It is of great significance for the long-term planning and allocation of Nanjing water resources to analyze the current situation of Nanjing water consumption, make reasonable prediction of Nanjing water consumption and master the future water demand. The analysis of water consumption in Nanjing from 2009 to 2019 showed that industrial and agricultural water consumption accounted for a large proportion of total water consumption in Nanjing, which played a crucial role in the change of total water consumption. The combined model of grey GM(1,1) model and Elman neural network was used to forecast the water consumption of all districts and the total water consumption of Nanjing. The results show that the grey Elman neural network model has a good prediction effect on the total water consumption of Nanjing City from 2009 to 2019. The relative errors of the forecasts were all less than 3.5%, and the average relative errors of the predicted results over the years were 1.55%; The relative error of the forecast results is less than 8.5% in the forecast of the water consumption of all districts in Nanjing in 2019. The model used in this paper can accurately predict the water consumption of Nanjing, which is of great significance to effectively control the regional water consumption and realize the principle of "four water and four determinations".

In order to improve the prediction accuracy of vibration signals of hydropower units, a prediction method based on variational mode decomposition (VMD), sample entropy (SE) reconstruction and particle swarm optimization (PSO) optimization of bi-directional gated circulation unit (BIGRU) was proposed. In the VMD-SE-PSO-BIGRU model, firstly, the vibration signal was decomposed into several subsequences by VMD, and the subsequences were reconstructed by SE. The trend, oscillation and noise components of the vibration signal were obtained. Then, parameter optimized BIGRU prediction models were established for the reconstructed components. Finally, the prediction results of each component were superimposed to achieve vibration prediction. Compared with other models, example analysis shows that the prediction error of the model is smaller and the prediction accuracy is higher, which can effectively predict the vibration signals of hydropower units.

In order to study the dynamic response of pipe-piercing dike under seismic load, taking a dike-crossing project in Guangdong Province as the research object, considering the interaction between pipeline and soil, a three-dimensional numerical simulation model of pipeline-dike was established. The simulation of foundation boundary spring-damper was realized through secondary development. The results show that under the action of 0.1g seismic acceleration, the vertical displacement of the dike increases with the increase of the height of the dike and decreases along the axis of the dike. The maximum displacement at the top of the pipeline is greater than that at the left and right ends. The stress distribution law of the pipeline is consistent with displacement, and the maximum stress of the pipeline is proportional to the thickness of the soil cover layer. The Mises stress at each point of the midpoint section of the pipeline through the dike is the largest, and the seismic capacity of the middle section of the dike is relatively weak. The stress and displacement near the midpoint section of the pipeline in the dike should be monitored in the seismic design of the subsequent dike project. This study has important practical significance to ensure the safe and stable operation of the dike-crossing project.

A new type of MBC impellerr with a guide vane slot structure was proposed to improve the energy capture and wave reduction efficiency of Savonius-type (S-type) impeller. A multi-objective optimization algorithm combined BP neural network, NSGA-Ⅱ, numerical simulation and experimental test was used to optimize five parameters of the MBC impeller including overlap ratio, gap ratio, internal and external arc angle, internal arc radius, and guide vane size. The performance of the optimal MBC impeller was compared with that of the S-type and MB-type impellers. The results show that the prediction error of the relevant performance values is less than 10% compared to the actual values, verifying the good performance of the established prediction model. The obtained optimal parameters are: overlap ratio of 0.136, gap ratio of 0.003, internal and external arc angle of 5.23°, internal arc radius of 41.42 mm, and guide vane size of 2.83 mm. Compared with the traditional S-type impeller, the optimal MBC impeller has increased energy capture efficiency by 35.8% and wave reduction efficiency by 11%.

In response to the problems of low accuracy and poor reliability of water consumption prediction due to the strong randomness and non-stationary state exhibited by the water consumption signal, this paper proposed a hybrid water consumption prediction model based on improved EEMD-WOA-SRU. Firstly, the LSTM prediction method was used to suppress the endpoint effect of the EEMD to obtain the improved intrinsic mode functions (IMF). Then the whale optimization algorithm (WOA) was used to optimize the simple recurrent unit (SRU) and predicted each component. Finally, the final prediction results were obtained by accumulation. The experimental results show that the decomposition error of the EEMD is reduced by 0.94% on average; Compared with the SRU, the average absolute error of EEMD-WOASRU model prediction is reduced by 45.42%, the root mean square error is reduced by 50.43%, and the reliability is improved by 52.38%. It can provide a basis for water resources decision making.

In view of the fact that the reservoirs of medium and small hydropower stations usually operate at a lower level during the flood season because of the smaller regulating reservoir capacity, short decision time for flood regulation, maximum head of the unit and inundation limitation of the upstream reservoir area, etc., the flood resource utilization benefit is not fully utilized during the flood season regardless of the magnitude of the flood. The multi-objective risk analysis model for flood operation and scheduling of medium and small hydropower reservoirs is established with the objective of maximizing the power generation benefit and minimizing the flood risk, and the solution method for the optimal flood level is given when the forecasted incoming flood flow is in different ranges. The results show that when the reservoir faces different levels of floods, the optimal operation level can be obtained by coordinating the benefits and risks to increase the power generation benefits during small floods and reduce the flood losses during large floods, which provides a reference for the flood operation and scheduling of medium and small hydropower reservoirs under changing environment.

Timely and accurate forecasting residential water consumption is critical to design and operational management of water supply systems. Long short-term memory (LSTM) is an effective data-driven prediction model for water consumption, but it usually relies on a large number of parameter settings. This paper proposed a multilayer long short-term memory neural network model (MLSTM), which was built on the LSTM model by superimposing a time distribution module. The results indicate that the MLSTM model has lower complexity and higher prediction accuracy than the LSTM model, especially for the prediction of peak water consumption with M_MAPE reduced by about 60%. Meanwhile, the MLSTM model is insignificantly affected by external environmental conditions (e.g., weather).

With the completion of a large number of major water conservancy projects with the characteristics of "high water head, large flow, and complex geological conditions", the environmental problems caused by flood discharge atomization have become increasingly prominent, and it is urgent to carry out research on mitigation technology of flood discharge atomization. The types of flip bucket have a direct impact on flood discharge atomization. Based on the methods of physical model test and numerical simulation calculation, the influence of flip bucket types on flood discharge atomization is studied. The results show that: under the same test conditions, the distribution of the nappe wind velocity of the continuous bucket is symmetrical along the two sides of the downstream axis, showing a unimodal distribution; and the distribution of the nappe wind velocity of the contraction bucket and the expansion bucket is approximately symmetrical bimodal distribution. The distribution of flood discharge rainfall is closely related to the type of the flip bucket. Compared with the continuous bucket, the number of the splashed water droplets of contraction bucket and expansion bucket is greatly increased. In the actual project, the purpose of reducing the influence of flood discharge atomization can be achieved by reasonably optimizing the types of flip bucket.

The phenomenon of mixed free-surface-pressure flow exists in the process of water level variation in the lower reservoir (roadway group) of mine-type pumped storage power station, which directly affects the operation stability of the system and the hydraulic safety of the roadway group. Based on 3D numerical simulation technology of hydraulic system, considering the three controlling cases including lower reservoir water filling, load rejection and pumping power failure, the characteristics of the transition process of water flow in roadway group and the evolution law of related hydraulic parameters were analyzed, and its influence on the hydraulic safety of roadway group was evaluated. The research shows that there is no obvious unfavorable flow pattern in the initial water filling process of the lower reservoir (roadway group); For load rejection with dead water level of the lower reservoir, the water level of the regulating pool decreases by less than 0.4 m, and for pumping power failure with the normal water level of the lower reservoir, the water level of the regulating pool increases by less than 10.0 m; The roadway group can enter and exhaust normally during the transition process, and the hydraulic transitions in the roadway section is smooth including the possible free-surface-pressure flow; The regulating pool and the ventilation channel meet the requirements of hydraulic optimization to ensure the hydraulic safety of the roadway group.

During construction and operation, it is inevitable to have such engineering problems as cutoff wall defects. It is very important to accurately and systematically analyze the influence of defects in anti-seepage wall on seepage and deformation of cofferdam. The finite element model of an anti-seepage wall cofferdam project was established. By using the fluid-solid coupling analysis method, the material parameters of anti-seepage wall element in the finite element model were changed one by one to simulate different defects of anti-seepage wall. The influence of defect location of anti-seepage wall on saturation line, velocity vector field and deformation field of cofferdam was studied. The results show that the bottom defects of the anti-seepage wall have little influence on the saturation line, velocity vector field and deformation field of the cofferdam. With the upward movement of the anti-seepage wall defects, saturation line, pore water pressure and deformation value of the cofferdam behind the anti-seepage wall increase continuously, and the velocity of the cofferdam increases firstly and then tends to be stable. The research results can provide reference for the design and construction of anti-seepage wall and stability analysis of cofferdam.