Hydropower multi-source information fusion and real-time optimal scheduling system and method

Abstract

The application discloses a water and electricity multi-source information fusion and real-time optimization scheduling system and method, belongs to the field of water and electricity intelligent scheduling, and acquires water grass information, water body conditions and water turbine set conditions in a water body, dynamically evaluates the movement speed and trajectory of each water grass at each time in the future based on stress analysis on the water grass, evaluates the water grass arrival time distribution and space concentration evolution based on water grass movement state and aggregation analysis, evaluates the water grass cutting probability based on discrete water grass units and flow field data, and dynamically evaluates the water grass winding cumulative mass, evaluates the unit operation risk based on the water grass cutting probability, winding mass and water turbine set vibration parameters, controls the unit in a safe manner, fuses multi-source information, realizes water grass movement prediction, winding evaluation and unit risk analysis, and improves the safety and stability of the water turbine set operation.

Description

Technical Field

[0001] This application belongs to the field of intelligent hydropower dispatching, specifically a hydropower multi-source information fusion and real-time optimization dispatching system and method. Background Technology

[0002] Hydropower, as a crucial component of clean energy, occupies a vital position in the global energy structure. As the core equipment of a hydropower station, the operational safety and stability of the turbine directly impact power generation efficiency and equipment lifespan. However, natural rivers, lakes, and reservoirs often contain abundant aquatic plants, floating debris, and other aquatic vegetation. Especially during high-temperature seasons, eutrophication, or flood seasons, aquatic plants experience explosive growth, significantly impacting the safe operation of hydropower units. In actual operation, aquatic plants enter the intake channel under the influence of water flow. Even after passing through the trash rack, some still enter the water intake system and eventually reach the turbine area. Under the influence of complex flow fields, these plants bend, tumble, aggregate, and entangle, easily adhering to guide vanes, runner blades, or the runner chamber walls, forming a "grass-hanging" phenomenon. Over time, the continuous accumulation of aquatic plants not only alters the local flow field structure but also increases flow resistance and exacerbates energy loss, ultimately leading to a decrease in turbine efficiency.

[0003] Existing research largely focuses on single-dimensional analysis, such as hydrodynamic analysis based on flow velocity monitoring or floating object detection based on image recognition. However, it lacks multi-source information fusion mechanisms, making it difficult to comprehensively reflect the actual state of aquatic plants. Furthermore, regarding the motion behavior of aquatic plants, due to their flexible structure, their motion in the flow field exhibits strong nonlinear characteristics, making it difficult for traditional rigid body or simplified models to accurately describe their force and motion patterns. In addition, aquatic plants may entangle to form clusters, whose mechanical properties differ significantly from those of individual plants, further increasing the difficulty of modeling and prediction. Regarding the interaction between aquatic plants and turbines, existing technologies typically ignore the fluid-structure interaction between aquatic plants and blades, lacking quantitative analysis of aquatic plant cutting, breakage, and entanglement processes, resulting in an inability to accurately assess the evolutionary behavior of aquatic plants within the turbine unit. Simultaneously, existing methods fail to effectively couple the influence of aquatic plants with operating parameters such as turbine vibration and load, lacking a unified risk assessment index system, making it difficult to achieve real-time monitoring and early warning of the turbine unit's operating status.

[0004] This application integrates multi-source sensing information, the movement and aggregation behavior of aquatic plants in complex flow fields, and combines the operating status of the turbine to achieve risk assessment and dynamic control, thereby improving the safety and stability of turbine unit operation. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this application proposes a hydropower multi-source information fusion and real-time optimization scheduling system and method.

[0006] To achieve the above objectives, this application provides the following technical solution: Firstly, this application provides a method for multi-source information fusion and real-time optimized scheduling of hydropower, including the following specific steps: To obtain information on aquatic plants in the water body, water conditions, and turbine unit status; Based on the force analysis of aquatic plants, the speed and trajectory of each aquatic plant at different future moments are dynamically evaluated. Based on the analysis of aquatic plant movement and aggregation, the temporal distribution of aquatic plant arrival and the spatial concentration evolution are evaluated; The probability of aquatic plant cutting is evaluated based on discrete aquatic plant units and flow field data, and the cumulative mass of aquatic plant entanglement is dynamically evaluated. Based on the probability of aquatic plant cutting, the quality of entanglement, and the vibration parameters of the turbine unit, the operational risks of the unit are assessed, and safety control of the unit is implemented.

[0007] Preferably, the acquisition of information on aquatic plants, water conditions, and turbine unit conditions in the water body includes the following specific steps: S11. Using high-frequency image sonar and laser scanner, non-contact scanning of floating objects in water flow is performed to obtain aquatic plant image information, extract the geometric and physical properties of aquatic plants, including aquatic plant species, density, distribution location, length and flow posture, and obtain the aquatic plant mass concentration per unit volume by identifying the intensity of sonar echoes and calibrating them experimentally. S12. The basic distribution of the flow field is obtained by using an acoustic Doppler velocity profiler and a water level gauge deployed at the inlet of the turbine unit. The velocity vector at any point (x, y, z) in the rectangular coordinate system at time t is: Where u, v, and w are the components of the flow velocity in the transverse, longitudinal, and vertical directions, respectively, and i, j, and k are unit vectors, obtained directly through layered scanning along the cross-section using ADCP. The degree of tumbling of aquatic plants in the flow field is assessed by calculating the turbulence intensity. The formula for calculating the turbulence intensity is: ,in, , and This represents the fluctuating values ​​of the flow velocity in each direction, i.e., the difference between the real-time value and the average value. The average flow velocity is given. The greater the turbulence intensity, the more intense the water flow disturbance, and the higher the probability of irregular entanglement of aquatic plants. S13. Obtain internal parameters of the turbine unit, including rotational speed, blade angle, and vibration signal, through the existing monitoring and data acquisition system of the turbine unit. Resample using a linear interpolation method based on a unified timestamp to align the aquatic plant data, water body data, and turbine unit data on the same time axis.

[0008] Preferably, the dynamic evaluation of the movement speed and trajectory of each aquatic plant at future moments based on force analysis includes the following specific steps: S21. Establish a full-domain three-dimensional CFD model including the inlet channel, trash rack, water diversion pipe, and turbine chamber inlet. Discretize each collected aquatic plant individual into a Lagrange particle. Each aquatic plant includes spatial coordinates, velocity vector, geometric features, mechanical features, state markers, and cluster state. The spatial coordinates represent the three-dimensional position of the aquatic plant's center of mass at the current moment, the velocity vector represents the aquatic plant's velocity at the current moment, the geometric features include length, equivalent diameter, and curvature index, the mechanical features include tensile strength, toughness modulus, and density, the state markers include floating state, and the cluster state is whether it is intertwined with other aquatic plants to form a clump. S22. In the flow field, aquatic plants are subjected to gravity, buoyancy, drag, and additional forces from fluid acceleration. The motion state of the aquatic plants is evaluated by the forces acting on them in the water. The equation of motion for the aquatic plants is as follows: ,in, For fluid resistance, Due to the buoyancy of the aquatic plants, Due to the weight of the aquatic plants, This is the pressure gradient force, caused by uneven water flow velocity. For the quality of aquatic plants, Let be the velocity vector of the aquatic plants. By integrating the equation of motion of the aquatic plants over time, we can obtain the velocity of each aquatic plant at various future moments. The formula for calculating fluid resistance is as follows: ,in, For water density, The drag coefficient, Let V be the projected area of ​​the aquatic plant in the direction of water flow, and V be the local water flow velocity. For long, narrow aquatic plants, the projected area is related to the water inflow angle. The projected area of ​​the aquatic plant in the direction of water flow is calculated using the plant's attitude angle. The formula for calculating the projected area of ​​the aquatic plant in the direction of water flow is: Where L is the length of the aquatic plant, d is the equivalent diameter of the aquatic plant, and θ is the angle between the water flow direction and the long axis of the aquatic plant. The formula for calculating the drag coefficient is: Where Re is the Reynolds number based on the equivalent diameter of the aquatic plants, and f is the flexibility correction factor. The greater the flexibility, the smaller the drag coefficient. The formulas for calculating gravity and buoyancy are: ,in, For aquatic plant density, For water density, Let g be the volume of the aquatic plants and g be the acceleration due to gravity. When the density of the aquatic plants is less than the density of the water, the aquatic plants have positive buoyancy and tend to float to the surface; otherwise, they sink. The formula for calculating the pressure gradient force is: ,in, The substantial derivative of the fluid particle represents the acceleration of the water flow. It is obtained by spatially differentiating the spatial velocity field V(x,y,z) obtained in the first step. For example, in the contraction section, the velocity increases with position, which generates an induced force pointing towards the high flow acceleration. When aquatic plants enter areas where the water flow accelerates rapidly, such as the turbine inlet, the force is generated due to the uneven water pressure. Preferably, the assessment of the temporal distribution and spatial concentration evolution of aquatic plants based on their movement and aggregation analysis includes the following specific steps: S31. For each turbine unit, define a target area, which is a fan-shaped or rectangular area in front of the unit's inlet. Record the moment when each aquatic plant first enters the target area. Statistically analyze all aquatic plants to obtain the aquatic plant arrival time distribution, the first wave arrival time, and the peak arrival time. The arrival time distribution is represented by a histogram or probability density function, indicating the number of aquatic plants or the total biomass arriving in different time intervals. The first wave arrival time is the moment when the first aquatic plant arrives, used to trigger an early warning. The peak arrival time is the time window with the highest aquatic plant arrival rate. Further subdivide the target area into several sub-areas and statistically analyze the number of aquatic plants arriving in each sub-area to form a spatiotemporal distribution map of aquatic plant concentration. S32. Assess the concentration of aquatic plants by measuring their movement speed, and evaluate the blockage at the turbine inlet. The target area is... The formula for calculating the concentration of aquatic plants at a given time is: ,in, For the local flow field gradient, For the speed of aquatic plant movement, The flux function depends on the velocity of the aquatic plants and the local flow field gradient, where the flow field gradient is the rate of change of the velocity in space. Based on the discrete flow field data V(x,y,z) obtained in the first step, the derivative is calculated within the computational grid using the finite difference method or the least squares gradient reconstruction method. The flux function describes the mass of aquatic plants passing through a unit area per unit time. The formula for calculating the flux function is: Where C represents the local concentration of aquatic plants. Let be the turbulent diffusion tensor, whose magnitude is proportional to the modulus of the local flow field gradient and the turbulent kinetic energy. For the concentration gradient.

[0009] Preferably, the dynamic evaluation of the probability of aquatic plant cutting based on discrete aquatic plant units and flow field data, and the dynamic evaluation of the cumulative mass of aquatic plant entanglement, includes the following specific steps: S41. Discretize a continuous aquatic plant into a series of units connected by flexible joints. A single aquatic plant of length L and diameter d is discretized into N equal-length cylindrical segments, each considered a rigid body. The segments are connected by ball joints, allowing relative rotation. A torsion spring and damper are placed at each connection point to simulate the bending stiffness of the aquatic plant. Each cylindrical segment contains mass, inertia tensor, bending stiffness, tensile stiffness, and fracture limit. Each unit has mass, position, and velocity properties. The connections between units simulate the internal mechanical behavior of the aquatic plant. The connections between units utilize springs... The damping model uses spring elements to provide elastic restoring force against tension and bending. The elastic coefficient is determined based on the elastic modulus and cross-sectional properties of the aquatic plant material. The damping element dissipates vibration energy, simulating the internal friction and fluid damping of the aquatic plant. The damping coefficient is calibrated experimentally. When the tensile force or bending moment on the connection exceeds the critical value, the connection breaks and the aquatic plant splits into two parts. When multiple aquatic plants meet in the flow field, they intertwine to form a larger cluster. The mechanical properties of the cluster are calculated using a merging algorithm, treating all contacting cylindrical segments as a whole and recalculating the center of mass, total mass, and outer envelope dimensions. S42. Using large eddy simulation or separated eddy simulation, simulate the dynamic behavior of aquatic plants in the turbine runner area, evaluate the interaction between each aquatic plant and the rotating blades, and quantify the degree of accumulation of aquatic plants on the unit and its feedback effect on the flow field. For each aquatic plant, simulate from entering the runner chamber inlet to leaving the tailrace outlet or completely wrapped around the runner, calculate the fluid resistance, lift, and pressure gradient force on each cylindrical section, and calculate the contact between the cylindrical section of the aquatic plant and the blade surface, the inner wall of the runner chamber, and the surface of the drain cone. Use the Hertz contact model and the Coulomb friction model to calculate the normal collision force and tangential friction force. When the normal force exceeds the normal force threshold and the relative velocity is less than the relative velocity threshold, it is determined to be adhesion. S43. Based on the squeezing and stretching effect of the blade leading edge on the aquatic plants, the local shear stress on the aquatic plant section is evaluated. When the shear stress exceeds the shear strength of the aquatic plants, cutting occurs. The discrete element aquatic plant model is embedded in the CFD flow field for fluid-structure interaction simulation. Aquatic plants are arranged in the inlet area of ​​the impeller. The incident position is determined according to the aggregation area. The plants are concentrated in the incident position area of ​​the inlet section. The aquatic plants are released in batches at different times according to the arrival time. The initial orientation of the aquatic plants is set according to the flow field direction. Explicit time integration is used for simulation. At each time step, the flow field is updated, the flow field force and gravity on each discrete element are calculated, the position and velocity of the element are updated, the contact between the element and the blade surface is detected, and contact events are identified through geometric judgment. If contact occurs, the contact force is calculated, the motion state of the element is updated, and the proportion of various results is statistically analyzed. The cutting probability of aquatic plants is generated according to different states of the aquatic plants. The cutting probability formula is: ,in, The normal relative velocity is between the aquatic plant segment and the leading edge of the leaf. Let be the radius of curvature of the leading edge of the blade. The shear strength of aquatic plants is directly proportional to their tensile strength. For the impact angle, This is the blade sharpness correction coefficient. When the numerator exceeds the denominator, the cutting probability tends to 1, the cutting fails, and the aquatic plants enter a tangled state. S44. Substitute the cutting probability into the cumulative entanglement mass assessment formula to evaluate the total mass of aquatic plants hanging on the leaves per unit time. The cumulative entanglement mass assessment formula is as follows: ,in, The concentration of aquatic plants. Let be the cutting probability of the i-th aquatic plant. The real-time flow rate entering the unit is denoted as n, the number of aquatic plants in the target area is denoted as i, and the cumulative entanglement mass assessment formula describes the total mass of aquatic plants hanging on the leaves per unit time.

[0010] Preferably, the assessment of unit operating risk and the implementation of safety control for the unit based on the probability of aquatic weed cutting, the quality of entanglement, and the vibration parameters of the turbine unit includes the following specific steps: S51. Substitute the cutting probability and winding quality into the comprehensive risk index assessment formula to evaluate the real-time safety status of the turbine unit. The comprehensive risk index assessment formula is as follows: ,in, M represents the average cutting probability across the entire blade region, and M represents the cumulative entanglement mass. The maximum allowable straw-hanging load critical value for the unit was determined through centrifugal force balance experiments and shaft strength design values. For real-time monitoring of vibration amplitude, This is the vibration alarm limit value. , and These are the weighting coefficients; S52. Compare the comprehensive risk index of the turbine unit with the safety threshold of the turbine unit, and rank all units according to their comprehensive risk index. Select the turbine unit with the lowest comprehensive risk for priority operation, and issue an entanglement warning for the turbine unit that exceeds the safety threshold to remind the user to maintain it.

[0011] Secondly, a hydropower multi-source information fusion and real-time optimization scheduling system is also provided, which is implemented based on the aforementioned hydropower multi-source information fusion and real-time optimization scheduling method, and specifically includes: The data acquisition module is used to acquire information on aquatic plants in the water body, water conditions, and turbine unit conditions. The aquatic plant movement assessment module is used to dynamically assess the speed and trajectory of each aquatic plant at different future moments by analyzing the forces acting on it. The aquatic plant distribution assessment module is used to assess the temporal distribution and spatial concentration evolution of aquatic plants through the analysis of their movement and aggregation. The aquatic plant cutting evaluation module is used to evaluate the probability of aquatic plant cutting by using discrete aquatic plant units and flow field data. The aquatic plant entanglement assessment module is used to dynamically assess the cumulative quality of aquatic plant entanglement based on the probability of aquatic plant cutting. The unit risk assessment module is used to assess the unit's operational risks by considering factors such as the probability of weed cutting, the quality of weed wrapping, and the turbine unit's vibration parameters, and to implement safety control measures for the unit.

[0012] Thirdly, an electronic device is provided, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the above-mentioned hydropower multi-source information fusion and real-time optimization scheduling method by calling the computer program stored in the memory.

[0013] Fourthly, a computer-readable storage medium is provided, characterized in that it stores instructions that, when the instructions are executed on a computer, cause the computer to perform the above-described method for multi-source information fusion and real-time optimization scheduling of hydropower.

[0014] Compared with the prior art, the beneficial effects of this application are: This application acquires information on aquatic plants, water conditions, and turbine unit conditions in the water body. Based on the force analysis of the aquatic plants, it dynamically evaluates the movement speed and trajectory of each aquatic plant at various future moments. Based on the movement state and aggregation analysis of the aquatic plants, it assesses the temporal distribution and spatial concentration evolution of the aquatic plants. Based on discrete aquatic plant units and flow field data, it evaluates the probability of aquatic plant cutting and dynamically evaluates the cumulative mass of aquatic plant entanglement. Based on the probability of aquatic plant cutting, entanglement mass, and turbine unit vibration parameters, it assesses the unit's operational risks and implements safety control of the unit. By integrating multi-source information, it achieves aquatic plant movement prediction, entanglement assessment, and unit risk analysis, thereby improving the safety and stability of turbine unit operation. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the overall process of the hydropower multi-source information fusion and real-time optimization scheduling method in this application; Figure 2 This is a flowchart for assessing the concentration of aquatic plants in this application; Figure 3 This is a flowchart of the comprehensive risk index assessment process for the turbines in this application; Figure 4This is a schematic diagram of the overall framework of the hydropower multi-source information fusion and real-time optimization scheduling system of this application. Detailed Implementation

[0016] The technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations thereof. In the absence of conflict, the embodiments and technical features in the embodiments can be combined with each other.

[0017] Please see Figures 1-3 This application provides an embodiment of a method for multi-source information fusion and real-time optimization scheduling of hydropower, which includes the following specific steps: To obtain information on aquatic plants in the water body, water conditions, and turbine unit status; Based on the force analysis of aquatic plants, the speed and trajectory of each aquatic plant at different future moments are dynamically evaluated. Based on the analysis of aquatic plant movement and aggregation, the temporal distribution of aquatic plant arrival and the spatial concentration evolution are evaluated; The probability of aquatic plant cutting is evaluated based on discrete aquatic plant units and flow field data, and the cumulative mass of aquatic plant entanglement is dynamically evaluated. Based on the probability of aquatic plant cutting, the quality of entanglement, and the vibration parameters of the turbine unit, the operational risks of the unit are assessed, and safety control of the unit is implemented.

[0018] In this embodiment, it should be specifically explained that obtaining information on aquatic plants, water conditions, and turbine unit conditions in the water body includes the following specific steps: S11. Using high-frequency image sonar and laser scanner, non-contact scanning of floating objects in water flow is performed to obtain aquatic plant image information, extract the geometric and physical properties of aquatic plants, including aquatic plant species, density, distribution location, length and flow posture, and obtain the aquatic plant mass concentration per unit volume by identifying the intensity of sonar echo (backscattering intensity) and calibrating it through experiments. S12. The basic distribution of the flow field is obtained by using an acoustic Doppler current profiler (ADCP) and a water level gauge deployed at the inlet of the turbine unit. The velocity vector at any point (x, y, z) in the rectangular coordinate system at time t is: Where u, v, and w are the components of the flow velocity in the transverse, longitudinal, and vertical directions, respectively, and i, j, and k are unit vectors, obtained directly through ADCP layered scanning along the cross-section. The formula is derived from the basic equations of motion in fluid mechanics. The degree of tumbling of aquatic plants in the flow field is evaluated by calculating the turbulence intensity. The formula for calculating the turbulence intensity is: ,in, , and This represents the fluctuating values ​​of the flow velocity in each direction, i.e., the difference between the real-time value and the average value; The average flow velocity is given. The greater the turbulence intensity, the more intense the water flow disturbance, and the higher the probability of irregular entanglement of aquatic plants. S13. Obtain internal parameters of the turbine unit through the existing monitoring and data acquisition system (SCADA) of the turbine unit, including speed, blade angle and vibration signal. Resample using linear interpolation based on a unified timestamp to align the aquatic plant data, water body data and turbine unit data on the same time axis.

[0019] In this embodiment, it should be specifically explained that, based on the force analysis of the aquatic plants, the dynamic evaluation of the movement speed and trajectory of each aquatic plant at different future moments includes the following specific steps: S21. Establish a full-domain 3D CFD model including the inlet channel, trash rack, water diversion pipe, and turbine chamber inlet. Discretize each collected aquatic plant individual into a Lagrange particle. Each aquatic plant includes spatial coordinates, velocity vector, geometric features, mechanical features, state markers, and cluster state. The spatial coordinates represent the 3D position of the aquatic plant's center of mass at the current moment, the velocity vector represents the aquatic plant's velocity at the current moment, the geometric features include length, equivalent diameter, and curvature index, the mechanical features include tensile strength, toughness modulus, and density, the state markers include floating state (floating on the water surface, suspended in the water, rolling near the bottom), and the cluster state is whether it is intertwined with other aquatic plants to form a clump. For example, in this embodiment, the global three-dimensional CFD model adopts the standard k-ε or shear stress transport turbulence model, with the total number of grids controlled between 5 million and 20 million. The CFD model uses the inlet velocity distribution measured by ADCP as the inlet boundary condition and the flow rate corresponding to the turbine guide vane opening as the outlet boundary condition. Through steady-state or transient solutions, it outputs the three-directional velocity components (u, v, w), pressure p, and turbulence parameters (turbulent kinetic energy k, dissipation rate ε) of each grid node in the entire computational domain. The intrinsic orthogonal decomposition (POD) is employed. Alternatively, dynamic mode decomposition (DMD) reduction techniques are used. In the offline phase, extensive CFD calculations are performed in advance for different operating conditions (different inlet velocity distributions, different water levels, different guide vane openings) to form a flow field snapshot library. The snapshot library is then subjected to dimensionality reduction decomposition to extract the top M most important flow field modes (M=20~50). In the online phase, based on the current ADCP measured velocity distribution, the global flow field that best matches the current boundary conditions is rapidly reconstructed in the low-dimensional mode space through interpolation, obtaining a spatially continuous three-dimensional velocity field that is dynamically updated over time. Using spatial coordinates, turbulent fluctuations exist in actual water bodies, affecting the diffusion and aggregation of aquatic plants. The fluctuating velocity is superimposed on the average flow velocity field. The formula for calculating the turbulent fluctuating velocity is: ,in, For turbulent fluctuation velocity, The timescale is the Lagrange integral (related to turbulent kinetic energy and dissipation rate). For the turbulent velocity variance, For Wiener process increments; S22. In the flow field, aquatic plants are subjected to gravity, buoyancy, drag, and additional forces from fluid acceleration. The motion state of the aquatic plants is evaluated by the forces acting on them in the water. The equation of motion for the aquatic plants is as follows: ,in, For fluid resistance, Due to the buoyancy of the aquatic plants, Due to the weight of the aquatic plants, This is the pressure gradient force, caused by uneven water flow velocity. For the quality of aquatic plants, Let be the velocity vector of the aquatic plants. By integrating the equation of motion of the aquatic plants over time, we can obtain the velocity of each aquatic plant at various future moments. The formula for calculating fluid resistance is as follows: ,in, For water density, The drag coefficient, Let V be the projected area of ​​the aquatic plant in the direction of water flow, and V be the local water flow velocity. For long, narrow aquatic plants, the projected area is related to the water inflow angle. The projected area of ​​the aquatic plant in the direction of water flow is calculated using the plant's attitude angle. The formula for calculating the projected area of ​​the aquatic plant in the direction of water flow is: Where L is the length of the aquatic plant, d is the equivalent diameter of the aquatic plant, and θ is the angle between the water flow direction and the long axis of the aquatic plant. The formula for calculating the drag coefficient is: Where Re is the Reynolds number based on the equivalent diameter of the aquatic plants, and f is the flexibility correction factor. The greater the flexibility, the smaller the drag coefficient. The formulas for calculating gravity and buoyancy are: ,in, For aquatic plant density, For water density, Let g be the volume of the aquatic plants and g be the acceleration due to gravity. When the density of the aquatic plants is less than the density of the water, the aquatic plants have positive buoyancy and tend to float to the surface; otherwise, they sink. The formula for calculating the pressure gradient force is: ,in, The substantial derivative of the fluid particle represents the acceleration of the water flow, obtained by spatially differentiating the spatial velocity field V(x,y,z) acquired in the first step. For example, in the contraction section, the velocity increases with position, generating an induced force pointing towards the high-velocity acceleration. When the water plants enter areas where the water flow accelerates rapidly, such as the turbine inlet, the force generated by the uneven water pressure forms a rigid set of ordinary differential equations. The fourth-order Runge-Kutta method is used for time integration, with the time step Δt set to 0.01 seconds to 0.05 seconds. The integration interval corresponds to the prediction time window. Within each time step, the velocity of the water plants at their current position is interpolated from the established spatiotemporal flow field using trilinear interpolation or radial basis function interpolation. When the water plants reach the free surface, the vertical velocity component is set to zero, allowing horizontal movement. When the water plants collide with the debris barrier, it is determined whether they pass or are intercepted based on the spacing between the bars and the size of the water plants. Intercepted water plants are marked and removed from subsequent trajectory predictions. After integration, the spatial position of each water plant at various future times is obtained.

[0020] In this embodiment, it should be specifically explained that, based on the analysis of aquatic plant movement and aggregation, the assessment of the temporal distribution and spatial concentration evolution of aquatic plants includes the following specific steps: S31. For each turbine unit, define a target area, which is a fan-shaped or rectangular area in front of the unit's inlet. Record the moment when each aquatic plant first enters the target area. Statistically analyze all aquatic plants to obtain the aquatic plant arrival time distribution, the first wave arrival time, and the peak arrival time. The arrival time distribution is represented by a histogram or probability density function, indicating the number of aquatic plants or the total biomass arriving in different time intervals. The first wave arrival time is the moment the first aquatic plant arrives, used to trigger an early warning. The peak arrival time is the time window with the highest aquatic plant arrival rate. Further subdivide the target area into several sub-areas. For example, along the width direction, divide it into left, middle, and right; along the water depth direction, divide it into surface, middle, and bottom layers. Statistically analyze the number of aquatic plants arriving in each sub-area to form... The spatiotemporal distribution map of aquatic plant concentration is presented in the form of a heat map, which intuitively shows which sub-region the aquatic plants will mainly gather in. Considering the randomness of turbulence and the uncertainty of initial conditions, the Monte Carlo method is adopted. For the same initial aquatic plant field, the aquatic plant tracking model is run multiple times (each time superimposed with different random turbulent fluctuations) to obtain multiple sets of trajectories. The probability of aquatic plants arriving in each unit and each time window is calculated. The probability is defined as the percentage of times that at least one aquatic plant arrives in the target area before time t in the Monte Carlo simulation. During the normal operation of the power station, the actual movement trajectory of the aquatic plants is observed. These measured trajectories are compared with the model prediction trajectories to calculate the position error. The model parameters are dynamically adjusted using ensemble Kalman filtering or aquatic plant filtering methods to minimize the prediction error. S32. Assess the concentration of aquatic plants by measuring their movement speed, and evaluate the blockage at the turbine inlet. The target area is... The formula for calculating the concentration of aquatic plants at a given time is: ,in, For the local flow field gradient, For the speed of aquatic plant movement, The flux function depends on the velocity of the aquatic plants and the local flow field gradient (i.e., where the water flow turns or slows down). The aquatic plant aggregation concentration represents how the aquatic plants migrate with the water flow and converge in low-speed and eddy regions. The flow field gradient describes the rate of change of the flow velocity in space, i.e., the shear rate. Based on the discrete flow field data V(x,y,z) obtained in the first step, the derivative is calculated within the computational grid using the finite difference method or the least squares gradient reconstruction method. The flux function describes the mass of aquatic plants passing through a unit area per unit time. In this embodiment, the flux function determines the accumulation rate of aquatic plants in a certain space. The formula for calculating the flux function is: Where C represents the local concentration of aquatic plants. Let be the turbulent diffusion tensor, whose magnitude is proportional to the modulus of the local flow field gradient and the turbulent kinetic energy. For the concentration gradient, the flux function consists of an advection term (displacement caused by water flow) and a diffusion term (random dispersion due to turbulent fluctuations). It is obtained by converting the turbulence intensity I in the first step into Prandtl's mixing length theory.

[0021] In this embodiment, it should be specifically explained that the evaluation of the probability of aquatic plant cutting based on discrete aquatic plant units and flow field data, and the dynamic evaluation of the cumulative mass of aquatic plant entanglement, include the following specific steps: S41. Discretize a continuous aquatic plant into a series of units connected by flexible connections. Discretize a single aquatic plant of length L and diameter d into N equal-length cylindrical segments, each of which is considered a rigid body. The segments are connected by ball joints, allowing relative rotation. A torsion spring and a damper are placed at each connection point to simulate the bending stiffness of the aquatic plant. Each cylindrical segment contains mass, inertia tensor, bending stiffness, tensile stiffness, and fracture limit. Each unit has mass, position, and velocity properties. The connections between units simulate the internal mechanical behavior of the aquatic plant. The connections between units adopt a spring-damping model, with spring elements providing elastic restoring forces against tension and bending. The elastic coefficient is determined based on the material of the aquatic plant. The elastic modulus and cross-sectional properties of the material are determined, and the damping element dissipates vibration energy. The internal friction and fluid damping of the aquatic plants are simulated. The damping coefficient is calibrated by experiments. When the tensile force or bending moment of the connection exceeds the critical value, the connection breaks and the aquatic plants split into two parts. When multiple aquatic plants meet in the flow field, they intertwine to form larger clusters. The mechanical properties of the clusters (equivalent length, equivalent stiffness, and equivalent mass) are calculated by a merging algorithm. All the cylindrical segments in contact with each other are regarded as a whole, and the center of mass, total mass, and outer envelope size are recalculated. The bending stiffness of the clusters increases significantly. The formation of clusters by multiple intertwined aquatic plants greatly increases the probability of entanglement because the clusters are more likely to get stuck in the gap between the blades and the impeller chamber. S42. Using large eddy simulation or separated eddy simulation, simulate the dynamic behavior of aquatic plants within the turbine runner region, evaluate the interaction between each aquatic plant and the rotating blades (cutting, entanglement, or safe passage), and quantify the cumulative degree of entanglement on the unit and its feedback impact on the flow field. The computational domain is limited to the runner region (including the runner chamber, runner blades, and spillway cones) from the guide vane outlet to the tailrace inlet. The flow field of this region is provided by the previous-level CFD model. However, to simulate the transient interaction between the aquatic plants and the blades, the model inputs include: aquatic plant information (position, velocity, geometry, and mechanical properties) output from the second step, the current blade geometry (including post-wear sharpness and measured tip clearance), runner speed and guide vane opening, and the instantaneous velocity boundary at the runner chamber inlet. For each aquatic plant, the simulation begins from its entry into the runner chamber inlet and continues until it leaves the tailrace outlet or is completely entangled on the runner. Calculate the fluid resistance, lift, and pressure gradient force on each cylindrical section. Due to the high velocity and strong shear in the runner region, the Reynolds number may reach 10. 5 The above uses a modified formula related to the local turbulence intensity for the drag coefficient. In addition to the Saffman lift, the lift also includes the Magnus force generated by the rotation of the aquatic plants. The cylindrical section of the aquatic plants comes into contact with the blade surface, the inner wall of the impeller chamber, and the surface of the drain cone. The Hertz contact model and the Coulomb friction model are used to calculate the normal collision force and the tangential friction force. When the normal force exceeds the normal force threshold and the relative velocity is less than the relative velocity threshold, it is determined to be attachment, that is, the aquatic plants begin to entangle. For example, in this embodiment, the CFD simulation mesh and boundary conditions are as follows: the impeller region adopts a hexahedral structured mesh or a tetrahedral / prism hybrid mesh; the blade surface boundary layer is set with at least 10 prism layers; the impeller chamber wall, blade surface, and discharge cone surface are all set to no-slip wall conditions; the inlet boundary is derived from the instantaneous velocity distribution (including turbulent fluctuation components) provided by the upstream CFD reduced-order model; the outlet boundary is a pressure outlet; the static pressure is set according to the downstream water level; the impeller rotation adopts a slip mesh or dynamic mesh technology; and the measured rotational speed is given. S43. Shear stress originates from the compression and stretching of the aquatic plants by the blade leading edge. Based on the compression and stretching effect of the blade leading edge on the aquatic plants, the local shear stress on the aquatic plant section is assessed. When the shear stress exceeds the shear strength of the aquatic plants, they are cut. The CFD simulation outputs a detailed flow field distribution in the impeller region, including: velocity field: three-dimensional velocity components, calculating relative velocity (velocity relative to the rotating blades); pressure field: static and dynamic pressure distribution, calculating pressure gradient force; shear rate field: velocity gradient tensor, assessing the flow field's cutting ability on the aquatic plants; flow characteristics: turbulent kinetic energy and dissipation rate, assessing the intensity of random fluctuations. The discrete element aquatic plant model is embedded into the CFD flow field for fluid-structure interaction simulation in the impeller inlet region. Aquatic plants are deployed, and the incident position is determined based on the aggregation area. They are concentrated in the incident position area at the inlet section. Aquatic plants are released in batches at different times according to their arrival time. The initial orientation of the aquatic plants is set according to the flow field direction. Explicit time-integration simulation is used. At each time step, the flow field is updated, the flow field force and gravity acting on each discrete element are calculated, and the element's position and velocity are updated. Contact between the element and the blade surface is detected, and contact events are identified through geometric judgment (distance, penetration depth). If contact occurs, the contact force (normal contact force and tangential friction force) is calculated, the element's motion state is updated, and the proportions of various results are statistically analyzed. The cutting probability of the aquatic plants is generated based on different plant states. The cutting probability formula is: ,in, The normal relative velocity is between the aquatic plant segment and the leading edge of the leaf. Let be the radius of curvature of the leading edge of the blade. The shear strength of aquatic plants is directly proportional to their tensile strength. The smaller the angle between the long axis of the aquatic plant and the tangent to the leading edge of the leaf, the easier it is to cut. The blade sharpness correction coefficient (1.0 for new blades, less than 1 after wear) is used when the numerator (hydrodynamic impact pressure multiplied by the radius of curvature) exceeds the denominator (material shear strength multiplied by the angle factor), the cutting probability tends to 1, the cutting fails, and the aquatic plants enter a tangled state. S44. Substitute the cutting probability into the cumulative entanglement mass assessment formula to evaluate the total mass of aquatic plants hanging on the leaves per unit time. The cumulative entanglement mass assessment formula is as follows: ,in, The concentration of aquatic plants. Let be the cutting probability of the i-th aquatic plant. The real-time flow rate entering the unit is given by n, the number of aquatic plants in the target area is given by i, and the cumulative entanglement mass assessment formula represents the total mass of aquatic plants hanging on the leaves per unit time.

[0022] In this embodiment, it should be specifically explained that, based on the probability of weed cutting, the entanglement quality, and the vibration parameters of the turbine unit, the assessment of the unit's operational risk and the implementation of safety control for the unit include the following specific steps: S51. Substitute the cutting probability and winding quality into the comprehensive risk index assessment formula to evaluate the real-time safety status of the turbine unit. The comprehensive risk index assessment formula is as follows: ,in, M represents the average cutting probability across the entire blade region, and M represents the cumulative entanglement mass. The maximum allowable straw-hanging load critical value for the unit was determined through centrifugal force balance experiments and shaft strength design values. For real-time monitoring of vibration amplitude, This is the vibration alarm limit value. , and These are the weighting coefficients; For example, in this embodiment, the weight coefficients are obtained as follows: based on the operating mechanism of the turbine unit and the importance of each influencing factor, a preliminary analysis is conducted on the impact of the probability of waterweed cutting, the cumulative mass of entanglement, and vibration parameters on the safety of the unit, and an initial range of weight coefficient values ​​is given. Based on historical operating data and experimental data, a mapping relationship between the comprehensive risk index and the actual operating state of the unit is constructed. The cutting probability, the mass of waterweed, and the vibration amplitude under different operating conditions are used as inputs, and whether the unit has an abnormality is used as the output. The contribution of each parameter is quantified by regression analysis, principal component analysis, or machine learning methods to obtain the initial estimated value of each weight coefficient. With the goal of improving the accuracy of risk assessment, an optimization objective function is constructed. By minimizing the error between the predicted risk and the actual operating state, the weight coefficients are iteratively optimized and solved. The optimized weight coefficients are normalized to meet the constraint that the sum of the weights is 1. In the actual operation process, adaptive adjustments are made according to real-time data to obtain weight coefficients that can accurately reflect the degree of influence of each factor. S52. Compare the comprehensive risk index of the turbine unit with the safety threshold of the turbine unit, and rank all units according to their comprehensive risk index. Select the turbine unit with the lowest comprehensive risk for priority operation, and issue a winding warning for turbine units that exceed the safety threshold to remind users to maintain them. For example, in this embodiment, the safety threshold of the turbine unit is determined by combining design parameter analysis, experimental calibration, and historical data statistics: Based on the design value of the unit's shaft strength, the bearing capacity of the blade structure, and the centrifugal force balance conditions, the maximum allowable grass-hanging load critical value of the unit under normal operating conditions is calculated, and this is used as the theoretical upper limit of the safety threshold. Through field tests or model tests, the equivalent grass-hanging amount is gradually increased under different grass-hanging conditions. The vibration amplitude, power fluctuation, and structural response characteristics of the unit are monitored in real time to determine the grass-hanging quality critical point and vibration alarm limit corresponding to the transition of the unit from stable operation to abnormal state. Combined with historical operating data, the unit's operating status and fault occurrence under high grass-hanging conditions are statistically analyzed to establish a mapping relationship between comprehensive risk indicators and abnormal operating states. The safe operating range is extracted, and the above design limit values, experimental calibration results, and statistical analysis results are normalized and weighted to obtain the comprehensive safety threshold of the unit. The safety threshold is dynamically corrected according to the real-time flow rate, grass concentration, and unit operating status to achieve adaptive updating of the safety threshold.

[0023] The advantages of this embodiment compared to the prior art are: This application acquires information on aquatic plants, water conditions, and turbine unit conditions in the water body. Based on the force analysis of the aquatic plants, it dynamically evaluates the movement speed and trajectory of each aquatic plant at various future moments. Based on the movement state and aggregation analysis of the aquatic plants, it assesses the temporal distribution and spatial concentration evolution of the aquatic plants. Based on discrete aquatic plant units and flow field data, it evaluates the probability of aquatic plant cutting and dynamically evaluates the cumulative mass of aquatic plant entanglement. Based on the probability of aquatic plant cutting, entanglement mass, and turbine unit vibration parameters, it assesses the unit's operational risks and implements safety control of the unit. By integrating multi-source information, it achieves aquatic plant movement prediction, entanglement assessment, and unit risk analysis, thereby improving the safety and stability of turbine unit operation.

[0024] like Figure 4As shown, the hydropower multi-source information fusion and real-time optimization scheduling system is implemented based on the aforementioned hydropower multi-source information fusion and real-time optimization scheduling method. Specifically, it includes a data acquisition module, a water plant movement assessment module, a water plant distribution assessment module, a water plant cutting assessment module, a water plant entanglement assessment module, and a unit risk assessment module. The data acquisition module is used to acquire information on water plants, water conditions, and turbine unit conditions. The water plant movement assessment module is used to dynamically assess the movement speed and trajectory of each water plant at future times through force analysis. The water plant distribution assessment module is used to assess the temporal distribution and spatial concentration evolution of water plants through water plant movement state and aggregation analysis. The water plant cutting assessment module is used to assess the probability of water plant cutting through discrete water plant units and flow field data. The water plant entanglement assessment module is used to dynamically assess the cumulative mass of water plant entanglement based on the water plant cutting probability. The unit risk assessment module is used to assess the unit's operational risk and implement safe control of the unit based on the water plant cutting probability, entanglement mass, and turbine unit vibration parameters.

[0025] Embodiments of this application also provide an electronic device, including a memory, a processor, and a communication bus; the memory and the processor are connected via the communication bus. The memory stores a method for multi-source hydropower information fusion and real-time optimization scheduling, which can be loaded and executed by the processor as provided in the above embodiments.

[0026] The memory can be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the hydropower multi-source information fusion and real-time optimization scheduling method provided in the above embodiments. The data storage area may store data involved in the hydropower multi-source information fusion and real-time optimization scheduling method provided in the above embodiments.

[0027] A processor may include one or more processing cores. The processor executes instructions, programs, code sets, or instruction sets stored in memory, and calls data stored in memory to perform various functions and process data as described in this application. The processor may be at least one of a specific application-specific integrated circuit, a digital signal processor, a digital signal processing device, a programmable logic device, a field-programmable gate array, a central processing unit, a controller, a microcontroller, and a microprocessor. It is understood that, for different devices, the electronic devices used to implement the above-described processor functions may also be other types, and the embodiments of this application do not specifically limit this.

[0028] A communication bus may include a pathway for transmitting information between the aforementioned components. The communication bus can be a PCI bus or an EISA bus, etc. Communication buses can be categorized into address buses, data buses, control buses, etc.

[0029] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments for the hydropower multi-source information fusion and real-time optimization scheduling method.

[0030] In this embodiment, a computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), staging random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0031] The term includes, or any other variation thereof, is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0032] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A method for multi-source information fusion and real-time optimized scheduling of hydropower, characterized in that, It includes the following specific steps: To obtain information on aquatic plants in the water body, water conditions, and turbine unit status; Based on the force analysis of aquatic plants, the speed and trajectory of each aquatic plant at different future moments are dynamically evaluated. Based on the analysis of aquatic plant movement and aggregation, the temporal distribution of aquatic plant arrival and the spatial concentration evolution are evaluated; The probability of weed cutting is evaluated based on discrete weed units and flow field data, and the cumulative mass of weed entanglement is dynamically assessed. The specific steps include: discretizing continuous weeds into a series of units connected by flexible links; discretizing a single weed of length L and diameter d into N equal-length cylindrical segments, each containing mass, inertia tensor, bending stiffness, tensile stiffness, and fracture limit; when multiple weeds meet in the flow field, they entangle to form larger clusters, and the mechanical properties of these clusters are calculated using a merging algorithm, treating all contacting cylindrical segments as a whole, and recalculating the center of mass, total mass, and outer envelope dimensions; using large eddy simulation or separated eddy simulation methods to simulate the dynamic behavior of weeds in the turbine runner region, evaluating the interaction between each weed and the rotating blades, and quantifying the degree of accumulation on the unit and its feedback effect on the flow field; for each weed, the simulation is performed from its entry into the runner chamber inlet to its exit from the tailrace outlet and complete entanglement on the runner, calculating the fluid resistance experienced by each cylindrical segment, Lift and pressure gradient forces are used to assess the local shear stress on the aquatic plant section based on the squeezing and stretching effects of the blade leading edge. When the shear stress exceeds the shear strength of the aquatic plant, it is cut. Discrete element aquatic plants are embedded in the CFD flow field for fluid-structure interaction simulation. Aquatic plants are arranged in the inlet area of ​​the impeller, and the incident position is determined based on the aggregation area. They are concentrated in the incident position area of ​​the inlet section. Aquatic plants are released in batches at different times according to the arrival time. The initial orientation of the aquatic plants is set according to the flow field direction. Explicit time integration is used for simulation. At each time step, the flow field is updated, the flow field force and gravity on each discrete element are calculated, the position and velocity of the element are updated, the contact between the element and the blade surface is detected, and contact events are identified through geometric judgment. If contact occurs, the contact force is calculated, the motion state of the element is updated, and the proportion of various results is statistically analyzed. The aquatic plant cutting probability is generated based on the different states of the aquatic plants. The cutting probability is substituted into the entanglement cumulative mass assessment formula to evaluate the total mass of aquatic plants hanging on the blade per unit time. The entanglement cumulative mass assessment formula is as follows: ,in, The concentration of aquatic plants. Let be the cutting probability of the i-th aquatic plant. The real-time flow rate entering the unit is n, where n is the number of aquatic plants in the target area and i is the i-th aquatic plant. Based on the probability of aquatic plant cutting, the quality of entanglement, and the vibration parameters of the turbine unit, the operational risks of the unit are assessed, and safety control of the unit is implemented.

2. The hydropower multi-source information fusion and real-time optimization scheduling method as described in claim 1, characterized in that, The process of obtaining information on aquatic plants, water conditions, and turbine unit status in the water body includes the following specific steps: The first step is to use high-frequency imaging sonar and laser scanner to perform non-contact scanning of floating objects in the water flow, obtain aquatic plant image information, extract the geometric and physical properties of aquatic plants, including aquatic plant species, density, distribution location, length and flow posture, and obtain the aquatic plant mass concentration per unit volume. The second step involves obtaining the basic distribution of the flow field using an acoustic Doppler velocity profiler and a water level gauge deployed at the turbine inlet. The velocity vector at any point (x, y, z) in Cartesian coordinates at time t is: Where u, v, and w are the components of the flow velocity in the horizontal, vertical, and longitudinal directions, respectively, and i, j, and k are unit vectors. The degree of tumbling of aquatic plants in the flow field is evaluated by calculating the turbulence intensity. The formula for calculating the turbulence intensity is: ,in, , and These represent the fluctuating values ​​of the flow velocity in each direction. The average flow velocity; The third step is to obtain internal parameters of the turbine unit, including rotational speed, blade angle, and vibration signals, through the existing monitoring and data acquisition system of the turbine unit.

3. The hydropower multi-source information fusion and real-time optimization scheduling method as described in claim 2, characterized in that, The dynamic evaluation of the movement speed and trajectory of each aquatic plant at future moments, based on the force analysis of the aquatic plants, includes the following specific steps: The first step is to establish a full-domain 3D CFD model including the inlet channel, trash rack, water pipe, and turbine chamber inlet. Each individual aquatic plant is discretized into a Lagrange particle. Each aquatic plant includes spatial coordinates, velocity vector, geometric features, mechanical features, state markers, and cluster state. The second step is to assess the motion of the aquatic plants by analyzing the forces acting on them in the water. The equation for the motion of the aquatic plants is as follows: ,in, For fluid resistance, Due to the buoyancy of the aquatic plants, Due to the weight of the aquatic plants, For pressure gradient force, For the quality of aquatic plants, Let be the velocity vector of the aquatic plants. By integrating the equation of motion of the aquatic plants over time, we can obtain the velocity of each aquatic plant at various future moments.

4. The hydropower multi-source information fusion and real-time optimization scheduling method as described in claim 3, characterized in that, The assessment of the temporal distribution and spatial concentration evolution of aquatic plants based on their movement and aggregation analysis includes the following specific steps: The first step is to define a target area for each turbine unit, record the time when each aquatic plant first enters the target area, count all aquatic plants to obtain the aquatic plant arrival time distribution, the first wave arrival time and the peak arrival time, count the number of aquatic plants arriving in each sub-area, and form a spatiotemporal distribution map of aquatic plant concentration. The second step is to assess the concentration of aquatic plants by measuring their movement speed, with the target area being... The formula for calculating the concentration of aquatic plants at a given time is: ,in, For the local flow field gradient, For the speed of aquatic plant movement, This is the flux function.

5. The hydropower multi-source information fusion and real-time optimization scheduling method as described in claim 4, characterized in that, The assessment of unit operation risk and the implementation of safety control based on the probability of aquatic weed cutting, the quality of entanglement, and the vibration parameters of the turbine unit include the following specific steps: The first step is to substitute the cutting probability and entanglement quality into the comprehensive risk index assessment formula to evaluate the real-time safety status of the turbine unit. The comprehensive risk index assessment formula is as follows: ,in, Let M be the average cutting probability over the entire blade region, and M be the cumulative entanglement mass. This is the critical value of the maximum allowable straw load for the unit. For real-time monitoring of vibration amplitude, This is the vibration alarm limit value. , and These are the weighting coefficients; The second step is to compare the comprehensive risk index of the turbine units with the safety threshold of the turbine units, and rank all units according to their comprehensive risk index. The turbine units with the lowest comprehensive risk are selected for priority operation, and entanglement warnings are issued for turbine units that exceed the safety threshold to remind users to perform maintenance.

6. A hydropower multi-source information fusion and real-time optimization scheduling system, which is implemented based on the hydropower multi-source information fusion and real-time optimization scheduling method as described in any one of claims 1-5, characterized in that, Specifically, it includes: The data acquisition module is used to acquire information on aquatic plants in the water body, water conditions, and turbine unit conditions. The aquatic plant movement assessment module is used to dynamically assess the speed and trajectory of each aquatic plant at different future moments by analyzing the forces acting on it. The aquatic plant distribution assessment module is used to assess the temporal distribution and spatial concentration evolution of aquatic plants through the analysis of their movement and aggregation. The aquatic plant cutting evaluation module is used to evaluate the probability of aquatic plant cutting by using discrete aquatic plant units and flow field data. The aquatic plant entanglement assessment module is used to dynamically assess the cumulative quality of aquatic plant entanglement based on the probability of aquatic plant cutting. The unit risk assessment module is used to assess the unit's operational risks by considering factors such as the probability of weed cutting, the quality of weed wrapping, and the turbine unit's vibration parameters, and to implement safety control measures for the unit.

7. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The characteristic feature is that the processor executes the hydropower multi-source information fusion and real-time optimization scheduling method as described in any one of claims 1-5 by calling the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform the hydropower multi-source information fusion and real-time optimization scheduling method as described in any one of claims 1-5.

Images