The paper describes the design method of a neural/fuzzy variable structural proportional-integral-derivative (neural/fuzzy VSPID) control system. The neural/fuzzy VSPID controller has a structure similar to that of the conventional PID. In this controller, the PD mode is used in the case of large errors to speed up response, whereas the PI mode is applied for small error conditions to eliminate the steady-state offset. A sigmoidal-like neuron is employed as a preassigned algorithm of the law of structural change. Meanwhile, the controller parameters would be changed according to local conditions. Bounded neural networks or bounded fuzzy logic systems are used for constructing the nonlinear relationship between the PID controller parameters and local operating control conditions. Flexible changes of controller modes and resilient controller parameters of the neural/fuzzy VSPID during the transient could thereby solve the typical conflict in nature between steady-state error and dynamic responsiveness. A neutralisation process is used to demonstrate the applicability of such a controller for controlling highly nonlinear processes.
References
-
-
1)
-
H. Wang ,
M. Brown ,
C.J. Harris
.
Neural network modelling of unknown nonlinear systems subject to immeasurabledisturbances.
IEE Proc., Control Theory Appl.
,
4 ,
216 -
222
-
2)
-
F.C. Clark
.
PID algorithms and their computer implementation.
Trans. Inst. Meas. Control
,
305 -
316
-
3)
-
F.G. Shinskey
.
(1988)
Process control systems: application, design, and tuning.
-
4)
-
S.N. Kavuri ,
V. Venkatasubramanian
.
Using fuzzy clustering with ellipsoidal units in neural networks forrobust fault classification.
Comput. Chem. Eng.
,
8 ,
765 -
784
-
5)
-
G. Lightbody ,
G.W. Irwin
.
Direct neural model reference adaptive control.
IEE Proc., Control Theory Appl.
,
1 ,
31 -
43
-
6)
-
W.C. Chen ,
C.L. Chen
.
Nonlinear PI controller design: a neural network approach.
J. Chin. I. Chem. E.
,
2 ,
67 -
79
-
7)
-
J. Park ,
I.W. Sandberg
.
Approximation and radial-basis-function networks.
Neural Comput.
,
305 -
316
-
8)
-
J. Moody ,
C.J. Darken
.
Fast learning in networks of locally-tuned processing units.
Neural Comput.
,
281 -
294
-
9)
-
F.C. Chen
.
Back-propagation for nonlinear self-tuning adaptive control.
IEEE Control Syst. Mag.
,
44 -
48
-
10)
-
D.H. Nguyen ,
B. Widrow
.
Neural networks for self-learning control system.
IEEE Control Syst. Mag.
,
18 -
23
-
11)
-
S. Horikawa ,
T. Furuhashi ,
Y. Uchikawa
.
On fuzzy modelling using fuzzy neural networks with backpropagation algorithm.
IEEE Trans. Neural Netw.
,
801 -
806
-
12)
-
T.J. McAvoy ,
E. Hsu ,
S. Lowenthal
.
Dynamics of pH in controlled stirred tank reactor.
Ind. Eng. Chem. Process Des. Develop.
,
68 -
70
-
13)
-
J.R. Raol
.
Neural network based parameter estimation of unstable aerospace dynamicsystems.
IEE Proc., Control Theory Appl.
,
6 ,
385 -
388
-
14)
-
D. Psaltis ,
A. Sideris ,
A.A. Yamamura
.
A multilayered neural network controller.
IEEE Control Syst. Mag.
,
17 -
21
-
15)
-
S. Tan ,
Yu. Lin ,
P. Wang ,
S. He
.
Objective-centered formulation of an adaptive fuzzy control scheme.
Int. J. Uncertainty, Fuzziness and Knowledge-Based Syst.
,
3 ,
321 -
331
-
16)
-
C.L. Chen ,
W.C. Chen ,
F.Y. Chang
.
Hybrid learning algorithm for Gaussian potential function networks.
IEE Proc. D
,
6 ,
442 -
448
-
17)
-
L.X. Wang
.
(1994)
Adaptive fuzzy systems and control.
-
18)
-
Y.Y. Yang ,
D.A. Linkens
.
Adaptive neural-network-based approach for the control of continuouslystirred tank reactor.
IEE Proc., Control Theory Appl.
,
5 ,
341 -
349
-
19)
-
A. Jutan
.
A nonlinear PI(D) controller.
Can. J. Chem. Eng.
,
485 -
493
-
20)
-
S. CHEN ,
C. COWAN ,
P. GRANT
.
Orthogonal least squares learning algorithm for radial basis function networks.
IEEE Trans. Neural Netw.
,
302 -
309
-
21)
-
Powell, M.J.D.: `Radial basis function for multivariate interpolation: a review', DAMPT 1985/NA12, Technical report, 1985.
-
22)
-
M. Vidyasagar
.
(1978)
Nonlinear system analysis.
-
23)
-
D.E. Rumelhart ,
G.E. Hinton ,
R.J. Williams ,
D.E. Rumelhart ,
J.L. McClelland
.
(1986)
Learning internal representations by error propagation, Parallel distributed processing: explorations in the microstructuresof cognition. Vol.1: foundations.
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-cta_19960261
Related content
content/journals/10.1049/ip-cta_19960261
pub_keyword,iet_inspecKeyword,pub_concept
6
6