Distribution network fault location positioning method and device, electronic equipment and storage medium

Abstract

The invention provides a distribution network fault location positioning method and device, electronic equipment and a storage medium, and relates to the technical field of power fault analysis. The method comprises the following steps: acquiring various operation data of distribution network equipment corresponding to a target positioning point, wherein the target positioning point corresponds to multiple pieces of distribution network equipment; determining the difference between the operation data of the plurality of distribution network devices and reference distribution network data corresponding to the operation data for any operation data in the plurality of operation data; if the difference corresponding to any kind of operation data meets the fault condition, the target positioning point can be directly determined as the distribution network fault position, the fault position positioning process and algorithm complexity are simplified, and then the positioning efficiency and accuracy of the distribution network fault position are improved. And the fault position is determined through the plurality of distribution network devices associated with the target positioning point, so that the reliability of fault judgment is improved, and the positioning accuracy of the fault position is further improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power failure analysis, and particularly relates to a distribution network fault location method and device, electronic equipment and a storage medium. BACKGROUND

[0002] In the power system, various faults often occur in the distribution network equipment, which causes the distribution network to fail to provide power safely and stably. Therefore, it is particularly important to quickly and accurately locate the fault position and timely and effectively repair.

[0003] In related technologies, the position of the distribution network fault is located by analyzing the fault state after the fault occurs in the distribution network. However, the fault state of the distribution network is usually complex, and therefore the analysis of the fault state generally takes a long time, so that the distribution network fault position cannot be quickly and accurately located. SUMMARY

[0004] The present application provides a distribution network fault location method and device, electronic equipment and a storage medium, which can quickly and accurately locate the distribution network fault position.

[0005] In a first aspect, the present application provides a distribution network fault location method, comprising:

[0006] Obtaining a plurality of operating data of the distribution network equipment corresponding to the target positioning point, the target positioning point corresponding to a plurality of distribution network equipment;

[0007] For any one of the plurality of operating data, determining the difference between the operating data of the plurality of distribution network equipment and the reference distribution network data corresponding to the operating data;

[0008] If the difference corresponding to any one of the operating data meets the fault condition, the fault position of the distribution network is determined as the target positioning point.

[0009] In one possible implementation, the difference between the operating data of the plurality of distribution network equipment and the reference distribution network data corresponding to the operating data is determined, comprising:

[0010] Weighted sum of the operating data of the plurality of distribution network equipment to obtain a first intermediate value;

[0011] Weighted sum of the reference distribution network data corresponding to the operating data of the plurality of distribution network equipment to obtain a second intermediate value;

[0012] Taking the absolute difference between the first intermediate value and the second intermediate value as the denominator and the second intermediate value as the numerator to obtain a third intermediate value;

[0013] According to the cotangent value of the third intermediate value, the difference between the operating data of the plurality of distribution network equipment and the reference distribution network data corresponding to the operating data is obtained.

[0014] In a possible implementation, the method further includes:

[0015] If the difference corresponding to any of the operation data satisfies the fault condition, the fault frequency of the target positioning point is increased by a preset unit to obtain a new fault frequency corresponding to the target positioning point.

[0016] When the new fault frequency is greater than or equal to the fault frequency threshold, an early warning information is outputted, and the early warning information is used to prompt a relevant personnel to formulate a distribution network equipment updating plan.

[0017] In a possible implementation, the fault frequency threshold is determined in the following manner:

[0018] For each of the plurality of distribution network equipments, a difference between a service life of the distribution network equipment and the length of time in service is taken as a numerator, and an environmental factor corresponding to the distribution network equipment is taken as a denominator to obtain a fourth intermediate value.

[0019] The fourth intermediate value is multiplied by the service life of the distribution network equipment to obtain a frequency threshold of the distribution network equipment.

[0020] The frequency thresholds of the plurality of distribution network equipments corresponding to the target positioning point are weighted and summed to obtain the fault frequency threshold.

[0021] In a possible implementation, before the plurality of operation data of the distribution network equipment corresponding to the target positioning point is obtained, the method further includes:

[0022] Obtaining a distribution network topology structure;

[0023] Based on a preset positioning accuracy, the distribution network topology structure is divided to obtain at least one sub-topology structure, and the positioning accuracy is used to represent a minimum granularity of the division of the distribution network topology structure.

[0024] A positioning point is set for the sub-topology structure, and a mapping relationship between the positioning point and the distribution network equipment included in the sub-topology structure is stored.

[0025] In a possible implementation, the plurality of operation data of the distribution network equipment corresponding to the target positioning point is obtained in the following manner:

[0026] The plurality of original operation data of the distribution network equipment corresponding to the target positioning point is obtained.

[0027] For each of the plurality of original operation data, a respective pre-processing is performed to obtain the plurality of operation data of the distribution network equipment corresponding to the target positioning point, and the pre-processing includes at least one of data cleaning, data conversion, and data integration.

[0028] In a possible implementation, the method further includes:

[0029] If the difference corresponding to any type of operational data meets the fault conditions, then based on the operational data, the fault cause of the target location point is determined by using a pre-trained fault cause prediction model.

[0030] And / or, store the running data in a pre-set distribution network fault cause dataset to enrich the training sample data of the fault cause prediction model.

[0031] Secondly, this application provides a power distribution network fault location device, comprising:

[0032] The acquisition module is used to acquire various operating data of the distribution network devices corresponding to the target location point. The target location point corresponds to multiple distribution network devices.

[0033] The first determining module is used to determine the difference between the operating data of multiple distribution network devices and the corresponding benchmark distribution network data for any one type of operating data among multiple operating data.

[0034] The second determination module is used to determine the fault location of the distribution network as the target location point when the difference corresponding to any type of operating data meets the fault conditions.

[0035] In one possible implementation, the first determining module is specifically used for: performing a weighted summation of the operating data of multiple distribution network devices to obtain a first intermediate value; performing a weighted summation of the benchmark distribution network data corresponding to the operating data of the multiple distribution network devices to obtain a second intermediate value; using the absolute difference between the first intermediate value and the second intermediate value as the denominator and the second intermediate value as the numerator to obtain a third intermediate value; and obtaining the difference between the operating data of the multiple distribution network devices and the benchmark distribution network data corresponding to the operating data based on the cotangent value of the third intermediate value.

[0036] In one possible implementation, the distribution network fault location device further includes a processing module, which is used to: if the difference corresponding to any kind of operating data meets the fault conditions, perform a preset unit increase processing on the fault frequency of the target location point to obtain a new fault frequency corresponding to the target location point; when the new fault frequency is greater than or equal to the fault frequency threshold, output early warning information, which is used to prompt relevant personnel to formulate a distribution network equipment update plan.

[0037] In one possible implementation, the fault frequency threshold is determined as follows: for each of the multiple distribution network devices, the difference between the service life of the distribution network device and the time it has been put into use is used as the numerator, and the environmental factor corresponding to the distribution network device is used as the denominator to obtain a fourth intermediate value; the fourth intermediate value is multiplied by the service life of the distribution network device to obtain the frequency threshold of the distribution network device; the frequency thresholds of the multiple distribution network devices corresponding to the target location point are weighted and summed to obtain the fault frequency threshold.

[0038] In one possible implementation, the processing module is further configured to: acquire the distribution network topology before acquiring various operating data of the distribution network equipment corresponding to the target location point; divide the distribution network topology based on a preset positioning accuracy to obtain at least one sub-topology, wherein the positioning accuracy is used to characterize the minimum granularity of the distribution network topology division; set a location point for the sub-topology and store the mapping relationship between the location point and the distribution network equipment contained in the sub-topology.

[0039] In one possible implementation, the acquisition module is specifically used to: acquire multiple raw operating data of the distribution network equipment corresponding to the target location point; and preprocess each type of raw operating data to obtain multiple operating data of the distribution network equipment corresponding to the target location point. The preprocessing includes at least one of data cleaning, data conversion, and data integration.

[0040] In one possible implementation, the processing module is further configured to: if the difference corresponding to any type of operating data satisfies the fault condition, determine the fault cause of the target location point based on the operating data and through a pre-trained fault cause prediction model; and / or store the operating data in a preset distribution network fault cause dataset to enrich the training sample data of the fault cause prediction model.

[0041] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0042] The memory stores the instructions that the computer executes;

[0043] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0044] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible embodiments of the first aspect.

[0045] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0046] The method, apparatus, electronic device, and storage medium for locating fault locations in a distribution network provided in this application acquire multiple operating data of the distribution network equipment corresponding to the target location point, and the target location point corresponds to multiple distribution network equipment; for any one of the multiple operating data, the difference between the operating data of the multiple distribution network equipment and the corresponding benchmark distribution network data is determined; if the difference corresponding to any one of the operating data meets the fault conditions, the fault location of the distribution network is determined as the target location point. This application directly identifies the target location as the fault location by monitoring the differences between the operating data of multiple distribution network devices associated with the target location point and the baseline distribution network data. When the differences meet the fault conditions, the target location point can be directly identified as the distribution network fault location. Compared with related technologies that indirectly determine the distribution network fault location by analyzing the fault status, this simplifies the fault location process and reduces algorithm complexity, thereby improving the efficiency and accuracy of distribution network fault location. By determining the fault location through multiple distribution network devices associated with the target location point, multi-device collaborative analysis is achieved, improving the reliability of fault judgment and further enhancing the accuracy of distribution network fault location. In addition, the real-time judgment of the fault status of the target location point based on multi-dimensional operating data improves fault detection sensitivity, timely identifies the fault location of the distribution network, facilitates timely and effective emergency repairs by relevant personnel, and ensures the stability of the distribution network power supply. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0048] Figure 1 A schematic diagram illustrating a scenario for the power distribution network fault location method provided in this application embodiment;

[0049] Figure 2 A flowchart illustrating the distribution network fault location method provided in this application embodiment. Figure 1 ;

[0050] Figure 3 A flowchart illustrating the distribution network fault location method provided in this application embodiment. Figure 2 ;

[0051] Figure 4 Schematic diagram of the structure of the power distribution network fault location device provided in the embodiments of this application Figure 1 ;

[0052] Figure 2 Schematic diagram of the structure of the power distribution network fault location device provided in the embodiments of this application Figure 6 ;

[0053] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0054] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0055] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0056] The terms “first,” “second,” etc., used in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, products, or apparatus.

[0057] In related technologies, the location of a distribution network fault is typically determined by analyzing its status after the fault occurs. However, the fault status of a distribution network is usually quite complex, making the analysis time-consuming and thus unable to quickly and accurately locate the fault. This hinders timely and effective repairs and may result in unstable power supply to the distribution network.

[0058] To address the aforementioned technical problems, this application provides a method for locating distribution network faults. By monitoring the differences between the operating data of multiple distribution network devices associated with a target location point and baseline distribution network data, the target location point can be directly determined as the location of the distribution network fault when the differences meet the fault conditions, thus improving the efficiency and accuracy of fault location. Furthermore, by judging the fault status of the target location point in real time based on multi-dimensional operating data, the fault detection sensitivity is improved, and the fault location of the distribution network can be identified promptly.

[0059] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0060] Figure 1 This is a schematic diagram illustrating a scenario for the power distribution network fault location method provided in an embodiment of this application. For example... Figure 1 As shown, the distribution network topology 11 includes multiple location points (A, B, C), and each location point corresponds to multiple distribution network devices. For example, location point A is associated with distribution network devices a1, a2, ... a1. n Location point B is associated with distribution network devices b1, b2, ... b n Location point C is associated with distribution network devices c1, c2, ... c n Server 12 collects various operational data from the distribution network devices associated with each location point in real time. Server 12 has pre-set baseline distribution network data corresponding to the operational data and stores the location information of each location point. The baseline distribution network data can also be obtained by server 12 from other databases, data centers, or other channels. Server 12 deploys the distribution network fault location method provided in this application embodiment, executes the method, and determines the fault location of the distribution network from location points A, B, and C. The specific fault location of the distribution network can be determined through the location information of the location points.

[0061] It should be noted that server 12 can be replaced by a server cluster or virtual container resources, and server 12 can also be an edge computing device. This embodiment of the application does not limit the number of location points or the number of network distribution devices under each location point; these can be set according to the actual scenario and business requirements.

[0062] The following is combined Figure 2 Application scenarios, refer to Figure 1 This application describes the distribution network fault location method provided in its embodiments. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this application, and the implementation methods of this application are not limited to those described herein. Figure 2 The limitations of the application scenarios shown.

[0063] Figure 1 A flowchart illustrating the distribution network fault location method provided in this application embodiment. Figure 2 ,like Figure 3 As shown, the method includes:

[0064] S201. Obtain various operating data of the distribution network equipment corresponding to the target location point. The target location point corresponds to multiple distribution network equipment.

[0065] The distribution network equipment is not limited to transformers, circuit breakers, disconnect switches, capacitors, and reactors, and the operating data may include voltage, current, power, equipment temperature, vibration, and noise.

[0066] For example, server 12 stores the mapping relationship between target location points and distribution network equipment, and obtains the operation data of multiple distribution network equipment corresponding to the target location points from the data management system, operation and maintenance database, etc. The target location point contains location information (physical coordinates and / or logical location identifier), for example, the location information of location point A: X=120.5°, Y=30.2°, feeder F01-branch B03.

[0067] It should be noted that each type of distribution network equipment may have different operating data that needs to be monitored. In this embodiment, the type of operating data to be acquired is determined by the type of distribution network equipment.

[0068] S202. For any one type of operating data among multiple operating data, determine the difference between the operating data of multiple distribution network devices and the corresponding benchmark distribution network data.

[0069] Among them, the benchmark distribution network data can be regarded as the operating data of the distribution network equipment under standard operating conditions, that is, the operating data under normal conditions. The benchmark distribution network data corresponds one-to-one with the type of distribution network equipment and the type of operating data. Accordingly, the benchmark distribution network data also includes voltage, current, power, equipment temperature, vibration and noise, etc.

[0070] For example, target location point A is associated with 5 distribution network devices (a1, a2, a3, a4, and a5). The operating data includes voltage, current, and power. Determine the difference B1 between the real-time voltage data and the reference distribution network voltage data, the difference B2 between the real-time current data and the reference distribution network current data, and the difference B3 between the real-time power data and the reference distribution network power data for distribution network devices a1, a2, a3, a4, and a5.

[0071] The magnitude of the difference reflects the degree to which the operation of the distribution network equipment associated with the target location deviates from expectations. The greater the difference, the more likely the distribution network equipment may have potential faults or performance degradation, and may need to be replaced or upgraded, the operating environment or conditions of the equipment adjusted, or load management or regulation performed.

[0072] Optionally, the baseline distribution network data can also be dynamically updated to avoid misjudgments caused by environmental factors. For example, the current baseline value during the summer peak load period needs to be higher than that in winter. To avoid the impact of changes in load on the line on the baseline distribution network data, for example, the baseline distribution network data can be dynamically updated by combining the Long Short-Term Memory (LSTM) network model to predict the load for the next 2 hours.

[0073] S203. If any difference in the operating data satisfies the fault conditions, then the fault location of the distribution network is determined as the target location point.

[0074] Considering that different faults may manifest in different data indicators, such as overcurrent tripping faults manifesting as a sudden increase in current, and overvoltage tripping manifesting as a sudden drop or rise in voltage, multi-dimensional monitoring can capture problems more comprehensively and sensitively.

[0075] For example, if any one of the voltage difference B1, current difference B2, and power difference B3 meets the fault condition, such as when the deviation value of any one of the operating data is greater than the threshold corresponding to that operating data, the location information corresponding to the target location point is determined as the specific fault location of the distribution network.

[0076] It should be noted that fault conditions can be set according to business scenarios and requirements. For example, fault conditions can be set according to the tolerance of the business scenario for faults. The lower the tolerance, the more stringent the fault conditions should be. This application embodiment does not impose specific restrictions on fault conditions.

[0077] Optionally, when the difference corresponding to any type of operating data meets the fault conditions, an alarm message is output. The alarm message carries the location information of the target location point to prompt relevant personnel to promptly grasp the fault location of the distribution network, carry out timely and effective emergency repairs, and ensure the stability of the power supply of the distribution network.

[0078] In this embodiment, by monitoring the differences between the operating data of multiple distribution network devices associated with the target location point and the baseline distribution network data, the target location point can be directly determined as the location of the distribution network fault when the differences meet the fault conditions. Compared with related technologies that indirectly determine the location of the distribution network fault by analyzing the fault status, this simplifies the fault location process and reduces algorithm complexity, thereby improving the efficiency and accuracy of distribution network fault location. By determining the fault location through multiple distribution network devices associated with the target location point, multi-device collaborative analysis is achieved, improving the reliability of fault judgment and further enhancing the accuracy of distribution network fault location. In addition, the fault status of the target location point is judged in real time based on multi-dimensional operating data, improving fault detection sensitivity, timely identification of the distribution network fault location, facilitating timely and effective emergency repairs by relevant personnel, and ensuring the stability of the distribution network power supply.

[0079] In some embodiments, determining the difference between the operating data of multiple distribution network devices and the corresponding benchmark distribution network data includes: performing a weighted summation on the operating data of the multiple distribution network devices to obtain a first intermediate value; performing a weighted summation on the benchmark distribution network data corresponding to the operating data of the multiple distribution network devices to obtain a second intermediate value; using the absolute difference between the first intermediate value and the second intermediate value as the denominator and the second intermediate value as the numerator to obtain a third intermediate value; and obtaining the difference between the operating data of the multiple distribution network devices and the corresponding benchmark distribution network data based on the cotangent of the third intermediate value.

[0080] For example, the difference between the operating data of multiple distribution network devices and the corresponding baseline distribution network data is determined by the following formula (1). It can be understood that the following formula (1) is executed for each type of operating data:

[0081]

[0082] in, Indicates the first The type of running data is relative to the first The difference between the operational data and the baseline distribution network data is that the data corresponds to the baseline data. It is an integer greater than 1. Indicates the first Baseline distribution network data for each distribution network device Indicates the first The weight of each distribution network device Indicates the first Operating data of individual power distribution network devices This indicates the number of distribution network devices corresponding to the target location point. It is an integer greater than 1.

[0083] It should be noted that, Used to evaluate the The impact of the difference between the operating data of a distribution network device and the corresponding baseline distribution network data on the health status of the target location point can be determined according to the actual situation of the distribution network device in the distribution network. This application embodiment does not make specific limitations on this.

[0084] In some embodiments, the method for locating distribution network faults further includes: if the difference corresponding to any type of operating data meets the fault conditions, then the fault frequency of the target location point is increased by a preset unit to obtain a new fault frequency corresponding to the target location point; when the new fault frequency is greater than or equal to the fault frequency threshold, an early warning message is output, which is used to prompt relevant personnel to formulate a distribution network equipment update plan.

[0085] For example, server 12 continuously maintains a variable named fault frequency. When the difference corresponding to any kind of operating data meets the fault condition and it is determined that there is a fault at the target location point, the variable named fault frequency will be automatically updated. For example, it will be incremented from the original fault frequency n to n+1, where n+1 is the new fault frequency.

[0086] Fault frequency reflects the operational stability of multiple distribution network devices corresponding to the target location point. A higher fault frequency indicates, to a certain extent, that the devices are more aged, have poorer performance, and are more prone to failure. Therefore, when the new fault frequency exceeds the preset fault frequency threshold, an early warning message is output to prompt relevant personnel to pay attention to the distribution network devices corresponding to the target location point and to formulate a plan in advance to determine whether hardware upgrades or replacements are needed.

[0087] In this embodiment, by timely updating the fault frequency of the target location point and outputting early warning information when the fault frequency exceeds a preset fault frequency threshold, relevant personnel are reminded to formulate a power distribution equipment upgrade plan in advance, effectively avoiding the problem of unstable power supply caused by power distribution equipment failure.

[0088] In some embodiments, the fault frequency threshold is determined as follows: for each of the multiple distribution network devices, the difference between the service life of the distribution network device and the time it has been put into use is used as the numerator, and the environmental factor corresponding to the distribution network device is used as the denominator to obtain a fourth intermediate value; the fourth intermediate value is multiplied by the service life of the distribution network device to obtain the frequency threshold of the distribution network device; the frequency thresholds of the multiple distribution network devices corresponding to the target location point are weighted and summed to obtain the fault frequency threshold.

[0089] Among these, service life serves as the baseline lifespan, used to measure the degree of aging of distribution network equipment under ideal conditions. The duration of operation indicates the running time of the distribution network equipment; the longer the equipment operates, the greater the accumulated losses and the higher the risk of failure. Environmental factors measure the environmental quality of the environment in which the distribution network equipment is located; better environmental quality results in a lower environmental factor, while worse environmental quality results in a higher environmental factor. Environmental factors can be determined by multiple environmental data points, such as temperature, humidity, vibration, and pollution.

[0090] For example, the service life, usage time, and environmental factors of distribution network equipment are obtained from the distribution network management system and asset management system, and the fault frequency threshold is determined by the following formula (2):

[0091]

[0092] In the formula, This represents the fault frequency threshold for the target location point. Indicates the first The weight of each distribution network device Indicates the first Environmental factors corresponding to each distribution network device. Indicates the first The lifespan of each power distribution network device. Indicates the first The duration of service of each power distribution network device. Indicates the number of distribution network devices. It is an integer greater than 1.

[0093] In some embodiments, before acquiring various operational data of the distribution network equipment corresponding to the target location point, the method further includes: acquiring the distribution network topology; dividing the distribution network topology based on a preset positioning accuracy to obtain at least one sub-topology, wherein the positioning accuracy is used to characterize the minimum granularity of the distribution network topology division; setting a location point for the sub-topology and storing the mapping relationship between the location point and the distribution network equipment contained in the sub-topology.

[0094] For example, positioning accuracy can be determined based on rules such as area radius (e.g., 5 meters, 10 meters), number of devices (e.g., 10 devices), or level (e.g., Level 1 = feeder level, Level 2 = branch level, Level 3 = device level). The higher the positioning accuracy, the finer the distribution network topology is divided.

[0095] Taking a 10kV distribution network (containing 1200 nodes) in a certain area as an example, the distribution network topology is obtained from the distribution network map management system. The positioning accuracy is set to level 3 (device level), and the smallest sub-topology contains fewer than 30 distribution network devices. The distribution network topology can be divided into 45 sub-topologies. For each sub-topology, a positioning point is set, and location information such as physical coordinates and logical location identifiers are bound to this positioning point, making it easy to directly locate the specific location using this location information.

[0096] The distribution network equipment is bound to the location point to form a mapping relationship between the location point and the distribution network equipment. For example, the distribution network equipment associated with location point A (X urban area - East District - Feeder F01) includes circuit breaker (CB_01), voltage transformer (VT_01), and fault indicator (FI_01).

[0097] It should be noted that the positioning accuracy should be set according to the actual business scenario and needs. It is necessary to ensure that the sub-topology structure after division meets the accuracy requirements and is managed independently. This application does not make specific limitations on the setting of positioning accuracy.

[0098] In this embodiment, the distribution network topology is divided by a preset positioning accuracy, which enables the positioning accuracy of the distribution network fault location to be customized according to different business scenarios and needs, meeting diverse user needs and thus effectively improving the user experience.

[0099] In some embodiments, obtaining multiple operating data of the distribution network equipment corresponding to the target location point includes: obtaining multiple raw operating data of the distribution network equipment corresponding to the target location point; and performing preprocessing on each type of raw operating data to obtain multiple operating data of the distribution network equipment corresponding to the target location point. The preprocessing includes at least one of data cleaning, data conversion, and data integration.

[0100] Data cleaning includes using ETL and other cleaning tools to process missing data, noisy data (i.e., data containing errors or deviating from expected values), and inconsistent data in the original operational data. Data transformation includes processing inconsistencies in the extracted data and cleaning abnormal data according to business rules to ensure the accuracy of subsequent analysis results. Data integration involves merging data from different data sources (such as data management systems, operational databases, and data centers) into a unified database. Data integration solves problems such as data pattern matching, data redundancy, and data value conflict detection and handling. Data integration organically centralizes data from different sources, formats, and characteristics logically or physically, thereby providing comprehensive data sharing.

[0101] The original operational data is processed by any one, two, or three of the following methods: data cleaning, data transformation, and data integration, to obtain operational data.

[0102] For example, data cleaning can specifically include the following steps: handling missing values, which can be done using interpolation, deletion, and imputation methods; handling outliers, which can be done using deletion, replacement, and smoothing methods; and handling duplicate values, which can be done using deletion, merging, and deduplication methods. Data transformation can specifically include the following steps: data normalization, converting data with different units and dimensions into a unified standard for subsequent analysis; data standardization, standardizing the data to eliminate the influence of units and dimensions; and data smoothing, smoothing the data to remove noise and outliers. Data integration can include the following steps: data extraction, extracting the required data from different data sources; data transformation, converting data from different data sources into a unified format and standard; and data merging, merging the extracted and transformed data to form a complete dataset.

[0103] Preprocessing can improve the quality of running data, increase the efficiency of subsequent data analysis, and reduce computing costs.

[0104] Optionally, preprocessing may also include data reduction processing, which includes selecting features closely related to the target variable from the original operating data. The target variable can be understood as the amount of data involved in the calculation of the difference between the operating data and the corresponding benchmark distribution network data in step S202; and aggregating data with similar features into one category to achieve subsequent unified application of the data.

[0105] Data reduction processing can compress and simplify data to reduce its dimensionality and complexity, thereby improving data processing efficiency and interpretability.

[0106] In some embodiments, the distribution network fault location method further includes: if the difference corresponding to any type of operating data meets the fault condition, then based on the operating data, the fault cause of the target location point is determined by a pre-trained fault cause prediction model; and / or, the operating data is stored in a preset distribution network fault cause dataset to enrich the training sample data of the fault cause prediction model.

[0107] In one implementation, when the difference corresponding to any type of operational data meets the fault conditions, the fault cause of the target location point is determined based on the operational data and a pre-trained fault cause prediction model. The operational data is then stored in a pre-set distribution network fault cause dataset.

[0108] For example, if the difference corresponding to any type of operational data meets the fault condition, it indicates that there is a fault at the target location point. The operational data is then input into a pre-trained fault cause prediction model, which outputs the fault cause corresponding to the operational data to assist relevant personnel in handling the fault.

[0109] The fault cause prediction model can be built based on classification algorithms (such as random forest, decision tree, neural network, etc.) and trained using historical fault data. Furthermore, the operational data is stored in the distribution network fault cause dataset to facilitate subsequent training of the fault cause prediction model.

[0110] In another implementation, if the difference corresponding to any type of operational data meets the fault conditions, the operational data is stored in a preset distribution network fault cause dataset.

[0111] For example, when the difference corresponding to any type of operational data meets the fault condition, it indicates that there is a fault at the target location point. According to the fault cause, the operational data is stored in the distribution network fault cause dataset corresponding to the fault cause. This can be regarded as establishing a correspondence between the fault cause and the operational data characteristics. When a fault is subsequently detected at the target location point, the fault cause corresponding to the operational data at the time of the fault can be quickly found based on the correspondence between the fault cause and the operational data characteristics.

[0112] In another implementation, when the difference corresponding to any type of operational data meets the fault conditions, the fault cause of the target location point is determined based on the operational data and through a pre-trained fault cause prediction model.

[0113] In this embodiment of the application, an intelligent fault cause prediction model can quickly and accurately determine the fault cause of the target location point, which improves efficiency and reduces labor costs compared to manually analyzing the fault cause.

[0114] Figure 2Flowchart of the distribution network fault location method provided in this application Figure 3 ,like Figure 4 As shown, based on the above embodiments, a specific embodiment will be used to describe the distribution network fault location method in detail. This distribution network fault location method includes:

[0115] S301. Based on the preset positioning accuracy, the obtained distribution network topology is divided into at least one sub-topology.

[0116] For example, taking a 10kV distribution network (containing 1200 nodes) in a certain area as an example, the distribution network topology of the 10kV distribution network is obtained from the distribution network map management system. The positioning accuracy is set to level 3 (equipment level). The smallest sub-topology contains less than 30 distribution network devices, and the distribution network topology can be divided into 45 sub-topologies.

[0117] S302. Set location points for the sub-topology and store the mapping relationship between the location points and the distribution network devices contained in the sub-topology.

[0118] For each sub-topology, a location point is set, and location information, such as physical coordinates and logical location identifiers, is bound to this point to facilitate direct location of the specific location. Distribution network equipment is then bound to this location point, forming a mapping relationship between the location point and the distribution network equipment. For example, location point A (X City Area - East District - Feeder F01) is associated with distribution network equipment including circuit breakers (CB_01), voltage transformers (VT_01), and fault indicators (FI_01).

[0119] S303. Obtain various operating data of the distribution network equipment corresponding to the target location point. The target location point corresponds to multiple distribution network equipment.

[0120] For example, the operating data of multiple distribution network devices (circuit breaker (CB_01), voltage transformer (VT_01), and fault indicator (FI_01)) corresponding to the target location A are obtained from the data management system, operation and maintenance database, etc. The operating data includes voltage, current, and power.

[0121] S304. For any one type of operating data among multiple operating data, determine the difference between the operating data of multiple distribution network devices and the corresponding baseline distribution network data.

[0122] Determine the differences between the real-time voltage data of the circuit breaker (CB_01), voltage transformer (VT_01), and fault indicator (FI_01) and the reference distribution network voltage data (B1); the differences between the real-time current data and the reference distribution network current data (B2); and the differences between the real-time power data and the reference distribution network power data (B3).

[0123] S305. Determine whether the difference corresponding to any type of operating data meets the fault conditions.

[0124] If the voltage difference B1, current difference B2, and power difference B3 do not meet the fault conditions, it indicates that there is no fault at the target location point, and S303 is executed. If the difference corresponding to any of the operating data meets the fault conditions, for example, if the deviation value of any operating data is greater than the threshold corresponding to that operating data, it indicates that there is a fault at the target location point, and S306 is executed.

[0125] It should be noted that steps S306, S307, and S308 can be executed in any order and can be executed simultaneously.

[0126] S306. Determine the target location as the fault location of the distribution network.

[0127] The location information corresponding to the target location point is determined as the specific fault location of the distribution network.

[0128] S307. Based on the operational data, determine the cause of the fault at the target location point using a pre-trained fault cause prediction model.

[0129] For example, if the difference corresponding to any type of operational data meets the fault condition, it indicates that there is a fault at the target location point. The operational data is then input into a pre-trained fault cause prediction model, which outputs the fault cause corresponding to the operational data to assist relevant personnel in handling the fault.

[0130] S308. If the difference corresponding to any type of operating data meets the fault condition, then the fault frequency of the target location point is increased by a preset unit to obtain the new fault frequency corresponding to the target location point.

[0131] For example, when the difference corresponding to any type of operational data meets the fault conditions, the original fault frequency n is automatically incremented to n+1, where n+1 is the new fault frequency. The fault frequency reflects the operational stability of multiple distribution network devices corresponding to the target location point. The higher the fault frequency, the higher the aging degree and the worse the performance of these multiple distribution network devices, making them more prone to failure.

[0132] S309. When the new fault frequency is greater than or equal to the fault frequency threshold, output a warning message.

[0133] When the frequency of new faults exceeds the preset fault frequency threshold, an early warning message is output to remind relevant personnel to pay attention to the distribution network equipment corresponding to the target location and to formulate a plan in advance to determine whether hardware equipment needs to be updated or replaced.

[0134] In summary, this application has at least the following beneficial effects:

[0135] I. By monitoring the differences between the operational data of multiple distribution network devices associated with the target location point and the baseline distribution network data, the target location point can be directly identified as the location of the distribution network fault when the differences meet the fault conditions. Compared with related technologies that indirectly determine the location of the distribution network fault by analyzing the fault status, this simplifies the fault location process and reduces algorithm complexity, improving the efficiency and accuracy of distribution network fault location. Determining the fault location by using multiple distribution network devices associated with the target location point enables multi-device collaborative analysis, improving the reliability of fault judgment and further enhancing the accuracy of distribution network fault location. Furthermore, real-time judgment of the fault status of the target location point based on multi-dimensional operational data improves fault detection sensitivity, enabling timely identification of the distribution network fault location, facilitating timely and effective repairs by relevant personnel, and ensuring the stability of the distribution network power supply.

[0136] Second, by updating the fault frequency of the target location in a timely manner, and outputting early warning information when the fault frequency exceeds the preset fault frequency threshold, relevant personnel are reminded to formulate a power distribution equipment upgrade plan in advance, effectively avoiding the problem of unstable power supply caused by power distribution equipment failure.

[0137] Third, by dividing the distribution network topology by preset positioning accuracy, the positioning accuracy of the distribution network fault location can be customized according to different business scenarios and needs, meeting diverse user needs and thus effectively improving the user experience.

[0138] Fourth, through the intelligent fault cause prediction model, the fault cause of the target location point can be quickly and accurately determined, which improves efficiency and reduces labor costs compared to manually analyzing the fault cause.

[0139] Figure 1 Schematic diagram of the structure of the power distribution network fault location device provided in the embodiments of this application Figure 2 , Figure 4 Schematic diagram of the structure of the power distribution network fault location device provided in the embodiments of this application Figure 5 .

[0140] like Figure 6 As shown, the distribution network fault location device 40 provided in this embodiment includes: an acquisition module 41, a first determination module 42, and a second determination module 43. Wherein:

[0141] The acquisition module 41 is used to acquire various operating data of the distribution network equipment corresponding to the target location point, and the target location point corresponds to multiple distribution network equipment.

[0142] The first determining module 42 is used to determine the difference between the operating data of multiple distribution network devices and the corresponding benchmark distribution network data for any one type of operating data among multiple operating data.

[0143] The second determining module 43 is used to determine the fault location of the distribution network as the target location point when the difference corresponding to any type of operating data meets the fault conditions.

[0144] In one possible implementation, the first determining module 42 is specifically used for: performing a weighted summation of the operating data of multiple distribution network devices to obtain a first intermediate value; performing a weighted summation of the benchmark distribution network data corresponding to the operating data of the multiple distribution network devices to obtain a second intermediate value; using the absolute difference between the first intermediate value and the second intermediate value as the denominator and the second intermediate value as the numerator to obtain a third intermediate value; and obtaining the difference between the operating data of the multiple distribution network devices and the benchmark distribution network data corresponding to the operating data based on the cotangent value of the third intermediate value.

[0145] like Figure 6 As shown, in one possible implementation, the distribution network fault location device 40 further includes a processing module 44, which is used to: if the difference corresponding to any kind of operating data meets the fault conditions, perform a preset unit increase processing on the fault frequency of the target location point to obtain a new fault frequency corresponding to the target location point; when the new fault frequency is greater than or equal to the fault frequency threshold, output early warning information, which is used to prompt relevant personnel to formulate a distribution network equipment update plan.

[0146] In one possible implementation, the fault frequency threshold is determined as follows: for each of the multiple distribution network devices, the difference between the service life of the distribution network device and the time it has been put into use is used as the numerator, and the environmental factor corresponding to the distribution network device is used as the denominator to obtain a fourth intermediate value; the fourth intermediate value is multiplied by the service life of the distribution network device to obtain the frequency threshold of the distribution network device; the frequency thresholds of the multiple distribution network devices corresponding to the target location point are weighted and summed to obtain the fault frequency threshold.

[0147] In one possible implementation, the processing module 44 is further configured to: acquire the distribution network topology before acquiring various operating data of the distribution network equipment corresponding to the target location point; divide the distribution network topology based on a preset location accuracy to obtain at least one sub-topology, wherein the location accuracy is used to characterize the minimum granularity of the distribution network topology division; set location points for the sub-topology and store the mapping relationship between the location points and the distribution network equipment contained in the sub-topology.

[0148] In one possible implementation, the acquisition module 41 is specifically used to: acquire multiple original operating data of the distribution network equipment corresponding to the target location point; and preprocess each type of original operating data to obtain multiple operating data of the distribution network equipment corresponding to the target location point. The preprocessing includes at least one of data cleaning, data conversion, and data integration.

[0149] In one possible implementation, the processing module 44 is further configured to: if the difference corresponding to any type of operating data satisfies the fault condition, determine the fault cause of the target location point based on the operating data and through a pre-trained fault cause prediction model; and / or store the operating data in a preset distribution network fault cause dataset to enrich the training sample data of the fault cause prediction model.

[0150] The distribution network fault location device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0151] ​ This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. ​ As shown, the electronic device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the electronic device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0152] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.

[0153] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0154] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0155] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0156] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0157] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0158] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0159] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0160] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0161] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0162] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0163] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0164] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0165] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0166] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for locating faults in a distribution network, characterized in that, include: Acquire various operational data of the distribution network equipment corresponding to the target location point, wherein the target location point corresponds to multiple distribution network devices; For any one of the various operating data, determine the difference between the operating data of the multiple distribution network devices and the corresponding baseline distribution network data; If any difference in the operating data satisfies the fault condition, then the fault location of the distribution network is determined as the target location point.

2. The method for locating distribution network faults according to claim 1, characterized in that, Determining the difference between the operating data of the multiple distribution network devices and the corresponding baseline distribution network data includes: The operating data of the multiple distribution network devices are weighted and summed to obtain the first intermediate value; The second intermediate value is obtained by weighted summing of the baseline distribution network data corresponding to the operating data of the plurality of distribution network devices; The third intermediate value is obtained by taking the absolute difference between the first intermediate value and the second intermediate value as the denominator and the second intermediate value as the numerator. Based on the cotangent value of the third intermediate value, the difference between the operating data of the multiple distribution network devices and the benchmark distribution network data corresponding to the operating data is obtained.

3. The method for locating distribution network faults according to claim 1 or 2, characterized in that, Also includes: If the difference corresponding to any type of operating data meets the fault condition, then the fault frequency of the target location point is increased by a preset unit to obtain a new fault frequency corresponding to the target location point. When the new fault frequency is greater than or equal to the fault frequency threshold, an early warning message is output, which is used to prompt relevant personnel to formulate a power distribution network equipment upgrade plan.

4. The method for locating distribution network faults according to claim 3, characterized in that, The fault frequency threshold is determined in the following way: For each of the plurality of distribution network devices, the difference between the service life of the distribution network device and the time it has been put into use is used as the numerator, and the environmental factor corresponding to the distribution network device is used as the denominator to obtain the fourth intermediate value. Multiply the fourth intermediate value by the lifespan of the distribution network equipment to obtain the frequency threshold of the distribution network equipment; The fault frequency threshold is obtained by weighted summation of the frequency thresholds of multiple distribution network devices corresponding to the target location point.

5. The method for locating faults in a distribution network according to claim 1 or 2, characterized in that, Before acquiring various operational data of the distribution network equipment corresponding to the target location point, the method further includes: Obtain the distribution network topology; Based on a preset positioning accuracy, the distribution network topology is divided to obtain at least one sub-topology. The positioning accuracy is used to characterize the minimum granularity of the distribution network topology division. A location point is set for the sub-topology, and the mapping relationship between the location point and the distribution network equipment included in the sub-topology is stored.

6. The method for locating faults in a distribution network according to claim 1 or 2, characterized in that, The acquisition of various operational data of the distribution network equipment corresponding to the target location point includes: Obtain various raw operating data of the distribution network equipment corresponding to the target location point; For each type of raw operating data, preprocessing is performed to obtain various operating data of the distribution network equipment corresponding to the target location point. The preprocessing includes at least one of data cleaning, data transformation, and data integration.

7. The method for locating faults in a distribution network according to claim 1 or 2, characterized in that, Also includes: If the difference corresponding to any type of operational data satisfies the fault condition, then based on the operational data, the fault cause of the target location point is determined by a pre-trained fault cause prediction model. And / or, store the running data in a preset distribution network fault cause dataset to enrich the training sample data of the fault cause prediction model.

8. A distribution network fault location device, characterized in that, include: The acquisition module is used to acquire various operating data of the distribution network equipment corresponding to the target location point, wherein the target location point corresponds to multiple distribution network devices; The first determining module is used to determine the difference between the operating data of the multiple distribution network devices and the corresponding benchmark distribution network data for any one of the multiple operating data; The second determining module is used to determine the fault location of the distribution network as the target location point when the difference corresponding to any type of operating data meets the fault conditions.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, Includes a computer program that, when executed, implements the method of any one of claims 1 to 7.

Images