A robust friction compensation scheme is studied using a dual-friction-parameter observer and a recurrent neural network combined with sliding mode control. To handle non-linear friction parameters, a dual-friction-model-based observer is used to estimate the friction parameter of the LuGre friction model. In addition, an approximating method for the system uncertainty is developed using a recurrent neural network approach to improve the precision positioning degree. Simulated and experimental results are presented that validate the performance of the proposed friction compensation scheme.
SweversJ.Al-BenderF.GansemanC.PrajogoT.‘An integrated friction model structure with improved presliding behavior for accurate friction structure.’IEEE Trans. Autom. Control45 (4) (2000): 675–686
5.
ChoiJ. J.HanS. I.KimJ. S.‘Development of a novel dynamic friction model and precise tracking control using adaptive back-stepping sliding mode controller.’Mechatonics16 (2006): 87–104
6.
Al-BenderF.LampaertV.SweverJ.‘The generalized Maxwell-slip model: A novel model for friction simulation and compensation.’IEEE Trans. Autom. Control50 (11) (2005): 1883–1887
7.
de WitCanudas C.LischinskyP.‘Adaptive friction compensation with partially known dynamic friction model.’Int. J. Adapt. Control Signal Process.11 (1997): 65–80
8.
LischinskyP.de WitCanudas C.MorelG.‘Friction compensation for an industrial hydraulic robot.’Control Sys. Magazine IEEE19 (1) (1999): 25-32 DOI: 10.1109/37.745763
9.
GeS. S.LeeT. H.RenS. X.‘Adaptive friction compensation of servo mechanisms.’Int. J. Syst. Sci.32 (4) (2001): 523–532
10.
TanY.ChangJ.TanT.‘Adaptive backstepping control and friction compensation for AC servo with inertia and load uncertainties.’IEEE Trans. Ind. Electron.50 (5) (2003): 944–952
LiL.WangF. Y.ZhouQ. Z.‘Integrated longitudinal and lateral tire/road friction modeling and monitoring for vehicle motion control.’IEEE Trans. Intell. Transp. Syst.7 (1) (2006): 1–17
13.
HuangS. N.TanK. K.LeeT. H.‘Adaptive friction compensation using neural network approximation.’IEEE Trans. Syst. Man Cybern.30 (4) (2000): 551–557
14.
SelmicR.LewisF. L.‘Neural network approximation of piecewise continuous functions: Application to friction compensation.’IEEE Trans. Neural Netw.50 (5) (2002): 745–751
15.
16.
LinC. T.LeeC. S. G.Neural systems: a neural-fuzzy synergism to intelligent systems (Prenctice-Hall) 1996
17.
LeuY. G.LeeT. T.WangW. Y.‘On-line tuning of fuzzy-neural networks for adaptive control of nonlinear dynamic systems.’IEEE Trans. Syst. Man Cybern.27 (6) (1997): 1034–1043
18.
LinF. J.HwangW. J.WaiR. J.‘A supervisory fuzzy neural network control system for tracking periodic inputs.’IEEE Trans. Fuzzy Syst.7 (1) (1997): 41–52
19.
WaiR. J.LinF. J.‘Fuzzy neural network sliding-mode position controller for induction servo motor drive.’IEE Proc. B, Electr. Power Appl.146 (3) (1999): 297–308
20.
LinF. J.WaiR. J.‘Robust recurrent fuzzy neural network control for linear synchronous motor drive system.’Neurocomputing50 (2003): 365–390
21.
LinC. H.‘Adaptive recurrent fuzzy neural network control for synchronous reluctance motor servo drive.’IEE Proc. B, Electr. Power Appl.151 (6) (2004): 711–724
22.
PengJ. Z.WangY. N.SunW.‘Trajectory-tracking control for mobile robot using recurrent fuzzy cerebellar model articulation controller.’Neural Inform. Process.-Lett. Rev.11 (1) (2007): 15–23
23.
SlotineJ. E.LiW.Applied nonlinear control (Prentice-Hall, New Jersey) 1991
