|
DESIGNING STATE-SPACE MODELS WITH NEURAL NETWORKS
Józef Korbicz* Marcin Mrugalski* Thomas Parisini**
* Institute of Control and Computation Engineering
University of Zielona Góra
ul.Podgórna 50, 65–246 Zielona Góra, Poland
fax: +48 68 3254615,
e-mail: {J.Korbicz,M.Mrugalski}@issi.uz.zgora.pl
** Department of Electrical, Electronic and Computer Engineering
DEEI-University of Trieste
Via Valerio 10 34127 Trieste, 20133 Milano, Italy
Italy Fax: +39 040 6763460,
e-mail: parisini@univ.trieste.it
This paper presents a new state-space identification framework for non-linear systems. In particular, a state-space model structure is designed with the Group Method of Data Handling type neural network. It is assumed that the neurons of the network have tangensoidal activation functions. For such a network type, a new approach based on a bounded-error set estimation technique is employed to estimate the parameters of the network. The final part of this work contains an llustrative example regarding the application of the proposed approach in the fault detection system.
Keywords: State-space models, neural networks, non-linear system identification, fault diagnosis
Session slot T-We-A10: Neuro-Fuzzy Applications of Fault Diagnosis/Area code 7e : Fault Detection, Supervision and Safety of Technical Processes
 | 