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

^*此作品的通信作者

電機工程學系

研究成果: Conference article › 同行評審

1 引文斯高帕斯（Scopus）

摘要

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.

原文	English
文章編號	532355
頁（從 - 到）	2777-2781
頁數	5
期刊	Proceedings of the American Control Conference
卷	4
DOIs	https://doi.org/10.1109/ACC.1995.532355
出版狀態	Published - 21 6月 1995
事件	Proceedings of the 1995 American Control Conference. Part 1 (of 6) - Seattle, WA, USA 持續時間: 21 6月 1995 → 23 6月 1995

存取文件

10.1109/ACC.1995.532355

其它文件與鏈接

Link to publication in Scopus

引用此

@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

摘要

存取文件

其它文件與鏈接

指紋

引用此