A method of controlling certain types of nonlinear dynamical systems whose dynamics can be modelled by a multilayer neural network is proposed. The control algorithm assumes that the plant equations are not known but the dimension of the system is known. The control input is derived by inversion of a forward neural network via the Newton Raphson method. During inversion of the multilayer neural network some optimal control senses are resolved. To suppress the control error due to the modelling error of the forward neural network, the inversion controller with a conventional feedback controller is proposed, which provides a better performance than a pure inversion controller. The proposed algorithm shows various advantages, and computer experiments on a bioreactor prove the effectiveness of this algorithm.
References
-
-
1)
-
D.A. Hoskins ,
J.N. Hwang ,
J. Vagners
.
Iterative inversion of a neural network and its application to adaptivecontrol.
IEEE Trans. Neural Netw.
,
2 ,
292 -
301
-
2)
-
D.E. Rumelhart ,
G.E. Hinton ,
R.J. Williams
.
Learning internal representations by error propagation.
Parallel Dist. Process.
-
3)
-
G. CYBENKO
.
Approximation by superpositions of a sigmoidal function.
Math. Control Signals Syst.
,
303 -
314
-
4)
-
K. Hornik ,
M. Stinchcombe ,
H. White
.
Multilayer feedforward networks are universal approximators.
Neural Netw.
,
359 -
399
-
5)
-
H. Miyamoto ,
M. Kawato ,
T. Setoyama ,
R. Suzuki
.
Feedback-error-learning neural network for trajectory control of a roboticmanipulator.
Neural Netw.
,
251 -
265
-
6)
-
A. Behera ,
M. Gopal ,
S. Chaudhury
.
Inversion of RBF networks and applications to adaptive control of nonlinearsystems.
IEE Proc. D
,
6 ,
617 -
624
-
7)
-
G. Lightbody ,
G.W. Irwin
.
Direct neural model reference adaptive control.
IEE Proc. D
,
1 ,
31 -
43
-
8)
-
L.H. Ungar ,
T. Miller ,
W. Shutton ,
P.J. Werbos
.
(1990)
A bioreactor benchmark problem for adaptive network-based process control, Neural networks for control.
-
9)
-
M. Iwata ,
S. Kitamura
.
An input tracking control systems and an input estimation system usinga feedforward model on neural network.
Trans. Soc. Instrum. Control Eng.
,
3 ,
303 -
309
-
10)
-
M. Gupta ,
H. Rao
.
(1994)
Neuro-control systems.
-
11)
-
K.J. Hunt ,
D. Sbárbaro ,
R. Zbikowsky ,
P.J. Gawthrop
.
Networks for control systems – a survey.
Automatica
,
6 ,
1083 -
1112
-
12)
-
J.W. Lee ,
J.H. Oh
.
Hybrid learning of errors and Jacobian in multilayer perceptron neuralnetworks.
Neural Comput.
,
5 ,
937 -
958
-
13)
-
Y.Y. Yang ,
D.A. Linkens
.
Adaptive neural network-based approach for the control of continuouslystirred tank reactor.
IEE Proc. D
,
5 ,
341 -
349
-
14)
-
Gomi, H., Kawato, M.: `Learning control for a closed loop system using feedback error learning', Proceedings of 29th IEEE conference on Decision and control, 1990, p. 3289–3294.
-
15)
-
W.T. Miller ,
R.S. Sutton ,
P.J. Werbos
.
(1990)
Neural networks for control.
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-cta_19971360
Related content
content/journals/10.1049/ip-cta_19971360
pub_keyword,iet_inspecKeyword,pub_concept
6
6