» Download Article

Authors
Amara, Zied; Berard, Caroline; Bordeneuve-Guibé, Joel

Digital Object Identifier (DOI)
10.3182/20080706-5-KR-1001.01166

Page Numbers:
6879-6884

Index Terms
Fuzzy logic; Neural networks technology

Abstract
In this paper we addressed the problem of improving the control of AC motors used for the specific application of 3 degrees of freedom moving base flight simulator. Indeed the presence of backlash in DC motors gearboxes induces shocks and naturally limits the flight feeling. A comparison is hence set up between two techniques aiming to deal with this problem: Adaptive Fuzzy Controller and Neural Controller. Dynamic inversion with Fuzzy Logic is used to design an adaptive backlash compensator. The classification property of fuzzy logic techniques makes them a natural candidate for the rejection of errors induced by the backlash. A tuning algorithm is given for the fuzzy logic parameters, so that the output backlash compensation scheme becomes adaptive. The compensator uses the Neural Networks techniques demonstrate that artificial neural networks can be used to compensate hysteresis caused by gear backlash in precision position-controlled mechanisms. A major contribution of this research is that physical analysis of the system nonlinearities and optimal control are used to design the neural network structure.

References

Amara Z., Bordeneuve-Guib� J. (2007). Control of new kind
of moving base simulator�, Conference on Systems and
control. Marrakech, Morocco.
Amara Z., Bordeneuve-Guib� J. (2007). Improvement of
flight simulator feeling using Adaptive Fuzzy Controller,
in IEEE, Power Control session. Taiwan.
Amara Z., Bordeneuve-Guib� J. (2007). Adaptive Fuzzy
Backlash compensation For a New Dynamic Flight
Simulator, IFAC AFNC. Valenciennes, France.
Guely F., Siarry P. (1991). Gradient descent method for
optimizing various fuzzy rule bases�. IEEE, pp. 1241�
1246, 2000.
Horikawa S., Furuhashi T. (1993), .On identification of
structures in premises of a fuzzy model using a fuzzy
neural network ,IEEE pp. 606� 611.
Hod K., Stinchcombe M., and White H., (2005). Multilayer
Feed forward networks are universal approximators,
Neural Networks, vol.2.
Harris C.J, Moore C.G.( 2002). Intelligent identification and
control for autonomous guided vehicles using adaptive
fuzzy-based algorithms, Engineering Applications of
Artificial Intelligence 2, 267�285,.
Harris C.J, Moore C.G. (1993), �Intelligent control - aspects
of fuzzy logic and neural nets�,Singapore: World
Scientific,.
Jager R,. Verbruggen H.B, Adaptive fuzzy control, In
Proceedings European Simulation Symposium, Ghent,
Belgium, pp. 140�144. SCS.
Jang J. 0, (July 2002) Backlash compensation of nonlinear
systems using fuzzy logic, Proc. IFAC 151h World
Congers.
Rumelhart D. E, Hinton G. E., and Williams R. J.,
�Learning intemal representations by error propagation,�
Parallel Distributed Processing. Cambridge, MA: MIT
Press, 2001, pp. 45-76. 1967, pp. 128-130.
Slotine J.-J. E., Li W.( 1991) Applied Nonlinear Control
Englewood. Cliffs, NJ: Prentice-Hall.
Seidl R. (1995) Neural network compensation of gear
backlash hysteresis in position-controlled mechanisms,
In Proc IEEE Ind. Applicat, vol.31, N� 6.
Seild R. (1996) .Mention and motor control using neural
network , University of WISCONSIN-MADISON.
Shimojima I., Fukuda T. (Oct. 2005), Fuzzy neural networks
based on spline functions, in IEEE, Neural Networks
session, . Proceedings of International Joint Conference
on Volume 1, Issue, 25-29 Page(s): 754 - 757 vol.1