Fault detection and accommodation plays a very important role in critical applications. A new software redundancy approach based on an adaptive neurofuzzy system (ANFIS) is introduced. An ANFIS model is used to detect the fault while another model is used to accommodate it. An accurate plant model is assumed with arbitrary additive faults. The two models are trained online using a gradient-based approach. The accommodation mechanism is based on matching the output of the plant with the output of a reference model. Furthermore, the accommodation mechanism does not assume a special type of system or nonlinearity. Simulation studies prove the effectiveness of the new system even when a severe failure occurs. Robustness to noise and inaccuracies in the plant model are also demonstrated.
References
-
-
1)
-
JONES, H.L.: `Failure detection in linear systems', 1973, PhD. thesis.
-
2)
-
J. DECKERT ,
M. DESAI ,
J. DEYST ,
A. WILLSKY
.
DFBW sensor failure identification using analytic redundancy.
IEEE Trans.
,
795 -
809
-
3)
-
ISERMANN, R.: `On the applicability of model-based fault detection for technical processes', Proceedings of the 12th IFAC World Congress, 1993, 3, p. 209–212.
-
4)
-
S. NIADU ,
E. ZAFIRIOU ,
T. M
.
Use of neural networks for sensor failure detection in control system.
IEEE Contr. Syst. Mag.
,
3 ,
49 -
55
-
5)
-
MIZUTANI, E., JANG, R.: `Coactive neural fuzzy modeling', Proceedings of the International Conference on Neural networks, 1995, p. 760–765.
-
6)
-
K. NARENDRA ,
J. BALAKRISHNAN ,
M. CILIZ
.
Adaptation and learning using multiple models, switching, and tuning.
IEEE Contr. Syst. Mag.
,
3 ,
37 -
51
-
7)
-
R. JANG
.
ANFIS: adaptive-network-based fuzzy inference systems.
IEEE Trans.
,
3 ,
665 -
685
-
8)
-
J.A. FARELL ,
T. BERGER ,
B. APPELBY
.
Using learning techniques to accommodate unanticipated faults.
IEEE Control Syst. Mag.
,
3 ,
40 -
49
-
9)
-
M.M. POLYCARPOU ,
A.J. HELMICKI
.
Automated fault detection and accommodation: a learning systems approach.
IEEE Trans.
,
11 ,
1447 -
1458
-
10)
-
KRISHNASWAMI, V., LUH, G.C., RIZZONI, G.: `Fault detection in ic engines using nonlinear parity equations', Proceedings of the American Control Conference, 1994, Baltimore, MD, p. 2001–2005.
-
11)
-
A.L. DEXTER
.
Fuzzy model based fault diagnosis.
IEE Proc., Contr. Theory Appl.
,
6 ,
545 -
550
-
12)
-
R. CLARK ,
D. FOSTH ,
V. WALTON
.
Detection instrument malfunctions in control systems.
IEEE Trans.
,
465 -
473
-
13)
-
Y. LEE ,
C. HWANG ,
Y. SHIH
.
A combined approach to fuzzy model identification.
IEEE Trans.
,
5 ,
736 -
744
-
14)
-
M. KITAMURA
.
Detection of sensor failures in nuclear plant using analytic redundancy.
Trans. Am. Nucl. Soc.
,
581 -
583
-
15)
-
J. GERTLER
.
Survey of model-based failure detection and isolation in complex plants.
IEEE Contr. Syst Mag.
,
6 ,
3 -
11
-
16)
-
T. TAKAGI ,
M. SUGENO
.
Fuzzy identification of systems and its application to modeling and control.
IEEE Trans.
,
110 -
132
-
17)
-
W. KWONG ,
K. PASSINO
.
Dynamically focused fuzzy learning control.
IEEE Trans.
,
1 ,
53 -
74
-
18)
-
R. MEHRA ,
I. PESHON
.
An innovations approach to fault detection and diagnosis in dynamic systems.
Automatica
,
637 -
640
-
19)
-
R.J. PATTON ,
S.W. WILLCOX ,
J.S. WINTER
.
A parameter insensitive technique for aircraft sensor fault analysis.
AIAA J. Guidance Cont. Dyn.
,
10 ,
359 -
367
-
20)
-
E.G. LAUKONEN ,
K. PASSINO ,
V. KRISHNASWAMI ,
G. LUH ,
G. RIZZONI
.
Fault detection and isolation for an experimental internal combustion engine via fuzzy identication.
IEEE Trans.
,
3 ,
347 -
355
-
21)
-
LEVIN, E., GEWIRTZMAN, R., INBAR, G.: `Neural network architecture for adaptive system modeling and control', Proceedings of 1989 International Joint Conference on Neural networks, 1989, 2, p. 311–316.
-
22)
-
K.S. NARENDRA ,
K. PARTHASARATHY
.
Identifcation and control of dynamical systems using neural networks.
IEEE Trans.
,
4 -
27
-
23)
-
J.-S.R. Jang ,
C.-T. Sun ,
E. Mizutani
.
(1997)
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence.
-
24)
-
E. LAUKONEN ,
K. PASSINO
.
Training fuzzy systems to perform estimation and identification.
Engng Appli. AI
,
5 ,
449 -
514
-
25)
-
C.A. JACOBSON ,
C. NETT
.
An integrated approach to controls and diagnostics using the four parameters controller.
IEEE Contr. Syst. Mag.
,
22 -
29.
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-cta_20010463
Related content
content/journals/10.1049/ip-cta_20010463
pub_keyword,iet_inspecKeyword,pub_concept
6
6