Neural Networks in Civil Engineering. I: Principles and Understanding

TLDR

The first of two papers discusses the understanding, usage, and potential of artificial neural networks in civil engineering, while the second demonstrates their application to various civil engineering problems. The papers aim to develop a clear understanding of neural network operation and address key issues to ensure successful development and application in civil engineering. A supervised feedforward network is used to solve a simple structural‑analysis problem, followed by discussion of learning factors, training pattern selection, configuration limitations, and validation. The study presents a graphical interpretation of how neural networks operate.

Abstract

This is the first of two papers providing a discourse on the understanding, usage, and potential for application of artificial neural networks within civil engineering. The present paper develops an understanding of how these devices operate and explains the main issues concerning their use. A simple structural‐analysis problem is solved using the most popular form of neural‐networking system—a feedforward network trained using a supervised scheme. A graphical interpretation of the way in which neural networks operate is first presented. This is followed by discussions of the primary concepts and issues concerning their use, including factors affecting their ability to learn and generalize, the selection of an appropriate set of training patterns, theoretical limitations of alternative network configurations, and network validation. The second paper demonstrates the ways in which different types of civil engineering problems can be tackled using neural networks. The objective of the two papers is to ensure the successful development and application of this technology to civil engineering problems.