Prediction of Local scour around bridge pier using Soft Computing Techniques

Abstract

Bridges play an essential role in the society since they enable quick access across a river or any water body. Bridges facilitate transportation of goods and people and hence play a leading role in the development of a province. The safety of the bridge is the important factor with respect to scour failure which is the leading failure factor in river bridges. Scour is the removal of sediment near or around the structure which is located in the flowing water. There are different factors which affects scour mainly on the scour depth are flow depth, discharge, velocity, sediment size, porosity, pier shape and size etc. There are two types of scour conditions on which scour is classified and studied namely, clear water and live bed scour. The scour is the complex phenomenon and there is no common or general simple method to predict the scour depth around the bridge pier. There are several researchers who studied the scour mechanism using laboratory experiments. In the present days the artificial intelligence is the focal point for several researchers. Soft computing techniques, such as, Artificial Neural Network (ANN), Support Vector Machine (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Particle Swarm Optimization (PSO) have been efficiently used for modeling scour related problems. The study used the data for developing the soft computing models, is obtained from a physical model study on scour depth around bridge pier, carried out by Goswami Pankaj in 2013 in a 2-D wave flume. The input parameters, namely, sediment size (d50), velocity (U), time (t) and sediment quantity (ppm) are used to predict the scour depth of different pier shapes such as circular, rectangular, round nosed and sharp nosed pier for both clear water and live bed scour condition. The complete original data is divided into training and testing. In the study, the soft computing techniques such as ANN, SVM, ANFIS, PSO-SVM and PSO-ANN are developed. The ANN model with feed-forward backpropagation network is developed with different hidden neurons. The RBF, Linear and Polynomial kernel functions are used in the SVM model. the ANFIS model is also developed with Trapezoidal, Gbell and Triangular membership function. The evolutionary optimization technique, particle swarm optimization is used to tune the SVM and ANN parameters to improve the efficiency of models prediction.ii The performance of individual and hybrid soft computing models are compared using statistical parameters such as, Correlation Coefficient (CC), Normalized Root Mean Square Error (NRMSE), Nash–Sutcliffe coefficient (NSE) and Normalized Mean Bias (NMB). Scatter plots are used to evaluate the accuracies of the models and box plots were used to analyze the spread or distribution of the data points estimated by the models. The validation of the developed models is done using the experimental values. The validation results shows that the proposed models are well correlated and in good agreement with experimental results. The hybrid models displayed a better performance compared to individual models. It is found that the hybrid PSO-SVM model is the best and efficient model in estimating the scour depth effectively around bridge pier for both live bed and clear water scour condition when compared to all the other models developed.