Study on identification of structural system and optimum design by neural network

Shingo Watari, Hiroshi Yamakawa

Research output: Contribution to journalArticle

Abstract

Design of practical structures can involve difficulties when it is based only on analytical models. Experimental data are therefore often made use of for such cases. There have been many studies on identification of statistical and dynamical characteristics of structural systems, making use of experimental data. In this study, we propose a method to identify the characteristics of structures with proper accuracy by using a hierarchical neural network (HNN) that has excellent projection ability even for systems which have nonlinearities. HNN has been generally used to learn dynamic characteristics with minimum number of experimental data. We use HNN as the solver of an optimum design, that is to estimate the dynamic characteristics and sensitivities. The effectiveness of this method is demonstrated through several numerical examples and experiments. Then we utilize the derived sensitivities for gradient-based optimization techniques and to solve the optimum design problems. It is found that the proposed method is valid and effective for such optimum design problems.

Original languageEnglish
Pages (from-to)4238-4244
Number of pages7
JournalNippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C
Volume61
Issue number591
Publication statusPublished - 1995 Nov
Externally publishedYes

Fingerprint

Identification (control systems)
Systems analysis
Neural networks
Analytical models
Optimum design
Experiments

ASJC Scopus subject areas

  • Mechanics of Materials
  • Mechanical Engineering
  • Industrial and Manufacturing Engineering

Cite this

Study on identification of structural system and optimum design by neural network. / Watari, Shingo; Yamakawa, Hiroshi.

In: Nippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C, Vol. 61, No. 591, 11.1995, p. 4238-4244.

Research output: Contribution to journalArticle

@article{e2b8e75a61c04f569f8dcb68dbd1fa31,
title = "Study on identification of structural system and optimum design by neural network",
abstract = "Design of practical structures can involve difficulties when it is based only on analytical models. Experimental data are therefore often made use of for such cases. There have been many studies on identification of statistical and dynamical characteristics of structural systems, making use of experimental data. In this study, we propose a method to identify the characteristics of structures with proper accuracy by using a hierarchical neural network (HNN) that has excellent projection ability even for systems which have nonlinearities. HNN has been generally used to learn dynamic characteristics with minimum number of experimental data. We use HNN as the solver of an optimum design, that is to estimate the dynamic characteristics and sensitivities. The effectiveness of this method is demonstrated through several numerical examples and experiments. Then we utilize the derived sensitivities for gradient-based optimization techniques and to solve the optimum design problems. It is found that the proposed method is valid and effective for such optimum design problems.",
author = "Shingo Watari and Hiroshi Yamakawa",
year = "1995",
month = "11",
language = "English",
volume = "61",
pages = "4238--4244",
journal = "Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C",
issn = "0387-5024",
publisher = "Japan Society of Mechanical Engineers",
number = "591",

}

TY - JOUR

T1 - Study on identification of structural system and optimum design by neural network

AU - Watari, Shingo

AU - Yamakawa, Hiroshi

PY - 1995/11

Y1 - 1995/11

N2 - Design of practical structures can involve difficulties when it is based only on analytical models. Experimental data are therefore often made use of for such cases. There have been many studies on identification of statistical and dynamical characteristics of structural systems, making use of experimental data. In this study, we propose a method to identify the characteristics of structures with proper accuracy by using a hierarchical neural network (HNN) that has excellent projection ability even for systems which have nonlinearities. HNN has been generally used to learn dynamic characteristics with minimum number of experimental data. We use HNN as the solver of an optimum design, that is to estimate the dynamic characteristics and sensitivities. The effectiveness of this method is demonstrated through several numerical examples and experiments. Then we utilize the derived sensitivities for gradient-based optimization techniques and to solve the optimum design problems. It is found that the proposed method is valid and effective for such optimum design problems.

AB - Design of practical structures can involve difficulties when it is based only on analytical models. Experimental data are therefore often made use of for such cases. There have been many studies on identification of statistical and dynamical characteristics of structural systems, making use of experimental data. In this study, we propose a method to identify the characteristics of structures with proper accuracy by using a hierarchical neural network (HNN) that has excellent projection ability even for systems which have nonlinearities. HNN has been generally used to learn dynamic characteristics with minimum number of experimental data. We use HNN as the solver of an optimum design, that is to estimate the dynamic characteristics and sensitivities. The effectiveness of this method is demonstrated through several numerical examples and experiments. Then we utilize the derived sensitivities for gradient-based optimization techniques and to solve the optimum design problems. It is found that the proposed method is valid and effective for such optimum design problems.

UR - http://www.scopus.com/inward/record.url?scp=0029410468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029410468&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0029410468

VL - 61

SP - 4238

EP - 4244

JO - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

JF - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

SN - 0387-5024

IS - 591

ER -