A novel robust-neuro control scheme for rotating disc vibrations is explored. In the approach proposed, a robust controller is first adopted to suppress the regulation error resulting from the unmodelled residuals while avoiding the spillover effect. In addition to the robust controller, a multilayer feedforward neural network is introduced to improve regulation performance. To maintain loop stability during neural network learning, a confinement algorithm for adaptive adjustment of the network weights is investigated. Simulation studies for a flexible rotating disc show that the control scheme proposed provides fast vibration suppression while maintaining robust stability.
MeirovitchL.Dynamics and Control of Structures, 1990 (John Wiley, New York).
2.
HuttonS. G.ChonanS.LehmannB. F.Dynamic response of a guided circular saw. J. Sound Vibr., 1987, 112, 527–539.
3.
RadcliffeC. J.MoteC. D.Jr.Identification and control of rotating disk vibration. Trans. ASME, J. Dynamic Syst., Measmt, Control, 1983, 105, 39–45.
4.
MoteC. D.Jr.RahimiA.Real time vibration control of rotating circular plates by temperature control and system identification. Trans. ASME, J. Dynamic Syst., Measmt Control, 1984, 106, 123–128.
5.
LeeC. W.ByunS. W.Optimal complex model-space control of rotating disc vibrations. Optimal Control Applic. Meth., 1988, 9, 371–401.
6.
ByunS. W.LeeC. W.Pole assignment in rotating disk vibration control using complex model state feedback. Mech. Syst. Signal Processing, 1988, 23, 225–241.
7.
KimC. S.LeeC. W.Travelling wave control of rotating discs and analysis of its spillover effect. Proc. Instn Mech. Engrs, Part C, Journal on Mechanical Engineering Science, 1988, 202 (C2), 119–127.
8.
YamY.LangJ. H.StaelinD. H.JohnsonT. L.The experimental computer control of a two-dimensional hyperbolic system. IEEE Trans. Autom. Control, 1988, 33, 79–87.
9.
BlantonM. L.SadekI. S.Optimal active point control of vibrating plates. J. Franklin Inst., 1992, 329, 801–815.
10.
EllisR. W.MoteC. D.Jr.A feedback vibration controller for circular saws. Trans. ASME, J. Dynamic Syst., Measmt, Control, 1979, 101, 44–49.
11.
ChoH. S.ChoY. C.Suboptimal controller design for active control of circular saw vibrations. Optimal Control Applic. Meth., 1981, 2, 299–310.
12.
FunahashiK. I.On the approximate realization of continuous mappings by neural networks. Neural Networks, 1989, 2, 183–192.
13.
IrwinG. W.WarwickK.HuntK. J. (Eds) Neural Network Applications in Control, 1995 (The Institution of Electrical Engineers, London).
14.
GuptaM. M.ShinhaN. K. (Eds) Intelligent Control Systems, 1996 (IEEE, New York).
15.
LamS.HungY. S.Stability analysis for dynamical neural network systems. In Proceedings of IEEE International Conference on Neural Networks, Orlando, Florida, 1994, pp. 960–963 (IEEE, New York).
16.
LimanondS.SiJ.Neural-network-based control design: An LMI approach. IEEE Trans. Neural Networks, 1998, 9, 1422–1429.
17.
LinC. L.ChenB. S.Robust observer-based control of large flexible structures. Trans. ASME, J. Dynamic Syst., Measmt, Control, 1994, 116, 713–722.
18.
LinC. L.Synthesis of real-time robust flexible structure controllers. Am. Inst. Aeronaut. Astronaut. J. Guidance, Control, and Dynamics, 1998, 21, 1001–1004.
19.
GahinetP.NemirovskiA.LaubA. J.ChilaiM.LMI Control Toolbox: For Use with MATLAB, 1995 (The Math Works, Natick, Massachusetts).
20.
VidyasagarM.Nonlinear Systems Analysis, 1993 (Prentice-Hall, Engtewood Cliffs, New Jersey).
21.
DesoerC. A.VidyasagarM.Feedback Systems: Input-Output Properties, 1975 (Academic Press, New York).
22.
LuenbergerD. G.Optimization by Vector Space Methods, 1969 (John Wiley, New York).
