Digital twinning-based power grid engineering meteorological early warning system

Abstract

The invention relates to the technical field of large-scale power grid safety guarantee and defense systems, and particularly discloses a power grid project meteorological early warning system based on digital twinning. The system mainly comprises a digital twinborn model construction module, a weather forecast data acquisition module, a severe weather data extraction module, a facility influence evaluation module and an early warning information generation module, wherein the digital twinborn model construction module is used for constructing a three-dimensional digital twinborn model of a power grid facility; the weather forecast data acquisition module is used for acquiring weather forecast data; the severe weather data extraction module is used for extracting severe weather data from the weather forecast data; and the facility influence evaluation module is used for evaluating the influence of the severe meteorological data on the operation of the power grid. According to the method, the meteorological conditions which threaten the power grid facilities can be rapidly identified, the potential influence of severe weather on the power grid facilities is effectively evaluated, the accuracy of risk evaluation can be ensured while the calculation amount is small, and therefore more targeted early warning and protection measures are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of large-scale power grid security and defense systems, and in particular to a meteorological early warning system for power grid projects based on digital twins. Background Art

[0002] The main purpose of weather warning for power grid projects is to ensure the safety and stable operation of the power system. Extreme weather may cause equipment damage, line failures and power outages, seriously affecting power supply. Early warning can help take preventive measures in a timely manner to reduce losses and ensure the normal operation of power facilities.

[0003] In the process of meteorological early warning for power grid projects, due to the large number of power grid facilities, evaluating the impact of each facility under extreme weather conditions one by one requires a lot of computing resources and time, which may lead to a lag in early warning information and fail to reflect potential risks in a timely manner, increasing the response time of the system and affecting the accuracy and practicality of the early warning. Summary of the invention

[0004] This application provides a digital twin-based meteorological early warning system for power grid projects, which solves the problem in the prior art that due to the large number of power grid facilities, a large amount of computing resources and time are required to evaluate the impact of each facility under extreme weather conditions one by one. This application can ensure the accuracy of risk assessment while reducing the amount of calculation, thereby achieving more targeted early warning and protection measures.

[0005] The present application provides a digital twin-based power grid engineering meteorological early warning method, which includes the following steps: constructing a three-dimensional digital twin model of power grid facilities, defining physical and electrical parameters for each power grid facility in the model, the parameters including: load capacity, wind resistance level V rated , Dielectric strength safety threshold E min ; Determine the importance of each power grid facility I; obtain weather forecast data, the weather data includes: predicted wind speed V tacual , predict rainfall, predict humidity changes and predict temperature changes; extract severe weather data from weather forecast data; evaluate the impact of the severe weather data on the operation of the power grid, and generate early warning information based on the importance of the power grid facilities.

[0006] Further, I is: I = W 1 ×S 1 +W 2 ×S 2 +W 3 ×S 3 +W 4 ×S 4 +W 5 ×S 5 +W 6 ×S6 Where S 1 Represents the power supply importance score, S 2 Represents the system reliability score, S 3 Represents the load condition score, S 4 Represents the fault impact range score, S 5 Represents the device type and technical complexity score, S 6 represents the geographic location score, W 1 , W 2 , W 3 , W 4 , W 5 and W 6 They respectively represent the weight coefficients reflecting the importance of power supply, system reliability, load conditions, fault impact range, equipment type and technical complexity, and geographical location importance.

[0007] Furthermore, extracting severe weather data from weather forecast data specifically includes: determining the predicted wind speed V tacual Is it greater than the wind speed threshold? If so, the wind speed V will be predicted. tacual Classify it as severe meteorological data; determine whether the predicted rainfall is greater than the rainfall threshold, if so, classify the predicted rainfall as severe meteorological data.

[0008] Further, the impact of the severe meteorological data on the operation of the power grid is evaluated, specifically including: calculating the minimum wind speed required when the power grid facilities are affected under the rainfall threshold, calculating the minimum rainfall required when the power grid facilities are affected under the wind speed threshold; calculating the power grid facilities AF3 whose load capacity does not meet the meteorological conditions, specifically including: determining whether the minimum wind speed is less than the predicted wind speed V in the severe meteorological data tacual If yes, then select the lowest wind speed that is less than the predicted wind speed V in the severe weather data. tacual The corresponding power grid facilities are selected and set AF1 is constructed; it is determined whether the minimum rainfall is less than the predicted rainfall in the severe meteorological data, and if so, the power grid facilities corresponding to the minimum rainfall less than the predicted rainfall in the severe meteorological data are selected and set AF2 is constructed; set AF1 and set AF2 are integrated to obtain power grid facilities AF3 whose load capacity does not meet the meteorological conditions.

[0009] Further, evaluating the impact of the severe weather data on the operation of the power grid also includes: determining that the load capacity does not meet the predicted wind speed V tacual and the power grid facilities AF4 of the predicted rainfall, specifically including: determining the rated load P of the power grid facilities rated ; Calculate the predicted wind speed V tacual and the additional load P due to the predicted rainfall weather ; Calculate the current load P of the power grid facilities actual , Pactual For: P actual =

[0010] P base +P weather , where P base Represents the basic load; judge the current load P actual Is the rated load P exceeded? rated , the current load P actual Exceeding the rated load P rated The power grid facilities are classified as power grid facilities AF4; among them, the predicted wind speed V tacual When the wind speed is less than the threshold and the predicted rainfall is less than the rainfall threshold, the current load P of all power grid facilities actual Both are less than the rated load P rated .

[0011] Furthermore, the additional load includes: wind pressure load P wind and rainfall load P rain , wind pressure load P wind for: In the formula, C d represents the drag coefficient depending on the shape of the equipment, A represents the frontal area of ​​the equipment, ρ represents the air density, and v represents the wind speed; the rainfall load P rain For: P rain =k·R; where k represents the coefficient of rainfall impact on the equipment, determined based on experience, and R represents the rainfall.

[0012] Furthermore, evaluating the impact of the severe weather data on the operation of the power grid also includes: determining the AAF of the power grid facilities that are most susceptible to the impact, specifically including: determining the wind resistance level V rated Less than the predicted wind speed V tacual AF5 of power grid facilities; Determine the dielectric strength safety threshold E min The grid facility AF6 does not meet the predicted humidity change or the predicted temperature change; the grid facility AF4, the grid facility AF5 and the grid facility AF6 are integrated to obtain the grid facility AAF.

[0013] Further, determine the wind resistance level V rated Less than the predicted wind speed V tacual The power grid facilities AF5 specifically include: Determine the wind resistance level V rated Is it less than the predicted wind speed V? tacual , the wind resistance level V rated Is it less than the predicted wind speed V? tacual The grid facilities are classified as grid facilities AF5.

[0014] Furthermore, the dielectric strength safety threshold E is determined minGrid facilities that do not meet the predicted humidity change or predicted temperature change AF6 specifically include: Determine the dielectric strength E of the grid facilities under standard conditions 0 ; Determine the dielectric strength E of the power grid facilities under the predicted temperature change and predicted humidity change, E is: E = E 0 ·(1-k T ΔT-k H ·ΔH); where k T represents the temperature influence coefficient, k H represents the humidity influence coefficient, ΔT represents the temperature change, and ΔH represents the humidity change; the safety threshold E of the power grid facilities is determined min Is it less than E? Set the safety threshold E min Grid facilities with a value less than E are classified as grid facilities AF6.

[0015] Furthermore, generating early warning information specifically includes: weather forecast data includes sudden weather data and non-sudden weather data, judging whether the weather forecast data is sudden weather data; if the weather forecast data is sudden weather data, inputting the power grid facility AFF and weather data into the prediction model to obtain the damage degree D of each power grid facility. i ; Calculate the priority P of each facility i , P i For: P i =α×I i +β×D i ; In the formula, α and β represent weight coefficients reflecting the relative impact of importance and damage degree on priority; generate the priority P i If the weather forecast data is non-sudden weather data, warning information including the AAF of the power grid facilities will be generated.

[0016] In the second aspect, the present application provides a digital twin-based meteorological early warning system for power grid projects, which adopts the digital twin-based meteorological early warning method for power grid projects described in the first aspect, and includes: a digital twin model construction module, a meteorological forecast data acquisition module, a severe weather data extraction module, a facility impact assessment module and a warning information generation module.

[0017] The digital twin model construction module is used to construct a three-dimensional digital twin model of the power grid facilities, define the physical and electrical parameters for each power grid facility in the model, the parameters include: load capacity, wind resistance level, dielectric strength safety threshold, and determine the importance of each power grid facility; the meteorological forecast data acquisition module is used to obtain meteorological forecast data, and the meteorological data includes: predicted wind speed, predicted rainfall, predicted humidity change and predicted temperature change; the severe weather data extraction module is used to extract severe weather data from the meteorological forecast data; the facility impact assessment module is used to assess the impact of the severe weather data on the operation of the power grid; the early warning information generation module is used to generate early warning information based on the impact of the severe weather data on the operation of the power grid and the importance of the power grid facilities.

[0018] In a third aspect, the present application provides a digital twin-based meteorological early warning device for power grid projects, which includes: a memory and a processor.

[0019] The memory is used to store computer programs; the processor is used to implement the steps of the digital twin-based power grid engineering meteorological early warning method as described in the first aspect when executing the computer program.

[0020] The technical solution provided by this application has at least the following technical effects or advantages:

[0021] This application can quickly screen out power grid facilities that may be affected under specific meteorological conditions by evaluating the potential impact of severe weather conditions on power grid facilities. Due to the large number of power grid facilities, evaluating the impact of each facility under extreme weather conditions one by one requires a lot of computing resources and time. It can quickly identify meteorological conditions that pose a threat to power grid facilities and effectively evaluate the potential impact of severe weather on power grid facilities. It can ensure the accuracy of risk assessment while reducing the amount of calculation, thereby achieving more targeted early warning and protection measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a module diagram of the digital twin-based meteorological early warning system for power grid projects in this application;

[0023] Figure 2 A schematic diagram of the process of generating warning information for this application;

[0024] Figure 3 Schematic diagram of the process of determining the AAF of the highly vulnerable grid facilities for this application. DETAILED DESCRIPTION

[0025] By evaluating the potential impact of severe weather conditions on power grid facilities, this application can quickly screen out power grid facilities that may be affected under specific meteorological conditions, quickly identify meteorological conditions that pose a threat to power grid facilities, and effectively evaluate the potential impact of severe weather on power grid facilities. It can ensure the accuracy of risk assessment while reducing the amount of calculation, thereby achieving more targeted early warning and protection measures.

[0026] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0027] Embodiment 1:

[0028] Please refer to Figure 1 - Figure 3 , this embodiment provides a digital twin-based power grid engineering meteorological early warning method, which includes the following steps:

[0029] S100. Build a 3D digital twin model of power grid facilities and define the physical and electrical parameters for each power grid facility in the model. The parameters include: load capacity, wind resistance level V rated , Dielectric strength safety threshold E min , determine the importance of each power grid facility I.

[0030] The three-dimensional digital twin model is a virtual representation of power grid facilities, reflecting their status and performance through real-time data. Power grid facilities include key components such as substations and transmission lines. Parameters describe the material and structural characteristics of the facilities, such as strength and durability, which affect their performance under extreme conditions. Load capacity refers to the maximum carrying capacity of the facility under normal operation to ensure that overload does not occur. The wind resistance level indicates the maximum wind speed that the facility can withstand to ensure that it is not damaged in severe weather. The dielectric strength safety threshold is used to measure the electrical insulation capacity of the facility to ensure safe operation.

[0031] S200. Obtain weather forecast data, including: predicted wind speed V tacual , predict rainfall, predict humidity changes and predict temperature changes.

[0032] Meteorological forecast data refers to future weather information obtained through meteorological models and observations, which is crucial to the safe operation of the power grid. The predicted wind speed indicates the wind speed in a certain period of time in the future, and the predicted rainfall indicates the estimated intensity and duration of future rainfall, which affects the dielectric strength safety threshold and foundation stability of the power grid facilities and may cause equipment failure or short circuit. Changes in humidity will affect the dielectric strength safety threshold of electrical equipment. Excessive humidity may cause equipment corrosion or leakage. Temperature changes affect the material properties of power grid facilities. For example, high temperature may cause equipment overheating and affect its normal operation. In this embodiment, the predicted wind speed, predicted rainfall, predicted humidity change and predicted temperature change all take the maximum value.

[0033] S300. Extract severe weather data from weather forecast data.

[0034] Severe weather data refers to weather condition data that may pose risks to power grid facilities, identified and screened from weather forecast data.

[0035] S400. Evaluate the impact of severe weather data on the operation of the power grid.

[0036] By evaluating the impact of severe weather data on the operation of the power grid, we can provide a basis for the safe management and emergency response of the power grid and ensure the reliability of power supply.

[0037] S500. Generate warning information based on the impact of severe weather data on the operation of the power grid and the importance of power grid facilities.

[0038] Early warning information can include specific risk levels, recommended response measures and necessary maintenance actions, helping the power dispatch center to take preventive measures in a timely manner.

[0039] In S100-S500, by building a three-dimensional digital twin model of the power grid facilities, detailed physical and electrical parameters are defined for each power grid facility in the model to ensure that the system can accurately simulate the behavior of the power grid facilities under different meteorological conditions. By extracting severe weather data and combining it with the importance of the power grid facilities I, the potential impact of severe weather on power grid facilities can be effectively assessed, and early warning information can be generated in a timely manner so that appropriate response measures can be taken.

[0040] Through digital twin technology combined with meteorological data, real-time analysis and early warning are carried out to improve the operational safety and reliability of power grid facilities under severe weather conditions. The system provides differentiated early warning information based on the importance of the facilities, which helps to prioritize the protection of key power grid facilities and reduce the negative impact of severe weather on the overall operation of the power grid.

[0041] In S100, I is: I = W 1 ×S 1 +W2 ×S 2 +W 3 ×S 3 +W 4 ×S 4 +W 5 ×S 5 +W 6 ×S 6 Where S 1 Represents the power supply importance score, S 2 Represents the system reliability score, S 3 Represents the load condition score, S 4 Represents the fault impact range score, S 5 Represents the device type and technical complexity score, S 6 represents the geographic location score, W 1 , W 2 , W 3 , W 4 , W 5 and W 6 They respectively represent the weight coefficients reflecting the importance of power supply, system reliability, load conditions, fault impact range, equipment type and technical complexity, and geographical location importance.

[0042] In this embodiment, the power supply importance score reflects the degree of dependence of a specific area or user on power supply. The higher the importance, the greater the impact of power outages. The system reliability score is used to measure the ability of the power grid system to maintain power supply under normal and abnormal conditions. The higher the reliability, the greater the stability of the system in the event of failures or load fluctuations. The load condition score indicates the load carried by the power grid facilities. The greater the load, the greater the pressure and risk of the equipment, which may affect the safe operation of the power grid. The fault impact range score represents the scope and number of users that may be affected once a fault occurs. The wider the impact range, the higher the severity of the fault. The equipment type and technical complexity score is used to indicate the technical level and equipment type of the power grid facilities. The difficulty and time cost of repairing highly complex equipment in the event of a fault are relatively high. The geographical location score reflects the particularity of the geographical location of the power grid facilities, such as the impact of factors such as terrain and climate on the operation of the facilities. Some areas may be more susceptible to natural disasters.

[0043] By calculating the formula I = W 1 ×S 1 +W 2 ×S 2 +W 3 ×S 3 +W 4 ×S 4 +W 5 ×S 5 +

[0044] W 6 ×S 6 To determine the importance I of each power grid facility, each score S corresponds to the performance of the power grid facility in a certain aspect, and the weight coefficient W reflects the relative impact of each score on the overall importance. It can quantify the importance of power grid facilities and provide a basis for subsequent risk assessment and early warning.

[0045] By reasonably setting the scoring and weight coefficients, the system can flexibly adjust the importance assessment criteria of different power grid facilities to adapt to the needs of different regions or power grid structures and ensure the accuracy and practicality of early warning information.

[0046] In S300, extracting severe weather data from weather forecast data specifically includes: determining the predicted wind speed V tacual Is it greater than the wind speed threshold? If so, the wind speed V will be predicted. tacual Classify it as severe meteorological data; determine whether the predicted rainfall is greater than the rainfall threshold, if so, classify the predicted rainfall as severe meteorological data.

[0047] This embodiment can effectively identify severe weather conditions by setting thresholds for wind speed and rainfall. tacual Or when the rainfall exceeds the set threshold, these data are classified as severe weather data and further used for risk assessment and early warning information generation of power grid facilities. They can quickly identify meteorological conditions that pose a threat to power grid facilities and improve the accuracy and response speed of early warnings.

[0048] In S400, the impact of severe meteorological data on the operation of the power grid is evaluated, specifically including: S410. Calculating the minimum wind speed required when the power grid facilities are affected under the rainfall threshold, calculating the minimum rainfall required when the power grid facilities are affected under the wind speed threshold, and calculating the load capacity of the power grid facilities AF3 that do not meet the meteorological conditions.

[0049] In S410, the calculation of the load capacity of the power grid facility AF3 that does not meet the meteorological conditions specifically includes: S411. Determining whether the minimum wind speed is less than the predicted wind speed V in the severe meteorological data tacual If yes, then select the lowest wind speed that is less than the predicted wind speed V in the severe weather data. tacual The corresponding power grid facilities are selected and set AF1 is constructed; S412. Determine whether the minimum rainfall is less than the predicted rainfall in the severe meteorological data. If so, select the power grid facilities corresponding to the minimum rainfall less than the predicted rainfall in the severe meteorological data and set AF2 is constructed; S413. Integrate set AF1 and set AF2 to obtain power grid facilities AF3 whose load capacity does not meet the meteorological conditions.

[0050] This implementation method evaluates the potential impact of severe weather conditions on power grid facilities by calculating the minimum wind speed required for power grid facilities under a specific rainfall threshold and the minimum rainfall required under a specific wind speed threshold. By comparing these calculated values ​​with the actual predicted meteorological data, power grid facilities that may be affected under specific meteorological conditions can be quickly screened out and integrated into the AF3 set for further risk analysis and early warning.

[0051] Since the minimum wind speed and the minimum rainfall required by the power grid facilities under a specific rainfall threshold can be calculated in advance, it is only necessary to screen out the wind speeds that are less than the predicted wind speed V in the severe weather data. tacual The corresponding power grid facilities and the power grid facilities corresponding to the minimum rainfall less than the predicted rainfall in the severe weather data are integrated to obtain the power grid facilities AF3 whose load capacity does not meet the meteorological conditions, without the need to calculate the load capacity according to the predicted wind speed V tacual The load capacity of each power grid facility is calculated based on the predicted rainfall, which can ensure the accuracy of risk assessment while reducing the amount of calculation, thereby achieving more targeted early warning and protection measures.

[0052] In S400, the impact of severe weather data on the operation of the power grid is evaluated, and the following further includes: S420. Determining that the load capacity does not meet the predicted wind speed V tacual and the power grid facility AF4 of the predicted rainfall, S420 specifically includes: S421. Determine the rated load P of the power grid facility rated ; S422. Calculate the predicted wind speed V tacual and the additional load P due to the predicted rainfall weather ; S423. Calculate the current load P of the power grid facilities actual ,

[0053] P actual For: P actual =P base +P weather , where P base Represents the basic load; S424. Determine the current load P actual Is the rated load P exceeded? rated , the current load P actual Exceeding the rated load P rated The power grid facilities are classified as power grid facilities AF4; among them, the predicted wind speed V tacual When the wind speed is less than the threshold and the predicted rainfall is less than the rainfall threshold, the current load P of all power grid facilities actual Both are less than the rated load P rated .

[0054] This embodiment calculates the actual load of the power grid facilities under the predicted meteorological conditions to evaluate whether they exceed the rated load. First, the basic load P of each power grid facility is determined. base , and then calculate the additional load P caused by meteorological conditions based on the predicted wind speed and rainfall weather , add the basic load and the additional load to get the current load P actual , and then with the rated load P rated For comparison, if the current load exceeds the rated load, the system will mark the grid facility as AF4, indicating that it may face the risk of overload under current meteorological conditions.

[0055] By considering the impact of meteorological conditions on the load of power grid facilities, facilities that may experience overload problems under extreme weather conditions can be identified in advance. This early warning can help operators take preventive measures, such as adjusting load distribution or strengthening monitoring, to reduce the risk of failures caused by overload.

[0056] When setting the wind speed threshold and rainfall threshold, it is necessary to ensure that the predicted wind speed V tacual When the wind speed is less than the threshold and the predicted rainfall is less than the rainfall threshold, the current load P_actual of all power grid facilities is less than the rated load P_rated.

[0057] In S423, the additional loads include: wind pressure load P wind and rainfall load P rain , wind pressure load P wind for: In the formula, C d represents the drag coefficient depending on the shape of the equipment, A represents the frontal area of ​​the equipment, ρ represents the air density, and v represents the wind speed; the rainfall load P rain For: P rain =k·R; where k represents the coefficient of rainfall impact on the equipment, determined based on experience, and R represents the rainfall.

[0058] In this embodiment, the wind pressure load is calculated based on parameters such as the windward area of ​​the equipment, air density and wind speed, reflecting the direct force of wind on the power grid facilities. The rainfall load is calculated based on the rainfall amount and rainfall influence coefficient, indicating the additional pressure of rainfall on the equipment. Through the calculation of these two loads, the impact of extreme weather on power grid facilities can be evaluated more accurately, providing a basis for early warning decisions.

[0059] Through meticulous load calculations, the pressure on power grid facilities in the actual environment can be simulated more accurately, which improves the reliability of meteorological warnings and helps operators better assess and respond to threats to power grid facilities posed by extreme weather.

[0060] In S400, evaluating the impact of severe weather data on the operation of the power grid also includes: S430. Determining the AAF of the power grid facilities that are most susceptible to being affected. S430 specifically includes: S431. Determining the wind resistance level V rated Less than the predicted wind speed V tacual Grid facilities AF5; S432. Determine the dielectric strength safety threshold E min The power grid facility AF6 does not meet the predicted humidity change or the predicted temperature change; S433. Integrate the power grid facility AF4, the power grid facility AF5 and the power grid facility AF6 to obtain the power grid facility AAF.

[0061] This implementation method identifies the grid facilities that are most vulnerable to being affected under specific severe weather conditions by comprehensively evaluating the wind resistance level and dielectric strength safety threshold of the grid facilities. First, determine whether the wind resistance level of the grid facilities is lower than the predicted wind speed. If so, it is classified as AF5. Evaluate whether the dielectric strength safety threshold of the facility cannot meet the safety requirements under the predicted humidity or temperature changes. If not, it is classified as AF6. Then integrate these vulnerable facilities with the previously identified overloaded facilities AF4 to obtain the extremely vulnerable grid facilities AAF. Through multi-dimensional evaluation criteria, the system can more comprehensively identify grid facilities that may have problems under severe weather conditions, which helps to provide early warning and reduce the risk of grid outages or failures caused by meteorological disasters.

[0062] In S431, determine the wind resistance level V rated Less than the predicted wind speed V tacual The power grid facilities AF5 specifically include: Determine the wind resistance level V rated Is it less than the predicted wind speed V? tacual , the wind resistance level V rated Is it less than the predicted wind speed V? tacual The grid facilities are classified as grid facilities AF5.

[0063] This implementation method compares the wind resistance level V of the power grid facilities. rated With V tacual , identify when the wind speed exceeds the wind resistance level V rated First, obtain the wind resistance level V of each power grid facility. rated and the predicted wind speed V provided in the weather forecast tacual For comparison, if the predicted wind speed V tacual Exceeds the facility's wind resistance level V rated , the facility is marked as AF5, indicating that it has a high risk under the current wind speed conditions. By evaluating the wind resistance of the facilities, the system can accurately identify the grid facilities that are vulnerable to damage under high wind speed conditions, thereby providing operators with targeted risk prevention and control measures to effectively reduce the risk of grid failures caused by wind disasters.

[0064] In S432, the dielectric strength safety threshold E is determined. min Grid facilities that do not meet the predicted humidity change or predicted temperature change AF6 specifically include: Determine the dielectric strength E of the grid facilities under standard conditions 0 ; Determine the dielectric strength E of the power grid facilities under the predicted temperature change and predicted humidity change, E is: E = E 0 ·(1-k T ΔT-k H ·ΔH); where k T represents the temperature influence coefficient, k H represents the humidity influence coefficient, ΔT represents the temperature change, and ΔH represents the humidity change; the safety threshold E of the power grid facilities is determined min Is it less than E? Set the safety threshold E min Grid facilities with a value less than E are classified as grid facilities AF6.

[0065] This implementation method analyzes the dielectric strength safety threshold of power grid facilities under different temperature and humidity conditions to evaluate their safety under predicted meteorological conditions. First, the dielectric strength of the power grid facilities under standard conditions is determined, and the dielectric strength E under new conditions is calculated based on changes in temperature and humidity. If the calculated dielectric strength is lower than the safety threshold of the facility, the facility is identified as AF6, indicating that its dielectric strength safety threshold may be insufficient under current meteorological conditions. This allows for early identification of power grid facilities with insulation risks under temperature and humidity changes, thereby avoiding equipment failures and safety hazards caused by insulation failure.

[0066] In S500, generating early warning information specifically includes: weather forecast data includes sudden weather data and non-sudden weather data, judging whether the weather forecast data is sudden weather data; if the weather forecast data is sudden weather data, inputting the power grid facility AFF and weather data into the prediction model to obtain the damage degree D of each power grid facility. i ; Calculate the priority P of each facility i , P i For: P i =α×I i +β×D i ; In the formula, α and β represent the weight coefficients reflecting the relative influence of importance and damage degree on priority; the priority P is generated i If the weather forecast data is non-sudden weather data, warning information including the AAF of the power grid facilities will be generated.

[0067] This implementation method adopts different warning generation strategies according to the suddenness of meteorological data. For sudden meteorological data, the system will calculate the priority of each facility based on the importance and damage degree of the power grid facilities, and generate priority-ordered warning information. For non-sudden meteorological data, the system will generate warning information including the AAF of the power grid facilities, indicating the potential risks of the power grid facilities.

[0068] By distinguishing between sudden and non-sudden meteorological events, more targeted warning information can be provided. In sudden events, priority-ordered warning information helps operators quickly identify and protect the most critical facilities, effectively reducing losses. In non-sudden events, the comprehensive facility risk list provided by the system ensures adequate response to potential risks.

[0069] Embodiment 2:

[0070] This embodiment provides a digital twin-based meteorological early warning system for power grid projects, which adopts the digital twin-based meteorological early warning method for power grid projects in Embodiment 1, and includes: a digital twin model construction module, a meteorological forecast data acquisition module, a severe meteorological data extraction module, a facility impact assessment module, and a warning information generation module.

[0071] The digital twin model construction module is used to construct a three-dimensional digital twin model of the power grid facilities, and define the physical and electrical parameters for each power grid facility in the model. The parameters include: load capacity, wind resistance level, dielectric strength safety threshold, and determine the importance of each power grid facility; the meteorological forecast data acquisition module is used to obtain meteorological forecast data. The meteorological data includes: predicted wind speed, predicted rainfall, predicted humidity change and predicted temperature change; the severe weather data extraction module is used to extract severe weather data from the meteorological forecast data; the facility impact assessment module is used to assess the impact of severe weather data on the operation of the power grid; the early warning information generation module is used to generate early warning information based on the impact of severe weather data on the operation of the power grid and the importance of power grid facilities.

[0072] This embodiment has all the advantages of the meteorological early warning method for power grid projects based on digital twins in Embodiment 1, and can automatically implement all steps of the meteorological early warning method for power grid projects based on digital twins.

[0073] Embodiment three:

[0074] This embodiment provides a digital twin-based meteorological early warning device for power grid projects, which includes: a memory and a processor.

[0075] The memory is used to store computer programs; the processor is used to implement the steps of the digital twin-based meteorological early warning method for power grid projects in Example 1 when executing the computer program.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

Claims

1. A meteorological early warning system for power grid projects based on digital twins, It is characterized in that It includes: Digital twin model building module: It is used to build a three-dimensional digital twin model of power grid facilities and define physical and electrical parameters for each power grid facility in the model, including load capacity, wind resistance level V rated , Dielectric strength safety threshold E min ; Determine the importance of each grid facility I; Weather forecast data acquisition module: It is used to obtain weather forecast data, the weather data includes: predicted wind speed V tacual , predict rainfall, predict humidity changes and predict temperature changes; Severe weather data extraction module: used to extract severe weather data from weather forecast data; Facility impact assessment module: used to assess the impact of the severe weather data on the operation of the power grid; Warning information generation module: It is used to generate warning information based on the impact of the severe weather data on the operation of the power grid and the importance level I of the power grid facilities.

2. The digital twin-based meteorological early warning system for power grid projects according to claim 1, It is characterized in that I is: I=W 1 ×S 1 +W 2 ×S 2 +W 3 ×S 3 +W 4 ×S 4 +W 5 ×S 5 +W 6 ×S 6 Where S 1 Represents the power supply importance score, S 2 Represents the system reliability score, S 3 Represents the load condition score, S 4 Represents the fault impact range score, S 5 Represents the device type and technical complexity score, S 6 represents the geographic location score, W 1 , W 2 , W 3 , W 4 , W 5 and W 6 They respectively represent the weight coefficients reflecting the importance of power supply, system reliability, load conditions, fault impact range, equipment type and technical complexity, and geographical location importance.

3. The digital twin-based meteorological early warning system for power grid projects according to claim 1, It is characterized in that Extracting severe weather data from weather forecast data specifically includes: Determine the predicted wind speed V tacual Is it greater than the wind speed threshold? If so, the wind speed V will be predicted. tacual Classified as severe weather data; Determine whether the predicted rainfall is greater than the rainfall threshold. If so, classify the predicted rainfall as severe weather data.

4. The digital twin-based meteorological early warning system for power grid projects according to claim 1, It is characterized in that Assess the impact of the severe weather data on the operation of the power grid, including: Calculate the minimum wind speed required for grid facilities to be affected under a rainfall threshold, Calculate the minimum rainfall required for grid facilities to be affected under a wind speed threshold, Calculation load capacity does not meet the meteorological conditions of the power grid facilities AF3, including: Determine whether the minimum wind speed is less than the predicted wind speed V in the severe weather data tacual If yes, then select the lowest wind speed that is less than the predicted wind speed V in the severe weather data. tacual The corresponding power grid facilities and construct the set AF1; Determine whether the minimum rainfall is less than the predicted rainfall in the severe weather data, and if so, select power grid facilities corresponding to the minimum rainfall less than the predicted rainfall in the severe weather data and construct a set AF2; The set AF1 and the set AF2 are integrated to obtain the power grid facility AF3 whose load capacity does not meet the meteorological conditions.

5. The digital twin-based meteorological early warning system for power grid projects according to claim 3, It is characterized in that Evaluating the impact of the severe weather data on the operation of the power grid also includes: determining that the load capacity does not meet the predicted wind speed V tacual and the power grid facilities AF4 for predicting rainfall, including: Determine the rated load P of the power grid facility rated ; Calculate the predicted wind speed V tacual and the additional load P due to the predicted rainfall weather ; Calculate the current load P of the power grid facility actual , P actual For: P actual =P base +P weather , where P base represents the base load; Determine the current load P actual Is the rated load P exceeded? rated , the current load P actual Exceeding the rated load P rated The grid facilities are classified as grid facilities AF4; Among them, the predicted wind speed V tacual When the wind speed is less than the threshold and the predicted rainfall is less than the rainfall threshold, the current load P of all power grid facilities actual Both are less than the rated load P rated .

6. The digital twin-based meteorological early warning system for power grid projects according to claim 5, It is characterized in that The additional loads include: wind pressure load P wind and rainfall load P rain , Wind pressure load P wind for: In the formula, C d represents the drag coefficient that depends on the shape of the device, A represents the frontal area of ​​the device, ρ represents the air density, and v represents the wind speed; Rainfall load P rain For: P rain =k·R; where k represents the coefficient of rainfall impact on the equipment, determined based on experience, and R represents the rainfall.

7. The digital twin-based meteorological early warning system for power grid projects according to claim 5, It is characterized in that Assessing the impact of the severe weather data on the operation of the power grid also includes: determining the AAF of the power grid facilities that are extremely susceptible to the impact, including: Determine the wind resistance level V rated Less than the predicted wind speed V tacual Grid facilities AF5; Determine the dielectric strength safety threshold E min Grid facilities that do not meet predicted humidity changes or predicted temperature changes AF6; The grid facility AF4, the grid facility AF5 and the grid facility AF6 are integrated to obtain the grid facility AAF.

8. The digital twin-based meteorological early warning system for power grid projects according to claim 7, It is characterized in that Determine the wind resistance level V rated Less than the predicted wind speed V tacual The power grid facilities AF5 specifically include: Determine wind resistance level V rated Is it less than the predicted wind speed V? tacual , the wind resistance level V rated Is it less than the predicted wind speed V? tacual The grid facilities are classified as grid facilities AF5.

9. The digital twin-based meteorological early warning system for power grid projects according to claim 7, It is characterized in that Determine the dielectric strength safety threshold E min The grid facilities that do not meet the predicted humidity change or predicted temperature change AF6 specifically include: Determine the dielectric strength E of power grid facilities under standard conditions 0 ; Determine the dielectric strength E of the power grid facility under the predicted temperature change and predicted humidity change, E is: E = E 0 ·(1-k T ΔT-k H ·ΔH); where k T represents the temperature influence coefficient, k H represents the humidity influence coefficient, ΔT represents the temperature change, and ΔH represents the humidity change; Determine the safety threshold E of power grid facilities min Is it less than E? Set the safety threshold E min Grid facilities with a value less than E are classified as grid facilities AF6.

10. The digital twin-based meteorological early warning system for power grid projects according to claim 1, It is characterized in that The generated warning information specifically includes: Weather forecast data includes sudden weather data and non-sudden weather data, and whether the weather forecast data is sudden weather data is determined; If the weather forecast data is sudden weather data, the AFF of the power grid facilities and the weather data are input into the prediction model to obtain the damage degree D of each power grid facility. i ; Calculate the priority P of each facility i , P i For: P i =α×I i +β×D i ; In the formula, α and β represent weight coefficients reflecting the relative impact of importance and damage degree on priority; generate the priority P i early warning information; If the weather forecast data is non-sudden weather data, warning information including the AAF of the power grid facility is generated.

Images