Abstract:Aiming at the problems of sparse data, strong nonlinearity and insufficient mechanism characterization in aquatic ecological environment research, this paper uses literature published between 2014 and 2024 retrieved from the China National Knowledge Infrastructure (CNKI) and the Web of Science Core Collection. On the basis of sorting out the basic principles of classical machine learning, deep learning, ensemble learning and automated machine learning, this paper reviews the application progress of machine learning in the field of aquatic ecological environment from four research scenarios, including water quality prediction and management, water pollutant analysis, eutrophication and cyanobacterial bloom research, and aquatic ecosystem protection. Furthermore, a comparative analysis is carried out based on data characteristics, task objectives and model performance, and problem-oriented suggestions for algorithm selection are proposed. The results indicate that ensemble learning algorithms such as random forest and XGBoost have good applicability for small- and medium-sized samples, the mining of multi-factor nonlinear relationships and the identification of variable importance. Models including LSTM and GRU are more applicable to multi-site and multi-temporal scale sequence prediction. CNN, Transformer and other models show considerable application potential in remote sensing recognition and algal biological image analysis. At present, the application of machine learning still faces several challenges, including inconsistent data quality, insufficient model interpretability, high computational cost, and inadequate collaboration with mechanistic models. In the future, by leveraging data-sharing systems, the application scope of machine learning in the aquatic ecological environment field can be further expanded.

Abstract:To clarify the research and development direction of shipboard domestic wastewater treatment technology under the background of upgraded discharge standards and differences between domestic and international standards, identify technological bottlenecks, and promote the sustainable development of the industry, this paper systematically analyzes China’s discharge standards for shipboard domestic wastewater, the current application status of treatment equipment, and technological research progress. First, by comparing previous and current discharge standards as well as the indicators of domestic and international discharge standards for seagoing and inland waterway vessels, the core characteristics of increasingly stringent standards and their higher requirements for treatment processes are clarified. Second, through literature review and statistical analysis of discharge data, mainstream treatment processes and the current status of equipment installation are reviewed, and their technical applicability and limitations are analyzed. Third, by combining field surveys and case analyses of typical treatment equipment in the Yangtze River Basin, key technological bottlenecks affecting shipboard application are identified, and the main directions for technological breakthroughs are pointed out. The results show that China’s discharge standards are more stringent than foreign standards in terms of both the number and values of indicators, imposing higher requirements on the multi-objective synergistic removal capacity and operational stability of treatment processes, while conventional biochemical/physicochemical treatment processes can hardly guarantee satisfactory treatment performance. For small vessels below 400 gross tonnage, the installation rate of treatment equipment is extremely low due to space constraints and limited technical adaptability. Membrane bioreactors and electrochemical coupling processes have become mainstream technological directions, but they still face challenges such as insufficient shock-loading resistance, shipboard environmental constraints, and insufficient capacity for digital operation and maintenance as well as supervision. Therefore, a systematic approach should be adopted for the treatment of shipboard domestic wastewater to establish a technical pathway featuring spatial adaptability, stable operation, and simultaneous treatment of blackwater and graywater. Efforts should focus on three directions: synergistic treatment of blackwater and graywater, development of shock-resistant processes, and ship-shore digital operation, maintenance, and supervision. In addition, source-separated reuse and zero-discharge technologies should be taken as important breakthrough directions, so as to promote the coordinated energy conservation, pollution reduction, and carbon reduction in shipboard domestic wastewater treatment.

Abstract:To quantitatively characterize the fracture damage evolution mechanism inside concrete under cyclic loading, this paper systematically investigates the evolution laws of crack length, displacement gradient, and residual strain in the fracture process zone (FPZ) of concrete through three-point bending beam tests. A Tikhonov regularization-based cohesive stress inversion method is employed to invert the cohesive stress distribution, and the cohesive stress softening curve is obtained. The results indicate that under constant-amplitude loading, the crack length exhibits a two-stage characteristic of a rapid increase followed by nearly linear slow growth. The FPZ displacement gradient undergoes a two-stage attenuation process consisting of a steep decline followed by a gradual decline, with the attenuation magnitude at low load levels significantly higher than that at high load levels. Under envelope loading, the crack length continues to increase with the number of loading cycles and then tends to stabilize, whereas the FPZ displacement gradient decreases monotonically. The crack propagation rate lags behind the increase in crack mouth opening displacement, resulting in an increase in the width of the fracture process zone and a decrease in its length. Owing to the synergistic development of cohesive stress degradation, material damage, and plastic deformation induced by cyclic loading, the residual strain in the FPZ accumulates continuously over loading cycles at an accelerating rate. Based on the assumption of a linear distribution of FPZ opening displacement, the Tikhonov regularization method was used to invert the cohesive stress distribution. The resulting softening curve approximately follows a power-law form, and the inverted displacement field agrees well with the experimental data, thereby verifying the reliability of the inversion method.

Abstract:The early-age rheological properties of hydraulic engineered cementitious composites (HECC) were investigated through rheological tests, workability tests, setting time tests, and hydration heat tests. The effects of three superplasticizers, a high-performance polycarboxylate superplasticizer (PCA-1), a non-slump-retaining high-performance polycarboxylate superplasticizer (PCA-2), and an early-strength high-performance polycarboxylate superplasticizer (PCA-3), on the rheological characteristics of HECC were evaluated. The results showed that the rheological behavior of fresh HECC followed the Bingham model, with both yield stress and viscosity increasing over time. At the same dosage, the three superplasticizers exhibited similar water-reducing effects but differed in slump retention. At a given testing time, mixtures containing PCA-3 exhibited slightly higher yield stress and viscosity. The initial and final setting times determined by the penetration resistance method were 3-4 h and 5-6 h longer, respectively, than those determined by the Vicat method. Field construction observations confirmed that the penetration resistance method provided more accurate results. The heat release peaks of mixtures containing PCA-2 and PCA-3 occurred 1.93 h and 1.77 h earlier, respectively. Cumulative heat release decreased by 1.366 J/g with PCA-2 and increased by 0.998 J/g with PCA-3. The early-strength superplasticizer regulated the rheological characteristics of HECC by promoting hydration, whereas the non-slump-retaining superplasticizer exerted its effect by affecting interparticle adsorption.

Abstract:To address the problem of data noise interference in dam deformation monitoring and improve the quality of monitoring data, a dam deformation data cleaning method based on unsupervised learning is proposed by integrating the grey wolf optimizer (GWO) algorithm, variational mode decomposition (VMD), wavelet threshold denoising (WTD), and the Savitzky-Golay (S-G) filter. In this method, the decomposition parameters of VMD are adaptively optimized using the GWO algorithm, and the optimized VMD is employed to decompose the deformation sequence into multiple intrinsic mode functions (IMFs). Then, the IMFs are classified according to their sample entropy, and classification-based denoising is applied to the high-frequency IMFs and the medium- and low-frequency IMFs. Finally, the processed IMFs are reconstructed to obtain the cleaned deformation data. Case validation on an arch dam shows that the proposed method effectively eliminates noise across multiple frequency bands while well preserving the statistical characteristics of the deformation data, and exhibits robustness to different noise levels. The denoised sequence, when used as training samples, can improve the accuracy of the point-interval prediction model. In addition, the method has good applicability to monitoring sequences of different lengths.

Abstract:To address the insufficient consideration of spatial variability of rockfill rheological model parameters in stochastic finite element analysis, taking an actual concrete-faced rockfill dam (CFRD) project as an example, a deterministic finite element model considering the rheological effects of rockfill materials was established. The Cholesky covariance decomposition method was employed to generate random fields of rheological model parameters. Through the integrated interaction of ABAQUS, MATLAB, and Python, a non-intrusive stochastic finite element calculation accounting for the spatial variability of material parameters was achieved. The Monte Carlo method was then used to perform statistical analyses of the stress and deformation responses of the CFRD. The results show that, compared with the finite element analysis based on a single set of deterministic material parameters, the stochastic finite element analysis considering rheological properties yields more conservative stress and deformation estimates. The differences in the extreme values of various indicators range from 2% to 6%, and the exceedance probabilities for all indicators are all greater than 50%. The proposed stochastic finite element method incorporating the spatial variability of rockfill rheological model parameters is more consistent with actual engineering conditions and can improve the reliability of deformation predictions for CFRDs.

Abstract:To address the insufficient consideration of hydrological physical processes in current intelligent streamflow simulation, an intelligent streamflow simulation method incorporating the spatiotemporal distribution of watershed runoff generation was proposed. Taking the Yong’anxi River Basin in Zhejiang Province as a case study, a tri-SWAT-Transformer model was developed using the three daily runoff generation components simulated by the SWAT model for each sub-basin as model inputs. The simulation performance of the proposed model was compared with that of the SWAT model and other comparative models. The results show that the tri-SWAT-Transformer model achieves the best streamflow simulation performance, with Nash-Sutcliffe efficiency (NSE) values of 0.95 and 0.89 during the calibration and validation periods, representing improvements of 90.0% and 107.0%, respectively, over the SWAT model. Under high-flow conditions, the proposed model also performs best, with the NSE increased by 200.0%, and the percent bias and root mean square error reduced by 89.6% and 68.8%, respectively, compared with the SWAT model. Furthermore, correlation analysis between runoff generation components and streamflow components explains why the tri-SWAT-Transformer model outperforms the other models. The results indicate that the tri-SWAT-Transformer model can fully capture the spatiotemporal distribution characteristics of various runoff generation hydrological physical processes through the multi-head attention mechanism of Transformer, and makes better use of the spatiotemporal distribution of runoff generation information than other reference models.

Abstract:The spatiotemporal evolution characteristics of water yield and carbon storage in Ordos City from 2010 to 2022 were analyzed using the InVEST model. The geographically and temporally weighted regression (GTWR) model and spatial autocorrelation analysis were used to investigate the spatial clustering characteristics of influencing factors and the spatial heterogeneity between water yield and carbon storage. The results show that the mean Moran’s index of water yield and carbon storage was 0.351, exhibiting high water yield-high carbon storage and low water yield-low carbon storage clustering patterns. The multi-year average water yield was 2.796 5 billion m³ with significant interannual fluctuations, and it was primarily influenced by land use type, evapotranspiration, and carbon storage. Carbon storage showed an increasing trend, rising from 1.156 6 billion tons in 2010 to 1.194 9 billion tons in 2022, and was mainly affected by land use type and water yield.

Abstract:To optimize the adjustment-section length for the side inlet/outlet of a pumped storage power station, this paper takes the side inlet/outlet of the lower reservoir of the Yabuli Pumped Storage Power Station as its research object, and uses the numerical simulation method to discuss the influence of the ratio of the adjustment-section length to the diffusion-section length on the hydraulic characteristics of the side inlet/outlet, while keeping the total length of the inlet/outlet fixed. Under the outflow condition, the results show that as the ratio of adjustment-section to diffusion-section length rises, the mainstream position at the trash rack section of the middle channel gradually shifts from the upper-middle part of the orifice to the bottom of the orifice, while that of the side channel does not change significantly. The velocity non-uniformity coefficients at the trash rack section of both the middle and side channels first decrease and then increase. When the adjustment-section length is 50% of the diffusion-section length, the velocity non-uniformity coefficient at the trash rack section reaches its minimum, and there is no negative velocity at the trash rack section. Under the inflow condition, the hydraulic indices of the inlet/outlet are essentially unaffected by variations in adjustment-section length. Therefore, with the total length of the inlet/outlet fixed, all hydraulic indices of the inlet/outlet are relatively better when the adjustment-section length is 50% of the diffusion-section length.

Abstract:Based on a comprehensive analysis of the structure composition and operational characteristics of irrigation districts, a safety evaluation indicator system for large-scale irrigation district projects was constructed from five aspects: channel engineering risk, risk of other structures, rainstorm and flood risk, earthquake and frost risk, and operation and management risk. The system includes 20 indicators, such as canal slope landslide, main structure instability, energy dissipation failure, structural seismic damage, and historical hazard events. The order relation analysis method and the coefficient of variation method were employed to calculate the subjective and objective weights of the evaluation indicators, respectively, and combined weighting was determined based on game theory, which effectively improved the accuracy and reliability of the indicator weighting. Furthermore, the Pythagorean fuzzy number was introduced into the traditional cloud model, and a Pythagorean fuzzy cloud model suitable for the safety evaluation of complex irrigation districts was established. Finally, the model was used to evaluate the safety of a large-scale irrigation district in Henan Province. The results show that the comprehensive safety index of the irrigation district is 0.857, classifying it as “safe”. The safety evaluation results derived from the Pythagorean fuzzy cloud model exhibit high stability, providing a novel method for safety evaluation of large-scale irrigation districts.

Abstract:To reveal the influence mechanism of frequent small-fluctuation transient processes on the hydraulic stability of hydroelectric units, a 1D-3D coupling method was adopted to conduct a full-passage numerical simulation of the transient process of an 800 MW-class Francis turbine when its load increased from 55.6% to 61.2% of the rated power. This study focused on the guide vane regulation transient process, the vortex evolution laws in the runner and draft tube regions, and the pressure pulsation characteristics. The results show that as the guide vane opening increases, the discharge grows steadily, the axial force undergoes a sudden change due to the water hammer effect, and the radial force, affected by the guide vane regulation disturbance, exhibits typical low-amplitude pulsation characteristics, though its amplitude is significantly larger than that under steady operating conditions. As the load increases, the scale of the inter-blade vortex gradually decreases. When the load reaches 61.2% of the rated power, the inter-blade vortex basically dissipates, and the draft tube vortex rope evolves from a single vortex rope structure into a stable double vortex rope structure at the center of the draft tube. During the load-increasing process, the unit is affected by the coupling of water hammer, vortex structure evolution, and rotor-stator interaction frequency, generating high-amplitude frequency components such as 0.11 f n, 0.21 f n, 0.85 f n, and 15 f n.

Abstract:To reveal the mechanism by which oblique inflow at bends affects the hydraulic characteristics of a single-orifice sluice, a three-dimensional hydrodynamic numerical model is constructed using the Erhe Hub Sluice on the Huaihe River Seaward Waterway as a case study. The flow field structure and water level variation patterns upstream of the sluice are simulated and analyzed under inflow angles of 30°, 45°, 60°, and 75°. A formula for calculating the comprehensive discharge coefficient of the sluice under oblique inflow conditions is established, considering factors such as inflow angle, Froude number, and width-to-depth ratio. The results indicate that the longitudinal velocity distribution pattern of lower velocities on the concave bank and higher velocities on the convex bank intensifies with increasing inflow angle. When the inflow angle ranges from 30° to 75°, the ratio of the velocity difference between the concave and convex banks to the mean cross-sectional velocity at the bend outlet increases from 16.5% to a maximum of 84.3%. The variation of cross-sectional circulation intensity with inflow angle differs under different discharge conditions. The water level at the bend outlet cross-section exhibits a lateral distribution with higher levels on the concave bank and lower levels on the convex bank. When the inflow angle ranges from 30° to 75°, the ratio of the water level difference between the concave and convex banks to the mean cross-sectional water level increases from 1.3% to a maximum of 30.7%, and the inhibitory effect of flow inertia on circulation decreases with increasing inflow angle. Under identical discharge conditions, the comprehensive discharge coefficient of the sluice decreases with increasing inflow angle. The average relative error between the actual values and the values calculated from the established formula for the comprehensive discharge coefficient of the sluice is 2.01%, demonstrating generally high accuracy.

Abstract:Based on a case of cavitation erosion damage on the sidewalls at the outlet of a radial gate during the operation of a sediment flushing tunnel in a domestic hydraulic project, hydraulic model tests were conducted to study the flow characteristics and wall pressure characteristics in the outlet region of the radial gate under different opening conditions, and the causes of cavitation erosion damage were thoroughly analyzed. The results show that when the radial gate is fully open, the aeration facility operates well and cavitation erosion damage is unlikely to occur. When the radial gate is partially open, the lateral diffusion angle of the outlet flow increases, the length of the side cavity shortens rapidly, and the pressure downstream of the flow impingement zone drops rapidly, resulting in a relatively small cavitation number in this region and the presence of a clear-water zone on the sidewall, which intensifies the risk of cavitation erosion damage. The extent of the clear-water zone is basically consistent with that of the damage zone.

Abstract:To address the limitations of traditional manual inspection in construction quality control of deep foundation pits, including poor timeliness, limited visualization, and excessive reliance on inspectors’ experience, a construction quality inspection method integrating augmented reality (AR), building information modeling (BIM), and knowledge base technologies is proposed. Image-assisted localization and point cloud registration techniques are employed to achieve high-precision registration between the BIM model and the construction site in an AR environment, thereby enabling accurate alignment of the virtual model with the real-world scene. A semantically enriched BIM model for deep excavations is established and used as the information carrier to construct a BIM-integrated knowledge base for quality inspection. An intelligent virtual-real augmented construction quality inspection system is developed, providing inspection assistance through virtual-real scene integration, multi-source knowledge retrieval, and visual feedback. Validation through an engineering case study demonstrates that the proposed method is effective and practical, providing a reliable technical approach for intelligent and refined quality management of deep excavation construction.

Abstract:Facing the severe challenges of synergistic resource optimization and regional high-quality development, a multi-objective optimization model for the water-energy-food nexus system at the county scale was developed for the Hengyang-Shaoyang Arid Corridor. The model was constructed based on the NSGA-Ⅲ algorithm by considering social, economic, and ecological benefits under current and future scenarios. The optimal allocation schemes under different hydrological years were identified using the entropy weight-TOPSIS method, and key drivers affecting regional benefits were explored using the Geodetector. The results showed that a 1% increase in water supply could increase the comprehensive benefits by 3.875% to 7.650% in the current scenario. By optimizing crop structures and reallocating water resources, competition among sectors was alleviated, achieving synergistic improvements in social, economic, and ecological benefits. Under the future normal-flow scenario, crop structure optimization and water redistribution increased annual grain production to 9.2885 million tons, exceeding the per capita standard by 24%, while reducing COD emissions by 9.8%. Under the dry-year scenario, the food security threshold can be maintained by reducing the planting area of high-water-consumption crops, with annual grain production exceeding the standard by 12.9%. Regarding driving effects, influencing factors were more dispersed in normal-flow years but became significantly concentrated in dry years. The explanatory power of multi-factor synergistic effects on social, economic,and ecological benefit variations was substantially enhanced, indicating that the synergistic effect between water supply security and resource allocation equity was the key mechanism driving the evolution of target benefits in the Hengyang-Shaoyang Arid Corridor.