Low-voltage distribution fault location method based on artificial intelligence

Abstract

The present disclosure provides an artificial intelligence-based low-voltage distribution fault location method, belonging to the field of distribution automation technology. The method includes: calculating the fault probability of each distribution area based on the operation monitoring data of each distribution area; dividing each distribution area into a target area; generating a location order for each distribution area based on the magnitude of the fault probability; and sequentially inputting the protector action data corresponding to each distribution area into a fault location model based on the location order until the fault location result of the target area is obtained. The artificial intelligence-based low-voltage distribution fault location method provided by the present disclosure can improve the troubleshooting efficiency of low-voltage distribution systems.

Description

Technical Field

[0001] The present disclosure belongs to the field of power distribution automation technology, and more specifically, relates to a low-voltage power distribution fault location method based on artificial intelligence. Background Art

[0002] The factory's low-voltage power distribution system transmits and distributes electricity from the upper power grid to various power consumption points within the factory to meet the power needs of different equipment and processes. Among them, the distribution cabinet is the core of the factory's low-voltage power distribution system. When a fault occurs in the low-voltage distribution system, each distribution cabinet needs to be checked one by one. Due to the complex internal wiring of the distribution cabinet, the troubleshooting process is time-consuming and labor-intensive. Existing low-voltage distribution fault location methods based on artificial intelligence usually pre-train a fault location model based on the low-voltage distribution system. When a low-voltage distribution fault occurs, the protector action data of the low-voltage distribution system is input into the fault location model to obtain the fault location result of the low-voltage distribution system. This method saves the trouble of manual troubleshooting, but its computing speed needs to be improved. Summary of the Invention

[0003] The purpose of the present disclosure is to provide a low-voltage power distribution fault location method based on artificial intelligence to improve the fault detection efficiency of the low-voltage power distribution system.

[0004] A first aspect of the embodiments of the present disclosure provides a low-voltage power distribution fault location method based on artificial intelligence, comprising:

[0005] Calculating the failure probability of each distribution area based on the operation monitoring data of each distribution area; each distribution area is obtained by dividing the target area;

[0006] Generate a location order for each distribution area based on the magnitude of the fault probability;

[0007] Based on the positioning order, the protector action data corresponding to each distribution area is sequentially input into the fault location model until the fault location result of the target area is obtained.

[0008] A second aspect of the embodiments of the present disclosure provides a low-voltage power distribution fault location device based on artificial intelligence, comprising:

[0009] A probability calculation module is used to calculate the failure probability of each distribution area based on the operation monitoring data of each distribution area; each distribution area is obtained by dividing the target area;

[0010] A sequence determination module is used to generate a location order for each distribution area based on the magnitude of the fault probability;

[0011] The fault location module is used to input the protector action data corresponding to each distribution area into the fault location model in sequence based on the location order until the fault location result of the target area is obtained.

[0012] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned artificial intelligence-based low-voltage distribution fault location method when executing the computer program.

[0013] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based low-voltage distribution fault location method are implemented.

[0014] The beneficial effects of the low-voltage power distribution fault location method based on artificial intelligence provided by the embodiments of the present disclosure are:

[0015] The embodiment of the present disclosure takes into account that there are many protectors in the target area, and the amount of protector action data is large. A large amount of protector action data input into the fault location model will generate a large amount of calculation, resulting in slow calculation speed and high requirements on processor performance. Therefore, the present disclosure divides the target area into multiple distribution areas, and calculates the failure probability of each distribution area based on the operation monitoring data of each distribution area. The higher the failure probability of a distribution area, the higher the probability of failure. Based on this, each distribution area is prioritized according to the failure probability of each distribution area, and the distribution area with the highest failure probability is the first to undergo fault investigation (fault location). In this way, the fault point can be determined based on the protector action data of some distribution areas, which is conducive to quickly determining the fault point, thereby improving the efficiency of fault investigation. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] Figure 1 A flowchart of a low-voltage power distribution fault location method based on artificial intelligence provided by an embodiment of the present disclosure;

[0018] Figure 2 A schematic diagram of the line topology structure of a power distribution area provided in an embodiment of the present disclosure;

[0019] Figure 3This is a structural block diagram of a low-voltage power distribution fault location device based on artificial intelligence provided by an embodiment of the present disclosure;

[0020] Figure 4 A schematic block diagram of an electronic device provided in one embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present disclosure with unnecessary detail.

[0022] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0023] Please refer to Figure 1 , Figure 1 A flowchart of a low-voltage power distribution fault location method based on artificial intelligence provided in one embodiment of the present disclosure is provided. The method includes:

[0024] S101: Calculating the failure probability of each power distribution area based on operation monitoring data of each power distribution area, wherein each power distribution area is obtained by dividing the target area.

[0025] In this embodiment, the distribution area can be divided based on the number of protectors in the target area. For example, if there are a large number of protectors inside a distribution cabinet A, the distribution cabinet can be divided into a separate distribution area. If there are a small number of protectors inside distribution cabinets B and C, distribution cabinets B and C can be divided into one distribution cabinet area.

[0026] The distribution area's operational monitoring data, including parameters such as voltage, current, power factor, and temperature, can be used to monitor the area's operating status in real time. By analyzing this data, the likelihood of a failure can be estimated, effectively calculating the distribution area's failure probability.

[0027] S102: Generate a positioning order for each power distribution area based on the magnitude of the fault probability.

[0028] In this embodiment, the power distribution areas may be sorted in descending order of fault probability to obtain a troubleshooting order (ie, a location order) for the power distribution areas.

[0029] S103: Inputting the protector action data corresponding to each distribution area into the fault location model in sequence based on the location order until a fault location result of the target area is obtained.

[0030] In this embodiment, each distribution area can be checked (fault location) in sequence. If the specific fault point can be obtained based on the protector action data of the current distribution area, the fault checking can be stopped and the fault point obtained from the current distribution area can be used as the fault location result of the target area.

[0031] From the above, it can be concluded that the embodiment of the present disclosure takes into account that there are many protectors in the target area, and the amount of protector action data is large. A large amount of protector action data input into the fault location model will generate a large amount of calculation, resulting in slow calculation speed and high requirements on processor performance. Therefore, the present disclosure divides the target area into multiple distribution areas, and calculates the failure probability of each distribution area based on the operation monitoring data of each distribution area. The higher the failure probability of a distribution area, the higher the probability of failure. Based on this, each distribution area is prioritized according to the failure probability of each distribution area, and the distribution area with the highest failure probability is the first to undergo fault investigation (fault location). In this way, the fault point can be determined based on the protector action data of some distribution areas, which is conducive to quickly determining the fault point, thereby improving the efficiency of fault investigation.

[0032] In one embodiment of the present disclosure, calculating the failure probability of each power distribution area based on the operation monitoring data of each power distribution area includes:

[0033] A first failure probability of each power distribution area is calculated based on internal operation data of each power distribution area.

[0034] The second fault probability of each power distribution area is calculated based on the load operation law of each power distribution area.

[0035] The third fault probability of each power distribution area is calculated based on the load mutation data of each power distribution area.

[0036] The failure probability of each power distribution area is calculated based on the first failure probability, the second failure probability, and the third failure probability corresponding to each power distribution area.

[0037] In this embodiment, the primary cause of a distribution zone failure is the presence of internal operating data exceeding normal values ​​(e.g., parameters such as voltage, current, and temperature). Furthermore, the load operating patterns of the distribution zone can also affect its reliable operation. For example, under a constant power load, the voltage or current does not fluctuate significantly. In this case, the voltage and current within the distribution zone are relatively stable, reducing voltage fluctuations and current surges, and facilitating smooth operation. On some automated production lines, however, robotic arms, conveyor belts, and other automated equipment need to start and stop frequently, causing frequent operation of electrical components such as circuit breakers and contactors within the distribution zone. This increases wear and tear on these components, shortening their service life. Furthermore, uncontrollable factors can also cause load fluctuations, impacting the normal operation of the distribution zone. For example, insufficient raw material supply can cause certain production lines to halt production. Once sufficient raw materials are available, production resumes, causing load fluctuations within the distribution zone. This places additional stress on equipment within the distribution zone, accelerating wear and aging.

[0038] This embodiment comprehensively considers the degree of influence of internal operating data, load operating rules and load mutation data on the operation of the distribution area. First, the first fault probability of each distribution area is calculated based on the internal operating data of each distribution area, the second fault probability of each distribution area is calculated based on the load operating rules of each distribution area, and the third fault probability of each distribution area is calculated based on the load mutation data of each distribution area. Then, the failure probability of each distribution area is calculated based on the first failure probability, second failure probability and third failure probability corresponding to each distribution area, which is conducive to the accurate calculation of the failure probability of the distribution area.

[0039] Specifically, a weighted summation may be performed on the first fault probability, the second fault probability, and the third fault probability corresponding to each distribution area to obtain the fault probability of each distribution area. The weight coefficient of the weighted summation may be adjusted according to actual conditions.

[0040] In one embodiment of the present disclosure, calculating the first failure probability of each power distribution area based on internal operating data of each power distribution area includes:

[0041] The first failure rate of each power distribution area is calculated based on the usage time of the equipment in each power distribution area.

[0042] A second failure rate for each power distribution area is calculated based on the temperature data of each power distribution area.

[0043] A first failure probability of each power distribution area is calculated based on the first failure rate and the second failure rate corresponding to each power distribution area.

[0044] In this embodiment, internal operational data that influences the failure rate of a distribution area may include the age of equipment in the distribution area. After long-term use, equipment in the distribution area will experience component aging and wear, impacting the performance and stability of the distribution area. Therefore, the longest-serving device among the key equipment in the distribution area can be selected as the equipment age for that distribution area. Before the equipment age in the distribution area reaches a first service life, a low failure rate (referred to in this embodiment as the first failure rate) can be set. After reaching the first service life (e.g., six years), the first failure rate will gradually increase. After reaching a second service life (e.g., ten years), replacement of the equipment should be considered.

[0045] Specifically, the first failure rate P of the power distribution area can be calculated using the following formula: 11 :

[0046]

[0047] Among them, n is the service life of the equipment in the distribution area, n1 is the first service life, n2 is the second service life, a, b and are preset constants, and 0 <a<b<1。

[0048] In this embodiment, the internal operating data that influences the failure rate of the distribution area may also include the distribution area's temperature data. If equipment within the distribution area operates at high temperatures for extended periods, the stability and reliability of components within the distribution area may decline. High temperatures may also cause insulation aging and breakdown of equipment coils and leads, increasing the risk of equipment failure. The device with the highest temperature can be selected from multiple temperature monitoring points within the distribution area. Based on the temperature data of this device within the third time period before the failure, the duration of the distribution area's high-temperature operation within that time period can be calculated. The longer the distribution area's high-temperature operation lasts, the higher the second failure rate.

[0049] Specifically, the second failure rate P of the power distribution area can be calculated using the following formula: 12 :

[0050]

[0051] in, The sum of the time periods when the temperature data is greater than the preset temperature value. is the duration of the third time, c and d are both preset constants. and When the proportion of is small (less than d), the second failure rate P 12 Set to a smaller constant c, when and When the proportion of is greater than d, the second failure rate P 12 Based on the constant c increases with the increase of .

[0052] On the basis of obtaining the first failure rate and the second failure rate, the first failure rate and the second failure rate are weighted and summed to obtain a first failure rate of the corresponding power distribution area.

[0053] In one embodiment of the present disclosure, calculating the second fault probability of each power distribution area based on the load operation law of each power distribution area includes:

[0054] The first mapping relationship is searched based on the load operation rule of each power distribution area to obtain the second fault probability of each power distribution area.

[0055] In this embodiment, the probability of a distribution area failure under various load conditions can be pre-recorded to construct a first mapping relationship. This first mapping relationship can characterize the correspondence between load operating patterns and distribution area failure probabilities. This allows for convenient determination of the corresponding second failure probabilities for each distribution area based on the load operating patterns of each distribution area when locating a distribution system fault. The first mapping relationship can be in the form of a table or a wiring diagram, which is not limited here.

[0056] In one embodiment of the present disclosure, calculating the third fault probability of each power distribution area based on the load mutation data of each power distribution area includes:

[0057] Calculate the number of load mutations in each distribution area in the first period before a fault occurs.

[0058] The third fault probability of each power distribution area is calculated based on the number of load mutations corresponding to each power distribution area.

[0059] In this embodiment, the number of load mutations in each distribution area can be calculated based on the data records of each distribution area within the first time before the fault occurs. The greater the number of load mutations, the higher the third fault probability of the corresponding distribution area.

[0060] Specifically, the third failure probability P3 can be calculated using the following formula:

[0061]

[0062] in, is the duration of the first time, in days, m is the number of load mutations, e is a preset constant, 0 <e<1。

[0063] In one embodiment of the present disclosure, calculating the number of load mutations in each distribution area within the first period before a fault occurs includes:

[0064] A curve segment having a load power greater than a preset power and a duration greater than a second time is selected from the recent load curves of each distribution area; the recent load curves of each distribution area are the load curves of each distribution area within the first time before the fault occurs.

[0065] The number of curve segments is determined as the number of load mutations in the corresponding distribution area.

[0066] In this embodiment, the number of load mutations can be obtained based on the load curves of each distribution area within the first period before the fault occurs. The load curve is a curve that indicates how the load changes over time. The curve segments where the load power exceeds the preset power and lasts longer than the second time are considered as load mutation time periods. The number of load mutations can be obtained by counting the number of load mutation time periods. To avoid the influence of interference signals during data collection, the load mutation time periods only consider curve segments where the load power continuously exceeds the preset power (for a duration longer than the second time).

[0067] In one embodiment of the present disclosure, the protector action data corresponding to any distribution area is a vector composed of action values ​​of each protector in the distribution area.

[0068] In this embodiment, after determining the troubleshooting order, an artificial intelligence-based method can be used to locate the fault in each distribution area. Figure 2 As shown, the equipment within the distribution area can be divided into multiple sub-areas (sec1, sec2, sec3, sec4, sec5, and sec6) based on the line topology. Each sub-area is equipped with a protector (including circuit breakers and current protectors). When a fault occurs in the distribution area, if a protector triggers a protection action, its action value is set to 1; otherwise, its action value is set to 0. The circuit breaker action value or current protector action value in each sub-area constitutes a protector action vector and is input into a pre-trained fault localization model. The fault localization model outputs the fault probability of each sub-area. If there are sub-areas with a fault probability exceeding a preset value, these sub-areas are identified as possible fault points and are investigated first. Otherwise, the distribution area is considered fault-free and troubleshooting can proceed to the next distribution area. The pre-trained fault localization model can be trained using a BP neural network, a probabilistic neural network, or other similar techniques to leverage the powerful nonlinear processing capabilities of neural networks to locate faults in complex lines within the distribution network.

[0069] Corresponding to the low-voltage power distribution fault location method based on artificial intelligence in the above embodiment, Figure 3 This is a structural block diagram of a low-voltage power distribution fault location device based on artificial intelligence provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 3The artificial intelligence-based low-voltage power distribution fault location device 20 includes: a probability calculation module 21, a sequence determination module 22 and a fault location module 23.

[0070] The probability calculation module 21 is used to calculate the failure probability of each distribution area based on the operation monitoring data of each distribution area; each distribution area is obtained by dividing the target area.

[0071] The sequence determination module 22 is used to generate a positioning sequence for each power distribution area based on the magnitude of the fault probability.

[0072] The fault location module 23 is used to input the protector action data corresponding to each distribution area into the fault location model in sequence based on the location order until the fault location result of the target area is obtained.

[0073] In one embodiment of the present disclosure, the probability calculation module 21 is specifically configured to:

[0074] A first failure probability of each power distribution area is calculated based on internal operation data of each power distribution area.

[0075] The second fault probability of each power distribution area is calculated based on the load operation law of each power distribution area.

[0076] The third fault probability of each power distribution area is calculated based on the load mutation data of each power distribution area.

[0077] The failure probability of each power distribution area is calculated based on the first failure probability, the second failure probability, and the third failure probability corresponding to each power distribution area.

[0078] In one embodiment of the present disclosure, the probability calculation module 21 is further configured to:

[0079] A first failure rate of each power distribution area is calculated based on the usage time of each power distribution area.

[0080] A second failure rate for each power distribution area is calculated based on the temperature data of each power distribution area.

[0081] A first failure probability of each power distribution area is calculated based on the first failure rate and the second failure rate corresponding to each power distribution area.

[0082] In one embodiment of the present disclosure, the probability calculation module 21 is further configured to:

[0083] The first mapping relationship is searched based on the load operation rule of each power distribution area to obtain the second fault probability of each power distribution area.

[0084] In one embodiment of the present disclosure, the probability calculation module 21 is further configured to:

[0085] Calculate the number of load mutations in each distribution area in the first period before a fault occurs.

[0086] The third fault probability of each power distribution area is calculated based on the number of load mutations corresponding to each power distribution area.

[0087] In one embodiment of the present disclosure, the probability calculation module 21 is further configured to:

[0088] A curve segment having a load power greater than a preset power and a duration greater than a second time is selected from the recent load curves of each distribution area. The recent load curves of each distribution area are the load curves of each distribution area within the first time before the fault occurs.

[0089] The number of curve segments is determined as the number of load mutations in the corresponding distribution area.

[0090] In one embodiment of the present disclosure, the protector action data corresponding to any distribution area is a vector composed of action values ​​of each protector in the distribution area.

[0091] See also Figure 4 , Figure 4 This is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 4 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules / units in the above-mentioned device embodiments, such as Figure 3 The functions of modules 21 to 23 are shown.

[0092] It should be understood that in the embodiments of the present disclosure, the processor 301 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0093] The input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0094] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store device type information.

[0095] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the artificial intelligence-based low-voltage distribution fault location method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0096] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When executed by a processor, the program instructions implement all or part of the process steps in the above-described method embodiments. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-described method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0097] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the computer-readable storage medium can include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or is about to be output.

[0098] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0099] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0100] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or can be an electrical, mechanical or other form of connection.

[0101] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the objectives of the embodiments of the present disclosure.

[0102] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0103] The above are only specific embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or replacements within the technical scope disclosed in this disclosure, and such modifications or replacements should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A low-voltage power distribution fault location method based on artificial intelligence, characterized in that: include: Calculate the failure probability of each distribution area based on the operation monitoring data of each distribution area; Each power distribution area is obtained by dividing the target area; Generate a location order for each distribution area based on the magnitude of the fault probability; Inputting the protector action data corresponding to each distribution area into the fault location model in sequence based on the location order until the fault location result of the target area is obtained; The calculating of the failure probability of each power distribution area based on the operation monitoring data of each power distribution area includes: Calculating the first failure probability of each power distribution area based on internal operating data of each power distribution area; Calculating the second fault probability of each distribution area based on the load operation law of each distribution area; Calculating the third fault probability of each distribution area based on the load mutation data of each distribution area; Calculating the failure probability of each power distribution area based on the first failure probability, the second failure probability, and the third failure probability corresponding to each power distribution area; The calculating the first failure probability of each power distribution area based on the internal operation data of each power distribution area includes: Calculate the first failure rate of each power distribution area based on the equipment usage time of each power distribution area; calculating a second failure rate of each power distribution area based on the temperature data of each power distribution area; Calculating a first failure probability for each power distribution area based on the first failure rate and the second failure rate corresponding to each power distribution area; Among them, the first failure rate P 11 The calculation formula is as follows: Among them, n is the service life of the equipment in the distribution area, n1 is the first service life, n2 is the second service life, a, b and are preset constants, and 0 <a < b <1; The second failure rate P 12 The calculation formula is as follows: in, The sum of the time periods during which the temperature data is greater than the preset temperature value within the third period before the fault. is the duration of the third time, c and d are both preset constants; The calculating the third fault probability of each power distribution area based on the load mutation data of each power distribution area includes: Selecting a curve segment whose load power is greater than a preset power and whose duration is greater than a second time from a recent load curve of each power distribution area; the recent load curve of each power distribution area is a load curve of each power distribution area within the first time before the fault occurs; Determine the number of the curve segments as the number of load mutations in the corresponding power distribution area; The third failure probability of each power distribution area is calculated based on the number of load mutations corresponding to each power distribution area.

2. The artificial intelligence-based low-voltage power distribution fault location method according to claim 1, characterized in that: The calculating the second fault probability of each power distribution area based on the load operation rule of each power distribution area includes: The first mapping relationship is searched based on the load operation rule of each power distribution area to obtain the second fault probability of each power distribution area.

3. The artificial intelligence-based low-voltage power distribution fault location method according to claim 1, characterized in that: The protector action data corresponding to any distribution area is a vector composed of the action values ​​of each protector in the distribution area.

4. A low-voltage power distribution fault location device based on artificial intelligence, characterized in that: include: A probability calculation module is used to calculate the failure probability of each distribution area based on the operation monitoring data of each distribution area; Each power distribution area is obtained by dividing the target area; A sequence determination module is used to generate a location order for each distribution area based on the magnitude of the fault probability; A fault location module is used to input the protector action data corresponding to each distribution area into the fault location model in sequence based on the location order until the fault location result of the target area is obtained; The probability calculation module is specifically used for: Calculating the first failure probability of each power distribution area based on internal operating data of each power distribution area; Calculating the second fault probability of each distribution area based on the load operation law of each distribution area; Calculating the third fault probability of each distribution area based on the load mutation data of each distribution area; Calculating the failure probability of each power distribution area based on the first failure probability, the second failure probability, and the third failure probability corresponding to each power distribution area; The probability calculation module is also used to: Calculating a first failure rate of each power distribution area based on the usage time of each power distribution area; calculating a second failure rate of each power distribution area based on the temperature data of each power distribution area; Calculating a first failure probability for each power distribution area based on the first failure rate and the second failure rate corresponding to each power distribution area; Among them, the first failure rate P 11 The calculation formula is as follows: Among them, n is the service life of the equipment in the distribution area, n1 is the first service life, n2 is the second service life, a, b and are preset constants, and 0 <a < b <1; The second failure rate P 12 The calculation formula is as follows: in, The sum of the time periods during which the temperature data is greater than the preset temperature value within the third period before the fault. is the duration of the third time, c and d are both preset constants; The probability calculation module is also used to: Selecting a curve segment whose load power is greater than a preset power and whose duration is greater than a second time from a recent load curve of each power distribution area; the recent load curve of each power distribution area is a load curve of each power distribution area within the first time before the fault occurs; Determine the number of the curve segments as the number of load mutations in the corresponding power distribution area; The third failure probability of each power distribution area is calculated based on the number of load mutations corresponding to each power distribution area.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images