A water conservancy perception system based on edge computing

Abstract

The present invention relates to the technical field of energy efficiency management, and particularly to a water conservancy perception system based on edge computing. The system includes the following modules: a river channel edge perception module, a water conservancy feature analysis module, a sediment transport simulation module, and a siltation and scouring early warning module; a river channel water conservancy perception network is constructed; real-time water conservancy monitoring data is collected according to the river channel water conservancy perception network to obtain river channel water conservancy perception data; the river channel water conservancy perception data is processed by a three-dimensional flow field model to obtain a three-dimensional sediment flow field network model; particle flow field simulation is carried out on the three-dimensional sediment flow field network model to generate sediment transport spatio-temporal distribution data; siltation and scouring area identification is carried out according to the sediment transport spatio-temporal distribution data, and the siltation and scouring area data is uploaded to the cloud platform through an edge computing node for abnormal event alarm to obtain river channel cross-section monitoring data. The present invention realizes real-time, accurate and intelligent monitoring and early warning of the process of river channel sediment siltation and scouring.

Description

Technical Field

[0001] The present invention relates to the technical field of water conservancy measurement, and particularly to a water conservancy perception system based on edge computing. Background Art

[0002] Rivers are an important part of water resources and undertake multiple functions such as water supply, shipping, and ecology. Sediment deposition and erosion are the basic processes of river channel evolution, which have a profound impact on river channel morphology, navigation capacity, water ecological environment, and the safety of water conservancy projects. Therefore, accurately and timely grasping the dynamics of sediment deposition and erosion in the river channel is of great significance for ensuring the flood discharge safety of the river channel, maintaining the smoothness of the waterway, optimizing the allocation of water resources, guiding the design and management of water conservancy projects, and is crucial for the real-time monitoring and effective management of the sediment deposition and erosion process in the river channel. However, traditional water conservancy perception systems mainly rely on manual measurement, regular sampling analysis, or the use of fixed hydrological stations. Manual measurement and sampling analysis are time-consuming and laborious, and it is difficult to achieve high-frequency real-time monitoring. Especially at river bends, narrow river sections, or areas with complex riverbed structures, the degree of sediment deposition and erosion often varies greatly, and traditional monitoring points are difficult to capture these local changes; moreover, traditional hydrological measurement data usually needs to go through links such as manual processing, analysis, and reporting, with a long cycle, and cannot meet the requirements of real-time monitoring and early warning. This leads to a lag in the response to changes in river channel sediment, and it is difficult to achieve refined management and risk prevention and control of water conservancy projects. Summary of the Invention

[0003] Based on this, the present invention provides a water conservancy perception system based on edge computing to solve at least one of the above technical problems.

[0004] To achieve the above object, a water conservancy perception system based on edge computing includes the following modules:

[0005] A river channel edge perception module, including a high-definition camera, an acoustic Doppler current profiler, and a lidar scanner, is used to connect edge computing nodes to the high-definition camera, the acoustic Doppler current profiler, and the lidar scanner to construct a river channel water conservancy perception network; real-time water conservancy monitoring data is collected according to the river channel water conservancy perception network to obtain river channel water conservancy perception data;

[0006] A water conservancy feature analysis module is used to perform time synchronization and spatial registration on the river channel water conservancy perception data to obtain spatio-temporal river channel perception data; water conservancy monitoring feature analysis is performed according to the spatio-temporal river channel perception data to obtain real-time cross-section monitoring feature data; three-dimensional flow field model processing is performed according to the real-time cross-section monitoring feature data to obtain a three-dimensional sediment flow field network model;

[0007] The sediment transport simulation module is used to perform particle flow field simulation on the three-dimensional sediment flow field network model to generate particle trajectory data; perform sediment transport analysis based on the particle trajectory data to generate sediment transport spatio-temporal distribution data;

[0008] The siltation and scouring warning module is used to identify the siltation and scouring areas according to the sediment transport spatio-temporal distribution data to obtain siltation and scouring area data; upload the siltation and scouring area data to the cloud platform through the edge computing node for abnormal event alarm to obtain the river channel cross-section monitoring data.

[0009] Preferably, the river channel edge perception module includes the following functions:

[0010] Obtain the elevation terrain data of the target river channel;

[0011] Mark the key cross-sections of the target river channel for the elevation terrain data to generate key cross-section position data;

[0012] Install high-definition cameras, acoustic Doppler current profilers, and lidar scanners at the key cross-sections of the river channel according to the key cross-section position data to obtain the layout data of water conservancy perception devices;

[0013] Connect the high-definition cameras, acoustic Doppler current profilers, and lidar scanners to the edge computing node based on the layout data of water conservancy perception devices to construct a river channel water conservancy perception network;

[0014] Collect real-time water conservancy monitoring data according to the river channel water conservancy perception network to obtain river channel water conservancy perception data.

[0015] Preferably, the marking of the key cross-sections of the target river channel for the elevation terrain data includes:

[0016] Extract the center line of the target river channel for the elevation terrain data, and identify the left and right river bank lines to obtain river channel geometric constraint data;

[0017] Based on the river channel geometric constraint data, divide the cross-sections perpendicular to the center line of the river channel using a preset equal-spacing threshold to obtain river channel cross-section data;

[0018] Perform spatial superposition on the river channel cross-section data through the elevation terrain data of the target river channel to generate river channel cross-section elevation data;

[0019] Perform cross-section morphology analysis according to the river channel cross-section elevation data to obtain cross-section geometric morphology parameters;

[0020] Calculate the cross-section morphology coefficient according to the cross-section geometric morphology parameters to generate the cross-section morphology coefficient;

[0021] Screen the key river channel sections from the river channel section data through the section form coefficient based on a preset key section identification threshold, and generate key section position data.

[0022] Preferably, the water conservancy feature analysis module includes the following functions:

[0023] Synchronize the time and register the space of the river channel water conservancy perception data to obtain spatio-temporal river channel perception data;

[0024] Transmit the spatio-temporal river channel perception data to the edge computing node and perform data preprocessing to generate water conservancy monitoring data; wherein, the water conservancy monitoring data includes cross-section water body image data, cross-section flow velocity profile data, and cross-section riverbed terrain data;

[0025] Conduct water conservancy monitoring feature analysis based on the water conservancy monitoring data to obtain real-time cross-section monitoring feature data;

[0026] Construct a three-dimensional space network based on the target river channel elevation terrain data to generate a river channel three-dimensional space model;

[0027] Perform three-dimensional flow field model processing on the river channel three-dimensional space model through the real-time cross-section monitoring feature data to obtain a three-dimensional sediment flow field network model.

[0028] Preferably, the water conservancy monitoring feature analysis includes:

[0029] Identify the sediment particle texture of the cross-section water body image data to obtain sediment particle texture data;

[0030] Conduct particle size statistics based on the sediment particle texture data and calculate the particle size mean value to generate real-time sediment particle size data;

[0031] Fit the near-bottom flow velocity distribution curve of the cross-section flow velocity profile data to obtain near-bottom flow velocity distribution curve data;

[0032] Calculate the riverbed bottom shear stress based on the cross-section riverbed terrain data using the near-bottom flow velocity distribution curve data to generate bottom shear stress data;

[0033] Estimate the real-time cross-section concentration based on the cross-section flow velocity profile data and the bottom shear stress data to generate cross-section sediment concentration distribution data;

[0034] Integrate the real-time sediment particle size data, cross-section sediment concentration distribution data, and bottom shear stress data for water conservancy monitoring feature integration to generate real-time cross-section monitoring feature data.

[0035] Preferably, the real-time cross-section concentration estimation includes:

[0036] Perform echo intensity correction based on cross-sectional velocity profile data, calculate the reference concentration of suspended sediment, and generate reference concentration data of suspended sediment;

[0037] Query the sediment settling velocity for the real-time sediment particle size data through a preset sediment particle size-settling velocity relationship database to obtain sediment settling velocity data;

[0038] Calculate the sediment incipient probability based on the sediment settling velocity data and the bottom shear stress data to generate sediment incipient probability data;

[0039] Estimate the sediment suspension concentration based on the reference concentration data of suspended sediment and the sediment incipient probability data, and process the cross-sectional concentration distribution to generate cross-sectional sediment concentration distribution data.

[0040] Preferably, the three-dimensional flow field model processing of the river channel three-dimensional space model includes:

[0041] Perform cross-sectional three-dimensional coordinate conversion based on the cross-sectional sediment concentration distribution data to generate cross-sectional concentration position data;

[0042] Perform interpolation processing on the river channel three-dimensional space model through the cross-sectional concentration position data to obtain a three-dimensional sediment concentration network model;

[0043] Set the bottom boundary conditions of the riverbed according to the cross-sectional riverbed terrain data and the bottom shear stress data to generate bottom boundary condition data;

[0044] Construct a three-dimensional flow field numerical simulation model based on the bottom boundary condition data and the three-dimensional sediment concentration network model through the Navier-Stokes equation to generate a three-dimensional sediment flow field network model.

[0045] Preferably, the sediment transport simulation module includes the following functions:

[0046] Calculate the grid cell volume based on the three-dimensional sediment flow field network model to generate grid cell volume data;

[0047] Mark the cross-sectional monitoring points on the three-dimensional sediment flow field network model and set the virtual particle release positions to obtain virtual particle release position data;

[0048] Allocate the number of particles to the three-dimensional sediment flow field network model through the cross-sectional sediment concentration distribution data to obtain virtual particle number data;

[0049] Perform particle flow field simulation on the three-dimensional sediment flow field network model based on the virtual particle release position data and the virtual particle number data, and perform Lagrangian particle tracking to generate particle trajectory data;

[0050] Sediment transport analysis is carried out based on particle trajectory data to generate spatio-temporal distribution data of sediment transport.

[0051] Preferably, the sediment transport analysis based on particle trajectory data includes:

[0052] Statistically calculate the average displacement vector of grid particles based on particle trajectory data to generate grid average displacement data;

[0053] Calculate the sediment transport flux according to the grid average displacement data to generate sediment transport flux data;

[0054] Convert the theoretical sediment-carrying capacity of particles according to the sediment transport flux data to obtain the theoretical sediment-carrying capacity of particles;

[0055] Calculate the sediment transport rate of the three-dimensional sediment flow field network model through the sediment transport flux data to generate sediment transport rate data;

[0056] Integrate the theoretical sediment-carrying capacity of particles and the sediment transport rate data in the grid spatio-temporal distribution to generate spatio-temporal distribution data of sediment transport.

[0057] Preferably, the sediment deposition and erosion warning module includes the following functions:

[0058] Calculate the net sediment transport volume of grid cells according to the spatio-temporal distribution data of sediment transport to generate net sediment transport volume data;

[0059] Calculate the change amount of grid riverbed elevation based on the net sediment transport volume data through a preset time step to obtain the change amount of riverbed elevation data;

[0060] Superimpose the elevation of the target river channel elevation terrain data and the change amount of riverbed elevation data, and compare it with the preset riverbed terrain erosion threshold to obtain the data of exceeding the sediment deposition and erosion limit;

[0061] Identify the sediment deposition and erosion areas according to the data of exceeding the sediment deposition and erosion limit to obtain the sediment deposition and erosion area data;

[0062] Calculate the sediment erosion and deposition intensity according to the real-time cross-section monitoring characteristic data to generate the sediment erosion and deposition intensity data of grid cells;

[0063] Judge the warning events according to the data of exceeding the sediment deposition and erosion limit and the sediment erosion and deposition intensity data of grid cells, and upload the sediment deposition and erosion area data to the cloud platform through the edge computing node for abnormal event alarm to obtain the river channel cross-section monitoring data.

[0064] The present invention deploys a perception module that integrates high-definition cameras, acoustic Doppler current profilers (ADCPs) and laser radar scanners at the edge of the river channel, and uses edge computing nodes for connection to build a highly integrated, multi-source heterogeneous river water conservancy perception network. This network can achieve all-round and three-dimensional perception of multiple factors such as river flow, sediment, and riverbed topography. High-definition cameras provide real-time video images of the river surface, intuitively reflecting the floating objects on the water surface, water color changes, etc.; ADCP can accurately measure key parameters such as water flow velocity, flow rate, and sediment concentration; and laser radar scanners can quickly obtain high-precision three-dimensional riverbed topographic data. This multi-sensor fusion method makes up for the limitations of a single sensor and realizes comprehensive and accurate perception of the river channel state. Through the deployment of edge computing nodes, real-time collection and preprocessing of raw perception data are realized. Unlike the traditional water conservancy perception system that transmits all data to a remote data center for processing, this system completes the time synchronization, spatial registration, and water conservancy feature extraction processing steps of the data on the edge side close to the data source. Time synchronization ensures the temporal consistency of data collected by different sensors, and the spatial matching criterion unifies these data into the same geographic coordinate system, thereby obtaining river channel perception data that is consistent in time and space. Based on these data, the system further extracts key characteristic parameters that reflect the state of water flow and sediment movement in the river channel, providing high-quality input data for building a three-dimensional flow field model. The introduction of edge computing has greatly reduced the latency and bandwidth requirements of data transmission, improved the efficiency of data processing, and enabled the system to respond quickly to changes in river channel sediment. Especially when dealing with sudden sediment flow events, this low-latency data processing capability can buy valuable time for timely warning and disposal. Using the extracted real-time cross-section monitoring feature data and combining it with advanced computational fluid dynamics (CFD) technology, a sophisticated three-dimensional sediment flow field network model is constructed. This model can not only reflect the overall water flow movement state of the river channel, but also depict the complex processes of sediment particle transport, suspension, and sedimentation in the water flow. Compared with traditional empirical formulas or simplified models, the three-dimensional flow field model can more accurately simulate the actual situation of river channel sediment movement, especially in river sections with complex terrain and variable water flow, where its advantages are more obvious. The system simulates the movement trajectories of a large number of sediment particles under the action of water flow, and then generates the spatiotemporal distribution data of sediment migration. This simulation can understand the sedimentation and scouring process of the river channel, and can also predict the evolution trend of the river channel in the future. By analyzing the movement trajectory and deposition location of sediment particles, areas prone to sedimentation or scouring can be accurately identified, providing important reference information for river management and waterway maintenance. Based on the spatiotemporal distribution data of sediment migration, the system can automatically identify high-risk areas for sedimentation and scouring, and upload this information to the cloud platform in real time through edge computing nodes, triggering abnormal event alarms.This active warning mechanism changes the traditional passive response mode of water conservancy monitoring, achieving real-time monitoring and risk warning of river sediment changes. The application of the cloud platform enables managers to remotely grasp the real-time situation of the river and take timely countermeasures, such as adjusting the operation mode of water conservancy projects, dredging waterways, strengthening dikes, etc., thus effectively ensuring the flood discharge safety and navigation capacity of the river. Therefore, a water conservancy perception system based on edge computing of the present invention deploys high-definition cameras, acoustic Doppler current profilers (ADCPs), and lidar scanners at key river sections to construct a multi-source heterogeneous river water conservancy perception network, achieving all-round perception of water flow, sediment, and riverbed topography. Using edge computing nodes to perform real-time time synchronization and spatial registration on the collected data, extracting water conservancy monitoring features, further combining computational fluid dynamics (CFD) technology to construct a three-dimensional sediment flow field network model, simulating the sediment migration process, automatically identifying sedimentation and erosion areas, and uploading warning information to the cloud platform in real time through edge computing nodes, realizing real-time monitoring and warning of river sediment changes, and effectively improving the intelligent level of river management. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic diagram of the module process of the water conservancy perception system based on edge computing of the present invention;

[0066] Figure 2 is Figure 1 a detailed implementation process schematic diagram of the sediment migration simulation module in

[0067] Figure 3 is Figure 1 a detailed implementation process schematic diagram of the sedimentation and erosion warning module in

[0068] The realization, functional characteristics, and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art within the scope of the present invention without creative efforts belong to the scope of protection of the present invention.

[0070] In addition, the attached drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that although terms such as "first" and "second" may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0072] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a water conservancy perception system based on edge computing, including the following modules:

[0073] The river channel edge perception module includes a high-definition camera, an acoustic Doppler current profiler, and a lidar scanner, and is used to connect edge computing nodes to the high-definition camera, the acoustic Doppler current profiler, and the lidar scanner to construct a river channel water conservancy perception network; collect real-time water conservancy monitoring data according to the river channel water conservancy perception network to obtain river channel water conservancy perception data;

[0074] The water conservancy feature analysis module is used to perform time synchronization and spatial registration on the river channel water conservancy perception data to obtain spatio-temporal river channel perception data; perform water conservancy monitoring feature analysis according to the spatio-temporal river channel perception data to obtain real-time cross-section monitoring feature data; perform three-dimensional flow field model processing according to the real-time cross-section monitoring feature data to obtain a three-dimensional sediment flow field network model;

[0075] The sediment transport simulation module is used to perform particle flow field simulation on the three-dimensional sediment flow field network model to generate particle trajectory data; perform sediment transport analysis according to the particle trajectory data to generate sediment transport spatio-temporal distribution data;

[0076] The siltation and scouring warning module is used to identify siltation and scouring areas according to the sediment transport spatio-temporal distribution data to obtain siltation and scouring area data; upload the siltation and scouring area data to the cloud platform through the edge computing node for abnormal event alarm to obtain river channel cross-section monitoring data.

[0077] In an embodiment of the present invention, the water conservancy perception system based on edge computing includes the following modules:

[0078] S1: River channel edge perception module, including high-definition camera, acoustic Doppler current profiler and lidar scanner, used to connect the high-definition camera, acoustic Doppler current profiler and lidar scanner to edge computing nodes, build a river channel water conservancy perception network; collect real-time water conservancy monitoring data according to the river channel water conservancy perception network to obtain river channel water conservancy perception data;

[0079] In an embodiment of the present invention, sensing equipment is installed at the key section according to the river channel DEM data and key section marking results obtained in the early stage. The high-definition camera is fixed on a customized waterproof bracket, and the bracket is fixed to the riverbed or embedded parts by expansion bolts to ensure that the camera is stable and the lens is facing the center of the river. The acoustic Doppler current profiler (ADCP) is installed in a buoy style. The buoy is fixed to a predetermined position on the riverbed by an anchor chain, and the ADCP probe is facing downward to ensure that the complete flow profile is measured. The lidar scanner (such as RIEGL VZ-400i or FARO Focus S70) is installed at a commanding height on the river bank (such as a bridge pier or a special tower). By adjusting the pitch angle and azimuth angle of the scanner, ensure that the laser beam covers the entire key section and its surrounding area. After the installation is completed, the edge computing node is connected. An edge computing node (for example, an Advantech MIC-7700 industrial computer or an industrial computer with similar configuration) is set up near each key section. The node is equipped with an Intel Core i7 processor, 16GB memory, a 512GB solid-state drive, and an Ubuntu 20.04 operating system. The camera is connected to the PoE (Power over Ethernet) interface of the edge computing node via a Gigabit Ethernet cable to transmit real-time video streams. The ADCP is connected to the serial-to-Ethernet module of the edge computing node via an RS-485 serial cable to transmit data such as flow rate and water depth. The lidar scanner is connected to the edge computing node via a Gigabit Ethernet cable to transmit point cloud data. The edge computing nodes are connected by optical fiber to form a local area network. At the same time, each edge computing node is connected to the Internet through a 4G / 5G wireless router (for example, Huawei AR502H or an industrial router with similar functions) to achieve data interaction with the cloud platform. After the network is built, data collection is started. The high-definition camera shoots 1080P video encoded in H.264 at a rate of 25 frames per second. ADCP measures velocity profiles at a frequency of 1 Hz, and each profile contains velocity data for 20 cells. LiDAR scanners scan the river section once an hour, generating point cloud data containing millions of points.

[0080] S2: A water conservancy feature analysis module, which is used to perform time synchronization and spatial registration on the river channel water conservancy perception data to obtain spatio-temporal river channel perception data; perform water conservancy monitoring feature analysis based on the spatio-temporal river channel perception data to obtain real-time cross-section monitoring feature data; perform three-dimensional flow field model processing based on the real-time cross-section monitoring feature data to obtain a three-dimensional sediment flow field network model.

[0081] In the embodiment of the present invention, the received data is subjected to time synchronization and spatial registration. All data is based on GPS time for time synchronization. For data with different sampling frequencies, a linear interpolation method is used to unify to one data point per minute. In terms of spatial registration, the camera images are geometrically corrected through the camera's internal and external parameters (obtained through calibration), and the pixel coordinates are converted into WGS84 geographic coordinates. The ADCP and lidar data directly use their own GPS positioning information. Data preprocessing is performed on the edge computing node. The camera video stream is decoded by H.264 hardware, and image enhancement (such as histogram equalization) and denoising (such as median filtering) are performed using the OpenCV library. Bad values of the ADCP data are removed (according to the signal-to-noise ratio threshold), and coordinate conversion is performed (converting the instrument coordinate system to the geographic coordinate system). The lidar point cloud data is filtered (such as statistical filtering) to remove noise points. The preprocessed data is classified according to the data type to form cross-section water body image data (JPEG format), cross-section flow velocity profile data (CSV format), and cross-section riverbed terrain data (LAS format). The position of the water surface line is extracted using image processing algorithms (such as Canny edge detection). Parameters such as cross-section average velocity, maximum velocity, and flow rate are calculated using the ADCP data. Parameters such as cross-section area, wetted perimeter, and hydraulic radius are calculated using the lidar point cloud data. These characteristic parameters are stored in JSON format to form real-time cross-section monitoring feature data. The preprocessed lidar point cloud data is used to construct a three-dimensional model of the river channel. CloudCompare software is used for point cloud stitching, registration, and triangulation to generate a three-dimensional model in STL format. The real-time cross-section monitoring feature data (such as flow velocity and water level) is combined with the three-dimensional model, and CFD simulation is performed using OpenFOAM software to obtain a three-dimensional sediment flow field network model.

[0082] S3: A sediment transport simulation module, which is used to perform particle flow field simulation on the three-dimensional sediment flow field network model to generate particle trajectory data; perform sediment transport analysis based on the particle trajectory data to generate sediment transport spatio-temporal distribution data.

[0083] In the embodiments of the present invention, ParaView or other software that supports the VTK format is used to read the three-dimensional sediment flow field network model, which is usually an unstructured grid and contains data such as node coordinates, element connection relationships, flow velocities, and sediment concentrations at each node. Calculate the volume of each grid cell (e.g., tetrahedron or hexahedron). The volume calculation formula depends on the type of grid cell. For a tetrahedron cell, the formula V=(1 / 6) |(a - d)·((b - d)×(c - d))|, where a, b, c, and d are vertex coordinates. According to the actual monitoring section position, mark the corresponding grid nodes or elements in the model. For example, if there are ADCPs and water level gauges at the center point and near both banks of a certain section, find the grid nodes closest to these positions in the model and mark them. Set virtual particle release positions near the marked points. For example, release points can be set every 1 meter along the section direction 10 meters upstream of the marked point, and release points can be set every 0.5 meter in the vertical direction for each release point. Record the three-dimensional coordinates of each release point. According to the cross-section sediment concentration distribution data obtained by the hydraulic characteristics analysis module, determine the number of particles at each release position. Assuming a total of 10,000 virtual particles are released, normalize the sediment concentration of the grid cell where each release position is located, and then multiply the total number of particles by the normalized concentration to obtain the number of particles at that release position. Use OpenFOAM or other CFD software that supports particle tracking to perform Lagrangian particle tracking. Each particle moves according to the flow velocity at its location, while considering the sediment settling velocity (calculated based on the particle size - settling velocity relationship) and random diffusion (simulated by adding random displacements). Record the trajectory of each particle, including the position and velocity at each time step.

[0084] S4: The sediment deposition and erosion warning module is used to identify sediment deposition and erosion areas based on the spatio-temporal distribution data of sediment migration, and obtain sediment deposition and erosion area data; upload the sediment deposition and erosion area data to the cloud platform through the edge computing node for abnormal event alarm, and obtain the river cross-section monitoring data.

[0085] In the embodiments of the present invention, according to the particle trajectory data, the net sediment transport volume of each grid cell is calculated. The number of particles entering and leaving the grid cell within each time step is counted, and the net transport volume is calculated based on the theoretical sediment-carrying capacity of each particle (the initial value is determined according to the total sediment volume and the total number of particles, and is adjusted subsequently according to the flux). According to the net sediment transport volume and the preset time step (such as 1 hour), the change in the riverbed elevation of each grid cell is calculated. The net transport volume is divided by the bulk density and the bottom area of the grid cell to obtain the change in elevation. The initial river channel elevation data (from lidar scanning) is superimposed with the change in elevation to obtain the new riverbed elevation. The new riverbed elevation is compared with the preset scouring threshold (such as 0.5 m) and the silting threshold (such as 0.3 m), and the grid cells exceeding the limit are marked. Using OpenCV or other image processing libraries, connected component analysis is performed on the grid cells exceeding the limit to identify continuous silting or scouring areas, and the area of each area is calculated. According to the real-time cross-section monitoring characteristic data (such as the flow velocity and bottom shear stress measured by ADCP), the scouring and silting intensity of each grid cell is calculated. For example, the bottom shear stress can be directly used as an index of the scouring and silting intensity. Finally, warning rules are set, such as: (1) there are scouring or silting areas exceeding the limit with an area greater than 100 square meters; (2) the average scouring and silting intensity within the area exceeding the limit is greater than 0.1 Pa; (3) the duration exceeds 6 hours. If any two of the above conditions are met, it is determined that a warning event has occurred. The edge computing node sends the warning information (including the area location, area, scouring and silting intensity, etc.) to the cloud platform through the 4G / 5G network, and the cloud platform triggers an alarm mechanism (such as sending a text message notification) and stores the data in the database.

[0086] Preferably, the river channel edge perception module includes the following functions:

[0087] Obtain the target river channel elevation terrain data;

[0088] Mark the key cross-sections of the target river channel elevation terrain data to generate the key cross-section position data;

[0089] Install a high-definition camera, an acoustic Doppler current profiler, and a lidar scanner at the key cross-sections of the river channel according to the key cross-section position data to obtain the water conservancy perception device layout data;

[0090] Connect the high-definition camera, the acoustic Doppler current profiler, and the lidar scanner to the edge computing node based on the water conservancy perception device layout data to construct a river channel water conservancy perception network;

[0091] Collect real-time water conservancy monitoring data according to the river channel water conservancy perception network to obtain the river channel water conservancy perception data.

[0092] In the embodiments of the present invention, the unmanned aerial vehicle (UAV) flies along a pre-planned route. The lidar scanner emits laser pulses and receives the reflected echoes. By calculating the round-trip time difference of the laser, the three-dimensional coordinates (X, Y, Z) of each sampling point on the ground surface are obtained. During the aerial survey process, the UAV needs to be equipped with a real-time kinematic (RTK) or network RTK (NRTK) device. By receiving the differential correction signals from the ground base station, centimeter-level positioning accuracy is achieved. The acquired original lidar point cloud data is filtered to remove non-ground points such as vegetation and buildings, and the ground points reflecting the river channel topography are retained. Then, the triangulation method (TIN) is used to triangulate the filtered ground points to construct an irregular triangular network. Through an interpolation algorithm, such as Kriging interpolation, the irregular triangular network is converted into a regular grid to generate elevation raster data, that is, the target river channel elevation terrain data. The water flow direction of the river channel is analyzed to determine the main streamline of the river channel. Along the main streamline, cross-section lines are set at fixed distance intervals (for example, every 50 meters) or in areas where the river channel morphology changes significantly (such as where the river channel widens, narrows, or bends). To ensure that the cross-section lines are perpendicular to the water flow direction, it is necessary to use hydrological analysis software to calculate the average flow direction angle of each cross-section and adjust the direction of the cross-section line to be perpendicular to the average flow direction angle. Cross-section lines must also be set at important hydrological control points (such as bridges, sluices, and confluence inlets). Each cross-section line is numbered, and the geographical coordinates (latitude and longitude) at both ends of the cross-section line, as well as all elevation point data on the cross-section line, are recorded. The selection criteria for key cross-sections include: the cross-section morphology is representative (such as U-shaped, V-shaped) and can reflect the main hydraulic characteristics of the river channel; the cross-section location is near the river channel control nodes (such as reservoirs, bridges, and dangerous sections); the cross-section location is convenient for the installation and maintenance of water conservancy sensing devices. At each key cross-section, the device installation plan is determined according to the cross-section morphology and water depth conditions. The high-definition camera is installed in a customized waterproof housing and fixed to the river bottom or the bank slope through a bracket, with the lens facing the center of the river channel to ensure clear underwater images are captured. The acoustic Doppler current profiler (ADCP) is usually installed on a ship or a buoy. The shipborne ADCP is fixed to the bottom of the survey ship and measures the cross-section velocity distribution by traversing; the buoy-mounted ADCP is fixed to the buoy and anchored to the river bottom through an anchor chain. The lidar scanner is installed at a high position on the river bank, such as on the top of a bridge or a special tower, and the scanning range covers the entire key cross-section and its surrounding area. During the installation process, information such as the model, serial number, installation location (latitude, longitude, elevation), and installation time of each device is recorded, and this information is associated with the key cross-section number to form the data of the layout of water conservancy sensing devices. An edge computing node is set near each key cross-section. The edge computing node selects an industrial-grade embedded computer, which has powerful computing capabilities, rich interfaces, and good environmental adaptability. The high-definition camera, acoustic Doppler current profiler, and lidar scanner are connected to the corresponding edge computing nodes through a wired or wireless network (such as 4G / 5G, optical fiber).The high-definition camera is connected to the edge computing node through an Ethernet interface or an HDMI interface to transmit real-time video streams. The acoustic Doppler current profiler is connected to the edge computing node through an RS-232 or RS-485 serial port to transmit data such as flow velocity and water depth. The lidar scanner is connected to the edge computing node through an Ethernet interface to transmit point cloud data. After the river channel water conservancy sensing network is constructed, each sensor collects data according to the preset frequency and working mode. The high-definition camera continuously shoots underwater videos to record information such as water flow status, riverbed morphology, and suspended solids. The acoustic Doppler current profiler continuously measures the water flow velocity and water depth to obtain cross-sectional flow velocity distribution data. The lidar scanner periodically scans the river channel cross-section and the surrounding terrain to obtain high-precision point cloud data for monitoring water level changes, bank slope stability, etc. The edge computing node receives and processes the data collected by the sensors in real time, and extracts key information such as average flow velocity, maximum flow velocity, water level, and water surface line.

[0093] Preferably, the marking of key river channel sections for the target river channel elevation terrain data includes:

[0094] Extracting the center line of the river channel from the target river channel elevation terrain data and identifying the left and right river bank lines of the river channel to obtain river channel geometric constraint data;

[0095] Based on the river channel geometric constraint data, perform cross-section division perpendicular to the center line of the river channel using a preset equal-spacing threshold to obtain river channel cross-section data;

[0096] Perform spatial superposition on the river channel cross-section data through the target river channel elevation terrain data to generate river channel cross-section elevation data;

[0097] Perform cross-section morphology analysis based on the river channel cross-section elevation data to obtain cross-section geometric morphology parameters;

[0098] Calculate the cross-section morphology coefficient based on the cross-section geometric morphology parameters to generate the cross-section morphology coefficient;

[0099] Based on a preset key cross-section identification threshold, screen the river channel cross-section data through the cross-section morphology coefficient to generate key cross-section position data.

[0100] In the embodiments of the present invention, based on the acquired Digital Elevation Model (DEM), the DEM is processed by filling depressions to eliminate the influence of depressions on water flow simulation. Then, the flow direction of each grid cell is calculated, that is, which adjacent cell among the eight adjacent cells the water flow from this cell flows to. The D8 algorithm is used for flow direction calculation, that is, according to the elevation difference between each cell and its eight adjacent cells, the direction of the maximum slope drop is determined as the flow direction. Next, the flow accumulation is calculated, that is, the area of the upstream catchment area of each grid cell. The grid cell with a high flow accumulation value represents the location where water flow converges. Finally, a threshold is set according to the flow accumulation value. For example, the area where the flow accumulation value is greater than 1000 grid cells is defined as the river channel. By connecting these grid cells, a continuous vector line, that is, the center line of the river channel, is formed. For the identification of the river bank line, the generated center line of the river channel is extended to form buffer zones with a fixed distance on both sides. Using the DEM data, by comparing the change rate or gradient of the DEM elevation values within the buffer zone, an elevation gradient threshold is set, and the positions above this threshold are identified as the points on the river bank line. Connecting these points in sequence forms two river bank lines on the left and right. The center line of the river channel and the left and right river bank lines together constitute the geometric constraint data of the river channel. Based on the extracted center line of the river channel, cross-section lines are generated along the center line according to a preset equal-spacing threshold. For example, if the preset equal-spacing threshold is 50 meters, a cross-section line perpendicular to the center line is generated every 50 meters. The perpendicular relationship is achieved by calculating the tangent direction of each segment point on the center line, and then generating a straight line segment perpendicular to the tangent direction at this point. The length of the straight line segment needs to be greater than the width of the river channel to ensure intersection with the left and right river bank lines. In practical applications, since the river channel is not completely regular, simple equal-spacing division will result in the absence of cross-sections at some key positions. Therefore, it is allowed to manually add or adjust cross-section lines on the basis of equal-spacing division. For example, add cross-section lines at sharp bends or positions with obvious hydraulic structures in the river channel. Each generated cross-section line records the coordinates of its starting point and ending point, as well as the intersection coordinates with the center line. These information constitute the river channel cross-section data. The intersection points of each cross-section line and the DEM are obtained, and the elevation values of these intersection points are extracted. For each cross-section line, in the order from the left bank to the right bank (or vice versa), the intersection points and their corresponding elevation values are organized into an ordered sequence. This sequence describes the elevation change on the cross-section. Each point in the sequence contains X and Y coordinates (planar position) and Z coordinate (elevation value). Using the trapezoidal rule or Simpson's rule, the cross-section elevation data is integrated to obtain the cross-section wetted area. Then, the wetted perimeter is calculated, that is, the perimeter where the water flow contacts the river bed. By accumulating the distances between adjacent points in the cross-section elevation data, the length of the wetted perimeter is obtained. Next, the hydraulic radius is calculated, that is, the ratio of the wetted area to the wetted perimeter. The hydraulic radius is an important parameter reflecting the hydraulic efficiency of the river channel. In addition, parameters such as the maximum water depth, average water depth, and cross-section width can also be calculated. The following formula is used to calculate the cross-section shape factor: Shape factor = Wetted perimeter / (2 sqrt(cross-sectional area)). The larger the shape coefficient, the more irregular the cross-sectional shape. Calculate the width-depth ratio of the cross-section, which reflects the width of the cross-section. The width-depth ratio of the cross-section can be calculated using the following formula: width-depth ratio = cross-sectional width / average cross-sectional water depth. Among them, the cross-sectional width refers to the width of the river channel at the cross-section, and the average cross-sectional water depth refers to the cross-sectional area divided by the cross-sectional width. Calculate the hydraulic efficiency of the cross-section, which reflects the water flow transportation capacity of the cross-section. The larger the hydraulic radius and the smaller the roughness coefficient, the higher the hydraulic efficiency. The hydraulic efficiency of the cross-section can be calculated using the following formula: hydraulic efficiency = hydraulic radius / channel roughness coefficient. Associate the calculated morphological coefficients such as the cross-sectional shape coefficient, width-depth ratio of the cross-section, and hydraulic efficiency of the cross-section with the corresponding cross-section numbers to form cross-sectional morphological coefficients. For the ranges of the cross-sectional shape coefficient, width-depth ratio of the cross-section, and hydraulic efficiency morphological coefficients. For example, set the shape coefficient threshold to be greater than 1.5, the width-depth ratio threshold to be greater than 10, and the hydraulic efficiency threshold to be greater than 0.5. For each cross-section, determine whether its cross-sectional morphological coefficients meet the set threshold conditions. If all the morphological coefficients of a cross-section meet the set threshold conditions, then the cross-section is determined as a key cross-section. Store the geometric shape and geographical location information of the key cross-section as vector data and associate it with the key cross-section number to form key cross-section location data.

[0101] Preferably, the water conservancy feature analysis module includes the following functions:

[0102] Synchronize the time and register the space of the river channel water conservancy perception data to obtain spatio-temporal river channel perception data;

[0103] Transmit the spatio-temporal river channel perception data to the edge computing node and perform data preprocessing to generate water conservancy monitoring data; among them, the water conservancy monitoring data includes cross-sectional water body image data, cross-sectional flow velocity profile data, and cross-sectional riverbed terrain data;

[0104] Perform water conservancy monitoring feature analysis based on the water conservancy monitoring data to obtain real-time cross-sectional monitoring feature data;

[0105] Construct a three-dimensional space network based on the target river channel elevation terrain data to generate a three-dimensional river channel space model;

[0106] Perform three-dimensional flow field model processing on the three-dimensional river channel space model through the real-time cross-sectional monitoring feature data to obtain a three-dimensional sediment flow field network model.

[0107] In the embodiments of the present invention, the data from different sensors are time-synchronized. Since different sensors use different clocks or there is clock drift, it is necessary to calibrate the timestamps of all data to a unified time reference. The clock of the central server is selected as the time reference. Each edge computing node periodically synchronizes time with the central server to obtain the current standard time. When uploading data, the edge computing node corrects the timestamp of the local data with the standard time to ensure that the timestamps of all data are based on the same time reference. Then, it is necessary to perform spatial registration on the data from different locations. Using the device geographical coordinates recorded in the data of the water conservancy sensing device layout, the data collected by each sensor is associated with the corresponding geographical location. Using the spatial coordinate conversion function of GIS software, all data is converted to a unified geographical coordinate system (such as the WGS84 coordinate system). The time-synchronized data and the spatially registered data are integrated to form spatio-temporal river channel sensing data. The spatio-temporal river channel sensing data is transmitted to the corresponding edge computing node through a wired or wireless network (such as 4G / 5G, optical fiber). After receiving the data, the edge computing node first performs data format conversion, converting the data of different sensors into a unified format, such as JSON or CSV. Then, data cleaning is performed to remove outliers and incorrect data. For example, for flow velocity data, a reasonable range is set, and the data outside the range is considered an outlier. For image data, the noise and interference in the image are detected and removed. Then, data compression is performed to reduce the data volume and improve the transmission and storage efficiency. For example, for video data, H.264 or H.265 encoding is used for compression. For flow velocity profile data and riverbed terrain data, the data structure is optimized, such as converting a two-dimensional array into a one-dimensional array. The preprocessed data is classified according to the data type to form cross-section water body image data (processed video frames), cross-section flow velocity profile data (two-dimensional flow velocity matrix), and cross-section riverbed terrain data (point cloud or raster data), collectively referred to as water conservancy monitoring data. For the cross-section water body image data, image processing algorithms are used to analyze the characteristics of the water body such as color and texture, and evaluate water quality indicators such as turbidity and transparency of the water body. Floating objects in the water body image are detected, the types and quantities of the floating objects are identified, and the degree of river channel pollution is evaluated. For the cross-section flow velocity profile data, the distribution of the flow velocity is analyzed, and hydrological parameters such as average flow velocity, maximum flow velocity, and flow velocity gradient are calculated. The change trend of the flow rate is analyzed to evaluate the change of the flow rate of the river channel. For the cross-section riverbed terrain data, the undulation change of the riverbed is analyzed, and terrain parameters such as average elevation and standard deviation of the riverbed are calculated. The scouring and silting conditions of the riverbed are analyzed to evaluate the stability of the river channel. The information such as cross-section water quality indicators, hydrological parameters, and terrain parameters obtained from the analysis is integrated to form real-time cross-section monitoring characteristic data. The elevation terrain data is meshed, and the river channel area is divided into a series of three-dimensional grid cells. The size of the grid cells depends on the data accuracy and computing resources.Then, triangulate each grid cell and divide the grid cell into a series of triangular patches. The triangular patches can better approximate the complex surface of the river channel. Use the triangular grid method (TIN) to triangulate the elevation data and construct an irregular triangular network. Optimize the irregular triangular network, such as Delaunay triangulation, to ensure the quality of the triangular patches. Connect all the triangular patches to form a three-dimensional grid model. To improve the visualization effect of the model, texture mapping can be performed on the model, mapping the elevation values to the surface color of the model. The generated three-dimensional grid model serves as the three-dimensional space model of the river channel. Interpolate the cross-section monitoring data onto the three-dimensional space grid. For example, interpolate the cross-section velocity profile data onto the corresponding cross-section in the three-dimensional model to obtain the velocity values at each grid node. The interpolation method can use Kriging interpolation, inverse distance weighting interpolation, or other spatial interpolation methods. Then, use computational fluid dynamics (CFD) methods, such as the finite volume method or the finite element method, to solve the three-dimensional Navier-Stokes equations and simulate the water flow movement in the river channel. The CFD simulation requires setting boundary conditions, such as the inlet velocity, outlet water level, riverbed roughness, etc. These boundary conditions can be obtained from real-time monitoring data. For sediment movement, use sediment transport equations, such as the Meyer-Peter & Müller formula or the Engelund-Hansen formula, to calculate the sediment transport rate. Couple the sediment transport rate with the water flow field to simulate the erosion and deposition processes of sediment. Finally, obtain the three-dimensional sediment flow field network model.

[0108] Preferably, the water conservancy monitoring feature analysis includes:

[0109] Perform sediment particle texture recognition on the cross-section water body image data to obtain sediment particle texture data;

[0110] Conduct particle size statistics based on the sediment particle texture data and calculate the particle size mean value to generate real-time sediment particle size data;

[0111] Fit the near-bottom velocity distribution curve for the cross-section velocity profile data to obtain near-bottom velocity distribution curve data;

[0112] Calculate the riverbed bottom shear stress based on the cross-section riverbed terrain data using the near-bottom velocity distribution curve data to generate bottom shear stress data;

[0113] Estimate the cross-section real-time concentration based on the cross-section velocity profile data and the bottom shear stress data to generate cross-section sediment concentration distribution data;

[0114] Integrate the real-time sediment particle size data, cross-section sediment concentration distribution data, and bottom shear stress data to generate real-time cross-section monitoring feature data.

[0115] In the embodiments of the present invention, preprocessing is performed on the cross-sectional water body image data, including operations such as image enhancement and denoising to improve the image quality. Image segmentation technology is adopted, such as the segmentation method based on threshold, to separate the sediment particles in the image from the background water body. A threshold is set, and the pixel points in the image with gray values higher than the threshold are determined as sediment particles, and the pixel points lower than the threshold are determined as the background water body. In order to improve the segmentation accuracy, morphological operations, such as opening operation and closing operation, are used to optimize the segmentation result and remove small isolated regions and connected broken regions. For the segmented sediment particles, their texture features are extracted. The texture features can reflect information such as the surface roughness and directionality of the sediment particles. The gray-level co-occurrence matrix (GLCM) method can be used to extract the texture features. Based on the sediment particle texture data, the number of sediment particles with different particle sizes is counted, and the average particle size of the sediment particles is calculated. Using image processing algorithms, such as edge detection algorithms, edge detection is performed on the sediment particles to extract the boundaries of the sediment particles. According to the boundaries of the sediment particles, the area and perimeter of the sediment particles are calculated. Using the area and perimeter, the particle size of the sediment particles is estimated. The following formula can be used to estimate the particle size of the sediment particles: particle size = sqrt(4 × area / pi). The sediment particles are classified according to the particle size, such as being divided into different particle size groups such as fine sand, medium sand, and coarse sand. The number of sediment particles in each particle size group is counted. The average particle size of the sediment particles is calculated. The following formula can be used to calculate the average particle size: average particle size = (∑(particle size × number)) / ∑ number. Where the particle size refers to the particle size of each particle size group, and the number refers to the number of sediment particles in each particle size group. The calculated average particle size is used as the real-time sediment particle size data. The flow velocity data within a certain height range from the bottom of the riverbed is selected as the near-bottom flow velocity data. The flow velocity data within 0.1 meter from the bottom of the riverbed can be selected. The logarithmic velocity formula is used to fit the near-bottom flow velocity data. The logarithmic velocity formula describes the variation law of the flow velocity with height in the turbulent boundary layer: u = (u / k) ln(z / z0). Where u refers to the flow velocity at a height z from the bottom of the riverbed, is the friction velocity, k is the von Kármán constant (usually taken as 0.4), and z0 is the roughness height. The least squares method is used to fit the logarithmic velocity formula to obtain the values of the friction velocity and the roughness height z0. According to the obtained friction velocity and roughness height from the fitting, a near-bottom flow velocity distribution curve is generated. The following formula is used to calculate the shear stress at the bottom of the riverbed: τ = ρ ^2. Where τ refers to the shear stress at the bottom of the riverbed, ρ refers to the density of water, Refers to the friction velocity. The friction velocity can be obtained from the fitting results of the near-bottom flow velocity distribution curve. Riverbed terrain data can be used to calculate the average slope of the riverbed. The slope can affect the magnitude of the shear stress at the riverbed bottom. The calculated shear stress at the riverbed bottom is associated with its corresponding cross-section position information to form bottom shear stress data. The Rouse formula can be used to estimate the sediment concentration distribution. The Rouse formula describes the variation law of the suspended sediment concentration with height: c / ca = ((H - z) / z za / (H - za))^Z. Where c refers to the sediment concentration at a height z from the riverbed bottom, ca refers to the sediment concentration at the reference height za, H refers to the water depth, and Z refers to the Rouse number. The Rouse number can reflect the suspension ability of sediment, and its calculation formula is: Z = ws / (k ). Where ws refers to the sediment settling velocity, and k refers to the von Karman constant (usually taken as 0.4). Refers to the friction velocity. The real-time sediment particle size data, cross-section sediment concentration distribution data, and bottom shear stress data are associated with their corresponding cross-section position information and time information to form a comprehensive real-time cross-section monitoring characteristic data.

[0116] Preferably, the cross-section real-time concentration estimation includes:

[0117] Perform echo intensity correction based on the cross-section flow velocity profile data, and calculate the reference concentration of suspended sediment to generate reference concentration data of suspended sediment;

[0118] Query the sediment settling velocity for the real-time sediment particle size data through a preset sediment particle size-settling velocity relationship database to obtain sediment settling velocity data;

[0119] Calculate the sediment incipient motion probability based on the sediment settling velocity data and the bottom shear stress data to generate sediment incipient motion probability data;

[0120] Estimate the sediment suspension concentration based on the reference concentration data of suspended sediment and the sediment incipient motion probability data, and perform cross-section concentration distribution processing to generate cross-section sediment concentration distribution data.

[0121] In the embodiment of the present invention, in the cross-section flow velocity profile data, a height relatively close to the riverbed bottom is selected as the reference height. It is possible to select a height of 0.05 meters from the riverbed bottom as the reference height. Using the relationship between the echo intensity and the suspended sediment concentration, calculate the suspended sediment concentration at the reference height. The relationship between the echo intensity and the suspended sediment concentration is usually a linear relationship or an exponential relationship, which can be obtained through experimental calibration. The following formula can be used to estimate the suspended sediment concentration: Cref = a Echo + b. Where Cref is the suspended sediment concentration at the reference height, Echo is the echo intensity at the reference height, and a and b are calibration coefficients. The calculated suspended sediment concentration at the reference height is used as the suspended sediment reference concentration data. Using the relationship between sediment particle size and settling velocity, determine the settling velocities of sediments with different particle sizes. Establish a sediment particle size - settling velocity relationship database. This database can contain empirical formulas such as the Rubey formula, Stokes formula, etc., or contain experimental measurement data. The Rubey formula is applicable to calculating the settling velocity of sediments with larger particle sizes, and the Stokes formula is applicable to calculating the settling velocity of sediments with smaller particle sizes. For each particle size value in the real-time sediment particle size data, look up the corresponding settling velocity in the sediment particle size - settling velocity relationship database. If there is no exactly matching particle size value, interpolation methods can be used to estimate the settling velocity. The queried sediment settling velocity is used as the sediment settling velocity data. Calculate the Shields number based on the bottom shear stress data: Shields number = / (( - p) g d), where is the bottom shear stress, is the sediment density, p is the density of water, g is the acceleration due to gravity, and d is the sediment particle size. Then, calculate the particle Reynolds number based on the sediment settling velocity and the friction velocity. Compare the calculated Shields number and particle Reynolds number with the Shields curve. If the calculated point is above the Shields curve, it is considered that sediment incipient motion occurs; if it is below the curve, it is considered that sediment does not incipient motion. To more precisely describe the probability of sediment incipient motion, a probability model can be used, such as P = 1 - exp(-k (Shields number - Shields number_c)), where P is the sediment incipient motion probability, k is an empirical coefficient, and Shields number_c is the critical Shields number. The calculated sediment incipient motion probability is a value between 0 and 1, indicating the likelihood of sediment particle incipient motion under the current conditions. This value is the sediment incipient motion probability data. Use the Rouse formula or its improved form: C(z) = C_a ((h - z) / z a / (h - a))^Z, where C(z) is the sediment concentration at a height z above the riverbed, C_a is the sediment concentration at the reference height a (i.e., the suspended sediment reference concentration), h is the water depth, Z is the Rouse number, Z = ω / (β k ) where ω is the sediment settling velocity, β is a coefficient, and k is the von Kármán constant (usually taken as 0.4). The Rouse formula describes the distribution law of suspended sediment concentration with water depth. During the calculation process, sediment settling velocity data (for calculating Z), bottom shear stress data, and reference suspended sediment concentration data (as C_a) are required. For the near-bottom region, the calculated sediment concentrations are arranged in the vertical and horizontal directions (along the cross-section) to form a two-dimensional array. This array represents the sediment concentration distribution of the entire cross-section.

[0122] Preferably, the three-dimensional flow field model processing of the three-dimensional river channel space model includes:

[0123] Performing three-dimensional coordinate transformation on the cross-section sediment concentration distribution data to generate cross-section concentration position data;

[0124] Interpolating the three-dimensional river channel space model through the cross-section concentration position data to obtain a three-dimensional sediment concentration network model;

[0125] Setting the bottom boundary conditions of the riverbed according to the cross-section riverbed terrain data and the bottom shear stress data to generate bottom boundary condition data;

[0126] Constructing a three-dimensional flow field numerical simulation model based on the bottom boundary condition data and the three-dimensional sediment concentration network model through the Navier-Stokes equation to generate a three-dimensional sediment flow field network model.

[0127] In the embodiments of the present invention, the cross-sectional sediment concentration distribution data is based on a two-dimensional cross-sectional coordinate system (usually the x-z coordinate system, where the x-axis is along the cross-sectional direction and the z-axis is perpendicular to the riverbed). To apply it to a three-dimensional river model, coordinate transformation is required. First, the position and orientation of each two-dimensional cross-section in the three-dimensional model need to be known. This can be determined by the previously generated key cross-section position data and river channel geometric constraint data. For each cross-section, its center point coordinates (latitude and longitude) and orientation (perpendicular to the river channel centerline) are known. Then, each point (x, z) in the two-dimensional cross-sectional coordinate system is transformed into a point (X, Y, Z) in the three-dimensional coordinate system. The transformation formula depends on the specific coordinate system definition and cross-section position. Generally, the transformation can be carried out through the following steps: 1. Translate the origin of the two-dimensional coordinate system to the position of the cross-section center point in the three-dimensional model. 2. Rotate the x-axis of the two-dimensional coordinate system to be consistent with the cross-section direction. 3. Use the z coordinate in the two-dimensional coordinate system as the Z coordinate in the three-dimensional coordinate system. After transformation, each sediment concentration data point corresponds to a three-dimensional coordinate (X, Y, Z), indicating the position of the concentration value in three-dimensional space. Interpolate the existing cross-sectional concentration position data (discrete point data) into the entire three-dimensional river model to obtain a continuous three-dimensional concentration field. According to the cross-sectional riverbed terrain data, determine the geometric shape of the riverbed. This can be achieved by extending the cross-sectional terrain data to the entire three-dimensional model. Then, according to the bottom shear stress data, set the roughness of the riverbed. The roughness can be represented by parameters such as Manning's coefficient, Chezy coefficient, or roughness height. There is a certain relationship between the bottom shear stress and the roughness, which can be transformed according to empirical formulas or measured data. For example, the roughness height z0 can be estimated based on the friction velocity and logarithmic velocity distribution formula. Combine the riverbed geometric shape and roughness parameters to form the bottom boundary condition data. Use the computational fluid dynamics (CFD) method to construct a three-dimensional flow field numerical simulation model based on the Navier-Stokes equation (N-S equation) and sediment transport equation. The Navier-Stokes equation describes the momentum conservation of the fluid, and the sediment transport equation describes the convection and diffusion of sediment. These equations are all partial differential equations and need to be numerically discretized to be solved. Commonly used numerical methods include the finite volume method (FVM), finite difference method (FDM), and finite element method (FEM). Take the three-dimensional sediment concentration network model as the initial condition and the bottom boundary condition data as the boundary condition, and input them into numerical simulation software such as OpenFOAM, ANSYS Fluent, or COMSOL Multiphysics. Set simulation parameters in the software, such as time step, convergence criterion, etc. Then, perform numerical solution. The solution process usually requires a large amount of computing resources and time. After the solution is completed, a three-dimensional flow field is obtained, including information such as velocity, pressure, and sediment concentration at each grid node.

[0128] Preferably, the sediment transport simulation module includes the following functions:

[0129] Calculate the grid cell volume according to the three-dimensional sediment flow field network model to generate grid cell volume data;

[0130] Mark the cross-section monitoring points of the three-dimensional sediment flow field network model and set the virtual particle release positions to obtain virtual particle release position data;

[0131] Allocate the number of particles to the three-dimensional sediment flow field network model based on the cross-section sediment concentration distribution data to obtain virtual particle number data;

[0132] Perform particle flow field simulation on the three-dimensional sediment flow field network model based on the virtual particle release position data and the virtual particle number data, and conduct Lagrangian particle tracking to generate particle trajectory data;

[0133] Conduct sediment transport analysis based on the particle trajectory data to generate sediment transport spatio-temporal distribution data.

[0134] As an example of the present invention, refer to Figure 2 shown, for Figure 1 the detailed implementation process schematic diagram of the sediment transport simulation module in

[0135] S31: Calculate the grid cell volume according to the three-dimensional sediment flow field network model to generate grid cell volume data;

[0136] In the embodiment of the present invention, the three-dimensional sediment flow field network model is usually composed of a large number of three-dimensional grid cells (such as tetrahedrons, hexahedrons, etc.). In order to perform subsequent sediment transport simulation, it is necessary to calculate the volume of each grid cell. The calculation method of the grid cell volume depends on the type of the grid cell. For a tetrahedron cell, the volume V can be calculated by the coordinates of its four vertices: V=(1 / 6) |(a - d)·((b - d) (c - d))|, where a, b, c, d are the coordinates of the four vertices of the tetrahedron, "·" represents the vector dot product, "×" represents the vector cross product, and "||" represents the vector modulus. For a hexahedron cell, it can be decomposed into multiple tetrahedron cells, and then the volumes are calculated and summed respectively. Or, the volume can be directly calculated using the vertex coordinates of the hexahedron cell and the Gaussian integral formula.

[0137] S32: Mark the cross-section monitoring points of the three-dimensional sediment flow field network model and set the virtual particle release positions to obtain virtual particle release position data;

[0138] In the embodiments of the present invention, the Lagrangian particle tracking method is adopted. It is necessary to release virtual particles in the model and track their movement trajectories. First, according to the actual cross-section monitoring positions, the corresponding grid nodes or grid cells are marked in the three-dimensional sediment flow field network model. These marked points represent the actual observation positions and are used to compare with the simulation results. Then, the release positions of the virtual particles are determined. The release positions can be set according to the research purpose and simulation requirements. For example, particles can be evenly released at the cross-section of the river entrance, or concentratedly released in a specific area (such as the bottom of the riverbed or the water surface). The release position can be a point, a line, a surface, or a volume. For each release position, its three-dimensional coordinates (X, Y, Z) are recorded. These coordinate data constitute the virtual particle release position data. The data is stored in the form of a list or an array, and each element represents a release position.

[0139] S33: Allocate the number of particles to the three-dimensional sediment flow field network model through the cross-section sediment concentration distribution data to obtain the virtual particle number data;

[0140] In the embodiments of the present invention, according to the cross-section sediment concentration distribution data, the number of virtual particles released at each release position is determined. The principle of particle number allocation is: the higher the sediment concentration, the more particles are released. This can more realistically reflect the distribution and migration of sediment. The specific allocation method can adopt the following steps: 1. Calculate the sediment concentration of the grid cell where each release position is located. If the release position is a point, the concentration value of the grid cell where the point is located is taken; if the release position is an area, the average concentration value of all grid cells within the area is taken. 2. Normalize the concentration values of all release positions so that their sum is 1. 3. According to the preset total number of particles and the normalized concentration values, calculate the number of particles to be allocated at each release position: Ni = N_total Ci_norm, where Ni is the number of particles at the i-th release position, N_total is the total number of particles, and Ci_norm is the normalized concentration value at the i-th release position. The number of particles calculated for each release position is stored in integer form, forming a one-dimensional array with the same number as the number of release positions, that is, the virtual particle number data.

[0141] S34: Based on the virtual particle release position data and the virtual particle number data, perform particle flow field simulation on the three-dimensional sediment flow field network model and conduct Lagrangian particle tracking to generate particle trajectory data;

[0142] In the embodiments of the present invention, particle tracking simulation is carried out in a three-dimensional sediment flow field network model. Using the Lagrangian method, each virtual particle is regarded as an independent mass point, and its motion trajectory in the flow field is tracked. The motion equation of each particle is: dx / dt = u(x,t), where x is the position vector of the particle, t is the time, and u(x,t) is the flow velocity vector at the position of the particle. The flow velocity vector u(x,t) is obtained from the three-dimensional sediment flow field network model and obtained by spatial interpolation. The motion equation of the particle is solved by a numerical integration method, such as the Euler method, the Runge-Kutta method, etc. The Euler method is relatively simple but has low accuracy; the Runge-Kutta method has high accuracy but a large amount of calculation. In each time step, according to the current position and velocity of the particle, its position in the next time step is calculated. At the same time, the sediment settlement effect is considered. In the vertical direction, a downward settlement velocity ω is applied to the particle, and the value of ω is determined according to the relationship between the sediment particle size and the settlement velocity. In addition, the random diffusion effect of sediment can also be considered. In each time step, a random displacement is applied to the particle to simulate the turbulent diffusion of sediment. The tracking process continues until the particle leaves the simulation area or reaches the preset simulation time. Record the motion trajectory of each particle, including the position coordinates (X, Y, Z) and time at each time step. These data constitute the particle trajectory data. The data is stored in the form of a list or an array, and each element represents the trajectory of a particle.

[0143] S35: Perform sediment transport analysis based on the particle trajectory data to generate sediment transport spatio-temporal distribution data.

[0144] In the embodiments of the present invention, the number of particles in different regions in different time periods is counted to reflect the change of sediment concentration. For example, the change of the number of particles on each cross-section over time can be counted to reflect the sediment transport along the course. Then, parameters such as the average transport velocity and transport distance of the particles are calculated to reflect the transport rate and transport range of the sediment. The average transport velocity can be calculated by the ratio of the displacement of the particle in a period of time to the time. The transport distance can be calculated by accumulating the displacements of the particle in each time step. Then, analyze the spatial distribution characteristics of the particles, such as whether there are aggregation areas, retention areas, etc. This can be achieved by drawing a particle distribution density map or an isogram.

[0145] Preferably, the sediment transport analysis according to the particle trajectory data includes:

[0146] Statistically analyze the average displacement vector of grid particles based on the particle trajectory data to generate grid average displacement data;

[0147] Calculate the sediment transport flux according to the grid average displacement data to generate sediment transport flux data;

[0148] Convert the sediment carrying capacity of particles according to the sediment transport flux data to obtain the theoretical sediment carrying capacity of particles;

[0149] Calculate the sediment transport rate of the three-dimensional sediment flow field network model through the sediment transport flux data to generate sediment transport rate data;

[0150] Integrate the theoretical sediment carrying capacity of particles and the sediment transport rate data in the grid space-time distribution to generate sediment transport space-time distribution data.

[0151] In the embodiments of the present invention, the particle trajectory data is grouped according to grid cells. For each grid cell, all the particles passing through this cell are found. Then, for each particle, the displacement vector within this grid cell is calculated. The displacement vector is defined as the position when the particle leaves the grid cell minus the position when it enters the grid cell. If a particle passes through multiple grid cells within one time step, the displacement vector needs to be decomposed into each grid cell. Then, the displacement vectors of all the particles within the same grid cell are averaged to obtain the average displacement vector of this grid cell. The averaging method can be simple arithmetic averaging or weighted averaging, and the weights can be determined according to the residence time or path length of the particle within this grid cell. The calculated average displacement vector of each grid cell contains three components (in the X, Y, and Z directions), representing the average migration direction and distance of the sediment within this grid cell. For tetrahedral grids, the interface is triangular; for hexahedral grids, the interface is quadrilateral. Then, the area and normal vector of each interface are calculated. The normal vector points to the outside of the interface. Next, for each interface, the dot product of the average displacement vectors of the grid cells on both sides of it is calculated, and then multiplied by the area of the interface. This dot product reflects the velocity component of the sediment passing through this interface. Finally, this velocity component is multiplied by the sediment concentration (which can be obtained from the three-dimensional sediment concentration network model) to get the sediment mass flux passing through this interface. It should be noted that the sediment concentration should be taken as the average value or the upstream value of the grid cells on both sides of the interface. The calculated sediment migration flux of each interface is a scalar, representing the sediment mass passing through this interface per unit time. Since virtual particles are used in the simulation to represent actual sediment particles, a connection between virtual particles and actual sediment needs to be established. One method is to regard each virtual particle as representing a certain mass of sediment. This mass can be determined through the following steps: 1. Calculate the total sediment mass within the entire simulation area. This can be obtained by integrating the three-dimensional sediment concentration network model. 2. Count the total number of virtual particles released in the simulation. 3. Divide the total sediment mass by the total number of particles to get the average mass of sediment represented by each virtual particle. This average mass is the initial value of the theoretical sediment-carrying capacity of the particle. During the simulation process, due to the erosion and deposition of sediment, the sediment mass represented by each particle will change. Therefore, it is necessary to dynamically adjust the sediment-carrying capacity of each particle according to the sediment migration flux data. For example, if a particle passes through an interface where sediment is deposited, its sediment-carrying capacity should increase; if it passes through an interface where sediment is eroded, its sediment-carrying capacity should decrease. The adjustment amplitude is proportional to the sediment migration flux. For each grid cell, calculate the sum of the sediment migration fluxes of all its interfaces. It should be noted that the positive or negative sign of the flux indicates whether the sediment flows into or out of this grid cell. Inflow is positive and outflow is negative. Then, divide the sum of the fluxes by the volume of the grid cell to get the sediment mass change rate per unit volume. This change rate is the sediment migration rate.The calculated sediment transport rate is a scalar, representing the change in sediment mass per unit time and per unit volume. A positive value indicates sediment deposition, while a negative value indicates sediment erosion. The theoretical particle sediment-carrying capacity and sediment transport rate data are associated with the three-dimensional sediment flow field network model to determine the theoretical particle sediment-carrying capacity and sediment transport rate for each grid cell. The theoretical particle sediment-carrying capacity and sediment transport rate data can be used as attributes of the grid cell and stored in the data structure of the grid cell.

[0152] Preferably, the deposition and erosion warning module includes the following functions:

[0153] Calculate the net sediment transport volume of the grid cell based on the sediment transport spatio-temporal distribution data to generate net sediment transport volume data;

[0154] Calculate the change in riverbed elevation of the grid based on the net sediment transport volume data through a preset time step to obtain riverbed elevation change data;

[0155] Overlay the target river channel elevation terrain data with the riverbed elevation change data and compare it with a preset riverbed terrain erosion threshold to obtain deposition and erosion overrun data;

[0156] Identify the deposition and erosion areas based on the deposition and erosion overrun data to obtain deposition and erosion area data;

[0157] Calculate the sediment erosion and deposition intensity based on the real-time cross-section monitoring characteristic data to generate grid cell erosion and deposition intensity data;

[0158] Judge the warning events based on the deposition and erosion overrun data and the grid cell erosion and deposition intensity data, and upload the deposition and erosion area data to the cloud platform through the edge computing node for abnormal event alarm to obtain river channel cross-section monitoring data.

[0159] As an example of the present invention, refer to Figure 3 shown in Figure 1 is a schematic diagram of the detailed implementation process of the deposition and erosion warning module in

[0160] S41: Calculate the net sediment transport volume of the grid cell based on the sediment transport spatio-temporal distribution data to generate net sediment transport volume data;

[0161] In an embodiment of the present invention, a time period is determined, such as a simulation step or a plurality of simulation steps. Then, for each grid cell, the sediment transport rate at all time steps within this time period is multiplied by the time step to obtain the sediment mass change at each time step. Next, the sediment mass changes at all time steps are accumulated to obtain the net sediment transport volume within this time period. If the net transport volume is positive, it indicates sediment deposition within this grid cell; if it is negative, it indicates sediment scouring. The calculated net sediment transport volume for each grid cell is a numerical value, representing the net change in sediment mass within this grid cell during this time period. These numerical values constitute the net sediment transport volume data.

[0162] S42: Calculate the change amount of the grid riverbed elevation through a preset time step based on the net sediment transport volume data to obtain the riverbed elevation change amount data;

[0163] In an embodiment of the present invention, the bulk density ρb of the sediment is determined. The bulk density can be determined through measured data or empirical values. Then, the bottom area of each grid cell is calculated. For a three-dimensional grid, the bottom area refers to the area of the surface where the grid cell contacts the riverbed. For a two-dimensional grid, the bottom area is the area of the grid cell. Next, the net sediment transport volume of each grid cell is divided by the bulk density and the bottom area to obtain the riverbed elevation change amount: Δh = ΔM / (ρb A), where Δh is the riverbed elevation change amount, ΔM is the net sediment transport volume, ρb is the bulk density, and A is the bottom area. The calculated riverbed elevation change amount is a numerical value, representing the change amount of the riverbed elevation of this grid cell during this time period.

[0164] S43: Perform elevation superposition on the target river channel elevation terrain data and the riverbed elevation change amount data, and compare with a preset riverbed terrain scouring threshold to obtain the deposition and scouring overrun data;

[0165] In an embodiment of the present invention, the initial elevation value of each grid cell is added to the corresponding elevation change amount. Then, the new riverbed elevation data is compared with a preset riverbed terrain scouring threshold. The scouring threshold is a preset numerical value, representing the allowable riverbed scouring depth. The setting of the threshold needs to be determined according to the characteristics of the specific river channel and flood control requirements. For each grid cell, if its new riverbed elevation value is lower than the initial elevation value minus the scouring threshold, it is considered that overrun scouring has occurred in this grid cell; if its new riverbed elevation value is higher than the initial elevation value plus the deposition threshold (another preset value), it is considered that overrun deposition has occurred in this grid cell. Mark these overrun grid cells and record their positions and overrun types (scouring or deposition).

[0166] S44: Identify the deposition and scouring areas based on the deposition and scouring overrun data to obtain the deposition and scouring area data;

[0167] In the embodiments of the present invention, based on the obtained siltation and scouring over-limit data, continuous siltation or scouring areas are identified. This can be achieved by using the connected component analysis method in image processing. The grid cells marked as over-limit are regarded as pixels in the image, with a value of 1 (or different values are assigned according to the type of over-limit), and other grid cells are regarded as background pixels with a value of 0. Then, the four-neighborhood or eight-neighborhood connectivity analysis method is used to connect adjacent over-limit grid cells to form connected components. Each connected component represents a siltation area or a scouring area. Information such as the position, area, and shape of each area is recorded. For example, a rectangular frame or a polygon can be used to represent the range of each area, constituting the siltation and scouring area data.

[0168] S45: Calculate the sediment erosion and deposition intensity based on the real-time cross-section monitoring characteristic data to generate the grid cell erosion and deposition intensity data;

[0169] In the embodiments of the present invention, parameters related to the erosion and deposition intensity are extracted from the real-time cross-section monitoring characteristic data, such as water flow velocity, water depth, sediment concentration, bottom shear stress, etc. These parameters can reflect the erosion and deposition ability of the water flow on the riverbed. Then, using empirical formulas or hydrodynamic models, the erosion and deposition intensity of each grid cell is calculated. The erosion and deposition intensity can be expressed as the amount of sediment erosion or deposition per unit area per unit time. Commonly used erosion and deposition intensity calculation formulas include the Einstein formula, the Meyer-Peter Müller formula, etc.

[0170] S46: Judge the early warning events based on the siltation and scouring over-limit data and the grid cell erosion and deposition intensity data, and upload the siltation and scouring area data to the cloud platform through the edge computing node for abnormal event alarm to obtain the river cross-section monitoring data.

[0171] In an embodiment of the present invention, the over-limit data of siltation and scouring and the scouring and silting intensity data of the grid unit are considered to determine whether an early warning event occurs. The judgment criteria of the early warning event can be set according to specific needs. For example, the following criteria can be set: 1. There is an over-limit scouring or silting area, and the area of ​​the area is greater than a certain threshold. 2. The average scouring and silting intensity in the over-limit area is greater than a certain threshold. 3. The duration of the over-limit area is greater than a certain threshold. If one or more of the above criteria are met, it is determined that an early warning event has occurred. Once it is determined that an early warning event has occurred, the edge computing node immediately uploads the siltation and scouring area data (including location, range, over-limit type, scouring and silting intensity, etc.) to the cloud platform through the network (such as 4G / 5G, optical fiber). After the cloud platform receives the data, it triggers an alarm mechanism, such as sending SMS, email or APP notification to relevant personnel. At the same time, the cloud platform can store the data in the database and display it visually, such as marking the siltation and scouring area on the map. These alarm information and visualization data constitute the river section monitoring data, which is used to monitor the river conditions in real time and promptly discover and handle abnormal situations.

[0172] The present application is to build a highly integrated, multi-source heterogeneous river water conservancy perception network by deploying a perception module integrating a high-definition camera, an acoustic Doppler current profiler (ADCP) and a lidar scanner at the edge of the river channel, and connecting them using edge computing nodes. This network can achieve all-round and three-dimensional perception of multiple factors such as river flow, sediment, riverbed topography, etc. The system completes the time synchronization, spatial registration and water conservancy feature extraction of data on the edge side close to the data source, ensuring the temporal consistency of data collected by different sensors. The spatial registration criterion unifies these data into the same geographic coordinate system, thereby obtaining river channel perception data that is consistent in time and space. Based on these data, the system further extracts key characteristic parameters reflecting the state of river flow and sediment movement, providing high-quality input data for constructing a three-dimensional flow field model. The introduction of edge computing greatly reduces the latency and bandwidth requirements of data transmission, improves the efficiency of data processing, and enables the system to respond quickly to changes in river sediment. Especially when dealing with sudden sediment flow events, this low-latency data processing capability can buy valuable time for timely warning and disposal. Based on the spatiotemporal distribution data of sediment migration, the system can automatically identify high-risk areas for siltation and scouring, and upload this information to the cloud platform in real time through edge computing nodes, triggering abnormal event alarms. This active early warning mechanism has changed the passive response mode of traditional water conservancy monitoring, and realized real-time monitoring and risk warning of river sediment changes. The application of the cloud platform enables managers to remotely grasp the real-time status of the river and take timely response measures, such as adjusting the operation mode of water conservancy projects, dredging waterways, and strengthening embankments, thereby effectively ensuring the flood safety and navigation capacity of the river.

[0173] Therefore, in any aspect, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Thus, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0174] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A water conservancy perception system based on edge computing, characterized in that: Includes the following modules: The river channel edge perception module includes a high-definition camera, an acoustic Doppler current profiler and a lidar scanner, which is used to connect the high-definition camera, the acoustic Doppler current profiler and the lidar scanner with edge computing nodes to build a river channel water conservancy perception network; real-time water conservancy monitoring data is collected according to the river channel water conservancy perception network to obtain river channel water conservancy perception data; the river channel edge perception module specifically includes: Obtaining the elevation terrain data of the target river; Mark the key sections of the target river elevation terrain data and generate key section location data; According to the key section location data, high-definition cameras, acoustic Doppler flow profilers and lidar scanners are installed at the key sections of the river to obtain the layout data of water conservancy sensing equipment; Based on the deployment data of water conservancy sensing equipment, edge computing nodes of high-definition cameras, acoustic Doppler current profilers and lidar scanners are connected to build a river water conservancy sensing network; Real-time water conservancy monitoring data collection is carried out according to the river water conservancy sensing network to obtain river water conservancy sensing data; The hydraulic characteristic analysis module is used to synchronize the time and space of the river hydraulic perception data to obtain the spatiotemporal river perception data; perform hydraulic monitoring characteristic analysis based on the spatiotemporal river perception data to obtain the real-time cross-section monitoring characteristic data; perform three-dimensional flow field model processing based on the real-time cross-section monitoring characteristic data to obtain a three-dimensional sediment flow field network model; wherein, the hydraulic characteristic analysis module specifically includes: Perform time synchronization and spatial registration on river water conservancy sensing data to obtain spatiotemporal river sensing data; The spatiotemporal river channel sensing data is transmitted to the edge computing node, and the data is preprocessed to generate water conservancy monitoring data; wherein the water conservancy monitoring data includes cross-sectional water body image data, cross-sectional flow velocity profile data, and cross-sectional riverbed topography data; Water conservancy monitoring feature analysis is performed based on water conservancy monitoring data to obtain real-time cross-section monitoring feature data; wherein, water conservancy monitoring feature analysis includes: Perform sediment particle texture recognition on the cross-sectional water body image data to obtain sediment particle texture data; Perform particle size statistics based on sediment particle texture data and calculate the mean particle size to generate real-time sediment particle size data; Fitting the near-bottom velocity distribution curve to the cross-sectional velocity profile data to obtain the near-bottom velocity distribution curve data; Based on the cross-sectional riverbed topography data and using the near-bottom velocity distribution curve data, the riverbed bottom shear stress is calculated to generate bottom shear stress data; The real-time concentration of the cross section is estimated based on the cross-section velocity profile data and the bottom shear stress data to generate the cross-section sediment concentration distribution data; the real-time concentration estimation of the cross section includes: According to the cross-sectional velocity profile data, the echo intensity is corrected and the suspended sediment reference concentration is calculated to generate the suspended sediment reference concentration data; The sediment settling velocity data is queried by using the preset sediment particle size-sedimentation velocity relationship database to obtain the sediment settling velocity data; Calculate the probability of sediment initiation based on sediment settling velocity data and bottom shear stress data to generate sediment initiation probability data; The sediment suspension concentration is estimated based on the suspended sediment reference concentration data and the sediment initiation probability data, and the cross-sectional concentration distribution is processed to generate the cross-sectional sediment concentration distribution data; Integrate the real-time sediment particle size data, cross-section sediment concentration distribution data and bottom shear stress data into water conservancy monitoring characteristics to generate real-time cross-section monitoring characteristic data; Construct a three-dimensional spatial network based on the target river elevation terrain data to generate a three-dimensional spatial model of the river; The three-dimensional flow field model is processed on the three-dimensional spatial model of the river channel through the real-time cross-section monitoring characteristic data to obtain a three-dimensional sediment flow field network model; The sediment migration simulation module is used to simulate the particle flow field of the three-dimensional sediment flow field network model and generate particle trajectory data; the sediment migration analysis is performed based on the particle trajectory data to generate the sediment migration time and space distribution data; The siltation and scour warning module is used to identify the siltation and scour areas based on the spatiotemporal distribution data of sediment migration and obtain the siltation and scour area data; upload the siltation and scour area data to the cloud platform through the edge computing node to alarm for abnormal events and obtain the river section monitoring data.

2. The water conservancy sensing system based on edge computing according to claim 1 is characterized in that: The marking of key sections of the target river elevation terrain data includes: Extract the centerline of the target river channel from the elevation terrain data and identify the left and right riverbanks to obtain the geometric constraint data of the river channel; Based on the river channel geometric constraint data, the preset equal spacing threshold is used to divide the section perpendicular to the river channel centerline to obtain the river channel section data; The river section data is spatially superimposed through the target river elevation terrain data to generate river section elevation data; Perform cross-sectional morphology analysis based on the river section elevation data to obtain cross-sectional geometric parameters; Calculate the cross-sectional shape coefficient according to the cross-sectional geometric shape parameters to generate the cross-sectional shape coefficient; Based on the preset key section identification threshold, the river section data is screened for key sections through the section morphology coefficient to generate key section location data.

3. The water conservancy sensing system based on edge computing according to claim 1 is characterized in that: The three-dimensional flow field model processing of the three-dimensional spatial model of the river channel includes: Perform cross-section three-dimensional coordinate transformation based on cross-section sediment concentration distribution data to generate cross-section concentration position data; The three-dimensional spatial model of the river channel is interpolated through the cross-section concentration position data to obtain a three-dimensional sediment concentration network model; The bottom boundary conditions of the riverbed are set according to the cross-section riverbed topography data and the bottom shear stress data, and the bottom boundary condition data are generated; Based on the bottom boundary condition data and the three-dimensional sediment concentration network model, a three-dimensional flow field numerical simulation model is constructed through the Navier-Stokes equation to generate a three-dimensional sediment flow field network model.

4. The water conservancy sensing system based on edge computing according to claim 1 is characterized in that: The sediment migration simulation module includes the following functions: Calculate the grid unit volume based on the three-dimensional sediment flow field network model to generate grid unit volume data; Mark the cross-section monitoring points of the three-dimensional sediment flow field network model, set the virtual particle release position, and obtain the virtual particle release position data; The particle number distribution of the three-dimensional sediment flow field network model is carried out through the cross-section sediment concentration distribution data to obtain the virtual particle number data; Based on the virtual particle release position data and virtual particle quantity data, the particle flow field simulation is performed on the three-dimensional sediment flow field network model, and Lagrangian particle tracking is performed to generate particle trajectory data; Sediment migration analysis is performed based on particle trajectory data to generate spatiotemporal distribution data of sediment migration.

5. The water conservancy sensing system based on edge computing according to claim 4 is characterized in that: The sediment migration analysis based on particle trajectory data includes: Perform grid particle average displacement vector statistics based on particle trajectory data to generate grid average displacement data; Calculate the sediment migration flux based on the grid average displacement data to generate sediment migration flux data; The theoretical particle sediment carrying capacity is converted according to the sediment migration flux data to obtain the theoretical particle sediment carrying capacity; The sediment migration rate is calculated for the three-dimensional sediment flow field network model through the sediment migration flux data to generate sediment migration rate data; The theoretical particle sediment carrying capacity and sediment migration rate data are integrated into the grid spatiotemporal distribution to generate the spatiotemporal distribution data of sediment migration.

6. The water conservancy sensing system based on edge computing according to claim 1 is characterized in that: The siltation and scouring early warning module includes the following functions: Calculate the net sediment transport of grid cells based on the temporal and spatial distribution data of sediment migration to generate net sediment transport data; Based on the net sediment transport data, the grid riverbed elevation change is calculated through a preset time step to obtain the riverbed elevation change data; The target river elevation terrain data and the riverbed elevation change data are superimposed, and compared with the preset riverbed terrain scour threshold to obtain the siltation scour excess data; According to the over-limit data of siltation and scour, the siltation and scour area is identified to obtain the siltation and scour area data; Calculate the sediment scouring and silting intensity based on the real-time cross-section monitoring characteristic data to generate grid unit scouring and silting intensity data; Early warning events are judged based on the excessive siltation and scouring data and the grid unit scouring and silting intensity data, and the siltation and scouring area data are uploaded to the cloud platform through the edge computing node for abnormal event alarm to obtain river section monitoring data.

Images