A method and system for detecting faults in power distribution lines based on unmanned aerial vehicle (UAV) inspection

Abstract

This invention provides a method and system for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection, belonging to the field of power grid fault detection and identification technology. The method includes: determining a target line based on line anomaly information and obtaining the path information of the target line; dispatching a UAV to inspect along the target line direction, obtaining magnetic field measurements, UAV position data, and the distance between the UAV and the target line, thus obtaining a magnetic field sampling sequence; constructing a magnetic field distribution map along the target line based on the preprocessed magnetic field sampling sequence; determining suspected anomaly locations, fault types, and fault location information based on the magnetic field distribution map, and outputting the magnetic field distribution map, fault type, and fault location information to a display terminal for display. This method enables rapid inspection of abnormal distribution network lines, achieving identification of suspected anomaly locations, fault type discrimination, fault location information determination, and visual display, thereby improving the efficiency of distribution network line fault inspection and maintenance.

Description

Technical Field

[0001] This invention belongs to the field of power grid fault detection and identification technology, and in particular relates to a method and system for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection. Background Technology

[0002] A distribution network refers to a power grid that receives electrical energy from the transmission network or regional power plants and distributes it locally or in stages according to voltage to various users through distribution facilities. It consists of overhead lines, cables, poles, distribution transformers, disconnect switches, reactive power compensators, and some auxiliary facilities, and plays an important role in distributing electrical energy within the power grid.

[0003] Distribution networks are characterized by multiple voltage levels, complex network structures, diverse equipment types, numerous and widespread work sites, and relatively poor safety environments, resulting in a relatively large number of safety risk factors. Furthermore, since the function of distribution networks is to provide electrical energy to various users, higher requirements are placed on their safe and reliable operation.

[0004] Currently, for power distribution lines in the field, due to different terrains and complex mountainous and riverine areas, not only is it difficult to erect power distribution lines, but it is also very difficult to maintain and repair them later. When a power distribution line in a certain area is damaged or abnormal, or a node is short-circuited or open-circuited, the abnormal area can only be roughly understood based on the back-end operation data. In particular, when a line spans a large distance, even several kilometers or hundreds of kilometers, in a complex environment, even if it is known that the line is abnormal, it is difficult for maintenance personnel to pinpoint the specific maintenance points under such conditions, and it is impossible to determine the cause of the damage or abnormality, which brings great difficulties to maintenance and repair. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection. This system can quickly inspect abnormal distribution network lines, accurately obtain magnetic field information distributed along the target line, and realize the identification of suspected abnormal locations, fault type discrimination, fault location information determination and visualization display, thereby improving the efficiency of fault inspection and maintenance of distribution network lines.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for detecting faults in power distribution lines based on unmanned aerial vehicle (UAV) inspection, comprising: Obtain line anomaly information, determine the target line based on the line anomaly information, and obtain the path information of the target line; The drone is dispatched to patrol along the target route and collect data at intervals during the patrol process to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route at each collection time, and to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route uploaded by the drone. Based on the path information of the target route, the location data of the UAV, and the distance information between the UAV and the target route, the location of the target route at each collection time is determined, and the magnetic field measurement values ​​at each collection time are arranged in the order of the target route locations to obtain the magnetic field sampling sequence. The magnetic field sampling sequence is preprocessed, and a magnetic field distribution map along the target line is constructed based on the preprocessed magnetic field sampling sequence. Based on the magnetic field distribution map, the suspected abnormal location, fault type, and fault location information are determined, and the magnetic field distribution map, fault type, and fault location information are output to the display terminal for display, so as to facilitate fault diagnosis.

[0007] Furthermore, the step of determining the target route based on the route anomaly information and obtaining the path information of the target route includes: Based on the distribution network operation monitoring results, switch status information, protection action information, line voltage and current monitoring information, feeder automation system alarm information, or manual repair information, determine the abnormal line sections; Within the abnormal line section, a starting end node and an ending end node are determined. The end node can be any one of a power equipment node, a pole / tower node, a transformer node, a switch node, or a line connection node. The target route is determined based on the starting and ending nodes. The path information of the target route is retrieved from the route map database. The path information includes at least one of the following: route direction information, pole and tower location information, broken line node information, route segmentation information, end node coordinate information, and surrounding geographical environment information.

[0008] Furthermore, the step of dispatching the drone to inspect along the target route includes: The inspection route is planned based on the path information of the target route, and the drone is controlled to fly to the vicinity of the starting node of the target route. Control the drone to fly along the inspection route from the starting node to the ending node of the target route, and collect data at intervals during the flight.

[0009] Furthermore, the step of performing interval data collection during the inspection process to obtain the magnetic field measurement values, UAV location data, and distance information between the UAV and the target route at each collection time includes: During flight, the drone samples at a fixed sampling frequency or at fixed flight distance intervals to form sampling records at each sampling moment; Each sampling record includes: the time of collection, the magnetic field measurement value, the current location data of the UAV, and the distance information between the UAV and the target route; The magnetic field measurement value is a uniaxial magnetic field component value, a biaxial magnetic field component value, a triaxial magnetic field component value, or a fused magnetic field strength value.

[0010] Furthermore, the step of determining the target line location corresponding to each acquisition time includes: Based on the path information of the target route, the UAV position data corresponding to each collection time is projected onto the target route path to obtain the corresponding route projection position; Based on the relative position of the projected position of the line between the starting node and the ending node of the target line, the target line position at the time of acquisition is determined, and the corresponding position is any one of the cumulative distance value along the line, the position of the line segment, or the proportional position value within the segment.

[0011] Furthermore, the step of preprocessing the magnetic field sampling sequence and constructing a magnetic field distribution map along the target line based on the preprocessed magnetic field sampling sequence includes: The magnetic field sampling sequence is subjected to at least two of the following: outlier removal, noise filtering, data smoothing, distance compensation, and normalization. Based on the distance information between the UAV and the target route, distance compensation processing is performed on the magnetic field measurement values ​​in the magnetic field sampling sequence; Based on the target route location and magnetic field measurement values ​​corresponding to each acquisition time, a magnetic field distribution map along the target route is constructed. The magnetic field distribution map can be a line graph, a color bar graph, a segment coloring graph, or a point sequence graph. In the magnetic field distribution map, the magnetic field measurement values ​​corresponding to each acquisition time are displayed according to the corresponding target route location, or several adjacent acquisition times are aggregated into a line analysis segment, and the average value, median value, maximum value, or weighted statistical value of the magnetic field measurement values ​​in the line analysis segment are used as the magnetic field characterization value.

[0012] Furthermore, the step of determining the suspected anomaly location, fault type, and fault location information based on the magnetic field distribution map includes: Based on at least one of the following: the difference in magnetic field measurement values ​​between adjacent acquisition times, the difference in magnetic field measurement values ​​between adjacent sections along the line, the rate of change of magnetic field measurement values ​​along the line direction, the extreme value characteristics within a local window, and the sudden increase or decrease characteristics of magnetic field measurement values ​​within a continuously acquired section, the suspected abnormal location is determined. In the magnetic field distribution diagram, when there is a difference in the magnetic field distribution before and after the abnormal location, it is determined to be an open circuit fault; when there is a magnetic field distribution before and after the abnormal location, and the local magnetic field distribution shows abnormal enhancement, abnormal distortion, or abnormal fluctuation, it is determined to be a short circuit fault or an external discharge fault; when the overall magnetic field distribution of the target line is lower than the preset distribution characteristics, it is determined to be an abnormal fault at the terminal node. Based on the cumulative distance along the line or the location of the line segment corresponding to the suspected abnormal location, determine which two nodes the fault is located between and the distance from one of the nodes.

[0013] In a second aspect, the present invention provides a power distribution line fault detection system based on unmanned aerial vehicle (UAV) inspection, comprising: a server, a UAV, and a display terminal, wherein the server comprises: The route determination module is used to acquire route anomaly information, determine the target route based on the route anomaly information, and acquire the path information of the target route; The inspection and scheduling module is used to schedule the drone to inspect along the target route and to collect data at intervals during the inspection process to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route at each collection time, and to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route uploaded by the drone. The location determination module is used to determine the location of the target line at each collection time based on the path information of the target line, the location data of the UAV, and the distance information between the UAV and the target line, and to arrange the magnetic field measurement values ​​at each collection time in the order of the target line locations to obtain the magnetic field sampling sequence. The mapping module is used to preprocess the magnetic field sampling sequence and construct a magnetic field distribution map along the target line based on the preprocessed magnetic field sampling sequence. The output module is used to determine the suspected abnormal location, fault type and fault location information based on the magnetic field distribution map, and output the magnetic field distribution map, fault type and fault location information to the display terminal for display, so as to facilitate fault diagnosis.

[0014] In a third aspect, the present invention provides an electronic device including a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement a method for detecting faults in power distribution lines based on unmanned aerial vehicle (UAV) inspection.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium storing at least one instruction, which, when executed by a processor, implements a method for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention first determines the target route based on route anomaly information and obtains the path information of the target route. Then, it dispatches a drone to inspect along the direction of the target route. During the inspection, it obtains the magnetic field measurement values, drone position data, and distance information between the drone and the target route at each collection time. Furthermore, it determines the target route position at each collection time, forms a magnetic field sampling sequence, and constructs a magnetic field distribution map along the target route. Finally, it realizes the identification of suspected abnormal locations, the determination of fault types, and the output of fault location information. This transforms the originally scattered aerial inspection measurement results into an orderly magnetic field distribution result along the target route, which not only improves the pertinence and efficiency of fault troubleshooting, but also enhances the intuitiveness and accuracy of fault identification and location.

[0017] 2. By identifying abnormal line sections based on distribution network operation monitoring results, switch status information, protection action information, line voltage and current monitoring information, feeder automation system alarm information, or manual repair reports, and further determining the starting and ending nodes and target line path information, combined with inspection route planning and interval data collection along the target line direction, the UAV inspection process can be carried out around a clearly defined target line, avoiding large-scale blind inspections and narrowing the scope of fault diagnosis. At the same time, by forming sampling records through fixed sampling frequency or fixed flight distance intervals, it is possible to ensure a stable correspondence between the magnetic field measurement values, UAV position data, and distance information between the UAV and the target line at each collection moment, thereby providing a reliable data foundation for subsequent target line location determination and magnetic field sampling sequence construction.

[0018] 3. By projecting the UAV position data corresponding to each acquisition time onto the target route path, and determining the target route position corresponding to each acquisition time based on the relative position of the route projection position between the starting and ending nodes of the target route, the measurement results on the flight trajectory can be accurately mapped to data sequentially unfolded along the target route. Furthermore, by preprocessing the magnetic field sampling sequence with outlier removal, noise filtering, data smoothing, distance compensation, and normalization, and constructing magnetic field distribution maps in the form of line charts, color bar charts, segment coloring maps, or point sequence charts, the impact of measurement distance variations, environmental noise, and flight state fluctuations on magnetic field measurement values ​​can be effectively reduced, improving the comparability and stability of the magnetic field distribution analysis along the route. Based on this, the suspected abnormal locations and fault types are determined based on the differences in magnetic field measurement values ​​between adjacent acquisition times, the differences in magnetic field measurement values ​​between adjacent segments along the route, the rate of change of magnetic field measurement values ​​along the route direction, local window extreme value characteristics, and sudden rises or falls within continuous acquisition segments. Combined with the cumulative distance value along the route or the location of the route segment, fault location information is output, thereby improving the accuracy of fault identification and location. Attached Figure Description

[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart illustrating the method for detecting faults in power distribution lines based on unmanned aerial vehicle (UAV) inspection, according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the color stripe distribution of the magnetic field along the target line in an embodiment of the present invention; Figure 3 This is a schematic diagram of a power distribution line fault detection system based on unmanned aerial vehicle (UAV) inspection, according to an embodiment of the present invention. Figure 4 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0020] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0021] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0022] This embodiment provides a method for detecting faults in distribution network lines based on drone inspection. It is suitable for rapid inspection, fault identification, and fault location of overhead lines and terminal branches in distribution networks. This method can be implemented collaboratively by a power grid backend, a line map database, a drone flight platform, an airborne magnetic field measurement device, and a display terminal. It is particularly suitable for rapid fault diagnosis in distribution network lines in areas where manual inspection is difficult, such as mountainous areas, valleys, forests, and road intersections.

[0023] In this embodiment, the target line can be a single-circuit line or a multi-circuit line deployed in parallel; the fault types can include open-circuit faults, short-circuit faults, external discharge faults, and terminal node abnormal faults. The UAV can be a multi-rotor UAV, a fixed-wing UAV, or a compound-wing UAV, with a multi-rotor UAV preferred for stable low-altitude line-side inspection. The airborne magnetic field measuring device is used to measure the power frequency magnetic field around the target line to obtain the magnetic field measurement values ​​required for subsequent fault analysis.

[0024] like Figure 1 As shown, the method for detecting faults in distribution network lines based on UAV inspection provided by the present invention includes the following steps S1 to S5.

[0025] In step S1, line anomaly information is obtained, a target line is determined based on the line anomaly information, and the path information of the target line is obtained.

[0026] Specifically, based on the distribution network operation monitoring results, switch status information, protection action information, line voltage and current monitoring information, feeder automation system alarm information, or manual repair information, abnormal line sections can be identified, thereby initially narrowing down the scope of abnormal lines.

[0027] Furthermore, within the abnormal line section, a starting node and an ending node are determined. These ending nodes can be any of the following: power equipment nodes, pole / tower nodes, transformer nodes, switch nodes, or line connection nodes. After determining the target line based on the starting and ending nodes, the path information of the target line is retrieved from the line map database. This path information includes at least one of the following: line orientation information, pole / tower location information, polyline node information, line segmentation information, ending node coordinates, and surrounding geographical environment information. Through this process, subsequent UAV inspections and data processing can be clearly focused on the target line, avoiding large-scale blind investigations and thus improving fault diagnosis efficiency.

[0028] In step S2, the drone is scheduled to patrol along the target route and collect data at intervals during the patrol process to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route at each collection time, and to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route uploaded by the drone.

[0029] Specifically, an inspection route can be planned based on the path information of the target route, and the UAV can be controlled to fly to the vicinity of the starting node of the target route, and then the UAV can be controlled to fly along the inspection route to the ending node, and interval data collection can be performed during the flight. The interval data collection can be achieved by a fixed sampling frequency or a fixed flight distance interval, so as to form a sampling record at each data collection moment. Each sampling record includes data collection moment information, magnetic field measurement value, current position data of the UAV, and distance information between the UAV and the target route. The magnetic field measurement value can be a single-axis magnetic field component value, a two-axis magnetic field component value, a three-axis magnetic field component value, or a fused magnetic field strength value.

[0030] In one implementation, the comprehensive magnetic field strength value can be obtained by calculating the magnitude of the three-axis magnetic field components, and used as the magnetic field measurement value for subsequent analysis. The current position data of the UAV can be provided by one or more of a satellite positioning module, inertial navigation module, visual positioning module, or laser ranging module; the distance information between the UAV and the target route can be calculated based on the spatial positional relationship between the UAV and the target route, or it can be measured in real time by an airborne ranging device, or read from the inspection route parameters. To improve the comparability of data at different collection times, it is preferable to keep the distance between the UAV and the target route within a preset range as much as possible while the UAV flies along the target route; in scenarios where this distance cannot be strictly maintained, the recorded distance information between the UAV and the target route can be used as the basis for subsequent distance compensation processing.

[0031] The magnetic field measurements, the UAV location data, and the distance information between the UAV and the target route can be uploaded in real time, or they can be cached locally on the UAV and uploaded all at once after a single inspection is completed. This method allows for the simultaneous acquisition of magnetic field, location, and distance information at the same time point during the inspection process, providing a data foundation for subsequently determining the target route location and constructing a magnetic field sampling sequence.

[0032] In step S3, the target route position is determined according to the path information of the target route, the UAV position data, and the distance information between the UAV and the target route. The magnetic field measurement values ​​corresponding to each collection time are arranged in the order of the target route positions to obtain the magnetic field sampling sequence.

[0033] Specifically, based on the path information of the target route, the UAV position data corresponding to each collection time can be projected onto the target route path to obtain the corresponding route projection position. Then, based on the relative position of the route projection position between the starting node and the ending node of the target route, the target route position corresponding to that collection time can be determined. The corresponding position can be any one of the cumulative distance value along the route, the route segment position, or the proportional position value within the segment. For scenarios where the target route is a polyline path composed of several polyline nodes, the positional relationship between the route projection position and each polyline segment of the target route can be used to associate the UAV position data corresponding to each collection time with the specific route segment on the target route, thereby determining the target route position corresponding to each collection time.

[0034] Through the above processing, the magnetic field measurements originally scattered along the UAV flight path can be converted into a magnetic field sampling sequence arranged in order of the target route position. This transforms the measurement results on the flight path into measurement results distributed along the target route, facilitating subsequent preprocessing and magnetic field distribution map construction.

[0035] In step S4, the magnetic field sampling sequence is preprocessed, and a magnetic field distribution map along the target route is constructed based on the preprocessed magnetic field sampling sequence. Specifically, at least two of the following can be performed on the magnetic field sampling sequence: outlier removal, noise filtering, data smoothing, distance compensation, and normalization. The outlier removal can be used to eliminate discrete outliers caused by sudden turns, sudden shaking, instantaneous obstruction, measurement jumps, or communication errors of the UAV; the noise filtering can be used to reduce environmental background magnetic field fluctuations, sensor noise, and flight vibration interference; and the data smoothing can be used to improve the continuity of the magnetic field sampling sequence, making subsequent suspected anomaly locations clearer.

[0036] Furthermore, based on the distance information between the UAV and the target route, distance compensation processing can be performed on the magnetic field measurement values ​​in the magnetic field sampling sequence to unify the magnetic field measurement values ​​obtained at different measurement distances to the same reference conditions, thereby reducing the impact of measurement distance changes on the magnetic field measurement values ​​and improving the comparability of magnetic field measurement values ​​between different acquisition times.

[0037] Specifically, the actual measurement distance at each acquisition time can be determined first based on the distance information between the UAV and the target route at each acquisition time. Then, a preset reference distance is selected as a unified reference condition, and a distance compensation relationship between the magnetic field measurement value and the measurement distance is established in advance. The distance compensation relationship can be implemented using any of the following: a distance compensation relationship table, a distance compensation function model, or a distance compensation model constructed based on historical calibration data.

[0038] When performing distance compensation, the magnetic field measurement value acquired at each acquisition time can be converted into a compensated magnetic field measurement value corresponding to the preset reference distance, based on the actual measurement distance at each acquisition time and according to the aforementioned distance compensation relationship. For cases where the actual measurement distance does not directly fall on the preset calibration point, interpolation or approximate matching methods can be used to determine the corresponding compensation result. Through the above processing, the magnetic field measurement values, which originally fluctuated due to changes in the distance between the UAV and the target route, can be compared under unified reference conditions, thereby improving the accuracy of magnetic field distribution analysis along the target route.

[0039] For example, when a drone deviates from the preset inspection distance at a certain sampling moment due to terrain undulations, obstacle avoidance, or flight attitude adjustment, the magnetic field measurement value obtained at that sampling moment will have a deviation relative to other sampling moments caused by the change in measurement distance. Through the distance compensation processing, the magnetic field measurement value at that sampling moment can be corrected to an equivalent measurement value under the same reference distance conditions as other sampling moments, thereby avoiding misjudging the amplitude fluctuation caused by distance changes as abnormal magnetic field changes of the target line itself.

[0040] After preprocessing, a magnetic field distribution map along the target line is constructed based on the target line location and magnetic field measurement values ​​corresponding to each acquisition time. This magnetic field distribution map can be a line graph, color bar graph, segmented coloring graph, or point sequence graph. In the magnetic field distribution map, the magnetic field measurement values ​​corresponding to each acquisition time can be displayed according to the corresponding target line location; alternatively, several adjacent acquisition times can be aggregated into a single analysis segment along the line, and the average, median, maximum, or weighted statistical value of the magnetic field measurement values ​​within that analysis segment can be used as the magnetic field characterization value. Using a segmented display method can reduce the impact of single-point noise on the results and improve the identifiability of abnormal segments along the line. Through the above processing, a magnetic field distribution map corresponding to the actual spatial location of the target line can be obtained, providing an intuitive and continuous data foundation for subsequent fault identification and fault location.

[0041] In a preferred embodiment, the magnetic field distribution map obtained in step S4 above can be displayed as a color bar chart of the magnetic field distribution unfolded along the target line, such as... Figure 2 As shown. Figure 2 The color bars in the image represent the magnetic field distribution map generated based on the target line location at each acquisition time and the preprocessed magnetic field measurements. This magnetic field distribution map is also the data output to the display terminal in step S5. Specifically, in... Figure 2In this method, the target line is unfolded from the starting node to the ending node, and the distance along the line is used as the positional order. The magnetic field measurement values ​​corresponding to each acquisition time are displayed sequentially in color bars according to the corresponding target line position. Darker colors indicate larger magnetic field values ​​at the corresponding positions, while lighter colors indicate smaller magnetic field values. Based on this magnetic field distribution map, the continuous changes in the magnetic field distribution along the target line can be visually identified. When a local section shows a sudden color change, darkens in color, or has a significant difference from the preceding and following sections, that local section can be identified as a suspected anomaly. Further, the fault type can be determined by combining the magnetic field distribution characteristics before and after the anomaly position. At the same time, by combining the cumulative distance value along the line or the line section position corresponding to the suspected anomaly position, it can be determined which two nodes the fault is located between and the distance from one of the nodes.

[0042] In step S5, the suspected abnormal location, fault type, and fault location information are determined based on the magnetic field distribution map, and the magnetic field distribution map, fault type, and fault location information are output to the display terminal for display to facilitate fault diagnosis. Specifically, the suspected abnormal location can be determined based on at least one of the following: the difference in magnetic field measurement values ​​between adjacent acquisition times, the difference in magnetic field measurement values ​​between adjacent sections along the line, the rate of change of magnetic field measurement values ​​along the line direction, extreme value characteristics within a local window, and sudden increases or decreases in magnetic field measurement values ​​within a continuously acquired section. In the magnetic field distribution map, when there is a difference in the magnetic field distribution before and after the abnormal location, it is determined to be an open circuit fault; when there is a magnetic field distribution before and after the abnormal location, and the local magnetic field distribution shows abnormal enhancement, abnormal distortion, or abnormal fluctuation, it is determined to be a short circuit fault or an external discharge fault; when the overall magnetic field distribution of the target line is lower than the preset distribution characteristics, it is determined to be an abnormal fault at the end node, wherein the preset distribution characteristics are reference distribution characteristics pre-set based on historical inspection results or magnetic field distribution under normal operating conditions. Furthermore, based on the cumulative distance along the line or the location of the line segment corresponding to the suspected abnormal location, it can be determined which two nodes the fault is located between and the distance from one of the nodes.

[0043] Finally, the magnetic field distribution map, fault type, and fault location information are output to a display terminal for on-site fault diagnosis. This method not only creates a visual representation of the magnetic field status along the target line but also allows for rapid identification of fault types and locations based on differences in the magnetic field distribution map and local anomalies, thus providing a basis for maintenance personnel to quickly reach the site.

[0044] To facilitate understanding, the following explanation uses an overhead distribution line as an example. Assume the power grid backend identifies an abnormal line section based on feeder automation monitoring results, and within this abnormal section, determines the starting and ending nodes. Then, based on these starting and ending nodes, it determines the target line. Subsequently, the power grid backend retrieves the path information of the target line from the line map database and plans an inspection route based on this information. It then controls a drone to fly to the vicinity of the starting node of the target line and then flies along the inspection route to the ending node. During the flight, the drone samples at fixed flight distance intervals, forming multiple sampling records. Each sampling record includes the magnetic field measurement value at the corresponding sampling time, the drone's position data, and the distance information between the drone and the target line.

[0045] After receiving the data from the drone at each collection time, the backend projects the drone's position data at each collection time onto the target route path based on the target route's path information, obtaining the corresponding route projection position. Based on the relative position of the route projection position between the starting and ending nodes of the target route, the target route position at each collection time is determined. Then, the magnetic field measurement values ​​at each collection time are arranged in order of the target route positions to obtain a magnetic field sampling sequence. Subsequently, outlier removal, data smoothing, and distance compensation are performed on the magnetic field sampling sequence, and a color-coded bar chart of the magnetic field distribution is constructed based on the compensated magnetic field measurement values.

[0046] If there is a significant difference in the magnetic field distribution before and after a certain line segment in the magnetic field distribution map, that location can be identified as a suspected anomaly. If there is a magnetic field distribution before and after the suspected anomaly location, and there are local abnormal enhancements, abnormal distortions, or abnormal fluctuations, the corresponding fault type can be identified as a short-circuit fault or an external discharge fault. If the overall magnetic field distribution of the target line is lower than the preset distribution characteristics, the corresponding fault type can be identified as an end node anomaly fault. The preset distribution characteristics are reference distribution characteristics pre-set based on historical inspection results or the magnetic field distribution under normal operating conditions. Finally, based on the cumulative distance value along the line or the location of the line segment corresponding to the suspected anomaly location, the two nodes between which the fault is located and the distance from one of the nodes are determined. The magnetic field distribution map, fault type, and fault location information are then pushed to the display terminal to assist in on-site fault diagnosis.

[0047] In one extended implementation, when the target line is long or multiple abnormal line sections need to be inspected simultaneously, multiple drones can perform inspection tasks on different abnormal line sections. Each drone collects data at intervals according to its corresponding inspection route and uploads the collected magnetic field measurements, drone position data, and distance information between the drone and the target line to the power grid backend. The power grid backend can determine the target line position corresponding to each collection time within different abnormal line sections and generate magnetic field sampling sequences and magnetic field distribution maps, or stitch them together under a unified target line position sequence, thereby shortening the overall fault investigation time.

[0048] In another extended implementation, for scenarios with parallel line deployments, the path information of the corresponding loop can be retrieved after the target line is determined. When determining the target line location at each acquisition time, the path information of the target line is preferentially matched, thereby improving the accuracy of distinguishing the target line from adjacent lines. For lines with accumulated historical inspection results, the magnetic field distribution map obtained from the current inspection can be compared with the magnetic field distribution map under historical normal conditions to help determine the difference between the current faulty section and the historical operating state, further improving the accuracy of fault diagnosis.

[0049] The above technical solution achieves at least the following effects: First, the invention utilizes abnormal line information to determine the target line and obtain its path information. Then, it dispatches a drone to perform interval inspections and data collection along the target line, acquiring the magnetic field measurement values, drone position data, and distance information between the drone and the target line at each collection time. Based on this, the position of the target line at each collection time is determined, forming a magnetic field sampling sequence arranged in order of target line position. This significantly reduces the scope of fault investigation, improves inspection efficiency, and transforms the originally scattered flight measurement results into ordered data unfolding along the target line. Furthermore, by preprocessing the magnetic field sampling sequence with outlier removal, noise filtering, data smoothing, distance compensation, and normalization, and constructing a magnetic field distribution map along the target line, the comparability between magnetic field measurement values ​​at different collection times is enhanced, improving the stability and accuracy of magnetic field distribution analysis. Based on this, the magnetic field distribution map is used to determine suspected abnormal locations, fault types, and fault location information, enabling effective identification and location of open-circuit faults, short-circuit faults, external discharge faults, and terminal node abnormal faults. This provides maintenance personnel with an intuitive and reliable display basis for quickly reaching the fault site.

[0050] Example 2 like Figure 3 As shown, based on the same inventive concept as the above embodiments, the present invention also provides a power distribution line fault detection system based on drone inspection, comprising: a server, a drone, and a display terminal, wherein the server includes: The route determination module is used to acquire route anomaly information, determine the target route based on the route anomaly information, and acquire the path information of the target route; The inspection and scheduling module is used to schedule the drone to inspect along the target route and to collect data at intervals during the inspection process to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route at each collection time, and to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route uploaded by the drone. The location determination module is used to determine the location of the target line at each collection time based on the path information of the target line, the location data of the UAV, and the distance information between the UAV and the target line, and to arrange the magnetic field measurement values ​​at each collection time in the order of the target line locations to obtain the magnetic field sampling sequence. The mapping module is used to preprocess the magnetic field sampling sequence and construct a magnetic field distribution map along the target line based on the preprocessed magnetic field sampling sequence. The output module is used to determine the suspected abnormal location, fault type and fault location information based on the magnetic field distribution map, and output the magnetic field distribution map, fault type and fault location information to the display terminal for display, so as to facilitate fault diagnosis.

[0051] Example 3 like Figure 4 As shown, the present invention also provides an electronic device 100 for implementing a method for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection; The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0052] The memory 101 can be used to store the computer program 103. The processor 102 implements the power distribution line fault detection method based on UAV inspection in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0053] The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0054] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0055] The memory 101 in the electronic device 100 stores multiple instructions to implement a method for detecting faults in power distribution lines based on UAV inspection. The processor 102 can execute multiple instructions to achieve: obtaining line abnormality information, determining the target line based on the line abnormality information, and obtaining the path information of the target line. The drone is dispatched to patrol along the target route and collect data at intervals during the patrol process to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route at each collection time, and to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route uploaded by the drone. Based on the path information of the target route, the location data of the UAV, and the distance information between the UAV and the target route, the location of the target route at each collection time is determined, and the magnetic field measurement values ​​at each collection time are arranged in the order of the target route locations to obtain the magnetic field sampling sequence. The magnetic field sampling sequence is preprocessed, and a magnetic field distribution map along the target line is constructed based on the preprocessed magnetic field sampling sequence. Based on the magnetic field distribution map, the suspected abnormal location, fault type, and fault location information are determined, and the magnetic field distribution map, fault type, and fault location information are output to the display terminal for display, so as to facilitate fault diagnosis.

[0056] Example 4 If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0057] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0061] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for detecting faults in power distribution lines based on unmanned aerial vehicle (UAV) inspection, characterized in that, include: Obtain line anomaly information, determine the target line based on the line anomaly information, and obtain the path information of the target line; The drone is dispatched to patrol along the target route and collect data at intervals during the patrol process to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route at each collection time, and to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route uploaded by the drone. Based on the path information of the target route, the location data of the UAV, and the distance information between the UAV and the target route, the location of the target route at each collection time is determined, and the magnetic field measurement values ​​at each collection time are arranged in the order of the target route locations to obtain the magnetic field sampling sequence. The magnetic field sampling sequence is preprocessed, and a magnetic field distribution map along the target line is constructed based on the preprocessed magnetic field sampling sequence. Based on the magnetic field distribution map, the suspected abnormal location, fault type, and fault location information are determined, and the magnetic field distribution map, fault type, and fault location information are output to the display terminal for display, so as to facilitate fault diagnosis.

2. The method for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection according to claim 1, characterized in that, The steps of determining the target route based on the route anomaly information and obtaining the path information of the target route include: Based on the distribution network operation monitoring results, switch status information, protection action information, line voltage and current monitoring information, feeder automation system alarm information, or manual repair information, determine the abnormal line sections; Within the abnormal line section, a starting end node and an ending end node are determined. The end node can be any one of a power equipment node, a pole / tower node, a transformer node, a switch node, or a line connection node. The target route is determined based on the starting and ending nodes. The path information of the target route is retrieved from the route map database. The path information includes at least one of the following: route direction information, pole and tower location information, broken line node information, route segmentation information, end node coordinate information, and surrounding geographical environment information.

3. The method for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection according to claim 2, characterized in that, The steps for dispatching the drone to inspect along the target route include: The inspection route is planned based on the path information of the target route, and the drone is controlled to fly to the vicinity of the starting node of the target route. Control the drone to fly along the inspection route from the starting node to the ending node of the target route, and collect data at intervals during the flight.

4. The method for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection according to claim 3, characterized in that, The step of performing interval data collection during the inspection process to obtain the magnetic field measurement values, UAV location data, and distance information between the UAV and the target route at each collection time includes: During flight, the drone samples at a fixed sampling frequency or at fixed flight distance intervals to form sampling records at each sampling moment; Each sampling record includes: the time of collection, the magnetic field measurement value, the current location data of the UAV, and the distance information between the UAV and the target route; The magnetic field measurement value is a uniaxial magnetic field component value, a biaxial magnetic field component value, a triaxial magnetic field component value, or a fused magnetic field strength value.

5. The method for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection according to claim 4, characterized in that, The steps for determining the target line location corresponding to each acquisition time include: Based on the path information of the target route, the UAV position data corresponding to each collection time is projected onto the target route path to obtain the corresponding route projection position; Based on the relative position of the projected position of the line between the starting node and the ending node of the target line, the target line position at the time of acquisition is determined, and the corresponding position is any one of the cumulative distance value along the line, the position of the line segment, or the proportional position value within the segment.

6. The method for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection according to claim 5, characterized in that, The steps of preprocessing the magnetic field sampling sequence and constructing a magnetic field distribution map along the target line based on the preprocessed magnetic field sampling sequence include: The magnetic field sampling sequence is subjected to at least two of the following: outlier removal, noise filtering, data smoothing, distance compensation, and normalization. Based on the distance information between the UAV and the target route, distance compensation processing is performed on the magnetic field measurement values ​​in the magnetic field sampling sequence; Based on the target route location and magnetic field measurement values ​​corresponding to each acquisition time, a magnetic field distribution map along the target route is constructed. The magnetic field distribution map can be a line graph, a color bar graph, a segment coloring graph, or a point sequence graph. In the magnetic field distribution map, the magnetic field measurement values ​​corresponding to each acquisition time are displayed according to the corresponding target route location, or several adjacent acquisition times are aggregated into a line analysis segment, and the average value, median value, maximum value, or weighted statistical value of the magnetic field measurement values ​​in the line analysis segment are used as the magnetic field characterization value.

7. The method for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection according to claim 6, characterized in that, The steps for determining the suspected anomaly location, fault type, and fault location information based on the magnetic field distribution map include: Based on at least one of the following: the difference in magnetic field measurement values ​​between adjacent acquisition times, the difference in magnetic field measurement values ​​between adjacent sections along the line, the rate of change of magnetic field measurement values ​​along the line direction, the extreme value characteristics within a local window, and the sudden increase or decrease characteristics of magnetic field measurement values ​​within a continuously acquired section, the suspected abnormal location is determined. In the magnetic field distribution diagram, when there is a difference in the magnetic field distribution before and after the abnormal location, it is determined to be an open circuit fault; when there is a magnetic field distribution before and after the abnormal location, and the local magnetic field distribution shows abnormal enhancement, abnormal distortion, or abnormal fluctuation, it is determined to be a short circuit fault or an external discharge fault; when the overall magnetic field distribution of the target line is lower than the preset distribution characteristics, it is determined to be an abnormal fault at the terminal node. Based on the cumulative distance along the line or the location of the line segment corresponding to the suspected abnormal location, determine which two nodes the fault is located between and the distance from one of the nodes.

8. A power distribution line fault detection system based on unmanned aerial vehicle (UAV) inspection, characterized in that, include: The server includes: a drone and a display terminal. The route determination module is used to acquire route anomaly information, determine the target route based on the route anomaly information, and acquire the path information of the target route; The inspection and scheduling module is used to schedule the drone to inspect along the target route and to collect data at intervals during the inspection process to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route at each collection time, and to obtain the magnetic field measurement value, drone position data and distance information between the drone and the target route uploaded by the drone. The location determination module is used to determine the location of the target line at each collection time based on the path information of the target line, the location data of the UAV, and the distance information between the UAV and the target line, and to arrange the magnetic field measurement values ​​at each collection time in the order of the target line locations to obtain the magnetic field sampling sequence. The mapping module is used to preprocess the magnetic field sampling sequence and construct a magnetic field distribution map along the target line based on the preprocessed magnetic field sampling sequence. The output module is used to determine the suspected abnormal location, fault type and fault location information based on the magnetic field distribution map, and output the magnetic field distribution map, fault type and fault location information to the display terminal for display, so as to facilitate fault diagnosis.

9. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the distribution network line fault detection method based on UAV inspection as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the distribution network line fault detection method based on unmanned aerial vehicle (UAV) inspection as described in any one of claims 1 to 7.

Images