Wind power plant station current collection line lightning protection evaluation optimization method and system

Abstract

The invention relates to the technical field of wind power plant station lightning protection, and particularly discloses a wind power plant station current collection line lightning protection evaluation optimization method and system, and the method comprises the steps: obtaining current collection line site blocks and corresponding current collection line site data, and determining the clustering subarea of each site block according to the current collection line site data; determining a corresponding clustering center according to the clustering partition of the site block, and determining a lightning protection evaluation level of the site block according to the clustering center; historical lightning stroke events of the current collection line site are obtained, a strong association rule of the historical lightning stroke events is mined, and a lightning protection optimization strategy of the site block is determined according to the strong association rule; and judging whether the site block needs to be subjected to lightning protection optimization or not according to the lightning protection evaluation grade, and if the site block needs to be subjected to lightning protection optimization, performing lightning protection optimization on the site block according to a lightning protection optimization strategy. According to the invention, the lightning protection grade of the current collection line site can be accurately evaluated in blocks, and meanwhile, the targeted lightning protection optimization strategy is generated, so that the lightning protection performance of the current collection line site is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of lightning protection for wind farms, and more specifically, to a method and system for evaluating and optimizing lightning protection for collector lines of wind farms. Background Art

[0002] Wind farm collector lines are a system for transmitting electricity, connecting wind turbines, substations, and the power grid. Based on the transmission medium, they are categorized as overhead lines and cable lines. Overhead lines are widely used due to their simple structure, short construction period, low construction costs, large transmission capacity, and easy maintenance and repair. Except in special circumstances such as narrow terrain, congested lines, crossing critical areas, or protecting forests, overhead transmission lines typically use insulators to mount conductors on towers and interconnect with wind farms or substations to form a power system or grid for transmitting electricity.

[0003] Due to the complex terrain in wind farm locations, some areas experience strong thunderstorms, with frequent, intense, and widespread strikes. When lightning strikes occur, high-density lightning currents can cover nearly all of the collector lines. The collector lines, however, run along hilltops, are prominent and face a steep ground inclination, reducing the ground's shielding effect and making them highly susceptible to lightning strikes. Due to the complex terrain of the collector line sites, existing lightning protection assessments often deviate significantly from actual conditions, making it difficult to generate effective optimization strategies. This results in poor lightning protection performance for wind farm collector lines. Summary of the Invention

[0004] The present invention provides a method and system for optimizing lightning protection assessment of wind farm collector lines, which is used to solve the problems in the prior art of inaccurate lightning protection assessment results and ineffective optimization strategies for wind farm collector lines, including: Obtaining collector line site blocks and corresponding collector line site data, and determining cluster partitions of each site block based on the collector line site data; Determine the corresponding cluster center according to the cluster partition of the site block, and determine the lightning protection assessment level of the site block according to the cluster center; Obtain historical lightning strike events at the collector line site, mine strong association rules of historical lightning strike events, and determine the lightning protection optimization strategy for the site block based on the strong association rules; Determine whether the site area needs lightning protection optimization based on the lightning protection assessment level. If lightning protection optimization is required, perform lightning protection optimization on the site area according to the lightning protection optimization strategy.

[0005] Furthermore, the obtaining of collector line site blocks and corresponding collector line site data, and determining cluster partitions of each site block based on the collector line site data, includes: Obtain a preset grid, and divide the collector line site according to the preset grid to obtain a number of site blocks; Determine the altitude, undulation characteristics and distance to water of the site block based on site data, and determine the lightning strike probability of the site based on the altitude, undulation characteristics and distance to water; Determine the ambient humidity, ambient temperature and electric field gradient of the site area based on site data, and determine the lightning strike intensity of the site based on the ambient humidity, ambient temperature and electric field gradient; The clustering and partitioning of each site block is determined based on the site lightning strike probability and site lightning strike intensity.

[0006] Furthermore, the clustering and partitioning of each site block according to the site lightning strike probability and site lightning strike intensity includes: A sample data set is established based on the site lightning strike probability and site lightning strike intensity, and k initial cluster centers of the sample data set are randomly selected; Calculate the Euclidean distance between the sample data in the sample data set and the initial cluster center, and divide each site block into the corresponding cluster partition according to the Euclidean distance between the sample data in the sample data set and the initial cluster center; Calculate the average value of the sample data in each cluster partition, and recalculate the cluster center based on the average value of the sample data in each cluster partition; Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the preset maximum number of iterations, and obtain the cluster partitioning of each site block.

[0007] Furthermore, the step of determining the corresponding cluster center according to the cluster partition of the site block, and determining the lightning protection assessment level of the site block according to the cluster center, includes: Setting the venue block as the venue node, obtaining the venue distance value of the venue nodes in the same cluster partition, and connecting the venue nodes whose venue distance value is less than a first preset threshold with a line; Obtain the node degrees of the site nodes after line connection, and determine the influence coefficient of the site nodes according to the node degrees; Obtain the cluster center of the cluster partition corresponding to the site node, and determine the lightning protection assessment level of the corresponding site block based on the cluster center and affected coefficient of the site node.

[0008] Furthermore, determining the lightning protection assessment level of the corresponding site block according to the cluster center and the influence coefficient of the site node includes: Determine the central lightning strike probability and central lightning strike intensity of the cluster center according to the cluster center of the site nodes, and calculate the lightning protection assessment level of the site block based on the lightning protection assessment level calculation formula according to the central lightning strike probability, central lightning strike intensity and affected coefficient; The calculation formula for the lightning protection assessment level is specifically:

[0009] in, The lightning protection assessment level of the site area, is the affected coefficient, is the central lightning strike probability, is the preset standard center lightning strike probability, is the central lightning strike intensity, For the preset standard center lightning intensity, , are the first weight and the second weight respectively.

[0010] Furthermore, the mining of strong association rules of historical lightning events and determining the lightning protection optimization strategy of the site block according to the strong association rules include: Determine the lightning strike parameters of each site block based on historical lightning strike events at the collector line site. The lightning strike parameters include lightning strike severity, occurrence time, tower density, and periodic ambient humidity, and discretize the lightning strike parameters. Strong association rules are mined based on the discretized lightning strike parameters, and the lightning strike factors of each site block are determined based on the strong association rules. The corresponding lightning protection optimization strategy is determined based on the lightning strike factors of the site block.

[0011] Furthermore, mining strong association rules based on the discretized lightning stroke parameters includes: S1, scan the transaction database, calculate the minimum support of all items under each lightning strike parameter in the transaction database, sort them in ascending order according to the minimum support of the items, generate candidate frequent 1-item sets, delete the items with preset minimum support from the candidate frequent 1-item sets, and obtain the frequent 1-item set X1; S2, scan the pre-established decision table J1, delete the rows in decision table J1 that do not include any item set in X1, and obtain decision table J2. Similarly, obtain decision table Jk and candidate frequent k item sets; S3, delete the item set Ik that does not contain the lightning strike severity in the candidate frequent k-item set, obtain the minimum support of each transaction in Ik, delete the item set with less than the preset minimum support in Ik, and generate the frequent k-item set Xk; S4, delete the rows in Jk that do not include any item set in Xk, and obtain the decision table Jk+1; S5, repeat steps S3 and S4 until the frequent k-item set Xk is empty; S6, calculate the confidence of each frequent k-item set. If the confidence of the frequent k-item set is greater than the preset minimum confidence, a strong association rule is obtained. This process continues until the confidence calculation of all frequent k-item sets is completed, and the strong association rule of the site block is obtained.

[0012] Furthermore, the determination of the corresponding lightning protection optimization strategy according to the lightning strike factors of the site block includes: Establish a lightning protection strategy database, obtain lightning strike factor data and corresponding lightning protection optimization strategies in the lightning protection strategy database, and establish a training sample set based on the lightning strike factor data and the corresponding lightning protection optimization strategies; Establish an initial strategy generation model based on the training sample set and train the initial strategy generation model to obtain a trained strategy generation model; The lightning strike factors corresponding to the site blocks are input into the trained strategy generation model to obtain the corresponding lightning protection optimization strategy.

[0013] Furthermore, judging whether the site block needs to be optimized for lightning protection according to the lightning protection assessment level, and if lightning protection optimization is required, optimizing the site block for lightning protection according to the lightning protection optimization strategy includes: Obtain the preset standard lightning protection level and calculate the difference between the lightning protection assessment level of the site block and the preset standard lightning protection level; Determine whether the difference between the lightning protection assessment level of the site block and the preset standard lightning protection level is greater than a second preset threshold; if the difference between the lightning protection assessment level of the site block and the preset standard lightning protection level is greater than the second preset threshold, perform lightning protection optimization on the collector line of the site block according to the lightning protection optimization strategy; If the difference between the lightning protection assessment level of the site block and the preset standard lightning protection level is less than or equal to the second preset threshold, the lightning protection optimization of the collector line is not performed.

[0014] In order to achieve the above objectives, the present invention also provides a wind farm station collector line lightning protection assessment and optimization system, comprising: A partitioning module is used to obtain the collector line site blocks and the corresponding collector line site data, and determine the cluster partitioning of each site block according to the collector line site data; An evaluation module is used to determine the corresponding cluster center according to the cluster partition of the site block, and determine the lightning protection evaluation level of the site block according to the cluster center; The mining module is used to obtain historical lightning strike events at the collector line site, mine strong association rules of historical lightning strike events, and determine the lightning protection optimization strategy of the site block based on the strong association rules; The optimization module is used to determine whether the site block needs lightning protection optimization based on the lightning protection assessment level. If lightning protection optimization is required, the site block is optimized according to the lightning protection optimization strategy.

[0015] The beneficial effects of the present invention are: By applying the above technical solution, the present invention divides the collector line site into blocks and evaluates the lightning protection assessment level of each block based on different site block data, thereby improving the accuracy and reliability of the lightning protection assessment. At the same time, by mining the strong association rules of historical lightning strike events in the site blocks, the optimal lightning protection optimization strategy is generated, effectively improving the lightning protection performance of the collector line site. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 The overall flow chart of a method for optimizing lightning protection assessment of wind farm collector lines proposed in an embodiment of the present invention is shown; Figure 2 The present invention provides a schematic structural diagram of a wind farm station collector line lightning protection evaluation and optimization system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0019] The present application embodiment provides a method for optimizing lightning protection assessment of wind farm station collector lines, such as Figure 1 Shown, including: S101, obtaining collector line site blocks and corresponding collector line site data, and determining cluster partitions of each site block based on the collector line site data; In some embodiments of the present application, the obtaining of collector line site blocks and corresponding collector line site data, and determining the clustering and partitioning of each site block based on the collector line site data, includes: obtaining a preset grid, dividing the collector line site according to the preset grid to obtain a plurality of site blocks; determining the altitude, undulation characteristic values and water distance of the site block based on the site data, and determining the site lightning strike probability based on the altitude, undulation characteristic values and water distance; determining the ambient humidity, ambient temperature and electric field gradient of the site block based on the site data, and determining the site lightning strike intensity based on the ambient humidity, ambient temperature and electric field gradient; and determining the clustering and partitioning of each site block based on the site lightning strike probability and the site lightning strike intensity.

[0020] In this embodiment, the altitude is the average altitude of the site block. The higher the altitude, the greater the probability of lightning strike. The undulation characteristic value of the site block is the difference between the altitude of the highest point and the altitude of the lowest point. The undulation degree of the site block is determined by the undulation characteristic value. The higher the undulation degree, the higher the degree of electric field distortion in the corresponding area and the greater the probability of lightning strike. The water area distance is the minimum distance between the site block and the nearest water area. The lower the water area distance, the greater the probability of lightning strike. By combining the altitude of the site block, the undulation characteristic value and the water area distance, the site lightning strike probability of the corresponding block can be calculated.

[0021] In this embodiment, the electric field gradient is the atmospheric electric field intensity gradient of the site area block. The higher the electric field gradient, the greater the lightning strike intensity. The site lightning strike intensity is calculated by combining the ambient humidity, ambient temperature and electric field gradient, and the site area blocks are clustered according to the site lightning strike probability and site lightning strike intensity to obtain the cluster partition of each site area block.

[0022] In some embodiments of the present application, the cluster partitioning of each site area block according to the site lightning strike probability and the site lightning strike intensity includes: establishing a sample data set according to the site lightning strike probability and the site lightning strike intensity, and randomly selecting k initial cluster centers of the sample data set; calculating the Euclidean distance from the sample data in the sample data set to the initial cluster center, and dividing each site area block into a corresponding cluster partition according to the Euclidean distance from the sample data in the sample data set to the initial cluster center; calculating the average value of the sample data in each cluster partition, and recalculating the cluster center according to the average value of the sample data in each cluster partition; repeatedly iterating the above steps until the cluster center no longer changes or the number of iterations reaches a preset maximum number of iterations, thereby obtaining the cluster partitioning of each site area block.

[0023] S102, determining a corresponding cluster center according to the cluster partition of the site block, and determining a lightning protection assessment level of the site block according to the cluster center; In some embodiments of the present application, the method of determining the corresponding cluster center according to the cluster partition of the site area block and determining the lightning protection assessment level of the site area block according to the cluster center includes: setting the site area block as a site node, obtaining the site distance value of the site nodes in the same cluster partition, and connecting the site nodes whose site distance value is less than a first preset threshold value with lines; obtaining the node degree of the site node after the line connection, and determining the affected coefficient of the site node according to the node degree; obtaining the cluster center of the cluster partition corresponding to the site node, and determining the lightning protection assessment level of the corresponding site area block according to the cluster center and the affected coefficient of the site node.

[0024] In this embodiment, the site nodes within the cluster partition are connected by line according to the site distance of the site nodes within the same cluster partition. The higher the degree of the site node within the same cluster partition, the higher its influence coefficient. The lightning protection assessment level of the corresponding site block is determined by the cluster center and influence coefficient of the site node.

[0025] In some embodiments of the present application, determining the lightning protection assessment level of the corresponding site block according to the cluster center and the affected coefficient of the site node includes: determining the central lightning strike probability and the central lightning strike intensity of the cluster center according to the cluster center of the site node, and calculating the lightning protection assessment level of the site block based on the lightning strike probability, the central lightning strike intensity and the affected coefficient based on the lightning protection assessment level calculation formula; the lightning protection assessment level calculation formula is specifically,

[0026] in, The lightning protection assessment level of the site area, is the affected coefficient, is the central lightning strike probability, is the preset standard center lightning strike probability, is the central lightning strike intensity, For the preset standard center lightning intensity, , are the first weight and the second weight respectively.

[0027] S103, obtaining historical lightning strike events at the collector line site, mining strong association rules of the historical lightning strike events, and determining a lightning protection optimization strategy for the site block based on the strong association rules; In some embodiments of the present application, the method of mining strong association rules of historical lightning strike events and determining the lightning protection optimization strategy of the site block according to the strong association rules includes: determining the lightning strike parameters of each site block according to the historical lightning strike events of the collector line site, the lightning strike parameters including the severity of the lightning strike, the time of occurrence, the pole tower density, and the periodic environmental humidity, and discretizing the lightning strike parameters; mining strong association rules according to the discretized lightning strike parameters, determining the lightning strike factors of each site block according to the strong association rules, and determining the corresponding lightning protection optimization strategy according to the lightning strike factors of the site block.

[0028] In this embodiment, the lightning strike parameters of each site block when struck by lightning are determined through historical lightning strike events in the collector line site. By mining the strong association rules of the discretized lightning strike parameters, the occurrence time, tower density and periodic environmental humidity corresponding to the high severity of the lightning strike in the corresponding site block are extracted, thereby obtaining the lightning strike factors. Targeted lightning protection optimization strategies are generated based on the different lightning strike factors in different site blocks.

[0029] In some embodiments of the present application, the method for mining strong association rules based on the discretized lightning strike parameters includes: S1, scanning the transaction database, calculating the minimum support of all items under each lightning strike parameter in the transaction database, sorting the items in ascending order according to their minimum support, generating candidate frequent 1-item sets, deleting items with preset minimum support from the candidate frequent 1-item sets, and obtaining frequent 1-item set X1; S2, scanning a pre-established decision table J1, deleting rows in the decision table J1 that do not include any item set in X1, and obtaining decision table J2, and so on, obtaining decision table Jk and candidate frequent k-item sets; S3, deleting Excluding the item set Ik that does not contain the lightning strike severity in the candidate frequent k-item set, obtain the minimum support of each transaction in Ik, delete the item sets with less than the preset minimum support in Ik, and generate the frequent k-item set Xk; S4, delete the rows that do not include any item set in Xk in Jk, and obtain the decision table Jk+1; S5, repeat steps S3 and S4 until the frequent k-item set Xk is empty; S6, calculate the confidence of each frequent k-item set. If the confidence of the frequent k-item set is greater than the preset minimum confidence, a strong association rule is obtained. This process continues until the confidence calculation of all frequent k-item sets is completed, and the strong association rule of the site block is obtained.

[0030] In some embodiments of the present application, determining the corresponding lightning protection optimization strategy based on the lightning strike factors of the site area block includes: establishing a lightning protection strategy database, obtaining lightning strike factor data and corresponding lightning protection optimization strategies in the lightning protection strategy database, and establishing a training sample set based on the lightning strike factor data and the corresponding lightning protection optimization strategies; establishing an initial strategy generation model based on the training sample set and training the initial strategy generation model to obtain a trained strategy generation model; inputting the lightning strike factors corresponding to the site area block into the trained strategy generation model to obtain the corresponding lightning protection optimization strategy.

[0031] S104: judging whether the site block needs to be optimized for lightning protection according to the lightning protection assessment level; if it needs to be optimized for lightning protection, performing the optimization for lightning protection on the site block according to the lightning protection optimization strategy.

[0032] In some embodiments of the present application, the method of judging whether a site area block needs to be optimized for lightning protection based on the lightning protection assessment level, and if lightning protection optimization is required, performing lightning protection optimization on the site area block according to the lightning protection optimization strategy, includes: obtaining a preset standard lightning protection level, and calculating the difference between the lightning protection assessment level of the site area block and the preset standard lightning protection level; judging whether the difference between the lightning protection assessment level of the site area block and the preset standard lightning protection level is greater than a second preset threshold; if the difference between the lightning protection assessment level of the site area block and the preset standard lightning protection level is greater than the second preset threshold, performing lightning protection optimization on the collector line of the site area block according to the lightning protection optimization strategy; if the difference between the lightning protection assessment level of the site area block and the preset standard lightning protection level is less than or equal to the second preset threshold, not performing lightning protection optimization on the collector line.

[0033] In this embodiment, whether lightning protection optimization is needed is determined by the difference between the lightning protection assessment level of the site block and the preset standard lightning protection level. When the difference is greater than a second preset threshold, lightning protection optimization is performed on the wind farm's collector line.

[0034] Based on the same technical concept, such as Figure 2 As shown, the present invention also provides a wind farm station collector line lightning protection assessment and optimization system, including: a partitioning module, used to obtain collector line site blocks and corresponding collector line site data, and determine the cluster partitions of each site block according to the collector line site data; an assessment module, used to determine the corresponding cluster center according to the cluster partition of the site block, and determine the lightning protection assessment level of the site block according to the cluster center; a mining module, used to obtain historical lightning strike events of the collector line site, mine strong association rules of the historical lightning strike events, and determine the lightning protection optimization strategy of the site block according to the strong association rules; an optimization module, used to judge whether the site block needs to be optimized for lightning protection according to the lightning protection assessment level, and if lightning protection optimization is required, the site block is optimized according to the lightning protection optimization strategy.

[0035] By applying the above technical solutions, the present invention obtains the collector line site blocks and the corresponding collector line site data, determines the cluster partitions of each site block according to the collector line site data; determines the corresponding cluster center according to the cluster partition of the site block, and determines the lightning protection assessment level of the site block according to the cluster center; obtains the historical lightning strike events of the collector line site, mines the strong association rules of the historical lightning strike events, and determines the lightning protection optimization strategy of the site block according to the strong association rules; determines whether the site block needs to be optimized for lightning protection according to the lightning protection assessment level, and if lightning protection optimization is required, performs lightning protection optimization on the site block according to the lightning protection optimization strategy. It can accurately evaluate the lightning protection level of the collector line site by block and generate a targeted lightning protection optimization strategy, effectively improving the lightning protection performance of the collector line site.

[0036] Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention can be implemented via hardware or via software combined with a necessary general-purpose hardware platform. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product. This software product can be stored on a non-volatile storage medium (such as a CD-ROM, USB flash drive, or external hard drive) and includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute the methods described in various implementation scenarios of the present invention.

[0037] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A lightning protection evaluation and optimization method for wind farm station collector lines, characterized in that: include: Obtaining collector line site blocks and corresponding collector line site data, and determining cluster partitions of each site block based on the collector line site data; Determine the corresponding cluster center according to the cluster partition of the site block, and determine the lightning protection assessment level of the site block according to the cluster center; Obtain historical lightning strike events at the collector line site, mine strong association rules of historical lightning strike events, and determine the lightning protection optimization strategy for the site block based on the strong association rules; Determine whether the site area needs lightning protection optimization based on the lightning protection assessment level. If lightning protection optimization is required, perform lightning protection optimization on the site area according to the lightning protection optimization strategy.

2. The wind farm station collector line lightning protection assessment optimization method according to claim 1 is characterized in that: The obtaining of collector line site blocks and corresponding collector line site data, and determining cluster partitions of each site block according to the collector line site data, includes: Obtain a preset grid, and divide the collector line site according to the preset grid to obtain a number of site blocks; Determine the altitude, undulation characteristics and distance to water of the site block based on site data, and determine the lightning strike probability of the site based on the altitude, undulation characteristics and distance to water; Determine the ambient humidity, ambient temperature and electric field gradient of the site area based on site data, and determine the lightning strike intensity of the site based on the ambient humidity, ambient temperature and electric field gradient; The clustering and partitioning of each site block is determined based on the site lightning strike probability and site lightning strike intensity.

3. The wind farm station collector line lightning protection assessment optimization method according to claim 2 is characterized in that: The clustering and partitioning of each site block according to the site lightning strike probability and site lightning strike intensity includes: A sample data set is established based on the site lightning strike probability and site lightning strike intensity, and k initial cluster centers of the sample data set are randomly selected; Calculate the Euclidean distance between the sample data in the sample data set and the initial cluster center, and divide each site block into the corresponding cluster partition according to the Euclidean distance between the sample data in the sample data set and the initial cluster center; Calculate the average value of the sample data in each cluster partition, and recalculate the cluster center based on the average value of the sample data in each cluster partition; Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the preset maximum number of iterations, and obtain the cluster partitioning of each site block.

4. The wind farm station collector line lightning protection assessment and optimization method according to claim 1 is characterized in that: Determining the corresponding cluster center according to the cluster partition of the site block, and determining the lightning protection assessment level of the site block according to the cluster center includes: Setting the venue block as the venue node, obtaining the venue distance value of the venue nodes in the same cluster partition, and connecting the venue nodes whose venue distance value is less than a first preset threshold with a line; Obtain the node degrees of the site nodes after line connection, and determine the influence coefficient of the site nodes according to the node degrees; Obtain the cluster center of the cluster partition corresponding to the site node, and determine the lightning protection assessment level of the corresponding site block based on the cluster center and affected coefficient of the site node.

5. The wind farm station collector line lightning protection assessment optimization method according to claim 4 is characterized in that: Determining the lightning protection assessment level of the corresponding site block based on the cluster center and the affected coefficient of the site node includes: Determine the central lightning strike probability and central lightning strike intensity of the cluster center according to the cluster center of the site nodes, and calculate the lightning protection assessment level of the site block based on the lightning protection assessment level calculation formula according to the central lightning strike probability, central lightning strike intensity and affected coefficient; The calculation formula for the lightning protection assessment level is specifically: in, The lightning protection assessment level of the site area, is the affected coefficient, is the central lightning strike probability, is the preset standard center lightning strike probability, is the central lightning strike intensity, For the preset standard center lightning intensity, , are the first weight and the second weight respectively.

6. The wind farm station collector line lightning protection assessment and optimization method according to claim 1 is characterized in that: The method of mining strong association rules of historical lightning strike events and determining the lightning protection optimization strategy of the site block according to the strong association rules includes: Determine the lightning strike parameters of each site block based on historical lightning strike events at the collector line site. The lightning strike parameters include lightning strike severity, occurrence time, tower density, and periodic ambient humidity, and discretize the lightning strike parameters. Strong association rules are mined based on the discretized lightning strike parameters, and the lightning strike factors of each site block are determined based on the strong association rules. The corresponding lightning protection optimization strategy is determined based on the lightning strike factors of the site block.

7. The wind farm station collector line lightning protection assessment and optimization method according to claim 6 is characterized in that: The mining of strong association rules based on the discretized lightning stroke parameters includes: S1, scan the transaction database, calculate the minimum support of all items under each lightning strike parameter in the transaction database, sort them in ascending order according to the minimum support of the items, generate candidate frequent 1-item sets, delete the items with preset minimum support from the candidate frequent 1-item sets, and obtain the frequent 1-item set X1; S2, scan the pre-established decision table J1, delete the rows in decision table J1 that do not include any item set in X1, and obtain decision table J2. Similarly, obtain decision table Jk and candidate frequent k item sets; S3, delete the item set Ik that does not contain the lightning strike severity in the candidate frequent k-item set, obtain the minimum support of each transaction in Ik, delete the item set with less than the preset minimum support in Ik, and generate the frequent k-item set Xk; S4, delete the rows in Jk that do not include any item set in Xk, and obtain the decision table Jk+1; S5, repeat steps S3 and S4 until the frequent k-item set Xk is empty; S6, calculate the confidence of each frequent k-item set. If the confidence of the frequent k-item set is greater than the preset minimum confidence, a strong association rule is obtained. This process continues until the confidence calculation of all frequent k-item sets is completed, and the strong association rule of the site block is obtained.

8. The wind farm station collector line lightning protection assessment and optimization method according to claim 6 is characterized in that: The corresponding lightning protection optimization strategy is determined according to the lightning strike factors of the site block, including: Establish a lightning protection strategy database, obtain lightning strike factor data and corresponding lightning protection optimization strategies in the lightning protection strategy database, and establish a training sample set based on the lightning strike factor data and the corresponding lightning protection optimization strategies; Establish an initial strategy generation model based on the training sample set and train the initial strategy generation model to obtain a trained strategy generation model; The lightning strike factors corresponding to the site blocks are input into the trained strategy generation model to obtain the corresponding lightning protection optimization strategy.

9. The wind farm station collector line lightning protection assessment and optimization method according to claim 1, characterized in that: The determination of whether the site block needs lightning protection optimization is made based on the lightning protection assessment level. If lightning protection optimization is required, the lightning protection optimization is performed on the site block according to the lightning protection optimization strategy, including: Obtain the preset standard lightning protection level and calculate the difference between the lightning protection assessment level of the site block and the preset standard lightning protection level; Determine whether the difference between the lightning protection assessment level of the site block and the preset standard lightning protection level is greater than a second preset threshold; if the difference between the lightning protection assessment level of the site block and the preset standard lightning protection level is greater than the second preset threshold, perform lightning protection optimization on the collector line of the site block according to the lightning protection optimization strategy; If the difference between the lightning protection assessment level of the site block and the preset standard lightning protection level is less than or equal to the second preset threshold, the lightning protection optimization of the collector line is not performed.

10. A lightning protection assessment and optimization system for wind farm collector lines, characterized in that: include: A partitioning module is used to obtain the collector line site blocks and the corresponding collector line site data, and determine the cluster partitioning of each site block according to the collector line site data; An evaluation module is used to determine the corresponding cluster center according to the cluster partition of the site block, and determine the lightning protection evaluation level of the site block according to the cluster center; The mining module is used to obtain historical lightning strike events at the collector line site, mine strong association rules of historical lightning strike events, and determine the lightning protection optimization strategy of the site block based on the strong association rules; The optimization module is used to determine whether the site block needs lightning protection optimization based on the lightning protection assessment level. If lightning protection optimization is required, the site block is optimized according to the lightning protection optimization strategy.

Images