A watershed management method and system based on digital twins

Abstract

This invention discloses a watershed management method and system based on digital twins. The method includes: acquiring BeiDou data, remote sensing data, and IoT data of a hydropower station watershed to construct a watershed database; based on the watershed database, digitally mapping the hydropower station watershed using multiple engines to generate a corresponding digital twin watershed; acquiring watershed services, and simulating these services in the digital twin watershed using algorithms associated with these services. These services include one or more of the following: gate control simulation, regional inundation analysis, watershed geological disaster early warning, and dam stress early warning. This invention processes various sensing data from the hydropower station watershed using multiple engines, achieving accurate and intelligent construction of the digital twin watershed. Simultaneously, by simulating various watershed services in the digital twin watershed using multiple algorithms, it improves the management efficiency and emergency command capabilities of the hydropower station watershed.

Description

Technical Field

[0001] This invention relates to the field of digital twin technology, and in particular to a watershed management method and system based on digital twins. Background Technology

[0002] A digital twin watershed is a digital mapping and intelligent simulation of all elements of a physical watershed (such as a hydropower station watershed), based on spatiotemporal data, with mathematical models as the core and water conservancy knowledge as the driving force. It achieves synchronous simulation operation, virtual-real interaction, and iterative optimization with the physical watershed.

[0003] Current watershed management methods suffer from the following problems: Firstly, there is a lack of watershed sensing data sources, with most data originating from ground sensors and less attention paid to underwater, aerial, and terrestrial data. Furthermore, the ability to process multi-source heterogeneous data is poor, hindering the accurate construction of digital twin watersheds. Secondly, the management methods for watershed operational functions are simplistic, with most functions focused on real-time early warning. For example, patent CN113222283A discloses a flash flood forecasting and early warning method and system based on digital twins. Although this system senses multiple data points of the target watershed, the constructed digital twin watershed may be inaccurate without processing these multiple data points. In addition, this system is only applicable to flash flood forecasting and early warning, resulting in a relatively limited operational function.

[0004] Therefore, how to accurately and intelligently construct digital twin watersheds and effectively manage various watershed operations remains a technical problem that current watershed management methods need to solve. Summary of the Invention

[0005] Therefore, it is necessary to provide a watershed management method and system based on digital twins to address the aforementioned technical problems.

[0006] To achieve the above objectives, the present invention provides a watershed management method based on digital twins, comprising:

[0007] Acquire BeiDou data, remote sensing data, and IoT data from the hydropower station basin to construct a basin database;

[0008] Based on the aforementioned watershed database, the hydropower station watershed is digitally mapped using multiple engines to generate a corresponding digital twin watershed.

[0009] The watershed services are acquired, and the services are simulated in the digital twin watershed using algorithms associated with the watershed services; the watershed services are one or more of the following: gate control simulation, regional inundation analysis, watershed geological disaster early warning, and dam stress early warning.

[0010] Furthermore, this invention also provides a watershed management system based on digital twins, comprising:

[0011] The watershed sensing module is used to acquire BeiDou data, remote sensing data, and IoT data of the hydropower station's watershed to build a watershed database;

[0012] The digital twin module is used to digitally map the hydropower station's watershed based on the watershed database using multiple engines, and generate a corresponding digital twin watershed.

[0013] The business management module is used to acquire watershed business and perform business simulation in the digital twin watershed through the algorithm associated with the watershed business; the watershed business is one or more of the following: gate control pre-simulation, regional inundation analysis, watershed geological disaster early warning, and dam stress early warning.

[0014] The watershed management method and system based on digital twins provided by this invention have the following beneficial effects:

[0015] 1) By acquiring various sensing data of the hydropower station basin, including BeiDou data, remote sensing data and IoT data, we can achieve comprehensive perception of the hydropower station basin in the continuous space of the sky, air, ground and underwater, and provide data support for the construction of digital twin basin;

[0016] 2) Based on multiple engines, process BeiDou data, remote sensing data and IoT data of hydropower station basins to realize the accurate and intelligent construction of digital twin basins and provide technical support for basin operations;

[0017] 3) By using various algorithms related to watershed operations, multiple watershed operations are simulated in the digital twin watershed, which improves the management efficiency and emergency command capabilities of the hydropower station watershed and enhances the watershed display effect. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating a watershed management method based on digital twins in one embodiment of the present invention.

[0020] Figure 2 This is a flowchart illustrating step S20 of a watershed management method based on digital twins in one embodiment of the present invention.

[0021] Figure 3This is a schematic diagram of the structure of a watershed management system based on digital twins in one embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of the structure of a digital twin module of a watershed management system based on digital twins in one embodiment of the present invention. Detailed Implementation

[0023] To make the technical problems, technical solutions, and beneficial effects of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0024] like Figure 1 As shown, an embodiment of the present invention provides a watershed management method based on digital twins, which specifically includes the following steps:

[0025] Step S10: Obtain BeiDou data, remote sensing data, and IoT data for the hydropower station basin to construct a basin database.

[0026] In step S10, the hydropower station's watershed is monitored using BeiDou satellites, remote sensing equipment, and IoT devices to obtain relevant data, including three types of sensing data: BeiDou data, remote sensing data, and IoT data. This data is then processed, summarized, and managed to construct a watershed database. Specifically, the BeiDou data includes BeiDou positioning data, BeiDou short message data, and BeiDou timing data. Remote sensing data includes both the watershed's own geographic information and related geographic information. The watershed's own geographic information refers to the geographic information of the hydropower station's watershed itself, including Tianditu (a national online map platform), digital elevation data, and orthophoto data. Related geographic information includes the geographic information of buildings, equipment, etc., located or deployed within the hydropower station's watershed, including oblique photogrammetry data of hydraulic structures, point cloud data of underwater topography, and BIM (Building Information Modeling) data of key electromechanical equipment. Hydraulic structures include water-retaining structures and spillway structures, while key electromechanical equipment includes gates, turbines and their governors, generators and their excitation systems, and HVAC and fire protection equipment. IoT data includes meteorological data, dam deformation data, gate data, hydrological and rainfall telemetry data, water quality monitoring data, gas monitoring data, soil moisture data, noise data, and video data, including intelligent video data and surveillance video data.

[0027] As a preferred embodiment, in order to comprehensively perceive data from the hydropower station basin in four continuous spaces—sky, air, ground, and underwater—step S10 includes the following steps:

[0028] Step S101: Monitor the hydropower station basin through BeiDou satellites, and connect BeiDou positioning data, BeiDou short message data, and BeiDou timing data to the BeiDou data sub-database through the BeiDou data interface.

[0029] In step S101, the BeiDou data interface includes an Ethernet interface and a carrier communication interface. At this time, when monitoring the hydropower station basin via BeiDou satellite, the BeiDou positioning data of each fixed monitoring point in the hydropower station basin is connected to the BeiDou data sub-database through the Ethernet interface, and the BeiDou short message data and BeiDou timing data of the hydropower station basin are connected to the BeiDou data sub-database through the carrier communication interface.

[0030] Step S102: Monitor the hydropower station basin using remote sensing equipment, and connect the basin's own geographic information and related geographic information to the remote sensing data sub-database through the remote sensing data interface; the basin's own geographic information includes Tianditu (a map-based information platform), digital elevation data, and orthophoto data of the hydropower station basin; the related geographic information includes oblique photography data of hydraulic structures, point cloud data of underwater topography, and BIM data of key electromechanical equipment.

[0031] In step S102, the remote sensing equipment includes remote sensing satellites, drones, lidar, and a 3D model intelligent terminal. The remote sensing data interface includes a remote sensing satellite communication interface, a drone communication interface, a radar communication interface, and a remote terminal communication interface. At this time, when monitoring the hydropower station basin through various remote sensing devices, the Tianditu (sky map), digital elevation data, and orthophoto data of the hydropower station basin obtained by remote sensing satellites are respectively connected to the remote sensing data sub-database through the remote sensing satellite communication interface; the oblique photography data of hydraulic structures in the hydropower station basin obtained by drones are connected to the remote sensing data sub-database through the drone communication interface; the point cloud data of underwater topography obtained by lidar scanning is connected to the remote sensing data sub-database through the radar communication interface; and the BIM data of key electromechanical equipment in the hydropower station basin automatically generated by the 3D model intelligent terminal is connected to the remote sensing data sub-database through the remote terminal communication interface.

[0032] Step S103: Monitor the hydropower station basin through IoT devices, and connect meteorological data, dam deformation data, gate data, water and rainfall telemetry data, water quality monitoring data, gas monitoring data, soil moisture data, noise data, and video data to the IoT data sub-database through the IoT data interface.

[0033] In step S103, the IoT devices include meteorological satellites and 5G slicing communication devices. The IoT data interfaces include a meteorological satellite communication interface, an ultra-reliable low-latency communication interface (i.e., uRLLC interface), a massive machine-type communication interface (mMTC interface), and an enhanced mobile broadband communication interface (i.e., eMMB interface). At this time, when monitoring the hydropower station basin through various IoT devices, meteorological data obtained from meteorological satellite images are accessed to the IoT data sub-database via the meteorological satellite communication interface; dam deformation data, gate data, and hydrological and rainfall telemetry data are accessed to the IoT data sub-database via the ultra-reliable low-latency communication interface; water quality monitoring data, gas monitoring data, and soil moisture data are accessed to the IoT data sub-database via the massive machine-type communication interface; and noise data and video data are accessed to the IoT data sub-database via the enhanced mobile broadband communication interface.

[0034] It should be noted that steps S101 to S103 can be performed simultaneously, or a certain step can be performed before the others.

[0035] Step S104 involves cleaning and processing the data from the BeiDou data sub-database, remote sensing data sub-database, and IoT data sub-database to construct a watershed database.

[0036] In step S104, the data cleaning process includes integrity checks, accuracy checks, and uniqueness checks. At this point, after accessing the three types of sensing data from the hydropower station basin, data cleaning is performed on the three data sub-databases: the BeiDou data sub-database, the remote sensing data sub-database, and the IoT data sub-database. This involves sequentially performing integrity checks, accuracy checks, and uniqueness checks on the three data sub-databases to remove incomplete, erroneous, and duplicate data. Finally, a basin database is constructed based on the three data sub-databases after the data cleaning process.

[0037] Understandably, this embodiment monitors the hydropower station basin through BeiDou satellites, remote sensing equipment, and IoT devices. The three types of sensing data—BeiDou data, remote sensing data, and IoT data—are accessed to their respective data sub-databases through corresponding data interfaces. After unified data cleaning and processing of the three data sub-databases, a basin database is constructed. This enables comprehensive perception of the basin's continuous space in the sky, air, ground, and underwater, providing rich data for building a digital twin basin.

[0038] Step S20: Based on the watershed database, the watershed of the hydropower station is digitally mapped using multiple engines to obtain the corresponding digital twin watershed.

[0039] In step S20, multiple engines are used, including a BeiDou solution engine, a GIS (Geographic Information System) engine, a VR (Virtual Reality) engine, and a video streaming engine. The BeiDou solution engine is used to analyze BeiDou data from the hydropower station's basin, providing three-dimensional coordinates, high-precision time synchronization, and short message communication services for the data twin basin to be constructed. The GIS engine is used to overlay and fuse remote sensing data from the hydropower station's basin, including Tianditu (a national online map platform), digital elevation data, orthophoto data, oblique photogrammetry data, point cloud data, and BIM data, providing multi-dimensional visualization services for the data twin basin. The VR engine is used to organically fuse IoT data involving visual, auditory, voice, and sensory feedback, including meteorological data, dam deformation data, gate data, hydrological and rainfall telemetry data, water quality monitoring data, gas monitoring data, soil moisture data, and noise data, providing human-computer interaction services for the data twin basin. The video streaming engine is used to process video data in IoT data, providing services such as video management, video storage, video transcoding, video encryption, video distribution, and video playback for the data twin streaming domain to be built.

[0040] That is, step S20, based on a watershed database containing BeiDou data, remote sensing data, and IoT data, uses a BeiDou calculation engine, GIS engine, VR engine, and video stream engine to comprehensively digitize and intelligently simulate the hydropower station's watershed space, obtaining a corresponding digital twin watershed. Preferably, the construction of the digital twin watershed can include three steps: physical framework mapping, virtual object generation, and multi-dimensional attribute filling. Physical framework mapping is used to roughly digitize the entities in the hydropower station's watershed; virtual object generation is used to map the models of key objects in the hydropower station's watershed to corresponding models; and multi-dimensional attribute filling is used to verify and expand the attributes of key objects in the digital twin watershed. At this point, such as... Figure 2 As shown, step S20 includes the following steps:

[0041] Step S201, Physical Framework Mapping: Based on the geographical information of the watershed itself in the remote sensing data, a 3D model of the hydropower station watershed is performed using a GIS engine to digitally map the basic elements in the hydropower station watershed and form the underlying framework of the digital twin watershed.

[0042] In step S201, the basic elements include rivers, slopes, roads, and vegetation within the hydropower station's basin. Specifically, during the physical framework mapping process, the basin's own geographic information is extracted from the basin database, including Tianditu (a national map platform), digital elevation data, and orthophoto data of the hydropower station's basin. Based on this geographic information, a 3D model of the basin area is created using a GIS engine, completing the digital mapping of rivers, slopes, roads, and vegetation within the basin area, thus forming the underlying framework of the digital twin basin.

[0043] Step S202, Virtual Object Generation: Based on the basin-related geographic information in remote sensing data and meteorological data in IoT data, the key objects in the hydropower station basin are modeled using GIS engine and VR engine, and the generated key object models are overlaid on the underlying framework to form a digital twin basin.

[0044] In step S202, the key objects include dams, bridges, hydraulic structures, large mechanical equipment (such as gates), underwater topography, and clouds in the hydropower station basin. Specifically, during the virtual object generation process, two threads for model generation are initiated. One thread extracts basin-related geographic information from the basin database, including oblique photography data of hydraulic structures located in the hydropower station basin, BIM data of major electromechanical equipment, and point cloud data of underwater topography. Based on the basin-related geographic information, a GIS engine is used to generate models of dams, bridges, hydraulic structures, large mechanical equipment, and underwater topography in the digital twin basin. The other thread extracts meteorological data from the basin database and, based on the meteorological data, a VR engine is used to generate models of clouds in the digital twin basin. The generated key object models are then overlaid onto the underlying framework formed in step S201 to form the digital twin basin corresponding to the hydropower station basin.

[0045] Step S203, Multi-dimensional attribute filling: Based on BeiDou data and IoT data, attribute verification and attribute expansion are performed on each key object of the digital twin watershed through the BeiDou calculation engine, VR engine and video stream engine.

[0046] In step S203, attribute verification includes the correspondence of attributes such as length, width, height, area, volume, latitude and longitude; attribute expansion includes the filling of attributes such as water level, flow rate, flow velocity, water quality, noise, video, cloud layer, air pressure, wind speed, wind direction, rainfall, temperature, humidity, displacement, vibration, and subsidence. Specifically, during the multi-dimensional attribute filling process, a first thread for attribute verification and a second thread for attribute expansion are initiated. The first thread extracts BeiDou data from the watershed database, including BeiDou positioning data, BeiDou short message data, and BeiDou timing data. Based on the BeiDou data, the BeiDou calculation engine performs attribute mapping for the digital twin watershed and each key object within it, including length, width, height, area, volume, and latitude and longitude. Simultaneously, the second thread extracts IoT data from the watershed database, including meteorological data, dam deformation data, gate data, hydrological and rainfall telemetry data, water quality monitoring data, gas monitoring data, soil moisture data, noise data, and video data. Based on the IoT data, the VR engine and video streaming engine fill in attributes such as water level, flow rate, flow velocity, water quality, noise, video, cloud cover, air pressure, wind speed, wind direction, rainfall, temperature, humidity, displacement, vibration, and subsidence for each key object within the digital twin watershed.

[0047] Understandably, this embodiment can achieve accurate and intelligent construction of digital twin watersheds through physical framework mapping, virtual object generation, and multi-dimensional attribute filling, and provide technical support for subsequent watershed operations.

[0048] Step S30: Obtain watershed business and simulate business in the digital twin watershed using the algorithm associated with the watershed business.

[0049] In step S30, the watershed service includes one or more of the following: gate control simulation, regional inundation analysis, watershed geological disaster early warning, and dam stress early warning. Specifically, the system acquires control commands sent by the user through VR (Virtual Reality) and AR (Augmented Reality) devices during the watershed service simulation process, combines them with algorithms associated with the watershed service, simulates the watershed service in a digital twin watershed, and displays the simulation results to the user.

[0050] In an optional embodiment, when the watershed service is a gate control rehearsal, step S30 includes the following steps:

[0051] Step S3011: Determine the gates in the digital twin watershed;

[0052] Step S3012: Construct a gate flow analysis model based on the gate data;

[0053] Step S3013: Simulate the gate flow change information according to the gate flow analysis model, receive and parse the gate control command during the simulation process, and control the gate to open or close according to the control information obtained from the parsing.

[0054] In this embodiment, the gate data includes the number of gates, gate opening degree, gate width, and inlet water depth. The simulation process for gate control pre-playing is as follows: First, all gates in the digital twin watershed are determined. Then, based on the number of gates, gate opening degree, gate width, and inlet water depth, a gate flow analysis model is constructed. This gate flow analysis model can be expressed as:

[0055]

[0056] Where n is the number of gates, Q i Let Q be the flow rate after the i-th gate is opened; Q is the total flow rate after opening n gates; Q is the flow rate after the i-th gate is opened. i It can be represented as:

[0057]

[0058] Where δ is the flow coefficient; w is the gate width; e is the gate opening; g is the gravitational acceleration; h is the water depth upstream of the gate, i.e., the distance from underwater to the bottom of the gate; the flow coefficient δ can be expressed as:

[0059]

[0060] Then, the gate flow rate changes are simulated using a gate flow rate analysis model. During the simulation, users can monitor the gate flow rate changes in real time using VR glasses and send gate control commands via VR wristbands. When a gate control command is received, it can be parsed to obtain gate control information, which can then be used to remotely control gate opening and closing and set the gate opening degree. The gate control information includes the gate opening degree, gate opening command, and gate closing command.

[0061] In an optional implementation, when the watershed operation is regional inundation analysis, step S30 includes the following steps:

[0062] Step S3021: Determine the target area in the digital twin watershed;

[0063] Step S3022: Construct a flooding analysis model based on the orthographic projection data, digital elevation data, point cloud data, and meteorological data of the target area;

[0064] Step S3023: Obtain the flood range of the target area within a preset time period based on the flood analysis model, and display the flood range.

[0065] In this embodiment, the simulation process of regional inundation analysis is as follows: A regional selection command sent by the user via the sand table control handle is obtained; a target area is determined in the digital twin watershed based on the regional selection command; and an inundation analysis module is established based on the orthophoto data, digital elevation data, and point cloud data of the underwater topography of the target area, fused with predicted ultra-short-term meteorological data. The inundation range of the target area within a preset time period is obtained through the inundation analysis module, and the inundation range within the preset time period is dynamically visualized using a VR digital sand table corresponding to the sand table control handle. Preferably, the inundation analysis model can be expressed as:

[0066]

[0067] Where, η i S represents the water level rise in the i-th depression within the target area; Δ is the projected area of ​​the grid triangles within the depression on the browser page, and depends on the orthographic projection data; N is the number of grid triangles within the depression, and depends on the point cloud data; d is the predicted precipitation for the target area, and depends on the meteorological data; s is the current water surface area of ​​the depression, and depends on the digital elevation data.

[0068] In an optional implementation, when the watershed service is watershed geological disaster early warning, step S30 includes the following steps:

[0069] Step S3031: Determine the geological disaster area in the digital twin watershed;

[0070] Step S3032: Construct a regional geological disaster hazard model based on BeiDou positioning data, Tianditu data, orthophoto data, digital elevation data, and oblique photogrammetry data of the geological disaster area;

[0071] Step S3034: Issue a geological disaster early warning for the geological disaster area based on the geological disaster early warning model.

[0072] In this embodiment, the simulation process of watershed geological disaster early warning is as follows: First, the inspection request sent by the user through the VR egg chair is received. Based on the inspection request, the geological disaster area in the digital twin watershed is determined. Then, based on the Beidou positioning data obtained by monitoring the geological disaster area by Beidou satellite, and the data obtained by remote sensing equipment by taking pictures of the geological disaster area, including Tianditu, orthophoto data, digital elevation data and oblique photography data, a regional geological disaster hazard model is established to conduct real-time status perception and trend early warning of the geological disaster area through the regional geological disaster hazard model.

[0073] Taking a geological disaster area containing slopes as an example, step S3032, which involves constructing a geological disaster hazard model, includes the following steps:

[0074] Step a: Based on the BeiDou positioning data and oblique photography data of the slope, perform coordinate transformation on Tianditu to obtain fixed monitoring points;

[0075] Step b: Based on the data obtained from the regular multi-angle photography of the slope by remote sensing equipment, the geomorphological changes of the slope are compared and marked to obtain the variable monitoring surface;

[0076] Step c: Establish a slope geological hazard model based on fixed monitoring points and variable monitoring surfaces. Preferably, the slope geological hazard model is as follows:

[0077] ΔD=|D t -D t-1 |,

[0078] Where ΔD is the geological hazard value of the slope; D t Let D be the geological hazard analysis value of the slope at time t. t-1 Here is the geological hazard analysis value of the slope at time t-1; the geological hazard analysis value can be expressed as:

[0079] D = g*w1 + s*w2,

[0080] Where D is the geological disaster analysis value; g and s are the variable monitoring surface and the fixed monitoring point, respectively; w1 and w2 are the weights of the fixed monitoring point and the variable monitoring surface, respectively, and w1 = 0.9 and w2 = 0.1.

[0081] Understandably, after obtaining the hazard value of a slope using a slope hazard model, the hazard value is compared with a preset hazard boundary. A hazard warning is issued when the hazard value meets the boundary conditions. The hazard boundary can be set according to requirements. For example, if ΔD < 0.1, the slope is considered normal and no hazard warning is needed; if ΔD ≥ 0.1, the slope is considered abnormal. Furthermore, if 0.1 ≤ ΔD < 0.2, a non-emergency hazard warning can be issued; if ΔD ≥ 0.2, an emergency hazard warning can be issued.

[0082] In an optional implementation, when the watershed service is a dam stress early warning, step S30 includes the following steps:

[0083] Step S3041: Identify the dams in the digital twin watershed;

[0084] Step S3042: Obtain historical monitoring data and BIM data of the dam; wherein, the historical monitoring data is obtained by extending the attributes of the dam through IoT data, including water level, flow rate, flow velocity and air pressure for historical time periods;

[0085] Step S3043: Obtain the current monitoring data of the dam; wherein, the current monitoring data includes the water level, flow rate, flow velocity and air pressure for the current time period;

[0086] Step S3044: Construct a dam stress detection network and train the dam stress detection network using historical monitoring data and BIM data;

[0087] Step S3045: Input the current monitoring data into the trained dam stress detection network and obtain the dam stress results;

[0088] Step S3046: Obtain the dam status based on the dam stress results, and issue an anomaly warning based on the dam status.

[0089] In this embodiment, the dam stress detection network consists of an input layer, a hidden layer, and an output layer. The input layer is used to acquire input parameters, including water level, flow rate, flow velocity, air pressure, and BIM data. The hidden layer is used to calculate the weights of the input parameters. The output layer is used to output the pressure at multiple measuring points set on the dam, and the number of measuring points is the same as the number of neurons in the output layer.

[0090] The formula for calculating the hidden layer is as follows:

[0091]

[0092] Among them, H j x is the output of the j-th neuron in the hidden layer; i Let be the i-th input parameter; n is the number of input parameters; a j w is the threshold of the j-th neuron. ij Let f(x) be the weight value; f(x) is the activation function, which can be expressed as:

[0093]

[0094] The formula for calculating the output layer is:

[0095]

[0096] Among them, O k The output of the k-th neuron in the output layer; w jk b is the weight value. k The threshold value is the threshold value of the k-th neuron.

[0097] Specifically, the simulation process for dam stress early warning is as follows: After identifying the dam in the digital twin watershed, the dam stress detection network is first trained based on the dam's historical monitoring data and BIM data. Then, the current monitoring data of the dam is input into the trained dam stress detection network to obtain the dam stress results. These results include the pressure at multiple measuring points on the dam. At this point, the dam's condition can be determined based on the pressure at these multiple measuring points. If the dam's condition is abnormal, an anomaly early warning message is generated. Preferably, the dam condition detection method can be as follows: First, check if the pressure at each measuring point on the dam is greater than the corresponding pressure threshold. If so, the measuring point is identified as an abnormal measuring point. Then, check if the number of abnormal measuring points is greater than a preset value (the preset value can be two-thirds of the total number of measuring points). If so, the dam's condition is determined to be abnormal; otherwise, the dam's condition is determined to be normal.

[0098] Understandably, the watershed management method based on digital twins provided in this embodiment has the following beneficial effects:

[0099] 1) By acquiring various sensing data of the hydropower station basin, including BeiDou data, remote sensing data and IoT data, we can achieve comprehensive perception of the hydropower station basin in the continuous space of the sky, air, ground and underwater, and provide data support for the construction of digital twin basin;

[0100] 2) Based on multiple engines, process BeiDou data, remote sensing data and IoT data of hydropower station basins to realize the accurate and intelligent construction of digital twin basins and provide technical support for basin operations;

[0101] 3) By using various algorithms related to watershed operations, multiple watershed operations are simulated in the digital twin watershed, which improves the management efficiency and emergency command capabilities of the hydropower station watershed and enhances the watershed display effect.

[0102] In addition, such as Figure 3 As shown, corresponding to any of the above embodiments, an embodiment of the present invention also provides a watershed management system based on digital twins, including a watershed sensing module 110, a digital twin module 120, and a business management module 130. Detailed descriptions of each functional module are as follows:

[0103] The watershed sensing module 110 is used to acquire BeiDou data, remote sensing data and IoT data of the hydropower station watershed to build a watershed database;

[0104] The digital twin module 120 is used to digitally map the hydropower station's watershed based on a watershed database and through multiple engines to generate a corresponding digital twin watershed.

[0105] The business management module 130 is used to acquire watershed business and perform business simulation in the digital twin watershed through algorithms associated with the watershed business; the watershed business is one or more of the following: gate control pre-simulation, regional inundation analysis, watershed geological disaster early warning, and dam stress early warning.

[0106] In an optional embodiment, the watershed sensing module 110 includes the following sub-modules, and the detailed description of each functional sub-module is as follows:

[0107] The BeiDou data access submodule is used to monitor the hydropower station basin through BeiDou satellites and to connect BeiDou positioning data, BeiDou short message data and BeiDou timing data to the BeiDou data sub-database through the BeiDou data interface.

[0108] The remote sensing data access submodule is used to monitor the hydropower station basin through remote sensing equipment and to access the basin's own geographic information and related geographic information into the remote sensing data sub-database through the remote sensing data interface. The basin's own geographic information includes Tianditu (a map-based information platform), digital elevation data, and orthophoto data of the hydropower station basin. The related geographic information includes oblique photography data of hydraulic structures, point cloud data of underwater topography, and BIM data of key electromechanical equipment.

[0109] The IoT data access submodule is used to monitor the hydropower station basin through IoT devices and to access meteorological data, dam deformation data, gate data, water and rainfall telemetry data, water quality monitoring data, gas monitoring data, soil moisture data, noise data and video data into the IoT data sub-library through the IoT data interface;

[0110] The watershed database construction submodule is used to clean and process the data from the BeiDou data sub-database, remote sensing data sub-database, and IoT data sub-database before constructing the watershed database.

[0111] In an alternative implementation, such as Figure 4 As shown, the digital twin module 120 includes the following sub-modules, and the detailed description of each functional sub-module is as follows:

[0112] The physical framework mapping submodule 121 is used to perform three-dimensional modeling of the hydropower station basin based on the basin's own geographic information in remote sensing data through a GIS engine, so as to digitally map the basic elements in the hydropower station basin and form the underlying framework of the digital twin basin.

[0113] The virtual object generation submodule 122 is used to generate models of key objects in the hydropower station basin based on the basin-related geographic information in remote sensing data and meteorological data in IoT data, through the GIS engine and VR engine, and to overlay the generated key object models onto the underlying framework to form a digital twin basin.

[0114] The multi-dimensional attribute filling submodule 123 is used to perform attribute verification and attribute expansion on each key object of the digital twin watershed based on Beidou data and IoT data, through the Beidou calculation engine, VR engine and video stream engine.

[0115] In an optional implementation, the business management module 130 includes one or more functional modules selected from the following: a gate control pre-simulation module, a regional inundation analysis module, a watershed geological disaster early warning module, and a dam stress early warning module; a detailed description of each functional unit is as follows:

[0116] The gate control simulation module is used to determine the gates in the digital twin flow domain; construct a gate flow analysis model based on the gate data; simulate the flow change information of the gate based on the gate flow analysis model; receive and parse gate control commands during the simulation process; and control the gate to open or close based on the control information obtained from the parsing.

[0117] The regional inundation analysis module is used to determine the target area in the digital twin watershed; construct an inundation analysis model based on the orthographic projection data, digital elevation data, point cloud data and meteorological data of the target area; obtain the inundation range of the target area within a preset time period based on the inundation analysis model, and display the inundation range;

[0118] The watershed geological disaster early warning module is used to identify geological disaster areas in the digital twin watershed; based on BeiDou positioning data, Tianditu (a Chinese online map platform), orthophoto data, digital elevation data, and oblique photogrammetry data of the geological disaster areas, a regional geological disaster hazard model is constructed; and geological disaster early warning is issued for the geological disaster areas based on the regional geological disaster hazard model.

[0119] The dam stress early warning module is used to identify dams in the digital twin watershed; acquire historical monitoring data and BIM data of the dam; the historical monitoring data is obtained by extending the attributes of the dam through IoT data, including water level, flow rate, flow velocity, and air pressure for historical time periods; acquire current monitoring data of the dam; the current monitoring data includes water level, flow rate, flow velocity, and air pressure for the current time period; construct a dam stress detection network, and train the dam stress detection network using historical monitoring data and BIM data; input the current monitoring data into the trained dam stress detection network and obtain the dam stress results; obtain the dam status based on the dam stress results, and issue anomaly warnings based on the dam status.

[0120] The system described above is used to implement the corresponding methods in the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0121] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention is limited to these examples; within the framework of the invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of the invention as described above, which are not provided in detail for the sake of brevity.

[0122] The embodiments of this invention are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of this invention. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this invention should be included within the protection scope of this invention.

Claims

1. A watershed management method based on digital twins, characterized in that, include: Acquire BeiDou data, remote sensing data, and IoT data from the hydropower station basin to construct a basin database; Based on the aforementioned watershed database, the hydropower station watershed is digitally mapped using multiple engines to generate a corresponding digital twin watershed. The watershed services are acquired, and the services are simulated in the digital twin watershed using algorithms associated with the watershed services; the watershed services are one or more of the following: gate control simulation, regional inundation analysis, watershed geological disaster early warning, and dam stress early warning. The watershed operation is a gate control rehearsal; The acquisition of watershed services, and the simulation of services in the digital twin watershed using algorithms associated with the watershed services, include: Determine the gates in the digital twin watershed; Construct a gate flow analysis model based on gate data; The gate flow rate analysis model is used to simulate the flow rate change information of the gate, and the gate control command is received and parsed during the simulation process. The gate is then opened or closed based on the control information obtained from the parsing. The gate data includes the number of gates, gate opening, gate width, and water depth in front of the gate; At this point, the simulation process for gate control pre-play is as follows: First, all gates in the digital twin watershed are determined, and based on the number of gates, gate opening, gate width, and inlet water depth, a gate flow analysis model is constructed, which is expressed as: ， in, For the number of gates, For the first The flow rate after each gate is opened; To open Total flow rate of the gates; Flow rate after the gate is opened Represented as: ， in, For flow coefficient; The width of the gate; This refers to the gate opening degree; It is the acceleration due to gravity; The depth of water upstream of the gate, i.e., the distance from underwater to the bottom of the gate; the flow coefficient. Represented as: Then, the gate flow rate change information is simulated through a gate flow rate analysis model. During the simulation, the user uses VR glasses to monitor the gate flow rate change information in real time and sends gate control commands through a VR wristband. When the gate control command is received, the gate control command is parsed to obtain the gate control information, and then the gate opening and closing and the gate opening degree are remotely implemented according to the gate control information. The gate control information includes the gate opening degree, the gate opening command, and the gate closing command.

2. The watershed management method based on digital twins according to claim 1, characterized in that, The acquisition of BeiDou data, remote sensing data, and IoT data from the hydropower station's basin, and the construction of a basin database, includes: The BeiDou satellite system monitors the hydropower station basin and connects BeiDou positioning data, BeiDou short message data, and BeiDou timing data to the BeiDou data sub-database through the BeiDou data interface. The hydropower station basin is monitored by remote sensing equipment, and the basin's own geographic information and related geographic information are connected to the remote sensing data sub-database through the remote sensing data interface; the basin's own geographic information includes Tianditu (a map-based information platform), digital elevation data, and orthophoto data of the hydropower station basin; the related geographic information includes oblique photography data of hydraulic structures, point cloud data of underwater topography, and BIM data of key electromechanical equipment. The hydropower station basin is monitored through IoT devices, and meteorological data, dam deformation data, gate data, water and rainfall telemetry data, water quality monitoring data, gas monitoring data, soil moisture data, noise data and video data are connected to the IoT data sub-database through IoT data interface; After cleaning and processing the BeiDou data sub-database, the remote sensing data sub-database, and the IoT data sub-database, a watershed database is constructed.

3. The watershed management method based on digital twins according to claim 2, characterized in that, The process of digitally mapping the hydropower station's watershed based on the watershed database using multiple engines to generate a corresponding digital twin watershed includes: Based on the geographical information of the watershed itself in the remote sensing data, a 3D model of the hydropower station watershed is performed using a GIS engine to digitally map the basic elements in the hydropower station watershed and form the underlying framework of the digital twin watershed. Based on the basin-related geographic information in the remote sensing data and the meteorological data in the IoT data, the key objects in the hydropower station basin are modeled using the GIS engine and VR engine, and the generated key object models are superimposed on the underlying framework to form the digital twin basin. Based on the BeiDou data and the IoT data, the attributes of the digital twin watershed and each key object in the digital twin watershed are verified and expanded through the BeiDou calculation engine, VR engine and video streaming engine.

4. The watershed management method based on digital twins according to claim 2, characterized in that, The watershed operation is a gate control rehearsal; The acquisition of watershed services, and the simulation of services in the digital twin watershed using algorithms associated with the watershed services, include: Determine the gates in the digital twin watershed; Construct a gate flow analysis model based on gate data; The gate flow rate analysis model is used to simulate the flow rate change information of the gate. During the simulation, gate control commands are received and parsed, and the gate is opened or closed based on the control information obtained from the parsing.

5. The watershed management method based on digital twins according to claim 2, characterized in that, The watershed service is regional inundation analysis; The acquisition of watershed services, and the simulation of services in the digital twin watershed using algorithms associated with the watershed services, include: Determine the target region within the digital twin watershed; A flooding analysis model is constructed based on the orthographic projection data, digital elevation data, point cloud data, and meteorological data of the target area. The flooding range of the target area within a preset time period is obtained based on the flooding analysis model, and the flooding range is displayed.

6. The watershed management method based on digital twins according to claim 2, characterized in that, The aforementioned watershed service is watershed geological disaster early warning; The acquisition of watershed services, and the simulation of services in the digital twin watershed using algorithms associated with the watershed services, include: Identify the geological disaster areas within the digital twin watershed; Based on the BeiDou positioning data, Tianditu, orthophoto data, digital elevation data, and oblique photogrammetry data of the disaster-prone area, a regional disaster hazard model is constructed. Geological disaster early warning is carried out in the geological disaster area based on the regional geological disaster hazard model.

7. The watershed management method based on digital twins according to claim 2, characterized in that, The aforementioned watershed service is dam stress early warning; The acquisition of watershed services, and the simulation of services in the digital twin watershed using algorithms associated with the watershed services, include: Identify the dams in the digital twin watershed; The historical monitoring data and BIM data of the dam are obtained; wherein, the historical monitoring data is obtained by extending the attributes of the dam through the IoT data, and includes water level, flow rate, flow velocity and air pressure for historical time periods; Obtain the current monitoring data of the dam; wherein the current monitoring data includes the water level, flow rate, flow velocity, and air pressure for the current time period; A dam stress detection network is constructed, and the network is trained using the historical monitoring data and the BIM data. The current monitoring data is input into the trained dam stress detection network, and the dam stress results are obtained; The dam's state is obtained based on the stress results, and anomaly warnings are issued based on the dam's state.

8. A watershed management system based on digital twins, characterized in that, include: The watershed sensing module is used to acquire BeiDou data, remote sensing data, and IoT data of the hydropower station's watershed to build a watershed database; The digital twin module is used to digitally map the hydropower station's watershed based on the watershed database using multiple engines, and generate a corresponding digital twin watershed. The business management module is used to acquire watershed business data and perform business simulations in the digital twin watershed using algorithms associated with the watershed business data; the watershed business data includes one or more of the following: gate control simulation, regional inundation analysis, watershed geological disaster early warning, and dam stress early warning. The watershed operation is a gate control rehearsal; The acquisition of watershed services, and the simulation of services in the digital twin watershed using algorithms associated with the watershed services, include: Determine the gates in the digital twin watershed; Construct a gate flow analysis model based on gate data; The gate flow rate analysis model is used to simulate the flow rate change information of the gate, and the gate control command is received and parsed during the simulation process. The gate is then opened or closed based on the control information obtained from the parsing. The gate data includes the number of gates, gate opening, gate width, and water depth in front of the gate; At this point, the simulation process for gate control pre-play is as follows: First, all gates in the digital twin watershed are determined, and based on the number of gates, gate opening, gate width, and inlet water depth, a gate flow analysis model is constructed, which is expressed as: ， in, For the number of gates, For the first The flow rate after each gate is opened; To open Total flow rate of the gates; Flow rate after the gate is opened Represented as: ， in, For flow coefficient; The width of the gate; This refers to the gate opening degree; It is the acceleration due to gravity; The depth of water upstream of the gate, i.e., the distance from underwater to the bottom of the gate; the flow coefficient. Represented as: Then, the gate flow rate change information is simulated through a gate flow rate analysis model. During the simulation, the user uses VR glasses to monitor the gate flow rate change information in real time and sends gate control commands through a VR wristband. When the gate control command is received, the gate control command is parsed to obtain the gate control information, and then the gate opening and closing and the gate opening degree are remotely implemented according to the gate control information. The gate control information includes the gate opening degree, the gate opening command, and the gate closing command.

9. The watershed management system based on digital twins according to claim 8, characterized in that, The watershed sensing module includes: The BeiDou data access submodule is used to monitor the hydropower station basin through BeiDou satellites and to connect BeiDou positioning data, BeiDou short message data and BeiDou timing data to the BeiDou data sub-database through the BeiDou data interface. The remote sensing data access submodule is used to monitor the hydropower station basin through remote sensing equipment and to access the basin's own geographic information and related geographic information through the remote sensing data interface into the remote sensing data sub-database. The basin's own geographic information includes Tianditu (a map-based information platform), digital elevation data, and orthophoto data of the hydropower station basin. The related geographic information includes oblique photography data of hydraulic structures, point cloud data of underwater topography, and BIM data of key electromechanical equipment. The IoT data access submodule is used to monitor the hydropower station basin through IoT devices and to access meteorological data, dam deformation data, gate data, water and rainfall telemetry data, water quality monitoring data, gas monitoring data, soil moisture data, noise data and video data into the IoT data sub-library through the IoT data interface; The watershed database construction submodule is used to construct the watershed database after cleaning and processing the data from the BeiDou data sub-database, the remote sensing data sub-database, and the IoT data sub-database.

10. The watershed management system based on digital twins according to claim 8, characterized in that, include: The physical framework mapping submodule is used to perform three-dimensional modeling of the hydropower station basin based on the basin's own geographic information in the remote sensing data through a GIS engine, so as to digitally map the basic elements in the hydropower station basin and form the underlying framework of the digital twin basin. The virtual object generation submodule is used to generate models of key objects in the hydropower station basin based on the basin-related geographic information in the remote sensing data and the meteorological data in the IoT data, through the GIS engine and VR engine, and to overlay the generated key object models onto the underlying framework to form the digital twin basin. The multi-dimensional attribute filling submodule is used to perform attribute verification and attribute expansion on the digital twin watershed and each key object of the digital twin watershed based on the Beidou data and the IoT data, through the Beidou calculation engine, VR engine and video stream engine.

Images