ANN optimized by PSO and Firefly algorithms for predicting scour depths around bridge piers

The estimation of scour depths is extremely important in designing the foundation of piers which ensure the integrity of bridges and other hydraulic structures. Complicated hydrodynamic processes around piers are the main challenge to formulate explicitly empirical equations in providing scour depth estimation. Consequently, the proposed empirical formulae only yield good prediction results for specific conditions. In this study, the particle swarm optimization and Firefly algorithms are proposed to optimize artificial neural network (ANN) models to improve predicting the scour depths around circular piers at the equilibrium stage. The results of the proposed modelling frameworks are compared with an ANN network trained by the Levenberg–Marquardt (LM) algorithm which was widely adopted in the literature for prediction purposes. The predicted results exhibit that the equilibrium maximum scouring depths derived from our proposed models are better compared to the values from empirical models and the single ANN model trained by LM. Our study implicates that the new model frameworks could successfully replace the traditional methods, and more applications of these frameworks on computational fluid mechanics and hydraulic structure designs should be considered.

[1]  B. Melville,et al.  Scale Effect in Pier-Scour Experiments , 1998 .

[2]  Robert Ettema,et al.  SCOUR AT BRIDGE PIERS , 1980 .

[3]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[4]  Xin-She Yang,et al.  Nature-Inspired Metaheuristic Algorithms , 2008 .

[5]  Kittur G. Ranga Raju,et al.  TEMPORAL, VARIATION OF SCOUR AROUND CIRCULAR BRIDGE PIERS , 1992 .

[6]  Abidin Kaya,et al.  Artificial neural network study of observed pattern of scour depth around bridge piers , 2010 .

[7]  Duong Tran Anh,et al.  Improved Rainfall Prediction Using Combined Pre-Processing Methods and Feed-Forward Neural Networks , 2019, J.

[8]  A. Melih Yanmaz,et al.  STUDY OF TIME-DEPENDENT LOCAL SCOUR AROUND BRIDGE PIERS , 1991 .

[9]  Roland K. Price,et al.  Machine Learning Approach to Modeling Sediment Transport , 2007 .

[10]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[11]  Jasim Imran,et al.  Numerical Modeling of Three-Dimensional Flow Field Around Circular Piers , 2004 .

[12]  V. R. Schneider,et al.  Local Scour Around Bridge Piers , 1969 .

[13]  Dong-Sheng Jeng,et al.  Neural Network Modeling for Estimation of Scour Depth Around Bridge Piers , 2007 .

[14]  B. Melville.  PIER AND ABUTMENT SCOUR: INTEGRATED APPROACH , 1997 .

[15]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[16]  A. J. Sutherland,et al.  DESIGN METHOD FOR LOCAL SCOUR AT BRIDGE PIERS , 1988 .

[17]  Vijay Panchang,et al.  Three-Dimensional Simulation of Scour-Inducing Flow at Bridge Piers , 1998 .

[18]  Slawomir Zak,et al.  Firefly Algorithm for Continuous Constrained Optimization Tasks , 2009, ICCCI.

[19]  W. Hager,et al.  Temporal Evolution of Clear-Water Pier and Abutment Scour , 2002 .

[20]  Holger R. Maier,et al.  State of the Art of Artificial Neural Networks in Geotechnical Engineering , 2008 .

[21]  B. Melville,et al.  TIME SCALE FOR LOCAL SCOUR AT BRIDGE PIERS , 2000 .

[22]  Satyobroto Talukder,et al.  Mathematical Modelling and Applications of Particle Swarm Optimization , 2011 .

[23]  Mufeed Odeh,et al.  Large scale clear-water local pier scour experiments , 2004 .

[24]  H. W. Shen,et al.  Local Scour Around Cylindrical Piers , 1977 .

[25]  D. Legates,et al.  Evaluating the use of “goodness‐of‐fit” Measures in hydrologic and hydroclimatic model validation , 1999 .

[26]  Edward E. Fischer,et al.  Closure of "Scour Around Bridge Piers at High Flow Velocities" , 1980 .