Confluences act as critical nodes in a river network as they affect flow, sediment transport, water quality, and ecological patterns. A complete knowledge about hydro‐morpho‐sedimentary processes at river confluences is still incompleted and it has been usually accepted that secondary flows are weak because of the significant role of form roughness in large rivers. In this study, two field surveys were conducted on the flow structure, suspended sediment transport and morphology of the confluence between the Yangtze River (the largest river in China) and the Poyang Lake (the largest freshwater lake in China). Dual counter‐rotating cells were observed during high flow conditions and a single secondary cell appeared in low flow conditions. These helical cells restricted the core size of high sediment concentration and downwelling flows acted as a barrier hindering the exchange of sediment between the two rivers. Furthermore, the observed large scour hole was likely related to the downwelling and upwelling flows caused by helical motions. In low flow conditions, the scour hole looked like a deep channel, which was likely related to a long‐surviving helical cell. The scour hole disappeared further downstream, when either the helical motion got weak during low flow conditions, or when a reverse helical cell occurred during high flow conditions. Hydrodynamics, suspended sediment transport and morphological features observed at such a large confluence demonstrated that river planform geometry and discharge ratio affected the flow structure, especially the helical motion. This in turn affected sediment transport as well as the local bed morphology.

The knowledge of the dynamics of urban channel confluences is insufficient as most past studies have focused on natural river confluences. This paper reports experimental observations on bed morphology and hydrodynamics of the urban confluences and their dependence to the discharge ratio. Typical hydrodynamic and morphological features such as the shear layer, helical cells, bars and scour holes are identified. Nevertheless, the presence of a region of low-velocity flow for a small discharge ratio differs from results obtained in previous studies. Two sand ridges associated with the corridors of the eroded sediment from the scour holes merge into a mid-stream bar. Results also show that the intense shear towards the bed by downwelling and upwelling flows involved in helical motions is responsible for the mid-stream scour hole.

Large-volume hydraulic concrete structures, such as concrete dams, often suffer from damage due to the influence of alternating loads and material aging during the service process. The occurrence and further expansion of cracks will affect the integrity, impermeability, and durability of the dam concrete. Therefore, monitoring the changing status of cracks in hydraulic concrete structures is very important for the health service of hydraulic engineering. This study combines computer vision and artificial intelligence methods to propose an automatic damage detection and diagnosis method for hydraulic structures. Specifically, to improve the crack feature extraction effect, the Xception backbone network, which has fewer parameters than the ResNet backbone network, is adopted. With the aim of addressing the problem of premature loss of image detail information and small target information of tiny cracks in hydraulic concrete structures, an adaptive attention mechanism image semantic segmentation algorithm based on Deeplab V3+ network architecture is proposed. Crack images collected from concrete structures of different types of hydraulic structures were used to develop crack datasets. The experimental results show that the proposed method can realize high-precision crack identification, and the identification results have been obtained in the test set, achieving 90.537% Intersection over Union (IOU), 91.227% Precision, 91.301% Recall, and 91.264% F1_score. In addition, the proposed method has been verified on different types of cracks in actual hydraulic concrete structures, further illustrating the effectiveness of the method.

Laboratory experiments were carried out to investigate local scouring around twin cylindrical piers in open-channel flows. The experimental results of clear-water scouring around the twin piers show that the scour hole formed around the upstream pier at different pier spacing was almost the same as that around an isolated pier. However, the local scour depth around the downstream pier was less than that around the upstream pier. The local scour depth around the downstream pier with the velocity can be segregated into four regions: a no-scour region, synchronous-scouring region, transition region, and a radical-deviation region. Finally, a relationship between the deviation in the radical-deviation region and the spacing of the two piers was obtained.