ASCE will be sunsetting the Civil Engineering Database (CEDB) in the coming months. We encourage you to start using the ASCE Library to perform content searches. In the ASCE Library, you can save your search results as well as receive email content alerts when new content relevant to your area of interest is published. Try it out today at https://ascelibrary.org.

 

Neural Network Learning in Structural Engineering Applications

by D. J. Gunaratnam, Univ of Sydney, Sydney, Australia,
J. S. Gero, Univ of Sydney, Sydney, Australia,



Document Type: Proceeding Paper

Part of: Computing in Civil and Building Engineering

Abstract:

Neural networks based on the backpropagation learning algorithm have been used in a number of structural engineering applications. The paper classifies the different types of relationships that arise in these applications and describes different ways of enhancing the performance of these networks. It identifies three levels at which enhancements can be effected. The different techniques that have been successfully implemented at each level are described and techniques that can be combined to further improve performance are identified. These combined techniques are then used to learn design relationships for polar orthotropic circular plates.

Subject Headings: Neural networks | Plates | Algorithms | Structural engineering | Structural design | Orthotropic materials | Artificial intelligence (AI)

Services: Buy this book/Buy this article

 

Return to search