A novel training method based on variable structure systems theory for fuzzy neural networks

Ozkan Cigdem; Erdal Kayacan; Mojtaba Ahmadieh Khanesar; Okyay Kaynak; Mohammad Teshnehlab

doi:10.1109/CICA.2011.5945757

A novel training method based on variable structure systems theory for fuzzy neural networks

Ozkan Cigdem^*, Erdal Kayacan, Mojtaba Ahmadieh Khanesar, Okyay Kaynak, Mohammad Teshnehlab

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Uncertainty is an inevitable problem in real-time industrial control systems and, to handle this problem and the additional one of possible variations in the parameters of the system, the use of sliding mode control theory-based approaches is frequently suggested. In this paper, instead of using a conventional sliding mode controller, a sliding mode control theory-based learning algorithm is proposed to train the fuzzy neural networks in a feedback-error-learning structure. The parameters of the fuzzy neural network are tuned by the proposed algorithm not to minimize the error function but to ensure that the error satisfies a stable equation. The parameter update rules of the fuzzy neural network are derived, and the proof of the learning algorithm is verified by using the Lyapunov stability method. The proposed method is tested on a real-time servo system with time-varying and nonlinear load conditions.

Original language	English
Title of host publication	IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CICA 2011 - 2011 IEEE Symposium on Computational Intelligence in Control and Automation
Number of pages	8
Publication date	2011
Pages	44-51
Article number	5945757
ISBN (Print)	9781424499038
DOIs	https://doi.org/10.1109/CICA.2011.5945757
Publication status	Published - 2011
Externally published	Yes
Event	2011 IEEE Symposium Series on Computational Intelligence - Paris, France Duration: 11 Apr 2011 → 15 Apr 2011

Conference

Conference	2011 IEEE Symposium Series on Computational Intelligence
Country/Territory	France
City	Paris
Period	11/04/2011 → 15/04/2011
Sponsor	IEEE

Keywords

Feedback error learning
Fuzzy neural networks
Servo system
Variable structure systems

Access to Document

10.1109/CICA.2011.5945757

OpenUrl availability

Full text

Cite this

Cigdem, O., Kayacan, E., Khanesar, M. A., Kaynak, O., & Teshnehlab, M. (2011). A novel training method based on variable structure systems theory for fuzzy neural networks. In IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CICA 2011 - 2011 IEEE Symposium on Computational Intelligence in Control and Automation (pp. 44-51). Article 5945757 https://doi.org/10.1109/CICA.2011.5945757

@inproceedings{40a9b2dfb0d84fbc810cd6fc90ffb214,

title = "A novel training method based on variable structure systems theory for fuzzy neural networks",

abstract = "Uncertainty is an inevitable problem in real-time industrial control systems and, to handle this problem and the additional one of possible variations in the parameters of the system, the use of sliding mode control theory-based approaches is frequently suggested. In this paper, instead of using a conventional sliding mode controller, a sliding mode control theory-based learning algorithm is proposed to train the fuzzy neural networks in a feedback-error-learning structure. The parameters of the fuzzy neural network are tuned by the proposed algorithm not to minimize the error function but to ensure that the error satisfies a stable equation. The parameter update rules of the fuzzy neural network are derived, and the proof of the learning algorithm is verified by using the Lyapunov stability method. The proposed method is tested on a real-time servo system with time-varying and nonlinear load conditions.",

keywords = "Feedback error learning, Fuzzy neural networks, Servo system, Variable structure systems",

author = "Ozkan Cigdem and Erdal Kayacan and Khanesar, {Mojtaba Ahmadieh} and Okyay Kaynak and Mohammad Teshnehlab",

year = "2011",

doi = "10.1109/CICA.2011.5945757",

language = "English",

isbn = "9781424499038",

pages = "44--51",

booktitle = "IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CICA 2011 - 2011 IEEE Symposium on Computational Intelligence in Control and Automation",

note = "2011 IEEE Symposium Series on Computational Intelligence, SSCI 2011 ; Conference date: 11-04-2011 Through 15-04-2011",

}

Cigdem, O, Kayacan, E, Khanesar, MA, Kaynak, O & Teshnehlab, M 2011, A novel training method based on variable structure systems theory for fuzzy neural networks. in IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CICA 2011 - 2011 IEEE Symposium on Computational Intelligence in Control and Automation., 5945757, pp. 44-51, 2011 IEEE Symposium Series on Computational Intelligence, Paris, France, 11/04/2011. https://doi.org/10.1109/CICA.2011.5945757

A novel training method based on variable structure systems theory for fuzzy neural networks. / Cigdem, Ozkan; Kayacan, Erdal; Khanesar, Mojtaba Ahmadieh et al.
IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CICA 2011 - 2011 IEEE Symposium on Computational Intelligence in Control and Automation. 2011. p. 44-51 5945757.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - A novel training method based on variable structure systems theory for fuzzy neural networks

AU - Cigdem, Ozkan

AU - Kayacan, Erdal

AU - Khanesar, Mojtaba Ahmadieh

AU - Kaynak, Okyay

AU - Teshnehlab, Mohammad

PY - 2011

Y1 - 2011

N2 - Uncertainty is an inevitable problem in real-time industrial control systems and, to handle this problem and the additional one of possible variations in the parameters of the system, the use of sliding mode control theory-based approaches is frequently suggested. In this paper, instead of using a conventional sliding mode controller, a sliding mode control theory-based learning algorithm is proposed to train the fuzzy neural networks in a feedback-error-learning structure. The parameters of the fuzzy neural network are tuned by the proposed algorithm not to minimize the error function but to ensure that the error satisfies a stable equation. The parameter update rules of the fuzzy neural network are derived, and the proof of the learning algorithm is verified by using the Lyapunov stability method. The proposed method is tested on a real-time servo system with time-varying and nonlinear load conditions.

AB - Uncertainty is an inevitable problem in real-time industrial control systems and, to handle this problem and the additional one of possible variations in the parameters of the system, the use of sliding mode control theory-based approaches is frequently suggested. In this paper, instead of using a conventional sliding mode controller, a sliding mode control theory-based learning algorithm is proposed to train the fuzzy neural networks in a feedback-error-learning structure. The parameters of the fuzzy neural network are tuned by the proposed algorithm not to minimize the error function but to ensure that the error satisfies a stable equation. The parameter update rules of the fuzzy neural network are derived, and the proof of the learning algorithm is verified by using the Lyapunov stability method. The proposed method is tested on a real-time servo system with time-varying and nonlinear load conditions.

KW - Feedback error learning

KW - Fuzzy neural networks

KW - Servo system

KW - Variable structure systems

UR - http://www.scopus.com/inward/record.url?scp=79961183049&partnerID=8YFLogxK

U2 - 10.1109/CICA.2011.5945757

DO - 10.1109/CICA.2011.5945757

M3 - Article in proceedings

AN - SCOPUS:79961183049

SN - 9781424499038

SP - 44

EP - 51

BT - IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CICA 2011 - 2011 IEEE Symposium on Computational Intelligence in Control and Automation

T2 - 2011 IEEE Symposium Series on Computational Intelligence

Y2 - 11 April 2011 through 15 April 2011

ER -

A novel training method based on variable structure systems theory for fuzzy neural networks

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this