Neural Network Control of a Laboratory Magnetic Levitator

Neural Network Control of a Laboratory Magnetic Levitator

J. Katende (Botswana International University of Science and Technology, Botswana) and M. Mustapha (Bayero University, Nigeria)
DOI: 10.4018/978-1-4666-2208-1.ch017
OnDemand PDF Download:
No Current Special Offers


Magnetic levitation (maglev) systems are nowadays employed in applications ranging from non-contact bearings and vibration isolation of sensitive machinery to high-speed passenger trains. In this chapter a mathematical model of a laboratory maglev system was derived using the Lagrangian approach. A linear pole-placement controller was designed on the basis of specifications on peak overshoot and settling time. A 3-layer feed-forward Artificial Neural Network (ANN) controller comprising 3-input nodes, a 5-neuron hidden layer, and 1-neuron output layer was trained using the linear state feedback controller with a random reference signal. Simulations to investigate the robustness of the ANN control scheme with respect to parameter variations, reference step input magnitude variations, and sinusoidal input tracking were carried out using SIMULINK. The obtained simulation results show that the ANN controller is robust with respect to good positioning accuracy.
Chapter Preview

2. Mathematical Model Of The Maglev System

The maglev system considered in this paper consists of ferromagnetic ball suspended in a magnetic field. Only the vertical motion is considered. The objective is to keep the ball at a prescribed reference level. The dynamical equations of the maglev system are derived using the Lagrange method.

Complete Chapter List

Search this Book: