Application of neural networks to preliminary structural design

Swift, R.; Batill, Stephen M.

doi:10.2514/6.1991-1038

Cited by 34 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of approximation algorithms in conceptual structural and architectural design was examined by Swift and Batill in 1991 [13]. Specifically, for truss problems, with the variables being the positions of some nodes of the truss and the objective the structural weight, a design space was sampled and later approximated using neural networks.…”

Section: Surrogate Modelling For Structural Designsmentioning

confidence: 99%

Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures

Tseranidis

Brown

Mueller

2016

Automation in Construction

View full text Add to dashboard Cite

This paper explores the use of data-driven approximation algorithms, often called surrogate modelling, in the earlystage design of structures. The use of surrogate models to rapidly evaluate design performance can lead to a more indepth exploration of a design space reduce computational time of optimization algorithms. While this approach has been widely developed and used in related disciplines such as aerospace engineering, there are few examples of its application in civil engineering. This paper focuses on the general use of surrogate modelling in the design of civil structures, and examines six model types that span a wide range of characteristics. Original contributions include novel metrics and visualization techniques for understanding model error, and a new robustness framework that accounts for variability in model comparison. These concepts are applied to a multi-objective case study of an airport terminal design that considers both structural material volume and operational energy consumption.

show abstract

Section: Surrogate Modelling For Structural Designsmentioning

confidence: 99%

Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures

Tseranidis

Brown

Mueller

2016

Automation in Construction

View full text Add to dashboard Cite

show abstract

“…The MDO framework presented in this paper has evolved from the fundamental structure of the Concurrent Subspace Optimization (CSSO) proposed by Sobieski 1 and it exploits the use of neural network based response surface approximations [2][3] . The integration of automated decision making processes, i.e.…”

Section: Concurrent Subspace Design Frameworkmentioning

confidence: 99%

Application of the Concurrent Subspace Design framework to aircraft brake component design optimization

Stelmack

Batill

BeckT³

et al. 1998

39th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference and Exhibit

View full text Add to dashboard Cite

The Concurrent Subspace Design (CSD) framework has been used to conduct a preliminary design optimization of an aircraft landing gear subsystem. The application required the implementation of the MDO framework with existing industrial analysis software. The CSD framework employs artificial neural networks to provide approximations to the design space, which are the means of coordinating design decisions in the individual disciplines. This approach was applied to the design of an aircraft brake actuation system which contains continuous and discrete design variables. The results demonstrate that the mixed CSD framework was able to efficiently identify improved designs. This study also demonstrated that the CSD framework can be exploited using existing engineering analysis methods.

show abstract

“…Much of the earlier work involved utilizing polynomials as approximators (Box & Draper, 1987;Khuri & Cornell, 1987;Myers, 1971). Neural networks also can be used as approximators (Rumelhart & McClelland, 1986;Anderson & Rosenfeld, 1988;Hornik et al, 1989;Swift & Batill, 1991;Carpenter & Barthelemy, 1993). Indeed, the use of neural networks has found extensive application in all areas of civil engineering.…”

Section: Introductionmentioning

confidence: 99%

Selecting the architecture of a class of back-propagation neural networks used as approximators

Carpenter

Hoffman²

1997

AIEDAM

View full text Add to dashboard Cite

This paper examines the architecture of back-propagation neural networks used as approximators by addressing the interrelationship between the number of training pairs and the number of input, output, and hidden layer nodes required for a good approximation. It concentrates on nets with an input layer, one hidden layer, and one output layer. It shows that many of the currently proposed schemes for selecting network architecture for such nets are deficient. It demonstrates in numerous examples that overdetermined neural networks tend to give good approximations over a region of interest, while underdetermined networks give approximations which can satisfy the training pairs but may give poor approximations over that region of interest. A scheme is presented that adjusts the number of hidden layer nodes in a neural network so as to give an overdetermined approximation. The advantages and disadvantages of using multiple output nodes are discussed. Guidelines for selecting the number of output nodes are presented.

show abstract

Application of neural networks to preliminary structural design

Cited by 34 publications

References 1 publication

Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures

Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures

Application of the Concurrent Subspace Design framework to aircraft brake component design optimization

Selecting the architecture of a class of back-propagation neural networks used as approximators

Contact Info

Product

Resources

About