This paper deals with the identification of a radial-type active magnetic bearing (AMB) system using Artificial Neural Network (ANN). Identification and validation experiments are performed on a laboratory magnetic bearing system. Since the electromechanical configuration is inherently unstable, the identification data is gathered while the AMB is operating in closed loop with a controller in the loop. From this data, the identification procedure generates an open-loop plant model. A NNARX (Neural network autoregressive external input model) structure is proposed and evaluated for emulating the system’s dynamic. The model is implemented by a Neural network, constructed using a multilayer perceptron (MLP) topology, and trained using as inputs the rotor’s displacements and excitation currents. Validation tests are performed under perturbation conditions (impact applied on the rotor). Results show that the neural network based model presented here is a powerful tool for dynamic plant’s identification, and that it could be also suitable for robust control application.
Skip Nav Destination
ASME Turbo Expo 2004: Power for Land, Sea, and Air
June 14–17, 2004
Vienna, Austria
Conference Sponsors:
- International Gas Turbine Institute
ISBN:
0-7918-4171-5
PROCEEDINGS PAPER
A Neural Network-Based Closed Loop Identification of a Magnetic Bearings System
Jose´ Medina,
Jose´ Medina
Universidad Simo´n Boli´var, Caracas, Venezuela
Search for other works by this author on:
Mo´nica Parada,
Mo´nica Parada
Universidad Simo´n Boli´var, Caracas, Venezuela
Search for other works by this author on:
Victor Guzma´n,
Victor Guzma´n
Universidad Simo´n Boli´var, Caracas, Venezuela
Search for other works by this author on:
Luis Medina,
Luis Medina
Universidad Simo´n Boli´var, Caracas, Venezuela
Search for other works by this author on:
Sergio Di´az
Sergio Di´az
Universidad Simo´n Boli´var, Caracas, Venezuela
Search for other works by this author on:
Jose´ Medina
Universidad Simo´n Boli´var, Caracas, Venezuela
Mo´nica Parada
Universidad Simo´n Boli´var, Caracas, Venezuela
Victor Guzma´n
Universidad Simo´n Boli´var, Caracas, Venezuela
Luis Medina
Universidad Simo´n Boli´var, Caracas, Venezuela
Sergio Di´az
Universidad Simo´n Boli´var, Caracas, Venezuela
Paper No:
GT2004-53103, pp. 593-598; 6 pages
Published Online:
November 24, 2008
Citation
Medina, J, Parada, M, Guzma´n, V, Medina, L, & Di´az, S. "A Neural Network-Based Closed Loop Identification of a Magnetic Bearings System." Proceedings of the ASME Turbo Expo 2004: Power for Land, Sea, and Air. Volume 6: Turbo Expo 2004. Vienna, Austria. June 14–17, 2004. pp. 593-598. ASME. https://doi.org/10.1115/GT2004-53103
Download citation file:
7
Views
Related Proceedings Papers
Related Articles
Estimating Model Uncertainty using Confidence Interval Networks: Applications to Robust Control
J. Dyn. Sys., Meas., Control (September,2006)
An Active Auxiliary Bearing Control Strategy to Reduce the Onset of Asynchronous Periodic Contact Modes in Rotor/Magnetic Bearing Systems
J. Eng. Gas Turbines Power (May,2010)
Exploration of NDE Properties of AMB Supported Rotors for Structural Damage Detection
J. Eng. Gas Turbines Power (October,2011)
Related Chapters
Cybercrime Detection Through Multilayer Perceptron Neural Network: Evaluate and Compare
International Conference on Computer Technology and Development, 3rd (ICCTD 2011)
Estimating Resilient Modulus Using Neural Network Models
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17
Fitting a Function and Its Derivative
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17