Design of Riprap Stone Around Bridge Piers Using Empirical and Neural Network Method
An attempt was made to develop a method for sizing stable riprap around bridge piers based on a huge amount of experimental data, which is available in the literature. All available experimental data for circular as well as round-nose-and-tail rectangular piers were collected. The data for rectangul...
Saved in:
Published in | Civil engineering infrastructures journal Vol. 48; no. 1; pp. 175 - 188 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
University of Tehran Press
01.06.2015
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | An attempt was made to develop a method for sizing stable riprap around bridge piers based on a huge amount of experimental data, which is available in the literature. All available experimental data for circular as well as round-nose-and-tail rectangular piers were collected. The data for rectangular piers, with different aspect ratios, aligned with the flow or skewed at different angles to the flow, were used in this analysis. In addition, new experiments were also conducted for larger pier width to riprap size ratio, which was not available in the literature. Based on at least 190 experimental data, the effect of important parameters on riprap stability were studied which showed that the effective pier width is the most effective parameter on riprap stability. In addition, an empirical equation was developed by multiple regression analysis to estimate the stable riprap stone size around bridge piers. The ratio of predicted to experiment riprap size value for all experimental data is larger than one with an average value of 1.75, which is less than many other empirical equations. Finally, in order to achieve a higher accuracy for riprap design, the artificial neural network (ANN) method based on utilizing non-dimensional parameters was deployed. The results showed that the ANN model provides around a 7% improved prediction for riprap size compared to the conventional regression formula. |
---|---|
ISSN: | 2322-2093 2423-6691 |
DOI: | 10.7508/ceij.2015.01.012 |