Development and application of a novel radial basis function sliding mode controller

Generally, physical systems have certain non-linear and time-varying behaviours and various uncertainties. It is difficult to establish an appropriate model for controller design. Adaptive and sliding mode control schemes have been employed to solve some of these problems under certain model-based conditions and limitations. Here a novel adaptive radial basis functions sliding mode control is proposed by combining the advantages of the adaptive, neural network and sliding mode control strategies without precise system model information. It has on-line learning ability to deal with the system time-varying and non-linear uncertainties by adjusting the control parameters. The proposed scheme is implemented on a three degree-of-freedom dynamic absorber system. Only five radial basis functions are required for this control system and their weightings can be established and updated continuously by on-line learning. The experimental results show that this intelligent control approach effectively suppresses the vibration amplitude of the main mass due to external disturbances.

[1]  Shiuh-Jer Huang,et al.  A Combination of Fuzzy Logic and Neural Network Algorithms for Active Vibration Control , 1996 .

[2]  Qing-Guo Wang,et al.  A framework for robust neural network-based control of nonlinear servomechanisms , 1994 .

[3]  R. L. Hardy.  Multiquadric equations of topography and other irregular surfaces , 1971 .

[4]  Kang G. Shin,et al.  Direct control and coordination using neural networks , 1993, IEEE Trans. Syst. Man Cybern..

[5]  Songwu Lu,et al.  Robust nonlinear system identification using neural-network models , 1998, IEEE Trans. Neural Networks.

[6]  Christopher Edwards,et al.  Sliding mode control : theory and applications , 1998 .

[7]  Chih-Lyang Hwang,et al.  Neural-network-based variable structure control of electrohydraulic servosystems subject to huge uncertainties without persistent excitation , 1999 .

[8]  V. Utkin.  Variable structure systems with sliding modes , 1977 .

[9]  Robert M. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991, 1991 American Control Conference.

[10]  J. J. Slotine,et al.  Tracking control of non-linear systems using sliding surfaces with application to robot manipulators , 1983, 1983 American Control Conference.

[11]  M. J. D. Powell,et al.  Radial basis functions for multivariable interpolation: a review , 1987 .

[12]  Vadim I. Utkin,et al.  Sliding Modes and their Application in Variable Structure Systems , 1978 .

[13]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

[15]  Tong Heng Lee,et al.  Real-time parallel adaptive neural network control for nonlinear servomechanisms—an approach using direct adaptive techniques , 1993 .

[16]  Fu-Chuang Chen,et al.  Adaptive control of non-linear continuous-time systems using neural networks—general relative degree and MIMO cases , 1993 .

[17]  T Poggio,et al.  Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks , 1990, Science.

[18]  J. Mason,et al.  Algorithms for approximation , 1987 .

[19]  M. V. C. Rao,et al.  A tunable fuzzy logic controller for vehicle-active suspension systems , 1997, Fuzzy Sets Syst..

[20]  Kumpati S. Narendra,et al.  Adaptive control using neural networks , 1990 .

[21]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[22]  R. P. Jones,et al.  Fuzzy logic control of an automotive suspension system , 1995 .

[23]  Kenneth Andrew Marko,et al.  Neural network architectures for active suspension control , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[24]  Edge C. Yeh,et al.  A fuzzy preview control scheme of active suspension for rough road , 1994 .