A NEURAL NETWORK CONTROLLER OPTIMISED WITH MULTI OBJECTIVE GENETIC ALGORITHMS FOR A LABORATORY ANTI-LOCK BRAKING SYSTEM

K LAMAMRA, K BELARBI, J BOSCHE, A EL HAJJAJI

Résumé


In this work, we consider the design of a neural network controller for the ABS laboratory system witch’s highly non linear. The objective is to control the wheel slip. The controller is designed off-line using a multi-objective optimisation process solved using a multi objective genetic algorithms. The objective of the design process is to find a satisfactory controller with a reasonable structure. The structure is defined as the number of input variables and the number of neurons in the hidden layer. Thus the multi objective genetic algorithms has to minimize three objectives: the number of neurons in the hidden layer, the error which is the difference between the wheel slip reference and the real wheel slip and the third objective is the number and type of inputs to the network.  The results of simulation are encouraging.


Mots-clés


ABS systems; Neural Network; Multi Objective Genetic Algorithms

Texte intégral :

PDF

Références


J.R. Choa, J.H. Choia,W.S.Yooa, G.J. Kimb, J.S.Woob, “Estimation of dry road braking distance considering frictional energy of patterned tires”, Science Direct, Finite Elements in Analysis and Design 42, 1248 – 1257, 2006.

M. Gavas, M. Izciler, “Deep drawing with anti-lock braking system (ABS)”, Science Direct, Mechanism and Machine Theory 41, 1467–1476, 2006.

K. Karakoc, “Design of a Magnetorheological Brake System Based on Magnetic Circuit Optimization”, master of applied science thesis, BSc - Bogazici University, turkey, 2005.

Ming-chin Wu, Ming-chang Shih, “Simulated and experimental study of hydraulic anti-lock braking system using sliding-mode PWM control”, Elsevier Science Ltd, Mechatronics 13, 331–351, 2003.

W.P. Fu, Z.D. Fang, Z.G. Zhao, Periodic solutions and harmonic analysis of an anti-lock brake system with piecewise-nonlinearity, J. Sound Vib. 246 (3), 543–550, 2001.

A. B. Will, S. Hui and S. Zak, ”Sliding Mode Wheel Slip Controller for an Antilock Braking System”, Int. J. of Vehicle Design, 19(4), p523-539, 1998.

K. Hornik, M. Stinchombe, and H. White, ‘’Multilayer feedforward networks are universal approximators’’, Neural netwoks ,vol. 2, pp. 1083-1112, 1989.

K. L. Funahashi, ’’On the approximate realization of continuous mapping by neural networks’’, Neural Networks, vol. 2, pp. 183-192, 1989.

J. R. Jang, C. T. Sun and E. Mizutani, Neuro-Fuzzy and soft computing Englewoods Cliffs, NJ Prentice-hall, 1997.

D. Burton, A Delaney, S Newstead, D.Logan, B. Fildes, “Evaluation of Anti-Lock Braking Systems Effectiveness”, royal automobile club of vectoria Ltd, 2004.

The laboratory ABS system user manual, INTECO Ltd.

A. Isidori, “Nonlinear control systems”, (2nd edition), Berlin, Springer, 1989.

K. Hornik, M. Stinchombe, and H. White, ‘’Multilayer feedforward networks are universal approximators’’, Neural netwoks ,vol. 2, pp. 1083-1112, 1989.

M. Gilson, " Entraînement de réseaux de neurones récurrents à pulses appliqué à la modélisation d’un tissu neuronal biologique", thèse, école polytechnique de Montréal, canada, 2003.

N. Srinivas and K. Deb, “Multi-objective optimisation using non dominated sorting in genetic algorithms,” Evolutionnary Computation 2 (3), pp. 221-248, 1995.


Renvois

  • Il n'y a présentement aucun renvoi.




Direction des Publications et de l'animation scientifique

Université des Frères Mentouri Constantine 1. Route Ain El-Bey. 25000. Algérie.