Unmanned aerial vehicle cluster power transmission line inspection method and system

Abstract

The invention discloses an unmanned aerial vehicle cluster power transmission line inspection method and system. The method comprises the following steps: acquiring first inspection information fed back by each unmanned aerial vehicle in an unmanned aerial vehicle cluster; first logical judgment and second logical judgment are carried out through the first inspection information, the first logical judgment is used for representing the inspection condition of the power transmission line, and the second logical judgment is used for obtaining the position of an inspection vehicle; and triggering the corresponding unmanned aerial vehicle to go to the position of the inspection vehicle according to the inspection condition of the power transmission line. The power transmission line inspection information fed back by each unmanned aerial vehicle in the unmanned aerial vehicle cluster is obtained, the first logical judgment and the second logical judgment are performed, and when the power transmission line is detected to be abnormal, the corresponding unmanned aerial vehicle is immediately triggered to go to the position of the inspection vehicle instead of continuing inspection, so that the waiting time of the unmanned aerial vehicle can be remarkably shortened; therefore, the unmanned aerial vehicle cluster can participate in the next round of inspection task more quickly, so that the collaborative inspection efficiency of the unmanned aerial vehicle cluster is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission line inspection, and in particular to a method and system for unmanned aerial vehicle cluster power transmission line inspection. Background Art

[0002] With the continuous advancement of drone technology, the application of drones in power transmission line inspection has gradually become a research hotspot. Drones can quickly reach areas that are difficult for people to reach, capture high-definition images and collect data, greatly improving inspection efficiency and safety. However, the endurance and coverage of a single drone are limited, especially in long-distance and large-scale power transmission line inspections. This problem is more prominent. In order to overcome these limitations, drone swarm technology has emerged. Through the collaborative operation of multiple drones, the inspection range can be effectively expanded and the inspection speed and quality can be improved. Drone swarms are usually dispatched uniformly by a ground control station, and through preset flight paths and task allocation, each drone can be ensured to efficiently complete the inspection task within the designated area.

[0003] Although drone swarm technology has shown great potential in power transmission line inspection, it still faces some challenges in practical application. The first is the coordination and management of drone swarms. In large-scale inspection tasks, the performance parameters of different drones, such as flight speed and battery capacity, may differ, resulting in some drones completing the task ahead of schedule while other drones are still executing. In this case, the drone that completes the task first must wait for other drones before starting the next round of inspection tasks, thereby reducing the overall inspection efficiency. Secondly, the dynamic scheduling of drone swarms is also a difficult problem. The environment of the transmission line is complex and changeable, and the flight path and task allocation of the drone need to be adjusted in time. If these changes cannot be responded to in time, the inspection task may fail or the efficiency may be reduced. In addition, the take-off and landing and charging of drones at parking points are also important factors affecting the inspection efficiency. The inspection vehicle, as a mobile platform, is responsible for transporting drones to different parking points. The drone takes off at the parking point, returns after inspection, and is then transported to the next parking point by the inspection vehicle. In this process, the take-off and landing time and charging time of the drone will affect the efficiency of the entire inspection process.

[0004] In summary, how to optimize the inspection process of drone swarms, improve inspection efficiency and reduce waiting time is an urgent problem to be solved in the current drone swarm transmission line inspection technology. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a UAV cluster transmission line inspection method and system, aiming to improve the overall inspection efficiency of the UAV cluster by improving task allocation and dynamic scheduling strategies.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for inspecting power lines using a drone cluster, comprising: obtaining first inspection information fed back by each drone in the drone cluster; performing a first logical judgment and a second logical judgment based on the first inspection information, wherein the first logical judgment is used to characterize the inspection status of the power line, and the second logical judgment is used to obtain the location of the inspection vehicle; and triggering the corresponding drone to go to the location of the inspection vehicle according to the inspection status of the transmission line.

[0009] As a preferred solution of the UAV cluster transmission line inspection method of the present invention, the triggering of the corresponding UAV to go to the location of the inspection vehicle includes:

[0010] Obtaining the remaining power of the inspection vehicle and determining a first working time of the inspection vehicle;

[0011] Calculating a first running time, where the first running time at least includes an actual running time between the inspection vehicle and the target parking point and a first loss threshold;

[0012] By comparing the first working time and the first operating time, it is determined whether the power of the inspection vehicle can support it to reach the target parking point.

[0013] As a preferred solution of the UAV cluster transmission line inspection method of the present invention, the first logical judgment includes:

[0014] Performing a first processing on the first inspection information fed back by each drone in the drone cluster;

[0015] Inputting the first processed inspection information into a trained fault recognition model to obtain a recognition result;

[0016] It is determined whether there is an abnormality in the power transmission line according to the identification result.

[0017] As a preferred scheme of the UAV cluster transmission line inspection method described in the present invention, the identification results include at least single-phase grounding fault, two-phase grounding fault, two-phase short circuit fault, three-phase grounding fault, three-phase short circuit fault and no fault.

[0018] As a preferred solution of the UAV cluster transmission line inspection method of the present invention, the trained fault identification model includes:

[0019] Collect various fault images and label them by type, and perform secondary processing on the labeled images;

[0020] Inputting the image after the second processing into a preset neural network model for forward propagation calculation to obtain a prediction result, and updating the parameters of the preset neural network model by using stochastic gradient descent;

[0021] Repeat the above process until the preset number of training times is reached to obtain a trained fault recognition model.

[0022] As a preferred solution of the UAV cluster transmission line inspection method described in the present invention, the actual running time between the inspection vehicle and the target parking point is obtained by calculating the distance between the inspection vehicle and the target parking point and dividing it by the set speed of the inspection vehicle.

[0023] As a preferred solution of the UAV cluster transmission line inspection method of the present invention, the second logic judgment includes:

[0024] Determine whether there are any unexecuted inspection tasks, and use a preset inspection task database to perform a table lookup operation on the unexecuted inspection tasks to obtain the target parking point corresponding to the unexecuted inspection tasks;

[0025] The preset inspection task database stores the corresponding relationship between the inspection tasks and the target parking points;

[0026] The patrol vehicle closest to the target parking point is determined, and the position of the patrol vehicle closest to the target parking point is obtained.

[0027] In a second aspect, the present invention provides a UAV cluster transmission line inspection system, comprising:

[0028] A data acquisition module is used to obtain the first inspection information fed back by each drone in the drone cluster;

[0029] A logic judgment module, used to perform a first logic judgment and a second logic judgment based on the first inspection information, wherein the first logic judgment is used to characterize the inspection status of the power transmission line, and the second logic judgment is used to obtain the position of the inspection vehicle;

[0030] The inspection control module is used to trigger the corresponding UAV to go to the location of the inspection vehicle according to the inspection situation of the transmission line.

[0031] In a third aspect, the present invention provides an electronic device, comprising:

[0032] Memory and processor;

[0033] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the drone cluster transmission line inspection method are implemented.

[0034] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the drone cluster transmission line inspection method.

[0035] Compared with the prior art, the present invention has the following beneficial effects: the present invention provides a method and system for power transmission line inspection by a drone cluster, which obtains the power transmission line inspection information fed back by each drone in the drone cluster, and performs a first logical judgment and a second logical judgment. When an abnormality in the transmission line is detected, the corresponding drone is immediately triggered to go to the location of the inspection vehicle instead of continuing the inspection. This can significantly reduce the waiting time of the drone, allowing it to participate in the next round of inspection tasks more quickly, thereby effectively improving the efficiency of the drone cluster in conducting collaborative inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0037] Figure 1 This is a logical schematic diagram of the overall process of the UAV cluster transmission line inspection method described in one embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0039] Example 1

[0040] Reference Figure 1 As an embodiment of the present invention, a method for inspecting power lines by using a drone cluster is provided. By obtaining the power line inspection information fed back by each drone in the drone cluster and performing a first logic judgment and a second logic judgment, when an abnormality in the power line is detected, the corresponding drone is immediately triggered to go to the location of the inspection vehicle instead of continuing the inspection. This can significantly reduce the waiting time of the drone, allowing it to participate in the next round of inspection tasks more quickly, thereby effectively improving the efficiency of the drone cluster in conducting collaborative inspections. Figure 1 The specific steps shown include:

[0041] S100: Obtaining first inspection information fed back by each drone in the drone cluster;

[0042] In an optional embodiment, the first inspection information in step S100 may be high-definition pictures and videos of the power transmission line and its surrounding environment taken by the drone, the first inspection information may be a temperature distribution map of the transmission line and collected sound data, and the first inspection information may also be high-precision three-dimensional terrain and object contour information obtained by using laser radar technology and precise location information of the drone;

[0043] In an embodiment of the present application, the first inspection information is the image of the transmission line during the inspection process and the position corresponding to the image of the transmission line; wherein the position corresponding to the image of the transmission line during the inspection process is the position of the drone when the image of the transmission line is taken.

[0044] It should be noted that the above step S100 can obtain the first inspection information fed back by each drone in the drone cluster, provide timely and accurate data support for subsequent logical judgment and decision-making, ensure real-time monitoring of the inspection of transmission lines, and also help to quickly locate the position of the inspection vehicle, laying the foundation for rapid response and handling of abnormal situations, thereby improving the overall efficiency and reliability of the drone cluster inspection system.

[0045] S200: performing a first logical judgment and a second logical judgment based on the first inspection information, wherein the first logical judgment is used to characterize the inspection status of the power transmission line, and the second logical judgment is used to obtain the position of the inspection vehicle;

[0046] In an optional embodiment, the first logical judgment may be a series of judgment rules for determining whether there is an abnormality in the power transmission line by analyzing the first inspection information fed back by the drone, including but not limited to:

[0047] ① Image recognition judgment: Use image recognition technology to analyze the photos of power transmission lines taken by drones to detect whether there are obvious damage, breakage, hanging foreign objects, etc.;

[0048] ② Thermal imaging analysis: Use thermal imaging data to detect whether there is overheating in the transmission line;

[0049] ③ Historical data comparison: compare the current inspection data with historical data to identify trends or abnormal situations that are different from the past;

[0050] ④Sensor data analysis: Analyze various sensor data carried by the drone, such as environmental parameters such as temperature, humidity, wind speed, and the drone’s own status information, such as flight altitude, speed, etc.

[0051] ⑤ Abnormal sound detection: Through the sound data collected by the drone, detect whether there is abnormal discharge in the transmission line.

[0052] In an embodiment of the present application, the step of the first logical judgment includes: performing a first processing on the first inspection information fed back by each drone in the drone cluster; inputting the first processed inspection information into a trained fault identification model to obtain an identification result; judging whether there is an abnormality in the transmission line based on the identification result, wherein the identification result includes at least a single-phase grounding fault, a two-phase grounding fault, a two-phase short-circuit fault, a three-phase grounding fault, a three-phase short-circuit fault and no fault.

[0053] Specifically, the trained fault recognition model includes: collecting various types of fault images and labeling them by type, determining the labeled images as sample images, and performing a second processing on the sample images; inputting the images after the second processing into a preset neural network model for forward propagation calculation to obtain a prediction result, calculating the cross entropy loss function, calculating the gradient through the back propagation algorithm, and using stochastic gradient descent to update the parameters of the preset neural network model; repeating the above process until the preset number of training times is reached to obtain a trained fault recognition model.

[0054] In an optional embodiment, the first processing may be to remove noise and invalid data in the inspection information and convert different types of data into a unified format and dimension; the first processing may be to extract useful features from the original data and increase the diversity of the data by methods such as rotation, scaling, and flipping; the first processing may also be to fuse data from different sensors or multi-modalities to generate a comprehensive feature vector, and detect and process outliers in the data by statistical methods or machine learning algorithms;

[0055] In an embodiment of the present application, the first processing step is to clean the acquired high-definition images, thermal imaging data, sensor data (such as temperature, humidity, wind speed), GPS positioning data and sound data, remove blurred images, thermal imaging noise, abnormal sensor readings, unreasonable GPS coordinates and background noise, and then standardize the data, normalize the image, thermal imaging, sensor, GPS and sound data to the range of 0-1, and unify the data format and dimension. Next, feature extraction is performed, using a convolutional neural network to extract edge and texture features in the image, extract temperature gradients and hot spots in the thermal imaging image, calculate statistical features of sensor data such as mean and variance, extract features of the drone flight trajectory, and extract spectral features of sound data. The multimodal data is then fused into a comprehensive feature vector by feature splicing or weighted averaging.

[0056] In an optional embodiment, the second processing may be data cleaning to remove blurred, overexposed or underexposed images; the second processing may be data standardization to normalize the image data to a range of 0-1 so that the pixel values ​​between different images are comparable; the second processing may also be data enhancement and feature extraction to increase the diversity of data by methods such as rotation, scaling, and flipping. Feature extraction may use a convolutional neural network to extract features such as edges and textures in the image.

[0057] In an embodiment of the present application, the second processing is to preprocess the sample image data, such as scaling, cropping, and normalization, to adapt to the input requirements of the neural network.

[0058] In an optional embodiment, the second logic judgment determines the current position of the inspection vehicle by analyzing the relevant data in the first inspection information, and the following methods may be used: ① GPS positioning data analysis: directly analyzing the GPS data fed back by the drone to obtain the precise position coordinates of the inspection vehicle; ② Communication signal strength analysis: inferring the approximate position of the inspection vehicle by analyzing the communication signal strength between the drone and the inspection vehicle; ③ Image matching: using the landmark features (such as specific buildings, signs, etc.) in the image taken by the drone to match with the known map data to determine the position of the inspection vehicle; ④ Path tracking: inferring the current position of the inspection vehicle by analyzing the inspection path and timestamp recorded by the drone;

[0059] In an embodiment of the present application, the second logical judgment step is: determine whether there are any unexecuted inspection tasks, use a preset inspection task database to perform a table lookup operation on the unexecuted inspection tasks, and obtain the target parking point corresponding to the unexecuted inspection tasks; the preset inspection task database stores the correspondence between the inspection tasks and the target parking points; determine the inspection vehicle closest to the target parking point, and obtain the position of the inspection vehicle closest to the target parking point.

[0060] It should be noted that the above step S200 can not only accurately evaluate the inspection status of the transmission line and discover potential problems in a timely manner, but also accurately obtain the location information of the inspection vehicle, which is crucial to ensure that the drone can respond quickly when an abnormality is detected. The dual logic judgment mechanism greatly improves the intelligence level and response speed of the inspection system, ensuring that the drone cluster can carry out collaborative inspection tasks efficiently and orderly, thereby significantly improving the inspection efficiency and the timeliness of problem handling.

[0061] S300: triggering the corresponding drone to go to the location of the inspection vehicle according to the inspection situation of the transmission line;

[0062] After the above step S300 triggers the corresponding drone to go to the location of the inspection vehicle according to the inspection situation of the transmission line, the following steps are also included:

[0063] Obtain the remaining power of the inspection vehicle and determine the first working time of the inspection vehicle;

[0064] Calculating a first running time, wherein the first running time at least includes an actual running time between the inspection vehicle and the target parking point and a first loss threshold;

[0065] By comparing the first working time and the first operating time, it is determined whether the power of the inspection vehicle can support it to reach the target parking point.

[0066] In an optional embodiment, the first working duration is the maximum length of time that the inspection vehicle can continue to work under the current power conditions. The first working duration is calculated based on the remaining power of the inspection vehicle and its working power, reflecting the time the inspection vehicle can run continuously without charging. For example, if the remaining power of the inspection vehicle is 80% and its working power is 100 watt-hours / hour, then ideally, the first working duration is the maximum working time that the remaining power can support, that is, 8 hours.

[0067] In an optional embodiment, the first running time is the total time required for the inspection vehicle to reach the target parking point from the current position, including the actual running time between the inspection vehicle and the target parking point and an additional first loss threshold, wherein the actual running time between the inspection vehicle and the target parking point is obtained by calculating the distance between the inspection vehicle and the target parking point and dividing it by the set speed of the inspection vehicle;

[0068] In an optional embodiment, the first loss threshold is an additional time buffer to cope with possible unexpected situations, such as traffic congestion, poor road conditions, increase in temporary tasks, etc. The specific value of the first loss threshold can be set based on experience and specific circumstances, for example, it can be set to 10% of the actual operating time or a fixed time period (such as 15 minutes).

[0069] Specifically, by comparing the first working time and the first operating time, it is determined whether the power of the inspection vehicle can support it to the target parking point; if the first operating time is less than the first working time, it is determined that the power of the inspection vehicle is sufficient to support it to the target parking point; otherwise, the power of the inspection vehicle cannot support it to the target parking point, and it is necessary to determine the inspection vehicle closest to the target parking point again and perform the above-mentioned power judgment.

[0070] It should be noted that the above step S300 ensures that when an abnormal situation is detected, the drone can respond quickly and reach the designated location for further inspection or processing, rather than continuing unnecessary inspection tasks. This not only reduces the ineffective waiting time of the drone and improves the efficiency of drone use, but also speeds up the processing of abnormal situations and enhances the flexibility and emergency response capabilities of the inspection system, thereby significantly improving the overall efficiency and effectiveness of drone cluster collaborative inspections.

[0071] Example 2

[0072] This embodiment provides an application example of a UAV cluster transmission line inspection method to verify and illustrate the technical effects adopted in this method.

[0073] In a feasible implementation, transmission line inspection information fed back by each drone in the drone cluster is obtained; the transmission line inspection information is used to characterize whether the transmission line is abnormal; determine whether there are any unexecuted inspection tasks; when there are unexecuted inspection tasks, determine the inspection vehicle and its position based on the unexecuted inspection tasks; the inspection vehicle is used to carry the drone to the parking point; and trigger the drone corresponding to the transmission line inspection information characterizing the abnormality of the transmission line to go to the position of the inspection vehicle.

[0074] In a feasible implementation, the transmission line inspection information includes the transmission line image during the inspection process and the position corresponding to the transmission line image during the inspection process; the position corresponding to the transmission line image during the inspection process is the position of the drone when the transmission line image is taken.

[0075] In a feasible implementation manner, the transmission line inspection information characterizing the abnormality of the transmission line is determined in the following manner: the transmission line image is input into a preset fault recognition model to obtain the result of the fault recognition model output; when the result of the fault recognition model output is abnormal, it is determined that the transmission line inspection information characterizing the abnormality of the transmission line. The results of the fault recognition model output include: single-phase grounding fault, two-phase grounding fault, two-phase short circuit fault, three-phase grounding fault, three-phase short circuit fault and no fault. In the case where the result of the fault recognition model output is one of single-phase grounding fault, two-phase grounding fault, two-phase short circuit fault, three-phase grounding fault and three-phase short circuit fault, it is determined that the result of the fault recognition model output is abnormal, and then it is determined that the transmission line inspection information characterizing the abnormality of the transmission line. Among them, single-phase grounding fault, two-phase grounding fault, two-phase short circuit fault, three-phase grounding fault and three-phase short circuit fault are the fault types of the transmission line.

[0076] In a feasible implementation, the preset fault recognition model is obtained by: training a preset neural network model using preset sample images to obtain a fault recognition model, wherein the preset sample images carry fault marks and the preset neural network model is a convolutional neural network (CNN).

[0077] In a feasible implementation, various fault pictures are collected from actual power transmission lines, such as single-phase grounding fault, two-phase grounding fault, two-phase short circuit fault, three-phase grounding fault, three-phase short circuit fault, etc., as well as pictures in normal state, and the collected sample pictures are labeled to clarify the fault type or normal state of each picture, and the labeled pictures are determined as sample pictures. The weights and bias parameters of the neural network model are randomly initialized, and the sample picture data is preprocessed, such as scaling, cropping, normalization, etc., to meet the input requirements of the neural network; the sample picture data is input into the neural network model, and the forward propagation calculation is performed to obtain the prediction result; the cross entropy loss function is calculated, and the gradient is calculated by the back propagation algorithm; the parameters of the neural network model are updated using stochastic gradient descent (SGD). The above process is repeated until the preset number of training times is reached, thereby obtaining a fault recognition model that can accurately identify power transmission line faults.

[0078] In a feasible implementation, the inspection vehicle and its position are determined based on the unexecuted inspection tasks, including: using a preset inspection task database to perform a table lookup operation on the unexecuted inspection tasks to obtain the target parking points corresponding to the unexecuted inspection tasks; the inspection task database stores the correspondence between the inspection tasks and the target parking points; determining the inspection vehicle closest to the target parking point, and obtaining the position of the inspection vehicle closest to the target parking point.

[0079] In a feasible implementation, after the drone corresponding to the transmission line inspection information representing the abnormality of the transmission line is triggered to go to the position of the inspection vehicle, it also includes: when the drone corresponding to the transmission line inspection information representing the abnormality of the transmission line arrives at the inspection vehicle, it is determined whether the power of the inspection vehicle is sufficient to support it to the target parking point. Determine whether the power of the inspection vehicle is sufficient to support it to the target parking point in the following way: obtain the remaining power of the inspection vehicle, and determine the remaining working time of the inspection vehicle according to the remaining power. Calculate the distance between the target parking point and the inspection vehicle and divide it by the set speed of the inspection vehicle to obtain the running time between the inspection vehicle and the target parking point. Determine the size between the running time and the remaining working time. When the running time is less than the remaining working time, it is determined that the power of the inspection vehicle is sufficient to support it to the target parking point; otherwise, the power of the inspection vehicle cannot support it to the target parking point.

[0080] In a feasible implementation, the drone cluster includes: drone A, drone B, drone C and drone D, etc. The server obtains the transmission line images during the inspection process fed back by drone A, drone B, drone C and drone D, respectively, and the positions of the drones when taking the transmission line images. Then, when there are unexecuted inspection tasks, the target parking points corresponding to the unexecuted inspection tasks are found in the inspection task database, and the position of the inspection vehicle closest to the target parking point is obtained. Then, the transmission line images fed back by drone A, drone B, drone C and drone D are respectively input into the preset fault recognition model to identify whether each transmission line is abnormal. For example, the transmission line images of drone A and drone B are identified as abnormal by the fault recognition model. Then drone A and drone B are triggered to go to the location of the inspection vehicle.

[0081] Therefore, the method provided by the present invention can facilitate the inspection vehicle to transport the drone corresponding to the transmission line inspection information that characterizes the abnormality of the transmission line to the target parking point, and by allowing the drone to go to the location of the inspection vehicle after detecting the abnormality of the transmission line instead of continuing the inspection, it is convenient for the drone to participate in the next round of transmission line inspection tasks more quickly, thereby improving the efficiency of the drone cluster in conducting collaborative inspections to a certain extent.

[0082] Example 3

[0083] This embodiment provides a UAV cluster transmission line inspection system, including:

[0084] A data acquisition module is used to obtain the first inspection information fed back by each drone in the drone cluster;

[0085] A logic judgment module, used to perform a first logic judgment and a second logic judgment based on the first inspection information, wherein the first logic judgment is used to characterize the inspection situation of the power transmission line, and the second logic judgment is used to obtain the position of the inspection vehicle;

[0086] The inspection control module is used to trigger the corresponding drone to go to the location of the inspection vehicle according to the inspection situation of the transmission line.

[0087] It should be noted that the technical solution of the drone swarm transmission line inspection system and the technical solution of the above-mentioned drone swarm transmission line inspection method belong to the same concept. For details not described in detail in the technical solution of the drone swarm transmission line inspection system in this embodiment, please refer to the description of the technical solution of the above-mentioned drone swarm transmission line inspection method.

[0088] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0089] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for inspecting a power transmission line of a drone cluster is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0090] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0091] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0092] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0093] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0094] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0098] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0099] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A UAV cluster transmission line inspection method, characterized in that: include: Obtain the first inspection information fed back by each drone in the drone cluster; Performing a first logical judgment and a second logical judgment through the first inspection information, wherein the first logical judgment is used to characterize the inspection status of the power transmission line, and the second logical judgment is used to obtain the position of the inspection vehicle; According to the inspection situation of the transmission line, the corresponding drone is triggered to go to the location of the inspection vehicle.

2. The UAV cluster power transmission line inspection method according to claim 1, characterized in that: The triggering of the corresponding drone to go to the location of the inspection vehicle includes: Obtaining the remaining power of the inspection vehicle and determining a first working time of the inspection vehicle; Calculating a first running time, where the first running time at least includes an actual running time between the inspection vehicle and the target parking point and a first loss threshold; By comparing the first working time and the first operating time, it is determined whether the power of the inspection vehicle can support it to reach the target parking point.

3. The UAV cluster transmission line inspection method according to claim 1, characterized in that: The first logical judgment comprises: Performing a first processing on the first inspection information fed back by each drone in the drone cluster; Inputting the first processed inspection information into a trained fault recognition model to obtain a recognition result; It is determined whether there is an abnormality in the power transmission line according to the identification result.

4. The UAV cluster transmission line inspection method according to claim 3, characterized in that: The identification result at least includes a single-phase grounding fault, a two-phase grounding fault, a two-phase short-circuit fault, a three-phase grounding fault, a three-phase short-circuit fault and no fault.

5. The UAV cluster transmission line inspection method according to claim 4, characterized in that: The trained fault identification model includes: Collect various fault images and label them by type, and perform secondary processing on the labeled images; Inputting the image after the second processing into a preset neural network model for forward propagation calculation to obtain a prediction result, and updating the parameters of the preset neural network model by using stochastic gradient descent; Repeat the above process until the preset number of training times is reached to obtain a trained fault recognition model.

6. The UAV cluster transmission line inspection method according to claim 2, characterized in that: The actual running time between the patrol vehicle and the target parking point is obtained by calculating the distance between the patrol vehicle and the target parking point and dividing it by the set speed of the patrol vehicle.

7. The UAV cluster transmission line inspection method according to claim 1, characterized in that: The second logical judgment includes: Determine whether there are any unexecuted inspection tasks, and use a preset inspection task database to perform a table lookup operation on the unexecuted inspection tasks to obtain the target parking point corresponding to the unexecuted inspection tasks; The preset inspection task database stores the corresponding relationship between the inspection tasks and the target parking points; The patrol vehicle closest to the target parking point is determined, and the position of the patrol vehicle closest to the target parking point is obtained.

8. A system using the UAV cluster power transmission line inspection method according to any one of claims 1 to 7, characterized in that: include: A data acquisition module is used to obtain the first inspection information fed back by each drone in the drone cluster; A logic judgment module, used to perform a first logic judgment and a second logic judgment based on the first inspection information, wherein the first logic judgment is used to characterize the inspection status of the power transmission line, and the second logic judgment is used to obtain the position of the inspection vehicle; The inspection control module is used to trigger the corresponding UAV to go to the location of the inspection vehicle according to the inspection situation of the transmission line.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the drone cluster transmission line inspection method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the drone cluster transmission line inspection method described in any one of claims 1 to 7.

Images