Abstract
An important advantage of cold-formed steel is the great flexibility of cross-sectional profiles and sizes available to the structural steel designer. However, this flexibility, in addition to the complex rules that govern cold-formed member design, makes the selection of the most economical section for a particular application difficult, both in optimisation terms. and in terms of practical design. Selecting the best cold-formed solution requires numerous iterations involving analysis of several possible profiles and aspect ratios. This process becomes prohibitively expensive due to the amount of computer time required for convergence to an optimum design. This paper investigates the potential for using neural networks to overcome these design problems. By carefully training a neural network with data relating section profile, aspect ratio and size to the load carrying capacity, the neural network can be prepared to estimate the best section requirements in new applications. The paper describes how this process has been carried out for a limited range of section profiles and presents an assessment of the results obtained. (C) 2001 Elsevier Science Ltd. All rights reserved.
| Original language | English |
|---|---|
| Pages (from-to) | 1687-1696 |
| Number of pages | 10 |
| Journal | Computers and Structures |
| Volume | 79 |
| Issue number | 18 |
| DOIs | |
| Publication status | Published - Jul 2001 |
Keywords
- structural applications
- neural networks
- design
- cold-formed steel