Diagnosis by the multimodel approach in the frequency domain

The surveillance of the industrial systems is of a big importance to assure the productivity and the security. Several methods can lead to the location of the abnormalities which distort the system. Seen the complexity of the processes and their not linear characteristic in the industrial domain, the multimodel approach is recognized as advantageous because it represents the system sophisticated by a set models in the time. The methods of diagnosis with models were developed by observing the evolution of the system in the temporal domain. In this paper we proposed an extension of it in the frequency domain.

[1]  P. Borne,et al.  Multimodel control using fuzzy fusion , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[2]  Elom Ayih Domlan.  Diagnostic des systèmes à changement de régime de fonctionnement , 2006 .

[3]  B. Abdennour Ridha,et al.  A systematic determination approach of a models' base for uncertain systems: experimental validation , 2002, IEEE International Conference on Systems, Man and Cybernetics.

[4]  Thierry-Marie Guerra,et al.  A multi-model controller , 2008, 2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence).

[5]  P. Borne,et al.  On the quadratic stabilization in discrete multimodel control , 2003, Proceedings of 2003 IEEE Conference on Control Applications, 2003. CCA 2003..

[6]  C. Zheng,et al.  ; 0 ; , 1951 .