To solve the problem of decreasing prediction accuracy caused by nonlinear runoff sequence and instability of single prediction model, this paper proposes a "selection-combination-correction" modeling strategy based on the "decomposition-prediction" model. Firstly, five models including DNN, SVM, LSTM, TCN, and GBRT are used to establish 15 coupled models based on EMD, CEEMDAN, and VMD, and the models are selected. Then, the selected model is used as the base model, and the predicted results of each period of the base model are processed and input into a multi-layer perceptron to construct a new combination model. A residual correction equation is constructed for the test period of the combination model to further improve the prediction accuracy. Finally, the method is applied to the test studies of Huaxian Station in Weihe River Basin and Yangxian Station in Hanjiang River Basin. The results show that the combination model constructed by the multi-layer perceptron has higher prediction accuracy than the single model, and can integrate the advantages of other models to improve the model's generalization ability. The model with residual correction technology is superior to the combination model in all aspects, especially in the fitting of peak discharge, further improving the prediction accuracy.

In order to solve the real-time online flow monitoring under complex conditions of wide and shallow river sections, based on the applicability of conventional online flow measuring equipment, the combined application of two-way probe H-ADCP facing each other was proposed. Taking the Gaogang Water Conservancy Project at the source of water intake of the East Route of the South-to-North Water Transfer Project as an example, the whole process of numerical simulation of river sections, flow field analysis, equipment installation, comparison measurement setting and other aspects were carried out applied research. The results show that the change of flow field in the flow measuring reach is complicated under different operation conditions of the control hub gate pump. The dual probe H-ADCP can be installed at the same section and the same height, and the ultrasonic beam crossing will not affect the collection of effective unit velocity data. The relationship between the double index velocity and the average velocity of the section can be established to calculate the real-time flow, and the accuracy of the combined applied flow measurement is higher than that of the single H-ADCP flow measurement data. The research results form a set of real-time flow monitoring application methods under complex conditions of wide and shallow rivers, which can provide ideas for the combined use of online flow measuring equipment.

In order to evaluate the applicability of the latest generation GPM IMERG satellite precipitation products in Jiangsu Province, the measured precipitation data of 73 ground stations were selected as references. Using statistical indicators and extreme precipitation index, the accuracy evaluation of GPM IMERG precipitation products were conducted from the perspectives of day, month, season, and their extreme precipitation monitoring capabilities were evaluated. The results show that the GPM satellite precipitation products have good observation effects in Jiangsu region. At the daily and monthly scales, their overall and regional data have a high correlation with ground station measured data (C_CC≥ 0.77), and the correlation becomes more significant with the increase of time scale. At the same time, the GPM satellites overestimate the measured precipitation, and the R_RMSE at the monthly scale is relatively higher. There are certain differences in the observation accuracy of GPM satellites in different seasons, and the winter observation effect is the best, with high correlation and the lowest observation error (C_CC=0.92, R_RMSE=26.37 mm, R_RB=23.4%). The GPM satellite has good ability to monitor extreme precipitation and can observe and describe the occurrence and intensity of extreme precipitation in Jiangsu region, especially in the southern Jiangsu region, with better observation effect.

Based on the hourly precipitation data (1980-2019) from 142 national stations in Hebei Province, Mann-Kendall (MK) trend and mutation test, K-means clustering, and hydrometeorologically homogeneous region methods were used to systematically analyze the temporal evolution characteristics and spatial distribution patterns of short-term extreme precipitation in Hebei Province. The results show that significant regional differences exist in interannual variation of short-term extreme precipitation, with an upward trend in high-altitude mountains and a downward trend in low-altitude plains/hills, marked by a 1996 change-point. Topography significantly influences patterns: the spatial extent decreases in plains and southern slopes but expands on northern slopes for 1 h and 3 h durations, indicating a shift towards mountainous areas. Seasonal differences are pronounced: winter/spring increases, while summer and autumn decreases significantly, with third-quarter Rx24h declining at 0.337 mm/a. The research results reveal the spatio-temporal differentiation law of short-term extreme precipitation in Hebei Province, providing a scientific basis for regional flood control and disaster reduction as well as adaptive management to climate change.

The Leizhou Peninsula exhibits one of the highest incidences of drought within the Pearl River Basin. Research on the characteristics and response mechanisms of meteorological and hydrological droughts in this area holds significant theoretical and practical importance for understanding drought patterns in regions with abundant rainfall yet fragile water resource systems. Based on the monthly meteorological and hydrological data from the representative station in Leizhou Peninsula, the standardized precipitation-evapotranspiration index (I_SPEI) and standard runoff index (I_SRI) were used to analyze the variation patterns of meteorological drought and hydrological drought in this region from 1970 to 2016. The Mann-Kendall trend test method, moving average method and Morlet wavelet analysis method were adopted to analyze the changing trends and cycles of meteorological drought and hydrological drought in this region at different time scales (3 and 12 months). Propagation characteristics of meteorological drought to hydrological drought were examined using the run-length theory. The results show that the meteorological drought in Leizhou Peninsula is increasing during the study period. Particularly, the 12-month I_SPEI obtained from Zhanjiang station and Xuwen station decreased significantly, at the rate of -0.014/month and -0.008/month, respectively. However, no obvious trend of hydrological drought was detected. Both drought types showed multi-scale periodicity, sharing a primary first-order period of 20 years in the north and 14 years in the south. The main cycles of meteorological drought and hydrological drought in the south and north are consistent, and the variation patterns are relatively synchronous. Hydrological drought in the southern peninsula demonstrated stronger responsiveness to meteorological drought than the northern region.

Under the background of frequent extreme climate events, analyzing the spatio-temporal changes of surface water bodies in the Songhua River Basin affected by climate change over the past 30 years is of great significance for the region to take and optimize climate response measures in advance. Based on the spatio-temporal dynamic changes of surface water area in the Songhua River Basin from 1990 to 2020, seasonal water bodies were classified and analyzed. By using the EC JRC global surface water product dataset and combining with MATLAB software, the time series feature +K-means clustering and dynamic statistical threshold method were adopted to analyze the changing trend of surface water area in the Songhua River Basin in the past 30 years, and to classify the seasonal water body area as well as detect and analyze the recovery dynamics of extreme hydrological years. The results show that during the study period, the seasonal water body area in the Songhua River Basin increased by 114%, while the permanent water body area decreased by 49.46%, and the total surface water area showed an upward trend. The annual seasonal water body area was classified into three categories: fluctuating-wet year, low fluctuation - dry year, and stable - normal year, with a silhouette coefficient of 0.549, indicating a good clustering effect. Two significant high-value years, 1998 and 2013, were identified, and it was analyzed that neither had fully recovered. The research results provide a direction for the effective management and protection of water resources by referring to historical extreme hydrological events and making flood and drought prevention preparations in advance for the Songhua River Basin in the face of future extreme weather.

In view of the sudden water pollution events in the main stream of Minjiang River, taking the lower reaches of the main stream of the Minjiang River as the study area, a coupling model of hydrodynamic and water quality was established to accurately simulate the flow dynamics and water quality changes under different scheduling scenarios. By comparing four different scheduling strategies: background simulation (i.e. no special scheduling measures), single optimization of Qianwei Avionics Water Conservancy Project, single optimization of Longxikou Avionics Water Conservancy Project, and joint optimization of two projects, this study comprehensively evaluated the emergency treatment ability of each strategy for water pollution in the main stream of the Minjiang River. The results show that from the point of view of pollutant concentration peak and pollutant exceeding standard time, the joint scheduling strategy of increasing the sluice flow of two hub projects simultaneously shows the best pollution group disposal effect. This strategy not only significantly reduces the peak concentration of pollutants, but also effectively shortens the period of time when pollutants exceed the standard, thus minimizing the negative impact of water pollution on the environment and ecology. The research results can provide reference for the emergency treatment of the Minjiang River main stream water pollution incident and improve the emergency treatment efficiency.

Irrigation drainage is an inevitable accompanying process in agricultural irrigation, widely present in the irrigated farmlands of the northwest region of China. Due to poor water quality, if it is returned to the river channels, it will pose a threat to the water ecological environment of the basin. Taking the Huanghe South Bank Irrigation District in Hangjin Banner as the research object, a MIKE SHE distributed hydrological model was established to predict the drainage volume and available volume of the irrigation district. Cross-checking was conducted with the simulation results of hydrological models by using the water equilibrium method and the ratio of diversion to drainage method. The results show that under the current drainage system conditions, the multi-year average drainage volume is 48.21 million m³, and the available volume is 43.39 million m³; After the drainage system is upgraded and transformed, the multi-year average drainage volume is 49.20 million m³, and the available volume is 44.28 million m³. The drainage volume prediction results of each method vary slightly, but the overall difference is not significant. The simulation results by MIKE SHE's hydrological model and the average deviation is controlled within ±4%, while the relative error of the simulated drainage during the verification period is 3.7%. The MIKE SHE hydrological model performs well in simulating the drainage process of the irrigation district, which can provide reference for the resource utilization of irrigation district drainage.

To explore the storage effect of functional zoning on different layout methods of LID facilities in industrial parks and identify the optimal LID facility combination scheme, a specific industrial park in Guangdong Province was selected as the subject of study. The software SWMM was employed to investigate the storage effect of individual LID facility layouts and the comprehensive storage benefits of various LID facility combination schemes. The results show that affected by the park's functional zoning, when the downstream greening positions in the study area are concentrated and the rainfall is relatively low, LID facilities installed in the middle of the concentration area demonstrate superior effectiveness compared to those installed downstream. As the rainfall increases, the downstream's storage advantages become fully apparent. When designing LID facility combinations, the scheme combining 5% green roofs and 15% sunken green spaces yields the best storage effect per unit layout area. However, due to the mutual influence among facilities, the effectiveness of this combination scheme is not as good as the arithmetic sum of the data for the individual facilities, failing to produce the desired synergistic effect of "1+1>2".

To clarify the first flush characteristics of particulate and dissolved pollutants in urban roof and road runoff and to scientifically determine the first flush volume (V_FF), this study investigated the typical cement roof and asphalt road runoff in Beijing using the M (V) curve method. The approach involved calculating average pollutant concentrations in specified runoff increments during rainfall events to assess water quality variations, quantify V_FF, and evaluate corresponding runoff pollution control effectiveness. The results show that the pollution levels of particulate and dissolved chemical oxygen demand (COD) and phosphorus in runoff from asphalt road are significantly higher than those from cement roof (p<0.05), but no such significant difference is observed for particulate and dissolved nitrogen. Particulate pollutants in cement roof runoff exhibit a stronger first flush phenomenon, whereas the first flush phenomenon of dissolved pollutants is more pronounced in asphalt road runoff. Except for the pollution indicators with weaker first flush phenomenon, there are significant differences between V_FF of COD, total nitrogen (TN), and total phosphorus (TP) and their particulate or dissolved indicators. According to the current national standard, the first 3 mm of runoff shall be discarded, cement roof and asphalt road can achieve SS pollution control rates of (65.26±32.40)% and (65.43±23.81)%, respectively, and COD pollution control rates of (58.17±32.49)% and (59.06±31.48)%, respectively. Higher runoff pollution control results will be obtained if V_FF is determined based on actual monitoring data. The findings will provide reference for implementing targeted control strategies and methods for particulate and dissolved pollutants in urban stormwater runoff.

To estimate the spatiotemporal characteristics of CO₂ partial pressure (p_CO2) and water-air interface CO₂ flux (F_CO2) along the Yangtze River, this study selected eight monitoring sections along the main channel of the river from upstream to downstream. Based on water quality data from 2020 to 2022, p_CO2 and F_CO2 were calculated using the CO₂ SYS software. The spatiotemporal variations of p_CO2 and F_CO2 were analyzed, and the relationships between p_CO2, F_CO2, and environmental factors were assessed using the Mantel test. The results show that from 2020 to 2022, p_CO2 in the Yangtze River ranged from 450.02 to 3 615.88 μatm, which was higher than the global atmospheric CO₂ average partial pressure of 414.78 μatm during the same period. Spatially, the distribution of p_CO2 was as follows: midstream > upstream > estuary. The average values of water-air F_CO2 during 2020-2022 were 40.25 mol/(m²·a), 74.74 mol/(m²·a), and 61.85 mol/(m²·a), respectively, with a spatial distribution of upstream > midstream > estuary. The Yangtze River is in a state of CO₂ oversaturation, and that the water-air F_CO2 flux showed an overall increasing trend from 2020 to 2022. p_CO2 exhibited a significant positive correlation with water temperature, dissolved oxygen, and pH, while F_CO2 was positively correlated with pH, dissolved oxygen, and conductivity.

Water park is an important window of ecological civilization construction. Taking 20 national water parks as examples, using the public comment data, the CES dictionary of water park was constructed to analyze the public perception frequency and satisfaction of the CES during and after the COVID-19 pandemic. And then IPA model was used to evaluate water park. The results show that the public focus on water park are consumption, transportation, scenic spot environment and water conservancy engineering, and there are differences in different stages; The frequency of aesthetic value and recreation is the highest, and the frequency of inspiration service is the lowest. The frequency of popular science education is lower during the COVID-19 pandemic; The overall satisfaction is 80.51% during the COVID-19 pandemic and 82.15% after the COVID-19 pandemic ends; The future construction of water park in Henan Province should pay attention to social relations and science education service, while fully exploiting the potential of cultural history and spiritual service. The research is of great significance to the evaluation and planning and construction of water park.

The construction of fish-friendly water passage has become an inevitable demand for habitat connectivity and protection. To further optimize the hydraulic characteristics of fish-friendly channels, based on a flume experiment, large-eddy simulation (LES) is used to construct a three-dimensional hydrodynamic model. The channel flow is simulated under the influence of regular triangular baffles and permeable triangular baffles. The results indicate that the permeable triangular baffle design effectively reduces the strength of the main recirculation zone and limits its development. The turbulent kinetic energy and Reynolds stress behind the baffle are reduced due to water inflow through the permeable apertures, leading to a 34.5% reduction in maximum turbulent kinetic energy along the vertical axis. Furthermore, at two different water depths, the permeable baffle design increases the proportion of resting zones and local low-velocity zones, while significantly reducing the proportion of negative flow velocity zones that are harmful to fish.

In order to meet the flood discharge and irrigation requirements of tributary channels, it is of great practical significance to master the water flow diversion characteristics of the three-branch river channel. Based on numerical simulation and physical model experiments, the water level changes, velocity distribution, and flow allocation characteristics at the mouth of three tributaries river under different branching angles were studied. The results show that for a three-branch river channel, the larger the branching angle, the smaller the flow velocity in the tributary is, and the flow allocation in the variable angle side gradually decreases, while the flow allocation in the fixed angle side and the main branch gradually increases. Based on dimensional analysis, a three-branch river flow diversion ratio calculation formula was obtained considering the Froude number at each branch inlet. The formula was verified, and it was found that the prediction accuracy of the formula for the flow diversion ratio of the tributary channels in a three-branch river system was good.

Underwater topography serves as essential foundational data for river management and reservoir scheduling. The riverbed longitudinal profile is a significant topographical characteristic and is one of the key elements determining the flow velocity and water level variation along the river or reservoir. Based on the energy equation of flow, this paper employs the width-to-depth ratio /H and the relative depth of the section centroid H_c/H as indicators to quantitatively assess the cross-sectional morphology. The correlation relationship between the cross-sectional area, hydraulic radius, and the maximum water depth for a certain power station is established. An analytical method for inverting the longitudinal profile of deep pools of underwater topography before and after reservoir siltation under the control of water surface lines was proposed. Case study results indicate that the proposed method can quickly and accurately invert underwater topography after the siltation of rivers and reservoirs, providing a new approach for rapid determination of topography before and after reservoir construction.

The permeability of karst medium is affected by multiple factors such as the geological characteristics of soluble rocks, the degree of karst development, and the fluid properties. The permeability coefficient estimation model of fractured rock mass is difficult to reflect the complexity of karst development, which makes it poorly applicable. Random Forest (RF), Support Vector Regression (SVR), CatBoost machine learning algorithm combined with Bayesian optimization algorithm were used to construct the permeability coefficient estimation model of karst media. The root mean square error (R_RMSE), mean square error (M_MSE) and coefficient of determination (R²) were used to verify the evaluation accuracy of the estimation model. The SHAP algorithm was used to analyze the dominant influencing factors of the permeability coefficient of karst media in machine learning model, and the influence of each influencing factor on the permeability coefficient of karst medium was clarified. The results show that the R_RMSE of the optimized SVR model is 0.128 8, M_MSE is 0.016 6 and R² is 0.74, which are better than the random forest and CatBoost models, and can better estimate the permeability coefficient of karst media. The SHAP diagram revealed that there were obvious differences in the permeability coefficient of karst media between different eigenvalues of each dominant factor, and the karst rate (BK), depth (Z) and filling content (AFC) of the borehole line were the main influencing factors of the permeability coefficient of karst media, and had a significant impact on the permeability coefficient of karst media. The SVR model has high estimation accuracy and strong interpretability, which provides a certain reference value for engineering applications in karst areas.

The stability of dam construction by tailings accumulation is closely related to the ultimate bearing capacity of geotextile used in dam construction. The fine tailings of Dayu Shilei Tungsten Mine in Ganzhou are used as the filling material. Through the uniaxial compressive strength test of the filling geotextile filled with fine tailings under different consolidation time and different filling degree, the variation law of the ultimate compressive strength of the geotextile and the failure mode of the geotextile and the strength reinforcement mechanism of the bag body are analyzed. The results show that when the geotextile reaches the ultimate compressive strength, the vertical strain is between 20% and 30%; The ultimate compressive strength of geotextile decreases with the increase of tailings filling degree (filling height), and increases with the increase of consolidation time. Under uniaxial compression, the failure position of the geotextile mainly occurs at the bottom of the intermediate geotextile, and the lower the filling degree, the greater the failure range is; The theoretical calculation value of the modified formula of ultimate compressive strength considering the influence of filling degree is compared with the experimental value of ultimate compressive strength, and the error between them is less than 4%. The conclusion can provide reference for similar fine-grained tailings geotextile dam construction.

To ensure the timeliness of frost resistance testing of hydraulic concrete and improve the safety of construction and operation of project, the methods for testing the frost resistance of concrete were systematically reviewed. The standard differences among slow freezing method, fast freezing method, single-sided freeze-thaw method and salt-resistant erosion method were compared. Two new trends were analyzed including the rapid detection technology of frost resistance based on the rapid freezing method and the rapid detection technology of concrete relying on process parameter control. The new ideas for rapid testing methods of frost resistance were proposed based on structures parameters of hardened concrete, accelerated destructive experiment, key process parameters of freezing and thawing. The concept of dedicated curves was established, and the specific procedures of the new methods was clarified. The work of all the above could provide new ideas for the frost resistance testing of hydraulic concrete.

To investigate the damage evolution and failure mechanism of fiber-reinforced concrete under action of earthquake, a series of monotonic and reciprocating axial compression tests were conducted on steel fiber reinforced concrete to analyze the influence of fiber addition on the stress-strain behavior of concrete. The focus was on exploring the relationship between the mechanical behavior degradation and internal damage accumulation of concrete under cyclic axial compression, including plastic strain, stiffness degradation, and energy dissipation. The results indicate that the monotonic loading curve is close to the envelope of the reciprocating axial compression curve. The addition of steel fibers significantly improves the post peak ductility of concrete and increases residual stress. Due to the crack resistance and toughening effect of steel fibers, the failure mode of concrete after adding fibers has evolved from brittle failure of a single vertical main crack to ductile failure mode of multi crack cracking. Steel fibers can effectively improve the seismic mechanical behavior of concrete. After adding fibers, the degradation of elastic stiffness and plastic strain development of concrete are effectively controlled, and the energy dissipation performance is enhanced.

To accurately calculate the effective range of vibration rods in reinforced concrete, this study proposes a new prediction model for the effective radius of vibration rods based on the rheological theory of fresh concrete. Under the assumptions that the vibrated concrete exhibits pseudoplastic fluid characteristics and the flow in the steel mesh is equivalent to seepage through porous media, an expression for the effective radius of the vibration rod in reinforced concrete is derived. The empirical parameters in the expression are then empirically fitted in conjunction with experimental results. By comparing the model calculations with experimental values, it shows that, except for a few cases with low vibration intensity of the rod, the overall prediction accuracy of the effective radius prediction model is higher. Considering that the vibration intensity of the rods used in concrete pouring at construction sites is generally high, the model can effectively guide on-site compaction operations and quantitatively evaluate the impact of steel bar layout schemes on the vibration range of the rod.

It is the key issues of reasonably and accurately predicting the thrust and torque of tunnel boring machines (TBM) to realize the intelligent control of TBMs. This paper proposes a two-stage prediction method of knowledge-data-driven spatio-temporal stacked convolutional network (KD-NTS-GAT). Firstly, based on expert knowledge and the NTS-NOTEARS method, a new information fusion technique is proposed. The discrete expert experience and the continuous NTS-NOTEARS indicators is mapped and smoothly fused through clustering. The causal relationships among the key operating parameters of the TBM is quantitatively extracted to improve the authenticity of the causal relationships significantly. Then, causality is further combined as a prior knowledge with stacked convolutional network deep learning model for predicting thrust and torque of TBM. Taking the bid Ⅳ of Xinjiang Water Conveyance Tunnel Project as an example, a comparative analysis of the KD-NTS-GAT method and the pure data-driven method shows that the KD-NTS-GAT has better prediction capability on thrust and torque. The conclusions can provide a reference for the intelligent control of TBM construction.

Predicting risks in later diversion stages is essential for the scientific evaluation of initial impoundment schemes for hydropower stations. Considering the gradual development process from dam overtopping to the failure of the diversion system, taking the later diversion systems of the upstream existing and downstream under-construction power stations as the research objects, a later diversion risk model for cascade power stations based on level sets is established, and the risk is expressed in the form of interval numbers. Based on the prospect theory, the initial impoundment scheme of the cascade power stations is evaluated by taking risk loss, relative storage reservoir power generation benefits and storage duration as the indicators. Finally, taking two adjacent under-construction power stations in the upper reaches of the Jinsha River as an example, the results show that when the level sets change from 0 to 1, the equivalent recurrence interval corresponding to the later diversion risk interval of the original impoundment scheme meets the flood design standard with a high safety margin. The staged storage time can be advanced by 40 days, which provides a reference for the safety and economy of advanced impoundment.

Addressing the issues of single model algorithm, low accuracy, and poor generalization in existing shield tunneling speed prediction methods, this study proposes a shield tunneling speed prediction approach to improve prediction accuracy based on Variational Mode Decomposition (VMD), Dung Beetle Optimizer (DBO), and Stacking ensemble learning. Firstly, to obtain more effective data, VMD is applied to decompose and reconstruct the original data to obtain denoised construction parameter data for subsequent model prediction. Secondly, based on the ensemble learning strategy, Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) models are selected as base learners, while Gaussian Process Regression (GPR) is chosen as the meta-learner to construct a Stacking ensemble learning prediction model with higher prediction accuracy and stronger generalization ability. Thirdly, to further enhance prediction accuracy, DBO is employed to optimize the hyperparameters of the ensemble learning model. Finally, this prediction method is applied to the shield tunneling construction of a water diversion tunnel project in Henan Province and compared with other prediction methods. Compared to other single models (SVR, RF, XGBoost), the results indicate that the proposed method achieves higher prediction accuracy, with average accuracy improvements of 7.76%, 6.70%, and 4.97%, respectively, providing a new approach for shield tunneling speed prediction.

Cemented gravel dam construction technique combines the advantages of earth-rock dams and concrete dams, and has broad application prospects. Taking Shaping first-level Hydropower Station as an example, production tests were carried out on C₁₈₀6, C₁₈₀10 and C₁₈₀20 cemented sand and gravel, and core drilling tests were carried out on their compressive strength, splitting tensile strength, permeability and SEM scanning tests at the age of 180 days. The results show that under scientific ratio and reasonable construction technology, the compressive strengths of C₁₈₀6, C₁₈₀10 and C₁₈₀20 have reached 7.1 MPa, 14.8 MPa and 29.4 MPa, respectively. Among them, the impermeability grade of C₁₈₀10 with the largest amount of project consumption is W8. The performance of cemented sand and gravel can achieve the expected results, which verifies the feasibility of the construction plan. Thus, it provides technical support for subsequent construction, and also provides reference examples for subsequent hydropower station construction.

Affected by hydrodynamic excitation and other factors, the opening-closing operation of hydraulic gates exhibits multi-field coupling effects and complex nonlinear dynamic characteristics, leading to difficulties in identifying equipment safety states. Test data of gate operation demonstrate that artificial neural network algorithms can identify hydrodynamic excitation disease features and accurately predict its development trends. To address this, BP and GA-BP neural networks were employed to construct identification and prediction models for hydrodynamic excitation disease. These models were applied to identify and forecast the effective values of reel vibration, with model performance evaluated using metrics including Relative Error (R_RE), Mean Absolute Percentage Error (M_MAPE), and Root Mean Square Error (R_RMSE). Compared to the BP model, the results indicate that the GA-BP model achieves reductions of 20.77% in R_RE, 4.74% in M_MAPE, and 6.27% in R_RMSE, demonstrating superior fitting to measured samples and enhanced stability with extended prediction durations, thus providing critical technical support for engineering risk mitigation and hazard prevention.

Perforated structures are commonly found in engineering applications, where stress concentration around holes significantly affects structural load-bearing capacity and safety. Therefore, accurate mechanical analysis of perforated structures is essential. However, the traditional finite element analysis methods face several challenges, including complex mesh generation, high computational resource requirements, and poor convergence when dealing with perforated structures. To overcome these challenges, a finite element analysis method based on the superposition principle is proposed. This approach replaces the original model with a simplified equivalent model featuring a less complex mesh for simulation. The stress field of sub-models is subsequently employed to correct the stress distribution around holes in the equivalent model. Comparative results indicate that the discrepancy between the equivalent model and the original model is within 5%. The equivalent model achieves a 25.2% reduction in mesh elements and a 75.1% reduction in simulation time, substantially improving simulation efficiency.

To address the issue of reduced detection accuracy under complex working conditions due to the fixed threshold of the isolation forest algorithm, an anomaly detection method for ship lock miter gate monitoring data based on singular spectrum analysis (SSA) and an improved isolation forest (KMIF) is proposed. The SSA is employed to decompose and reconstruct the monitoring data, and separate the trend and noise components. The isolation forest algorithm is improved by incorporating K-Means++ clustering to dynamically set anomaly thresholds for different monitoring datasets. The noise component is then fed into the improved isolation forest algorithm for training and anomaly detection. Taking the stress and vibration data from multiple measuring points of the lower lock miter gate in Jiangsu ship gate project as an example for validation, the results show that the proposed SSA-KMIF method performs excellently in terms of false positive rate, precision, recall ratio, and accuracy. It demonstrates high accuracy and flexibility, which provides a reliable technical support for health monitoring of ship lock miter gates.

Aqueducts are common water conveyance structures in water diversion projects, and accurate prediction of aqueduct deformation is crucial for ensuring the stable operation of water conservancy projects. For this purpose, taking the Liaohe Aqueduct in the South-to-North Water Diversion Project as an example, five different linear additive models, namely elastic net regression, multiple linear regression, stepwise regression, ridge regression and LASSO regression, were established based on the long-term deformation monitoring data of the aqueduct. The prediction results of the aqueduct's deformation behavior by the five different linear additive models were compared. The results indicate that as the prediction time increases, the prediction accuracy of different linear additive models gradually decreases. The LASSO model selects the optimal regularization parameter through cross-validation, achieving variable selection simplification and minimizing model complexity. Additionally, it is verified that the training length affects the prediction performance of multiple linear regression and stepwise regression. The findings of this study provide valuable references for selecting prediction model of aqueduct deformation.

The number of long-distance, high drop, pressurized, and self-flowing water pipeline projects is increasing in the northwest region. Most of the pipelines show undulating shapes, and the hydraulic transition process of the entire pipeline system becomes very complex during operation and regulation. When the water hammer protection setting is unreasonable, it will lead to pipe explosion, seriously threatening the safety of people and property. In order to ensure the safe operation of the entire system, the characteristic line method and the HAMMER V8i water hammer analysis software were used to analyze the hydraulic transition process of a long and high drop inverted siphon in a water transmission project. By setting isolation and maintenance valves, submerged energy dissipation valves, and exhaust valves along the pipeline, and setting regulating valves at the end of the pipeline, the positive pressure of the pipeline system is effectively controlled during normal operation and valve closure. By simulating the hydraulic transition process of the pipeline system under different flow rates after pipe explosion, the installation of water hammer protection equipment minimizes the harm caused by pipe explosion. The flow rate of the pipeline system after complete pipe explosion is not continuous. The action time and operation rules of the water hammer protection equipment for long-distance and high drop inverted siphon lines play a crucial role in the safety of the entire system. The research results can provide reference for the similar projects.

According to the prototype characteristic curve of the pump set, there will be a deviation between the theoretical value and the actual value when guiding the actual scheduling of the pumping station, which will affect the accuracy of daily scheduling and energy consumption evaluation. Therefore, taking Liyuzhou pumping station as an example, this paper proposes a method combining the measured data of the pumping station and the law of similarity to correct the prototype characteristic curve of the pump set. The flow optimization distribution model is established in terms of the actual operating conditions, and the difference of optimal flow distribution scheme of pumping station between the characteristic curve of the pump set before and after the correction is analyzed. The results show that the deviation between the actual operating head and the theoretical head is mainly concentrated in 8%-11%, and the deviation between the actual operating efficiency and the theoretical efficiency is mainly concentrated in 6%-9% when the prototype characteristic curve of the pump set is used. When the flow optimization distribution scheme is selected through the corrected characteristic curve of the pump set, the results are more in line with the actual operation situation, which can effectively strengthen the guiding role of the flow optimization distribution scheme of the pumping station on the actual scheduling.

The long-term prediction of concrete dam deformation is an important requirement for maintaining its structural integrity during actual operation. To improve the accuracy of long-term deformation prediction of concrete, a long-term dam deformation prediction model based on multi-layer perceptron (MLP) and ecoder-decoder (Ecoder-Decoder) architecture, MLP-Ecoder-Decoder (MED), was constructed. This model captured the long-term dependence of dam deformation and environmental loads through a deep auto-correlation (Deep-Auto-Correlation) mechanism, and used time series decomposition and deep auto-correlation mechanism for multi-step deformation prediction. The model was used to predict the deformation of a 250 m height arch dam in Qinghai Province under complex environmental conditions. The results show that the MED model effectively improves the prediction accuracy and has a strong advantage in extracting long-term time features.

There are problems of non-convergence and easy false alarm when formulating dam deformation monitoring indicators (which belong to fixed limits) based on the conventional low-probability method. A calculation method for formulating deformation monitoring indicators based on the low-probability method of separating aging components is proposed. Firstly, the statistical model of dam deformation is established to separate the time-dependent component. Then, aiming at the time series deformation of deducting the aging component, the annual extreme value is selected as the subsample. The corresponding deformation of the annual most unfavorable reservoir water level and temperature is selected as the subsample. The corresponding deformation of the unfavorable water level and temperature based on the combination of orthogonal test method is selected as the subsample. Then the statistical test is carried out, and the small probability method is used to formulate the deformation allowable value of deducting the aging component. Finally, the aging component is superimposed to obtain the non-convergence deformation monitoring index of the dam. Combined with the measured data of a deformation non-convergence gravity dam in southwest China, the analysis shows that compared with the monitoring index proposed by the conventional small probability method, the method based on the separation time component fully considers the time effect and enhances the reliability of the monitoring index.

Constructing a high-precision dam settlement prediction model is of great significance for ensuring the safety and risk control of dam during the construction period. Taking dam height, rainfall and aging as the influencing factors of dam settlement deformation during construction period, the long-term and short-term memory neural network LSTM algorithm is introduced, and the attention mechanism is embedded. Thus, a prediction model suitable for dam settlement of concrete face rockfill dam during construction period is proposed. The engineering application shows that the attention-LSTM model makes up for the defect that the LSTM cannot dynamically adjust the weight coefficient at the network layer, improves the computational efficiency and accuracy of the model, and has better nonlinear data processing ability, which can more accurately reflect the change trend of monitoring data in the time dimension during the construction period. The relevant experience can be used as a reference for similar projects.

Aiming at the complex karst environment of the lower reservoir of a pumped storage power station, a three-dimensional finite element model for seepage analysis was established to simulate the main buildings and karst passageways in the reservoir area. "The depth of seepage control curtain at the base of the dam is 0.5 times of the pre-dam head, the depth of seepage control curtain on both sides of the dam is 3 m below the 3 Lu line, the length of seepage control curtain on the right side of the dam is 200 m, and a single-row curtain is set up" is used as the preliminary seepage control scheme. The seepage field, infiltration slope and infiltration volume of the reservoir area were calculated. The preliminary seepage control scheme met the specification requirements. But the seepage rate and infiltration slope were close to the critical value. The four indexes of curtain depth on both sides of the bank, curtain depth at the base of the dam, length of curtain on the right bank, and double-row curtain were changed to optimize seepage control scheme. The impact of the changes of the indexes on the infiltration volume of the reservoir area was investigated so that the optimization of the seepage control scheme was put forward. The analysis results show that on the basis of the preliminary scheme, the double-row curtain is set up at the dam base, the infiltration flow at the dam base is reduced by 267.3 m³/d, and the effect of seepage control in the reservoir area is remarkable.

The pumped storage power station has the characteristics of frequent unit start-up and shutdown and working condition switching, which has great influence on the safe operation of the power station. At present, the on-site monitoring data of the vibration response of the underground powerhouse structure of pumped storage power station under the vibration load of the unit are few, especially the vibration monitoring of the unit under the transient conditions such as unit start-up and shutdown and load rejection. This paper takes the underground powerhouse of a pumped storage power station as the research object, and carries out the dynamic characteristics monitoring analysis under the transient conditions of power generation, pumping switch and different output load rejection. The results show that the peak vibration response of each typical part of the powerhouse structure under transient condition is obviously greater than that under steady condition, and the vibration response under power generation on and off condition is greater than that under pump pumping condition, but the vibration displacement and acceleration can basically meet the recommended limits of the current vibration standard. Under 100% load rejection conditions, the vibration response of the powerhouse structure is the strongest, and the maximum vibration acceleration can reach more than 30 m/s², which is easy to cause impact damage to the powerhouse structure. It is recommended to avoid 100% load rejection conditions during daily operation and maintenance of the power station. In case of occurrence, it is necessary to timely detect the key structural parts of the powerhouse to eliminate safety risks.

In order to explore the influence of pressure pulsation of the pumping unit on the powerhouse structure, the powerhouse of Dayuzhang pumping station was taken for an example. Based on the prototype observation data, the vibration source composition and vibration characteristics of powerhouse structure were analyzed using three-dimensional finite element simulation. The safety of the structure was analyzed and evaluated from the perspective of structural resonance check and vibration response. The results show that the hydraulic pulsation caused by RSI and the rotational frequency excitation caused by the operation of the unit have the greatest impact on the vibration of powerhouse under the stable operation condition of the unit, and the natural frequency of the local floor structure has a small degree of coincidence, which is easy to resonate. However, from the perspective of vibration response, the vibration response of each local part is within the allowable range, the outlet elbow and pump seat are the largest, and the pump floor slab is the smallest. This study has important theoretical value and practical significance for realizing the long-term and safe operation of the pumping station powerhouse structure.

The maximum water head endured by the floor of the high-pressure branch pipe at the Zhongdong Pumped Storage Power Station in Huizhou, Guangdong, is approximately 800 m during operation. The stability of the surrounding rock under this high internal water pressure is critical to the station's safe operation. To address this, in-situ stress and high-pressure water injection tests were conducted. Combined with three-dimensional in-situ stress field inversion, the stress field distribution, permeability characteristics, and hydraulic fracturing resistance of the high-pressure branch pipe area were analyzed, and the layout of bifurcated pipe was optimized. The results indicate that the maximum principal stress in the high-pressure branch pipe section ranges from 15.0 to 16.6 MPa, and the minimum principal stress ranges from 8.4 to 9.7 MPa. The rock permeability ranges from 0.01 to 0.19 Lu, indicating very low to low permeability. The initial high-pressure branch pipe location meets the stability requirements against uplift and seepage. However, within a 7 m range of the branch pipe opening, the class Ⅲ rock mass segment is affected by faults and does not meet the engineering requirements for hydraulic fracturing resistance. Based on a comprehensive analysis of the surrounding rock conditions, uplift resistance, hydraulic fracturing resistance, and seepage resistance, the initial high-pressure branch pipe location was shifted 10 m toward the powerhouse, which meets the stability requirements for uplift, hydraulic fracturing resistance, and seepage resistance.

The pumped storage power stations are critical infrastructure for achieving carbon neutrality goals. Based on the three-dimensional computational fluid dynamics method, the head loss characteristics in the combined diversion shaft-surge chamber arrangement are investigated. Firstly, the three-dimensional model from the upstream inlet to the inlet of the unit is established. Then, the hydraulic characteristics under different arrangement types are analyzed. Finally, the influence of the diameter of the turning section and the impedance holes on the head loss is explored under the combination arrangement. The results indicate that the pressure distributions are similar in combined and uncombined arrangements. The hydrodynamic characteristics are not deteriorated and reflective water hammer is more effective in combined arrangements. Under the combined arrangement, the larger the diameter of the turning section and the impedance hole, the smaller the head loss coefficient is. This study can provide theoretical references for the design of new structures for pumped storage power stations.

In order to solve the problem that the response ability of a large mixed-flow hydropower unit is affected by the change of operating water head, a method based on the adaptive feedforward function is proposed for the application of the turbine's primary frequency regulation function. The 3D curve function library of turbine's water head, guide vane opening and power is introduced into the primary frequency regulation feedforward control of the turbine. According to the real-time water head and power and the position of guide vane, the power change corresponding to the frequency change is calculated through the 3D database to directly affect the output of the controller. Compared with the conventional control mode of primary frequency regulation, it is verified by field practice. The experimental results show that the feedforward function can not only satisfy the consistency of the next frequency regulation performance of different water heads, but also effectively avoid setting and switching multi-group PID control parameters. Thus, it provides a new way to realize the function of primary frequency regulation of hydraulic turbine units.

To improve the efficiency and accuracy of fault diagnosis for hydroelectric units, combination of multifractal detrended fluctuation analysis algorithm and probabilistic neural network was used to establish a vibration signal feature extraction and recognition model. The binary gravity search algorithm was used to optimize its parameters. The results show that the classification accuracy of the feature extraction and recognition classification model can be improved to 99% and reduce the signal processing time to about 1.3 seconds after optimizing by the binary gravity search algorithm. The proposed vibration signal feature extraction and recognition model for hydroelectric units can significantly distinguish between the normal working state and the fault working state of hydroelectric units, achieving the purpose of using vibration signal features to diagnose faults in hydroelectric units.

Hydroelectric units generally use Babbitt Alloy with strong friction reduction properties as the bearing bush material. However, due to the bearing bush made by Babbitt Alloy material has lower strength, it can not be used in the need to withstand the larger pressure of large-scale hydropower generating sets. The Steel Kogu (SK) can withstand large loads while having good wear resistance. Therefore, the oil film temperature, bearing bush body temperature and power of SK bearing pad and Babbitt Metal bearing bush are studied comparatively through experiments. The thickness, pressure, maximum temperature of oil film, base deformation and power loss of the two types of bearing bush are studied comparatively by numerical calculation. The results show that at the same oil inlet temperature, the base deformation and maximum oil film temperature of SK bearing bush are lower than that of Babbitt Alloy by 0.06-0.08 mm and 9.6-14.6 ℃, respectively, and the oil film thickness of SK bearing bush is higher than that of Babbitt Alloy by 13-15 μm. The SK bearing bush can be used as a potential choice of bearing bush material for large-scale hydroelectric units because of its lower oil film temperature and smaller base deformation during the operating process.

Unsteady friction plays a very complex role in the water hammer phenomenon within pipeline systems. For hydropower station with super-long headrace tunnel (SLHT), it is crucial to consider the effects of unsteady friction adequately. This paper conducts a study on the nonlinear transient response characteristics of hydropower station with SLHT based on unsteady friction. Firstly, a system model of hydropower station with SLHT is established using the method of characteristics, incorporating unsteady friction based on instantaneous acceleration. Then, simulations of this model are performed under load and frequency disturbances. Finally, the stability of the model under frequency disturbances is evaluated using the Bode plot method, and the impact of unsteady friction parameters on system stability is investigated in conjunction with the energy equation. The results show that the unsteady friction in the pipeline primarily affects the rapid response phase of the water turbine in the hydropower station with SLHT. When the impact coefficients of local acceleration (k_t) and convective acceleration (k_l) increase, the system stability deteriorates. Moreover, changes in k_t and k_l make the system more sensitive to high-frequency disturbances.

In order to further improve the control performance of water turbine, a control strategy based on the adaptive chaotic particle swarm optimization variable domain fuzzy PID (CAS-PSO-VFPID) was proposed for the turbine regulation system. Firstly, a model of nonlinear hydraulic turbine regulation system was established, and a variable domain fuzzy controller was constructed according to the system model. Then, the adaptive chaotic particle swarm optimization (CAS-PSO) was used to optimize and design the variable domain fuzzy controller, and the CAS-PSO-VFPID controller was obtained. Finally, the applicability of the nonlinear turbine regulation system model was verified by simulation. The multiple control strategies under different working conditions were compared and simulated with Whale Algorithm Optimization Variation Domain Fuzzy PID (WOA-VFPID), Standard Particle Swarm Optimization PID (PSO-PID), Standard Particle Swarm Optimization Optimization Variable Domain Fuzzy PID (PSO-VFPID). The simulation results show that the system convergence speed and optimization ability of the CAS-PSO-VFPID control strategy are fast, which can effectively improve the response speed and accuracy of the hydraulic turbine regulation system, and make the system have better dynamic stability.

With the increasing proportion of new energy, the inertia support, voltage support, and frequency regulation ability are obviously weakened in current power system. The development of energy storage system with synchronous condenser and flywheel (ESSSCF) is of great significance to improve the regulation capability of new energy power generation and enhance the stability of new power systems. This article briefly describes the principle and different operation states of the magnetic-geared speed regulator (MGSR) for ESSSCF, and focuses on the design optimization of its electromagnetic structure. The electromagnetic finite element model of the MGSR is established. The shape of the flux barrier is selected for the inner rotor with V-shaped permanent magnet by calculating and analyzing the no-load leakage flux factor. The geometric parameters of the V-shaped permanent magnets and stator slots and the pole-arc coefficient of the modulating ring are optimized for multiple objectives, respectively, using genetic algorithm, under the conditions of a constant amount of permanent magnet and a constant area of stator slot. In addition, the correlation of the target performances with the geometric parameters is analyzed. The results of the design optimization and correlation analysis can direct the structural design of the magnetic-geared speed regulator for improvement of the torque and efficiency performances.

The tailwater level of hydropower station is a critical parameter for calculating the unit's output. When influenced by the downstream reservoir's backwater effect, discrepancies often arise between the designed tailwater curve and the actual observed values, leading to increased errors in the output-flow calculations. Utilizing the latest historical observation data, this study explores the relationship between the tailwater level of BHT Hydropower Station, its discharge, and the water level of the downstream XLD Reservoir. A Bayesian optimized long short-term memory (BO-LSTM) prediction model is developed based on multi-scenario analysis. The applied effect is analyzed under conditions of peak load and flood discharge. The results indicate that when the water level of XLD exceeds 585 meters, the tailwater level of BHT Hydropower Station is significantly influenced. Compared to the nonlinear curve fitting method, the BO-LSTM model based multi-scenario analysis demonstrates a substantial improvement in accuracy, with an average absolute error (M_MAE) reduced by 68.1%. The BO-LSTM model more accurately captures the fluctuations and changes in water levels under various operating conditions. The research results have important significant for refined operation of hydropower stations.

Aiming at the optimal dispatching problem of cascade hydropower stations in the lower reaches of the Jinshajiang River during the drawdown period, based on the analysis of the reservoir water balance, water level, discharge flow rate, and unit output, a daily-scale refined scheduling model was established by maximizing the total power generation of cascaded reservoirs and considering the actual scheduling requirements. The model was solved using the DPSA-POA algorithm. The effectiveness of the model and solution method was verified by the actual case. The results show that the proposed scheduling model can make full use of water resources and maximize the power generation in the drawdown period under the premise of ensuring the safe operation of each reservoir. Thus, it provides theoretical basis and technical support for the refined scheduling management of the cascaded reservoirs.

The Longyangxia and Liujiaxia Reservoirs in the upper reaches of the Yellow River have annual regulation capacity and undertake comprehensive utilization tasks such as flood control, water supply and irrigation, and power generation in the Yellow River Basin. The coordination and consistency of multiple objectives need to be achieved by constructing a multi-objective optimized dispatching system for cascade reservoirs. A multi-objective scheduling model has been established for the Longyangxia-Liujiashan cascaded reservoirs, with the goals of maximizing the peak shaving rate, total power generation, and average sediment flushing ratio. The model is solved using the NSGA-Ⅲ algorithm, and an analysis is conducted regarding the competitive relationships among the objectives of flood control, power generation, and sediment flushing. The established multi-objective optimization scheduling scheme is further evaluated through a developed indicator system, and the TOPSIS method is applied to optimize the set of scheduling solutions. The results show that there is a significant competitive relationship between the objectives of power generation and flood control; No significant competition exists between the objectives of sediment discharge and flood control, and there is some competition between the objectives of sediment discharge and power generation. Through a comparison of the optimal scheme and the actual scheduling data, it can be seen that the benefits of flood control, power generation, and sediment discharge in the optimal scheme increased by 20.89%, 16.02%, and 3.61%, respectively, compared to the actual scheduling.

With the construction and operation of integrated clean energy bases, there is an urgent need for multi-energy joint dispatch. On the basis of cascade hydropower joint scheduling, this article embeds the risk of channel electricity curtailment as a penalty constraint, integrates the working experience of scheduling personnels with rolling ideas, and explores a method for formulating multi-time scale cascade hydro-photovoltaic complementary joint scheduling rules based on actual operation. The potential risks of power abandonment is identified in advance and control measures are proposed. By selecting the benefits of hydroelectric power generation and energy storage, as well as photovoltaic power generation, a complementary function of hydro-photovoltaic joint system is established to evaluate the scheduling rules. The proposed method has been applied to the hydro-photovoltaic complementary system of Xiaowan and Manwan on the Lancang River. The results show that the economic benefits of the hydro-photovoltaic joint system is significantly increased without significantly affecting the hydropower regulations. The idea has the feasibility of promoting the joint operation of the integrated hydro -photovoltaic energy storage and clean energy watershed base in future.