Practical stability issues in CMAC neural network control systems

Fu-Chuang Chen; Chih Horng Chang

doi:10.1109/ACC.1995.532355

Practical stability issues in CMAC neural network control systems

Fu-Chuang Chen^*, Chih Horng Chang

^*Corresponding author for this work

Department of Electrical and Computer Engineering

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

The CMAC neural network is a practical tool for improving existing nonlinear control systems. A typical simulation study is used to clearly demonstrate that the CMAC can effectively reduce tracking error, but can also destabilize a control system which is otherwise stable. Then quantitative studies are presented to search for the cause of instability in the CMAC control system. Based on these studies, methods are discussed to improve system stability. Experimental results on controlling a real world system is provided to support the findings in simulations.

Original language	English
Article number	532355
Pages (from-to)	2777-2781
Number of pages	5
Journal	Proceedings of the American Control Conference
Volume	4
DOIs	https://doi.org/10.1109/ACC.1995.532355
State	Published - 21 Jun 1995
Event	Proceedings of the 1995 American Control Conference. Part 1 (of 6) - Seattle, WA, USA Duration: 21 Jun 1995 → 23 Jun 1995

Access to Document

10.1109/ACC.1995.532355

Cite this

@article{5ebb0059cc9a40398fafea9e8aad5509,

title = "Practical stability issues in CMAC neural network control systems",

abstract = "The CMAC neural network is a practical tool for improving existing nonlinear control systems. A typical simulation study is used to clearly demonstrate that the CMAC can effectively reduce tracking error, but can also destabilize a control system which is otherwise stable. Then quantitative studies are presented to search for the cause of instability in the CMAC control system. Based on these studies, methods are discussed to improve system stability. Experimental results on controlling a real world system is provided to support the findings in simulations.",

author = "Fu-Chuang Chen and Chang, {Chih Horng}",

year = "1995",

month = jun,

day = "21",

doi = "10.1109/ACC.1995.532355",

language = "English",

volume = "4",

pages = "2777--2781",

journal = "Proceedings of the American Control Conference",

issn = "0743-1619",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "Proceedings of the 1995 American Control Conference. Part 1 (of 6) ; Conference date: 21-06-1995 Through 23-06-1995",

}

TY - JOUR

T1 - Practical stability issues in CMAC neural network control systems

AU - Chen, Fu-Chuang

AU - Chang, Chih Horng

PY - 1995/6/21

Y1 - 1995/6/21

N2 - The CMAC neural network is a practical tool for improving existing nonlinear control systems. A typical simulation study is used to clearly demonstrate that the CMAC can effectively reduce tracking error, but can also destabilize a control system which is otherwise stable. Then quantitative studies are presented to search for the cause of instability in the CMAC control system. Based on these studies, methods are discussed to improve system stability. Experimental results on controlling a real world system is provided to support the findings in simulations.

AB - The CMAC neural network is a practical tool for improving existing nonlinear control systems. A typical simulation study is used to clearly demonstrate that the CMAC can effectively reduce tracking error, but can also destabilize a control system which is otherwise stable. Then quantitative studies are presented to search for the cause of instability in the CMAC control system. Based on these studies, methods are discussed to improve system stability. Experimental results on controlling a real world system is provided to support the findings in simulations.

UR - http://www.scopus.com/inward/record.url?scp=0029179196&partnerID=8YFLogxK

U2 - 10.1109/ACC.1995.532355

DO - 10.1109/ACC.1995.532355

M3 - Conference article

AN - SCOPUS:0029179196

SN - 0743-1619

VL - 4

SP - 2777

EP - 2781

JO - Proceedings of the American Control Conference

JF - Proceedings of the American Control Conference

M1 - 532355

T2 - Proceedings of the 1995 American Control Conference. Part 1 (of 6)

Y2 - 21 June 1995 through 23 June 1995

ER -

Practical stability issues in CMAC neural network control systems

Abstract

Access to Document

Other files and links

Fingerprint

Cite this