scour modeling piles of kambuzia industrial city bridge using hec-ras and artificial neural network

today, scouring is one of the important topics in the river and coastal engineering so that the most destruction in the bridges is occurred due to this phenomenon. whereas the bridges are assumed as the most important connecting structures in the communications roads in the country and their importance is doubled while floodwater, thus exact design and maintenance thereof is very crucial. for this purpose, the exact design has a substantial effect. therefore, the initial data of design should have the required and acceptable accuracy, at the meanwhile the scour depth is very important for the bridge piers so that the précised estimation of this depth increases the life time of operation and reduces the maintenance costs. in this study, scour of bridge pier at the entrance of kambuzia industrial area of zahedan has been discussed and investigated as a case study. for this purpose, hydraulic structures analysis software (hec-ras) has been used for bridge scour modeling. the summary of results indicates the depth 3.21m of scour for the piers of this bridge. as well as, establishment of hydraulic barriers such as gabion walls as a strategy for reduction of scour depth has been studied. the summary of modeling these barriers aiding hec-ras shows the effectiveness of this subject on the reduction of bridge’s scour depth, so that upon making these barriers in the bridge upstream, the scour depth has been reduced more than 25%. in continue, to present a useful method for estimation of scour depth, artificial neural network intelligent systems (ann) has been used. to evaluate the function of the mentioned method, the data resulted from analysis of studied bridge scour by hec-ras software has been used in four modes including raw, normalized, dimensionless and normalized dimensionless. after determination of the best structure for each one of these modes, for extendibility and ensuring from results of this method, a series of prototypes have been used to test the networks. the summary demonstrates the appropriate efficiency of this method in prediction of bridges scour depth. the results of this research show that normalization and dimensionless-making of data used in the neural networks causes the improvement of these networks’ function in prediction of the maximum scour depth comparing to the raw data mode.