Using the combination of genetic algorithm and artificial neural network to estimate scour depth around bridge foundations

Abstract

Scouring is a natural phenomenon that occurs as a result of the erosive action of water flow in alluvial waterways. This phenomenon is considered a serious threat to the stability of structures located in the flow path, such as the foundations of bridges. One of the most important and effective factors in the destruction and failure of bridges is scouring around bridge foundations and supports. Today, with the progress of science and technology, the use of intelligent computer systems for modeling complex and non-linear phenomena has become increasingly important. In this research, using real data, the efficiency of artificial intelligence systems, which include a combination of multilayer perceptron neural network and genetic algorithm, has been investigated. Among the models with different number of hidden neurons, the artificial neural network with three hidden neurons has the least error. Comparing the values ​​of the difference ratio between the proposed neuro-genetic model and the existing common equations shows that the accuracy of the neuro-genetic model has a higher efficiency compared to other equations. The root mean square error in the proposed model was calculated as 0.51, while this value was calculated above 0.89 for the existing experimental equations.

Keywords

• bridge breaking
• artificial intelligence
• genetic algorithm
• multilayer perceptron neural network