To solve the problem of low recognition accuracy caused by insufficient power data feature mining, this paper proposed a novel power data identification method based on multi-domain feature analysis and feature selection. Firstly, aiming at the shortcomings of existing power data feature extraction methods, a feature extraction method based on empirical mode decomposition (EMD) and Hilbert transform (EMD-Hilbert) was proposed, and the power features and V-I trajectory features of power data were quantified. Secondly, based on random forest and generalized sequence backward selection search strategy, the optimal feature subset was obtained. The random forest was employed to build a recognition model for the power data. Finally, the experimental results verified the effectiveness and identification accuracy of the proposed method. The results show that the proposed method can utilize the complementarity of different features to overcome the problem of low accuracy by single feature, and further improve the model recognition performance through feature selection.

Climate change and urbanization development have brought great challenges to reservoir flood control and disaster mitigation, and reservoir regulation is one of the important non-structural means for controlling floods. Therefore, this study applies the bibliometrics method and visualization analysis tools (CiteSpace and VOSviewer) to conduct a systematic quantitative analysis of the Chinese literature regarding the research topic of reservoir flood control regulation. The results indicate that the number of Chinese literature on reservoir flood control regulation can be divided into three periods in terms of the publication time, and the number of publications in different periods witnesses the development history of reservoir flood control regulation technology in China; The co-occurrence analysis of keywords provided the top 10 keywords in terms of frequency and centrality. The emergence analysis provided the development history of high popularity keywords since 2000. Cluster analysis classified keywords with significant correlation and displayed the relationship between different clusters; The analysis of authors, institutions, and literature sources can provide guidance for relevant researchers in the Chinese journal selection during the manuscript submission and the collaborator choices in Academia.

The water flow disorder, shock, spray splashing out of the side wall and incomplete water jump are often caused by insufficient discharge energy dissipation in the pool. In order to solve this problem, the influence law of the layout of T-shaped pier and its parameter variation on the hydraulic characteristics in the ballast tank was studied by using the model test method and numerical simulation. The results show that the energy dissipation rate increases with the increase of the length of T-shaped pier legs; The water depth increases with the installation of the impingement baffle, and the efficiency increases, and the energy dissipation rate decreases with the increase of the impingement baffle; The flow state of the water in the stilling pool is stable after the double-row T-shaped piers are arranged, and the energy dissipation increases first and then decreases with the increase of the distance between the front and back. According to the simulation results, a reasonable scheme is recommended and verified by model test. The results show that the energy dissipation rate of the recommended scheme reaches 76.06%, which increases by 12.51%. The flow state is stable and meets the engineering requirements.

In order to shorten the start-up time of the hydroelectric generating set and improve the stability of the generating set 's start-up process and non-loading, a start-up optimization strategy of hydropower unit based on improved grey wolf search coupling cuckoo algorithm was proposed. This fitness function weighs the two index values of the unit ' s start-up frequency ITAE index and the unit 's start-up time and standardizes them. Two penalty functions of unit frequency overshoot and unit frequency steady-state error are introduced to effectively improve the start-up performance evaluation index of the hydroelectric generating set. An improved grey wolf search coupled cuckoo algorithm (IGWSCSA) based on good point set theory to improve the initial population is proposed to optimize the start-up parameters of the generating set. Based on the simulation experiment of the refined model of the speed control system, the optimal parameters are obtained to shorten the start-up adjustment time of the generating set, and the overshoot is reduced from 0.235 to 0.004, which greatly optimizes the start-up speed and frequency fluctuation of the hydroelectric generating set.

The medium and long-term runoff simulation can provide a scientific basis for the rational allocation of water resources, which is of great significance to the high-quality development of the basin. Based on the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and singular spectrum analysis (SSA) two-stage decomposition strategy, the monthly runoff simulation model ICEEMDAN-SSA-WOA-LSTM was constructed by using the long short-term memory network model (LSTM) optimized by the whale optimization algorithm (WOA). It was applied to the simulation of monthly runoff in Stone River Reservoir and compared with the single decomposed ICEEMDAN-WOA-LSTM, SSA-WOA-LSTM and the undecomposed WOA-LSTM models. The results show that the ICEEMDAN-SSA-WOA-LSTM model has the best simulation effect, and the three evaluation indexes in the calibration period and validation period are better than other models, with the root mean square error of 1.278 m³/s, the average absolute error of 0.893 m³/s, and the Nash efficiency coefficient of 0.985 in the validation period. The two-stage decomposition strategy model can significantly improve the accuracy of monthly runoff simulation and can be used for year-round incoming runoff simulation.

The influence of inlet blade setting angle valued in a large range was studied on the performance of residual energy recovery turbine. Firstly, the theoretical predicted model was established between the inlet setting angle and optimal unit speed, and the numerical simulation model was determined based on the characteristics of residual energy recovery turbine. Then, three runners with different inlet setting angle were gave for the residual energy recovery turbine in water distribution networks, and numerical simulations were carried out with the same conditions of flow rate, head and rotate speed. The flow field and performance of the runner were compared. The results show that the optimal unit speed of residual energy recovery turbine was negatively correlated with the inlet setting angle. The range of best numerical predicted efficiency is between 92.72% and 93.60% while the inlet setting angle is between 30° and 70°. The inlet setting angle and optimal efficiency was hardly correlated. However, the range with high efficiency was corresponded to a larger unit speed with the decrease of inlet setting angle. It is feasible for residual energy recovery turbine to increase working range by changing inlet setting angle. The conclusions could provide a reference for the design of residual energy recovery turbine.

Bidding is the main way for a hydraulic engineering contractor to obtain a project, and the level of the bid price directly affects whether the contractor can obtain its construction right. Before bidding, predicting the distribution of the bid price of the proposed hydraulic engineering can optimize the formulation of its own quotation. A global optimization Bayesian-MCMC algorithm was used to predict the Beta distribution parameters. Bidding behavior of contractor was simulated by numeric analysis. The algorithm does not need to consider the conjugate of the prior distribution and likelihood function in Bayesian estimation. The numerical simulation results show that the Bayesian-MCMC algorithm requires less data for simulation and has better prediction effect than the traditional moment estimation method.

The movable guide vane of domestic large hydropower units in early stage was mostly made by sand casting, which had the characteristics of large abnormal shape parts and they were located in the water wheel room of the units with narrow space. At present, the nondestructive testing of the area where the movable guide vane is hided in the shaft sleeve of large hydropower unit in service is generally carried out after the movable guide vane is lifted out during the unit overhaul period. This paper attempts to test it though phased array testing technology, modeling simulation and simulated test block test. This method is successfully applied in actual detection. Finally, the problem that coarse crystal, long sound path and abnormal shape of casting movable guide vane have serious attenuation, loss of sound energy, and difficulty in receiving defect echo is solved. The feasibility of nondestructive detection on the hided area of casting movable guide vane in completely assembling state of large hydropower units in service is verified.

In order to address the limitations in forecasting the maximum scour depth of conventional river bends, this study amalgamated the methodologies of isolated forest (IF) and gene expression programming (GEP). An IF-GEP model for predicting the maximum scour depth of river bends was established. The validation results demonstrate that the IFGEP prediction model surpasses existing formulations in terms of its accuracy on the test set. Moreover, it exhibits enhanced predictive performance compared to the traditional GS-SVR and RF models. Application of the prediction model to various rivers yielded remarkably close results to the actual measured values, affirming its strong predictive capability and robust generalization performance.

Under the situation of "abundant and dry electricity supply" in Sichuan Province, affected by complex market environment factors and intensified power supply competition, accurate prediction of power generation plan is the key to optimizing the power generation mode of hydropower in dry periods in the basin. This paper analyzed the power supply capacity of the main grid, new energy power, power regulation capacity of the national power grid, outsourcing power transmission capacity and power generation capacity of the provincial hydropower and thermal power, respectively, and established a forecasting method for the generation plan of the cascade hydropower stations in the Dadu River basin. The results show that the prediction accuracy of power supply in main grid is 91.8%, and the prediction accuracy of wind and solar power generation is 87.4%. The prediction accuracy of the medium and long-term overall power generation plan of the hydropower station belonging to Guoneng Dadu River Basin Hydropower Development Co., Ltd. is 90.5%. The model can effectively predict the electricity quantity of each power source and calculate the medium and long-term power generation plan of the cascade hydropower stations in the Dadu River basin, and intelligently generate the fluctuation process under different working conditions based on the prediction results, which provides technical support for the scientific dispatching and operation of the cascade hydropower stations.