High Embankment Dam Stability Analysis Using Artificial Neural Networks

Abstract

Regular surveillance, data acquisition, and visual observation of high embankment dams are extremely important for the stability analysis of these structures. The stability issues that could occur during a dam's lifetime are mainly related to slope instability and internal erosion. The aim of continuous dam security monitoring and field measurement is to identify priority flow paths in the dam body, i.e. cracks and the erosion process. A key parameter for embankment dam stability assessment is the pore water pressure (PWP) response in the clay core. Increasing pore water pressure results in shear strength reduction and can cause dam instability. In this paper, four different models based on artificial neural networks will be developed for pore water pressure prediction in an embankment dam clay core, based on meteorological, hydrological, and geotechnical data. These models will be compared and the model that gives the smallest prediction error will be presented. In the light of climate change, the main objective of this paper is to find the model that can be used for embankment dam stability prediction in extreme weather events.

Keywords

• artificial neural network
• embankment dam
• pore water pressure
• stability analysis