Analysis of the influence of the daily regulation of power stations on navigable flow conditions at river confluences using the LSTM model

Abstract

The daily operations of large hydropower stations on rivers induce frequent variations in downstream water levels and flow velocities, resulting in unsteady and complex hydraulic characteristics at the confluence of the main stream and its tributaries, which adversely affect navigation safety. The continuity and momentum equations, along with the RNG k-ϵ turbulence model and the VOF model, were employed to simulate the river flow process at the confluence under unsteady flow conditions. The simulated results for water levels and velocity vector fields are in good agreement with experimental data. Variations in hydraulic characteristics, including water level, flow velocity, and longitudinal gradient at the confluence of the main stream and its tributaries, were analysed. The results indicated that the water level at the confluence decreases when the tributary merges with the main stream. As the confluence ratio increases, fluctuations in the water level at the confluence decrease. However, an increase in the staggered period results in greater fluctuations in the water level within this region. Moreover, a crescent-shaped high-speed flow region is formed at the confluence of the tributary and the main stream. As the unsteady flow discharge of the main stream increases, the relative area of this region correspondingly enlarges, reaching its maximum at peak discharge, and subsequently gradually diminishes as the discharge decreases. Based on these simulation data, a Long Short-Term Memory (LSTM) model was developed to effectively predict water levels and flow velocities, providing a more convenient and accurate method for obtaining real-time information on confluence areas than traditional mathematical and statistical approaches. This study provides novel insights into predicting flow characteristics in confluence areas, thereby offering a basis for formulating navigation safety plans.

Keywords

• Unsteady flow
• river confluence
• numerical simulation
• deep learning
• navigational flow conditions