Optimum design of truss structures using neural network

Seong B. Kim; Young Sang Cho; Dong Cheol Shin; Jun Seo Bae

Optimum design of truss structures using neural network

Seong B. Kim, Young Sang Cho, Dong Cheol Shin, Jun Seo Bae

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

Abstract

The purpose of this paper is to verify the applicability of the prototype of the Neural Network base model for Optimum Structural Design(NNOSD) to search the optimum design in all cases immediately. NNOSD suggest the procedure of the optimum design and the proper values of the neural network variables(training pattern, number of hidden neurons, maximum training error, steepness coefficient, learning constant, momentum term, etc.) to reduce the computer time and to improve the accuracy. And the methods of the connection between NNOSD and the existing design system is presented.

The artificial neural network is used as an alternative design model of the warren truss since it
can handle uncertainty through the probability method.

Original language	English
Title of host publication	SB07 Seoul
Subtitle of host publication	Proceedings of the International Conference on Sustainable Building Asia, 27-29 June 2007, Seoul, Korea
Pages	1073-1078
Publication status	Published - 2007
Externally published	Yes

Access to Document

http://www.irbnet.de/daten/iconda/CIB7955.pdfLicence: Unspecified

Cite this

@inproceedings{9d630ae80d3d4d74b1728f0310249289,

title = "Optimum design of truss structures using neural network",

abstract = "The purpose of this paper is to verify the applicability of the prototype of the Neural Network base model for Optimum Structural Design(NNOSD) to search the optimum design in all cases immediately. NNOSD suggest the procedure of the optimum design and the proper values of the neural network variables(training pattern, number of hidden neurons, maximum training error, steepness coefficient, learning constant, momentum term, etc.) to reduce the computer time and to improve the accuracy. And the methods of the connection between NNOSD and the existing design system is presented.The artificial neural network is used as an alternative design model of the warren truss since itcan handle uncertainty through the probability method.",

author = "Kim, {Seong B.} and Cho, {Young Sang} and Shin, {Dong Cheol} and Bae, {Jun Seo}",

year = "2007",

language = "English",

pages = "1073--1078",

booktitle = "SB07 Seoul",

}

TY - GEN

T1 - Optimum design of truss structures using neural network

AU - Kim, Seong B.

AU - Cho, Young Sang

AU - Shin, Dong Cheol

AU - Bae, Jun Seo

PY - 2007

Y1 - 2007

N2 - The purpose of this paper is to verify the applicability of the prototype of the Neural Network base model for Optimum Structural Design(NNOSD) to search the optimum design in all cases immediately. NNOSD suggest the procedure of the optimum design and the proper values of the neural network variables(training pattern, number of hidden neurons, maximum training error, steepness coefficient, learning constant, momentum term, etc.) to reduce the computer time and to improve the accuracy. And the methods of the connection between NNOSD and the existing design system is presented.The artificial neural network is used as an alternative design model of the warren truss since itcan handle uncertainty through the probability method.

AB - The purpose of this paper is to verify the applicability of the prototype of the Neural Network base model for Optimum Structural Design(NNOSD) to search the optimum design in all cases immediately. NNOSD suggest the procedure of the optimum design and the proper values of the neural network variables(training pattern, number of hidden neurons, maximum training error, steepness coefficient, learning constant, momentum term, etc.) to reduce the computer time and to improve the accuracy. And the methods of the connection between NNOSD and the existing design system is presented.The artificial neural network is used as an alternative design model of the warren truss since itcan handle uncertainty through the probability method.

M3 - Conference contribution

SP - 1073

EP - 1078

BT - SB07 Seoul

ER -

Optimum design of truss structures using neural network

Abstract

Access to Document

Fingerprint

Cite this