State and fault estimation for nonlinear recurrent neural network systems: Experimental testing on a three‐tank system

An observer is presented for the simultaneous estimation of the system state and actuator and sensor faults of a discrete recurrent neural network (RNN) system. The presented approach enables disturbance attenuation and guarantees observer convergence. First, the discrete RNN is converted to a discr...

Full description

Saved in:
Bibliographic Details
Published in:Canadian journal of chemical engineering 2020-06, Vol.98 (6), p.1328-1338
Main Authors: Zhang, Xiaoxiao, Feng, Xuexin, Mu, Zonglei, Wang, Youqing
Format: Article
Language:English
Subjects:
Actuators
Attenuation
fault estimation
H infinity
H∞ observers
Linear matrix inequalities
LPV systems
neural network
Neural networks
Nonlinear systems
Recurrent neural networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:An observer is presented for the simultaneous estimation of the system state and actuator and sensor faults of a discrete recurrent neural network (RNN) system. The presented approach enables disturbance attenuation and guarantees observer convergence. First, the discrete RNN is converted to a discrete linear parameter varying (LPV) model. Then, the LPV model is further transformed into a descriptor system by extending the system state and sensor fault. Next, an H∞ observer is presented for the simultaneous estimation of the extended state and actuator fault of the descriptor system. Finally, the problem of observer design is translated into solving a linear matrix inequality. Experimental tests on a three‐tank system have validated the effectiveness and correctness of the presented method.
ISSN:0008-4034
1939-019X
DOI:10.1002/cjce.23714