EXPERIMENTS WITH NEURAL NETWORKS AS A DESIGN-SUPPORT TOOL FOR COMPLEX ENGINEERING SYSTEMS

Abstract

Many civil engineering problems are based on an understanding of relationships between variables. Many of these variables are established from experimental or numerical observations and are defined in terms of algebraic expressions involving the variables. This paper focuses on the potential applications of neural networks for evaluating the relationships between these variables and for modelling complex and non-linear systems. Demonstration of the potential of this approach is illustrated through three civil engineering examples.

KEY WORDS:

• Civil engineering
• data analysis
• neural networks
• non-linear systems