Artificial intelligence-based intelligent water conservancy digital twin model construction method

Abstract

This invention discloses a method for constructing a digital twin model for smart water conservancy based on artificial intelligence, relating to the field of smart water conservancy technology. The method includes: establishing a project twin model based on smart water conservancy, performing related project analysis, and obtaining associatable equipment; establishing a twin model network and obtaining the response conditions and content of each node; and constructing a response analysis model based on the response content of real-time nodes. This invention addresses the problem in existing methods for constructing digital twin models for smart water conservancy that, when multiple types of water conservancy data exist and a certain type of water conservancy data exhibits abnormal changes, it is impossible to construct a targeted, real-time digital twin model for water conservancy equipment with significant data fluctuations. This results in an inability to effectively monitor abnormal equipment in water conservancy projects.

Description

Technical Field

[0001] This invention relates to the field of smart water conservancy technology, specifically to a method for constructing a smart water conservancy digital twin model based on artificial intelligence. Background Technology

[0002] Smart water conservancy is a new water conservancy development model that utilizes modern information technologies such as the Internet of Things, big data, cloud computing, and artificial intelligence to achieve comprehensive perception, intelligent early warning, and efficient management of water resources, water environment, and water ecology. The smart water conservancy digital twin model is a real-time synchronous virtual model built with digital technology based on physical water conservancy projects, used for full-process monitoring, intelligent scheduling, and risk prediction.

[0003] Existing methods for building digital twin models of smart water conservancy typically rely on data acquisition and transmission. This involves storing the acquired data in a data storage module and managing the water conservancy information using a relational database. After processing the managed data, a digital twin model is built based on the resulting dataset and various mathematical models. While this improved method can enhance data processing efficiency and enable rapid construction of smart water conservancy digital twin models, it still requires building a complete digital twin model when multiple types of water conservancy data exist and one type exhibits abnormal changes. It cannot specifically build real-time digital twin models for water conservancy equipment with significant data fluctuations. This results in an inability to effectively monitor abnormal equipment in water conservancy projects, leading to slow processing of anomalies and impacting actual water conservancy management. For example, patent application CN117372201A discloses a method for applying water... The proposed method for rapidly constructing a smart water conservancy digital twin model for reservoirs utilizes a variety of mathematical modeling techniques, including hydrological forecasting and computational fluid dynamics models, based on the processed dataset to establish an accurate and efficient digital twin water conservancy model. This enables the rapid construction of a smart water conservancy digital twin model for reservoir applications. However, other improvements in smart water conservancy digital twin model construction primarily focus on building a complete digital twin model based on actual conditions. They still cannot address the need to construct a complete digital twin model when multiple types of water conservancy data exist and a particular type of data exhibits abnormal changes. Furthermore, they cannot provide targeted, real-time construction of digital twin models for water conservancy equipment with significant data fluctuations. This results in an inability to effectively monitor abnormal equipment in water conservancy projects, leading to slow processing of anomalies and impacting actual water conservancy management. Therefore, it is necessary to improve the existing methods for constructing smart water conservancy digital twin models. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the existing technology by proposing an artificial intelligence-based method for constructing a digital twin model for smart water conservancy. This method addresses the issue that existing methods for constructing digital twin models for smart water conservancy still require building a complete digital twin model when multiple types of water conservancy data exist and a certain type of data exhibits abnormal changes. This makes it impossible to construct a targeted, real-time digital twin model for water conservancy equipment with significant data fluctuations. Consequently, it hinders effective data monitoring of equipment exhibiting abnormalities in water conservancy projects, resulting in slow processing of anomalies and impacting actual water conservancy management.

[0005] To achieve the above objectives, this application provides a method for constructing a smart water conservancy digital twin model based on artificial intelligence, including the following steps:

[0006] Multiple project twin models are established based on the core project of smart water conservancy, and the correlation analysis of each project twin model is performed. Based on the analysis results of the correlation analysis, the associatable devices of each project twin simulation are obtained. A twin model network is established based on all project twin models and the associatable devices of each project twin model.

[0007] The twin models of all projects associated with the secondary nodes in the twin model network are analyzed. Based on the analysis results, the response conditions and response content of each node are obtained. The twin models of projects associated with the secondary nodes are the models corresponding to the two primary nodes connected to the secondary nodes.

[0008] Artificial intelligence is used to collect data in real time from all core projects within the smart water conservancy system. Based on the real-time collection results and the response conditions of each secondary node, the latest secondary node in the response state is obtained and recorded as the real-time node. The response analysis model is built from the response content of the real-time node and used as a digital twin model for priority analysis of smart water conservancy.

[0009] Furthermore, based on the core projects of smart water conservancy, multiple project twin models are established, including:

[0010] All core projects constituting smart water conservancy are obtained, and all core projects are screened using an artificial intelligence-based project screening method. The project screening method includes: for any core project, core projects that include hydrological monitoring, water quality testing, water supply management, and drainage management are respectively denoted as hydrological monitoring project, water quality testing project, water supply management project, and drainage management project.

[0011] The twin model construction method was used to analyze all hydrological monitoring projects, water quality testing projects, water supply management projects, and drainage management projects respectively. Based on the analysis results, the corresponding project twin models of hydrological monitoring projects, water quality testing projects, water supply management projects, and drainage management projects were obtained and denoted as hydrological twin model, water quality twin model, water supply twin model, and drainage twin model respectively.

[0012] Furthermore, twin model construction methods include:

[0013] Based on the physical buildings at the reservoir site, acquire the physical equipment corresponding to all projects to be analyzed and record them as the basic equipment of the model; acquire the three-dimensional dimension data of all basic equipment of the model and the spatial relationship data between every two basic equipment of the model;

[0014] A spatial coordinate system is established and denoted as the twin model construction coordinate system. The units of the X-axis, Y-axis, and Z-axis of the twin model construction coordinate system are all meters. Using artificial intelligence, a model consisting of all the basic model devices is built within the twin model construction coordinate system based on the three-dimensional dimension data of all the basic model devices and the spatial relationship data between every two basic model devices. This model is denoted as the project twin model. After the project twin model is built, signal access and command issuance between the project twin model and the physical devices are realized based on the digital twin construction tool.

[0015] Furthermore, the analysis of related projects includes:

[0016] For any device α that exists in two project twin models and executes different powers: denote the two project twin models where device α is located as coexistence model A and coexistence model B, respectively, and denote the unit of the data corresponding to the powers executed by device α in coexistence model A and coexistence model B as power unit A and power unit B, respectively.

[0017] Establish a Cartesian coordinate system, denoted as the equipment analysis coordinate system. The unit of the X-axis of the equipment analysis coordinate system is h, and the unit of the Y-axis is either weight unit A or weight unit B. Based on the data stored in all core projects and artificial intelligence, perform k-hour operation simulations on the twin models of the two projects containing equipment α. Based on the operation simulation time and the data corresponding to the weights executed by equipment α in coexistence model A and coexistence model B during the operation simulation, plot the corresponding curves in the equipment analysis coordinate system, denoted as weight curve A and weight curve B.

[0018] Furthermore, the analysis of related projects also includes:

[0019] Find the points with the largest absolute values ​​of slope in the power curves A and B respectively, and denote them as high-rate point A and high-rate point B respectively; denote the closed interval formed by the abscissas of the peaks and troughs of the power curve A that are closest to high-rate point A as the high-rate monotonic interval; when the abscissa of high-rate point B is inside the high-rate monotonic curve, denote device α as an associable device, and denote coexistence model A and coexistence model B as the bi-connected model of device α.

[0020] Obtain all associatable devices in the devices corresponding to all core projects, as well as the dual connectivity model of each associatable device.

[0021] Furthermore, establishing a twin model network based on all project twin models and the associatable devices of each project twin model includes:

[0022] Construct a relational network with hydrological twin model, water quality twin model, water supply twin model and drainage twin model as the main nodes, and denote it as twin model network;

[0023] For any two master nodes in the twin model network, obtain the number of associative devices that form a dual-connection model with the two master nodes, and denote it as L; build L edges between the two master nodes, and add secondary nodes to each edge; fill in the associative devices that form a dual-connection model with the two master nodes in all secondary nodes in turn, wherein the associative devices filled in any two secondary nodes are different from each other.

[0024] Furthermore, establishing a twin model network based on all project twin models and the associatable devices of each project twin model also includes:

[0025] Based on all associable devices and dual-connected devices of associable devices, obtain the edges between all master nodes in the twin model network, and add secondary nodes to each edge.

[0026] Furthermore, the twin models of all associated projects within the twin model network are analyzed, and the response conditions and content of each node are obtained based on the analysis results, including:

[0027] For any secondary node, the response condition of the secondary node is set as follows: when the associatable device in the secondary node is operating, based on the data collected by the associatable device in the secondary node, the data corresponding to the powers executed by the associatable device in the project twin model associated with the secondary node is obtained in real time and recorded as response judgment data. Since there are two project twin models associated with the secondary node, the response judgment data contains two sets of data.

[0028] Furthermore, the analysis of the project twin models associated with all sub-nodes within the twin model network, and the acquisition of the response conditions and response content for each node based on the analysis results, also includes:

[0029] Plot the curves corresponding to the response judgment data in the device analysis coordinate system, and denote them as response judgment curve XP1 and response judgment curve XP2 respectively. When the absolute value of the slope of the rightmost point of response judgment curve XP1 is equal to K1 or the absolute value of the slope of the rightmost point of response judgment curve XP2 is equal to K2, the state of the secondary node is set to the response state. Here, K1 and K2 are the slopes of the high-rate points of the associatable devices in the secondary node when the twin model of the project associated with the secondary node is denoteed as a dual-connection model.

[0030] Furthermore, the analysis of the project twin models associated with all sub-nodes within the twin model network, and the acquisition of the response conditions and response content for each node based on the analysis results, also includes:

[0031] For any sub-node, when the sub-node is in a response state, the response content of the sub-node is set as follows: the project twin model associated with the sub-node is placed in the same twin model construction coordinate system, and based on the spatial relationship data between every two model basic devices in the twin model construction coordinate system at this time, artificial intelligence is used to build the model again, and the model obtained after construction is recorded as the response analysis model.

[0032] The beneficial effects of this invention are as follows: First, this application establishes multiple project twin models based on the core project of smart water conservancy, and performs correlation analysis on each project twin model. Based on the analysis results of the correlation analysis, the associatable devices of each project twin simulation are obtained. A twin model network is established based on all project twin models and the associatable devices of each project twin model. Then, the project twin models associated with all sub-nodes in the twin model network are analyzed, and the response conditions and response content of each node are obtained based on the analysis results. The advantage of this is that by obtaining associatable devices after establishing multiple project twin models, devices that can simultaneously reflect two project twin models can be obtained. Furthermore, by establishing a twin model network, the relationship between different types of water conservancy data can be obtained, which helps to obtain the corresponding response analysis model in a timely manner through abnormal data during subsequent real-time analysis, so as to achieve targeted data monitoring and improve the efficiency of handling abnormal phenomena in water conservancy projects.

[0033] This application also utilizes artificial intelligence to collect data in real time for all core projects within the smart water conservancy system. Based on the real-time collection results and the response conditions of each sub-node, it identifies the latest sub-node in a response state, denoted as a real-time node. A response analysis model is then built from the response content of the real-time nodes, and this model serves as a digital twin model for priority analysis of smart water conservancy. The advantage of this approach is that by acquiring real-time nodes and building a response analysis model from their response content, it is possible to promptly obtain digital twin models corresponding to the data types affected by the significant fluctuations or anomalies in water conservancy projects. This assists staff in conducting targeted data analysis. Because the constructed model is only for digital twin models corresponding to data with significant fluctuations or anomalies, compared to building a complete digital twin model, it improves the efficiency of handling anomalies in terms of model building speed and staff data processing speed. Attached Figure Description

[0034] Figure 1 This is a flowchart of the steps of the method of the present invention;

[0035] Figure 2 This is a schematic diagram of the equipment analysis coordinate system of the present invention;

[0036] Figure 3 This is a schematic diagram of the twin model network structure of the present invention;

[0037] Figure 4 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0038] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Example 1, please refer to Figure 1 As shown, this application provides a method for constructing a smart water conservancy digital twin model based on artificial intelligence, including the following steps:

[0040] Step S1: Establish multiple project twin models based on the core projects of smart water conservancy, and conduct correlation analysis on each project twin model. Based on the analysis results of the correlation analysis, obtain the associatable devices of each project twin simulation; establish a twin model network based on all project twin models and the associatable devices of each project twin model.

[0041] Step S1 includes: Step S101, obtaining all core projects constituting smart water conservancy, and using an artificial intelligence-based project screening method to screen all core projects; the project screening method includes: for any core project, core projects that include hydrological monitoring, water quality testing, water supply management, and drainage management are respectively denoted as hydrological monitoring project, water quality testing project, water supply management project, and drainage management project;

[0042] In the specific implementation process, this embodiment only analyzes hydrological monitoring, water quality testing, water supply management and drainage management. When there are other core projects in actual application, such as flood control and water resources management, the core projects can be added, deleted and modified to ensure that the constructed digital twin model meets the actual data analysis needs.

[0043] Step S102: Use the twin model construction method to analyze all hydrological monitoring projects, water quality testing projects, water supply management projects and drainage management projects respectively. Based on the analysis results, obtain the project twin models corresponding to the hydrological monitoring projects, water quality testing projects, water supply management projects and drainage management projects, and denot them as hydrological twin model, water quality twin model, water supply twin model and drainage twin model respectively.

[0044] In the specific implementation process, the hydrological twin model, water quality twin model, water supply twin model and drainage twin model are all the same, that is, the digital twin model is built by analyzing all the equipment corresponding to each core project using the twin model construction method.

[0045] The twin model construction method includes: step S1021, based on the physical buildings at the reservoir site, acquiring the physical equipment corresponding to all projects to be analyzed, and recording them as the basic equipment of the model; acquiring the three-dimensional dimension data corresponding to all basic equipment of the model and the spatial relationship data between every two basic equipment of the model;

[0046] Step S1022: Establish a spatial coordinate system, denoted as the twin model construction coordinate system, wherein the units of the X-axis, Y-axis, and Z-axis of the twin model construction coordinate system are all meters; using artificial intelligence, based on the three-dimensional dimension data corresponding to all model basic equipment and the spatial relationship data between every two model basic equipment, construct a model composed of all model basic equipment within the twin model construction coordinate system, denoted as the project twin model; after the project twin model is constructed, the signal access and command issuance between the project twin model and the physical equipment are realized based on the digital twin construction tool.

[0047] In the specific implementation process, for example, in an analysis, the hydrological monitoring items obtained include water level monitoring items, water flow monitoring items, and water quantity monitoring items. Then, "the physical equipment corresponding to all items to be analyzed" can include water level monitoring equipment, water flow monitoring equipment, and water quantity monitoring equipment.

[0048] Step S103, the associated project analysis includes: Step S1031, for any device α that exists in two project twin models and executes different powers: the two project twin models where device α is located are respectively denoted as coexistence model A and coexistence model B, and the units of the data corresponding to the powers executed by device α in coexistence model A and coexistence model B are respectively denoted as power unit A and power unit B;

[0049] In specific implementation, for example, during a data analysis, for the YSIProQuatro multi-parameter water quality analyzer that can simultaneously monitor dissolved oxygen and liquid flow rate, the YSIProQuatro multi-parameter water quality analyzer can perform flow rate monitoring and dissolved oxygen monitoring functions in the hydrological twin model and the water quality twin model. The hydrological twin model and the water quality twin model can then be denoted as the coexistence model A and coexistence model B corresponding to the YSIProQuatro multi-parameter water quality analyzer.

[0050] Step S1032: Establish a Cartesian coordinate system and denote it as the equipment analysis coordinate system. The unit of the X-axis of the equipment analysis coordinate system is h, and the unit of the Y-axis is either weight unit A or weight unit B. Based on the data stored in all core projects and artificial intelligence, perform k-hour operation simulation on the twin models of the two projects where equipment α is located. Based on the operation simulation time and the data corresponding to the weights executed by equipment α in coexistence model A and coexistence model B during the operation simulation, plot the corresponding curves in the equipment analysis coordinate system and denote them as weight curve A and weight curve B.

[0051] In specific implementation processes, such as analyzing data obtained from a simulation of the YSIProQuatro multi-parameter water quality analyzer, the established equipment analysis coordinate system is as follows: Figure 2 As shown, curves QQA and QQB represent weight curve A and weight curve B, respectively. Analysis reveals that points GLA and GLB represent high-rate points A and B, respectively. The interval formed by XX1 and XX2 is the high-rate monotonic interval. Since the x-axis of GLB is within the high-rate monotonic interval, it indicates that when the data corresponding to weight curve A has large fluctuations, the data corresponding to weight curve B will also have large fluctuations in the short term. Therefore, the YSIProQuatro multi-parameter water quality analyzer can be recorded as a correlated device, that is, a device that correlates coexistence model A and coexistence model B.

[0052] The associated project analysis also includes: step S1033, obtaining the point with the largest absolute value of the slope in the weight curve A and the weight curve B respectively, and recording them as high-rate point A and high-rate point B respectively; the closed interval formed by the horizontal coordinates of the peak and trough closest to high-rate point A in the weight curve A is recorded as the high-rate monotonic interval; when the horizontal coordinate of high-rate point B is inside the high-rate monotonic curve, device α is recorded as an associated device, and coexistence model A and coexistence model B are recorded as the bi-connected model of device α.

[0053] Step S1034: Obtain all associatable devices in the devices corresponding to all core projects and the dual-connection model of each associatable device;

[0054] Step S104: Construct a relational network with hydrological twin model, water quality twin model, water supply twin model and drainage twin model as the main nodes, and denot it as twin model network;

[0055] Step S105: For any two master nodes in the twin model network, obtain the number of associative devices with the two master nodes as the dual-connection model, and denot it as L; build L edges between the two master nodes, and add secondary nodes to each edge; fill in the associative devices with the two master nodes as dual-connection devices in all secondary nodes in turn, wherein the associative devices filled in any two secondary nodes are different from each other.

[0056] Step S106: Based on all associable devices and dual-connected devices of associable devices, obtain the edges between all master nodes in the twin model network, and add secondary nodes to each edge;

[0057] In specific implementation processes, such as during a data analysis, the resulting twin model network is as follows: Figure 3 As shown, ZJ1 to ZJ4 are all master nodes, and CJ1 to CJ6 are all secondary nodes.

[0058] Step S2: Analyze the project twin models associated with all secondary nodes in the twin model network, and obtain the response conditions and response content of each node based on the analysis results. The project twin models associated with the secondary nodes are the models corresponding to the two primary nodes connected to the secondary nodes.

[0059] Step S2 includes: Step S201, for any secondary node, the response condition of the secondary node is set as follows: when the associatable device in the secondary node is operating, based on the data collected by the associatable device in the secondary node, the data corresponding to the power executed by the associatable device in the secondary node in the project twin model associated with the secondary node is obtained in real time, and recorded as response judgment data. Since the project twin model associated with the secondary node is two models, the response judgment data contains two sets of data.

[0060] In specific implementation, for example, during a data analysis, the associatable device in the secondary node is the YSIProQuatro multi-parameter water quality analyzer, and the dual-connection model of the YSIProQuatro multi-parameter water quality analyzer is a hydrological twin model and a water quality twin model; when the hydrological twin model and the water quality twin model are denoted as the dual-connection model of the YSIProQuatro multi-parameter water quality analyzer, the absolute values ​​of the slopes of high-rate points A and B in the device analysis coordinate system are 4 and 2 respectively. Then, if the slope of the rightmost point of the response judgment curve corresponding to the response judgment data obtained from the YSIProQuatro multi-parameter water quality analyzer in the hydrological twin model is 4, or the slope of the rightmost point of the response judgment curve corresponding to the response judgment data obtained from the YSIProQuatro multi-parameter water quality analyzer in the water quality twin model is 4, or the slope of the rightmost point of the response judgment curve corresponding to the response judgment data obtained from the YSIProQuatro multi-parameter water quality analyzer in the water quality twin model is 4, then... The slope of the rightmost point of the response judgment curve corresponding to the response judgment data obtained by the ProQuatro multi-parameter water quality analyzer is 2, indicating that the data obtained by the YSIProQuatro multi-parameter water quality analyzer in both the hydrological twin model and the water quality twin model will have large data fluctuations in the short term. Therefore, the state of the sub-node where the YSIProQuatro multi-parameter water quality analyzer is located should be set to the response state, and the response analysis model should be obtained.

[0061] Step S202: Plot the curves corresponding to the response judgment data in the device analysis coordinate system, and record them as response judgment curve XP1 and response judgment curve XP2 respectively. When the absolute value of the slope of the rightmost point of response judgment curve XP1 is equal to K1 or the absolute value of the slope of the rightmost point of response judgment curve XP2 is equal to K2, set the state of the secondary node to the response state. Here, K1 and K2 are the slopes of the high-speed points of the associatable devices in the secondary node when the twin model of the project associated with the secondary node is recorded as a dual-connection model.

[0062] Step S203: For any sub-node, when the sub-node is in the response state, the response content of the sub-node is set as follows: the project twin model associated with the sub-node is placed in the same twin model building coordinate system, and based on the spatial relationship data between every two model basic devices in the twin model building coordinate system at this time, artificial intelligence is used to build the model again, and the model obtained after the building is recorded as the response analysis model.

[0063] In the specific implementation process, by acquiring the response analysis model, a digital twin model can be obtained based on data analysis that is associated with data that fluctuates significantly in the short term. This ensures that the digital twin model being analyzed can detect data with large fluctuations in a timely manner, thereby improving the effectiveness and accuracy of data monitoring by the digital twin model.

[0064] Step S3: The artificial intelligence collects data in real time for all core projects within the smart water conservancy system, and obtains the latest sub-node in response state based on the real-time collection results and the response conditions of each sub-node, which is recorded as the real-time node; obtains the response analysis model built from the response content of the real-time node, and uses the response analysis model as a digital twin model for priority analysis of smart water conservancy.

[0065] Example 2, please refer to Figure 4 As shown, Figure 4 The example illustrates the structure of an electronic device, which may include a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, which the processor can call. When the computer-readable instructions are executed by the processor, the steps in the AI-based smart water conservancy digital twin model construction method are performed to achieve the following functions: First, multiple project twin models are established based on the core projects of smart water conservancy, and each project twin model is analyzed in relation to other projects. Based on the analysis results, the associatable devices of each project twin simulation are obtained. A twin model network is established based on all project twin models and the associatable devices of each project twin model. Then, the project twin models associated with all secondary nodes in the twin model network are analyzed, and the response conditions and response content of each node are obtained based on the analysis results. Finally, AI collects data corresponding to all core projects in smart water conservancy in real time, and based on the real-time collection results and the response conditions of each secondary node, the latest secondary node in the response state is obtained, which is denoted as the real-time node. A response analysis model is obtained by building a response model based on the response content of the real-time node, and the response analysis model is used as the digital twin model for priority analysis of smart water conservancy.

[0066] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0067] Example 3: This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the AI-based smart water conservancy digital twin model construction method provided by the above methods. This method includes: first, establishing multiple project twin models based on the core projects of smart water conservancy, and performing correlation analysis on each project twin model respectively, and obtaining the associatable devices of each project twin simulation based on the analysis results; establishing a twin model network based on all project twin models and the associatable devices of each project twin model; then analyzing the project twin models associated with all secondary nodes in the twin model network, and obtaining the response conditions and response content of each node based on the analysis results; finally, using artificial intelligence to collect data corresponding to all core projects in smart water conservancy in real time, and obtaining the latest secondary node in the response state based on the real-time collection results and the response conditions of each secondary node, denoted as the real-time node; obtaining a response analysis model built from the response content of the real-time node, and using the response analysis model as the digital twin model for priority analysis of smart water conservancy.

[0068] Example 4: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps described above in the AI-based smart water conservancy digital twin model construction method to achieve the following functions: First, multiple project twin models are established based on the core projects of smart water conservancy, and each project twin model is analyzed for association with other projects. Based on the analysis results, the associatable devices of each project twin simulation are obtained. A twin model network is established based on all project twin models and the associatable devices of each project twin model. Then, the project twin models associated with all secondary nodes in the twin model network are analyzed, and the response conditions and response content of each node are obtained based on the analysis results. Finally, AI collects data corresponding to all core projects in smart water conservancy in real time, and obtains the latest secondary node in the response state based on the real-time collection results and the response conditions of each secondary node, which is denoted as the real-time node. A response analysis model is obtained by constructing the response content of the real-time node, and the response analysis model is used as the digital twin model for priority analysis of smart water conservancy.

[0069] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the technical solutions described above, or the parts that contribute to the prior art, can be embodied in the form of software products. These computer software products can be stored in computer-readable storage media, such as ROM / RAM, magnetic disks, optical disks, etc., and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0070] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for constructing a smart water conservancy digital twin model based on artificial intelligence, characterized in that, Includes the following steps: Multiple project twin models are established based on the core project of smart water conservancy, and the correlation analysis of each project twin model is performed. Based on the analysis results of the correlation analysis, the associatable devices of each project twin model are obtained. A twin model network is established based on all project twin models and the associatable devices of each project twin model. The twin models of all projects associated with the sub-nodes in the twin model network are analyzed. Based on the analysis results, the response conditions and response content of each sub-node are obtained. The project twin models associated with the sub-nodes are the models corresponding to the two master nodes connected to the sub-nodes. Artificial intelligence collects data in real time from all core projects within the smart water conservancy system. Based on the real-time collection results and the response conditions of each sub-node, the latest sub-node in response state is obtained and recorded as the real-time node. A response analysis model is built from the response content of the real-time node and used as a digital twin model for priority analysis of smart water conservancy. The related project analysis includes: For any device α existing in two project twin models and executing different functions: The two project twin models containing device α are denoted as coexistence model A and coexistence model B, respectively, and the units of the data corresponding to the functions executed by device α in coexistence model A and coexistence model B are denoted as function units A and function units B, respectively; a Cartesian coordinate system is established and denoted as the device analysis coordinate system, where the unit of the X-axis is h, and the unit of the Y-axis is function unit A or function unit B; based on the data stored in all core projects and artificial intelligence, a k-hour simulation is performed on the two project twin models containing device α, and based on the simulation time and the position of device α during the simulation... The data corresponding to the powers executed in coexistence model A and coexistence model B are plotted as curves in the device analysis coordinate system, denoted as power curve A and power curve B respectively; the points with the largest absolute values ​​of slope in power curve A and power curve B are obtained respectively, and denoted as high-rate point A and high-rate point B respectively; the closed interval formed by the abscissas of the peaks and troughs closest to high-rate point A in power curve A is denoted as the high-rate monotonic interval; when the abscissa of high-rate point B is within the high-rate monotonic curve, device α is denoted as an associable device, and coexistence model A and coexistence model B are denoted as the bi-connection model of device α; all associable devices in the devices corresponding to all core projects and the bi-connection model of each associable device are obtained; The process of establishing a twin model network based on all project twin models and the associative devices of each project twin model includes: constructing a relationship network with hydrological twin models, water quality twin models, water supply twin models, and drainage twin models as the main nodes, and denoting it as the twin model network; for any two main nodes in the twin model network, obtaining the number of associative devices with the two main nodes as the bi-connected model, and denoting it as L; building L edges between the two main nodes, and adding secondary nodes to each edge; sequentially filling all secondary nodes with associative devices with the two main nodes as the bi-connected model, wherein the associative devices filled in any two secondary nodes are different from each other; based on all associative devices and the bi-connected model of the associative devices, obtaining the edges between all main nodes in the twin model network, and adding secondary nodes to each edge; The project twin models associated with all sub-nodes within the twin model network are analyzed. Based on the analysis results, the response conditions and content of each sub-node are obtained, including: For any sub-node, the response condition is set as follows: When the associatable device in the sub-node operates, based on the data collected by the associatable device, the data corresponding to the powers executed by the associatable device in the project twin model associated with the sub-node is obtained in real time and recorded as response judgment data. Since there are two project twin models associated with the sub-node, the response judgment data contains two sets of data. Curves corresponding to the response judgment data are plotted in the device analysis coordinate system and recorded as response judgment curve XP1 and response judgment curve XP2, respectively. When the absolute value of the slope of the rightmost point of the judgment curve XP1 is equal to K1 or the absolute value of the slope of the rightmost point of the response judgment curve XP2 is equal to K2, the state of the secondary node is set to the response state. Here, K1 and K2 are the slopes of the high-rate points of the associatable devices in the secondary node when the twin model of the project associated with the secondary node is recorded as a dual-connection model. For any secondary node, when the secondary node is in the response state, the response content of the secondary node is set as follows: the twin model of the project associated with the secondary node is placed in the same twin model construction coordinate system, and based on the spatial relationship data between every two basic devices of the model in the twin model construction coordinate system at this time, artificial intelligence is used to build the model again, and the model obtained after construction is recorded as the response analysis model.

2. The method for constructing a smart water conservancy digital twin model based on artificial intelligence according to claim 1, characterized in that, Multiple project twin models have been established based on core smart water management projects, including: All core projects constituting smart water conservancy are obtained, and all core projects are screened using an artificial intelligence-based project screening method. The project screening method includes: for any core project, core projects that include hydrological monitoring, water quality testing, water supply management, and drainage management are respectively denoted as hydrological monitoring project, water quality testing project, water supply management project, and drainage management project. The twin model construction method was used to analyze all hydrological monitoring projects, water quality testing projects, water supply management projects, and drainage management projects respectively. Based on the analysis results, the corresponding project twin models of hydrological monitoring projects, water quality testing projects, water supply management projects, and drainage management projects were obtained and denoted as hydrological twin model, water quality twin model, water supply twin model, and drainage twin model respectively.

3. The method for constructing a smart water conservancy digital twin model based on artificial intelligence according to claim 2, characterized in that, Twin model construction methods include: Based on the physical buildings at the reservoir site, acquire the physical equipment corresponding to all projects to be analyzed and record them as the basic equipment of the model; acquire the three-dimensional dimension data of all basic equipment of the model and the spatial relationship data between every two basic equipment of the model; A spatial coordinate system is established and denoted as the twin model construction coordinate system. The units of the X-axis, Y-axis, and Z-axis of the twin model construction coordinate system are all meters. Using artificial intelligence, a model consisting of all the basic model devices is built within the twin model construction coordinate system based on the three-dimensional dimension data of all the basic model devices and the spatial relationship data between every two basic model devices. This model is denoted as the project twin model. After the project twin model is built, signal access and command issuance between the project twin model and the physical devices are realized based on the digital twin construction tool.

Images