Data parallel neural dynamics model for integrated design of large steel structures

Hyo Seon Park, Hojjat Adeli

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

We have two objectives in creating novel design theories and computational models: automation and optimization. These two aspects are particularly important in design of complex and large engineering structures. In this article, a robust data parallel neural dynamics model is presented for discrete optimization of large steel structures based on the AISC ASD or LRFD specifications. The computational model has been implemented on a CM-5 supercomputer and applied to integrated minimum-weight design of two steel high-rise building structures. The largest example is a 144-story modified tube-in-tube super-high-rise building structure with 20,096 members. Optimization of such a large structure subjected to the highly nonlinear constraints of actual design codes, such as the AISC LRFD code, where nonlinear second-order effects have to be taken into account, has never been attempted before. The computational model developed in this research finds the minimum-weight design for this very large structure subjected to multiple dead, live, and wind loadings in three different directions automatically. This research demonstrates how a new level in design automation is achieved through the ingenious use of a novel computational paradigm and new high-performance computer architecture.

Original languageEnglish
Pages (from-to)311-326
Number of pages16
JournalMicrocomputers in Civil Engineering
Volume12
Issue number5
Publication statusPublished - 1997 Sep 1

Fingerprint

steel structure
Steel structures
Dynamic models
automation
Automation
Computer architecture
Supercomputers
steel
Specifications
engineering
Steel

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Environmental Science(all)
  • Engineering(all)
  • Earth and Planetary Sciences(all)

Cite this

@article{ab722efbbd95485785093446a61e5762,
title = "Data parallel neural dynamics model for integrated design of large steel structures",
abstract = "We have two objectives in creating novel design theories and computational models: automation and optimization. These two aspects are particularly important in design of complex and large engineering structures. In this article, a robust data parallel neural dynamics model is presented for discrete optimization of large steel structures based on the AISC ASD or LRFD specifications. The computational model has been implemented on a CM-5 supercomputer and applied to integrated minimum-weight design of two steel high-rise building structures. The largest example is a 144-story modified tube-in-tube super-high-rise building structure with 20,096 members. Optimization of such a large structure subjected to the highly nonlinear constraints of actual design codes, such as the AISC LRFD code, where nonlinear second-order effects have to be taken into account, has never been attempted before. The computational model developed in this research finds the minimum-weight design for this very large structure subjected to multiple dead, live, and wind loadings in three different directions automatically. This research demonstrates how a new level in design automation is achieved through the ingenious use of a novel computational paradigm and new high-performance computer architecture.",
author = "Park, {Hyo Seon} and Hojjat Adeli",
year = "1997",
month = "9",
day = "1",
language = "English",
volume = "12",
pages = "311--326",
journal = "Computer-Aided Civil and Infrastructure Engineering",
issn = "1093-9687",
publisher = "Wiley-Blackwell",
number = "5",

}

Data parallel neural dynamics model for integrated design of large steel structures. / Park, Hyo Seon; Adeli, Hojjat.

In: Microcomputers in Civil Engineering, Vol. 12, No. 5, 01.09.1997, p. 311-326.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Data parallel neural dynamics model for integrated design of large steel structures

AU - Park, Hyo Seon

AU - Adeli, Hojjat

PY - 1997/9/1

Y1 - 1997/9/1

N2 - We have two objectives in creating novel design theories and computational models: automation and optimization. These two aspects are particularly important in design of complex and large engineering structures. In this article, a robust data parallel neural dynamics model is presented for discrete optimization of large steel structures based on the AISC ASD or LRFD specifications. The computational model has been implemented on a CM-5 supercomputer and applied to integrated minimum-weight design of two steel high-rise building structures. The largest example is a 144-story modified tube-in-tube super-high-rise building structure with 20,096 members. Optimization of such a large structure subjected to the highly nonlinear constraints of actual design codes, such as the AISC LRFD code, where nonlinear second-order effects have to be taken into account, has never been attempted before. The computational model developed in this research finds the minimum-weight design for this very large structure subjected to multiple dead, live, and wind loadings in three different directions automatically. This research demonstrates how a new level in design automation is achieved through the ingenious use of a novel computational paradigm and new high-performance computer architecture.

AB - We have two objectives in creating novel design theories and computational models: automation and optimization. These two aspects are particularly important in design of complex and large engineering structures. In this article, a robust data parallel neural dynamics model is presented for discrete optimization of large steel structures based on the AISC ASD or LRFD specifications. The computational model has been implemented on a CM-5 supercomputer and applied to integrated minimum-weight design of two steel high-rise building structures. The largest example is a 144-story modified tube-in-tube super-high-rise building structure with 20,096 members. Optimization of such a large structure subjected to the highly nonlinear constraints of actual design codes, such as the AISC LRFD code, where nonlinear second-order effects have to be taken into account, has never been attempted before. The computational model developed in this research finds the minimum-weight design for this very large structure subjected to multiple dead, live, and wind loadings in three different directions automatically. This research demonstrates how a new level in design automation is achieved through the ingenious use of a novel computational paradigm and new high-performance computer architecture.

UR - http://www.scopus.com/inward/record.url?scp=0031221990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031221990&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031221990

VL - 12

SP - 311

EP - 326

JO - Computer-Aided Civil and Infrastructure Engineering

JF - Computer-Aided Civil and Infrastructure Engineering

SN - 1093-9687

IS - 5

ER -