Distribution network line lightning stroke risk early warning method, device, equipment and storage medium

Abstract

The embodiment of the invention provides a distribution network line lightning stroke risk early warning method, device and equipment and a storage medium, and the method comprises the steps: building a multi-dimensional evaluation index based on lightning monitoring data, line parameter data and meteorological environment data which are collected in advance, and calculating the lightning stroke risk of a distribution network line according to the lightning density, the line exposure degree and the equipment vulnerability; the lightning stroke risk level of each line section in the distribution network line is calculated through a dynamic evaluation algorithm, and based on the lightning stroke risk levels of all the line sections and lightning nowcasting data obtained in advance, differential lightning protection transformation schemes are generated through a preset multi-target optimization model. And pushing the differentiated lightning protection transformation scheme to a manager. Through the above method, closed-loop management from data acquisition to decision execution is realized, the accuracy and efficiency of power grid lightning protection are significantly improved, and the lightning trip-out rate is reduced.

Description

Technical Field

[0001] This application relates to the field of lightning protection technology for power distribution networks, and in particular to a method, device, equipment and storage medium for early warning of lightning strike risks on power distribution lines. Background Technology

[0002] As the scale of power grid construction expands, the span and voltage level of distribution lines are also gradually increasing. Consequently, the risk of these lines being struck by lightning is increasing, and the economic losses and safety hazards caused by lightning strikes to regional power grids are becoming more severe. Lightning strikes are a major cause of distribution line failures, and lightning-induced power outages have become the greatest threat to the safe and stable operation of the power grid. Therefore, it is crucial to proactively implement targeted risk mitigation measures, monitor the lightning risk status of distribution lines in real time, and conduct early warning assessments.

[0003] Existing technologies typically classify power grids according to electric field strength and lightning distance to implement graded lightning strike early warning, or use real-time fault probability assessment methods for distribution lines based on distribution line data and lightning meteorological factors to calculate the real-time fault probability of distribution lines.

[0004] However, the above methods only consider lightning activity and atmospheric distribution around the distribution lines. In actual line trip warnings, problems such as high false alarm rate and low prediction accuracy may occur. Furthermore, they also rely on expert experience, which makes subjective factors have a significant impact and leads to unsatisfactory evaluation results. Summary of the Invention

[0005] This application provides a method, device, equipment, and storage medium for early warning of lightning strike risks in power distribution lines, in order to solve the problem of how to improve the accuracy of lightning protection early warning.

[0006] In a first aspect, embodiments of this application provide a method for early warning of lightning strike risks on distribution network lines, including:

[0007] Based on pre-collected lightning monitoring data, line parameter data, and meteorological environment data, a multi-dimensional evaluation index is established, which includes lightning density, line exposure, and equipment vulnerability.

[0008] Based on the lightning density, the line exposure, and the equipment vulnerability, the lightning risk level of each line segment in the distribution network is calculated using a dynamic evaluation algorithm.

[0009] Based on the lightning risk level of all line sections and the pre-acquired lightning nowcast data, a differentiated lightning protection renovation plan is generated through a pre-set multi-objective optimization model.

[0010] The differentiated lightning protection upgrade plan was pushed to the management personnel.

[0011] In one possible implementation, the lightning monitoring data includes lightning occurrence time, lightning occurrence location, lightning intensity, polarity parameter values, and atmospheric electric field monitoring data.

[0012] The line parameter data includes tower height, insulator configuration, conductor type and historical lightning strike fault records. The historical lightning strike fault records include fault point distribution, number of trips and equipment damage information.

[0013] The meteorological and environmental data includes thunderstorm paths, rainfall intensity, wind speed, and topographic data.

[0014] In one possible implementation, the establishment of multi-dimensional evaluation indicators based on pre-collected lightning monitoring data, line parameter data, and meteorological environmental data includes:

[0015] The lightning density is calculated using the lightning occurrence time, lightning occurrence location, lightning intensity, polarity parameter value, atmospheric electric field monitoring data, and thunderstorm path.

[0016] The line exposure is calculated based on the tower height, conductor type, wind speed, and terrain data.

[0017] The vulnerability of the equipment is calculated based on the insulator configuration, the distribution of fault points, the number of trips, the equipment damage information, and the rainfall intensity.

[0018] In one possible implementation, the step of calculating the lightning risk level of each line segment in the distribution network line using a dynamic evaluation algorithm based on the lightning density, the line exposure, and the equipment vulnerability includes:

[0019] For each line segment, the weight coefficient of each indicator is calculated through fuzzy comprehensive evaluation based on the lightning density, the line exposure degree, and the equipment vulnerability.

[0020] The comprehensive risk score of the line section is calculated based on the weighting coefficient of each indicator.

[0021] The comprehensive risk score is corrected by a pre-trained deep learning model to obtain the final risk score of the line section.

[0022] The lightning risk level of the line section is determined based on the final risk score.

[0023] In one possible implementation, the differentiated lightning protection upgrade plan is generated based on the lightning risk level of all line sections and pre-acquired lightning nowcasting data, using a pre-set multi-objective optimization model, including:

[0024] Based on the lightning risk level of all line sections and the pre-acquired lightning nowcast data, the warning level of each line section is determined according to the preset level classification rules.

[0025] The warning level of each line section is input into the multi-objective optimization model. Based on the preset constraints, multi-objective optimization is performed to generate the differentiated lightning protection renovation scheme.

[0026] In one possible implementation, calculating the lightning density using the lightning occurrence time, lightning occurrence location, lightning intensity, polarity parameter value, atmospheric electric field monitoring data, and thunderstorm path includes:

[0027] Based on the lightning occurrence location, the lightning intensity, and the polarity parameter, an initial lightning density is generated using a spatial interpolation algorithm;

[0028] By combining the atmospheric electric field monitoring data and the thunderstorm path, the initial lightning density is dynamically corrected to obtain the lightning density.

[0029] In one possible implementation, calculating the line exposure based on the tower height, the conductor type, the wind speed, and the terrain data includes:

[0030] Based on the tower height and the conductor type, the foundation exposure is calculated;

[0031] The basic exposure is corrected based on the wind speed and the terrain data to obtain the line exposure.

[0032] Secondly, embodiments of this application provide a lightning strike risk early warning device for distribution network lines, comprising:

[0033] A module is established to build multidimensional evaluation indicators based on pre-collected lightning monitoring data, line parameter data, and meteorological environment data. The multidimensional evaluation indicators include lightning density, line exposure, and equipment vulnerability.

[0034] The calculation module is used to calculate the lightning risk level of each line segment in the distribution network line based on the lightning density, the line exposure degree and the equipment vulnerability through a dynamic evaluation algorithm;

[0035] The generation module is used to generate differentiated lightning protection renovation schemes based on the lightning risk level of all line sections and the pre-acquired lightning nowcast data, through a pre-set multi-objective optimization model.

[0036] The push module is used to push the differentiated lightning protection renovation plan to the management personnel.

[0037] In one possible implementation, the lightning monitoring data includes lightning occurrence time, lightning occurrence location, lightning intensity, polarity parameter values, and atmospheric electric field monitoring data.

[0038] The line parameter data includes tower height, insulator configuration, conductor type and historical lightning strike fault records. The historical lightning strike fault records include fault point distribution, number of trips and equipment damage information.

[0039] The meteorological and environmental data includes thunderstorm paths, rainfall intensity, wind speed, and topographic data.

[0040] In one possible implementation, the establishment module specifically includes:

[0041] The lightning density is calculated using the lightning occurrence time, lightning occurrence location, lightning intensity, polarity parameter value, atmospheric electric field monitoring data, and thunderstorm path.

[0042] The line exposure is calculated based on the tower height, conductor type, wind speed, and terrain data.

[0043] The vulnerability of the equipment is calculated based on the insulator configuration, the distribution of fault points, the number of trips, the equipment damage information, and the rainfall intensity.

[0044] In one possible implementation, the computing module specifically includes:

[0045] For each line segment, the weight coefficient of each indicator is calculated through fuzzy comprehensive evaluation based on the lightning density, the line exposure degree, and the equipment vulnerability.

[0046] The comprehensive risk score of the line section is calculated based on the weighting coefficient of each indicator.

[0047] The comprehensive risk score is corrected by a pre-trained deep learning model to obtain the final risk score of the line section.

[0048] The lightning risk level of the line section is determined based on the final risk score.

[0049] In one possible implementation, the generation module specifically includes:

[0050] Based on the lightning risk level of all line sections and the pre-acquired lightning nowcast data, the warning level of each line section is determined according to the preset level classification rules.

[0051] The warning level of each line section is input into the multi-objective optimization model. Based on the preset constraints, multi-objective optimization is performed to generate the differentiated lightning protection renovation scheme.

[0052] In one possible implementation, the establishing module calculates the lightning density using the lightning occurrence time, lightning occurrence location, lightning intensity, polarity parameter value, atmospheric electric field monitoring data, and thunderstorm path, specifically including:

[0053] Based on the lightning occurrence location, the lightning intensity, and the polarity parameter, an initial lightning density is generated using a spatial interpolation algorithm;

[0054] By combining the atmospheric electric field monitoring data and the thunderstorm path, the initial lightning density is dynamically corrected to obtain the lightning density.

[0055] In one possible implementation, the establishment module calculates the line exposure based on the tower height, conductor type, wind speed, and terrain data, specifically including:

[0056] Based on the tower height and the conductor type, the foundation exposure is calculated;

[0057] The basic exposure is corrected based on the wind speed and the terrain data to obtain the line exposure.

[0058] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0059] The memory stores computer-executed instructions;

[0060] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0061] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0062] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0063] The distribution network line lightning risk early warning method, device, equipment, and storage medium provided in this application embodiment establish multi-dimensional evaluation indicators based on pre-collected lightning monitoring data, line parameter data, and meteorological environmental data. According to lightning density, line exposure, and equipment vulnerability, a dynamic evaluation algorithm calculates the lightning risk level of each line segment in the distribution network. Based on the lightning risk levels of all line segments and pre-acquired lightning nowcast data, a differentiated lightning protection renovation plan is generated through a pre-set multi-objective optimization model, and this plan is then pushed to management personnel. This method achieves closed-loop management from data collection to decision execution, significantly improving the accuracy and efficiency of power grid lightning protection and reducing the lightning tripping rate. Attached Figure Description

[0064] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0065] Figure 1 A schematic diagram of the application system structure for the lightning strike risk early warning method for distribution network lines provided in this application;

[0066] Figure 2 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 1 ;

[0067] Figure 3 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 2 ;

[0068] Figure 4 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 3 ;

[0069] Figure 5 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 4 ;

[0070] Figure 6 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 5 ;

[0071] Figure 7 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 6 ;

[0072] Figure 8 A schematic diagram of the structure of the distribution network line lightning risk early warning device provided in this application;

[0073] Figure 9 A schematic diagram of the structure of the electronic device provided in this application.

[0074] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0075] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0076] With the expansion of power grid construction, the span and voltage level of distribution lines are also gradually increasing. Therefore, the risk of lightning strikes on these lines is increasing, and the economic losses and safety hazards caused by lightning disasters to regional power grids are becoming more severe. Lightning strikes are the main cause of distribution line failures, and lightning tripping has become the biggest threat to the safe and stable operation of the power grid. To take targeted risk mitigation measures in advance, it is crucial to track the lightning risk status of distribution lines in real time and conduct early warning assessments. Existing technologies typically classify lightning strike warnings according to electric field strength and lightning distance, or use real-time fault probability assessment methods based on distribution line data and lightning meteorological factors to calculate the real-time fault probability of distribution lines. However, these methods only consider lightning activity and atmospheric distribution around the distribution lines. In actual line tripping warnings, problems such as high false alarm rates and low prediction accuracy may occur. Furthermore, they rely heavily on expert experience, resulting in significant subjective influence and unsatisfactory assessment results.

[0077] To address the aforementioned issues, this application provides a method, device, equipment, and storage medium for early warning of lightning strike risks in distribution network lines, thereby improving the accuracy of lightning protection early warning. Specifically, one existing study proposed a lightning strike early warning system based on data from an atmospheric electric field meter and a lightning location system. This system classifies lightning strikes according to electric field strength and lightning distance, implementing graded lightning strike early warnings for the power grid. This method only considers lightning activity and atmospheric distribution around the distribution lines, neglecting the influence of external terrain and its own parameters. Therefore, in actual line tripping warnings, problems such as high false alarm rates and low prediction accuracy may occur. Another study proposed a method for assessing the real-time fault probability of distribution lines based on distribution line data and lightning meteorological factors, which can calculate the real-time fault probability of distribution lines. This method requires expert experience to determine weighting coefficients, and the influence of subjective factors is significant, leading to unsatisfactory assessment results. Considering these problems, the inventors investigated whether it is possible to establish multi-dimensional assessment indicators based on multi-dimensional data, predict lightning strike risk levels based on these indicators, and then generate flexible and differentiated lightning protection modification schemes based on a preset multi-objective optimization model combined with lightning nowcasting data, thereby improving the accuracy of lightning protection. Based on this, the proposed solution is presented in this application.

[0078] Figure 1 A schematic diagram of the system structure for the distribution network line lightning strike risk early warning method provided in this application is shown below. Figure 1 As shown, the system includes a data acquisition layer, a risk assessment layer, an early warning and decision-making layer, and an execution and feedback layer. The system utilizes meteorological radar and satellite data, including thunderstorm paths, rainfall intensity, wind speed, and topographic data (the impact of mountainous areas, plains, and water bodies on lightning activity), to retrieve data from the data acquisition layer in real time. The collected data is combined with on-site environmental indicators to formulate decision-making plans, thereby providing graded early warnings for lightning strike risks on distribution network lines.

[0079] The data acquisition layer is used to collect lightning monitoring data and data from the meteorological and environmental data line parameter database. The early warning and decision-making layer will then retrieve the data collected in the data acquisition layer in real time and combine the collected data with on-site environmental indicators to formulate decision-making plans.

[0080] The risk assessment layer can adopt a lightning strike risk classification model, establish multi-dimensional assessment indicators based on lightning density, line exposure, and equipment vulnerability, and then select a dynamic assessment algorithm to dynamically calculate the lightning strike risk level of the line section.

[0081] The early warning and decision-making level adopts a tiered early warning system, which triggers early warning signals based on lightning proximity forecasts and issues early warnings according to risk levels, which are divided into yellow, orange, and red alerts. In addition, the early warning and decision-making level can generate multi-objective optimization schemes based on risk levels, transformation costs, expected benefits, and existing decision-making schemes.

[0082] The execution and feedback layer includes lightning protection measures and effectiveness evaluation. The implementation of lightning protection measures adopts differentiated transformation schemes, including the installation of surge arresters, the transformation of grounding grids, and the replacement of insulators. The effectiveness evaluation and optimization involves real-time monitoring of the lightning strike failure rate and equipment damage rate after the transformation, and iterative optimization of the risk assessment model through feedback data.

[0083] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0084] Figure 2 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 1 ,like Figure 2 As shown, the method includes:

[0085] S201: Establish multi-dimensional evaluation indicators based on pre-collected lightning monitoring data, line parameter data, and meteorological environment data.

[0086] In this step, in order to improve the accuracy of lightning protection for distribution network lines, predictions can be made based on multi-dimensional data. This can be achieved by collecting lightning monitoring data, line parameter data, and meteorological environmental data in advance, and then establishing multi-dimensional evaluation indicators based on the above multi-dimensional data. These multi-dimensional evaluation indicators include lightning density, line exposure, and equipment vulnerability.

[0087] Specifically, lightning monitoring data includes lightning occurrence time, location, intensity, polarity parameter values, and atmospheric electric field monitoring data. Line parameter data includes tower height, insulator configuration, conductor type, and historical lightning strike fault records, which include fault location distribution, number of trips, and equipment damage information. Meteorological environmental data includes thunderstorm paths, rainfall intensity, wind speed, and topographic data.

[0088] Lightning density is calculated by taking into account the time of lightning occurrence, location of lightning occurrence, intensity of lightning occurrence, polarity parameter values, atmospheric electric field monitoring data, and thunderstorm path.

[0089] The line exposure is calculated based on tower height, conductor type, wind speed, and topographic data.

[0090] The vulnerability of the equipment is calculated based on the insulator configuration, fault point distribution, number of trips, equipment damage information, and rainfall intensity.

[0091] By fusing multi-source data (lightning, power lines, and weather), a quantitative indicator reflecting lightning strike risk is constructed. This avoids the one-sidedness of assessment based on a single indicator, and comprehensively assesses risk from three dimensions: external threats (lightning density), power line characteristics (exposure), and equipment status (vulnerability).

[0092] It should be noted that the lightning density in the above multidimensional assessment indicators refers to the frequency and intensity of lightning activity, which is a direct driving factor of lightning strike risk. Line exposure refers to the physical structure and geographical environment of the line, which determines its probability of attracting lightning. Equipment vulnerability refers to the equipment's own lightning resistance capability, which directly affects the probability of lightning strike failure.

[0093] S202: Based on lightning density, line exposure, and equipment vulnerability, the lightning risk level of each line segment in the distribution network is calculated using a dynamic evaluation algorithm.

[0094] In this step, after establishing multidimensional assessment indicators, the risk level of lightning strikes can be determined based on these indicators. A dynamic algorithm can be used to fuse the multidimensional indicators and quantify the risk level. This transforms complex data into actionable early warning signals, which can then guide differentiated decision-making.

[0095] Specifically, for each line segment, the weight coefficient of each indicator is calculated through fuzzy comprehensive evaluation based on lightning density, line exposure, and equipment vulnerability. The comprehensive risk score of the line segment is calculated based on the weight coefficient of each indicator. The comprehensive risk score is then corrected by a pre-trained deep learning model to obtain the final risk score of the line segment. The lightning strike risk level of the line segment is determined based on the final risk score.

[0096] S203: Based on the lightning risk level of all line sections and the pre-acquired lightning nowcast data, a differentiated lightning protection renovation plan is generated through a pre-set multi-objective optimization model.

[0097] In this step, after determining the lightning risk level of each line section, in order to achieve lightning protection efficiently and accurately, it is also necessary to develop differentiated lightning protection renovation plans based on lightning nowcast data and on-site environmental conditions, matching the optimal renovation measures for sections with different risk levels to avoid wasting resources.

[0098] Specifically, based on the lightning risk level of all line sections and the pre-acquired lightning nowcast data, the warning level of each line section is determined according to the preset level classification rules. The warning level of each line section is then input into a multi-objective optimization model. Based on preset constraints, multi-objective optimization is performed to generate differentiated lightning protection renovation schemes.

[0099] S204: Push the differentiated lightning protection renovation plan to the management personnel.

[0100] In this step, after generating a differentiated lightning protection upgrade plan, decision-making instructions can be conveyed through a visual interactive interface, thereby ensuring that managers can quickly understand the risks and implement the plan.

[0101] For example, the design of the visualization interface could be to display the risk level as a heat map, list the measures, costs, and expected effects, and display the thunderstorm countdown and construction progress.

[0102] Optionally, managers can adjust the priority of measures, and construction results can also be fed back to the system, thereby optimizing the model in the above steps.

[0103] The lightning risk early warning method for distribution network lines provided in this application establishes multi-dimensional evaluation indicators based on pre-collected lightning monitoring data, line parameter data, and meteorological environmental data. According to lightning density, line exposure, and equipment vulnerability, a dynamic evaluation algorithm calculates the lightning risk level of each line segment in the distribution network. Based on the lightning risk levels of all line segments and pre-acquired lightning nowcasting data, a differentiated lightning protection upgrade plan is generated through a pre-set multi-objective optimization model, and this plan is then pushed to management personnel. This method achieves closed-loop management from data collection to decision execution, significantly improving the accuracy and efficiency of power grid lightning protection and reducing the lightning tripping rate.

[0104] Figure 3 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 2 ,like Figure 3 As shown, based on the above embodiment, step S201 specifically includes:

[0105] S301: The lightning density is calculated using the lightning occurrence time, lightning location, lightning intensity, polarity parameter values, atmospheric electric field monitoring data, and thunderstorm path.

[0106] In this step, lightning density quantifies the intensity of the lightning threat through the spatiotemporal distribution characteristics of lightning activity. It can dynamically reflect the degree of threat posed to power lines by current and future lightning activity, providing a fundamental input for risk assessment.

[0107] The time, location, intensity, and polarity of lightning can be obtained from a lightning location system (LLS), such as 10 lightning strikes occurring in a certain area within 1 hour (maximum intensity 50kA, negative polarity 80%).

[0108] Atmospheric electric field monitoring data is used to monitor changes in the ground electric field strength in real time, such as a sudden increase in electric field strength from 1 kV / m to 8 kV / m.

[0109] Thunderstorm path prediction is the prediction by weather radar of the direction of thunderstorm movement over the next two hours.

[0110] Specifically, based on the location, intensity, and polarity parameters of lightning, an initial lightning density is generated using a spatial interpolation algorithm. This initial lightning density is then dynamically corrected by combining atmospheric electric field monitoring data and thunderstorm paths to obtain the final lightning density.

[0111] S302: The line exposure is calculated based on the tower height, conductor type, wind speed, and topographic data.

[0112] In this step, the probability of the line being susceptible to lightning strikes due to its physical structure and geographical environment is assessed. High-exposure sections can be identified, guiding the priority deployment of lightning protection resources. The line exposure can then be calculated based on the multi-dimensional data obtained in the aforementioned embodiment steps.

[0113] Specifically, based on the tower height and conductor type, the foundation exposure is calculated, and then corrected according to wind speed and topographic data to obtain the line exposure.

[0114] S303: The vulnerability of the equipment is calculated based on the insulator configuration, fault point distribution, number of trips, equipment damage information, and rainfall intensity.

[0115] In this step, equipment vulnerability can be quantified to identify weaknesses in the equipment's resistance to lightning strikes. Modification measures are then developed to address these weaknesses and reduce the lightning strike failure rate.

[0116] The insulator configuration includes the insulator type (porcelain / composite), number of discs, and creepage distance;

[0117] Grounding resistance is the resistance value of the tower grounding device (unit: Ω);

[0118] Real-time rainfall intensity: Rainfall per unit time (mm / h).

[0119] Specifically, vulnerability scoring rules are pre-defined. For example, insulator configuration scoring: porcelain insulators have lower lightning resistance and are more susceptible to pollution and wet flashover → vulnerability +15%; composite insulators have strong resistance to pollution flashover and good hydrophobicity → vulnerability -10%; for each missing standard insulator (e.g., standard 6 insulators) → vulnerability +5%.

[0120] Example: A circuit has a standard of 6 wafers, but only 5 wafers are actually installed → vulnerability +5%.

[0121] Grounding resistance rating: The grounding resistance value directly affects the lightning current discharge capability: Grounding resistance ≤ 10Ω → no additional vulnerability; Grounding resistance > 10Ω → vulnerability +5% for every 5Ω increase (e.g., 15Ω → +5%, 20Ω → +10%).

[0122] Historical fault record scoring: Number of trips: Each trip caused by lightning strike on the same tower → vulnerability +10%; Example: A tower tripped 3 times → vulnerability +30%. Equipment damage level: Minor damage (such as burns on the surface of insulators) → vulnerability +5%; Severe damage (such as broken conductors) → vulnerability +15%.

[0123] Rainfall intensity correction: Rainfall wets the insulator surface, reducing flashover voltage: Rainfall intensity ≥ 50 mm / h → vulnerability +15%; Rainfall intensity ≥ 100 mm / h → vulnerability +25%.

[0124] Scoring is accumulated according to the insulator type, number of insulators, grounding resistance, fault point distribution, number of trips, and equipment damage information, following the rules mentioned above.

[0125] Example: Porcelain insulator (+15%) + number of pieces less than 1 (+5%) + grounding resistance 15Ω (+5%) + 3 trips (+30%) = initial score 55%.

[0126] If the real-time rainfall intensity is 60 mm / h, the vulnerability increases by 15%, resulting in a final score of 55% + 15% = 70%.

[0127] Optionally, the above process can also be dynamically adjusted based on real-time data updates, such as updating rainfall intensity every 5 minutes to trigger dynamic correction of the vulnerability score; if rainfall stops, the rainfall correction value is removed.

[0128] The lightning risk early warning method for distribution network lines provided in this application calculates lightning density based on lightning occurrence time, location, intensity, polarity parameter values, atmospheric electric field monitoring data, and thunderstorm path. It also calculates line exposure based on tower height, conductor type, wind speed, and terrain data, and calculates equipment vulnerability based on insulator configuration, fault point distribution, tripping frequency, equipment damage information, and rainfall intensity. This multi-dimensional dynamic assessment enables the system to accurately quantify and provide real-time early warning of lightning risk, significantly improving the proactiveness and cost-effectiveness of power grid lightning protection.

[0129] Figure 4 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 3 ,like Figure 4 As shown, based on the above embodiment, step S202 specifically includes:

[0130] S401: For each line section, the weight coefficient of each indicator is calculated through fuzzy comprehensive evaluation based on lightning density, line exposure and equipment vulnerability.

[0131] In this step, after determining the multi-dimensional assessment indicators, in order to accurately predict the lightning strike risk level, the distribution network lines are divided into sections for lightning strike risk level confirmation.

[0132] First, it is necessary to determine the weight coefficients for each indicator. Uncertainty is handled through fuzzy mathematics, combining expert experience with statistical data to quantify the relative importance of each indicator to lightning strike risk. This avoids subjective weighting bias and dynamically allocates the weights for lightning density, line exposure, and equipment vulnerability.

[0133] For each line segment, the correlation between different indicators and the number of faults in different segments is analyzed, the membership function of each indicator is defined, and the actual values ​​are transformed into fuzzy sets.

[0134] Example: Lightning density is divided into three fuzzy sets: "low", "medium", and "high", with a triangular distribution of membership function.

[0135] Fuzzy rules are generated based on expert experience and historical data matching.

[0136] Example rule 1: If the lightning density is "high" and the exposure is "medium", then the lightning density weight = 0.6 and the exposure weight = 0.3;

[0137] Example rule 2: If a device's vulnerability is "extremely high", its weight is automatically increased to 0.4.

[0138] Then, the center of gravity (COG) method is used to convert the fuzzy output into accurate weight coefficients.

[0139] Example: Lightning density weight = 0.5, exposure = 0.3, vulnerability = 0.2.

[0140] S402: The comprehensive risk score of the line section is calculated based on the weight coefficient of each indicator.

[0141] In this step, after determining the weighting coefficient of each indicator, the comprehensive risk score for the line segment is determined. The overall risk is quantified through weighted summation to reflect the synergistic effect of multiple indicators. The multi-dimensional indicators are normalized into a single score, facilitating risk classification.

[0142] Specifically, lightning density, exposure level, and vulnerability are mapped to the [0,1] interval. Then, a weighted average is calculated using the weighting coefficients obtained in the previous steps to obtain a comprehensive risk score.

[0143] S403: The comprehensive risk score is corrected by a pre-trained deep learning model to obtain the final risk score of the line section.

[0144] In this step, to improve scoring accuracy and reduce false alarms / missed alarms, neural networks can be used to capture nonlinear relationships (such as sudden weather changes) that are not covered by fuzzy evaluation.

[0145] For example, real-time data of the current environment (electric field intensity change rate, thunderstorm path change indicators, wind speed gradient, etc.) and the comprehensive risk score obtained in the above steps are input into a pre-trained deep learning model to calculate the output correction coefficient, thereby obtaining the final risk score.

[0146] S404: Determine the lightning risk level of the line section based on the final risk score.

[0147] In this step, after determining the final risk score for each segment, continuous scores can be mapped to discrete risk levels through threshold division, generating actionable early warning signals (yellow / orange / red) to guide emergency response.

[0148] For example, the ranking rules can be set as follows:

[0149] Low risk: 0-0.4; Medium risk: 0.4-0.7; High risk: 0.7 and above.

[0150] Optionally, the threshold can be automatically adjusted based on seasonal factors (such as the rainy season). For example, the red threshold can be reduced to 0.65 during the rainy season.

[0151] The lightning strike risk early warning method for distribution network lines provided in this application, for each line segment, calculates the weight coefficient of each indicator through fuzzy comprehensive evaluation based on lightning density, line exposure, and equipment vulnerability. A comprehensive risk score for the line segment is calculated based on the weight coefficients of each indicator. The comprehensive risk score is then corrected using a pre-trained deep learning model to obtain the final risk score for the line segment. The lightning strike risk level of the line segment is determined based on the final risk score. This method reduces subjective errors and improves the response speed of weight adjustment through fuzzy comprehensive evaluation. It also reduces the scoring error rate by fusing real-time data through a deep learning model and improves the accuracy of identifying high-risk sections by dynamically adapting to environmental changes through thresholds.

[0152] Figure 5 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 4 ,like Figure 5 As shown, based on the above embodiment, step S203 specifically includes:

[0153] S501: Based on the lightning risk level of all line sections and the pre-acquired lightning nowcast data, determine the warning level for each line section according to the preset level classification rules.

[0154] In this step, after determining the lightning risk level for each section, the warning level can be determined based on the lightning risk level and the lightning nowcast data to improve the accuracy of lightning protection. The lightning nowcast data includes the thunderstorm path, estimated arrival time (e.g., 0.5–2 hours), and the rate of change of electric field intensity.

[0155] Specifically, warning levels are dynamically determined by combining real-time lightning risk levels with lightning nowcast data (such as thunderstorm paths and time windows). Abstract risk scores are transformed into actionable warning signals (yellow / orange / red) to guide differentiated emergency responses.

[0156] The rules for classifying warning levels can be set according to the actual situation, and this application embodiment does not impose specific limitations.

[0157] For example, a yellow alert indicates low risk, but the thunderstorm path is expected to deviate from the designated area within the next 2 hours.

[0158] Orange alert: Medium risk + Thunderstorm path may cover the line in the next hour;

[0159] Red Alert: High Risk + Thunderstorm Path to Directly Hit Power Line in the Next 0.5 Hours with Sudden Increase in Electric Field Intensity.

[0160] S502: Input the warning level of each line section into the multi-objective optimization model, perform multi-objective optimization based on preset constraints, and generate differentiated lightning protection renovation schemes.

[0161] In this step, taking into account the actual on-site conditions, a differentiated lightning protection renovation plan can be generated based on a multi-objective optimization model to ensure that the plan achieves the best balance among multiple objectives and generates the most cost-effective combination of renovation measures for sections with different warning levels.

[0162] Optimization objectives can include renovation cost budgets, such as setting a maximum renovation cost for a single section and a total budget constraint. Expected benefit objectives, such as setting a threshold for reducing the lightning strike failure rate.

[0163] Constraints may include that high-risk sections must be covered by at least one of the following: installation of surge arresters or modification of grounding grids; no more than two modification measures for the same tower (such as replacement of surge arresters and insulators); and the total cost must not exceed the budget limit.

[0164] For example, a differentiated transformation scheme may include:

[0165] Red alert zone: Immediately implement surge arrester installation and grounding grid modification;

[0166] Orange alert zone: Replace surge arresters or insulators according to priority;

[0167] Yellow alert zone: No modifications will be made for the time being, only enhanced monitoring will be implemented.

[0168] The lightning strike risk early warning method for distribution network lines provided in this application, based on the lightning strike risk level of all line sections and pre-acquired lightning nowcasting data, determines the early warning level of each line section according to preset level classification rules. The early warning level of each line section is then input into a multi-objective optimization model. Based on preset constraints, multi-objective optimization is performed to generate differentiated lightning protection upgrade schemes. This method achieves dynamic hierarchical management of "one strategy per section" through real-time risk calculation and dynamic prediction of lightning activity for each line section. This not only improves the accuracy and timeliness of power grid lightning protection but also significantly reduces operation and maintenance costs.

[0169] Figure 6 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 5 ,like Figure 6 As shown, based on the above embodiments, step S301 specifically includes:

[0170] S601: Based on the location, intensity, and polarity parameters of lightning occurrence, an initial lightning density is generated using a spatial interpolation algorithm.

[0171] S602: By combining atmospheric electric field monitoring data and thunderstorm paths, the initial lightning density is dynamically corrected to obtain the lightning density.

[0172] Discrete lightning events are transformed into continuous spatial density distributions using spatial interpolation algorithms, quantifying the intensity of lightning activity per unit area. This provides fundamental data for risk assessment, reflecting the spatiotemporal distribution characteristics of lightning.

[0173] The location of the lightning strike is indicated by its latitude and longitude coordinates (e.g., 120.5°E, 30.3°N).

[0174] Lightning intensity: Lightning current amplitude (unit kA, e.g., 40kA);

[0175] Polarity parameter: positive polarity (+) or negative polarity (-).

[0176] The kernel function of the spatial interpolation algorithm can be a Gaussian kernel function, and the bandwidth (radius of influence range) is dynamically adjusted according to the terrain. The weights of lightning emphasis and polarity are determined, and for each grid point, the weighted density value of all lightning within its surrounding bandwidth range is calculated.

[0177] For example, three lightning strikes occurred within a 1 km² grid in a plain area:

[0178] Lightning 1: 40kA (weight 1.0), negative polarity (1.2) → equivalent weight = 1.0 × 1.2 = 1.2;

[0179] Lightning 2: 60kA (weight 1.5), negative polarity (1.2) → equivalent weight = 1.5 × 1.2 = 1.8;

[0180] Lightning 3: 30kA (weight 1.0), positive polarity (1.0) → equivalent weight = 1.0 × 1.0 = 1.0;

[0181] Kernel density calculation (bandwidth 3km): Initial density ≈ 1.33 times / km².

[0182] By monitoring the atmospheric electric field in real time and predicting thunderstorm paths, the initial density is adjusted to reflect the dynamic changes in thunderclouds. This improves the timeliness and accuracy of lightning density prediction, enabling early warning of high-risk areas.

[0183] For example, atmospheric electric field correction:

[0184] Electric field strength change rate: If the electric field strength change rate is ≥500V / (m·min), it indicates that the thundercloud is rapidly strengthening and the lightning density is increased by 20%.

[0185] Example: Initial density 1.33 times / km² → Increase by 20% → 1.33 × 1.2 = 1.6 times / km².

[0186] Thunderstorm path correction:

[0187] Path coverage area: The grid that is predicted to be covered by thunderstorms in the next 2 hours, with lightning density weighted by 1.2 times;

[0188] Path deviation area: Lightning density reduced to 0.8 times.

[0189] Example: If the above grid is located on the path of a thunderstorm → 1.6 × 1.2 = 1.92 times / km².

[0190] Final lightning density: 1.92 times / km².

[0191] The lightning strike risk early warning method for distribution network lines provided in this application generates an initial lightning density based on the location, intensity, and polarity parameters of lightning strikes using a spatial interpolation algorithm. This initial lightning density is then dynamically corrected by combining atmospheric electric field monitoring data and thunderstorm paths to obtain the final lightning density. This method, through spatial interpolation and dynamic correction, upgrades lightning density calculation from "static statistics" to "real-time prediction," significantly improving the proactive lightning protection capabilities of the power grid.

[0192] Figure 7 Flowchart of the lightning strike risk warning method for distribution network lines provided in this application Figure 6 ,like Figure 7 As shown, based on the above embodiments, step S302 specifically includes:

[0193] S701: The foundation exposure is calculated based on the tower height and conductor type.

[0194] S702: The basic exposure is corrected based on wind speed and topographic data to obtain the line exposure.

[0195] Tower height and conductor type directly affect the probability of a line being exposed to lightning; tall towers and overhead conductors are more likely to attract lightning. Quantifying the lightning strike risk caused by the line's own physical structure provides a baseline value for subsequent environmental modifications.

[0196] The conductor types can include overhead bare conductors (coefficient 1.0); overhead insulated conductors (coefficient 0.8); and underground cables (coefficient 0.3).

[0197] The baseline exposure can be calculated using the following formula:

[0198]

[0199] in, This represents the tower height coefficient, where H represents the tower height. This represents the conductor type coefficient, where T represents the conductor type.

[0200] Wind speed and topography indirectly affect exposure levels by altering the distribution of the electric field around the power line or the frequency of lightning activity. Adding the influence of environmental factors to the baseline exposure level improves the accuracy of the assessment.

[0201] For example, wind speed (W):

[0202] When the wind speed is ≥ level 8 (17.2 m / s), the swaying of the conductor increases the risk of exposure, and the correction factor is +0.2;

[0203] When the wind speed is less than level 8, the correction factor is 0.

[0204] Topography (D):

[0205] Plains (coefficient 1.0);

[0206] Mountainous areas (coefficient 1.3, orographic lifting thunderstorm activity);

[0207] Water area (coefficient 1.5, increased conductivity of water increases the probability of lightning attraction).

[0208] The corrected formula is then obtained as follows: .

[0209] It should be noted that the above formula setting is only an example and can be modified according to the actual application scenario. This application embodiment does not impose specific limitations.

[0210] The lightning strike risk early warning method for distribution network lines provided in this application calculates the foundation exposure based on tower height and conductor type, and then corrects the foundation exposure according to wind speed and topographic data to obtain the line exposure. This method, through step-by-step calculation and correction, accurately reflects the combined risk of "its own structure + environment" in the line exposure, providing a reliable basis for lightning protection decisions.

[0211] Figure 8 The schematic diagram of the lightning risk early warning device for distribution network lines provided in this application is as follows: Figure 8 As shown, the distribution network line lightning strike risk early warning device 800 provided in this embodiment includes:

[0212] Module 801 is established to create multidimensional evaluation indicators based on pre-collected lightning monitoring data, line parameter data, and meteorological environment data. The multidimensional evaluation indicators include lightning density, line exposure, and equipment vulnerability.

[0213] The calculation module 802 is used to calculate the lightning risk level of each line segment in the distribution network based on lightning density, line exposure and equipment vulnerability through a dynamic evaluation algorithm.

[0214] The generation module 803 is used to generate differentiated lightning protection renovation schemes based on the lightning risk level of all line sections and the pre-acquired lightning nowcast data, through a pre-set multi-objective optimization model.

[0215] The push module 804 is used to push differentiated lightning protection renovation plans to management personnel.

[0216] Optionally, lightning monitoring data includes lightning occurrence time, lightning location, lightning intensity, polarity parameter values, and atmospheric electric field monitoring data;

[0217] The line parameter data includes tower height, insulator configuration, conductor type and historical lightning strike fault records. The historical lightning strike fault records include fault point distribution, number of trips and equipment damage information.

[0218] Meteorological and environmental data include thunderstorm paths, rainfall intensity, wind speed, and topographic data.

[0219] In one possible implementation, module 802 is established, specifically including:

[0220] Lightning density is calculated by taking into account the time of lightning occurrence, location of lightning occurrence, intensity of lightning occurrence, polarity parameter values, atmospheric electric field monitoring data, and thunderstorm path.

[0221] The line exposure is calculated based on tower height, conductor type, wind speed, and topographic data.

[0222] The vulnerability of the equipment is calculated based on the insulator configuration, fault point distribution, number of trips, equipment damage information, and rainfall intensity.

[0223] In one possible implementation, the computing module 802 specifically includes:

[0224] For each line section, the weight coefficient of each indicator is calculated through fuzzy comprehensive evaluation based on lightning density, line exposure and equipment vulnerability.

[0225] The comprehensive risk score of the line segment is calculated based on the weighting coefficient of each indicator.

[0226] The comprehensive risk score is corrected by a pre-trained deep learning model to obtain the final risk score for the line section.

[0227] The lightning risk level of the line section is determined based on the final risk score.

[0228] Optionally, module 803 is generated, specifically including:

[0229] Based on the lightning risk level of all line sections and the pre-acquired lightning nowcast data, the warning level of each line section is determined according to the preset level classification rules.

[0230] The warning level of each line section is input into the multi-objective optimization model. Based on the preset constraints, multi-objective optimization is performed to generate differentiated lightning protection renovation schemes.

[0231] In one possible implementation, the module 801 calculates the lightning density using the lightning occurrence time, lightning location, lightning intensity, polarity parameter values, atmospheric electric field monitoring data, and thunderstorm path, specifically including:

[0232] Based on the location, intensity, and polarity parameters of lightning occurrence, an initial lightning density is generated using a spatial interpolation algorithm;

[0233] By combining atmospheric electric field monitoring data and thunderstorm paths, the initial lightning density is dynamically corrected to obtain the final lightning density.

[0234] In one possible implementation, module 801 calculates the line exposure based on tower height, conductor type, wind speed, and terrain data, specifically including:

[0235] Based on the tower height and conductor type, the foundation exposure is calculated;

[0236] The basic exposure is corrected based on wind speed and topographic data to obtain the line exposure.

[0237] The distribution network line lightning risk warning device provided in this embodiment can execute the distribution network line lightning risk warning method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0238] Figure 9 A schematic diagram of the structure of the electronic device provided in this application. Figure 9 As shown, the electronic device 900 provided in this embodiment includes at least one processor 901 and a memory 902. Optionally, the electronic device 900 further includes a communication component 903. The processor 901, memory 902, and communication component 903 are connected via a bus 904.

[0239] In a specific implementation, at least one processor 901 executes computer execution instructions stored in memory 902, causing at least one processor 901 to perform the methods of the above embodiments.

[0240] The specific implementation process of processor 901 can be found in the above-mentioned method embodiments, and its implementation principle and technical effect are similar. Therefore, it will not be repeated here.

[0241] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0242] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0243] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0244] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the methods of the various embodiments described above.

[0245] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the methods of the above embodiments.

[0246] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0247] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0248] The division of units is merely a logical functional division; 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 indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0249] 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.

[0250] In addition, 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.

[0251] If a function 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 this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this 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.

[0252] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0253] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A distribution line lightning stroke risk early warning method, characterized in that, The method comprises the following steps: Based on the pre-acquired lightning monitoring data, line parameter data and meteorological environment data, a multi-dimensional evaluation index is established, which includes lightning density, line exposure and equipment vulnerability; According to the lightning density, line exposure and equipment vulnerability, the lightning risk level of each line section in the distribution network line is calculated by a dynamic evaluation algorithm; Based on the lightning risk level of all line sections and the pre-acquired lightning proximity forecast data, a differentiated lightning protection reconstruction scheme is generated by a pre-set multi-objective optimization model; The differentiated lightning protection reconstruction scheme is pushed to the management personnel.

2. The method of claim 1, wherein, The lightning monitoring data includes lightning occurrence time, lightning occurrence location, lightning occurrence intensity, polarity parameter value and atmospheric electric field monitoring data; The line parameter data includes tower height, insulator configuration, conductor type and historical lightning fault record, and the historical lightning fault record includes fault point distribution, trip number and equipment damage information; The meteorological environment data includes thunderstorm path, rainfall intensity, wind speed and topographic data.

3. The method of claim 2, wherein, Based on the pre-acquired lightning monitoring data, line parameter data and meteorological environment data, a multi-dimensional evaluation index is established, which includes: The lightning density is calculated based on the lightning occurrence time, lightning occurrence location, lightning occurrence intensity, polarity parameter value, atmospheric electric field monitoring data and thunderstorm path; The line exposure is calculated based on the tower height, conductor type, wind speed and topographic data; The equipment vulnerability is calculated based on the insulator configuration, fault point distribution, trip number, equipment damage information and rainfall intensity.

4. The method according to claim 1 or 3, characterized in that, According to the lightning density, line exposure and equipment vulnerability, the lightning risk level of each line section in the distribution network line is calculated by a dynamic evaluation algorithm, which includes: For each line section, the weight coefficient of each index is calculated based on the lightning density, line exposure and equipment vulnerability by fuzzy comprehensive evaluation; The comprehensive risk score of the line section is calculated based on the weight coefficient of each index; The final risk score of the line section is obtained by correcting the comprehensive risk score through a pre-trained deep learning model; The lightning risk level of the line section is determined based on the final risk score.

5. The method of claim 1, wherein, Based on the lightning risk level of all line sections and the pre-acquired lightning proximity forecast data, a differentiated lightning protection reconstruction scheme is generated by a pre-set multi-objective optimization model, which includes: Based on the lightning risk level of all line sections and the pre-acquired lightning proximity forecast data, the warning level of each line section is determined according to the pre-set grade division rule; The warning level of each line section is input into the multi-objective optimization model, and the multi-objective optimization is performed based on the pre-set constraint condition to generate the differentiated lightning protection reconstruction scheme.

6. The method of claim 3, wherein, The lightning density is calculated based on the lightning occurrence time, the lightning occurrence location, the lightning occurrence intensity, the polarity parameter value, the atmospheric electric field monitoring data, and the thunderstorm path, and includes: Based on the lightning occurrence location, the lightning occurrence intensity, and the polarity parameter, an initial lightning density is generated by a spatial interpolation algorithm; The initial lightning density is dynamically corrected based on the atmospheric electric field monitoring data and the thunderstorm path to obtain the lightning density.

7. The method of claim 3, wherein, The line exposure degree is calculated based on the tower height, the conductor type, the wind speed, and the topographic and geomorphic data, and includes: Based on the tower height and the conductor type, a basic exposure degree is calculated; The basic exposure degree is corrected based on the wind speed and the topographic and geomorphic data to obtain the line exposure degree.

8. A lightning stroke risk early warning device for a distribution network line, characterized by, It includes: The establishment module is used to establish a multi-dimensional evaluation index based on pre-collected lightning monitoring data, line parameter data, and meteorological environment data, and the multi-dimensional evaluation index includes lightning density, line exposure degree, and device vulnerability; The calculation module is used to calculate the lightning risk level of each line section in the distribution network line based on the lightning density, the line exposure degree, and the device vulnerability through a dynamic evaluation algorithm; The generation module is used to generate a differentiated lightning protection reconstruction scheme based on the lightning risk level of all line sections and pre-acquired lightning proximity forecast data through a pre-set multi-objective optimization model; The push module is used to push the differentiated lightning protection reconstruction scheme to the management personnel.

9. An electronic device, comprising: It includes: A memory and a processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the distribution network line lightning risk early warning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the distribution network line lightning risk early warning method according to any one of claims 1 to 7.

Images