Sensitivity analysis of parameters affecting scour depth around bridge piers based on the non-tuned, rapid extreme learning machine method

The extreme learning machine (ELM) is a new, non-tuned and fast training algorithm for feedforward neural networks (FFNN). It is highly precise and randomly produces the input weights of single-layer FFNN. In the current study, the scour depth around bridge piers is predicted by ELM as a powerful method of nonlinear system modeling. To predict scour depth, the effective dimensionless parameters are determined through dimensional analysis. Due to the complexity of scour mechanisms around bridges, different models with diverse input numbers are presented. In 5 categories, 31 different models were obtained for modeling and ELM analysis. Following the training and validation of each model presented, the optimum model was selected from each of the 5 categories and its relationship to the respective category was identified to help determine scour depth in practical engineering. For the best models presented in the different input modes, new explicit expressions were deduced. The results show that the most important parameters affecting relative scour depth (ds/y) include ratio of pier width to flow depth (D/y) and ratio of pier length to flow depth (L/y) (RMSE = 0.08; MARE = 0.0.35). The ELM performance was compared for a range of pier geometries with regression-based equations. The results confirm that ELM outperforms other methods.

[1]  Peggy A. Johnson,et al.  Reliability‐Based Pier Scour Engineering , 1992 .

[2]  Mahmud Güngör,et al.  Generalized Regression Neural Networks and Feed Forward Neural Networks for prediction of scour depth around bridge piers , 2009, Adv. Eng. Softw..

[3]  H. Md. Azamathulla,et al.  Soft computing for prediction of river pipeline scour depth , 2012, Neural Computing and Applications.

[4]  Mohammad Najafzadeh,et al.  Neuro-fuzzy GMDH based particle swarm optimization for prediction of scour depth at downstream of grade control structures , 2015 .

[5]  ChunTian Cheng,et al.  Monthly discharge forecasting using wavelet neural networks with extreme learning machine , 2014, Science China Technological Sciences.

[6]  H. Md. Azamathulla,et al.  Gene-expression programming to predict pier scour depth using laboratory data , 2012 .

[7]  Mohammad Najafzadeh,et al.  Neuro-fuzzy GMDH systems based evolutionary algorithms to predict scour pile groups in clear water conditions , 2015 .

[8]  Shahaboddin Shamshirband,et al.  A combined support vector machine-wavelet transform model for prediction of sediment transport in sewer , 2016 .

[9]  Ahmed M. A. Sattar,et al.  Gene Expression Models for the Prediction of Longitudinal Dispersion Coefficients in Transitional and Turbulent Pipe Flow , 2014 .

[10]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

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

[12]  H. Md. Azamathulla,et al.  Genetic Programming to Predict Bridge Pier Scour , 2010 .

[13]  Yan Wang,et al.  Extreme Learning Machine for Reservoir Parameter Estimation in Heterogeneous Reservoir , 2015 .

[14]  Stanley R. Davis,et al.  Evaluating scour at bridges. , 1995 .

[15]  R. Deo,et al.  Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia , 2015 .

[16]  Mohammad Najafzadeh,et al.  Group method of data handling to predict scour depth around vertical piles under regular waves , 2013 .

[17]  C. Veṅkaṭādri,et al.  Scour Around Bridge Piers and Abutments , 1965 .

[18]  Lloyd H.C. Chua,et al.  Predicting time-dependent pier scour depth with support vector regression , 2012 .

[19]  Mustafa Gunal,et al.  Prediction of Scour Downstream of Grade-Control Structures Using Neural Networks , 2008 .

[20]  Hossein Bonakdari,et al.  A combined adaptive neuro-fuzzy inference system–firefly algorithm model for predicting the roller length of a hydraulic jump on a rough channel bed , 2018, Neural Computing and Applications.

[21]  Bahram Gharabaghi,et al.  Gene expression models for prediction of longitudinal dispersion coefficient in streams , 2015 .

[22]  Mahesh Pal,et al.  Support vector regression based modeling of pier scour using field data , 2011, Eng. Appl. Artif. Intell..

[23]  Aminuddin Ab. Ghani,et al.  Bridge pier scour prediction by gene expression programming , 2012 .

[24]  Mohammad Najafzadeh,et al.  Comparison of group method of data handling based genetic programming and back propagation systems to predict scour depth around bridge piers , 2011 .

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

[26]  Mohammad Najafzadeh,et al.  GMDH based back propagation algorithm to predict abutment scour in cohesive soils , 2013 .

[27]  Dennis A. Lyn,et al.  A Laboratory Sensitivity Study of Hydraulic parameters Important in the Deployment of Fixed-In-Place Scour-Monitoring Devices , 2000 .

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

[29]  H. Md. Azamathulla,et al.  Assessment of M5′ model tree and classification and regression trees for prediction of scour depth below free overfall spillways , 2012, Neural Computing and Applications.

[30]  Abdul Halim Ghazali,et al.  Validation of some bridge pier scour formulae using field and laboratory data , 2005 .

[31]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[32]  Mohammad Najafzadeh,et al.  Prediction of pipeline scour depth in clear-water and live-bed conditions using group method of data handling , 2012, Neural Computing and Applications.

[33]  Mohammad Reza Nikoo,et al.  Development of expert systems for the prediction of scour depth under live-bed conditions at river confluences: Application of different types of ANNs and the M5P model tree , 2015, Appl. Soft Comput..

[34]  Mohammad Najafzadeh,et al.  Application of improved neuro-fuzzy GMDH to predict scour depth at sluice gates , 2015, Earth Science Informatics.

[35]  David S. Mueller,et al.  U.S. Geological Survey Field Measurements of Pier Scour , 1999 .

[36]  H. Md. Azamathulla,et al.  Linear genetic programming for prediction of circular pile scour , 2009 .

[37]  Mustafa Gunal,et al.  Genetic Programming Approach for Prediction of Local Scour Downstream of Hydraulic Structures , 2008 .

[38]  Ali Selamat,et al.  Extreme Learning Machines Based Model for Predicting Permeability of Carbonate Reservoir , 2013 .

[39]  P. Bahr,et al.  Sampling: Theory and Applications , 2020, Applied and Numerical Harmonic Analysis.

[40]  P. B. Deolalikar,et al.  Neural Networks for Estimation of Scour Downstream of a Ski-Jump Bucket , 2005 .

[41]  Amir Hossein Zaji,et al.  Adaptive neuro-fuzzy inference system multi-objective optimization using the genetic algorithm/singular value decomposition method for modelling the discharge coefficient in rectangular sharp-crested side weirs , 2016 .

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