Hydraulic and pneumatic components are widely used in vehicle semi-active or active suspension systems. These dynamic systems have certain non-linear and time-varying behaviours. It is difficult to establish an appropriate dynamic model for model-based controller design. Here, a novel neural network based sliding mode control is proposed by combining the advantages of the adaptive, radial basis function neural network and sliding mode control strategies to release the model information requirement. It has online learning ability for handling the system time-varying and non-linear uncertainty behaviours by adjusting the neural network weightings and/or radial basis function parameters. It is implemented on a quarter-car hydraulic active suspension system. The minimum number of radial basis functions required for this neural network is 5. The experimental results show that this intelligent control approach effectively suppresses the oscillation amplitude of sprung mass in response to road surface disturbances.
NarendraK. S.Adaptive control using neural network. In Neural networks for control (Eds MillerW. T.SuttonR. S.WerbosP. J.), 1991, pp. 115–142 (MIT Press, Cambridge, Massachusetts).
2.
CuiX.ShinK. G.Direct control and coordination using neural networks. IEEE Trans. Syst., Man, and Cybernetics, 1993, 23 (3), 686–697.
3.
SannerR. M.SlotineJ.-J. E.Gaussian network for direct adaptive control. IEEE Trans. Neural Networks, 1992 (November), 3, 837–863.
4.
HwangC. L.Neural-network-based variable structure control of electrohydraulic servosystems subject to huge uncertainties without persistent excitation. IEEE/ASME Trans. Mechatronics, 1999, 4 (1), 50–59.
5.
CherryA. S.JonesR. P.Fuzzy logic control of an automotive suspension system. IEE Proc. Control Theory Applic., 1995, 142 (2), 149–160.
6.
YehE. C.TsaoY. J.Fuzzy preview control scheme of active suspension for rough road. Int. J. Veh. Des., 1994, 15, 166–180.
7.
D'AmatoF. J.ViassoloD. E.Fuzzy control for active suspensions. Mechatronics, 2000, 10, 897–920.
8.
KuoY. P.LiT. H. S.GA-based fuzzy PI/PD controller for automotive active suspension system. IEEE Trans. Ind. Electronics, 1999, 46 (6), 1051–1056.
9.
HampoR.MarkoK.Neural network architectures for active suspension control. In Proceedings of IJCNN-International Joint Conference onNeural Network, 1992, pp. 765–770.
10.
RongY.BaoX.An automobile semi-active suspension system using neural network control and simulation. In Proceedings of International Conference onIntelligent Mechatronics and Automation, Chengdu, China, 26–31 August 2004, pp. 187–190.
11.
SpentzasK.KanarachosS. A.Design of a non-linear hybrid car suspension system using neural networks. Math. and Computers in Simulation, 2002, 60, 369–378.
12.
RaoM. V.C.PrahladV.A tuneable fuzzy logic controller for vehicle active suspension system. Fuzzy Sets Syst., 1997, 85, 11–21.
13.
HuangS.-J.LinW.-C.A self-organizing fuzzy controller for an active suspension system. J. Vibr. and Control, 2003, 9 (9), 1023–1040.
14.
KimC.RoP. I.A sliding mode controller for vehicle active suspension systems with nonlinearities. InProc. Instn Mech. Engrs, Part D: J. Automobile Engineering, 1998, 212 (2), 79–92.
15.
SamY. M.OsmanJ. H. S.GhaniM. R. A.A class of proportional-integral sliding mode control with application to active suspension system. Syst. and Control Lett., 2004, 51, 217–223.
16.
YoshimuraT.KumeA.KurimotoM.HinoJ.Construction of an active suspension system of a quarter car model using the concept of sliding mode control. J. Sound and Vibr., 2001, 239, 187–199.
17.
ChenP. C.HuangA. C.Adaptive sliding control of active suspension systems based on function approximation technique. J. Sound and Vibr., 2005, 282, 1119–1135.
18.
HuangS.-J.LinW.-C.Adaptive fuzzy controller with sliding surface for vehicle suspension control. IEEE Trans. Fuzzy Syst., 2003, 11 (4), 550–559.
19.
SmithM. C.WangF. C.Controller parameterization for disturbance response decoupling: Application to vehicle suspension control. IEEE Trans. Control Syst. Technol., 2002, 10 (3), 397–407.
20.
HuangS. J.LianR. J.A combination of fuzzy logic and neural network algorithms for active vibration control. Proc. Instn Mech. Engrs, 1996, 210, 153–167.
21.
Al-HolonN.LahdhiriT.JooD. S.Al-AbbasF.Sliding mode neural network inference fuzzy logic control for active suspension systems. IEEE Trans. Fuzzy Syst., 2002, 10 (2), 234–246.
22.
HardyR. L.Multiquadric equations of topography and other irregular surfaces. J. Geophys. Res., 1971, 76, 1905–1915.
23.
PowellM. J. D.Radial basis functions for multi-variable interpolation: A review. In Algorithms for approximation (Eds MasonJ. C.CoxM. G.), 1987, pp. 143–167 (Clarendon, Oxford).
24.
PowellM. J. D.The theory of radial functions for multivariable approximation in 1990. The advances in numerical analysis (Ed. LightW.), 1992 (Oxford University Press, Oxford).
25.
PoggioT.GirosiF.Regularization algorithms for learning that are equivalent to multiplayer networks. Science, 1990, 247 (February), 978–982.
26.
LuS.BasarT.Robust nonlinear system identification using neural-network models. IEEE Trans. Neural Networks, 1998, 9 (3), 407–429.
27.
LiuC. C.ChenF. C.Adaptive control of nonlinear continuous time systems using neural networks general relative degree and MIMO case. Int. J. Control, 1993, 58 (2), 317–335.
28.
UtkinV. I.Variable structure systems with sliding modes. IEEE Trans. Autom. Control, 1977, AC-22 (2), 212–222.
29.
UtkinV. I.Sliding modes and their applications in variable structure systems, 1978 (Mir Moscow).
30.
SlotineJ.-J. E.Tracking control of nonlinear systems using sliding surfaces. Doctoral Dissertation, Massachusetts Institute of Technology, Cambridge, Massachusetts, 1983.
EdwardsC.SpurgeonS. K.Sliding mode control - theory and applications, 1998 (Taylor and Francis, London-Bristol).
33.
NarendraK. S.AnnaswamyA. M.A new adaptive law for robust adaptation without persistent excitation. IEEE Trans. Autom. Control, 1987, AC-32 (2), 134–145.
34.
ChenF. C.KhalilH. K.Adaptive control of nonlinear systems using neural networks a dead zone approach. In Proceedings of the 1991 American Control Conference, Boston, MA, 1991, pp. 667–672.
