Method and system for predicting partial discharge fault of power distribution network

Abstract

The embodiment of the invention relates to the technical field of electrical detection, in particular to a power distribution network partial discharge fault prediction method and system. The method comprises the steps that radio frequency current transformers are arranged at a neutral line and main lines and branch lines in a power distribution network to collect mutual inductance current data; a bracket is mounted on the inspection unmanned aerial vehicle, and an ultrasonic acquisition device is mounted on the bracket; the inspection unmanned aerial vehicle is controlled to collect sound data one by one from the marked position of the transformer shell of the transformer area in the power distribution network along a preset first inspection path; after the inspection unmanned aerial vehicle returns, mounting an electromagnetic wave acquisition device on a bracket of the inspection unmanned aerial vehicle; controlling the inspection unmanned aerial vehicle to fly over an electrical cabinet in the power distribution network along a preset second inspection path, and collecting electromagnetic radiation data; and the server receives the mutual inductance current data, the sound data and the electromagnetic radiation data and obtains a prediction result of the partial discharge fault according to the mutual inductance current data, the sound data and the electromagnetic radiation data.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the technical field of electrical detection, and specifically to a method and system for predicting partial discharge faults in a distribution network. Background Art

[0002] Partial discharge (PD) is an electrical discharge phenomenon that occurs in a local area within an insulating material. It can occur in solid, liquid, or gaseous insulating media. In a distribution network, due to reasons such as equipment aging, manufacturing defects, improper installation, or environmental factors, the insulation performance may decline, leading to partial discharge. Partial discharge gradually damages the insulating material, causing its performance to deteriorate, and may ultimately lead to insulation breakdown and short-circuit faults. Continuous partial discharge shortens the service life of power equipment, increases the risk of sudden faults, and affects power supply reliability. Equipment failures caused by partial discharge result in power outages and increased maintenance costs. Since the distribution network has a wide distribution range, and the electrical equipment in the distribution network is numerous and of various types, the detection of partial discharge in the distribution network is not only costly but also has a long cycle, making it difficult to meet the requirements for ensuring the safety of the distribution network. Therefore, it is necessary to improve the detection technology for partial discharge faults in the distribution network. Summary of the Invention

[0003] Multiple embodiments of this specification describe a method and system for predicting partial discharge faults in a distribution network.

[0004] In a first aspect, an embodiment of this specification provides a method for predicting partial discharge faults in a distribution network, including the steps of: At the neutral line of the substation transformer in the distribution network and at the main lines and branch lines in the distribution network, radio frequency current transformers are set to collect mutual inductance current data. The radio frequency current transformers have wireless communication modules, and the wireless communication modules establish communication connections with a preset server; A bracket is installed on an inspection drone, and an ultrasonic acquisition device is installed on the bracket. The ultrasonic acquisition device establishes a communication connection with the inspection drone, and the inspection drone establishes a communication connection with the server; Controlling the inspection drone to collect sound data one by one from the marked positions of the substation transformer housing in the distribution network along a preset first inspection path; After the inspection drone returns, an electromagnetic wave acquisition device is installed on the bracket of the inspection drone. The electromagnetic wave acquisition device establishes a communication connection with the inspection drone; Controlling the inspection drone to fly over the electrical cabinets in the distribution network along a preset second inspection path to collect electromagnetic radiation data; The server receives and obtains a prediction result of a partial discharge fault based on the mutual inductance current data, sound data, and electromagnetic radiation data.

[0005] In a second aspect, an embodiment of this specification provides a prediction system for partial discharge faults in a distribution network, including: A mutual inductance prediction module. At the neutral line of the substation transformer in the distribution network and at the main lines and branch lines in the distribution network, radio frequency current transformers are set to collect mutual inductance current data. The radio frequency current transformers have wireless communication modules, and the wireless communication modules establish communication connections with a preset server; An ultrasonic prediction module. A bracket is installed on the inspection drone, and an ultrasonic acquisition device is installed on the bracket. The ultrasonic acquisition device establishes a communication connection with the inspection drone, and the inspection drone establishes a communication connection with the server; A first acquisition module controls the inspection drone to collect sound data one by one from the marked positions of the outer shells of the substation transformers in the distribution network along a preset first inspection path; An electromagnetic wave prediction module. After the inspection drone returns, an electromagnetic wave acquisition device is installed on the bracket of the inspection drone. The electromagnetic wave acquisition device establishes a communication connection with the inspection drone; A second acquisition module controls the inspection drone to fly over the electrical cabinets in the distribution network along a preset second inspection path to collect electromagnetic radiation data; A fault prediction module. The server receives and obtains a prediction result of a partial discharge fault based on the mutual inductance current data, sound data, and electromagnetic radiation data.

[0006] In a third aspect, an embodiment of this specification provides an electronic device, including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program codes; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in any of the above aspects.

[0007] In a fourth aspect, an embodiment of this specification provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any of the above aspects is implemented.

[0008] In a fifth aspect, an embodiment of this specification provides a computer program product, including a computer program. When the computer program is executed by a processor, the method described in any of the above aspects is implemented.

[0009] The beneficial effects brought by the technical solutions provided in some embodiments of this specification at least include: In multiple embodiments of this specification, a prediction method and system for partial discharge faults in a distribution network are provided. By setting up radio frequency current transformers to collect mutual inductance current data and installing ultrasonic acquisition devices and electromagnetic wave acquisition devices on inspection drones, it is possible to comprehensively monitor partial discharge conditions from multiple dimensions, improving the accuracy and reliability of detection. Using inspection drones for automatic inspection can quickly cover large areas, especially suitable for the widely distributed distribution network environment, significantly improving the inspection efficiency. Using automated inspection means instead of traditional manual inspection methods not only reduces labor costs but also reduces the safety risks brought by staff contacting high-voltage equipment. Timely detection and handling of partial discharge problems help prevent short-circuit faults caused by insulation breakdown, ensuring the stable operation of the power system and improving power supply reliability.

[0010] Other features and advantages of multiple embodiments of this specification will be further revealed in the following specific implementation manners and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0012] Figure 1 Schematic flowchart of the prediction method for partial discharge faults provided for the embodiments of this specification.

[0013] Figure 2 Schematic diagram of the structure of the inspection drone provided for the embodiments of this specification.

[0014] Figure 3 Schematic flowchart of the first inspection path generation method provided for the embodiments of this specification.

[0015] Figure 4 Schematic diagram of the geometric marking point positions provided for the embodiments of this specification.

[0016] Figure 5 Schematic diagram of the electrical cabinet provided for the embodiments of this specification.

[0017] Figure 6 Schematic flowchart of the partial discharge fault diagnosis method provided for the embodiments of this specification.

[0018] Figure 7 Schematic flowchart of the method for obtaining the delay positioning reference table provided for the embodiments of this specification.

[0019] Figure 8 Schematic diagram of the prediction system for partial discharge faults provided for the embodiments of this specification.

[0020] Figure 9 Schematic diagram of the electronic device provided in the embodiments of this specification. Detailed implementation manners

[0021] The technical solutions of the embodiments of this specification will be explained and described below with reference to the accompanying drawings of the embodiments of this specification. However, the following embodiments are only the preferred embodiments of this specification and not all of them. Based on the embodiments in the implementation manners, other embodiments obtained by those skilled in the art without creative efforts all fall within the protection scope of this specification.

[0022] Terms such as "first", "second", "third", etc. in the specification, claims and the above-mentioned drawings of this specification are used to distinguish different objects rather than to describe a specific order. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0023] In the following description, terms indicating orientation or positional relationship such as "inner", "outer", "upper", "lower", "left", "right", etc. are only for the convenience of describing the embodiments and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation to this specification.

[0024] The data involved in this application are all information and data authorized by users or fully authorized by all parties, and the collection of relevant data complies with the relevant laws, regulations and standards of relevant countries and regions.

[0025] Before introducing the technical solutions described in this specification, the application scenarios of the technical solutions and related technologies will be introduced.

[0026] The distribution network is an important part of the power system and is responsible for distributing medium-voltage electrical energy from the substation to each user terminal. The distribution network includes the entire power transmission path from the low-voltage side of the substation to the final user. The structure of the distribution network is usually planned according to the characteristics of the power supply area (such as urban, rural or industrial areas) and load demand, mainly including high-voltage / medium-voltage substations, medium-voltage distribution networks, distribution transformers, low-voltage distribution networks and user terminals. The high-voltage / medium-voltage substation is the starting point of the distribution network and is responsible for stepping down the high-voltage electrical energy transmitted by the transmission network to a medium-voltage level suitable for distribution. Overhead lines use conductors supported by poles and are suitable for areas with sparse population. Underground cables are often used in urban areas to avoid visual pollution and reduce the impact of weather. Switching stations / ring main units allow operators to control the power flow for easy maintenance and fault isolation. Distribution transformers convert medium voltage to low voltage for use by households and small businesses. Distribution transformers include pole-mounted transformers installed on poles and also include pad-mounted transformers located on the ground or in basements. Output from the distribution transformer provides power directly to users. Similarly, the low-voltage lines can be connected to the internal wiring of users, including residential, commercial and industrial users, in the form of overhead lines or underground cables.

[0027] Partial Discharge (PD) in a transformer refers to a local electrical breakdown phenomenon that occurs in the transformer insulation system when the electric field strength exceeds the withstand voltage capacity of the insulating material in a certain local area. It usually occurs inside or on the surface of the insulating material, as well as in the air gaps between conductors. Although the energy released by a single partial discharge is small, if it occurs frequently, it will cause the insulating material to gradually deteriorate and be damaged, and may eventually lead to the failure of the entire insulation system, affecting the safe operation of the transformer. To effectively monitor and prevent faults caused by partial discharge, modern power systems use a variety of monitoring technologies to detect partial discharge in the transformer in real time. These technologies include, but are not limited to, obtaining the electrical pulse signals generated by partial discharge through Rogowski coils and using ultrasonic sensors to capture the ultrasonic signals generated during discharge.

[0028] Partial discharge in the electrical cabinet 30 refers to an electrical discharge phenomenon in a local area that occurs inside or on the surface of the insulating material, usually occurring in high-voltage electrical equipment such as switchgear and cable joints. When the insulating material is damaged or aged, its insulation performance deteriorates, which may lead to the occurrence of partial discharge. Partial discharge in distribution cables is one of the important factors affecting the insulation performance of cables and their accessories and may cause power system failures. In distribution cables, partial discharge usually occurs where there are defects inside or on the surface of the insulating material. These defects may be flaws in the manufacturing process, improper installation, aging caused by long-term operation or the influence of the external environment (such as moisture, pollution, etc.).

[0029] Due to the wide distribution range of the distribution network, and the large number and diverse types of electrical equipment in the distribution network, the partial discharge detection of the distribution network is not only costly but also has a long cycle, making it difficult to meet the requirements for ensuring the safety of the distribution network. Therefore, it is necessary to improve the detection technology for partial discharge faults in the distribution network. The four-rotor inspection UAV 11 has the characteristics of simple structure, flexible control, and vertical takeoff and landing, and has been widely used in many fields. In the power industry, a specially designed four-rotor inspection UAV 11 can resist the electromagnetic interference generated around power equipment and has been increasingly used in the distribution network inspection tasks in recent years, significantly improving the efficiency of the distribution network inspection.

[0030] This specification first provides a method for predicting partial discharge faults in a distribution network. Please refer to the appendix Figure 1 , including the steps: Step S101) At the neutral line of the substation transformer in the distribution network and at the main lines and branch lines in the distribution network, set up radio frequency current transformers to collect mutual inductance current data. The radio frequency current transformers have wireless communication modules, and the wireless communication modules establish communication connections with a preset server.

[0031] Monitor the insulation status of power equipment by detecting high-frequency current pulses generated due to partial discharge activities to prevent potential faults. Installing radio frequency current transformers at the neutral line of the substation transformer can help monitor partial discharges occurring inside low-voltage side equipment (such as cables, switch cabinets, etc.). Because partial discharges generate high-frequency currents in the entire circuit, and these currents will flow through the neutral line, monitoring here can capture partial discharge signals at multiple points within the system. Installing radio frequency current transformers on the main lines and branch lines in the distribution network can more directly monitor partial discharges within a specific line segment. It can help locate the line position where partial discharges occur, especially in complex network structures, and has a guiding role in the detection and troubleshooting of partial discharges.

[0032] Step S102) Install a bracket 12 on the inspection UAV 11, and install an ultrasonic acquisition device on the bracket 12. The ultrasonic acquisition device establishes a communication connection with the inspection UAV 11, and the inspection UAV 11 establishes a communication connection with the server. Please refer to the appendix Figure 2 , as a recommended method, the bracket 12 extends to a preset length at the front end of the inspection UAV 11 and is located below the rotor, and the vertical distance from the rotor is a preset value. The ultrasonic acquisition device can adopt the technologies already disclosed in the art. The anti-electromagnetic radiation technology of the inspection UAV can adopt the technologies already disclosed in the art.

[0033] There is a bracket 12 set on the inspection UAV 11, and a magnetic suction head 13 is installed at the end of the bracket 12. The magnetic suction head 13 is a permanent magnet.

[0034] This specification provides an implementation of an ultrasonic acquisition device, including a housing, a plurality of electromagnets, a plurality of magnets, a sound collector, an elastic bracket, a back magnet, a communication module, a controller, and a battery. The back magnet is installed on the back of the housing and is used to cooperate with the magnetic head 13. A plurality of the magnets are installed on the front of the housing. The electromagnets are installed inside the housing and are in one-to-one correspondence with the magnets in position. The sound collector is installed on the housing through the elastic bracket, and the sound collector extends out relative to the magnets. The electromagnets, the communication module, and the sound collector are all connected to the controller, and the battery supplies power to the remaining components.

[0035] The process of the inspection UAV 11 installing the ultrasonic acquisition device on the outer shell 21 of the transformer is as follows: The inspection UAV 11 uses the magnetic head 13 to attract and combine with the back magnet of an ultrasonic acquisition device, and through communication, makes the electromagnets of the corresponding ultrasonic acquisition device generate a magnetic field with the opposite magnetic pole direction to that of the magnets, and the two are basically offset, so that the ultrasonic acquisition device can be removed from the steel plate. After removal, the electromagnets are powered off to save electrical energy.

[0036] Then, the inspection UAV 11 carries the ultrasonic acquisition device and flies to the first marked point 23. Through flight control and attitude control, the magnetic head 13 on the bracket 12 drives the ultrasonic acquisition device to align with the geometric marked point 22. However, at this time, a certain distance still needs to be maintained from the outer shell 21. At this time, control the electromagnets to generate a magnetic field with the opposite magnetic pole direction to that of the magnets so that the magnetic fields of the two are basically offset from each other. Control the inspection UAV 11 to continue approaching the outer shell 21, so that the ultrasonic acquisition device aligns with the first marked point 23 and is close to the outer shell 21 of the transformer. Then control the electromagnets to power off. At this time, the ultrasonic acquisition device will be firmly adsorbed on the outer shell 21 of the transformer through the magnets and form a coupling with the outer shell 21. The inspection UAV 11 retreats at this time. The suction force between the magnetic head 13 and the back magnet is less than the suction force between the magnets and the outer shell 21 of the transformer. Therefore, the magnetic head 13 will be separated from the back magnet. The inspection UAV 11 also needs to complete time synchronization with the ultrasonic acquisition device. The time synchronization technology is carried out using the technology already disclosed in the art.

[0037] According to the positions of the geometric marked points 22, the inspection UAV 11 continues to place multiple ultrasonic acquisition devices at multiple geometric marked points 22 in sequence. After collecting ultrasonic data for a preset duration, the inspection UAV 11 removes the ultrasonic acquisition device from the transformer.

[0038] The steps for the inspection UAV 11 to remove the ultrasonic acquisition device from the transformer housing 21 include: The inspection UAV 11 makes the magnetic head 13 attract to the back magnet of the ultrasonic acquisition device through flight control and attitude control; then controls the electromagnet to generate a magnetic field with the opposite magnetic pole direction to the magnet, so that the magnetic fields of the two are basically cancelled out; the inspection UAV 11 flies backward, making the magnetic head 13 drive the ultrasonic acquisition device to separate from the transformer housing 21, and then controls the electromagnet to cut off the power; the inspection UAV 11 transports the ultrasonic acquisition device to a position close to the placed steel plate through flight control and attitude control. When it is a certain distance close to the steel plate, controls the electromagnet to generate a magnetic field with the opposite magnetic pole direction to the magnet. After completing the position placement, cuts off the power of the electromagnet, and the inspection UAV 11 can fly away.

[0039] Step S103) Control the inspection UAV 11 to collect sound data one by one from the marked positions of the transformer housings 21 in the medium-voltage transformer substations of the distribution network along the preset first inspection path.

[0040] Please refer to the appendix Figure 3 , The method for presetting the first inspection path includes: Step S201) Mark the first marked points on the housing 21 of each substation transformer. Select a prominent and easily recognizable position on the transformer housing 21 as the first marked point, such as a fixed position on the front of the housing. Please refer to the appendix Figure 4 , Use physical marks, such as sticking labels, spraying markings. Or virtual marks, such as marking based on the coordinate points of the GIS map. The marked points should be unified to ensure that the first marked points of all transformers have the same position.

[0041] Step S202) Obtain the coordinates of all substation transformers in the distribution network and the coordinates of the first marked points. Collect the spatial position information of all substation transformers and their first marked points to provide basic data for subsequent path planning. Use a GPS device or a GIS system to obtain the geographical coordinates of the substation transformers. For the first marked points, their specific coordinates can be calculated by relative position measurement or directly based on the offset of the transformer coordinates.

[0042] Step S203) Generate an approach path according to the coordinates of all the first marked points. The length of the approach path is a preset length, and the direction is perpendicular to the transformer housing 21. Preset a fixed approach path length, such as 0.5 meters - 0.8 meters. The direction of the approach path is perpendicular to the surface of the transformer housing 21 to ensure that the inspection equipment can approach the target point at the best angle.

[0043] Step S204) Generate the first inspection path according to the free ends of all the approach paths. The free end of the approach path refers to the starting point of the path at the end far from the transformer. Use the publicly disclosed path planning algorithm in the art to connect all the free ends into a shortest path or an optimal path.

[0044] The marked position includes a first marked point position and a plurality of geometric marked point positions 22. The method for collecting sound data from the marked position of the outer shell 21 of the distribution transformer in the medium voltage substation of the distribution network includes: Controlling the inspection UAV 11 to couple the ultrasonic acquisition device with the outer shell 21 of the distribution transformer along the approaching path; After waiting for a preset duration, removing the ultrasonic acquisition device and obtaining the sound data collected by the ultrasonic acquisition device.

[0045] After the inspection UAV 11 returns in step S104), an electromagnetic wave acquisition device is installed on the bracket 12 of the inspection UAV 11, and the electromagnetic wave acquisition device establishes a communication connection with the inspection UAV 11.

[0046] A transient breakdown phenomenon that occurs when the electric field strength in a local area exceeds the breakdown strength of the medium in that area. Partial discharge is usually accompanied by the generation of various physical phenomena, including electromagnetic radiation. The electromagnetic radiation generated by partial discharge has a certain directivity, which is related to the specific position of the discharge source and the surrounding geometric structure. Partial discharge is usually in the form of instantaneous pulses, with a very short duration, generally in the nanosecond to microsecond level. These pulse signals contain a large amount of high-frequency components, enabling the electromagnetic radiation to radiate outward in the form of electromagnetic waves. The amplitude and frequency of partial discharge may change with time and operating conditions. The generated electromagnetic wave frequency range is quite wide, which can extend from a few kilohertz (kHz) to several gigahertz (GHz). The specific frequency band depends on various factors, including but not limited to the characteristics of the partial discharge source, the properties of the surrounding medium, and the discharge position, etc. In the ultra-high frequency part, in the frequency band from several hundred MHz to several GHz, the electromagnetic waves generated by partial discharge have stronger penetration ability and less attenuation, which makes ultra-high frequency very suitable for detecting partial discharge phenomena in enclosed equipment, such as the detection of the electrical cabinet 30 in the distribution network shown in the figure. Usually, 2 - 4 antennas are used to capture electromagnetic radiation in different frequency bands respectively. Figure 5 As shown in the detection of the electrical cabinet 30 in the distribution network. Usually, 2 - 4 antennas are used to capture electromagnetic radiation in different frequency bands respectively.

[0047] Step S105): Controlling the inspection UAV 11 to fly over the electrical cabinet 30 in the distribution network along a preset second inspection path to collect electromagnetic radiation data.

[0048] The method for presetting the second inspection path includes: obtaining the positions of all the electrical cabinets 30 in the distribution network, setting a flyover point for each electrical cabinet 30, and obtaining the coordinates of the flyover point; generating a second inspection path according to the coordinates of all the flyover points.

[0049] Step S106): The server receives and obtains a prediction result of the partial discharge fault based on the mutual inductance current data, sound data, and electromagnetic radiation data.

[0050] Specifically, please refer to the appendix Figure 6 A method for obtaining a prediction result of a partial discharge fault based on the mutual inductance current data, sound data, and electromagnetic radiation data includes: Step S301) Use a preset feature extraction model to extract the features of the mutual inductance current data; Step S302) Compare the features with the pre-stored reference features. If the comparison is consistent, it is determined that there is no partial discharge in the corresponding neutral line, main line, or branch line. If the comparison is inconsistent, it is determined that there is partial discharge in the corresponding neutral line, main line, or branch line; Step S303) Extract the features of the sound data and compare them with the reference sound features stored in the inspection UAV 11. If the comparison is matched, it is determined that there is no partial discharge; Step S304) When the comparison is not matched, control the inspection UAV 11 to carry multiple ultrasonic acquisition devices one by one from a specified position and couple them to multiple geometric marking points 22 pre-marked on the outer shell 21 of the target transformer; Step S305) After waiting for a preset duration, remove the multiple ultrasonic acquisition devices one by one and obtain the sound data collected by the multiple ultrasonic acquisition devices; Step S306) Obtain a position prediction result of partial discharge based on the multiple sound data; Step S307) Extract the frequency domain features of the electromagnetic radiation data to obtain the frequency composition; Step S308) Compare the frequency composition with a preset reference frequency composition. When the comparison is consistent, it is determined that there is no partial discharge in the corresponding electrical cabinet 30. When the comparison is inconsistent, it is determined that there is partial discharge in the corresponding electrical cabinet 30.

[0051] Among them, the method of the preset feature extraction model includes: reading multiple mutual inductance current data as sample data; establishing an autoencoder model and training the autoencoder model using the sample data; obtaining a feature extraction model according to the first half of the autoencoder model.

[0052] Collect a large amount of mutual inductance current data, which contains signals under normal operation and partial discharge conditions, providing sufficient data support for subsequent training. The amount of data should be large enough to ensure that the model can capture the potential features of the data. An autoencoder is an unsupervised learning model that can compress input data into a low-dimensional space and reconstruct the original data on this basis. By training the autoencoder, the potential features of the mutual inductance current data can be learned.

[0053] The reference sound features stored in the inspection UAV 11 include the frequency composition and amplitude ratio of the sound data collected at the same predetermined positions corresponding to several transformer load intervals. The method for extracting the features of the sound data and comparing them with the reference sound features stored in the inspection UAV 11 includes: Select the frequency composition of the sound data within a preset frequency range, construct a vector of the selected frequency composition and its amplitude ratio, denoted as the first vector; According to the frequency composition included in the first vector, select the corresponding frequency composition and its amplitude ratio from the frequency compositions of the sound data corresponding to each transformer load interval to obtain a plurality of second vectors; Calculate the similarity between the first vector and each of the second vectors respectively. When there is a similarity value higher than a preset reference similarity threshold, it is determined that the comparison is matched. When there is no similarity value higher than the preset reference similarity threshold, it is determined that the comparison is unmatched. By dividing the load intervals and using the amplitude ratio for comparison, the change in the sound data caused by the load difference can be offset, and the accuracy of the comparison can be improved. The distance calculation between vectors can be carried out using the techniques disclosed in the art.

[0054] When the comparison is unmatched, the inspection UAV 11 carries the ultrasonic acquisition devices one by one, sets the time synchronization, acquisition duration, and acquisition frequency, and couples them to multiple marked points pre-marked on the outer shell 21 of the target transformer. After waiting for a preset duration, remove the multiple ultrasonic acquisition devices one by one, and obtain the sound data collected by the multiple ultrasonic acquisition devices through the wireless communication connection.

[0055] The method for obtaining the position prediction result of partial discharge based on the multiple sound data includes: After aligning the multiple sound data along the time axis, select the sound data corresponding to the specified marked point to calibrate a discharge pulse, and obtain the sound propagation delay of the discharge pulse generated at the remaining marked points based on the remaining sound data to obtain a delay vector; According to the delay vector and the delay positioning reference table pre-stored in the inspection UAV 11, obtain the position identification result of partial discharge. The delay positioning reference table is an association table between the position identification results and the delay vectors of the same model and the same marked points obtained under laboratory conditions.

[0056] The ultrasonic waves of the partial discharge fault inside the transformer are transmitted to the ultrasonic sensors coupled outside the wall through a multi-medium path. The ultrasonic sensors are mounted on the outer shell 21 of the transformer oil tank according to a certain geometric rule. Find the time difference between the partial discharge time measured by each sensor and the reference time and the coordinates of each sensor. The measured delay is used as the time from the discharge point to the sensor. Multiply the equivalent wave velocity v by the delay to obtain the spatial position from the discharge point to each sensor, and substitute it into the non-linear over-determined equation to obtain the position of the discharge source. Specifically, it includes establishing a spherical equation: (x0 - x i ) 2 +(y0 - y i ) 2+ (z0 - z i ) 2 =(vt i ) 2 where i = 1, 2, 3,..., n, representing the serial numbers of the ultrasonic acquisition devices, x i , y i , z i represent the coordinates of the i-th ultrasonic acquisition device, and x0, y0, z0 represent the position of the partial discharge point. t i represents the delay corresponding to each ultrasonic acquisition device, and v is the equivalent wave velocity. Since the propagation of ultrasonic waves inside the transformer is not a constant value but has a certain range, the wave velocity is regarded as a variable, that is, the equivalent wave velocity v. Plus the coordinates of the position of the partial discharge point to be solved, there are 4 variables. Using at least four ultrasonic acquisition devices can obtain the coordinates of the position of the partial discharge point and the equivalent wave velocity. Just use the least squares method to solve the spherical equation.

[0057] However, the least squares method is a non-linear algorithm, which takes a long time to calculate, occupies a large amount of memory, and the calculation results are greatly affected by the initial value and step size. If the selection is inappropriate, the system of equations may have no solution or a large error. For this reason, this embodiment provides a delay positioning reference table, and the approximate position of the partial discharge can be quickly obtained by looking up the table. According to the structure at the approximate position, the structure with the partial discharge fault is obtained for subsequent disposal reference.

[0058] Please refer to Appendix Figure 7 , and the method for obtaining the delay positioning reference table includes: Step S401) Divide the internal space of the selected type of transformer into multiple grids, and classify the grids that can perform pulse discharge tests under laboratory conditions into the first group, and the remaining grids into the second group; Step S402) For the grids in the first group, in turn, under laboratory conditions, perform pulse discharge tests within the grid range; Step S403) Obtain the sound data collected by multiple ultrasonic acquisition devices coupled to the transformer housing 21 according to the marked points and align them along the time axis; Step S404) Identify the time corresponding to the discharge pulse in the sound data corresponding to the specified marked point. Based on this time reference, obtain the sound propagation delay generated by the discharge pulse of the remaining ultrasonic acquisition devices; Step S405) Establish a delay vector corresponding to this grid according to the sound propagation delays corresponding to all ultrasonic acquisition devices; Step S406) Traverse the grids in the second group, and find the grids in the first group that are closest to this grid on the ultrasonic propagation path from this grid to each marked point, and record them as reference grids; Step S407) Calculate the sound propagation duration between the grid and each reference grid. According to the sound propagation duration and the duration from the reference grid to the ultrasonic acquisition device at the corresponding marked point during the pulse discharge test, obtain the duration from this grid to the ultrasonic acquisition device at each marked point; Step S408) Obtain the delay vector corresponding to this grid according to the duration from this grid to the ultrasonic acquisition device at each marked point; Step S409) Obtain the delay positioning reference table according to the delay vectors of all grids.

[0059] Through the delay positioning reference table, the inspection UAV 11 can quickly obtain the preliminary position of the partial discharge by looking up the table, avoiding a large amount of calculations. The accuracy of obtaining the preliminary position of the partial discharge is determined by the process of obtaining the delay positioning reference table. The preliminary position of the partial discharge is generally sufficient to assist in determining the structure where the partial discharge fault occurs.

[0060] A method for obtaining the position recognition result of the partial discharge according to the delay vector and the delay positioning reference table pre-stored in the inspection UAV 11 includes: Calculate the similarity between the delay vector and each delay vector in the delay positioning reference table respectively; The grid corresponding to the delay vector with the highest similarity is used as the position recognition result of the partial discharge.

[0061] On the other hand, this specification provides a prediction system for partial discharge faults in a distribution network. Please refer to the appendix Figure 8 , including: A mutual inductance prediction module 100. At the neutral line of the substation transformer in the distribution network and on the main lines and branch lines in the distribution network, radio frequency current transformers are set to collect mutual inductance current data. The radio frequency current transformers have wireless communication modules, and the wireless communication modules establish communication connections with preset servers; The ultrasonic prediction module 200 installs a bracket 12 on the inspection UAV 11, installs an ultrasonic acquisition device on the bracket 12, the ultrasonic acquisition device establishes a communication connection with the inspection UAV 11, and the inspection UAV 11 establishes a communication connection with the server; The first acquisition module 300 controls the inspection UAV 11 to sequentially collect sound data from the marked positions of the medium-voltage transformer housings 21 in the distribution network along a preset first inspection path; The electromagnetic wave prediction module 400, after the inspection UAV 11 returns, installs an electromagnetic wave acquisition device on the bracket 12 of the inspection UAV 11, and the electromagnetic wave acquisition device establishes a communication connection with the inspection UAV 11; The second acquisition module 500 controls the inspection UAV 11 to fly over the electrical cabinets 30 in the distribution network along a preset second inspection path to collect electromagnetic radiation data; The fault prediction module 600, the server receives and obtains a prediction result of a partial discharge fault based on the mutual inductance current data, sound data, and electromagnetic radiation data.

[0062] Please refer to Figure 9 the schematic structural diagram of an electronic device provided by the embodiment of the present specification shown.

[0063] As Figure 9 shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. Among them, the communication bus 1102 can be used to realize the connection and communication of the above-mentioned various components. Among them, the user interface 1103 may include buttons, and an optional user interface may further include a standard wired interface and a wireless interface. Among them, the network interface 1104 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc. Among them, the processor 1101 may include one or more processing cores. The processor 1101 connects various parts within the entire electronic device 1100 through various interfaces and lines, and by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1105, and by calling the data stored in the memory 1105, it executes various functions of the routing device 1100 and processes data. Optionally, the processor 1101 may be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor 1101 may integrate a combination of one or several of a CPU, a GPU, and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication.

[0064] It can be understood that the above-mentioned modem may not be integrated into the processor 1101 and can be implemented separately by a single chip.

[0065] Among them, the memory 1105 may include RAM or ROM. Optionally, the memory 1105 includes a non-transitory computer-readable medium. The memory 1105 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1105 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store the data involved in the above-mentioned various method embodiments. Optionally, the memory 1105 may also be at least one storage device located far from the aforementioned processor 1101. As a computer storage medium, the memory 1105 may include an operating system, a network communication module, a user interface module, and application programs. The processor 1101 can be used to call the application programs stored in the memory 1105 and execute the methods in the above-mentioned multiple embodiments.

[0066] The embodiments of this specification also provide a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer or a processor, the computer or the processor is caused to execute multiple steps in the above-mentioned embodiments. If the various component modules of the above-mentioned electronic device are implemented in the form of software function units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0067] The embodiments of this specification also provide a computer program product, including a computer program. When the computer program is executed by a processor, multiple steps in the above-mentioned embodiments are implemented.

[0068] Without conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0069] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes a plurality of computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this specification are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes a plurality of available media integrated. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a Digital Versatile Disc (DVD)), or a semiconductor medium (for example, a Solid State Disk (SSD)), etc.

[0070] When implemented by hardware or firmware, the foregoing method process is programmed into a hardware circuit to obtain a corresponding hardware circuit structure and implement the corresponding function. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit, and its logical function is determined by the user programming the device. A designer can program a digital system "integrated" on a PLD by himself / herself without asking a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL), and there are not only one but many kinds of HDLs. Those skilled in the art should also be clear that only by slightly logically programming the method process with the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain a hardware circuit that implements the logical method process.

[0071] The embodiments described above are merely described in the preferred embodiment mode of this specification, and do not limit the scope of this specification. Without departing from the design spirit of this specification, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of this specification shall fall within the protection scope determined by the claims of this specification.

Claims

1. A method for predicting partial discharge faults in a distribution network, characterized in that: Includes steps: A radio frequency current transformer is arranged at the neutral line of the transformer in the distribution network and the trunk line and branch line in the distribution network to collect mutual inductance current data, wherein the radio frequency current transformer has a wireless communication module, and the wireless communication module establishes a communication connection with a preset server; A bracket is installed on the inspection drone, an ultrasonic acquisition device is installed on the bracket, the ultrasonic acquisition device establishes a communication connection with the inspection drone, and the inspection drone establishes a communication connection with the server; Control the inspection drone to collect sound data from marked locations of transformer casings in the distribution network one by one along a preset first inspection path; After the inspection drone returns, an electromagnetic wave collection device is installed on the bracket of the inspection drone, and the electromagnetic wave collection device establishes a communication connection with the inspection drone; Controlling the inspection drone to fly over the electrical cabinets in the distribution network along a preset second inspection path to collect electromagnetic radiation data; The server receives and obtains a prediction result of a partial discharge fault according to the mutual inductance current data, the sound data and the electromagnetic radiation data.

2. A method for predicting partial discharge faults in a distribution network according to claim 1, characterized in that: The method for presetting the first inspection path includes: Mark the first marking point on the shell of each transformer in each substation; Obtaining the coordinates of all transformers in the distribution network and the coordinates of the first marking point; Generate an approach path according to the coordinates of all the first marking points, wherein the length of the approach path is a preset length and the direction is perpendicular to the transformer housing of the substation; A first inspection path is generated according to the free ends of all the approach paths.

3. A method for predicting partial discharge faults in a distribution network according to claim 2, characterized in that: The marking location includes a first marking point and a plurality of geometric marking points. The method of collecting sound data from the markings on the transformer casing in the distribution network includes: Controlling the inspection drone to couple the ultrasonic acquisition device with the transformer housing of the substation along the approach path; After waiting for a preset time, the ultrasonic collection device is removed to obtain the sound data collected by the ultrasonic collection device.

4. A method for predicting partial discharge faults in a distribution network according to claim 1, characterized in that: The method for presetting the second inspection path includes: Obtain the positions of all electrical cabinets in the distribution network, set a flyover point for each electrical cabinet, and obtain the coordinates of the flyover point; A second inspection path is generated according to the coordinates of all the flying points.

5. The method for predicting partial discharge faults in a distribution network according to claim 1, characterized in that: The method for obtaining the prediction result of partial discharge fault according to the mutual inductance current data, sound data and electromagnetic radiation data includes: Using a preset feature extraction model, extracting features of the mutual inductance current data; Comparing the features with pre-stored reference features, if the comparison is consistent, it is determined that there is no partial discharge in the corresponding neutral line, trunk line or branch line, and if the comparison is inconsistent, it is determined that there is partial discharge in the corresponding neutral line, trunk line or branch line; Extracting features of the sound data and comparing them with reference sound features stored in the inspection drone, and determining that there is no partial discharge if the comparison matches; When the comparison does not match, the inspection drone is controlled to carry multiple ultrasonic acquisition devices one by one from the designated position and couple to multiple geometric marking points pre-marked on the target transformer housing; After waiting for a preset time, the plurality of ultrasonic collection devices are removed one by one, and the sound data collected by the plurality of ultrasonic collection devices are obtained; Obtaining a local discharge position prediction result according to the plurality of sound data; Extracting frequency domain features of the electromagnetic radiation data to obtain frequency components; The frequency composition is compared with a preset reference frequency composition. When the comparison is consistent, it is determined that there is no partial discharge in the corresponding electrical cabinet. When the comparison is inconsistent, it is determined that there is partial discharge in the corresponding electrical cabinet.

6. A method for predicting partial discharge faults in a distribution network according to claim 5, characterized in that: Methods for presetting feature extraction models include: Reading a plurality of mutual inductance current data as sample data; Establishing an autoencoding model, and using the sample data to train the autoencoding model; According to the first half of the autoencoder model, a feature extraction model is obtained.

7. A method for predicting partial discharge faults in a distribution network according to claim 5, characterized in that: The reference sound features stored in the inspection drone include the frequency composition and amplitude proportion of the sound data collected at the same predetermined positions corresponding to a plurality of transformer load intervals, The method of extracting the features of the sound data and comparing them with the reference sound features stored in the inspection drone includes: Selecting the frequency components of the sound data within a preset frequency range, constructing a vector of the selected frequency components and their amplitude proportions, recorded as a first vector; According to the frequency components included in the first vector, select corresponding frequency components and their amplitude proportions from the frequency components of the sound data corresponding to each transformer load interval to obtain multiple second vectors; The similarity between the first vector and each of the second vectors is calculated respectively. When there is a similarity value higher than a preset reference similarity threshold, the comparison is determined to be matched; when there is no similarity value higher than the preset reference similarity threshold, the comparison is determined to be mismatched.

8. A method for predicting partial discharge faults in a distribution network according to claim 5, characterized in that: The method for obtaining a local discharge position prediction result according to a plurality of the sound data comprises: After aligning the plurality of sound data according to the time axis, selecting the sound data corresponding to the designated marked point to calibrate a discharge pulse, and obtaining the sound propagation delay generated by the discharge pulse at the remaining calibrated points according to the remaining sound data, and obtaining the delay vector; According to the delay vector and the delay positioning reference table pre-stored in the inspection drone, the position recognition result of the partial discharge is obtained. The delay positioning reference table is an association table of the position recognition results of the same model and the same marked points obtained under laboratory conditions and the delay vector.

9. A method for predicting partial discharge faults in a distribution network according to claim 8, characterized in that: The method of obtaining the delayed positioning reference table includes: The internal space of the selected transformer is divided into a plurality of grids, the grids capable of pulse discharge test under laboratory conditions are classified into the first group, and the remaining grids are classified into the second group; For the grids in the first group, pulse discharge tests are carried out in the grid range under laboratory conditions in turn; Acquire sound data collected by a plurality of ultrasonic collection devices coupled to the transformer housing according to the marked points and align them according to the time axis; Identify the time corresponding to the discharge pulse in the sound data corresponding to the designated mark point, and obtain the sound propagation delay generated by the discharge pulse of other ultrasonic acquisition devices based on the time reference; According to the sound propagation delays corresponding to all ultrasonic acquisition devices, a delay vector corresponding to the grid is established; Traversing the grids in the second group, finding the grid in the first group closest to the grid on the ultrasonic wave propagation path from the grid to each marked point, and recording it as a reference grid; Calculate the sound propagation time of the grid and each reference grid, and obtain the time for the grid to reach the ultrasonic collection device at each marked point according to the sound propagation time and the time for the reference grid to reach the ultrasonic collection device at the corresponding marked point during the pulse discharge test; According to the time length for the grid to reach the ultrasonic collection device at each marked point, a delay vector corresponding to the grid is obtained; The delay positioning reference table is obtained according to the delay vectors of all grids.

10. A method for predicting partial discharge faults in a distribution network according to claim 8, characterized in that: The method for obtaining the position identification result of the partial discharge according to the delay vector and the delay positioning reference table pre-stored by the inspection drone includes: respectively calculating the similarity between the delay vector and each delay vector in the delay positioning reference table; The grid corresponding to the delay vector with the highest similarity is used as the position recognition result of the partial discharge.

11. A prediction system for partial discharge faults in a distribution network, characterized in that: include: A mutual inductance prediction module is provided at the neutral line of the transformer in the distribution network and the trunk and branch lines in the distribution network to collect mutual inductance current data. The radio frequency current transformer has a wireless communication module, and the wireless communication module establishes a communication connection with a preset server; Ultrasonic prediction module, a bracket is installed on the inspection drone, an ultrasonic acquisition device is installed on the bracket, the ultrasonic acquisition device establishes a communication connection with the inspection drone, and the inspection drone establishes a communication connection with the server; A first collection module controls the inspection drone to collect sound data from the marked positions of the transformer casings in the distribution network one by one along a preset first inspection path; An electromagnetic wave prediction module, after the inspection drone returns, an electromagnetic wave collection device is installed on the bracket of the inspection drone, and the electromagnetic wave collection device establishes a communication connection with the inspection drone; A second collection module controls the inspection drone to fly over the electrical cabinets in the distribution network along a preset second inspection path to collect electromagnetic radiation data; The fault prediction module is configured so that the server receives and obtains a prediction result of a partial discharge fault according to the mutual inductance current data, the sound data and the electromagnetic radiation data.

12. An electronic device, characterized in that: including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images