A reservoir dam safety monitoring method and system based on digital twinning

Abstract

The application relates to the technical field of dam safety operation and maintenance, and provides a reservoir dam safety monitoring method and system based on digital twinning, which comprises the following steps: a change relationship between dam body stress and displacement is constructed through a water level stress transmission path established by a reservoir dam digital twinning model and historical stress and displacement data; after real-time stress and weather prediction data are acquired, the water level stress is predicted based on the change of the water level in combination with a physical mechanism model and a big data driving algorithm, dam body displacement prediction caused by water level change is obtained, dam body displacement prediction is monitored and early warning is performed, dynamic simulation and safety evaluation of the dam operation state are realized, and the early identification ability and prediction accuracy of dam safety hazards are improved.

Description

Technical Field

[0001] This invention relates to the field of dam safety operation and maintenance technology, and in particular to a method and system for monitoring the safety of reservoir dams based on digital twins. Background Technology

[0002] The core task of a reservoir dam is water storage and regulation. Therefore, compared with simple hydroelectric dams or flood control dams, they are characterized by large reservoir capacity and significant water level changes with weather. This means that the load on the reservoir dam changes rapidly with the weather. The residual stress inside the reservoir dam does not change with the water level in a short period of time. Traditional monitoring methods using stress sensors suffer from isolated data and delayed response, which affects the ability to identify potential safety hazards in the dam. Summary of the Invention

[0003] This invention provides a method for monitoring the safety of reservoir dams based on digital twins, which addresses the problem of delayed response in existing dam safety monitoring technologies.

[0004] The first aspect of this invention provides a method for monitoring the safety of reservoir dams based on digital twins, comprising:

[0005] Based on the location information of the dam's digital twin and various stress sensors, a water level stress transmission path is constructed; historical stress data and displacement data are acquired, and the relationship between dam stress and displacement changes is constructed based on the water level stress transmission path.

[0006] Real-time stress data and weather forecast data are acquired. Water level stress distribution data is predicted based on weather forecast data. The real-time stress data and water level stress distribution data are superimposed to obtain predicted stress data. The predicted stress is then substituted into the relationship between dam stress and displacement to obtain dam displacement prediction data.

[0007] The system monitors the predicted displacement data of the dam body, and if the predicted displacement value of the dam body exceeds the preset range, an early warning signal is issued.

[0008] Optionally, the step of substituting the predicted stress into the relationship between dam stress and displacement to obtain dam displacement prediction data specifically involves:

[0009] The predicted stress is substituted into the relationship between dam stress and displacement change according to time to obtain the dam displacement prediction data; after obtaining the dam displacement prediction data after a preset time length, the water level stress transmission path is corrected based on the dam displacement prediction data, and the relationship between dam stress and displacement change is updated.

[0010] Optionally, the step of predicting water level stress distribution data based on weather forecast data and superimposing real-time stress data with water level stress distribution data to obtain predicted stress data specifically involves:

[0011] A function for water level stress versus time is established using precipitation forecast data from weather forecast data, and a function for temperature stress versus time is established using temperature forecast data from weather forecast data. Based on time, real-time stress data, water level stress, and temperature stress are superimposed to obtain data on the predicted stress versus time.

[0012] Optionally, after acquiring historical stress data and displacement data, the method further includes:

[0013] The process involves obtaining the historical relationship between water level and seepage change over time to construct the seepage response time. After establishing the water level stress change function over time using precipitation forecast data from weather forecast data, the process further includes correcting the water level stress based on the seepage response time.

[0014] The second aspect of this application provides a reservoir dam safety monitoring system based on digital twins, comprising:

[0015] The stress-displacement relationship construction module is used to construct the water level stress transmission path based on the location information of the dam digital twin and various stress sensors; acquire historical stress data and displacement data, and construct the stress-displacement change relationship of the dam body based on the water level stress transmission path;

[0016] The displacement prediction module is used to acquire real-time stress data and weather forecast data, predict water level stress distribution data based on weather forecast data, and superimpose the real-time stress data and water level stress distribution data to obtain predicted stress data; the predicted stress is then substituted into the relationship between dam stress and displacement change to obtain dam displacement prediction data.

[0017] The safety monitoring module is used to monitor the dam displacement prediction data. If the dam displacement prediction value exceeds the preset range, an early warning signal will be issued.

[0018] Optionally, in the displacement prediction module, the predicted stress is substituted into the relationship between dam stress and displacement to obtain dam displacement prediction data, specifically as follows:

[0019] The predicted stress is substituted into the relationship between dam stress and displacement change according to time to obtain the dam displacement prediction data; after obtaining the dam displacement prediction data after a preset time length, the water level stress transmission path is corrected based on the dam displacement prediction data, and the relationship between dam stress and displacement change is updated.

[0020] Optionally, in the displacement prediction module, water level stress distribution data is predicted based on weather forecast data, and the real-time stress data is superimposed with the water level stress distribution data to obtain predicted stress data, specifically:

[0021] A function for water level stress versus time is established using precipitation forecast data from weather forecast data, and a function for temperature stress versus time is established using temperature forecast data from weather forecast data. Based on time, real-time stress data, water level stress, and temperature stress are superimposed to obtain data on the predicted stress versus time.

[0022] Optionally, after acquiring historical stress data and displacement data, the stress-displacement relationship construction module further includes:

[0023] Obtain the historical relationship between water level and seepage change over time, and construct the seepage response time;

[0024] In the displacement prediction module, after establishing the water level stress change function with time based on the precipitation prediction data in the weather forecast data, it also includes: correcting the water level stress according to the corresponding seepage time.

[0025] A third aspect of this application provides a method and device for monitoring the safety of a reservoir dam based on digital twins, the device comprising a processor and a memory:

[0026] The memory is used to store program code and transmit the program code to the processor;

[0027] The processor is used to execute, according to the instructions in the program code, a reservoir dam safety monitoring method based on digital twin as described in any of the first aspects of the present invention.

[0028] The fourth aspect of this application provides a computer-readable storage medium for storing program code for executing a reservoir dam safety monitoring method based on digital twins as described in any of the first aspects of this invention.

[0029] As can be seen from the above technical solutions, the present invention has the following advantages: by establishing the water level stress transmission path through the digital twin model of the reservoir dam, and by constructing the relationship between the stress and displacement of the dam body, after obtaining real-time stress and weather forecast data, and combining the physical mechanism model and big data-driven algorithms, it is possible to predict the water level stress based on the water level changes, thereby obtaining the dam body displacement prediction caused by the water level changes, monitoring and early warning of the dam body displacement prediction, realizing dynamic simulation and safety assessment of the dam's operating status, and improving the early identification capability and prediction accuracy of dam safety hazards. Attached Figure Description

[0030] 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.

[0031] Figure 1 A flowchart of a reservoir dam safety monitoring method based on digital twins;

[0032] Figure 2 This is a structural diagram of a reservoir dam safety monitoring system based on digital twins. Detailed Implementation

[0033] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0034] This invention provides a method for monitoring the safety of reservoir dams based on digital twins, which addresses the problem of delayed response in existing dam safety monitoring technologies.

[0035] Please see Figure 1 , Figure 1 The first flowchart of a reservoir dam safety monitoring method based on digital twins is provided for an embodiment of the present invention.

[0036] S100: Based on the location information of the dam's digital twin and various stress sensors, construct the water level stress transmission path; acquire historical stress data and displacement data, and construct the relationship between dam stress and displacement changes based on the water level stress transmission path;

[0037] It should be noted that the dam digital twin is constructed based on the dam structural model, and the displacement at various points on the dam is monitored in real time using displacement sensors. The structural model of the dam digital twin is updated in real time. The displacement sensors can be total stations or precision levels to measure the three-dimensional coordinate changes of measuring points on the dam surface.

[0038] Based on the digital twin of the dam, a corresponding stiffness matrix is ​​constructed. For continuous bodies like dams, the global stiffness matrix needs to be assembled step by step through discretization, i.e., dividing into finite elements. The stiffness matrix is ​​related to the material's elastic modulus, Poisson's ratio, and geometry. When the overall structure of the dam is displaced, the load transfer path is redistributed. The geometry of the stiffness matrix is ​​obtained based on the real-time displacement data of the dam's digital twin. Each node in the stiffness matrix can be established according to the distribution location of stress sensors. In this way, the stress detection location of historical stress data corresponds to the location of stress sensors, and thus the historical stress data corresponds to the displacement data. The material's elastic modulus and Poisson's ratio are obtained based on the concrete or soil-rock material of the dam. In this embodiment, the dam stiffness matrix is ​​set as the water level stress transfer path. After the dam is displaced, the stiffness matrix also changes, i.e., the stress transfer path also changes. The water level stress transfer path reflects the stress situation of the entire dam after water is pressed at a certain point in the dam.

[0039] The stress deformation of the dam body can be regarded as the dam body displacement. The cumulative horizontal displacement at the top of the dam is allowed to be within 80 mm, and the rate of change is allowed to be within 20 mm / d. The specific values ​​need to be determined in combination with factors such as dam type, dam height, and geological conditions. Exceeding the limit of displacement will cause damage to the dam body. The stress that causes the dam body deformation can be divided into internal and external stresses according to its source. The external load is the hydrostatic pressure brought by the water level, which brings shear stress to the dam body. This embodiment is aimed at the application scenario of reservoir dam, and the influence of wave force can be ignored. The internal stress is mainly self-weight stress and temperature stress. The historical stress data detected by each stress sensor is the sum of the internal and external stresses at its location. Based on the historical stress difference of the sensors at multiple time points and the displacement difference corresponding to the time points, the relationship between dam body stress and displacement change is constructed based on elasticity theory. The relationship can be simplified to {ϵ}=[K]. -1 {σ}, where {ϵ} is the strain vector, [K] -1 Let {σ} be the dam stiffness matrix and {σ} be the stress vector. For certain fixed locations in the dam body, such as the dam toe or the bottom of the dam foundation, where there are fixed constraints, the corresponding node rows and columns in the stiffness matrix should be removed or modified. Furthermore, neural networks with physical constraints, such as PINNs, can be trained, using the mechanical equations as the loss function, combined with machine learning, to calculate and predict the stress brought by each water level based on the digital twin of the reservoir dam, and to correct the relationship between dam stress and displacement changes.

[0040] S200: Acquire real-time stress data and weather forecast data; predict water level stress distribution data based on weather forecast data; and superimpose real-time stress data and water level stress distribution data to obtain predicted stress data; substitute the predicted stress into the relationship between dam stress and displacement to obtain dam displacement prediction data.

[0041] It should be noted that stress sensors monitor the magnitude and direction of stress at various points on the dam body in real time. Real-time stress data primarily consists of residual stress and water level stress. Residual stress includes stress caused by the temperature difference between the inside and outside during casting and cooling, self-weight stress, and residual stress after external loads such as earthquakes, blasting, and water pressure unloading. Water level stress is related to the real-time water level. Under different temperatures, the direction of temperature stress within the dam body varies due to thermal expansion and contraction. Combined with self-weight stress and water level stress, the stress direction at different points may also differ. Weather forecast data, including precipitation, can be obtained from the meteorological bureau via internet access. The millimeters of precipitation have a direct linear relationship with the rise in reservoir water level. Precipitation forecasts are used to predict future water level rises, and the water level stress on the dam body is determined based on different water level heights. In cases of high precipitation... There are instances where reservoir water levels rise rapidly and water is stored quickly. Due to the rapid rise in water level, the residual stress inside the dam will not dissipate in a short time. This stress can be considered to be consistent with the internal stress in the current real-time stress data. The superposition of changes can be achieved by calculating the difference between the stress at the predicted water level and the stress at the current water level. This difference is used to correct the real-time stress data to achieve superposition. For example, if the residual stress state of the dam is tensile stress, and heavy rainfall causes the water level to rise rapidly, the water pressure will increase sharply. The water level stress and the residual stress will be in the same direction and superimposed on the downstream slope. The dam body will shift downstream as a whole, and the toe pressure stress will increase. The predicted stress at various points on the dam can be obtained by predicting changes in the water level. Weather forecast data can also be used for predictions of long-term drought without rainfall. High temperatures will cause the water level to drop, reducing the water level stress and causing thermal expansion stress, which will cause the dam slope to shift outward and crack.

[0042] In the event of rapid rainfall or extreme high temperatures, the water level of a reservoir may rise or fall suddenly, and the water level stress will change rapidly. However, the residual stress inside the reservoir dam will not dissipate quickly in a short period of time, but will have a cumulative effect, affecting the dam structure.

[0043] Substituting the predicted stresses at various points on the dam into the stress-displacement relationship established in the previous steps yields the strain at the predicted stress location. This strain reflects the predicted direction and distance of the dam displacement after precipitation. Furthermore, assuming the dam body is internal and without cracks, it should be considered a single, continuous system. Real-time stress data from multiple discretely distributed stress sensors can be obtained. Based on the digital twin of the dam, the real-time stress distribution of the complete dam body can be reconstructed. After superimposing the stress predictions, the stress predictions at various points on the overall digital twin can be obtained. This allows for deformation and stress prediction in subsequent monitoring of areas without sensors or areas where sensor placement has changed due to displacement.

[0044] S300 monitors the predicted displacement data of the dam body. If the predicted displacement value of the dam body exceeds the preset range, an early warning signal will be issued.

[0045] It should be noted that the precipitation forecast data is updated in real time, and the dam displacement forecast data corresponding to the stress changes in precipitation in the aforementioned steps will also be updated accordingly. During this update process, the dam displacement forecast data needs to be monitored. The displacement preset range is set according to the construction specifications of different reservoirs and dams. If the dam displacement forecast value exceeds the preset range, there is a risk of dam cracking or collapse, and an early warning signal needs to be issued to request a manual decision-making solution. Based on the specific dam displacement forecast, the crack propagation path and dam failure process are simulated in the corresponding area to assist in the formulation of emergency plans. Displacement forecast monitoring can be carried out on key locations of the dam. The most important areas to pay attention to in the dam structure are stress concentration areas such as the dam heel and dam shoulder, and weak seepage prevention areas such as the core wall. Small deformations in these parts may lead to catastrophic consequences through a chain reaction. Therefore, displacement monitoring or early warning priorities can be set for these parts to reduce computing power consumption.

[0046] In this embodiment, the stress transmission path of the water level is established through the digital twin model of the reservoir dam, and the relationship between the stress and displacement of the dam body is constructed using historical stress and displacement data. After obtaining real-time stress and weather forecast data, the water level stress can be predicted based on the changes in water level, thereby obtaining the dam body displacement prediction caused by the water level change. The dam body displacement prediction is monitored and warned, realizing dynamic simulation and safety assessment of the dam's operating status, and improving the early identification and prediction accuracy of dam safety hazards.

[0047] The above is a detailed description of the first embodiment of a reservoir dam safety monitoring method based on digital twins provided in this application. The following is a detailed description of the second embodiment of a reservoir dam safety monitoring method based on digital twins provided in this application.

[0048] This embodiment further provides a method for monitoring the safety of reservoir dams based on digital twins. Please refer to [link to relevant documentation]. Figure 2 In the aforementioned step S200, the step of predicting water level stress distribution data based on weather forecast data and superimposing real-time stress data with water level stress distribution data to obtain predicted stress data specifically involves:

[0049] A function for water level stress versus time is established using precipitation forecast data from weather forecast data, and a function for temperature stress versus time is established using temperature forecast data from weather forecast data. Based on time, real-time stress data, water level stress, and temperature stress are superimposed to obtain data on the predicted stress versus time.

[0050] It should be noted that step S200 mentioned above generally addresses situations of sudden short-term water level changes, where the residual stress within the dam will not change significantly. However, in extreme weather conditions with continuous heavy rain for several days, the change in temperature stress also needs to be considered. The precipitation forecast data in the weather forecast is the number of millimeters of precipitation over a certain period. For example, in the case of rare torrential rain, the predicted precipitation in 24 hours may reach more than 250 millimeters. However, the precipitation is not evenly distributed within 24 hours. Instead, it can be distributed in specific hourly intervals such as 50 millimeters, 20 millimeters, and 15 millimeters based on the specific forecast data. Then, a function of water level changing with time can be established based on the predicted precipitation at each time. Furthermore, a function of water level stress changing with time can be established based on the relationship between water level and stress. In extreme weather conditions with continuous heavy rain for several days, the temperature will generally change accordingly, typically continuing to drop until the maximum temperature is 10℃-12℃ lower than before the rainfall. The temperature drop over several days will cause the temperature stress within the dam to change with the temperature. Therefore, a function of temperature stress changing with time can be established based on the coefficient of thermal expansion and contraction of the dam material.

[0051] Based on the current temperature and water level, real-time temperature stress and water level stress can be obtained. The real-time stress data is the superposition of residual stress, temperature stress, and water level stress. Based on the time-varying functions of water level stress and temperature stress, the increase, decrease, and direction of temperature stress and water level stress can be predicted, and the total stress at each location of the dam body can be obtained as a result of time, thus yielding predicted stress data.

[0052] Furthermore, in the aforementioned step S200, the step of substituting the predicted stress into the relationship between dam stress and displacement to obtain dam displacement prediction data specifically involves: substituting the predicted stress into the relationship between dam stress and displacement over time to obtain dam displacement prediction data; after obtaining dam displacement prediction data after a preset time length, correcting the water level stress transmission path based on the dam displacement prediction data, and updating the relationship between dam stress and displacement.

[0053] It should be noted that the stress on the dam changes over time, and the dam's displacement and deformation also change accordingly. The water level stress transmission path, i.e., the dam stiffness matrix, in step S100 is constructed based on the structural data of the dam's digital twin. When the dam undergoes displacement and deformation, the structure changes, and the nodes in the stiffness matrix will change accordingly. Consequently, the path of stress transmission on the dam changes, resulting in the stress-induced deformation displacement effect changing with the deformation. Therefore, this embodiment will correct the water level stress transmission path and the relationship between dam stress and displacement changes based on the predicted stress-induced deformation over a previous period. The updated relationship between dam stress and displacement is used to predict dam displacement over the next period. The shorter the preset time length, the more accurate the displacement prediction will be due to the updated stiffness matrix and relationship, but the higher the computational requirements will be. Conversely, the longer the preset time length, the greater the cumulative error caused by the unupdated stiffness matrix and relationship. Therefore, an appropriate time length needs to be set according to the dam's monitoring and safety requirements. While correcting the water level stress transmission path and stiffness matrix, the digital twin of the dam can also be updated, and the predicted dam displacement can be presented to the reservoir dam operation and maintenance personnel in a three-dimensional virtual visualization.

[0054] Furthermore, in the aforementioned step S100, after acquiring historical stress data and displacement data, the method further includes: acquiring the relationship between historical water level and seepage change time, and constructing the seepage response time; after establishing the water level stress change function with time using precipitation forecast data in the weather forecast data, the method further includes: correcting the water level stress according to the seepage response time.

[0055] It should be noted that reservoir dams constructed of earth and rock will experience significant seepage. Based on the principle of effective stress, rainfall seeps into the dam's pore system, increasing the internal saturation and thus increasing the internal pore water pressure, which reduces the effective stress. Seepage water creates uplift pressure in the dam foundation or within the dam body, offsetting part of the dam's effective self-weight, reducing its anti-sliding stability, and causing the dam to lift or shift horizontally. Seepage in the core wall or foundation of an earth-rock dam may lead to localized softening, increasing the risk of settlement. Furthermore, when water flows through the dam body or foundation, it applies dragging forces to soil particles or micro-cracks in the concrete, potentially triggering internal erosion and causing localized deformation. In some cases, the interaction between the seepage field and the stress field creates a positive feedback loop: high seepage pressure leads to increased displacement, which in turn increases permeability and seepage flow, further exacerbating the displacement. A typical manifestation of this is... The example is the tensile crack at the heel of a gravity dam, caused by the combined effect of seepage pressure and its own weight, resulting in tensile stress cracks. Although water level changes are the direct cause of seepage changes, seepage does not respond to water level changes in real time. In the first few hours of water level changes, there will be rapid and minimal seepage changes through small cracks, while significant seepage will only occur in the following days or even weeks. Therefore, it is necessary to establish the seepage response time based on the historical water level change time and the seepage pressure change time. The seepage change can be determined based on the water level change over time and the seepage response time, thereby obtaining the seepage pressure change over time. After obtaining the water level stress change function over time, stress correction is performed using the seepage pressure change over time to improve the accuracy of subsequent displacement prediction, incorporating the influence of seepage on dam displacement.

[0056] Furthermore, in the aforementioned step S100, before the location information based on the dam digital twin and various stress sensors, a digital twin is established based on the BIM model of the reservoir dam, and multiple types of sensors are set up to construct a sensor network to acquire temperature, displacement, and seepage data for real-time data updates of the digital twin. IoT, BIM, and GNSS technologies are used to set up a sensor network, monitoring instruments, and engineering entities to form the physical layer of the dam digital twin. A time-series database (InfluxDB) and a data lake are established to realize a structured database, real-time data stream, and historical archives, thus constructing the data layer. FEA, DEM-CFD coupling, and reduced-order modeling techniques are used to set up multi-scale simulation models and machine learning proxy models, thus constructing the model layer. Digital threads and knowledge graph technologies are used to build an early warning system, decision support, and visualization platform, thus constructing the service layer.

[0057] The above is a detailed description of a reservoir dam safety monitoring method based on digital twins, which is the first aspect of this application. The following is a detailed description of an embodiment of a reservoir dam safety monitoring system based on digital twins, which is the second aspect of this application.

[0058] Please see Figure 2 , Figure 2This is a structural diagram of a reservoir dam safety monitoring system based on digital twins. This embodiment provides a reservoir dam safety monitoring system based on digital twins, including:

[0059] The stress-displacement relationship construction module 10 is used to construct the water level stress transmission path based on the location information of the dam digital twin and various stress sensors; acquire historical stress data and displacement data, and construct the stress-displacement change relationship of the dam body based on the water level stress transmission path; the dam digital twin can use BIM+GIS technology to supplement the system's three-dimensional virtual visualization display interface, and use artificial intelligence technology to improve the system's auxiliary decision-making function; based on the GIS platform and BIM platform, geospatial technology and three-dimensional simulation technology are used to realize the multi-dimensional information visualization display and management of reservoir engineering safety monitoring, including three-dimensional deployment of monitoring instruments, three-dimensional display of monitoring data, three-dimensional positioning of early warning alarms, etc., supporting functions such as virtual visualization query and data query for specific time periods, and providing visualization simulation information support for modeling analysis, safety assessment and decision support modules.

[0060] The displacement prediction module 20 is used to acquire real-time stress data and weather forecast data, predict water level stress distribution data based on weather forecast data, and superimpose the real-time stress data and water level stress distribution data to obtain predicted stress data; and substitute the predicted stress into the relationship between dam stress and displacement change to obtain dam displacement prediction data.

[0061] The safety monitoring module 30 is used to monitor the dam displacement prediction data. If the dam displacement prediction value exceeds the preset range, an early warning signal will be issued.

[0062] Furthermore, in the displacement prediction module 20, the predicted stress is substituted into the relationship between dam stress and displacement change to obtain dam displacement prediction data, specifically as follows:

[0063] The predicted stress is substituted into the relationship between dam stress and displacement change according to time to obtain the dam displacement prediction data; after obtaining the dam displacement prediction data after a preset time length, the water level stress transmission path is corrected based on the dam displacement prediction data, and the relationship between dam stress and displacement change is updated.

[0064] Furthermore, in the displacement prediction module 20, water level stress distribution data is predicted based on weather forecast data, and the real-time stress data is superimposed with the water level stress distribution data to obtain predicted stress data, specifically as follows:

[0065] A function for water level stress versus time is established using precipitation forecast data from weather forecast data, and a function for temperature stress versus time is established using temperature forecast data from weather forecast data. Based on time, real-time stress data, water level stress, and temperature stress are superimposed to obtain data on the predicted stress versus time.

[0066] Furthermore, after acquiring historical stress data and displacement data, the stress-displacement relationship construction module 10 also includes:

[0067] Obtain the historical relationship between water level and seepage change over time, and construct the seepage response time;

[0068] The displacement prediction module 20, after establishing the water level stress change function with time based on the precipitation prediction data in the weather forecast data, also includes: correcting the water level stress according to the corresponding seepage time.

[0069] A third aspect of this application also provides a method and device for monitoring the safety of a reservoir dam based on digital twins, including a processor and a memory: wherein the memory is used to store program code and transmit the program code to the processor; the processor is used to execute the above-mentioned method for monitoring the safety of a reservoir dam based on digital twins according to the instructions in the program code.

[0070] The fourth aspect of this application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, the program code being used to execute the above-described method for monitoring the safety of a reservoir dam based on digital twins.

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and equipment can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0072] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0073] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0074] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0075] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or 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 the present invention. 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.

[0076] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention 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 the present invention.

Claims

1. A method for monitoring the safety of a reservoir dam based on digital twins, characterized in that... include: Based on the location information of the dam's digital twin and various stress sensors, a dam stiffness matrix is ​​set to construct the water level stress transmission path. This path reflects the stress on the entire dam body after water pressure is applied at a certain point. Historical stress and displacement data are acquired, and the relationship between dam body stress and displacement is constructed based on the water level stress transmission path. Specifically, this relationship is as follows: ,in For strain vector, Here is the dam stiffness matrix. This is the stress vector; Real-time stress data and weather forecast data are acquired. Based on the weather forecast data, water level stress distribution data is predicted. The real-time stress data and water level stress distribution data are superimposed to obtain predicted stress data. Based on the digital twin of the dam, the real-time stress distribution of the complete dam body is restored. After the stress prediction is superimposed, the stress prediction at each point of the overall digital twin is obtained. The predicted stress is substituted into the relationship between dam body stress and displacement to obtain dam body displacement prediction data. Deformation and stress prediction are performed in areas where no sensors are installed. The system monitors the predicted displacement data of the dam body, and if the predicted displacement value of the dam body exceeds the preset range, an early warning signal is issued.

2. The method for monitoring the safety of a reservoir dam based on digital twins according to claim 1, characterized in that, The process of substituting the predicted stress into the relationship between dam stress and displacement to obtain dam displacement prediction data is as follows: The predicted stress is substituted into the relationship between dam stress and displacement change according to time to obtain the dam displacement prediction data; after obtaining the dam displacement prediction data after a preset time length, the water level stress transmission path is corrected based on the dam displacement prediction data, and the relationship between dam stress and displacement change is updated.

3. The method for monitoring the safety of a reservoir dam based on digital twins according to claim 1, characterized in that, The process of predicting water level stress distribution data based on weather forecast data and then overlaying the real-time stress data with the water level stress distribution data to obtain the predicted stress data is as follows: A function for water level stress versus time is established using precipitation forecast data from weather forecast data, and a function for temperature stress versus time is established using temperature forecast data from weather forecast data. Based on time, real-time stress data, water level stress, and temperature stress are superimposed to obtain data on the predicted stress versus time.

4. The method for monitoring the safety of a reservoir dam based on digital twins according to claim 3, characterized in that, After acquiring historical stress data and displacement data, the process also includes: The process involves obtaining the historical relationship between water level and seepage change over time to construct the seepage response time. After establishing the water level stress change function over time using precipitation forecast data from weather forecast data, the process further includes correcting the water level stress based on the seepage response time.

5. A reservoir dam safety monitoring system based on digital twins, characterized in that, include: The stress-displacement relationship construction module is used to construct the water level stress transmission path by setting the dam stiffness matrix based on the location information of the dam digital twin and various stress sensors. The water level stress transmission path reflects the stress situation of the entire dam body after water is pressed at a certain point. It acquires historical stress and displacement data, and constructs the dam body stress-displacement change relationship based on the water level stress transmission path. Specifically, the dam body stress-displacement change relationship is as follows: ,in For strain vector, Here is the dam stiffness matrix. This is the stress vector; The displacement prediction module is used to acquire real-time stress data and weather forecast data, predict water level stress distribution data based on weather forecast data, and superimpose the real-time stress data with the water level stress distribution data to obtain predicted stress data. Based on the digital twin of the dam, the real-time stress distribution of the complete dam body is restored. After the stress prediction is superimposed, the stress prediction situation at each point of the overall digital twin is obtained. The predicted stress is substituted into the relationship between dam body stress and displacement change to obtain dam body displacement prediction data, and deformation and stress prediction are performed in areas where no sensors are installed. The safety monitoring module is used to monitor the dam displacement prediction data. If the dam displacement prediction value exceeds the preset range, an early warning signal will be issued.

6. A reservoir dam safety monitoring system based on digital twins according to claim 5, characterized in that, In the displacement prediction module, the predicted stress is substituted into the relationship between dam stress and displacement to obtain dam displacement prediction data, specifically: The predicted stress is substituted into the relationship between dam stress and displacement change according to time to obtain the dam displacement prediction data; after obtaining the dam displacement prediction data after a preset time length, the water level stress transmission path is corrected based on the dam displacement prediction data, and the relationship between dam stress and displacement change is updated.

7. A reservoir dam safety monitoring system based on digital twins according to claim 5, characterized in that, In the displacement prediction module, water level stress distribution data is predicted based on weather forecast data, and the real-time stress data is superimposed with the water level stress distribution data to obtain the predicted stress data, specifically: A function for water level stress versus time is established using precipitation forecast data from weather forecast data, and a function for temperature stress versus time is established using temperature forecast data from weather forecast data. Based on time, real-time stress data, water level stress, and temperature stress are superimposed to obtain data on the predicted stress versus time.

8. A reservoir dam safety monitoring system based on digital twins according to claim 7, characterized in that, The stress-displacement relationship construction module, after acquiring historical stress data and displacement data, also includes: Obtain the historical relationship between water level and seepage change over time, and construct the seepage response time; In the displacement prediction module, after establishing the water level stress change function with time based on precipitation prediction data in the weather forecast data, it also includes: correcting the water level stress according to the seepage response time.

9. A reservoir dam safety monitoring device based on digital twins, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute, according to the instructions in the program code, a reservoir dam safety monitoring method based on digital twins as described in any one of claims 1-4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the reservoir dam safety monitoring method based on digital twins as described in any one of claims 1-4.

Images