Modelling of an electromagnetic levitation system using a neural network

Systems which involve electromagnetic interactions are very difficult to model. Often, when developing controllers for such systems the model which is used is affected by uncertainties or is linearized. Even if these models can be used for the controller design process, they are not well suited for accurate simulations. In this paper, an electromagnetic levitation system is modeled. Based on the observed behavior of the system, a neural network is used to approximate a non-linear parameter in the model of the plant, which otherwise would have been very difficult to model.

[1]  Enrique Alba,et al.  Training Neural Networks with GA Hybrid Algorithms , 2004, GECCO.

[2]  John Chiasson,et al.  Linear and nonlinear state-space controllers for magnetic levitation , 1996, Int. J. Syst. Sci..

[3]  Mohamad Adnan Al-Alaoui,et al.  A cloning approach to classifier training , 2002, IEEE Trans. Syst. Man Cybern. Part A.

[4]  Zi-Jiang Yang,et al.  Robust Nonlinear Control of a Feedback Linearizable Voltage-Controlled Magnetic Levitation System , 2001 .

[5]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[6]  K N Toosi,et al.  Electromagnetic Levitation System An Experimental Approach , 2004 .

[7]  S. Paschall.  Design, Fabrication, and Control of a Single Actuator Magnetic Levitation System , 2002 .

[8]  Yi Xie.  Mechatronics examples for teaching modeling, dynamics, and control , 2003 .

[9]  Okyay Kaynak,et al.  An algorithm for fast convergence in training neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[10]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.