TY - JOUR ID - 53714 TI - Design of Riprap Stone Around Bridge Piers Using Empirical and Neural Network Method JO - Civil Engineering Infrastructures Journal JA - CEIJ LA - en SN - 2322-2093 AU - Karimaee Tabarestani, Mojtaba AU - Zarrati, Amir Reza AD - Ph.D. of Water Engineering, Civil and Environmental Department, Amirkabir University of Technology, P.O. Box 15915, Tehran, Iran AD - Professor, Civil and Environmental Department, Amirkabir University of Technology, P.O. Box 15915, Tehran, Iran Y1 - 2015 PY - 2015 VL - 48 IS - 1 SP - 175 EP - 188 KW - Artificial Neural Network Method KW - Local Scour KW - Rectangular and Circular Bridge Pier KW - Riprap Design KW - Riprap Stone Stability KW - Shear Failure DO - 10.7508/ceij.2015.01.012 N2 - 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. UR - https://ceij.ut.ac.ir/article_53714.html L1 - https://ceij.ut.ac.ir/article_53714_152badcf667bcf2c2827b6177aa05cc7.pdf ER -