Identification of neural dynamic models for fault detection and isolation: The case of a real sugar evaporation process

Journal of Process Control

Volumn 15, Issue 1, 2005, Pages 67-79

  Patan, Krzysztof ^a   Parisini, Thomas ^b  

^a UNIVERSITY OF ZIELONA GÓRA   (Poland)

^b UNIVERSITY OF TRIESTE   (Italy)

Author keywords

Actuators; Fault detection and isolation; Neural networks; Sensors; Stochastic approximation

Indexed keywords

DYNAMIC NEURON MODELS; FAULT DETECTION AND ISOLATION; MATHEMATICAL TOOLS; STOCHASTIC APPROXIMATION;

ACTUATORS; EVAPORATION; FEEDFORWARD NEURAL NETWORKS; IDENTIFICATION (CONTROL SYSTEMS); MATHEMATICAL MODELS; RANDOM PROCESSES; SENSORS; SUGAR MANUFACTURE;

PROCESS CONTROL;

EID: 4444329484     PISSN: 09591524     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jprocont.2004.04.001     Document Type: Article

References (25)

1. M. Ayoubi, Fault diagnosis with dynamic neural structure and application to a turbo-charger, in: Proc. Int. Symp. Fault Detection Supervision and Safety for Technical Processes, SAFEPROCESS'94, Espoo, Finland, vol. 2, 1994, pp. 618-623.
2. M. Bartyś, J.M. Kościelny, Application of fuzzy logic fault isolation methods for actuator diagnosis, in Proc. 15th IFAC Triennial World Congress, b'02. Barcelona, Spain, July 21-26, 2002. Published on CD-ROM.
3. Calado J.M.F., Korbicz J., Patan K., Patton R.J., Sa da Costa J.M.G. Soft computing approaches to fault diagnosis for dynamic systems. European Journal of Control. 7(2-3):2001;248-286.
4. Chen J., Patton R.J. Robust Model-Based Fault Diagnosis for Dynamic Systems. 1999;Kluwer Academic Publishers, Berlin.
5. Chin D.C. A more efficient global optimization algorithm based on Styblinski and Tang. Neural Networks. 7:1994;573-574.
6. P.M. Frank, Fuzzy supervision. Application of fuzzy logic to process supervision and fault diagnosis, in: Proc. Int. Workshop Fuzzy Technologies in Automation and Intelligent Systems, Fuzzy Duisburg'94, Duisburg, Germany, 1994, pp. 36-59.
7. Frank P.M., Köppen-Seliger B. New developments using AI in fault diagnosis. Artificial Intelligence. 10(1):1997;3-14.
8. Gertler J. Fault Detection and Diagnosis in Engineering Systems. 1999;Marcel Dekker, Inc, New York.
9. Guglielmi G., Parisini T., Rossi G. Fault diagnosis and neural networks: a power plant application (keynote paper). Control Engineering Practice. 3(5):1995;601-620.
10. Isermann R. Process fault detection and diagnosis methods. Ruokonen T. Proc. IFAC Symposium SAFEPROCESS'94, Helskinki, Finland. vol. 2:1994;Pergamon Press, Helsinki, Finland.
11. R. Isermann (Ed.) Supervision Fault Detection and Diagnosis of Technical Systems - Special Section, Control Engineering Practice 5(5) (1997).
12. Korbicz J., Patan K., Obuchowicz A. Dynamic neural networks for process modelling in fault detection and isolation systems. International Journal of Applied Mathematics and Computer Science. 9(3):1999;519-546.
13. Korbicz J., Patan K., Obuchowicz A. Neural network fault detection system for dynamic processes. Bulletin of the Polish Academy of Sciences. Technical Sciences. 49(2):2001;301-321.
14. J.M. Kościelny, A. Ostasz, P. Wasiewicz, Fault detection based on fuzzy neural networks - application to Sugar Factory Evaporator, in: Proc. Int. Symp. Fault Detection Supervision and Safety for Technical Processes, SAFEPROCESS 2000, Budapest, Hungary, 2000, pp. 337-342.
15. Ljung L. System Identification - Theory for the User. 1999;Prentice Hall.
16. Norgard M., Ravn O., Poulsen N.M., Hansen L.K. Networks for Modelling and Control of Dynamic Systems. 2000;Springer-Verlag, London.
17. K. Patan, Artificial dynamic neural networks and their application in modelling of industrial processes, Ph.D. dissertation, Warsaw University of Technology, Faculty of Mechatronics, Warszawa, 2000.
18. K. Patan, Fault detection of the actuators using neural networks, in: Proc. 7th IEEE Int. Conf. Methods and Models in Automation and Robotics, MMAR 2001, Miȩdzyzdroje, Poland, August 28-31, vol. 2, 2001, pp. 1085-1090.
19. K. Patan, T. Parisini, Stochastic approaches to dynamic neural network training. Actuator fault diagnosis study, in: Proc. 15th IFAC Triennial World Congress, b'02, Barcelona, Spain, July 21-26, 2002. Published on CD-ROM.
20. K. Patan, T. Parisini, Stochastic learning methods for dynamic neural networks: simulated and real-data comparisons, in: Proc. 2002 American Control Conference, ACC'02, Anchorage, Alaska, USA, May 8-10, 2002, pp. 2577-2582.
21. R.J. Patton, J. Chen, T.M. Siew, Fault diagnosis in nonlinear dynamic systems via neural networks, in: Proc. of CONTROL'94, Coventry, UK, vol. 2, 1994, pp. 1346-1351.
22. Patton R.J., Frank P.M., Clark R.N. Issues of Fault Diagnosis for Dynamic Systems. 2000;Springer-Verlag, Berlin.
23. Spall J.C. Multivariate stochastic aproximation using a simultaneous perturbation gradient approximation. IEEE Transactions of Automatic Control. (37):1992;332-341.
24. Spall J.C. Stochastic optimization, stochastic approximation and simulated annealing. Webster J.G. Encyclopedia of Electrical and Electronics Engineering. 1999;John Wiley &Sons, New York.
25. Walter E., Pronzato L. Identification of Parametric Models from Experimental Data. 1996;Springer, London.