Fault locating method, system, device and medium based on transformer area topology identification

Abstract

The application discloses a fault positioning method, system, device and medium based on transformer area topology identification, comprising: inputting the obtained total table first pulse number and the second pulse number of several sub-tables into a topology analysis model for solving to determine a first transformer area topology structure; based on each electrical quantity data, a target correlation coefficient between users is calculated, and a first user pair that does not satisfy a preset correlation threshold is eliminated to obtain several second user pairs, a target DTW distance of each second user pair is calculated, the second user pair with the maximum target DTW distance is taken as a third user pair, and the third user pair is taken as an initial clustering center for iterative optimization until a clustering termination condition is satisfied, and a target clustering result is output to determine a second transformer area topology structure; the first transformer area topology structure and the second transformer area topology structure are compared, if both are the same, a target transformer area topology structure is determined, and fault positioning is performed based on the target transformer area topology structure. The application can accurately position the transformer area fault point.

Description

Technical Field

[0001] This application relates to the field of power metering, and in particular to fault location methods, systems, equipment and media based on transformer substation topology identification. Background Technology

[0002] As a critical terminal unit of the power system, the accuracy of the topology of low-voltage distribution substations is crucial for the efficient operation and fault handling of the distribution network. Due to the complexity of low-voltage distribution substation lines, issues such as equipment exceeding its service life and unauthorized connections, coupled with the widespread application of distributed energy resources, substation topology identification has become key to achieving accurate fault location, emergency repairs, and the construction of new power systems. Accurate identification of the substation topology clarifies the correspondence between distribution transformers and users, providing accurate topological basis for fault location, quickly pinpointing the fault location, narrowing the investigation scope, improving operation and maintenance efficiency, and reducing economic losses.

[0003] Existing transformer substation topology identification technologies mainly include the following: First, manual data entry, which is simple and direct, but time-consuming and labor-intensive, making it difficult to adapt to power grid upgrades and timely detection of faulty meters; second, carrier communication, which identifies the transformer-household relationship by analyzing signal characteristics, but is affected by clock errors and communication quality, resulting in long identification cycles and poor real-time performance; third, instantaneous short-circuit identification, which actively creates instantaneous short circuits to generate pulse counts for topology identification, but this can endanger equipment and power grid safety and is costly; fourth, big data methods, which combine collected electrical quantity data with algorithmic analysis to solve for the transformer-household relationship, but its accuracy cannot be guaranteed due to limitations in the synchronization, accuracy, and sufficiency of data acquisition. These methods suffer from problems such as long data acquisition time, asynchronous acquisition, and inaccurate judgment in fault location, leading to inaccurate fault location, low efficiency, and difficulty in meeting practical application needs. Summary of the Invention

[0004] This application provides a fault location method, system, device, and medium based on transformer area topology identification to improve the accuracy of transformer area topology identification and thus accurately locate the fault point in the transformer area.

[0005] Firstly, this application provides a fault location method based on transformer area topology identification, including:

[0006] Obtain the first pulse count of the main meter in the meter box, and obtain the second pulse count and electrical quantity data of several sub-meters in the meter box;

[0007] The first pulse count and each of the second pulse counts are input into a preset topology analysis model for solution to obtain several attribution relationship coefficients. The topology structure of the first transformer area is determined based on each attribution relationship coefficient, wherein the attribution relationship coefficient is the coefficient by which each sub-table belongs to the main table.

[0008] Based on the electrical quantity data, the target correlation coefficient between users is calculated, and the first user pair whose target correlation coefficient does not meet the preset correlation threshold is eliminated to obtain several second user pairs. The target DTW distance of each second user pair is calculated, and the second user pair with the largest target DTW distance is taken as the third user pair. The third user pair is taken as the initial cluster center for iterative optimization until the clustering termination condition is met. The topology of the second transformer area is determined according to the output target clustering results.

[0009] The topology of the first transformer substation and the topology of the second transformer substation are compared. If they are the same, the topology of the target transformer substation is determined, and the fault is located based on the topology of the target transformer substation to identify the faulty energy meter in the transformer substation.

[0010] This embodiment of the application, by acquiring the first pulse count of the main meter and the second pulse count and electrical quantity data of the sub-meters, can collect the energy metering information and operating status data of each energy meter in the meter box, providing necessary information support for subsequent topology identification using different methods. By processing and analyzing the collected pulse count using a preset topology analysis model, key information reflecting the topological relationship of the transformer area can be extracted from the pulse count, initially establishing the topology of the transformer area. By calculating the target correlation coefficient between users, highly correlated user pairs can be screened, initially determining the set of users possibly located in the same transformer area. By eliminating user pairs that do not meet the correlation threshold, interference from irrelevant data is reduced, making the analysis more targeted. Next, the target DTW distance is calculated, and initial cluster centers are determined for iterative optimization until the clustering termination condition is met. This series of operations can fully utilize the time-series characteristics of electrical quantity data to uncover the similarities and differences in electrical characteristics among users, thereby more accurately dividing the transformer substation topology. This allows for topology identification from another dimension, complementing and verifying the pulse-number-based topology identification results, further improving the accuracy and reliability of topology identification. By comparing the two topologies, the credibility and accuracy of the topology identification results are greatly improved. Fault location based on the determined topology can quickly and accurately locate the faulty energy meter in the transformer substation, thereby enabling rapid response and handling of the fault. Compared with existing technologies, this application can improve the accuracy of transformer substation topology identification, thereby accurately locating the fault point in the transformer substation.

[0011] Furthermore, the calculation formula for the topology analysis model is as follows:

[0012]

[0013] In the formula, e j This represents the affiliation coefficient between the j-th sub-table and the current station area master table, where j = 1, 2, ..., p; These are the measurement values ​​for different time series within the same subtable; The total table contains the measurement values ​​for different time series; n is the number of data sets to be collected; ΔP j Let c be the second pulse number for all sub-tables whose topological relationships are to be determined, where j = 1, 2, ..., p; c p ΔN represents the impulse constant for all sub-tables whose topological relationships need to be determined. k c is the first pulse number in the total number of pulses in the distribution area table. k is the pulse constant of the total number of transformer substations, where k is the number of different transformer substations.

[0014] Furthermore, the electrical quantity data includes voltage data, current data, and power data, and the calculation of the target DTW distance for each of the second user pairs specifically involves:

[0015] For the voltage data, the current data, and the power data, respectively, a first distance matrix, a second distance matrix, and a third distance matrix are constructed.

[0016] A first cumulative matrix is ​​calculated based on the first distance matrix, a second cumulative matrix is ​​calculated based on the second distance matrix, and a third cumulative matrix is ​​calculated based on the third distance matrix.

[0017] For each cumulative matrix, find the optimal path with the smallest cumulative distance, and calculate the cumulative distance of the optimal path to obtain the first DTW distance, the second DTW distance, and the third DTW distance;

[0018] Based on preset weights, the first DTW distance, the second DTW distance, and the third DTW distance are weighted and fused to obtain the target DTW distance for each second user pair.

[0019] By calculating the target DTW distance, we can more accurately measure their similarity in electrical characteristics, which will facilitate the subsequent construction of a transformer substation topology that is more in line with the actual situation.

[0020] Furthermore, based on the electrical quantity data, the target correlation coefficient between users is calculated as follows:

[0021] Calculate a first correlation coefficient based on the voltage data between users;

[0022] Calculate a second correlation coefficient based on the current data between users;

[0023] A third correlation coefficient is calculated based on the power data between users, wherein the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient are all Pearson correlation coefficients;

[0024] Based on the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient, the target correlation coefficient between users is determined.

[0025] By calculating the target correlation coefficient between users, we can filter out user pairs with high correlation and preliminarily determine the set of users who may be in the same area. By removing user pairs that do not meet the correlation threshold, we can reduce the interference of irrelevant data and make the analysis more targeted.

[0026] Furthermore, the second user pair with the largest target DTW distance is selected as the third user pair, and the third user pair is used as the initial cluster center for iterative optimization until the clustering termination condition is met. The topology of the second transformer area is determined based on the output target clustering results. Specifically:

[0027] The second user pair with the largest target DTW distance is taken as the third user pair, and the third user pair is taken as the initial cluster center. The fourth DTW distance between each user and the initial cluster center is calculated, and each user is assigned to the initial cluster center that is closest to the fourth DTW distance.

[0028] For each user assigned to each initial cluster center, the mean sequence of the electrical quantity data is calculated, and the second cluster center is iteratively updated based on the mean sequence until the updated second cluster center meets the preset clustering termination condition. Then, the updated target clustering result is output, and the topology of the second transformer substation is determined based on the target clustering result.

[0029] By determining the initial cluster centers and iteratively optimizing them until the clustering termination condition is met, this series of operations can fully utilize the time-series characteristics of electrical quantity data to uncover the similarities and differences in electrical characteristics among users. This allows for a more accurate division of the transformer substation topology, enabling the identification of the substation topology from another dimension. This complements and verifies the topology identification results based on pulse count, further improving the accuracy and reliability of topology identification.

[0030] Furthermore, the comparison of the first and second transformer area topologies, and the determination of the target transformer area topology if they are identical, specifically involves:

[0031] The difference matrix is ​​determined by comparing the topology of the first transformer area and the topology of the second transformer area element by element.

[0032] If the difference between all elements in the difference matrix is ​​0, then the two are determined to be the same, and the target transformer area topology is determined.

[0033] By comparing the two topological structures, the reliability and accuracy of the topology recognition results are greatly improved.

[0034] Furthermore, the step of locating the faulty energy meter in the target transformer area based on its topology specifically involves:

[0035] Determine the third pulse number of each meter in the target transformer area topology, wherein the meters include a master meter and sub-meters;

[0036] Based on the third pulse count, the energy pulse correlation coefficient between each meter is calculated using the Pearson correlation coefficient. It is then determined whether the energy pulse correlation coefficient is greater than a preset threshold, and the faulty energy meter in the distribution area is identified based on the determination result.

[0037] By locating faults based on a defined topology, it is possible to quickly and accurately pinpoint the faulty electricity meter in the service area, thereby enabling rapid response and handling of the fault.

[0038] Secondly, this application provides a fault location system based on transformer area topology identification, including: an acquisition module, a first determination module, a second determination module, and a fault location module;

[0039] The acquisition module is used to acquire the first pulse count of the total meter in the meter box, and to acquire the second pulse count and electrical quantity data of several sub-meters in the meter box;

[0040] The first determining module is used to input the first pulse number and each of the second pulse numbers into a preset topology analysis model for solving, to obtain several attribution relationship coefficients, and to determine the topology structure of the first transformer area based on each of the attribution relationship coefficients, wherein the attribution relationship coefficients are the coefficients by which each sub-table belongs to the main table;

[0041] The second determining module is used to calculate the target correlation coefficient between users based on the electrical quantity data, and remove the first user pair whose target correlation coefficient does not meet the preset correlation threshold to obtain several second user pairs, calculate the target DTW distance of each second user pair, and take the second user pair with the largest target DTW distance as the third user pair, and take the third user pair as the initial cluster center for iterative optimization until the clustering termination condition is met, and determine the topology of the second transformer area based on the output target clustering result;

[0042] The fault location module is used to compare the topology of the first transformer area and the topology of the second transformer area. If they are the same, the target transformer area topology is determined, and the fault is located based on the target transformer area topology to identify the faulty energy meter in the transformer area.

[0043] This embodiment of the application, by acquiring the first pulse count of the main meter and the second pulse count and electrical quantity data of the sub-meters, can collect the energy metering information and operating status data of each energy meter in the meter box, providing necessary information support for subsequent topology identification using different methods. By processing and analyzing the collected pulse count using a preset topology analysis model, key information reflecting the topological relationship of the transformer area can be extracted from the pulse count, initially establishing the topology of the transformer area. By calculating the target correlation coefficient between users, highly correlated user pairs can be screened, initially determining the set of users possibly located in the same transformer area. By eliminating user pairs that do not meet the correlation threshold, interference from irrelevant data is reduced, making the analysis more targeted. Next, the target DTW distance is calculated, and initial cluster centers are determined for iterative optimization until the clustering termination condition is met. This series of operations can fully utilize the time-series characteristics of electrical quantity data to uncover the similarities and differences in electrical characteristics among users, thereby more accurately dividing the transformer substation topology. This allows for topology identification from another dimension, complementing and verifying the pulse-number-based topology identification results, further improving the accuracy and reliability of topology identification. By comparing the two topologies, the credibility and accuracy of the topology identification results are greatly improved. Fault location based on the determined topology can quickly and accurately locate the faulty energy meter in the transformer substation, thereby enabling rapid response and handling of the fault. Compared with existing technologies, this application can improve the accuracy of transformer substation topology identification, thereby accurately locating the fault point in the transformer substation.

[0044] Thirdly, this application also provides a terminal device, including: one or more processors; a memory coupled to the processors for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the fault location method based on transformer area topology identification as described in this application.

[0045] Fourthly, this application also provides a terminal device and a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the fault location method based on transformer area topology identification as described in this application. Attached Figure Description

[0046] Figure 1 This is a flowchart illustrating an embodiment of the fault location method based on transformer area topology identification provided in this application;

[0047] Figure 2 This is a schematic diagram of the interaction between the smart metering switch and the electricity meter provided in this application;

[0048] Figure 3 This is a flowchart illustrating steps S501 to S504 provided in this application;

[0049] Figure 4 This is a schematic diagram of the dynamic time curvature path of the electrical quantity time series provided in this application;

[0050] Figure 5 This is a schematic diagram of the first and second transformer area topologies provided in this application;

[0051] Figure 6 This is a schematic diagram of the structure of an embodiment of the fault location system based on transformer area topology identification provided in this application;

[0052] Figure 7 This is a schematic diagram of the hardware structure of the terminal device provided in this application. Detailed Implementation

[0053] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0054] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0055] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0056] The terms “comprising” and “including” indicate the presence of the described feature, whole, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0057] The term “and / or” refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes these combinations.

[0058] Next, the terms used in this application will be explained:

[0059] The "transformer-user" relationship refers to the correspondence between a distribution transformer (transformer) and the electricity users (users) within its power supply range in the operation and management of a distribution network. It clarifies which users a particular distribution transformer directly supplies electricity to and is fundamental information about the distribution network topology.

[0060] Bluetooth for electricity meters: A Bluetooth communication module is added to the traditional smart electricity meter. It is mainly used for short-range wireless transmission, enabling communication between several nodes with high efficiency.

[0061] Based on this, embodiments of this application provide a fault location method, system, device, and medium based on transformer area topology identification, which can improve the accuracy of transformer area topology identification and thus accurately locate the fault point in the transformer area.

[0062] This application provides a fault location method, system, device, and medium based on transformer area topology identification, which will be specifically described through the following embodiments. First, the fault location method based on transformer area topology identification in this application embodiment is described.

[0063] The fault location method based on transformer substation topology identification provided in this application relates to the field of power metering. This fault location method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the fault location method based on transformer substation topology identification, etc., but is not limited to the above forms.

[0064] This application can also be used in numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0065] Example 1

[0066] Please refer to Figure 1, Figure 1 This is a flowchart illustrating an embodiment of the fault location method based on transformer area topology identification provided in this application, including steps S101 to S104.

[0067] Step S101: Obtain the first pulse count of the main meter in the meter box, and obtain the second pulse count and electrical quantity data of several sub-meters in the meter box;

[0068] In some embodiments, the second pulse count and electrical quantity data of each sub-meter, as well as the first pulse count of the total meter, are synchronously acquired via a wireless connection through the Bluetooth module (or rail meter) of the smart measuring switch. The electrical quantity data includes voltage data, current data, and power data.

[0069] In some embodiments, a schematic diagram of the interaction between the smart metering switch and the energy meter is shown below. Figure 2 As shown, specifically, firstly, a smart metering switch with a built-in Bluetooth module is installed inside the meter box as the communication master device, and the main meter and each sub-meter (user energy meter) act as Bluetooth slave devices. The smart metering switch establishes a wireless communication connection with the main meter and each sub-meter through the Bluetooth module. Then, the smart metering switch synchronously sends data acquisition commands to the main meter and each sub-meter. After receiving the commands, the main meter and each sub-meter simultaneously send up the energy pulse count and instantaneous voltage, current, and other electrical quantity data. Finally, after receiving the data from the main meter, the smart metering switch uses it as the overall reference value of the meter box, that is, it obtains the first pulse count of the main meter. For each sub-meter, the smart metering switch receives the energy pulse count sent by it through the Bluetooth module, that is, it obtains the second pulse count of the sub-meter. At the same time, it also receives the voltage and current sent by the sub-meter, and synchronizes based on the obtained voltage and current data, and calculates the power, thereby obtaining the electrical quantity data.

[0070] It should be noted that intelligent metering switches are generally installed at the inlet of low-voltage metering boxes to replace the existing ordinary inlet switches. They are highly integrated intelligent metering devices that, while maintaining the original protection functions of the metering box's molded case circuit breaker, integrate the functions of a three-phase smart energy meter, an electricity consumption information collector, and a smart monitoring terminal for the metering box. They can monitor data such as voltage, current, power, power factor, and energy consumption in real time, and remotely control the switch's on / off state via an app, cloud platform, or local network (such as Wi-Fi, Bluetooth, or Zigbee). They also support cross-metering, file management, and topology identification.

[0071] Step S102: Input the first pulse count and each of the second pulse counts into a preset topology analysis model for solution to obtain several attribution relationship coefficients, and determine the topology structure of the first transformer area based on each attribution relationship coefficient, wherein the attribution relationship coefficient is the coefficient of each sub-table belonging to the main table;

[0072] In some embodiments, before inputting the first pulse count and each of the second pulse counts into a preset topology analysis model for solution, the method further includes: performing data synchronization, data preprocessing, and smoothing on the first pulse count and each of the second pulse counts respectively. Specifically: first, using the synchronization mechanism of Bluetooth communication, the first pulse count of the collected total table and each of the second pulse counts of the sub-tables are synchronized in time to ensure the periodicity and consistency of the data; then, the synchronized first pulse count and each of the second pulse counts of the sub-tables are preprocessed by means of filtering, noise reduction, and calibration to obtain the processed first pulse count and each of the second pulse counts.

[0073] In some embodiments, since the meter box topology and power supply relationship are the physical basis of the topology analysis model, based on the relationship that the power increment of the main meter in the same area is approximately equal to the sum of the power increments of each sub-meter, and combined with the pulse constants of the main meter and sub-meters, an equation is established between the power pulse numbers of the main meter and sub-meters. By accumulating data from multiple cycles, a set of equations, i.e., the topology analysis model, is formed. Then, the topology analysis model is solved to determine the attribution relationship between the sub-meters and the main meter.

[0074] It should be noted that the specific construction process of the topology analysis model is as follows: First, since there is strong synchronicity between the user energy pulses and the total meter energy pulses in the same transformer area, and there is no significant correlation between the user pulses and the total meter pulses in different transformer areas, that is, within the same transformer area, the increase in total meter energy should be approximately equal to the sum of the increases in each sub-meter. Therefore, it can be determined that:

[0075] ΔP 总 ≈∑ i∈台区 ΔP 分,i #(1), where ΔP 总 ΔP represents the increase in electrical energy in the total meter within the time window. 分,i This represents the energy increment of the i-th sub-meter within the same distribution area within the time window; then, combining the pulse constants of the main meter and each user's sub-meter (energy pulse count = pulse constant × energy consumption), formula (1) can be rewritten as:

[0076]

[0077] In the formula, ΔN 总 ΔP represents the first pulse count of the summary table within the time window. 分,i c represents the second pulse number of the i-th sub-table within the same station area within the time window. 总 c represents the pulse constant of the summary table. 分,i This represents the pulse constant of the i-th sub-meter within the same transformer area. Then, for the main meter and sub-meters with undetermined topology relationships, after accumulating data for n cycles in the meter box, a system of n equations can be obtained, which is the topology analysis model.

[0078] In some embodiments, the calculation formula of the topology analysis model is specifically as follows:

[0079]

[0080] In the formula, e j This represents the affiliation coefficient between the j-th sub-table and the current station area master table, where j = 1, 2, ..., p; These are the measurement values ​​for different time series within the same subtable; The total table contains the measurement values ​​for different time series; n is the number of data sets to be collected; ΔP j Let c be the second pulse number for all sub-tables whose topological relationships are to be determined, where j = 1, 2, ..., p; c p ΔN represents the impulse constant for all sub-tables whose topological relationships need to be determined. k c is the first pulse number in the total number of pulses in the distribution area table. k is the pulse constant of the total number of transformer substations, where k is the number of different transformer substations.

[0081] It should be noted that the numbers in parentheses in the topology analysis model represent different time data collected in a time series under the same energy meter. That is, a total of n sets of data must be collected before the system of equations can be solved. The number of equations to be solved is equal to the number of transformer substations.

[0082] In some embodiments, the first pulse count and each of the second pulse counts are input into a preset topology analysis model for solution, which yields the attribution coefficient e. j Where j = 1, 2, ..., p, that is, to solve for e1 to e p The coefficients of the attribution relationship between each sub-table and the current master table can be obtained by solving the system of equations using the least squares method or linear regression, and this application does not impose any restrictions.

[0083] In some embodiments, determining the topology of the first transformer area based on each of the attribution coefficients specifically involves: when the attribution coefficient e is obtained... j Then, the threshold is set to 0.5, and if the attribution coefficient e j If the coefficient is greater than 0.5, the user (i.e., the sub-table) is considered to be under the current master table. j If the value is less than 0.5, the user (i.e., the user in the sub-table) is considered not to belong to the current main table. The relevant formula is: In the formula, 1 represents belonging to the relation and 0 represents not belonging to the relation. After determining whether each sub-table belongs to the sub-area, the topology of the first sub-area can be determined.

[0084] It should be noted that, in order to more accurately determine the topology of the first transformer area, within the same transformer area, the topology analysis model can also be solved based on the number of second pulses of different phases of the main meter and the number of first pulses of different single-phase users, thereby realizing the distinction between different phases. For example, assuming that the pulse constants of the main meter and the sub-meters are the same, within the time window, the main meter A phase has a total of 100 pulses, sub-meter A has a total of 80 pulses, sub-meter B has 20 pulses, and sub-meter C has 30 pulses. It can be determined that sub-meters A and B are in the main meter A phase.

[0085] Step S103: Based on the electrical quantity data, calculate the target correlation coefficient between users, and remove the first user pair whose target correlation coefficient does not meet the preset correlation threshold to obtain several second user pairs. Calculate the target DTW distance of each second user pair, and take the second user pair with the largest target DTW distance as the third user pair. Use the third user pair as the initial cluster center for iterative optimization until the clustering termination condition is met. Determine the topology of the second transformer area based on the output target clustering results.

[0086] In some embodiments, before calculating the target correlation coefficient between users based on the electrical quantity data, the electrical quantity data is further normalized to eliminate dimensional differences.

[0087] It should be noted that users in the same transformer area are electrically close and have strong similarities in their fluctuation patterns, while users in different transformer areas are electrically far apart and have poor similarities in their fluctuation patterns. Therefore, clustering algorithms are used as an example to illustrate how to determine the topology of the second transformer area.

[0088] In some embodiments, the electrical quantity data includes voltage data, current data, and power data. The step of calculating the target correlation coefficient between users based on each of the electrical quantity data specifically involves: calculating a first correlation coefficient for the voltage data between users; calculating a second correlation coefficient for the current data between users; and calculating a third correlation coefficient for the power data between users. The first, second, and third correlation coefficients are all Pearson correlation coefficients. Based on the first, second, and third correlation coefficients, the target correlation coefficient between users is determined. Specifically, firstly, the correlation of voltage, current, and power time series between each pair of users (sub-meters) is calculated using the Pearson coefficient, where the formula for calculating the Pearson coefficient is: In the formula, x and y represent the electrical quantity data (including voltage, current, and power data) of the two users (separate meters) to be calculated, and n is the number of data collection groups. The first correlation coefficient r between users in the platform area can be calculated using the above formula. V Second correlation coefficient r IAnd the third correlation coefficient r P (Where V represents voltage, I represents current, and P represents power); then, the first correlation coefficient r between users... V Second correlation coefficient r I And the third correlation coefficient r P The average value is taken to obtain the target correlation coefficient between users. The relevant formula is:

[0089] It should be noted that the correlation coefficient between user electricity consumption data can be calculated from the data of the two groups of users. The correlation coefficient is distributed between -1 and 1. The closer the correlation coefficient is to 0, the lower the correlation between the two groups of data. The closer the correlation coefficient is to -1, the negative correlation between the two groups of data. The closer the correlation coefficient is to 1, the positive correlation between the two groups of data (that is, the higher the correlation between user data, the larger the correlation coefficient).

[0090] In some embodiments, eliminating first user pairs whose target correlation coefficient does not meet a preset correlation threshold specifically involves: when the target correlation coefficient is determined... Then, by setting a preset relevance threshold (e.g., 0.8), the target relevance coefficient between two users (between tables) is determined. If the correlation is less than the preset correlation threshold, it indicates that the correlation is low and can be eliminated. This method can quickly screen highly correlated user pairs, narrow down the scope of subsequent calculations, eliminate obviously irrelevant users, reduce the amount of DTW calculations, and obtain several second user pairs with higher correlation.

[0091] By calculating the target correlation coefficient between users, we can filter out user pairs with high correlation and preliminarily determine the set of users who may be in the same area. By removing user pairs that do not meet the correlation threshold, we can reduce the interference of irrelevant data and make the analysis more targeted.

[0092] In some embodiments, the electrical quantity data includes voltage data, current data, and power data. The step of calculating the target DTW distance for each of the second user pairs may, but is not limited to, include steps S501 to S504. Figure 3 As shown:

[0093] Step S501: For the voltage data, the current data, and the power data, respectively, construct the corresponding first distance matrix, second distance matrix, and third distance matrix;

[0094] In some embodiments, for voltage, current, and power data respectively, the absolute distance between each point in the time series of the two users is calculated to construct a first distance matrix (voltage), a second distance matrix (current), and a third distance matrix (power). The relevant calculation formula is: d(ws )=d(i,j)=|x i -y j |, where element w s It is the coordinate of the s-th point on the path, i.e., w s = (i,j), representing x in the electrical quantity sequence X of the smart meter. i And another smart meter Y in y i Correspondingly, i represents 1, 2, ..., n, and j represents 1, 2, ..., m. n and m represent the number of data points in the time series of electrical quantities for two different users, respectively.

[0095] It should be noted that, to facilitate the subsequent calculation of the optimal path, an n x m matrix D needs to be constructed, where n and m represent the number of data points in the two electrical quantity time series, respectively. The dynamic time curvature paths of the electrical quantity time series X and Y are as follows: Figure 4 As shown in the figure, the path formed by the gray diagonal squares represents the correspondence between the time series X and Y of the electrical quantities of the smart meter. It is only one of many paths, that is, each element D[i][j] in matrix D represents x. i and y j The absolute distance.

[0096] Step S503: Calculate a first cumulative matrix based on the first distance matrix, calculate a second cumulative matrix based on the second distance matrix, and calculate a third cumulative matrix based on the third distance matrix;

[0097] In some embodiments, for each distance matrix (including the first distance matrix, the second distance matrix, and the third distance matrix), the boundary values ​​D[0][0] = d(0,0) are first initialized. (First column) (First row), and generate the accumulation matrix using a dynamic programming recursive formula.

[0098] It should be noted that, in order to find the optimal path in the accumulation matrix, since there are multiple paths w, all possibilities of w are represented as a path space W. In W, there exists an optimal path such that... The minimum DTW distance between time series X and Y is: From (x1, y1) to (x n ,y m The shortest path to (x) needs to satisfy: when calculating the path to the (x)th node... i ,y j When finding the shortest path, it is necessary to find (x) i ,y j-1 ), (x i-1 ,y j-1 ), (x i-1 ,yj The third point to (x) i ,y j The shortest distance is used to determine the DTW distance.

[0099] Step S503: For each cumulative matrix, find the optimal path with the smallest cumulative distance, and calculate the cumulative distance of the optimal path to obtain the first DTW distance, the second DTW distance, and the third DTW distance;

[0100] In some embodiments, starting from the beginning (1,1) of each accumulation matrix and ending at the end (n,m), while ensuring monotonicity (the path can only move right, up, or to the upper right (ensuring time order)) and continuity (the path cannot skip any points), the path with the smallest cumulative distance, i.e., the optimal path, is found. The endpoint value of the path is the DTW distance of a single electrical quantity, which is the cumulative distance of the optimal path. DTW(X) i ,Y j = D[i][j], and calculate the DTW distance based on the voltage, current and power between users according to the situation of the transformer area. Thus, the first DTW distance (voltage), the second DTW distance (current) and the third DTW distance (power) can be obtained.

[0101] It should be noted that the DTW distance is the objective of dynamic programming. There are multiple paths w. The goal is to find the optimal path that minimizes the DTW distance between time series X and Y by forming a path space W with all possibilities of w.

[0102] Step S504: According to the preset weights, the first DTW distance, the second DTW distance, and the third DTW distance are weighted and fused to obtain the target DTW distance for each second user pair.

[0103] In some embodiments, weights are assigned based on the importance of electrical quantities (e.g., voltage 0.4, current 0.3, power 0.3) to calculate the overall DTW distance, thereby obtaining the target DTW distance for each second user pair. The relevant calculation formula is as follows: In the formula, X i ,Y j Two user data points representing the same electrical quantity, with weight w. k It can be allocated according to the importance of electrical quantities such as voltage, current, and power.

[0104] It should be noted that DTW (Dynamic Time Warping) is an algorithm used to measure the similarity between two time series. Its main principle is to map one time series to another through a non-linear mapping relationship, thereby measuring the similarity between the two time series. This mapping relationship can be solved using dynamic programming to find the optimal path that minimizes the distance between the two time series along that path.

[0105] By calculating the target DTW distance, we can more accurately measure their similarity in electrical characteristics, which will facilitate the subsequent construction of a transformer substation topology that is more in line with the actual situation.

[0106] Furthermore, the step of using the second user pair with the largest target DTW distance as the third user pair and using the third user pair as the initial cluster center for iterative optimization until the clustering termination condition is met, and determining the topology of the second transformer substation based on the output target clustering result, includes: using the second user pair with the largest target DTW distance as the third user pair and using the third user pair as the initial cluster center, calculating the fourth DTW distance between each user and the initial cluster center, and assigning each user to the initial cluster center with the closest fourth DTW distance; for each user assigned to each initial cluster center, calculating the mean sequence of the electrical quantity data, and iteratively updating the second cluster center based on the mean sequence until the updated second cluster center meets the preset clustering termination condition, outputting the updated target clustering result, and determining the topology of the second transformer substation based on the target clustering result. Specifically, since the core of cluster analysis is to determine the number of clusters K and the cluster points, the N low-voltage distribution transformer area users are divided into K sets. The number of clusters k is determined by the number of distribution transformers M. The process of determining the cluster points is as follows: First, the two users with the largest DTW distance (i.e., the third user pair) are taken as the two initial cluster points. Then, the comprehensive DTW distance from each user to the two initial cluster centers is calculated, and the user is assigned to the nearest initial cluster center. Then, for the users in each initial cluster center, the mean sequence of their electrical quantity time series (voltage data, current data, and power data) is calculated as the new cluster center, i.e., the second cluster center is updated, until any termination condition is met (the cluster center no longer changes or the preset maximum number of iterations is reached). At this time, the users can be divided into K sets (K = number of distribution transformers M), and the second distribution area topology is constructed based on the target clustering results (where the matrix rows represent distribution areas (cluster centers), and the columns represent users. If a user belongs to a certain distribution area, the corresponding position is marked as 1, otherwise it is 0).

[0107] It should be noted that, to more accurately determine the topology of the second transformer substation, the electrical quantity data of a single-phase user has a high similarity to the electrical quantity data of the corresponding phase of the transformer supplying it, resulting in a small DTW distance; while the similarity to the phase voltage curves of transformers of different phases is low, resulting in a larger DTW distance. Based on this principle, by calculating the DTW distance between the single-phase user and the three-phase voltage of the transformer, the phase with the smallest DTW distance is identified as the phase to which the single-phase user belongs, thus more accurately determining the topology of the second transformer substation.

[0108] By determining the initial cluster centers and iteratively optimizing them until the clustering termination condition is met, this series of operations can fully utilize the time-series characteristics of electrical quantity data to uncover the similarities and differences in electrical characteristics among users. This allows for a more accurate division of the transformer substation topology, enabling the identification of the substation topology from another dimension. This complements and verifies the topology identification results based on pulse count, further improving the accuracy and reliability of topology identification.

[0109] It should be noted that a series of heuristic optimization algorithms, least squares, regression optimization and other algorithms can also be used to obtain the topology of the second transformer area.

[0110] Step S104: Compare the topology of the first transformer area with the topology of the second transformer area. If they are the same, determine the target transformer area topology and locate the fault based on the target transformer area topology to identify the faulty energy meter in the transformer area.

[0111] It should be noted that "first" and "second" do not indicate a chronological order, but can be understood as names. The topology of the first transformer area is the pulse topology adjacency matrix determined through power pulse analysis, while the topology of the second transformer area is the electrical quantity topology adjacency matrix determined through big data analysis.

[0112] Furthermore, the comparison of the first and second transformer area topologies, and the determination of the target transformer area topology if they are identical, specifically involves: comparing the first and second transformer area topologies element-by-element to determine a difference matrix; if the difference between all elements in the difference matrix is ​​0, then they are determined to be identical, and the target transformer area topology is determined. Specifically, firstly, using an element-level comparison method, the values ​​at corresponding positions in the two matrices (the first and second transformer area topologies) are subtracted; if the difference between all positions is 0 (A... ij -B ijIf ≡0, where i is the number of transformer areas and j is the number of users, then the topology identified by the two methods is completely consistent. If there is a non-zero difference, it indicates that there is a discrepancy in the topology identification of the corresponding branch. More data needs to be collected for analysis to obtain the corresponding matrix until the pulse topology adjacency matrix and the electrical quantity topology adjacency matrix reach a consensus.

[0113] In some embodiments, if the topologies of the two transformer substations are different, a multi-cycle weighted average algorithm is triggered to smooth the electrical quantity data, the first pulse count, and the second pulse count. The relevant formula is: In the formula, For the electrical quantity data after multi-cycle smoothing in the i-th cycle, the number of the first pulse and the number of the second pulse, w k Let x be the weight for the k-th period. i+k The data is the historical data for the (i+k)th cycle, and M is the cumulative number of cycles. Pulse analysis and big data analysis are performed again until the obtained transformer topology results are consistent.

[0114] For example, please refer to Figure 5 , Figure 5 This is a schematic diagram of the topology of the first and second transformer substations (a and b). Both substation topologies include a master table 1 (T1), a master table 2 (T2), and users 1 (U1), 2 (U2), 3 (U3), 4 (U4), and 5 (U6). A value of 1 indicates that an element belongs to the master table for that substation, while 0 indicates that the element does not. By comparing the differences between the two matrices, two discrepancies are found: Discrepancy 1: (T1, U2) = 0 in the first substation topology, but (T1, U2) = 1 in the second substation topology; Discrepancy 2: (T2, U2) = 1 in the first substation topology, but (T2, U2) = 0 in the second substation topology. Therefore, the topologies obtained by the two methods are different, requiring further data collection and analysis to derive the corresponding matrices until the topologies of the first and second substations are consistent.

[0115] In some embodiments, if the topology of the first transformer area is exactly the same as that of the second transformer area, it means that both transformer area topologies are accurate, and either one can be selected as the target transformer area topology.

[0116] By comparing the two topological structures, the reliability and accuracy of the topology recognition results are greatly improved.

[0117] In some embodiments, fault location based on the target transformer area topology, and determining the faulty energy meter in the transformer area, includes: determining the third pulse count of each meter in the target transformer area topology, wherein the meter includes a main meter and sub-meters; calculating the energy pulse correlation coefficient between each meter using the Pearson correlation coefficient based on the third pulse count, determining whether the energy pulse correlation coefficient is greater than a preset threshold, and determining the faulty energy meter in the transformer area based on the determination result. Specifically, after determining the target transformer area topology, it is necessary to calculate the Pearson correlation coefficient of the energy pulse of each sub-meter within the target transformer area topology using the third pulse count corresponding to each sub-meter. Subsequently, two energy meters may cross-connect due to wiring errors, and their energy pulses will accumulate or increase synchronously, thus exhibiting a high correlation. Therefore, it is necessary to determine whether the energy pulse correlation coefficient is greater than a preset threshold (e.g., greater than 0.95) to determine that there is an abnormal correlation between the meters, that is, to determine that one or both of the two meters are faulty.

[0118] It should be noted that the preset threshold can be set based on historical data or experimental verification, and this application does not impose any restrictions.

[0119] By locating faults based on a defined topology, it is possible to quickly and accurately pinpoint the faulty electricity meter in the service area, thereby enabling rapid response and handling of the fault.

[0120] This embodiment of the application, by acquiring the first pulse count of the main meter and the second pulse count and electrical quantity data of the sub-meters, can collect the energy metering information and operating status data of each energy meter in the meter box, providing necessary information support for subsequent topology identification using different methods. By processing and analyzing the collected pulse count using a preset topology analysis model, key information reflecting the topological relationship of the transformer area can be extracted from the pulse count, initially establishing the topology of the transformer area. By calculating the target correlation coefficient between users, highly correlated user pairs can be screened, initially determining the set of users possibly located in the same transformer area. By eliminating user pairs that do not meet the correlation threshold, interference from irrelevant data is reduced, making the analysis more targeted. Next, the target DTW distance is calculated, and initial cluster centers are determined for iterative optimization until the clustering termination condition is met. This series of operations can fully utilize the time-series characteristics of electrical quantity data to uncover the similarities and differences in electrical characteristics among users, thereby more accurately dividing the transformer substation topology. This allows for topology identification from another dimension, complementing and verifying the pulse-number-based topology identification results, further improving the accuracy and reliability of topology identification. By comparing the two topologies, the credibility and accuracy of the topology identification results are greatly improved. Fault location based on the determined topology can quickly and accurately locate the faulty energy meter in the transformer substation, thereby enabling rapid response and handling of the fault. Compared with existing technologies, this application can improve the accuracy of transformer substation topology identification, thereby accurately locating the fault point in the transformer substation.

[0121] Example 2

[0122] Please refer to Figure 6 , Figure 6 This is a schematic diagram of the structure of an embodiment of the fault location system based on transformer area topology identification provided in this application, including: an acquisition module 100, a first determination module 200, a second determination module 300, and a fault location module 400;

[0123] The acquisition module 100 is used to acquire the first pulse count of the total meter in the meter box, and to acquire the second pulse count and electrical quantity data of several sub-meters in the meter box;

[0124] The first determining module 200 is used to input the first pulse number and each of the second pulse numbers into a preset topology analysis model for solving, to obtain a number of attribution relationship coefficients, and to determine the topology structure of the first transformer area based on each of the attribution relationship coefficients, wherein the attribution relationship coefficients are the coefficients by which each sub-table belongs to the main table;

[0125] The second determining module 300 is used to calculate the target correlation coefficient between users based on the electrical quantity data, and remove the first user pair whose target correlation coefficient does not meet the preset correlation threshold to obtain a number of second user pairs, calculate the target DTW distance of each second user pair, and take the second user pair with the largest target DTW distance as the third user pair, and take the third user pair as the initial cluster center for iterative optimization until the clustering termination condition is met, and determine the topology of the second transformer area based on the output target clustering result;

[0126] The fault location module 400 is used to compare the topology of the first transformer area and the topology of the second transformer area. If they are the same, the target transformer area topology is determined, and the fault is located based on the target transformer area topology to identify the faulty energy meter in the transformer area.

[0127] The information interaction and execution process between the modules in the above-mentioned fault location system based on transformer area topology identification are based on the same concept as the embodiment of the fault location method based on transformer area topology identification in the first aspect of the present invention, and the technical effects achieved are basically the same. For details, please refer to the description in the first embodiment of the method of the present invention, and will not be repeated here.

[0128] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate; 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 the method in this embodiment, depending on actual needs.

[0129] Please see Figure 7 , Figure 7 The hardware structure of a terminal device according to another embodiment is illustrated. The terminal device includes:

[0130] The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0131] The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701 to execute the dialogue risk assessment method based on a large model according to the embodiments of this application.

[0132] The input / output interface 703 is used to implement information input and output;

[0133] The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0134] Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704);

[0135] The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0136] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the fault location method based on transformer area topology identification as described in Embodiment 1 above.

[0137] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0138] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application.

[0139] In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application for those skilled in the art.

Claims

1. A fault location method based on transformer area topology identification, characterized in that, include: Obtain the first pulse count of the main meter in the meter box, and obtain the second pulse count and electrical quantity data of several sub-meters in the meter box; The first pulse count and each of the second pulse counts are input into a preset topology analysis model for solution to obtain several attribution relationship coefficients. The topology structure of the first transformer area is determined based on each attribution relationship coefficient, wherein the attribution relationship coefficient is the coefficient by which each sub-table belongs to the main table. Based on the electrical quantity data, the target correlation coefficient between users is calculated, and the first user pair whose target correlation coefficient does not meet the preset correlation threshold is eliminated to obtain several second user pairs. The target DTW distance of each second user pair is calculated, and the second user pair with the largest target DTW distance is taken as the third user pair. The third user pair is taken as the initial cluster center for iterative optimization until the clustering termination condition is met. The topology of the second transformer area is determined according to the output target clustering results. The topology of the first transformer area and the topology of the second transformer area are compared. If they are the same, the topology of the target transformer area is determined, and the fault location is performed based on the topology of the target transformer area to identify the faulty energy meter in the transformer area. The electrical quantity data includes voltage data, current data, and power data. The calculation of the target DTW distance for each second user pair specifically involves: constructing a first distance matrix, a second distance matrix, and a third distance matrix for the voltage data, the current data, and the power data, respectively; calculating a first cumulative matrix based on the first distance matrix, a second cumulative matrix based on the second distance matrix, and a third cumulative matrix based on the third distance matrix; for each cumulative matrix, finding the optimal path with the smallest cumulative distance, and calculating the cumulative distance of the optimal path to obtain the first DTW distance, the second DTW distance, and the third DTW distance; and weighting and fusing the first DTW distance, the second DTW distance, and the third DTW distance according to preset weights to obtain the target DTW distance for each second user pair.

2. The fault location method based on identification of the topology of the transformer district according to claim 1, characterized in that, The calculation formula for the topology analysis model is as follows: ； In the formula, This represents the affiliation coefficient between the j-th sub-table and the current station area master table, where j = 1, 2, ..., p; These are the measurement values ​​for different time series within the same subtable; The values ​​represent the measurements for different time series in the summary table; n is the number of data sets to be collected. Let j be the second pulse number of all sub-tables whose topological relationships are to be determined, where j = 1, 2, ..., p; The impulse constants for all sub-tables whose topological relationships are to be determined; This is the first pulse number in the total table for the distribution area. is the pulse constant of the total number of transformer substations, where k is the number of different transformer substations.

3. The fault location method based on transformer area topology identification according to claim 2, characterized in that, The target correlation coefficient between users is calculated based on the electrical quantity data, specifically as follows: Calculate a first correlation coefficient based on the voltage data between users; Calculate a second correlation coefficient based on the current data between users; A third correlation coefficient is calculated based on the power data between users, wherein the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient are all Pearson correlation coefficients; Based on the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient, the target correlation coefficient between users is determined.

4. The fault location method based on transformer area topology identification according to claim 1, characterized in that, The process involves selecting the second user pair with the largest target DTW distance as the third user pair, and using this third user pair as the initial cluster center for iterative optimization until the clustering termination condition is met. The second transformer area topology is then determined based on the output target clustering results. Specifically: The second user pair with the largest target DTW distance is taken as the third user pair, and the third user pair is taken as the initial cluster center. The fourth DTW distance between each user and the initial cluster center is calculated, and each user is assigned to the initial cluster center that is closest to the fourth DTW distance. For each user assigned to each initial cluster center, the mean sequence of the electrical quantity data is calculated, and the second cluster center is iteratively updated based on the mean sequence until the updated second cluster center meets the preset clustering termination condition. Then, the updated target clustering result is output, and the topology of the second transformer substation is determined based on the target clustering result.

5. The fault location method based on transformer area topology identification according to claim 1, characterized in that, The step of comparing the topology of the first transformer area and the topology of the second transformer area, and determining the target transformer area topology if they are the same, specifically involves: The difference matrix is ​​determined by comparing the topology of the first transformer area and the topology of the second transformer area element by element. If the difference between all elements in the difference matrix is ​​0, then the two are determined to be the same, and the target transformer area topology is determined.

6. The fault location method based on transformer area topology identification according to claim 1, characterized in that, The fault location based on the target transformer area topology, specifically determining the faulty energy meter in the transformer area, involves: Determine the third pulse number of each meter in the target transformer area topology, wherein the meters include a master meter and sub-meters; Based on the third pulse count, the energy pulse correlation coefficient between each meter is calculated using the Pearson correlation coefficient. It is then determined whether the energy pulse correlation coefficient is greater than a preset threshold, and the faulty energy meter in the distribution area is identified based on the determination result.

7. A fault location system based on transformer area topology identification, characterized in that, include: The module includes an acquisition module, a first determination module, a second determination module, and a fault location module. The acquisition module is used to acquire the first pulse count of the total meter in the meter box, and to acquire the second pulse count and electrical quantity data of several sub-meters in the meter box; The first determining module is used to input the first pulse number and each of the second pulse numbers into a preset topology analysis model for solving, to obtain several attribution relationship coefficients, and to determine the topology structure of the first transformer area based on each of the attribution relationship coefficients, wherein the attribution relationship coefficients are the coefficients by which each sub-table belongs to the main table; The second determining module is used to calculate the target correlation coefficient between users based on the electrical quantity data, and remove the first user pair whose target correlation coefficient does not meet the preset correlation threshold to obtain several second user pairs, calculate the target DTW distance of each second user pair, and take the second user pair with the largest target DTW distance as the third user pair, and take the third user pair as the initial cluster center for iterative optimization until the clustering termination condition is met, and determine the topology of the second transformer area based on the output target clustering result; The fault location module is used to compare the topology of the first transformer area and the topology of the second transformer area. If they are the same, the target transformer area topology is determined, and the fault is located based on the target transformer area topology to identify the faulty energy meter in the transformer area. The electrical quantity data includes voltage data, current data, and power data. The calculation of the target DTW distance for each second user pair specifically involves: constructing a first distance matrix, a second distance matrix, and a third distance matrix for the voltage data, the current data, and the power data, respectively; calculating a first cumulative matrix based on the first distance matrix, a second cumulative matrix based on the second distance matrix, and a third cumulative matrix based on the third distance matrix; for each cumulative matrix, finding the optimal path with the smallest cumulative distance, and calculating the cumulative distance of the optimal path to obtain the first DTW distance, the second DTW distance, and the third DTW distance; and weighting and fusing the first DTW distance, the second DTW distance, and the third DTW distance according to preset weights to obtain the target DTW distance for each second user pair.

8. A terminal device, characterized in that, include: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the fault location method based on transformer topology identification as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the fault location method based on transformer area topology identification as described in any one of claims 1-6.

Images