東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Design, stability and robustness ana...

Shen, Jie.

FindBook

Google Book

Amazon

博客來

Design, stability and robustness analyses of neural networks in control systems.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Design, stability and robustness analyses of neural networks in control systems./
作者:	Shen, Jie.
面頁冊數:	138 p.
附註:	Source: Dissertation Abstracts International, Volume: 59-03, Section: B, page: 1217.
Contained By:	Dissertation Abstracts International59-03B.
標題:	Engineering, Aerospace. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9828094
ISBN:	0591806010

Design, stability and robustness analyses of neural networks in control systems.
Shen, Jie.

Design, stability and robustness analyses of neural networks in control systems. - 138 p.

Source: Dissertation Abstracts International, Volume: 59-03, Section: B, page: 1217.

Thesis (Ph.D.)--University of Missouri - Rolla, 1998.

Artificial Neural Network (ANN), also known as connectionist learning and parallel distributed processing, is finding its applications in diverse fields: many branches of engineering, health sciences, cognitive science, archaeology, finance, etc. This research tries to make some efforts to emphasize "design" methodology in ANN, and to explore the structures by which ANN can solve difficult problems by identifying proper ANN architecture. Two classes of ANN--multi-layer neural networks and recurrent networks--are investigated in the context of control of systems and estimation of unknown parameters. The multi-layer neural networks converge to optimal solutions by satisfying mathematical formulations associated with the Hamilton approach and the dynamic programming approach. A benchmark aerospace application is used for illustration. A variant of the Hopfield network, called the Modified Hopfield Neural Network (MHNN), is proposed to show the design approach to the determination of weights in recurrent networks. It is shown how the equilibrium point of this network helps with inversion operations arising in optimal gain determination. Control of dynamic systems using recurrent neural networks are presented. The robustness of the recurrent networks to parameter variation is considered in the context of weights. Analyses are carried out in the frequency domain and the time domain.

ISBN: 0591806010Subjects--Topical Terms:

1018395
Engineering, Aerospace.

Design, stability and robustness analyses of neural networks in control systems.
LDR:02344nmm 2200301 4500 001 1840722
005 20050822101731.5
008 130614s1998 eng d
020 $a 0591806010
035 $a (UnM)AAI9828094
035 $a AAI9828094
040 $a UnM $c UnM
100 1 $a Shen, Jie. $3 1929047
245 1 0 $a Design, stability and robustness analyses of neural networks in control systems.
300 $a 138 p.
500 $a Source: Dissertation Abstracts International, Volume: 59-03, Section: B, page: 1217.
500 $a Adviser: S. N. Balakrishnan.
502 $a Thesis (Ph.D.)--University of Missouri - Rolla, 1998.
520 $a Artificial Neural Network (ANN), also known as connectionist learning and parallel distributed processing, is finding its applications in diverse fields: many branches of engineering, health sciences, cognitive science, archaeology, finance, etc. This research tries to make some efforts to emphasize "design" methodology in ANN, and to explore the structures by which ANN can solve difficult problems by identifying proper ANN architecture. Two classes of ANN--multi-layer neural networks and recurrent networks--are investigated in the context of control of systems and estimation of unknown parameters. The multi-layer neural networks converge to optimal solutions by satisfying mathematical formulations associated with the Hamilton approach and the dynamic programming approach. A benchmark aerospace application is used for illustration. A variant of the Hopfield network, called the Modified Hopfield Neural Network (MHNN), is proposed to show the design approach to the determination of weights in recurrent networks. It is shown how the equilibrium point of this network helps with inversion operations arising in optimal gain determination. Control of dynamic systems using recurrent neural networks are presented. The robustness of the recurrent networks to parameter variation is considered in the context of weights. Analyses are carried out in the frequency domain and the time domain.
590 $a School code: 0135.
650 4 $a Engineering, Aerospace. $3 1018395
650 4 $a Engineering, Mechanical. $3 783786
650 4 $a Engineering, System Science. $3 1018128
650 4 $a Artificial Intelligence. $3 769149
690 $a 0538
690 $a 0548
690 $a 0790
690 $a 0800
710 2 0 $a University of Missouri - Rolla. $3 1025712
773 0 $t Dissertation Abstracts International $g 59-03B.
790 1 0 $a Balakrishnan, S. N., $e advisor
790 $a 0135
791 $a Ph.D.
792 $a 1998
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9828094