In this paper a neural network adaptive force controller is proposed for a hydraulic system. The dynamic model of this system is highly non-linear and very complex to obtain. Thus, it is considered as a black box and a priori identification becomes necessary. A neural network is used to approximate the model and then a controller using the Lyapunov approach is designed. The neural network parameters are updated online according to an adaptation algorithm obtained via stability analysis. The performance of the proposed neural network controller is validated on an experimental plant.
MerritH. E.Hydraulic Control Systems, 1967 (John Wiley, New York).
2.
LiD.SalcudeanS. E.Modeling, simulation and control of hydraulic stewart platform. In Proceedings of IEEE International Conference onRobotics and Automation, April 1997.
3.
YunY. S.ChoH. S.Adaptive model following control of electrohydraulic velocity control systems subjected to unknown disturbances. IEE Proc., March 1998, 135 (2), 149–156.
4.
BobrowJ. E.LumK.Adaptive, high bandwidth control of a hydraulic actuator. In Proceedings of 1995 American Control Conference, Evanston, Illinois, June 1995, pp. 71–75 (American Automatic Control Council).
5.
ChernT.WuY.An optimal variable structure control with integral compensation for electrohydraulic position servo control systems. IEEE Trans. Ind. Electronics, October 1992, 39, 460–463.
6.
YanadaH.ShimaharaM.Sliding mode control of an electrohydraulic servo motor using a gain scheduling type observer and controller. Proc. Instn Mech. Engrs, Part I: J. Systems and Control Engineering, 1997, 211 (16), 407–416.
7.
HahnH.PiepenbrinkA.LeimbachK. D.Input/output linearization control of an electro-servo-hydraulic actuator. In Proceedings ofIEEE Conference on Control Applications, UK. 1994, pp. 995–1000.
8.
VossoughiG.DonathM.Dynamic feedback linearization for electrohydraulically actuated control systems. Trans. ASME, J. Dynamic Systems, Measmt, and Control, December 1995, 117, 468–477.
9.
SholG. A.BobrowJ. E.Experimentaland simulations on the nonlinear control of a hydraulic servosystem. IEEE Trans. Control Systems Technol., March 1999, 7, 238–247.
10.
AlleyneA.HedrickK.Nonlinear adaptive control of active suspensions. IEEE Trans. Control Systems Technol., March 1995, 3, 94–101.
11.
AlleyneA.Nonlinear force control of an electrohydraulic actuator. In Proceedings of 1996 Japan/USA Symposium onFlexible Automation, Boston, Massachusetts, 1996, pp. 193–200.
12.
13.
LavalL.Commande robuste en force d'un actionneur hydraulique confronté à un environnement incertain. Thèse de doctorat, Université Paris 6, France, 1997.
14.
LavalL.M'SirdiN. K.Modeling, identification and robust force control of hydraulic actuator usingH approach. In Proceedings of IMACS Internationál Symposium on System Analysis and Simulation, Berlin, Germany, 1995.
15.
MokhtariA.LavalL.M'SirdiN. K.Commande en force explicite d'un système hydraulique par l'approche GH polynomiale. In Proceedings of Conférence Intérnationale Francophone d'Automatique (CIFA'2000), Lille, France, 2000.
16.
IwasaT.MorizumiN.OmatuS.Temperature control in a batch process by neural networks. International Conference onRobotics and Automation, 1998, pp. 992–995.
17.
HemerlyE. M.NascimentoC. L.An NN-based approach for tuning servocontrollers. J. Neural Networks, 1998, 3, 157–163.
18.
19.
BenallegueA.MeddahD. Y.DaachiB.Neural network identification and control of a class of non linear systems. In Proceedings of 16th IMACS World Congress onScientific Computation, Applied Mathematics and Simulation, Lausanne, Switzerland, 2000.
20.
DaachiB.BenallegueA.M'SirdiN. K.Sliding mode observer and adaptive neural network control for rigid robot manipulators. In Proceedings of International Conference onNeural Information Processing (ICONIP'2000), Taejon, Korea, 2000.
