back to article
49. Zouaghi L., Alexopoulos A., Wagner A., Badreddin E. (2011), Modified particle petri nets for hybrid dynamical systems monitoring under environmental uncertainties, 2011 IEEE/SICE International Symposium on System Integration (SII), 497–502.10.1109/SII.2011.6147499
Search in Google Scholar Back to article