Unmanned aerial vehicle frog jump double-control relay type power transmission line channel scanning method, system, device and medium

Abstract

The application discloses a kind of unmanned aerial vehicle frog jump double-control relay type power transmission line channel scanning method, system, equipment and medium, it is related to power transmission line maintenance technical field, method includes: obtaining the basic data of the power transmission line to be scanned;According to the basic data of power transmission line, the flying patrol route of power transmission line is divided into multiple flying patrol sections based on geographic information system and machine learning model;Unmanned aerial vehicle is connected to two remote controllers simultaneously when flying, one is main control, the other is vice control, and the flying patrol section is set in turn as main control and vice control alternately controls unmanned aerial vehicle frog jump patrol starting from starting point;Data is obtained when unmanned aerial vehicle is controlled by main control and vice control and patrols according to flying patrol section.The method can automatically divide the flying patrol section, reduce the excessive dependence on personal experience, and the division result is more consistent and reliable.Using double-control mode greatly increases the efficiency and safety of flying patrol.Using frog jump flying patrol method improves the battery utilization rate and flying patrol efficiency of unmanned aerial vehicle.

Description

Technical Field

[0001] This invention relates to the field of power transmission line maintenance technology, specifically to a method, system, equipment, and medium for scanning power transmission line channels using a drone-based frog-jump dual-control relay system. Background Technology

[0002] Currently, the technology of using drones equipped with 3D LiDAR to scan and model transmission line corridors is widely used in transmission line corridor inspection work. This technology can accurately measure the safe distances of conductors to the ground, buildings, and crossings within the transmission line corridor. Maintenance personnel can accurately determine the nature of defects based on the measurement data and guide the defect elimination work.

[0003] However, due to the limited battery life of drones, each drone operation can only fly about 3 kilometers from the take-off and landing point before having to return immediately to replace the battery and move to the next take-off and landing point to continue patrol work. This method of patrol not only significantly reduces battery utilization (about 50%), but also wastes a lot of effective patrol time due to frequent relocations. The daily patrol distance of a single drone is only about 12 kilometers, resulting in low patrol efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, equipment, and medium for scanning power transmission line channels using a dual-control relay method involving a drone's leapfrog maneuver, which solves the problems of low battery utilization, short effective flight time, and low flight efficiency in traditional drone flight inspection methods.

[0005] This invention is achieved through the following technical solution:

[0006] In a first aspect, the first embodiment of the present invention provides a method for scanning transmission line channels using a drone-based frog-jump dual-control relay system, comprising:

[0007] Acquire basic data of the power transmission line to be scanned, including basic information of the power transmission line, geospatial data, dynamic environmental data, and UAV performance parameters;

[0008] Based on geographic information systems and machine learning models, the aerial inspection routes of transmission lines are divided into multiple aerial inspection sections according to the basic data of the transmission lines.

[0009] The drone is connected to two remote controllers at the same time during flight patrol, one as the main controller and the other as the secondary controller. The flight patrol section is set to be alternately controlled by the main controller and the secondary controller to conduct frog-jump inspections starting from the starting point.

[0010] Data is acquired from the inspections conducted by the UAV according to the flight patrol sections under the control of the main and secondary controllers.

[0011] Furthermore, the specific method for dividing the aerial inspection route of a transmission line into multiple aerial inspection sections based on the basic data of the transmission line using a geographic information system and machine learning model includes:

[0012] Integrate basic data of power transmission lines into a geographic information system;

[0013] Based on the maximum flight range of the drone, preliminary equidistant candidate sections are generated with towers as nodes;

[0014] The core features that influence the division of candidate segments are extracted from the geographic information system, and these core features are used as input variables for the machine learning model.

[0015] The core feature vectors of the candidate segments are input into the trained machine learning model for prediction. The model determines whether the candidate segments are reasonable and outputs the prediction results for each segment.

[0016] If the prediction result is unreasonable, the features are recalculated based on the reason for the unreasonableness and the prediction is repeated until all candidate segments are reasonable, thus obtaining the optimal multiple flight patrol segments.

[0017] Furthermore, the specific method for extracting the core features affecting the division of candidate segments from the geographic information system includes:

[0018] The basic information of the transmission line includes the total length of the line, tower coordinates, and the distance between adjacent towers. The transmission line vector map layer is loaded into the geographic information system to obtain the total length of the transmission line. The attribute table is obtained from the tower vector map layer, the spatial coordinates of each tower are extracted, and the tower number is associated as a unique identifier. The towers are sorted according to the line direction, and the straight-line distance between adjacent towers is calculated.

[0019] Furthermore, the specific method for extracting the core features affecting the division of candidate segments from the geographic information system includes:

[0020] The geospatial data includes topographic data, vegetation cover, and surface roughness. Topographic elevation model data is loaded into the geographic information system, and a slope layer is generated. A buffer zone is constructed with the transmission line as the center. The slope value within the buffer zone is extracted. The normalized vegetation index within the transmission line buffer zone is extracted using the geographic information system, and the normalized vegetation index is converted into vegetation cover. The surface roughness index is calculated based on the topographic elevation model data.

[0021] Furthermore, the specific method for extracting the core features affecting the division of candidate segments from the geographic information system includes:

[0022] The dynamic environmental data includes weather data. Taking the flight path as a unit, the latitude and longitude of the midpoint of the flight path are selected as the associated coordinates of the meteorological data, and real-time weather data and historical weather data are extracted.

[0023] The performance parameters of the UAV include the flight range and the actual flyable range after terrain correction. The actual flight range data in the operation and maintenance logs are used. The average flight time of the same model in plain terrain is taken as the base value. After deducting 10% redundant time, the effective flight time is obtained. The flight range is obtained by multiplying the effective flight time by the UAV's cruising speed. The terrain correction coefficient is set according to the slope value, and the wind speed correction coefficient is set according to the wind speed level in the weather. The actual flyable range after terrain correction is obtained by multiplying the flight range by the terrain correction coefficient and the wind speed correction coefficient.

[0024] Furthermore, the machine learning model employs a gradient boosting decision tree. The specific method for inputting the core feature vectors of candidate segments into the trained gradient boosting decision tree model for prediction includes:

[0025] Obtain the core feature vectors from the candidate segments;

[0026] The core feature vector is standardized to obtain the standardized feature vector.

[0027] The standardized feature vector is input into the trained gradient boosting decision tree model, which outputs a probability value between 0 and 1. If the probability value is greater than 0.5, the candidate segment is considered reasonable; if the probability value is less than or equal to 0.5, the candidate segment is considered unreasonable.

[0028] Secondly, another embodiment of the present invention provides a UAV-based frog-jump dual-control relay transmission line channel scanning system, comprising:

[0029] The basic data acquisition module is used to acquire basic data of the transmission line to be scanned. The basic data includes basic information of the transmission line, geospatial data, dynamic environmental data, and UAV performance parameters.

[0030] The segment division module is used to divide the aerial inspection route of the transmission line into multiple aerial inspection segments based on the basic data of the transmission line using geographic information system and machine learning model;

[0031] The dual-control module is used to connect two remote controllers simultaneously during drone flight inspection. One is the main controller and the other is the secondary controller. The flight inspection section is set up sequentially from the starting point to allow the main controller and secondary controller to alternately control the drone for frog-jump inspection.

[0032] The inspection data acquisition module is used to acquire data from the UAV's inspections conducted according to the flight inspection sections under the control of the main and secondary controllers.

[0033] Furthermore, the segmentation module includes: a data integration unit, a preliminary segmentation unit, a feature extraction unit, a prediction unit, and a correction unit;

[0034] The data integration unit is used to integrate basic data of power transmission lines into a geographic information system;

[0035] The preliminary segmentation unit is used to generate preliminary equidistant candidate segments based on the maximum flight range of the UAV, with towers as nodes.

[0036] The feature extraction unit is used to extract core features that affect the division of candidate segments from the geographic information system, and uses the core features as input variables for the machine learning model.

[0037] The prediction unit is used to input the core feature vector of the candidate segment into the trained machine learning model for prediction, determine whether the candidate segment is reasonable, and output the prediction result of each segment.

[0038] The correction unit is used to recalculate the features and predict again when the prediction result is unreasonable, based on the reason for the unreasonableness, until all candidate segments are reasonable, thus obtaining the optimal multiple flight patrol segments.

[0039] Thirdly, another embodiment of the present invention provides an electronic device comprising: a processor, an input device, an output device, and a memory, wherein the processor, the input device, the output device, and the memory are interconnected, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the method described in the first embodiment above.

[0040] Fourthly, another embodiment of the present invention provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method described in the first embodiment above.

[0041] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0042] This invention provides a method, system, equipment, and medium for UAV leapfrog dual-control relay scanning of power transmission line channels. Based on a geographic information system (GIS) and machine learning model, it divides the flight route of a power transmission line into multiple flight inspection sections according to the basic data of the transmission line. By transforming domain knowledge into computable features, the machine simulates expert decision-making, achieving intelligent division of UAV inspection areas for power transmission lines. Once the model is trained, the division of new lines can be completed within minutes, greatly improving efficiency. With the accumulation of more inspection data, the model can be continuously optimized, becoming increasingly intelligent, reducing over-reliance on personal experience, and resulting in more consistent and reliable division results. The leapfrog flight inspection method improves UAV battery utilization and single-flight inspection mileage, reducing the number of personnel relocations for the same power transmission line by half, and allowing personnel relocation and UAV flight inspections to proceed simultaneously, significantly improving UAV flight inspection efficiency. The dual-control approach greatly increases the efficiency and safety of flight inspections. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings:

[0044] Figure 1 A flowchart of a UAV frog-jump dual-control relay transmission line channel scanning method provided in the first embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of a UAV frog-jump dual-control relay transmission line channel scanning system provided in another embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0047] like Figure 1 As shown, the first embodiment of the present invention provides a UAV-based frog-jump dual-control relay method for scanning power transmission line channels, comprising:

[0048] Acquire basic data of the power transmission line to be scanned, including basic information of the power transmission line, geospatial data, dynamic environmental data, and UAV performance parameters;

[0049] Based on geographic information systems and machine learning models, the aerial inspection routes of transmission lines are divided into multiple aerial inspection sections according to the basic data of the transmission lines.

[0050] The drone is connected to two remote controllers at the same time during flight patrol, one as the main controller and the other as the secondary controller. The flight patrol section is set to be alternately controlled by the main controller and the secondary controller to conduct frog-jump inspections starting from the starting point.

[0051] Data is acquired from the inspections conducted by the UAV according to the flight patrol sections under the control of the main and secondary controllers.

[0052] In this embodiment, by acquiring basic information, geospatial data, dynamic environmental data, and UAV performance parameters of the transmission line to be scanned, the flight route of the transmission line is divided into multiple flight inspection sections, such as AB, BC, and CD, based on the basic data of the transmission line using a Geographic Information System (GIS) and machine learning models. After setting the flight inspection sections, the UAV is connected to two remote controllers simultaneously during inspection, one as the master controller and the other as the slave controller. The master and slave controllers take turns controlling the UAV according to the flight inspection sections. For example, the master controller takes off from point A and autonomously flies towards point B to inspect the line. After the UAV stabilizes, the master controller travels to point C by vehicle, continuously monitoring the process. The slave controller arrives at point B in advance to take over the UAV, land it, replace the battery, and take off again. When the UAV reaches the predetermined altitude, the master controller remotely takes over the UAV at point C to conduct the line inspection of section B to C, while the slave controller travels from point B to point D. After the UAV reaches point C, the master controller lands the UAV, replaces the battery, and operates the UAV to conduct the line inspection of section C to D. The secondary controller arrives at point D in advance to take over the drone's landing, battery replacement, and retakeoff. This process is repeated, with a leapfrog relay to complete the entire line patrol, acquiring and storing the drone's inspection data according to the patrol sections under the control of the primary and secondary controllers. This embodiment significantly increases the efficiency and safety of patrols by automatically dividing the transmission line into different patrol sections and using a dual-control approach. The leapfrog patrol method theoretically increases battery utilization and single-flight patrol mileage by 100%. The number of times control personnel need to relocate for patrols on the same transmission line is reduced by half, and personnel relocation and drone patrols are conducted simultaneously, greatly improving drone patrol efficiency. The daily patrol range increases from 12 kilometers to 80-100 kilometers.

[0053] Based on GIS and machine learning models, the aerial inspection routes of transmission lines are divided into multiple inspection sections according to the basic data of the transmission lines. The core is to integrate multi-source geospatial data through GIS and combine it with machine learning algorithms to model and analyze complex factors, ultimately achieving automated and intelligent division of aerial inspection sections. Specifically, this includes:

[0054] Integrate basic data of power transmission lines into a geographic information system;

[0055] Based on the maximum flight range of the drone, preliminary equidistant candidate sections are generated with towers as nodes;

[0056] The core features that influence the division of candidate segments are extracted from the geographic information system, and these core features are used as input variables for the machine learning model.

[0057] The core feature vectors of the candidate segments are input into the trained machine learning model for prediction. The model determines whether the candidate segments are reasonable and outputs the prediction results for each segment.

[0058] If the prediction result is unreasonable, the features are recalculated based on the reason for the unreasonableness and the prediction is repeated until all candidate segments are reasonable, thus obtaining the optimal multiple flight patrol segments.

[0059] The basic information of the transmission lines includes the total length of the line, tower coordinates (latitude, longitude, and altitude), spacing between adjacent towers, line direction, and conductor type. Geospatial data includes terrain data, vegetation cover, surface roughness, traffic data, and environmental data. Dynamic environmental data includes weather data, and UAV performance parameters include flight range and actual flyable range after terrain correction. The basic data of the transmission lines is integrated into a geographic information system to establish a spatial coordinate system, enabling the overlay of multiple layers such as line layers, terrain layers, traffic layers, and environmental layers. During data integration, the data undergoes preprocessing: spatial interpolation to fill in blank areas in the terrain data; format conversion to associate non-spatial data with spatial location; and feature quantification to transform qualitative data into quantitative indicators.

[0060] Specific methods for extracting core features influencing candidate segment division from a Geographic Information System (GIS) include: feature extraction from transmission line basic data. Specifically, this involves loading a transmission line vector layer into the GIS. This layer typically records the line direction as polylines, allowing for the acquisition of the total line length. If the line is segmented, the lengths of each segment need to be summed. An attribute table is obtained from the tower vector layer. This table usually stores latitude and longitude or planar coordinates (X = longitude, Y = latitude; or X = east, Y = north). The spatial coordinates of each tower are extracted and associated with its tower number as a unique identifier, such as #101, #102. The towers are then sorted according to the line direction, ensuring they are arranged sequentially from start to finish based on tower number or coordinate order. The straight-line distance between adjacent towers is calculated. Latitude and longitude coordinates are first converted to planar coordinates before calculating Euclidean distance, with the final result retaining meter-level accuracy, establishing a correspondence between tower A, tower B, and spacing.

[0061] Specific methods for extracting core features influencing candidate segment division from a Geographic Information System (GIS) include geospatial data feature extraction. Specifically, this involves loading terrain elevation model data into the GIS and generating a slope layer. A buffer zone is constructed centered on the power transmission line, and slope values ​​within this buffer zone are extracted. A 50m buffer zone (covering the drone inspection range) is then created centered on the power transmission line, and slope values ​​within this buffer zone are extracted. The regional average value is taken as the representative slope value for this line segment. Finally, normalization is performed: Slope index = Average slope ÷ 90; where 90° is the extreme steep slope, corresponding to an index of 1.

[0062] The Normalized Difference Vegetation Index (NDVI) within the transmission line buffer zone was extracted using a Geographic Information System (GIS), and then converted into vegetation cover. Specifically, the NDVI was first calculated from remote sensing images using the formula: NDVI = (Near Infrared Band - Red Band) ÷ (Near Infrared Band + Red Band). The NDVI result range is [-1, 1].

[0063] Extract the NDVI values ​​within the transmission line buffer zone and convert them into vegetation cover FVC using a pixel-based binary model:

[0064]

[0065] in, This represents the minimum vegetation cover, with a value of -0.1 indicating an area without vegetation. The maximum vegetation coverage is represented by 0.8, which represents a dense vegetation area. The final result is mapped to a 0-1 exponent.

[0066] The surface roughness index is calculated based on topographic elevation model data. The standard deviation of elevation between each grid cell and its eight surrounding grid cells is calculated using GIS tools, and then the average of the standard deviations within the buffer zone is taken. This average is then normalized to 0-1.

[0067] Roughness index = (mean standard deviation ÷ maximum possible standard deviation);

[0068] The maximum possible standard deviation is used to reference the elevation fluctuation value of the extremely rugged terrain in the reference area; it can also be combined with the texture analysis results of high-resolution imagery for weighted correction to improve accuracy.

[0069] Specific methods for extracting core features influencing candidate segment division from a Geographic Information System (GIS) include: dynamic environmental data feature extraction. Real-time weather data comes from meteorological website open interfaces and records from drone-borne meteorological sensors. The meteorological website open interface is called, the midpoint coordinates of the segment are input, and real-time data such as wind speed, precipitation, visibility, and temperature are obtained for subsequent correction of drone flight endurance. Historical weather data comes from the National Meteorological Science Data Center and archived data from local meteorological bureaus. Historical data for the area where the transmission line to be scanned is located and the corresponding inspection time period are selected from the meteorological database, such as the average monthly wind speed and number of rainy days in the past year. Using GIS spatial connection tools, meteorological station data is associated with the corresponding flight inspection segment, forming matching data between the segment and historical weather characteristics.

[0070] Specific methods for extracting core features influencing candidate segment division from a Geographic Information System (GIS) include: traffic and personnel data feature extraction. Traffic and personnel data includes parking point travel time and transfer time redundancy. Specifically, this involves obtaining road network layers, traffic network layers, pole vector layers, and parking point layers from the GIS. Parking point travel time: First, a road network dataset is constructed in the GIS, and speed limits for different road grades are entered, such as 80-100 km / h for highways and 20-30 km / h for rural roads. Candidate segment endpoints (e.g., pole B) and candidate parking points are determined, and the optimal driving route length between the two points is calculated using shortest path analysis. The travel time for each segment is calculated according to the segmented speed limits, and the summation yields the travel time (in minutes), using the formula:

[0071] Travel time = Length of each road segment ÷ Speed ​​limit of the corresponding road segment × 60.

[0072] Calculation of transfer time redundancy:

[0073] Step 1: Calculate the flight time (in minutes) of the drone in the candidate segment. The formula is: Flight time = length of candidate segment ÷ drone cruising speed × 60.

[0074] Step 2: Obtain the standard battery swapping time and the average value from the operation and maintenance logs, which is usually 5-10 minutes.

[0075] Step 3: Using the above method for calculating road travel time, obtain the travel time for people from the starting point of the current section to the starting point of the next section.

[0076] Step 4: Finally, calculate the transfer time redundancy using the following formula:

[0077] Transfer time redundancy = UAV flight time + battery swapping time - personnel movement time;

[0078] A positive result for the transfer time redundancy indicates sufficient time, while a negative result indicates a risk of transfer timeout.

[0079] Specific methods for extracting core features influencing candidate segment division from a Geographic Information System (GIS) include: UAV performance parameter feature extraction. UAV performance parameters include flight range and actual flyable range after terrain correction. Specifically: Flight range extraction uses actual flight range data from maintenance logs, taking the average flight time of the same model in plain terrain as the base value, deducting 10% redundant time to obtain the effective flight time, and multiplying the effective flight time by the UAV's cruising speed to obtain the flight range. For terrain-corrected actual flyable range extraction, a terrain correction coefficient is set based on the slope value. For example: slope ≤ 15°, coefficient is 1.0; 15° < slope ≤ 25°, coefficient is 0.9; slope > 25°, coefficient is 0.8. A wind speed correction coefficient is set based on the wind speed level in the weather data. If the weather data shows wind speed ≥ 5, an additional wind speed correction coefficient of 0.9 is added. The flight range is multiplied by the terrain correction coefficient and the wind speed correction coefficient to obtain the terrain-corrected actual flyable range.

[0080] In this embodiment, the machine learning model employs a gradient boosting decision tree model, which effectively handles mixed-type features. It has strong modeling capabilities for non-linear relationships and can output feature importance, aiding in understanding model decisions. A feature matrix is ​​formed according to the format of segments and features, and a training dataset is constructed with labels. The model training process involves randomly dividing the labeled dataset into training and test sets in an 8:2 ratio. The training set is input into the boosting decision tree model for training, and the test set is used to evaluate model performance, outputting the trained boosting decision tree model.

[0081] Specific methods for inputting the core feature vectors of candidate regions into a trained gradient boosting decision tree model for prediction include:

[0082] Obtain the core feature vectors from the candidate segments;

[0083] The core feature vector is standardized to obtain the standardized feature vector.

[0084] The standardized feature vectors are input into the trained gradient boosting decision tree model, which outputs a probability value between 0 and 1. If the probability value is greater than 0.5, the candidate segment is considered reasonable; if the probability value is less than or equal to 0.5, the candidate segment is considered unreasonable. For cases where the prediction result is unreasonable, the features are recalculated based on the reason for the unreasonableness, and the prediction is repeated until all candidate segments are reasonable, thus obtaining the optimal multiple flight patrol segments.

[0085] The 220 kV XX line was tested using a drone-based leapfrog dual-control relay method for scanning power transmission lines, as provided in this embodiment of the invention. The maximum distance covered in a single flight was 9.5 km. Including personnel relocation time, the entire 58 km section of the 220 kV XX line was inspected within 5 hours. The results are shown in Table 1.

[0086] Table 1 220 kV XX Line Flying Inspection Record Sheet

[0087]

[0088] On May 15, 2025, a special aerial patrol was conducted in the YY area. Facing challenges such as high altitude, poor 4G signal, and variable plateau climate, a method for scanning transmission line channels using a drone-based leapfrog dual-control relay system, as described in this invention, was employed. The entire channel patrol was completed in just 10 hours of effective operation, marking the first application of this method in a plateau region and demonstrating its effectiveness and practicality.

[0089] This invention provides a UAV-based leapfrog dual-control relay-style transmission line channel scanning method. Based on a geographic information system (GIS) and machine learning model, the method divides the flight route of a transmission line into multiple flight inspection sections according to the basic data of the transmission line. By transforming domain knowledge into computable features, the machine simulates expert decision-making, achieving intelligent division of transmission line inspection areas by UAVs. Once the model is trained, the division of new lines can be completed within minutes, greatly improving efficiency. With the accumulation of more inspection data, the model can be continuously optimized, becoming increasingly intelligent, reducing over-reliance on personal experience, and resulting in more consistent and reliable division results. The leapfrog flight inspection method improves UAV battery utilization and single-flight inspection mileage, reducing the number of personnel relocations for the same transmission line by half, and allowing personnel relocation and UAV flight inspections to proceed simultaneously, significantly improving UAV flight inspection efficiency. The dual-control approach greatly increases the efficiency and safety of flight inspections.

[0090] like Figure 2 As shown, another embodiment of the present invention provides a UAV-based frog-jump dual-control relay transmission line channel scanning system, comprising:

[0091] The basic data acquisition module is used to acquire basic data of the transmission line to be scanned. The basic data includes basic information of the transmission line, geospatial data, dynamic environmental data, and UAV performance parameters.

[0092] The segment division module is used to divide the aerial inspection route of the transmission line into multiple aerial inspection segments based on the basic data of the transmission line using geographic information system and machine learning model;

[0093] The dual-control module is used to connect two remote controllers simultaneously during drone flight inspection. One is the main controller and the other is the secondary controller. The flight inspection section is set up sequentially from the starting point to allow the main controller and secondary controller to alternately control the drone for frog-jump inspection.

[0094] The inspection data acquisition module is used to acquire data from the UAV's inspections conducted according to the flight inspection sections under the control of the main and secondary controllers.

[0095] The segmentation module includes: a data integration unit, a preliminary segmentation unit, a feature extraction unit, a prediction unit, and a correction unit.

[0096] The data integration unit is used to integrate basic data of power transmission lines into a geographic information system;

[0097] The preliminary segmentation unit is used to generate preliminary equidistant candidate segments based on the maximum flight range of the UAV, with towers as nodes.

[0098] The feature extraction unit is used to extract core features that affect the division of candidate segments from the geographic information system, and uses the core features as input variables for the machine learning model.

[0099] The prediction unit is used to input the core feature vector of the candidate segment into the trained machine learning model for prediction, determine whether the candidate segment is reasonable, and output the prediction result of each segment.

[0100] The correction unit is used to recalculate the features and predict again when the prediction result is unreasonable, based on the reason for the unreasonableness, until all candidate segments are reasonable, thus obtaining the optimal multiple flight patrol segments.

[0101] The execution process of each module can be carried out according to the steps of the UAV frog-jump dual-control relay transmission line channel scanning method provided in the first embodiment, and will not be described in detail in this embodiment.

[0102] The UAV-based frog-jump dual-control relay transmission line channel scanning system and the UAV-based frog-jump dual-control relay transmission line channel scanning method provided in this embodiment of the invention are based on the same inventive concept and have the same beneficial effects, and will not be described in detail here.

[0103] Another embodiment of the present invention provides an electronic device, which includes a processor, an input device, an output device, and a memory. The processor, the input device, the output device, and the memory are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions to execute the method described in the first embodiment above.

[0104] It should be understood that, in the embodiments of the present invention, the processor may be a Central Processing Unit (CPU), but it may also be 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. A general-purpose processor may be a microprocessor or any conventional processor.

[0105] Input devices may include touchpads, microphones, etc., while output devices may include displays (LCDs, etc.), speakers, etc.

[0106] The memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store information about the device type.

[0107] In specific implementations, the processor, input device, and output device described in the embodiments of the present invention can execute the implementation of the method embodiments described in the embodiments of the present invention, or they can execute the implementation of the system embodiments described in the embodiments of the present invention, which will not be repeated here.

[0108] The present invention also provides an embodiment of a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor, cause the processor to perform the method described in the first embodiment above.

[0109] The computer-readable storage medium can be an internal storage unit of the terminal described in the foregoing embodiments, such as the terminal's hard drive or memory. The computer-readable storage medium can also be an external storage device of the terminal, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the terminal. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of the terminal. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0110] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0111] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the terminals and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, or may be electrical, mechanical or other forms of connection.

[0113] 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 them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for scanning power transmission line channels using a dual-control relay-style frog-jump method for unmanned aerial vehicles (UAVs), characterized in that, include: Acquire basic data of the power transmission line to be scanned, including basic information of the power transmission line, geospatial data, dynamic environmental data, and UAV performance parameters; Based on geographic information systems and machine learning models, the aerial inspection routes of transmission lines are divided into multiple aerial inspection sections according to the basic data of the transmission lines. The drone is connected to two remote controllers at the same time during flight patrol, one as the main controller and the other as the secondary controller. The flight patrol section is set to be alternately controlled by the main controller and the secondary controller to conduct frog-jump inspections starting from the starting point. Acquire data on the inspection conducted by the UAV according to the flight patrol section under the control of the main and secondary controllers; The specific method for dividing the aerial inspection route of a transmission line into multiple aerial inspection sections based on the basic data of the transmission line using geographic information systems and machine learning models includes: The basic information of the transmission line includes the total length of the line, tower coordinates, and the distance between adjacent towers. The transmission line vector map layer is loaded into the geographic information system to obtain the total length of the transmission line. The attribute table is obtained from the tower vector map layer, the spatial coordinates of each tower are extracted, and the tower number is associated as a unique identifier. The towers are sorted according to the line direction, and the straight-line distance between adjacent towers is calculated.

2. The UAV-based frog-jump dual-control relay method for scanning power transmission line channels according to claim 1, characterized in that, The specific method for dividing the aerial inspection route of a transmission line into multiple aerial inspection sections based on the basic data of the transmission line using geographic information systems and machine learning models includes: The geospatial data includes topographic data, vegetation cover, and surface roughness. Topographic elevation model data is loaded into the geographic information system, and a slope layer is generated. A buffer zone is constructed with the transmission line as the center. The slope value within the buffer zone is extracted. The normalized vegetation index within the transmission line buffer zone is extracted using the geographic information system, and the normalized vegetation index is converted into vegetation cover. The surface roughness index is calculated based on the topographic elevation model data.

3. The UAV-based frog-jump dual-control relay method for scanning power transmission line channels according to claim 2, characterized in that, The specific method for dividing the aerial inspection route of a transmission line into multiple aerial inspection sections based on the basic data of the transmission line using geographic information systems and machine learning models includes: The dynamic environmental data includes weather data. Taking the flight path as a unit, the latitude and longitude of the midpoint of the flight path are selected as the associated coordinates of the meteorological data, and real-time weather data and historical weather data are extracted. The performance parameters of the UAV include the flight range and the actual flyable range after terrain correction. The actual flight range data in the operation and maintenance logs are used. The average flight time of the same model in plain terrain is taken as the base value. After deducting 10% redundant time, the effective flight time is obtained. The flight range is obtained by multiplying the effective flight time by the UAV's cruising speed. The terrain correction coefficient is set according to the slope value, and the wind speed correction coefficient is set according to the wind speed level in the weather. The actual flyable range after terrain correction is obtained by multiplying the flight range by the terrain correction coefficient and the wind speed correction coefficient.

4. A UAV-based frog-jump dual-control relay-type transmission line channel scanning system, characterized in that, The system for implementing the UAV-based frog-jump dual-control relay transmission line channel scanning method as described in any one of claims 1-3 includes: The basic data acquisition module is used to acquire basic data of the transmission line to be scanned. The basic data includes basic information of the transmission line, geospatial data, dynamic environmental data, and UAV performance parameters. The segment division module is used to divide the aerial inspection route of the transmission line into multiple aerial inspection segments based on the basic data of the transmission line using geographic information system and machine learning model; The basic information of the transmission line includes the total length of the line, tower coordinates and the distance between adjacent towers. The transmission line vector map layer is loaded into the geographic information system to obtain the total length of the transmission line. The attribute table is obtained from the tower vector map layer, the spatial coordinates of each tower are extracted and associated with the tower number as a unique identifier, the towers are sorted according to the line direction, and the straight-line distance between adjacent towers is calculated. The dual-control module is used to connect two remote controllers simultaneously during drone flight inspection. One is the main controller and the other is the secondary controller. The flight inspection section is set up sequentially from the starting point to allow the main controller and secondary controller to alternately control the drone for frog-jump inspection. The inspection data acquisition module is used to acquire data from the UAV's inspections conducted according to the flight inspection sections under the control of the main and secondary controllers.

5. An electronic device, comprising: The processor, input device, output device, and memory are interconnected, the memory being used to store a computer program, the computer program including program instructions, characterized in that the processor is configured to invoke the program instructions to perform the method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-3.

Images