Bridge pier live load analysis using neural networks

Authors:
Mark E. Williams;Marc I. Hoit
Affiliations:
Department of Civil and Coastal Engineering, Florida Bridge Software Institute, University of Florida, P.O. Box 116580, Gainesville, FL;College of Engineering, University of Florida, P.O. Box 116580, Gainesville, FL
Venue:
Advances in Engineering Software - Special issue on engineering computational technology
Year:
2004

Citing 4
Cited 1

Neural computing: theory and practice

Neural computing: theory and practice
Neurocomputing

Neurocomputing
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Analysis of highway bridges using computer-assisted modeling, neural networks, and data compression techniques

Analysis of highway bridges using computer-assisted modeling, neural networks, and data compression techniques

Prediction of lateral confinement coefficient in reinforced concrete columns using neural network simulation

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The positioning of vehicular live loads on a bridge superstructure to achieve the maximum force effects in the bridge pier is an important design issue. For highway bridges, the worst load positioning for the superstructure design usually does not produce the worst force effects for the pier design. As a result, the correct positioning of the loads for the pier is left to engineering judgment. This paper investigates an implementation of neural networks to predict the worst load positioning for the bridge pier. The networks predict the load positioning for both single and multiple column piers given input parameters that describe the pier and bridge configuration. The procedure presented herein is intended to offer an alternative to the trial and error load positioning method used by many practicing engineers.