AccScience Publishing / IJOCTA / Volume 1 / Issue 1 / DOI: 10.11121/ijocta.01.2011.0055
Cite this article
5
Download
1221
Views
Related Info Links
More by Authors Links
Journal Browser
Volume | Year
Issue
Search
News and Announcements
View All
ENGINEERING APPLICATIONS OF AI

A Comparative Study of Neural networks and Fuzzy Systems  in Modeling of a Nonlinear Dynamic System

Metin Demirtas1 ,  Musa Alci2
Show Less
1 Department of Electrical & Electronics Engineering , Balikesir University-Turkey
2 Department of Electrical & Electronics Engineering , Ege University-Turkey
Received: 4 May 2011 | Published online: 31 May 2011
© 2011 by the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

The aim of this paper is to compare the neural networks and fuzzy modeling  approaches on a nonlinear system. We have taken Permanent Magnet Brushless Direct Current  (PMBDC) motor data and have generated models using both approaches. The predictive  performance of both methods was compared on the data set for model configurations. The paper  describes the results of these tests and discusses the effects of changing model parameters on  predictive and practical performance. Modeling sensitivity was used to compare for two methods.

Keywords
Neural networks
fuzzy
brushless dc motor
modeling system
DSP
Conflict of interest
The authors declare they have no competing interests.
References

[1] N. Selvaganesan and R. Saraswathy Ramya, A  Simple Fuzzy Modeling of Permanent Magnet  Synchronous Generator,Elektrika, vol. 11, no. 1,  38-43, (2009)

[2] K.J.Astrom, C.C.Hang, P.Persson, and W.K.Ho,  Towards Intelligent PID Control, Automatica,  vol. 28, no. 1, 1-9,(1992)

[3] Saleem R.M., and Poslethwaite B.F., A  comparison of neural networks and fuzzy  relational systems in dynamic modeling,  control‟94, IEE, no.389, 1448-1452,(1994)

[4] Metin Demirtas, Off-line tuning of a PI speed  controller for a permanent magnet brushless DC  motor using DSP, Energy Conversion and  Management 52, 264–273,(2011)

[5] Zhang Bo, Li Zhong and Mao Zong Yuan, A  type of fuzzy modeling of the chaotic system of  Permanent Magnet Synchronous Motor, IEEE  Conf., pp 880-883.

[6] Jacek Kabzifski, Fuzzy modeling of disturbance  torques/forces in rotational/linear interior  permanent magnet synchronous motors, Proc.  On EPE, 1-10, (2005)

[7] S.Yamamoto and I. Hashimoto, “Present status  and future needs: the view from Japanese  industry. Chemical Process control”,  Proceedings of the fourth international conf. on  chemical process control, TX, (1991)

[8] Y. Wang and H. Shao, Optimal tuning for PI controller, Automatica, 36, 147-152, (2000)

[9] TECHNOFOFT DSP Motion Solutions,  MxWIN243 User Manuel, Switzerland, (2001)

[10] Cybenko G., “Approximation by superpositions  of a sigmoidal function”, Math. Control Signal  Syst., 303-314, (1989)

[11] Girosi., F., and Poggio., T., Networks and the  best approximation property, Biol. Cybernetics,  169-179,(1990)

[12] Park., J., and Sandberg, I.W., Universal  approximation using radial basis function  networks, Neur. Comput., 246-257,(1991)

[13] Ustun SV, Demirtas M, Optimal tuning of PI  speed controller coefficients for electric drives  using neural networks and genetic algorithms,  Electrical Engineering, vol. 87, No:2, 77-82,  (2005)

[14] Krishnan R., Election Criteria for Servo Motor  Drives, IEEE Transactions on Industry  Applications, vol.M-23 no.2, 270-275, (1987)

[15] G. R. Slemon, Electric Machines and Drives,  Addison-Wesley Publication Company, 503– 511, (1992)

Share
Back to top
An International Journal of Optimization and Control: Theories & Applications, Electronic ISSN: 2146-5703 Print ISSN: 2146-0957, Published by AccScience Publishing