To overcome the limitations of existing research in effectively addressing the high-dimensional and nonlinear hydraulic processes in open-channel sections of water transfer projects under water diversion disturbances during the icing period， and the high reliance on manual experience in actual operations， this study takes the Wangnou-ruwugou section of the Jiaodong Water Transfer Project as a case study to investigate real-time intelligent hydraulic regulation of gate-pump groups in open channels. Through one-dimensional hydrodynamic simulations of gate-pump groups， step disturbances were applied to the diversion flows of canal pools to reveal the coupling mechanism between hydraulic processes in open channels and the operational responses of gate-pump groups under various diversion disturbances， and thus determine safety thresholds for water diversion disturbances during the icing period. On this basis， a real-time intelligent regulation model for gate-pump groups in open channels was developed by coupling a hydraulic model with a deep reinforcement learning algorithm， which excels at handling nonlinear， high-dimensional problems and requires minimal modeling data. The robustness of the proposed model was validated under various operational conditions. Application results demonstrate that the derived scheduling strategy effectively raises and stabilizes the water level at control sections to the target ice-period regulation level while ensuring operational safety and reducing the gate adjustment frequency.

Exposed rocks on the lift joint surface of Rock-filled Concrete （RFC） dams can significantly enhance the shear capacity of the lift joints. While relevant codes and standards stipulate specific requirements regarding exposure of rocks at lift joints， there is currently a lack of rapid and effective detection and evaluation methods. This paper proposes a rapid segmentation and recognition algorithm for exposed rocks at lift joints， based on YOLOv11-Seg and incorporating the Slim-Neck attention mechanism and the FASFFHead detection head. Furthermore， by integrating actual engineering data and the latest code specifications， an evaluation method for exposure of rocks on lift joint surface is established based on the aforementioned segmentation algorithm. The research results indicate that the improved YOLOv11-Seg model achieves detection precision and recall rates of 91.4% and 89.33%， respectively， representing increases of 8.6% and 7.8% compared to the initial model， while maintaining high training and recognition efficiency. The measured exposure ratio of rocks at lift joints in actual RFC dam placements exhibits significant variation， and the detection results for individual lift joints conform to a Weibull distribution. In conjunction with the newly revised standard NB/T 10077-2024， Code for Design of Rock-Filled Concrete Dams， the proposed method can effectively evaluate the condition of surface-exposed rock on-site. The horizontal projected area of the exposed rocks shows a hyperbolic relationship with the outropping height of rocks and a linear correlation with the vertical projected area； this relationship can be utilized to further assess the enhancement of the interfacial shear capacity contributed by the exposed rocks. This research provides technical means and a foundation for monitoring and evaluating the quality of lift joints in Rock-filled Concrete dams.