Scour depth at abutment is a major cause of bridge failure and significant issue towards maintenance cost of a bridge. Thus, early estimation of scour depth at abutment is essential for safe and cost-effective abutment structure design. Extensive research has been carried out to develop methods for predicting the depth of abutment scour. Despite various models presented by researchers to estimate the equilibrium local scour depth, an efficient technique with enhanced estimation capability will be more beneficial. The paper is aimed at investigating the applicability of soft computing (SC) models viz. artificial neural network, gene-expression programming (GEP) and hybrid techniques for estimation of scour depth around vertical, semi-circular and 45° wing-wall abutments using laboratory data compiled from published literature. The paper also emphasizes on further enhancement of the performances of the SC based models. On experimentations, the performance of multilayer perceptron (MLP) neural network for each type of abutment was found more effective than radial basis function network, GEP model and empirical equations. The generalization performance of optimal MLP network developed for each type of abutment was then improved with evolving connection weights of the MLP by Genetic Algorithm (GA-MLP). Finally, the hybrid model is validated with different types of validation techniques. The study demonstrates the suitability of the SC based hybrid methodology in improving the predictive accuracy of scour depth around different types of abutments.

Scour depth, artificial neural network, genetic algorithm, hybrid technique, GEP

[1] A. K. Barbhuya, S. Dey, “Local scour at abutments: a review”, Sadhana, Vol. 29, Issue 5, pp. 449–476, 2004.
[2] G. H. Macky, Survey of roading expenditure due to scour, CR 90_09, Department of Scientific and Industrial Research, Hydrology Centre, Christchurch, New Zealand, 1990.
[3] D. C. Froehlich, “Local scour at bridge abutments”, Proc. Natl. Conf. Hydraulic Engineering (New Orleans, LA: Am. Soc. Civil Eng.), pp. 13–18, 1989.
[4] B. W. Melville, “Pier and abutment scour: Integrated approach”, Journal of Hydraulic Engineering, Vol. 123, Issue 2, pp. 125-136, 1997.
[5] J. K. Kandasamy, B. W. Melville, “Maximum local scour depth at bridge piers and abutments”, J. Hydraul. Research, Vol. 36, Issue 2, pp. 183-198, 1998.
[6] S. Dey, A. K. Barbhuiya, “Time Variation of Scour at Abutments”, Journal of Hydraulic Engineering, Vol. 131, Issue 1, pp. 11-23, 2005.
[7] R. Mohammadpour, “Estimation of dimension and time variation of local scour at short abutment”, Intl. J. River Basin Management, Vol. 11, Issue 1, pp. 121–135, 2013.
[8] J. H. Shin, H.I Park, “Neural Network Formula for Local Scour at Piers Using Field Data”, Marine Georesources & Geotechnology, Vol. 28, Issue 1, pp. 37-48, 2010.
[9] T. L. Lee, D.S. Jeng, G.H. Zhang, G.H. Hong, “Neural network modeling for estimation of scour depth around bridge piers”, Journal of hydrodynamics, Vol. 19, Issue 3, pp. 378-386, 2007.
[10] T. Gamal, M. Hosny, T. Al_Samman, N. Aboul_Atta, “Artificial Neural Network Prediction Of Maximum Scour Around Brige Piers Due To Aquatic Weeds’ Racks”, International Journal of Engineering, Research & Technology, Vol. 2, Issue 6, pp. 2322-2336, 2013.
[11] S. A. Begum, A. K. Md. Fujail, A. K. Barbhuiya, “Radial Basis Function to predict scour depth around bridge abutment”, IEEE Proceedings of the 2011 2nd National Conference on Emerging Trends and Applications in Computer Science, (Shillong, Meghalaya, India), ISBN- 978-1-4244-9581-8, pp. 76-82, 2011.
[12] S. A. Begum, A. K. Md. Fujail, A. K. Barbhuiya, “Artificial Neural Network to Predict Equilibrium Local Scour Depth around Semicircular Bridge Abutments”, 6thSASTech, Malaysia, Kuala Lumpur, 2012.
[13] H. M. Azamathulla, A. Ab. Ghani, “ANFIS-Based Approach for Predicting the Scour Depth at Culvert Outlets”, Journal of Pipeline Systems Engineering and Practice, ASCE, Vol. 2 Issue 1, pp. 35-40, 2011.
[14] M. Muzzammil, J. Alam, “ANFIS-based approach to scour depth prediction at abutments in armored beds”, Journal of Hydroinformatics, IWA Publishing, Vol. 13, Issue 4, pp. 699-713, 2011.
[15] H. M. Azamathulla, A. Ab. Ghani, N. A. Zakaria, A. Guven, “Genetic Programming to Predict Bridge Pier Scour”, Journal of Hydraulic Engineering, Vol. 136, Issue 3, pp. 165-169, 2010.
[16] R. Mohammadpour, A. Ab. Ghani, H. M. Azamathulla, “Estimating time to equilibrium scour at long abutment by using genetic programming”, 3rd International conference on managing rivers in the 21th century: Sustainable Solutions for Global Crisis of Flooding, Pollution and Water Scarcity, Rivers, Penang, Malaysia, pp. 369-374, 2011.
[17] R. Mohammadpour,, A. Ab. Ghani, H. M. Azamathulla, “Prediction of equilibrium scour time around long abutments”, Water Management, pp. 1-8, 2012.
[18] M. Khan, H. M. Azamathulla, M. Tufail, A. Ab. Ghani, “Bridge pier scour prediction by gene expression programming”, Water Management, Vol. 165, Issue 9, pp. 481-493, 2012.
[19] H. M. Azamathulla, M. Azlan, M. Yusoff, “Soft computing for prediction of river pipeline scour depth”, Neural Comput & Applic, Springer-Verlag London, pp. 1-5, 2012.
[20] R. Mohammadpour, A. Ab. Ghani, H. M. Azamathulla, “Estimation of dimension and time variation of local scour at short abutment”, Intl. J. River Basin Management, Vol. 11, Issue 1, pp. 121–135, 2013.
[21] S. E. Coleman, C. S. Lauchlan, B. W. Melville, “Clear-water scour development at bridge abutments”, Journal of Hydraulic Research, Vol. 41, Issue 5, pp. 521–531, 2003.
[22] F. Ballio, A. Teruzzi and Radice, “A. Constriction Effects in Clear-Water Scour at Abutments, Journal of Hydraulic Engineering, Vol. 135, Issue 2, pp. 140-145, 2009.
[23] M. H. Mazumder, Live-bed scour at abutment, PhD thesis, NIT, Silchar, 2015,.
[24] B. W. Melville, “Local scour at bridge abutment”, Journal of Hydraulic Engineering, Vol. 118, Issue 4, pp. 615-631, 1992.
[25] K. Levenberg, “A Method for the Solution of Certain Non-Linear Problems in Least Squares”, The Quarterly of Applied Mathematics, Vol. 2, pp. 164–168, 1944.
[26] C. Ferreira, “Gene Expression Programming: A newadaptive algorithm for solving problems”, Complex Systems, Vol. 13, Issue 2, pp. 87–129, 2001..
[27] C. Ferreira, “Function finding and a creation of numerical constants in gene expression programming”, In: Advances in Soft Computing, Engineering Design and Manufacturing (J.M. Benitez, O. Cordon, F. Hoffmann and R. Roy, Eds.), Springer-Verlag: Berlin, pp. 257–266, 2003.
[28] J. Koza, “Genetic programming: On the programming of computers by means of natural selection, MIT Press, Cambridge, 1992.
[29] S. Rajasekaran, G.A.V. Pai, “Neural network, fuzzy logic and genetic algorithms (Synthesis and applications), PHI learning, Delhi, 2014.
[30] G. Levitin, “Computational Intelligence in Reliability Engineering, Studies in computational Intelligence”, Vol. 39, Springer-Verlag Berlin Heidelberg, 2007.