Estimation of Bridge Pier Scour Using Statistical Methods and Intelligent Algorithms

When a stream is partially obstructed by a bridge pier, the flow pattern around the pier is significantly changed. Changes in flow pattern are the cause scour around piers. Bridge pier scouring estimates, is an important parameter in the design of bridges because inattention to it may cause damage or reduce the life of the bridge [1-4]. The safe and economical design of bridge piers requires accurate prediction of the maximum scour depth around their foundations [5].
Mathematical Principles of SVM is based Russian mathematician researches [6]. Ghazanfari Hashemi and Etemad Shahidi had predicted bridge pier scour using SVM method in a laboratory model. They showed that this method is more accurate than empirical relationship. Although extensive studies have been conducted on the pier scour, but a valid relationship does not exist that gives satisfactory results in different conditions [5].
Bates and Granger is one of the first research works in the field of hybrid approach [7]. Shamseldin et al. was used combination methods such as simple average, weighted average and neural network to predict floods [8].
Studying literature reveals that there is a lack of reliable formulas for prediction of the scour depth to cover different condition. The aim of this study is combination of the various pier scour relationships to predict the scour depth using conventional and intelligent (SVM) methods and combination of effective parameters of this phenomenon.