Power line inspection method and device based on cooperation of unmanned aerial vehicle units

Abstract

The invention discloses an electric power line inspection method and device based on cooperation of an unmanned aerial vehicle unit, and belongs to the field of electric power inspection, and the method comprises the steps: building a three-dimensional equivalent model of an electric power inspection region, planning a plurality of electric power inspection routes, and configuring an electric power inspection task; configuring an unmanned aerial vehicle group, executing a power inspection task, obtaining multi-modal detection data of the power line, and locking a line abnormal point when detecting that the line is abnormal; and determining a three-dimensional model of the abnormal region, performing abnormal evolution, obtaining an abnormal development prediction result, and performing power line maintenance on the line abnormal points. The technical problems that in the prior art, power line maintenance is performed only when obvious abnormity occurs in power line inspection, early abnormity is not maintained in time, and the operation reliability of the power line is affected are solved, the early abnormity of the power line is found in time, the future development trend is predicted through abnormity evolution, and the reliability of the power line is improved. Early maintenance of the power line is carried out, and the operation reliability of the power line is improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power inspection, and in particular to a method and device for electric power line inspection coordinated by an unmanned aerial vehicle group. Background Art

[0002] As an important part of the power transmission network, the safe operation of power lines directly affects the stability and reliability of the power grid. In order to ensure the safe operation of power lines, it is necessary to conduct regular inspections and maintenance of power lines. In the prior art, power line inspections detect obvious abnormalities in power lines by setting various detection thresholds. The lack of timely discovery and processing of early abnormalities can easily lead to the gradual deterioration of abnormal conditions, thereby causing serious power accidents and affecting the operational reliability of power lines. At the same time, due to the lack of prediction and evolution analysis of abnormal conditions, it is impossible to predict the development trend of abnormalities, resulting in passive maintenance work, missing the best processing time, and increasing maintenance costs. Therefore, in the prior art, power line inspections only perform power line maintenance when obvious abnormalities occur. The lack of timely maintenance of early abnormalities affects the operational reliability of power lines. Summary of the invention

[0003] The present application provides a method and device for power line inspection coordinated by an unmanned aerial vehicle group, aiming to solve the technical problem that in the prior art, power line inspection only performs power line maintenance when obvious abnormalities occur, lacks timely maintenance for early abnormalities, and affects the reliability of power line operation.

[0004] In view of the above problems, the present application provides a method and device for power line inspection coordinated by a group of unmanned aerial vehicles.

[0005] The first aspect disclosed in the present application provides a method for power line inspection coordinated by a drone group, the method comprising: establishing a three-dimensional equivalent model of the power inspection area, planning multiple power inspection routes according to the three-dimensional equivalent model, and configuring multiple power inspection tasks for each power inspection route; configuring a drone group according to the multiple power inspection tasks of each power inspection route, the drone group comprising a master control drone and multiple detection drones, wherein the master control drone is used to coordinately control multiple detection drones to complete the power inspection tasks, and summarize and process the collected data of the multiple detection drones, and the multiple detection drones respectively perform Carry out different types of inspection tasks; control the drone group to perform power inspection tasks along the corresponding power inspection route, obtain multimodal detection data of the power line in real time, and when the main control drone detects a line abnormality, lock the line abnormal point, and send the line abnormal point, multimodal detection data and abnormal detection results to the central processing platform; the central processing platform determines the three-dimensional model of the abnormal area in the three-dimensional equivalent model according to the line abnormal point, and combines the abnormal detection results with the multimodal detection data to perform abnormal evolution on the line abnormal point to obtain the abnormal development prediction results; perform power line maintenance on the line abnormal point according to the abnormal development prediction results.

[0006] Another aspect disclosed in the present application provides a power line inspection device coordinated by a drone group, the device comprising: a task planning unit, used to establish a three-dimensional equivalent model of the power inspection area, plan multiple power inspection routes according to the three-dimensional equivalent model, and configure multiple power inspection tasks for each power inspection route; a drone configuration unit, used to configure a drone group according to multiple power inspection tasks for each power inspection route, the drone group comprising a master drone and multiple detection drones, wherein the master drone is used to coordinately control multiple detection drones to complete power inspection tasks, and summarize and process the collected data of the multiple detection drones, and the multiple detection drones respectively perform different types of type of detection tasks; a task execution unit, used to control the drone group to perform power inspection tasks along the corresponding power inspection route, obtain multimodal detection data of the power line in real time, and when the main control drone detects a line abnormality, it locks the line abnormal point and sends the line abnormal point, multimodal detection data and abnormal detection results to the central processing platform; an abnormal evolution unit, used for the central processing platform to determine the three-dimensional model of the abnormal area in the three-dimensional equivalent model according to the line abnormal point, and combine the abnormal detection results with the multimodal detection data to perform abnormal evolution on the line abnormal point to obtain the abnormal development prediction result; the line maintenance unit is used to perform power line maintenance on the line abnormal point according to the abnormal development prediction result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Due to the adoption of a three-dimensional equivalent model for establishing the power inspection area, multiple power inspection routes are planned according to the three-dimensional equivalent model, and multiple power inspection tasks are configured for each power inspection route, which provides a basis for the subsequent inspection work of the drone group; according to the multiple power inspection tasks of each power inspection route, the drone group is configured, and the drone group includes a master control drone and multiple detection drones, so as to realize the division of labor and cooperation within the drone group. The master control drone is responsible for task allocation and data aggregation, and the detection drone is responsible for performing different types of detection tasks, so as to improve the inspection efficiency and the diversity of data collection; the drone group is controlled to perform power inspection tasks along the corresponding power inspection route, and the multimodal detection data of the power line is obtained in real time. When the master control drone detects a line abnormality, it locks the line abnormal point, and combines the line abnormal point, multimodal detection data and abnormal detection results The results are sent to the central processing platform, so that the drone group can realize real-time detection and abnormal discovery of power lines; the central processing platform determines the three-dimensional model of the abnormal area in the three-dimensional equivalent model according to the abnormal points of the line, and combines the abnormal detection results with the multimodal detection data to perform abnormal evolution on the abnormal points of the line, obtain the abnormal development prediction results, and realize the development prediction of the line abnormality; the power line is maintained at the abnormal points of the line according to the abnormal development prediction results, and the technical solution for early maintenance of the line is realized, which solves the technical problem that the power line inspection in the prior art only performs power line maintenance when obvious abnormalities occur, lacks timely maintenance of early abnormalities, and affects the reliability of power line operation. It achieves the technical effect of timely discovering early abnormalities of power lines, predicting future development trends through abnormal evolution, performing early maintenance of power lines, and improving the reliability of power line operation.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flowchart of a method for power line inspection coordinated by a drone group is provided for an embodiment of the present application;

[0011] Figure 2 A structural schematic diagram of a power line inspection device coordinated by an unmanned aerial vehicle group is provided for an embodiment of the present application.

[0012] Explanation of the reference numerals: mission planning unit 11, drone configuration unit 12, mission execution unit 13, anomaly evolution unit 14, line maintenance unit 15. DETAILED DESCRIPTION

[0013] The overall idea of ​​the technical solution provided by this application is as follows:

[0014] The embodiments of the present application provide a method and device for power line inspection coordinated by unmanned aerial vehicle groups. First, a three-dimensional digital model of the power inspection area is established, and on this basis, inspection routes and tasks are planned to provide guidance for the coordinated inspection of the unmanned aerial vehicle group. Secondly, a one-master-multiple-slave unmanned aerial vehicle group coordination solution is adopted, and the master control unmanned aerial vehicle coordinates and dispatches the detection unmanned aerial vehicles to carry out multimodal data collection and anomaly detection, so as to achieve efficient collaboration within the unmanned aerial vehicle group. Thirdly, during the real-time inspection of the unmanned aerial vehicle group, once an abnormality is found, the abnormal point is locked in time and the data is reported to the central processing platform. The central processing platform determines the three-dimensional model of the abnormal area according to the location of the abnormal point, and integrates multi-source detection data to carry out abnormal evolution analysis and predict the abnormal development trend. Afterwards, according to the abnormal development prediction results, the maintenance work of the abnormal points of the line is carried out in time to achieve early maintenance of the line.

[0015] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0016] Embodiment 1, as Figure 1 As shown, an embodiment of the present application provides a method for power line inspection coordinated by a drone group, the method comprising:

[0017] S1: Establish a three-dimensional equivalent model of the power inspection area, plan multiple power inspection routes according to the three-dimensional equivalent model, and configure multiple power inspection tasks for each power inspection route.

[0018] Specifically, first, collect geographic information data and power line information of the power inspection area, such as topography, vegetation distribution, line direction, tower location, etc. Secondly, through three-dimensional modeling software, integrate the collected geographic information data and power line information into a three-dimensional equivalent model, which not only contains natural geographical elements, but also accurately presents the spatial distribution of power lines. Then, based on the established three-dimensional equivalent model, further plan multiple power inspection routes. In the planning process, the complexity of the terrain, the density of line distribution, the flight characteristics of the drone (such as endurance, wind resistance, etc.) and the inspection requirements (such as inspection accuracy, coverage, etc.) are comprehensively considered, combined with the decision of the expert group, and multiple power inspection routes are generated to cover all power lines that need to be inspected, while avoiding obstacles that may affect flight safety. After completing the power inspection route planning, multiple specific power inspection tasks are configured for each power inspection route, including but not limited to visual inspection tasks, infrared detection tasks, laser scanning tasks, etc. Among them, the configuration of power inspection tasks needs to be adjusted according to the characteristics of the line and the actual inspection needs.

[0019] By establishing a three-dimensional equivalent model and planning power line inspection routes and tasks based on it, a solid foundation is provided for subsequent coordinated inspections by drone groups, thereby improving the efficiency, quality and safety of power line inspections.

[0020] S2: According to the multiple power inspection tasks of each power inspection route, a drone group is configured, and the drone group includes a master control drone and multiple detection drones, wherein the master control drone is used to coordinately control multiple detection drones to complete the power inspection tasks, and summarize and process the collected data of multiple detection drones. Multiple detection drones perform different types of detection tasks respectively.

[0021] Specifically, first, based on the planned power inspection routes and power inspection tasks, the drone group required for each power inspection route is configured. The configured drone group includes a master control drone and multiple detection drones. Among them, the master control drone has strong computing and communication capabilities, which is used to coordinate the actions of the entire drone group. Multiple detection drones are configured according to the type of power inspection tasks. Each detection drone specializes in performing a type of detection task, which corresponds to the power inspection task one by one. The master control drone is responsible for planning and coordinating the actions of the detection drones, and receiving and processing the data sent back by the detection drones in real time. Each detection drone is equipped with corresponding detection equipment, such as high-definition cameras, infrared thermal imagers, laser scanners, etc., according to the task type of the power inspection task it specializes in performing, to perform specific types of detection tasks.

[0022] Through the configuration of the drone group, the coordinated application of multiple detection methods can be realized to improve the efficiency and scalability of power line inspection. Each detection drone focuses on a specific type of detection task, which can better play its advantages and improve the quality of detection. At the same time, the unified coordination of the master drone ensures the orderly progress of the entire inspection process, and the collaborative work of multiple detection drones improves the coverage of the inspection and data collection capabilities, providing hardware support for the subsequent execution of power inspection tasks.

[0023] S3: Control the drone group to perform power inspection tasks along the corresponding power inspection route, and obtain multimodal detection data of the power line in real time. When the master drone detects a line abnormality, it locks the line abnormal point and sends the line abnormal point, the multimodal detection data and the abnormal detection result to the central processing platform.

[0024] Specifically, first, according to the configured drone group, the drone group is controlled to start performing the power inspection task according to the planned power inspection route. During the inspection process, multiple detection drones use the equipped detection equipment to collect the detection data of the power line in real time according to their respective power inspection tasks. Multiple detection drones form multimodal detection data, including but not limited to high-definition images, infrared thermal imaging, laser scanning data, etc., to provide multi-dimensional information for comprehensive evaluation of the power line status. Secondly, while coordinating the detection drones to perform tasks, the master drone receives and processes the multimodal detection data sent back by multiple detection drones in real time, and performs real-time analysis on the received multimodal detection data. For example, for different types of power inspection tasks, the corresponding normal threshold is set based on the design parameters and historical operation data of the power line to determine whether the multimodal detection data is within the normal range; the multimodal detection data received in real time is compared with the preset normal threshold; based on the comparison results, it is determined whether there is an abnormal situation; when one or more detection data exceeds its corresponding normal threshold, it is determined to be an abnormal situation.

[0025] When the multimodal detection data indicates that there is an abnormality in the power line, the master control drone immediately locks the location information of the power line and determines the abnormal point of the line. Then, the master control drone packages the detected abnormal point information of the line, the relevant multimodal detection data and the abnormal detection results, and sends them to the central processing platform through the wireless communication network, ensuring that the central processing platform can quickly obtain the on-site situation and provide necessary information support for subsequent in-depth analysis and decision-making of the abnormality.

[0026] Through real-time monitoring and data transmission, abnormal conditions of power lines can be quickly discovered and relevant information can be promptly transmitted to the central processing platform, improving the timeliness and accuracy of power line inspections and providing detailed data support for subsequent abnormality processing, thereby improving the operational reliability and safety of power lines.

[0027] S4: The central processing platform determines a three-dimensional model of the abnormal area in the three-dimensional equivalent model according to the abnormal point of the line, performs abnormal evolution on the abnormal point of the line in combination with the abnormal detection result and the multimodal detection data, and obtains an abnormal development prediction result.

[0028] Specifically, first, the central processing platform receives the line abnormal point information, multimodal detection data and abnormal detection results sent by the master control drone. Among them, the abnormal detection result is the information obtained after the master control drone performs abnormal detection. For example, a certain abnormal detection result is: abnormal type: abnormal conductor temperature; abnormal degree: temperature exceeds the standard by 8°C (measured 75°C, normal threshold 67°C); abnormal location: conductor between tower 10 and tower 11; related parameters: current load current 580A, ambient temperature 28°C, wind speed 1.5m / s, etc. Based on the received line abnormal points, the central processing platform locates the precise position of the line abnormal point in the three-dimensional equivalent model. Secondly, with the located line abnormal point as the center, a certain range of areas is delineated in the three-dimensional equivalent model, and the three-dimensional model information of the area is extracted to form a three-dimensional model of the abnormal area, which includes the topography and landforms around the line abnormal point, the distribution of power facilities and other information, and provides a spatial reference for the subsequent abnormal evolution analysis.

[0029] Then, the central processing platform combines the anomaly detection results and multimodal detection data to perform an anomaly evolution analysis on the abnormal points of the line. Specifically, the central processing platform first determines the type of anomaly based on the anomaly detection results, such as abnormal conductor temperature, abnormal line insulation layer, etc. Next, the anomaly evolution model corresponding to the anomaly type is called, and the multimodal detection data is input into the anomaly evolution model to simulate the development trend of the abnormal state over time. In the process of anomaly evolution, a variety of factors are considered comprehensively, such as meteorological conditions, load changes, material aging, etc., to improve the accuracy of the prediction. By running the anomaly evolution model, the changes in the abnormal state in the future period of time are simulated, including the speed of the anomaly degree, the expansion of the impact range, etc. Afterwards, based on the results of the anomaly evolution, the abnormal development prediction results are generated, including the timeline of the abnormal development, the change curve of the impact degree, the potential risk level and other information, to provide a reference for subsequent maintenance decisions.

[0030] Through abnormal evolution analysis based on three-dimensional models and multimodal data, it is possible to comprehensively evaluate and predict abnormal conditions in power lines, effectively improve the preventive maintenance capabilities of power lines, reduce the risk of sudden failures, and thus enhance the reliability and safety of power supply.

[0031] S5: Performing power line maintenance on the abnormal point of the line according to the abnormal development prediction result.

[0032] Specifically, first, the central processing platform formulates corresponding power line maintenance strategies based on the abnormal development prediction results obtained, taking into account factors such as the type, severity, development trend and potential risks of the abnormality. Secondly, based on the formulated power line maintenance strategy, a specific maintenance task list is generated, including maintenance priority, required professional and technical personnel, necessary maintenance tools and spare parts, and estimated maintenance time. Then, the central processing platform sends the abnormal development prediction results and the maintenance task list to the relevant maintenance team. After receiving them, the maintenance team will carry the necessary equipment and materials to the abnormal point of the line for on-site processing based on the abnormal development prediction results and the maintenance task list, such as replacing damaged parts, cleaning dirt, adjusting line tension, and strengthening support structures.

[0033] Through maintenance based on the prediction results of abnormal development, accurate and preventive maintenance of power lines can be achieved, which not only improves maintenance efficiency and reduces maintenance costs, but also effectively prevents the occurrence of potential faults, thereby improving the overall reliability and safety of power lines.

[0034] Furthermore, the embodiment of the present application also includes:

[0035] For the first power inspection route, traverse the multiple power inspection tasks and determine the first power inspection task; extract the first task execution point in the first power inspection task, control the drone group to fly to the first task execution point, wherein the first task execution point corresponds to the first power line to be inspected; according to the first power inspection task, use the multiple detection drones to synchronously perform power inspection on the first power line to be inspected to obtain multimodal detection data; transmit the multimodal detection data to the master control drone, perform anomaly detection on the multimodal detection data, and when a line abnormality is detected, use the first task execution point as the line abnormality point.

[0036] In a feasible implementation, the first power inspection route refers to any one of a plurality of power inspection routes, and the inspection methods of other power inspection routes are the same. For the first power inspection route, the master control drone sequentially traverses the plurality of power inspection tasks configured on the first power inspection route according to the inspection sequence, and determines one power inspection task each time as the first power inspection task. Then, the first task execution point in the first power inspection task is extracted. The first task execution point refers to the specific location where the detection needs to be performed in the first power inspection task, which is expressed in three-dimensional space coordinates. The first task execution point corresponds to the first power line to be inspected. The first power line to be inspected refers to the power line section that needs to be inspected corresponding to the first task execution point. The master control drone extracts the coordinate information of the first task execution point, and controls the entire drone group to fly to the position accordingly.

[0037] Then, multiple inspection drones perform synchronous inspections on the first power line to be inspected according to their respective tasks, thereby obtaining comprehensive multimodal inspection data, including various forms of inspection data, such as visible light images, infrared thermal imaging, laser scanning data, etc. Subsequently, the multimodal inspection data is transmitted to the master control drone, which receives and analyzes the multimodal inspection data. When an abnormality is found, the current first task execution point is marked as a line abnormality point, providing precise positioning for subsequent processing.

[0038] Through the division of labor and cooperation among multiple drones, efficient real-time monitoring and precise anomaly detection of power lines are achieved, the efficiency and comprehensiveness of detection are improved, and strong guarantees are provided for the safe operation of power lines.

[0039] Furthermore, the embodiment of the present application also includes:

[0040] According to the first power line to be inspected, the line model of the three-dimensional equivalent model is copied to obtain a first three-dimensional power line, wherein the first three-dimensional power line represents a normal state of the first power line to be inspected; before the power inspection task, the first three-dimensional power line is pre-stored in the master control drone; after the master control drone receives the multimodal detection data, the first three-dimensional power line is retrieved to perform abnormality detection on the multimodal detection data.

[0041] In a preferred embodiment, first, the precise position and range of the first power line to be inspected in the power inspection area are identified, so as to extract the local area corresponding to the first power line to be inspected from the constructed three-dimensional equivalent model, realize targeted replication of the three-dimensional equivalent model, and obtain the first three-dimensional power line, which not only includes the geometric features of the line itself (such as conductor sag, pole tower structure, etc.), but also includes the surrounding environmental information (such as terrain undulations, vegetation distribution, etc.). The first three-dimensional power line characterizes the various parameters and features of the first power line to be inspected under ideal or normal operating conditions, and provides a standard reference for subsequent abnormality detection.

[0042] It is executed before the actual inspection task begins, and the generated first three-dimensional power line is processed through data compression and optimization to adapt to the storage and processing capabilities of the master control drone. Subsequently, the first three-dimensional power line is transmitted and stored in the storage device of the master control drone, such as a solid-state drive or high-performance flash memory, thereby reducing the need for real-time data transmission and avoiding network delays or insufficient bandwidth problems that may occur during the inspection process. At the same time, it provides the master control drone with a standard reference that can be called at any time, improving the response speed and reliability of anomaly detection.

[0043] When the master drone receives the multimodal detection data from each detection drone, it immediately starts the abnormality detection process. First, the master drone quickly retrieves the pre-stored first three-dimensional power line from its storage device; then, the multimodal detection data acquired in real time is compared and analyzed with the first three-dimensional power line in multiple dimensions, including but not limited to image registration, point cloud matching, thermal imaging analysis, etc. Through precise comparison, the deviation between the actual line state and the normal state is identified, such as abnormal wire sag, wire damage and other problems, so as to timely discover potential safety hazards.

[0044] Through power line anomaly detection, using pre-built 3D models and combining real-time multimodal data, the detection efficiency is significantly improved while ensuring detection accuracy, providing strong technical support for preventive maintenance and safe operation of power systems.

[0045] Furthermore, the embodiment of the present application also includes:

[0046] Based on the first three-dimensional power line, a multimodal feature template of the first power line to be inspected in a normal state is extracted, and multiple modal normal feature libraries are constructed; the multimodal detection data is compared with the multiple modal normal feature libraries respectively, and the feature deviations of different types of detections are calculated to obtain multiple feature deviations; the deviation thresholds of different types of detections are extracted, and it is determined whether multiple feature deviations meet the corresponding deviation thresholds; if the multiple feature deviations all meet the corresponding deviation thresholds, it is determined that the state of the first power line to be inspected is normal; if any feature deviation among the multiple feature deviations does not meet the corresponding deviation threshold, it is determined that the state of the first power line to be inspected is abnormal.

[0047] In a preferred embodiment, first, a multi-dimensional analysis is performed on the pre-stored first three-dimensional power line. Through methods such as image processing algorithms, point cloud analysis technology and thermal imaging feature extraction, normal state features under multiple modes are extracted from the first three-dimensional power line as multi-modal feature templates, including but not limited to conductor geometry parameters (such as sag, line spacing), conductor surface texture features, normal operating temperature distribution of conductors, etc. Subsequently, these extracted multi-modal feature templates are classified and organized to construct multiple independent modal normal feature libraries. Each modal normal feature library corresponds to a specific detection mode, such as a visible light feature library, an infrared feature library, a laser point cloud feature library, etc., as a reference for subsequent abnormal detection. Subsequently, the multi-modal detection data acquired in real time is accurately compared with the constructed normal feature libraries of each mode. For each detection mode, the degree of deviation between the actual detection data and the normal feature is calculated to obtain a quantitative feature deviation. For example, for visible light images, the structural similarity index is calculated; for thermal imaging data, the root mean square error of the temperature distribution is calculated; for laser point cloud data, the average distance deviation after point cloud registration is calculated, etc., so as to obtain multiple feature deviations corresponding to different detection modes.

[0048] Afterwards, the deviation thresholds corresponding to various detection types are extracted from the preset parameter library. Among them, the deviation threshold is pre-set based on a large amount of historical data and expert experience, and represents the maximum acceptable deviation degree of each type of feature. Subsequently, the calculated multiple feature deviations are compared with the corresponding deviation thresholds, and each detection mode has its own independent judgment criteria. If the feature deviations of all detection modes do not exceed their respective deviation thresholds, from multiple dimensions, the various indicators of the first power line to be inspected are within an acceptable range, and there are no obvious abnormalities or potential risks. It is considered that the first power line to be inspected is in a normal state. On the contrary, if the feature deviation of any detection mode exceeds the corresponding deviation threshold, it is determined that the first power line to be inspected is in an abnormal state, ensuring that any potential abnormalities can be discovered in a timely manner.

[0049] Through comprehensive power line anomaly detection and comprehensive use of multimodal data, various types of line anomalies can be effectively identified, the reliability and safety of power line inspections can be improved, and a strong guarantee for the stable operation of the power system can be provided.

[0050] Furthermore, the embodiment of the present application also includes:

[0051] In the three-dimensional equivalent model, the three-dimensional spatial coordinates of the abnormal point of the line are obtained; with the three-dimensional spatial coordinates as the center, a three-dimensional buffer zone of a preset radius is established, and the three-dimensional equivalent model within the three-dimensional buffer zone is extracted to generate a three-dimensional model of the abnormal area; according to the abnormality detection result, the abnormality type of the abnormal point of the line is obtained, and according to the abnormality type, the corresponding abnormality evolution model is matched in the abnormality evolution knowledge base; based on the abnormality detection result and the multimodal detection data, the dynamic change process of the abnormal state over time is simulated through the abnormality evolution model to obtain the time series spatial distribution of the abnormal state; according to the time series spatial distribution, the abnormal development prediction result is generated.

[0052] In a feasible implementation, after the central processing platform receives the line abnormal point reported by the master control drone, it locates the line abnormal point in the pre-constructed three-dimensional equivalent model and extracts its three-dimensional spatial coordinates, laying the foundation for subsequent abnormal area modeling and analysis, and ensuring the accurate positioning of abnormal processing. Then, a three-dimensional buffer zone with a preset radius is constructed with the obtained three-dimensional coordinates of the abnormal point as the center. The size of the preset radius is dynamically adjusted according to factors such as the abnormal type and line characteristics. Subsequently, all information in the three-dimensional buffer zone, including power facilities, topography, surrounding environment, etc., is extracted from the complete three-dimensional equivalent model to form a local three-dimensional model of the abnormal area, providing a comprehensive spatial background for subsequent abnormal evolution analysis.

[0053] Then, the anomaly detection results are analyzed to determine the specific anomaly type of the line abnormal point, such as overheated conductors, broken lines, etc. The pre-established anomaly evolution knowledge base is accessed. The anomaly evolution knowledge base contains anomaly evolution models of various types of power line anomalies. The anomaly evolution model is a simulation prediction model built based on historical anomaly development data of different types of anomalies, which is used to simulate and predict the development process of a specific type of anomaly. Subsequently, the anomaly detection results and multimodal detection data are input into the selected anomaly evolution model, and the dynamic change process of the abnormal state over time, such as environmental conditions, load changes, etc., is simulated through simulation prediction. Through repeated iterations, a series of spatial distribution data representing the abnormal state at different time points are generated to form a time series spatial distribution of the abnormal state. Afterwards, based on the obtained time series spatial distribution, key features are extracted, development trends are identified, and comprehensive abnormal development prediction results are generated.

[0054] Through the precise positioning, comprehensive analysis and prediction of power line anomalies, not only the current abnormal state is taken into account, but also its future development trend is simulated, which provides important decision-making basis for the preventive maintenance and treatment of the power system, and effectively improves the safety and reliability of the power system.

[0055] Furthermore, the embodiment of the present application also includes:

[0056] Based on the spatial distribution of the time series, the rate of change of the line abnormal points over time is calculated to obtain the abnormal development speed; the main direction of the change of the line abnormal points with the spatial distribution is counted to obtain the abnormal development direction; along the abnormal development direction, in the three-dimensional model of the abnormal area, the abnormal influence range is extracted; according to the abnormal development speed, the abnormal development direction and the abnormal influence range, the abnormal development prediction result is generated.

[0057] In a preferred embodiment, first, the obtained time series spatial distribution is analyzed, and by comparing the abnormal states at different time points, the rate of change of the abnormal degree is calculated to obtain the abnormal development speed. Among them, the abnormal development speed includes multiple parameters, such as the temperature rise rate, the deformation rate of the insulation layer, etc. At the same time, by performing spatial statistical analysis on the spatial distribution of the time series, the diffusion trend of the abnormal state in space is analyzed, the main direction of the abnormal development is identified, the abnormal development direction is obtained, and the spatial pattern of the abnormal extension along the line is formed. Subsequently, along the predicted abnormal development direction, combined with the characteristics of the abnormal type and the surrounding environmental factors, the areas that may be affected are calculated and extracted in the simulation environment to generate the abnormal impact range. Afterwards, according to the obtained abnormal development speed, abnormal development direction and abnormal impact range, the abnormal degree change curve over time, the three-dimensional visualization model of the abnormal impact range, the key time point prediction, the potential risk assessment, etc. are generated as the abnormal development prediction result, providing intuitive and comprehensive information support.

[0058] Through accurate simulation analysis and prediction of power line anomalies, taking into account the development speed, direction and specific spatial environment of the anomalies, personalized and contextualized prediction results are provided to provide support for the formulation of targeted maintenance strategies.

[0059] Furthermore, the embodiment of the present application also includes:

[0060] Calculate the associated confidence between the line abnormal point and the abnormal development prediction result to obtain the abnormal prediction confidence; if the abnormal prediction confidence is less than or equal to the preset confidence threshold, send a data supplement instruction to the master control drone; after receiving the data supplement instruction, the master control drone coordinates and guides the multiple detection drones to fly again to collect the multimodal supplement data of the line abnormal point; send the multimodal supplement data to the master control drone, summarize and transmit it back to the central processing platform, re-evolve the abnormality of the line abnormal point, and obtain updated abnormal development prediction results.

[0061] In a preferred embodiment, after obtaining the abnormal development prediction results, the central processing platform conducts a reliability assessment on them. First, the development of similar anomalies in the historical database is analyzed, and the similarity between the current abnormal development prediction results and historical cases is compared, which is used as a quantified abnormal prediction confidence, that is, the associated confidence, reflecting the reliability of the current abnormal development prediction results. Subsequently, the calculated abnormal prediction confidence is compared with a pre-set confidence threshold. When the confidence is lower than or equal to the confidence threshold, it indicates that the current abnormal development prediction results are uncertain or significantly different from historical experience. In this case, the central processing platform generates and sends a data supplement instruction to the master control drone to start an additional data collection process.

[0062] After receiving the data supplement instruction, the master drone coordinates multiple inspection drones to the location of the line abnormality point. Based on the previous abnormality type and abnormal development prediction results, a targeted supplementary data collection strategy is formulated, including adjusting sensor parameters, changing the collection angle or increasing the sampling frequency. Under the command of the master drone, multiple inspection drones synchronously execute this optimized data collection task to obtain more comprehensive and accurate multimodal supplementary data. Subsequently, the multimodal supplementary data collected by multiple inspection drones are transmitted to the master drone for preliminary summary and processing, and the master drone transmits the processed multimodal supplementary data back to the central processing platform. After receiving the new multimodal supplementary data, the central processing platform integrates it with the previous data, re-executes the abnormal evolution analysis, and generates updated abnormal development prediction results with higher accuracy and reliability.

[0063] Through evaluation based on historical experience, data supplementation and re-analysis, the accuracy and reliability of abnormal prediction are improved, which can effectively respond to complex and changeable abnormal situations of power lines and provide more reliable support for the safe operation and maintenance decisions of the power system.

[0064] In summary, the power line inspection method coordinated by a drone group provided in the embodiment of the present application has the following technical effects:

[0065] A three-dimensional equivalent model of the power inspection area is established. Multiple power inspection routes are planned according to the three-dimensional equivalent model, and multiple power inspection tasks are configured for each power inspection route. This provides an action guide for the coordinated inspection of the drone group to ensure full coverage and high efficiency of the inspection. According to the multiple power inspection tasks of each power inspection route, a drone group is configured. The drone group includes a master drone and multiple detection drones. The master drone is used to coordinate and control multiple detection drones to complete power inspection tasks, and to summarize and process the collected data of multiple detection drones. Multiple detection drones perform different types of detection tasks respectively. Through task division and coordination, the overall effectiveness of the drone group is brought into play and the inspection efficiency is improved. The drone group is controlled to perform power inspection tasks along the corresponding power inspection route, and the multimodal detection data of the power line is obtained in real time. When the master drone detects a line abnormality, the line abnormal point is locked, and the line abnormal point, multimodal detection data and abnormal detection results are sent to the central processing platform to achieve rapid discovery and positioning of line abnormalities and provide data for subsequent abnormal analysis. The central processing platform determines the 3D model of the abnormal area in the 3D equivalent model based on the abnormal points of the line, combines the abnormal detection results with the multimodal detection data to perform abnormal evolution on the abnormal points of the line, obtains the abnormal development prediction results, realizes the process from abnormal detection to abnormal warning, grasps the abnormal development law, and provides a decision-making basis for formulating maintenance strategies. According to the abnormal development prediction results, the power line maintenance is carried out on the abnormal points of the line, and predictive maintenance is adopted to reduce maintenance costs, reduce the impact on line operation, and improve the reliability of line operation.

[0066] Embodiment 2 is based on the same inventive concept as the power line inspection method coordinated by a drone group in the above embodiment. Figure 2 As shown, an embodiment of the present application provides a power line inspection device coordinated by a drone group, the device comprising:

[0067] The task planning unit 11 is used to establish a three-dimensional equivalent model of the power inspection area, plan multiple power inspection routes according to the three-dimensional equivalent model, and configure multiple power inspection tasks for each power inspection route.

[0068] The drone configuration unit 12 is used to configure a drone group according to multiple power inspection tasks for each power inspection route. The drone group includes a master control drone and multiple detection drones, wherein the master control drone is used to coordinately control multiple detection drones to complete power inspection tasks and summarize and process the collected data of multiple detection drones. Multiple detection drones perform different types of detection tasks respectively.

[0069] The task execution unit 13 is used to control the drone group to perform the power inspection task along the corresponding power inspection route, obtain the multimodal detection data of the power line in real time, and when the master control drone detects a line abnormality, lock the line abnormal point, and send the line abnormal point, the multimodal detection data and the abnormal detection result to the central processing platform.

[0070] The abnormal evolution unit 14 is used for the central processing platform to determine the three-dimensional model of the abnormal area in the three-dimensional equivalent model according to the abnormal point of the line, and to perform abnormal evolution on the abnormal point of the line in combination with the abnormal detection result and the multimodal detection data to obtain the abnormal development prediction result.

[0071] The line maintenance unit 15 is used to perform power line maintenance on the abnormal point of the line according to the abnormal development prediction result.

[0072] Furthermore, the task execution unit 13 includes the following execution steps:

[0073] For the first power inspection route, traverse the multiple power inspection tasks and determine the first power inspection task; extract the first task execution point in the first power inspection task, control the drone group to fly to the first task execution point, wherein the first task execution point corresponds to the first power line to be inspected; according to the first power inspection task, use the multiple detection drones to synchronously perform power inspection on the first power line to be inspected to obtain multimodal detection data; transmit the multimodal detection data to the master control drone, perform anomaly detection on the multimodal detection data, and when a line abnormality is detected, use the first task execution point as the line abnormality point.

[0074] Furthermore, the task execution unit 13 further includes the following execution steps:

[0075] According to the first power line to be inspected, the line model of the three-dimensional equivalent model is copied to obtain a first three-dimensional power line, wherein the first three-dimensional power line represents a normal state of the first power line to be inspected; before the power inspection task, the first three-dimensional power line is pre-stored in the master control drone; after the master control drone receives the multimodal detection data, the first three-dimensional power line is retrieved to perform abnormality detection on the multimodal detection data.

[0076] Furthermore, the task execution unit 13 further includes the following execution steps:

[0077] Based on the first three-dimensional power line, a multimodal feature template of the first power line to be inspected in a normal state is extracted, and multiple modal normal feature libraries are constructed; the multimodal detection data is compared with the multiple modal normal feature libraries respectively, and the feature deviations of different types of detections are calculated to obtain multiple feature deviations; the deviation thresholds of different types of detections are extracted, and it is determined whether multiple feature deviations meet the corresponding deviation thresholds; if the multiple feature deviations all meet the corresponding deviation thresholds, it is determined that the state of the first power line to be inspected is normal; if any feature deviation among the multiple feature deviations does not meet the corresponding deviation threshold, it is determined that the state of the first power line to be inspected is abnormal.

[0078] Furthermore, the abnormal evolution unit 14 includes the following execution steps:

[0079] In the three-dimensional equivalent model, the three-dimensional spatial coordinates of the abnormal point of the line are obtained; with the three-dimensional spatial coordinates as the center, a three-dimensional buffer zone of a preset radius is established, and the three-dimensional equivalent model within the three-dimensional buffer zone is extracted to generate a three-dimensional model of the abnormal area; according to the abnormality detection result, the abnormality type of the abnormal point of the line is obtained, and according to the abnormality type, the corresponding abnormality evolution model is matched in the abnormality evolution knowledge base; based on the abnormality detection result and the multimodal detection data, the dynamic change process of the abnormal state over time is simulated through the abnormality evolution model to obtain the time series spatial distribution of the abnormal state; according to the time series spatial distribution, the abnormal development prediction result is generated.

[0080] Furthermore, the abnormal evolution unit 14 includes the following execution steps:

[0081] Based on the spatial distribution of the time series, the rate of change of the line abnormal points over time is calculated to obtain the abnormal development speed; the main direction of the change of the line abnormal points with the spatial distribution is counted to obtain the abnormal development direction; along the abnormal development direction, in the three-dimensional model of the abnormal area, the abnormal influence range is extracted; according to the abnormal development speed, the abnormal development direction and the abnormal influence range, the abnormal development prediction result is generated.

[0082] Furthermore, the embodiment of the present application also includes a supplementary evolution unit, which includes the following execution steps:

[0083] Calculate the associated confidence between the line abnormal point and the abnormal development prediction result to obtain the abnormal prediction confidence; if the abnormal prediction confidence is less than or equal to the preset confidence threshold, send a data supplement instruction to the master control drone; after receiving the data supplement instruction, the master control drone coordinates and guides the multiple detection drones to fly again to collect the multimodal supplement data of the line abnormal point; send the multimodal supplement data to the master control drone, summarize and transmit it back to the central processing platform, re-evolve the abnormality of the line abnormal point, and obtain updated abnormal development prediction results.

[0084] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0085] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these changes and variations.

Claims

1. A method for power line inspection coordinated by a drone group, characterized in that: include: Establishing a three-dimensional equivalent model of the power inspection area, planning multiple power inspection routes according to the three-dimensional equivalent model, and configuring multiple power inspection tasks for each power inspection route; According to the multiple power inspection tasks of each power inspection route, a drone group is configured, and the drone group includes a master control drone and multiple detection drones, wherein the master control drone is used to coordinate and control multiple detection drones to complete the power inspection tasks, and summarize and process the collected data of multiple detection drones, and the multiple detection drones respectively perform different types of detection tasks; Control the drone group to perform power inspection tasks along the corresponding power inspection route, obtain multimodal detection data of the power line in real time, and when the master drone detects a line abnormality, lock the line abnormal point, and send the line abnormal point, the multimodal detection data and the abnormal detection result to the central processing platform; The central processing platform determines a three-dimensional model of an abnormal area in a three-dimensional equivalent model according to the abnormal point of the line, performs abnormal evolution on the abnormal point of the line in combination with the abnormal detection result and the multimodal detection data, and obtains an abnormal development prediction result; Power line maintenance is performed on the abnormal point of the line according to the abnormal development prediction result.

2. The method for power line inspection using a drone group according to claim 1, characterized in that: Acquire multi-modal detection data of power lines in real time. When the master control drone detects a line abnormality, it locks the line abnormal point, including: For the first power inspection route, traverse the multiple power inspection tasks to determine the first power inspection task; Extracting a first task execution point in the first power inspection task, and controlling the drone group to fly to the first task execution point, wherein the first task execution point corresponds to a first power line to be inspected; According to the first power inspection task, using the multiple inspection drones to synchronously perform power inspection on the first power line to be inspected to obtain multimodal inspection data; The multimodal detection data is transmitted to the master control drone, and anomaly detection is performed on the multimodal detection data. When a line abnormality is detected, the first task execution point is used as a line abnormality point.

3. The method for power line inspection using a drone group according to claim 2 is characterized in that: The multimodal detection data is transmitted to the master control drone, and anomaly detection is performed on the multimodal detection data, including: According to the first power line to be inspected, copying the line model of the three-dimensional equivalent model to obtain a first three-dimensional power line, wherein the first three-dimensional power line represents a normal state of the first power line to be inspected; Before the power inspection task, the first three-dimensional power line is pre-stored in the master control drone; After receiving the multimodal detection data, the master control drone retrieves the first three-dimensional power line and performs abnormality detection on the multimodal detection data.

4. The method for power line inspection using a drone group as claimed in claim 3 is characterized in that: After receiving the multimodal detection data, the master control drone retrieves the first three-dimensional power line and performs abnormality detection on the multimodal detection data, including: Based on the first three-dimensional power line, extract a multi-modal feature template of the first power line to be inspected in a normal state, and construct multiple modal normal feature libraries; Comparing the multimodal detection data with the multiple modal normal feature libraries respectively, calculating the feature deviations of different types of detections, and obtaining multiple feature deviations; Extract the deviation thresholds of different types of detection and determine whether the deviations of multiple features meet the corresponding deviation thresholds; If the plurality of characteristic deviations all meet the corresponding deviation thresholds, it is determined that the state of the first power line to be inspected is normal; If any characteristic deviation among the multiple characteristic deviations does not satisfy the corresponding deviation threshold, it is determined that the state of the first power line to be inspected is abnormal.

5. The method for power line inspection using a drone group as claimed in claim 1, characterized in that: The central processing platform determines a three-dimensional model of an abnormal area in a three-dimensional equivalent model according to the abnormal point of the line, performs abnormal evolution on the abnormal point of the line in combination with the abnormal detection result and the multimodal detection data, and obtains an abnormal development prediction result, including: In the three-dimensional equivalent model, obtaining the three-dimensional spatial coordinates of the line abnormal point; Taking the three-dimensional space coordinates as the center, establishing a three-dimensional buffer zone with a preset radius, extracting a three-dimensional equivalent model within the three-dimensional buffer zone, and generating a three-dimensional model of the abnormal area; According to the anomaly detection result, the anomaly type of the line anomaly point is obtained, and according to the anomaly type, a corresponding anomaly evolution model is matched in an anomaly evolution knowledge base; Based on the anomaly detection result and the multimodal detection data, the anomaly evolution model is used to simulate the dynamic change process of the anomaly state over time to obtain the time series spatial distribution of the anomaly state; According to the spatial distribution of the time series, an abnormal development prediction result is generated.

6. The method for power line inspection using a drone group as claimed in claim 5, characterized in that: According to the spatial distribution of the time series, abnormal development prediction results are generated, including: Based on the spatial distribution of the time series, the rate at which the abnormal point of the line changes over time is calculated to obtain the abnormal development speed; Counting the main directions of the abnormal points on the line changing with spatial distribution to obtain the abnormal development direction; Extracting the impact range of the anomaly in the three-dimensional model of the anomaly region along the anomaly development direction; An abnormal development prediction result is generated according to the abnormal development speed, the abnormal development direction and the abnormal impact range.

7. The method for power line inspection using a drone group as claimed in claim 1, characterized in that: The method further comprises: Calculating the correlation confidence between the line abnormal point and the abnormal development prediction result to obtain the abnormal prediction confidence; If the abnormal prediction confidence is less than or equal to the preset confidence threshold, a data supplement instruction is sent to the master control drone; After receiving the data supplementation instruction, the master control drone coordinates and guides the multiple detection drones to fly and re-collect the multi-modal supplementary data of the abnormal points of the line; The multimodal supplementary data is sent to the master control drone, and then transmitted back to the central processing platform after being summarized, and the abnormal evolution of the line abnormal points is re-performed to obtain updated abnormal development prediction results.

8. A power line inspection device coordinated by an unmanned aerial vehicle group, characterized in that: A method for conducting a power line inspection using a drone group as described in any one of claims 1 to 7, comprising: A task planning unit, the task planning unit is used to establish a three-dimensional equivalent model of the power inspection area, plan multiple power inspection routes according to the three-dimensional equivalent model, and configure multiple power inspection tasks for each power inspection route; A drone configuration unit, the drone configuration unit is used to configure a drone group according to multiple power inspection tasks of each power inspection route, the drone group includes a master control drone and multiple detection drones, wherein the master control drone is used to coordinately control multiple detection drones to complete power inspection tasks, and summarize and process the collected data of multiple detection drones, and the multiple detection drones respectively perform different types of detection tasks; A task execution unit, the task execution unit is used to control the drone group to perform the power inspection task along the corresponding power inspection route, obtain the multimodal detection data of the power line in real time, and when the master control drone detects a line abnormality, lock the line abnormal point, and send the line abnormal point, the multimodal detection data and the abnormal detection result to the central processing platform; An abnormality evolution unit, the abnormality evolution unit is used for the central processing platform to determine the three-dimensional model of the abnormal area in the three-dimensional equivalent model according to the abnormal point of the line, and to perform abnormal evolution on the abnormal point of the line in combination with the abnormality detection result and the multimodal detection data to obtain the abnormal development prediction result; A line maintenance unit is used to perform power line maintenance on the abnormal point of the line according to the abnormal development prediction result.

Images