GA based meta-modeling of BPN architecture for constrained approximate optimization

Jongsoo Lee, Seongkyu Kang

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Artificial neural networks (ANN) have been extensively used as global approximation tools in the context of approximate optimization. ANN traditionally minimizes the absolute difference between target outputs and approximate outputs, thereby resulting in approximate optimal solutions being sometimes actually infeasible when it is used as a meta-model for inequality constraint functions. The paper explores the development of the modified back-propagation neural network (BPN) based meta-model that ensures the constraint feasibility of approximate optimal solution. The BPN architecture is optimized via genetic algorithm (GA) to determine integer/continuous decision parameters such as the number of hidden layers, the number of neurons in a hidden layer, and interconnection weights between layers in the network. The verification of the proposed approach is examined by adopting a number of standard structural problems and an optical disk drive (ODD) suspension problem. Finally, GA based approximate optimization of suspension with optical flying head (OFH) is conducted to enhance the shock resistance capability in addition to dynamic characteristics.

Original languageEnglish
Pages (from-to)5980-5993
Number of pages14
JournalInternational Journal of Solids and Structures
Volume44
Issue number18-19
DOIs
Publication statusPublished - 2007 Sep 1

Fingerprint

Metamodeling
Back-propagation Neural Network
Network Architecture
Network architecture
Backpropagation
genetic algorithms
Genetic algorithms
Genetic Algorithm
Neural networks
optimization
Optimization
Suspensions
Metamodel
Artificial Neural Network
Optimal Solution
shock resistance
optical disks
output
Output
Neurons

All Science Journal Classification (ASJC) codes

  • Modelling and Simulation
  • Materials Science(all)
  • Condensed Matter Physics
  • Mechanics of Materials
  • Mechanical Engineering
  • Applied Mathematics

Cite this

@article{0f184b0015c3482fa93c4410c1824c55,
title = "GA based meta-modeling of BPN architecture for constrained approximate optimization",
abstract = "Artificial neural networks (ANN) have been extensively used as global approximation tools in the context of approximate optimization. ANN traditionally minimizes the absolute difference between target outputs and approximate outputs, thereby resulting in approximate optimal solutions being sometimes actually infeasible when it is used as a meta-model for inequality constraint functions. The paper explores the development of the modified back-propagation neural network (BPN) based meta-model that ensures the constraint feasibility of approximate optimal solution. The BPN architecture is optimized via genetic algorithm (GA) to determine integer/continuous decision parameters such as the number of hidden layers, the number of neurons in a hidden layer, and interconnection weights between layers in the network. The verification of the proposed approach is examined by adopting a number of standard structural problems and an optical disk drive (ODD) suspension problem. Finally, GA based approximate optimization of suspension with optical flying head (OFH) is conducted to enhance the shock resistance capability in addition to dynamic characteristics.",
author = "Jongsoo Lee and Seongkyu Kang",
year = "2007",
month = "9",
day = "1",
doi = "10.1016/j.ijsolstr.2007.02.008",
language = "English",
volume = "44",
pages = "5980--5993",
journal = "International Journal of Solids and Structures",
issn = "0020-7683",
publisher = "Elsevier Limited",
number = "18-19",

}

GA based meta-modeling of BPN architecture for constrained approximate optimization. / Lee, Jongsoo; Kang, Seongkyu.

In: International Journal of Solids and Structures, Vol. 44, No. 18-19, 01.09.2007, p. 5980-5993.

Research output: Contribution to journalArticle

TY - JOUR

T1 - GA based meta-modeling of BPN architecture for constrained approximate optimization

AU - Lee, Jongsoo

AU - Kang, Seongkyu

PY - 2007/9/1

Y1 - 2007/9/1

N2 - Artificial neural networks (ANN) have been extensively used as global approximation tools in the context of approximate optimization. ANN traditionally minimizes the absolute difference between target outputs and approximate outputs, thereby resulting in approximate optimal solutions being sometimes actually infeasible when it is used as a meta-model for inequality constraint functions. The paper explores the development of the modified back-propagation neural network (BPN) based meta-model that ensures the constraint feasibility of approximate optimal solution. The BPN architecture is optimized via genetic algorithm (GA) to determine integer/continuous decision parameters such as the number of hidden layers, the number of neurons in a hidden layer, and interconnection weights between layers in the network. The verification of the proposed approach is examined by adopting a number of standard structural problems and an optical disk drive (ODD) suspension problem. Finally, GA based approximate optimization of suspension with optical flying head (OFH) is conducted to enhance the shock resistance capability in addition to dynamic characteristics.

AB - Artificial neural networks (ANN) have been extensively used as global approximation tools in the context of approximate optimization. ANN traditionally minimizes the absolute difference between target outputs and approximate outputs, thereby resulting in approximate optimal solutions being sometimes actually infeasible when it is used as a meta-model for inequality constraint functions. The paper explores the development of the modified back-propagation neural network (BPN) based meta-model that ensures the constraint feasibility of approximate optimal solution. The BPN architecture is optimized via genetic algorithm (GA) to determine integer/continuous decision parameters such as the number of hidden layers, the number of neurons in a hidden layer, and interconnection weights between layers in the network. The verification of the proposed approach is examined by adopting a number of standard structural problems and an optical disk drive (ODD) suspension problem. Finally, GA based approximate optimization of suspension with optical flying head (OFH) is conducted to enhance the shock resistance capability in addition to dynamic characteristics.

UR - http://www.scopus.com/inward/record.url?scp=34447523923&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34447523923&partnerID=8YFLogxK

U2 - 10.1016/j.ijsolstr.2007.02.008

DO - 10.1016/j.ijsolstr.2007.02.008

M3 - Article

AN - SCOPUS:34447523923

VL - 44

SP - 5980

EP - 5993

JO - International Journal of Solids and Structures

JF - International Journal of Solids and Structures

SN - 0020-7683

IS - 18-19

ER -