A substation inspection unmanned aerial vehicle inspection path planning method and system

Abstract

The application discloses a substation inspection unmanned aerial vehicle inspection path planning method and system, the method comprising: obtaining point cloud data of a substation, and constructing a three-dimensional point cloud model of the substation; receiving an inspection instruction for a target inspection subject, obtaining a starting point and an ending point of an unmanned aerial vehicle, and generating an initial inspection path; receiving power frequency electric field intensity data and power frequency magnetic field intensity data of a to-be-tested point of the substation, dividing the substation into m electromagnetic field regions, and the m electromagnetic field regions comprising at least one strong electromagnetic field region; obtaining communication parameters of the unmanned aerial vehicle, and determining a safe operation distance of the unmanned aerial vehicle in each strong electromagnetic field region; adjusting the initial inspection path according to the three-dimensional point cloud model and the safe operation distance of each strong electromagnetic field region to obtain a final inspection path; and sending the final inspection path to the unmanned aerial vehicle. The application is used for effectively reducing the risk of losing control of the unmanned aerial vehicle in the substation with a complex electromagnetic environment, and improving safety.

Description

Technical Field

[0001] This application relates to the field of path planning, and in particular to a method and system for planning the inspection path of a substation inspection drone. Background Technology

[0002] With the continuous development and expansion of power systems, substation inspection has become increasingly important and complex. Traditional manual inspection methods face problems such as low efficiency, high safety risks, and limited coverage. To address these issues, drone inspection technology has emerged as an important means of substation inspection. Drone inspection offers advantages such as high flexibility, high efficiency, and the ability to reach areas difficult for personnel to access, significantly improving the quality and efficiency of inspections.

[0003] However, substations present complex environments with numerous high-voltage devices and intricate electromagnetic fields, posing significant challenges to drone inspections. The strong electromagnetic fields within substations can not only affect the drone's communication and navigation systems but also potentially damage the drone itself. Therefore, ensuring both effective inspections and safe drone operation has become a crucial issue for drone inspection technology in substations.

[0004] Traditional drone route planning methods primarily focus on obstacle avoidance and coverage. These methods are typically based on 3D models or maps of substations, using various algorithms to generate inspection paths. A common algorithm is the artificial potential field method, which sets the target point as an attractive potential field and obstacles as repulsive potential fields. The drone moves within this virtual potential field, acting under the combined influence of attractive and repulsive forces, ultimately forming a path that avoids obstacles.

[0005] However, traditional UAV route planning methods have significant shortcomings when dealing with the complex electromagnetic environment of substations, as they do not take into account the intricate electromagnetic conditions within substations. Strong electromagnetic fields can interfere with the UAV's communication system, leading to control signal loss or degraded communication quality, increasing the risk of the UAV going out of control.

[0006] Therefore, new path planning methods need to be developed to achieve safer and more efficient unmanned substation inspections. Summary of the Invention

[0007] This application provides a method and system for planning the inspection path of a substation inspection drone, which can effectively reduce the risk of drones going out of control in substations with complex electromagnetic environments and improve safety.

[0008] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0009] Firstly, a method for planning the inspection path of a substation inspection drone is provided, applied to a central control unit. The central control unit is connected to the drone, and the drone is equipped with an electromagnetic detection device for detecting power frequency electric field strength and power frequency magnetic field strength. The method includes:

[0010] The drone acquires point cloud data of the substation and constructs a three-dimensional point cloud model of the substation based on the point cloud data.

[0011] In response to receiving an inspection command for the target inspection subject, the start point and end point of the UAV are obtained, and an initial inspection path is generated based on the three-dimensional point cloud model, the start point, the end point and the preset flight altitude, and the target inspection subject is located on the initial inspection path;

[0012] In response to receiving the power frequency electric field strength data and power frequency magnetic field strength data of the test point of the substation transmitted by the UAV, the substation is divided into m electromagnetic field regions according to the power frequency electric field strength data and the power frequency magnetic field strength data of the test point, where m is an integer greater than 1, and the m electromagnetic field regions include at least one strong electromagnetic field region, at least one standard electromagnetic field region and / or at least one weak electromagnetic field region.

[0013] The communication parameters of the UAV are obtained, and the safe operating distance of the UAV in each strong electromagnetic field region is determined based on the power frequency electric field strength data, the power frequency magnetic field strength data and the communication parameters in each strong electromagnetic field region.

[0014] Based on the three-dimensional point cloud model and the safe operating distance for each strong electromagnetic field region, the initial inspection path is adjusted to obtain the final inspection path;

[0015] The final inspection path is sent to the drone so that the drone can inspect the substation according to the final inspection path.

[0016] In one possible implementation of the first aspect, generating the initial inspection path based on the three-dimensional point cloud model, the starting point, the ending point, and the preset flight altitude includes:

[0017] A point cloud processing network is used to perform semantic segmentation on the 3D point cloud model, so as to divide the 3D point cloud model into n semantic regions, wherein each semantic region represents an element type;

[0018] A pattern matching algorithm is used to compare the n semantic regions with a pre-built standard template library of substation equipment structures to determine the element features corresponding to each semantic region;

[0019] Based on a pre-defined knowledge graph, determine the spatial and functional relationships between each element in the substation;

[0020] Obtain the 2D design document of the substation, determine the layout rules of the substation based on the 2D design document, and determine the properties of each element based on the layout rules of the substation.

[0021] The element type, element features, spatial and functional relationships between each element, and properties of each element corresponding to each semantic region are mapped to the three-dimensional point cloud model to annotate each element in the three-dimensional point cloud model.

[0022] The target inspection subject is mapped to the elements marked in the three-dimensional point cloud model to determine the target elements in the three-dimensional point cloud model;

[0023] The starting point, the ending point, and the flight altitude are mapped to the three-dimensional point cloud model to obtain the UAV starting point and UAV ending point in the three-dimensional point cloud model.

[0024] An initial inspection path is generated in the three-dimensional point cloud model using a preset path planning algorithm based on the UAV's starting point, the UAV's ending point, and the target element.

[0025] In another possible implementation of the first aspect, the steps for constructing the substation equipment structure standard template library include:

[0026] Acquire on-site images of the substation, extract features from the on-site images to obtain the geometric and texture features of each element in the substation, including buildings and equipment;

[0027] The contours and key points of each element are identified by using a preset edge detection algorithm and a preset corner detection algorithm.

[0028] Based on the geometric features, texture features, contours and key points of each element, a standard template library for substation equipment structures is constructed.

[0029] In another possible implementation of the first aspect, dividing the substation into m electromagnetic field regions based on the power frequency electric field strength data and the power frequency magnetic field strength data of the test point includes:

[0030] Using a preset interpolation algorithm, the substation is interpolated based on the power frequency electric field strength data and the power frequency magnetic field strength data of all the test points to obtain an electromagnetic field strength distribution map of the substation. The electromagnetic field strength distribution map includes multiple interpolation points and / or test points.

[0031] The interpolation points and / or test points of the power frequency electric field intensity data that are greater than the preset electric field intensity threshold and the power frequency magnetic field intensity data that are greater than the preset magnetic field intensity threshold in the electromagnetic field intensity distribution map are summarized to obtain m electromagnetic field regions.

[0032] In another possible implementation of the first aspect, the communication parameters include communication signal frequency, antenna gain, bit error rate, and minimum acceptable signal strength. Determining the safe operating distance of the UAV in each of the strong electromagnetic field regions based on the power frequency electric field strength data, the power frequency magnetic field strength data, and the communication parameters includes:

[0033] For any given strong electromagnetic field region, the power frequency electric field strength data, power frequency magnetic field strength data, communication signal frequency, and antenna gain of each test point in the strong electromagnetic field region are input into a pre-constructed communication interference model to obtain the signal attenuation value of the UAV at each test point in the strong electromagnetic field region.

[0034] Based on the maximum signal attenuation value, the bit error rate, and the minimum acceptable signal strength, the threshold value of interference for the UAV in the strong electromagnetic field region is determined.

[0035] Based on the interference threshold, the safe operating distance of the UAV in the strong electromagnetic field region is determined.

[0036] In another possible implementation of the first aspect, determining the interference threshold of the UAV in the strong electromagnetic field region based on the maximum signal attenuation value, the bit error rate, and the minimum acceptable signal strength includes:

[0037] The minimum acceptable signal strength is obtained by adding the minimum acceptable signal strength to the maximum signal attenuation value;

[0038] The minimum acceptable intensity, the preset influence factor, and the preset safety margin are added together to obtain the critical value of interference of the UAV in the strong electromagnetic field region, wherein the influence factor is calculated based on the bit error rate;

[0039] Determining the safe operating distance of the UAV in the strong electromagnetic field region based on the interference threshold includes:

[0040] Using a preset spatial path loss calculation formula, the theoretical maximum communication distance of the UAV in the strong electromagnetic field region is calculated based on the interference threshold.

[0041] The physical layout of the substation is determined based on the three-dimensional point cloud model, and the environmental constraint distance of the UAV is determined based on the physical layout.

[0042] The safe operating distance of the UAV in the strong electromagnetic field region is obtained by multiplying the minimum value of the theoretical maximum communication distance and the environmental constraint distance by a preset safety factor.

[0043] In another possible implementation of the first aspect, adjusting the initial inspection path based on the three-dimensional point cloud model and the safe operating distance for each of the strong electromagnetic field regions to obtain the final inspection path includes:

[0044] The initial inspection path is divided into multiple path segments based on the m electromagnetic field regions, and the target path segment located in the strong electromagnetic field region is determined among the multiple path segments.

[0045] For each target path segment, a spherical safety region with the safe working distance as its radius is constructed in the three-dimensional point cloud model, and the center point of the target path segment is located at the center of the spherical safety region;

[0046] Determine whether the initial inspection path intersects with p of the spherical safety zones, where p is a positive integer;

[0047] If the initial inspection path intersects with p of the spherical safety zones, then determine the trajectory points on the initial inspection path that are located within the spherical safety zones;

[0048] For any given trajectory point, determine its corresponding replacement point, and convert all the trajectory points into their corresponding replacement points to obtain the final inspection path.

[0049] In another possible implementation of the first aspect, determining the corresponding replacement point for any given trajectory point includes:

[0050] For any given trajectory point, multiple candidate points are uniformly sampled on the spherical surface of the spherical safety region;

[0051] Among the multiple candidate points, the point that is closest to the trajectory point and is not within any of the spherical safe areas is selected as the replacement point corresponding to the trajectory point.

[0052] Secondly, this application provides a central control host, comprising:

[0053] The memory is configured to store instructions; and

[0054] The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the aforementioned inspection path planning method for the substation inspection drone.

[0055] Thirdly, this application provides an inspection path planning system for a substation inspection drone, comprising:

[0056] Central control unit;

[0057] The drone is connected to the central control host, and the drone is equipped with an electromagnetic detection device for detecting the power frequency electric field strength and the power frequency magnetic field strength.

[0058] The above technical solution first uses a drone to acquire point cloud data of the substation and construct a 3D point cloud model, providing a precise spatial information foundation for subsequent path planning. Upon receiving an inspection command, an initial inspection path is generated based on the drone's start and end points, the 3D point cloud model, and the preset flight altitude, ensuring the target inspection object is located on the path and guaranteeing basic inspection coverage. Next, the electromagnetic detection device on the drone collects real-time data on power frequency electric and magnetic field strength, dividing the substation into multiple electromagnetic field regions, including strong electromagnetic field regions, standard electromagnetic field regions, and weak electromagnetic field regions, accurately identifying potential high-risk areas. Subsequently, based on the drone's communication parameters and the specific electromagnetic field strength data for each strong electromagnetic field region, the safe operating distance of the drone in each region is calculated. This allows for dynamic adjustment of the drone's safe distance according to the actual electromagnetic environment, significantly improving inspection safety. Finally, based on the 3D point cloud model and the calculated safe operating distance, the initial inspection path was adjusted to obtain the final inspection path. This path not only considered the avoidance of physical obstacles but also fully accounted for the influence of the electromagnetic environment, thus generating an optimal path that ensures both inspection effectiveness and UAV safety. By considering electromagnetic field strength as a crucial factor, the communication quality and operational stability of the UAV in strong electromagnetic field environments were improved, and the risk of discharge from the UAV's metal fuselage or exposed components was reduced. Simultaneously, the overall inspection efficiency and data quality were enhanced. Furthermore, the dynamic path planning method based on real-time electromagnetic field strength data provides a more comprehensive safety risk assessment mechanism for UAV inspections of substations, effectively improving the safety and efficiency of the inspections.

[0059] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0060] Figure 1 A flowchart illustrating a method for planning the inspection path of a substation inspection drone, provided in an embodiment of this application;

[0061] Figure 2 Pseudocode for a breadth-first search provided in this application embodiment;

[0062] Figure 3 A schematic diagram of a spherical security area provided in an embodiment of this application;

[0063] Figure 4 This is a schematic diagram of the inspection path planning system for a substation inspection drone provided in an embodiment of this application. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0065] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0066] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0067] Example 1

[0068] Figure 1 The illustration schematically shows a flowchart of an inspection path planning method for a substation inspection drone according to an embodiment of this application. Figure 1 As shown in the figure, this application provides a method for planning the inspection path of a substation inspection drone, which is applied to a central control host. The central control host is connected to the drone, and the drone is equipped with an electromagnetic detection device. The electromagnetic detection device is used to detect the power frequency electric field strength and the power frequency magnetic field strength. The method may include the following steps.

[0069] S110. Obtain point cloud data of the substation through drones, and construct a three-dimensional point cloud model of the substation based on the point cloud data.

[0070] S120. In response to receiving the inspection instruction for the target inspection subject, the drone's starting point and ending point are obtained, and an initial inspection path is generated based on the three-dimensional point cloud model, the starting point, the ending point and the preset flight altitude. The target inspection subject is located on the initial inspection path.

[0071] S130. In response to receiving the power frequency electric field strength data and power frequency magnetic field strength data of the test point of the substation transmitted by the UAV, the substation is divided into m electromagnetic field regions according to the power frequency electric field strength data and power frequency magnetic field strength data of the test point, where m is an integer greater than 1, and the m electromagnetic field regions include at least one strong electromagnetic field region, at least one standard electromagnetic field region and / or at least one weak electromagnetic field region.

[0072] S140. Obtain the communication parameters of the UAV, and determine the safe operating distance of the UAV in each strong electromagnetic field area based on the power frequency electric field strength data, power frequency magnetic field strength data and communication parameters.

[0073] S150. Based on the three-dimensional point cloud model and the safe working distance of each strong electromagnetic field area, adjust the initial inspection path to obtain the final inspection path.

[0074] S160. Send the final inspection path to the drone so that the drone can inspect the substation according to the final inspection path.

[0075] In this embodiment, a high-precision laser scanner or depth camera mounted on a drone is first used to perform a comprehensive scan and data acquisition of the substation. The laser scanner measures the three-dimensional coordinates of points on the object's surface by emitting a laser beam and receiving reflected signals, while the depth camera acquires depth information of the scene using structured light or time-of-flight methods. The drone flies along a preset flight path to ensure coverage of the entire substation area, while maintaining a stable flight attitude to improve the accuracy of data acquisition.

[0076] In practice, the following approach can be adopted: First, design a grid-like flight path covering the entire substation to ensure that the UAV can perform a comprehensive scan of the substation from multiple angles. Second, set appropriate scanning resolution and overlap rate, typically achieving centimeter-level resolution and maintaining an overlap rate of over 60% to ensure data integrity and accuracy. Then, execute the automated flight mission, collecting point cloud data in real time during the flight.

[0077] After data acquisition, the raw point cloud data is imported into point cloud processing software, such as CloudCompare. First, data cleaning is performed to remove noise and outliers. Next, registration is performed, stitching together point cloud data obtained from multiple scans into a complete point cloud model. Then, noise reduction and simplification are performed to reduce data volume while retaining key features. Finally, classification and segmentation are performed to identify various equipment and structures in the substation, ultimately resulting in a 3D point cloud model. This model not only contains the geometric information of the substation but also includes attribute information such as color and reflectivity, providing accurate spatial references for subsequent path planning. It can precisely reflect the substation's layout, equipment location, and size, aiding in obstacle avoidance and precise positioning.

[0078] After receiving the inspection instruction for the target inspection subject, the drone's starting point and ending point are obtained. Based on the 3D point cloud model, the starting point, ending point, and the preset flight altitude, an initial inspection path is generated. The target inspection subject is located on the initial inspection path. The inspection instruction for the target inspection subject is issued by the staff. The staff can click on the equipment or building to be inspected on the screen of the central control host. The equipment or building to be inspected is then the target inspection subject.

[0079] Specifically, an initial inspection path can be generated based on the constructed 3D point cloud model, combined with a path planning algorithm. First, the takeoff and landing points of the drone are obtained. The drone's start and end points can be manually set; that is, staff can set the drone's start and end points via the central control unit. The start and end points can be a single point. Then, based on the received inspection instructions, the target equipment or area to be inspected is determined. Next, a path planning algorithm can be used to find a path in 3D space from the start point to the end point, passing through the target inspection object.

[0080] In practical implementation, the following method can be adopted: First, mark the takeoff point, landing point, and the location of the target inspection body in the 3D point cloud model. Then, set a preset flight altitude, which can usually be set to be 5 to 10 meters higher than the highest equipment in the substation. Next, discretize the 3D point cloud model into a 3D grid map, and each grid can be marked as passable or an obstacle.

[0081] A pre-defined path planning algorithm is employed. Starting from the origin, the algorithm progressively explores the surrounding grid cells, calculating the estimated total cost (including the distance already traveled and the estimated remaining distance) from the origin through the current grid cell to the destination. The algorithm prioritizes exploring the grid cells with the lowest total cost until a path to the destination is found. During this process, the location of the target inspection object is also considered to ensure that the path passes through it.

[0082] To improve the smoothness and flyability of the path, optimization can be performed after the initial path is obtained. For example, Bézier curves or spline curves can be used to smooth the path and remove sharp turns. The initial inspection path meets the following characteristics: 1) it starts from a designated takeoff point and arrives at a designated landing point; 2) it passes through all target equipment or areas that need to be inspected; 3) it maintains a preset safe flight altitude; 4) it avoids obstacles in the substation; 5) the path is relatively smooth and conforms to the flight characteristics of the UAV. The path generated in this way can ensure the completion of the inspection task while maximizing the flight safety of the UAV.

[0083] In response to receiving the power frequency electric field strength data and power frequency magnetic field strength data of the substation test point transmitted by the UAV, the substation is divided into m electromagnetic field regions based on the power frequency electric field strength data and power frequency magnetic field strength data of the test point, where m is an integer greater than 1, and the m electromagnetic field regions include at least one strong electromagnetic field region, at least one standard electromagnetic field region and / or at least one weak electromagnetic field region.

[0084] Specifically, based on electromagnetic field data collected by drones, the electromagnetic environment of the substation area is classified and divided. Power frequency electric and magnetic fields are the main sources of electromagnetic interference in substations, and their intensity directly affects the communication quality of drones and the operational stability of equipment. In practice, the following approach can be adopted: First, during flight, the drone continuously collects power frequency (typically 50Hz or 60Hz) electric and magnetic field strength data using its onboard electromagnetic detection device. This data is correlated with the drone's GPS location information to form a dataset containing spatial location and electromagnetic field strength. The data acquisition frequency can be set to multiple times per second to ensure data continuity and integrity. The electromagnetic detection device can be a power frequency electromagnetic field measuring instrument, used to measure the power frequency electromagnetic field strength generated by power systems and electrical equipment, operating based on the principle of electromagnetic induction. For electric field measurements, electric field probes are typically used; for magnetic field measurements, magnetic field probes are used. These probes can convert the electric or magnetic field in the environment into measurable electrical signals.

[0085] Upon receiving the electromagnetic field data, preprocessing is first performed, including outlier removal and smoothing. Then, an interpolation algorithm (such as Kriging interpolation) is used to extend the discrete measurement point data to the entire substation area, forming a continuous electromagnetic field intensity distribution map.

[0086] According to national standards or industry specifications, threshold values ​​for electromagnetic field strength are set to divide substation areas into three categories: strong, standard, and weak electromagnetic field regions. For example, areas with an electric field strength greater than 10 kV / m or a magnetic induction intensity greater than 0.5 mT can be classified as strong electromagnetic field regions; areas with an electric field strength between 4 and 10 kV / m or a magnetic induction intensity between 0.1 and 0.5 mT can be classified as standard electromagnetic field regions; and areas below these values ​​can be classified as weak electromagnetic field regions.

[0087] The interpolated electromagnetic field intensity distribution map was segmented using an image segmentation algorithm to obtain different electromagnetic field regions. Each region was assigned a unique identifier, and its boundary coordinates and average electromagnetic field intensity value were recorded.

[0088] The final result is a detailed electromagnetic environment distribution map of the substation, containing multiple clearly defined electromagnetic field regions. This map not only reflects the spatial distribution characteristics of the electromagnetic field within the substation but also provides the specific intensity level of each region.

[0089] The communication parameters of the UAV are obtained, and the safe operating distance of the UAV in each strong electromagnetic field area is determined based on the power frequency electric field strength data, power frequency magnetic field strength data, and communication parameters.

[0090] Specifically, based on the characteristics of the UAV's communication system and the features of the strong electromagnetic field environment, the minimum distance at which the UAV can safely approach a strong electromagnetic field area is calculated while ensuring communication quality.

[0091] First, it is necessary to obtain the key communication parameters of the UAV, including but not limited to: communication frequency, transmit power, receive sensitivity, antenna gain, modulation method, and coding method. These parameters determine the anti-interference capability and signal transmission characteristics of the UAV communication system. Then, the impact of strong electromagnetic fields on the UAV communication system needs to be analyzed. Although power frequency electromagnetic fields (50Hz or 60Hz) are low in frequency, their intensity is very high, and they may interfere with the UAV communication system through electromagnetic induction, intermodulation, and other means. This interference may lead to problems such as signal distortion, increased bit error rate, and communication link interruption. In practical operation, the following methods can be used to determine the safe operating distance:

[0092] First, establish a model relating electromagnetic field strength to distance. Ideally, electric field strength decreases inversely with the square of the distance, while magnetic field strength decreases inversely with the cube of the distance. Second, calculate the impact of electromagnetic interference on the communication system. This impact can be quantified using signal-to-noise ratio (SNR) or signal-to-interference ratio (SIR). For example, the SIR can be calculated using the following formula:

[0093] SIR = P s -P i -Lp ;

[0094] Where Ps is the signal power transmitted by the UAV (dBm), Pi is the power of the interference signal (dBm), and Lp is the path loss (dB).

[0095] Then, based on the performance indicators of the UAV communication system (such as the minimum acceptable signal-to-interference ratio) and the above calculation results, the minimum distance that can meet the communication quality requirements is derived in reverse. This distance is the preliminary safe operating distance.

[0096] Considering the complexity of actual situations and potential uncertainties, this embodiment adds a safety margin to the calculated minimum distance. For example, the actual safe operating distance can be set to 1.2 times the calculated minimum distance.

[0097] Finally, for each region with a strong electromagnetic field, the above calculation process is repeated, as the electromagnetic field strength may vary significantly between different regions. This results in a set of safe operating distances for each region with a strong electromagnetic field. These safe operating distances ensure both effective inspection and maximum flight safety.

[0098] Based on the 3D point cloud model and the safe operating distance for each strong electromagnetic field area, the initial inspection path is adjusted to obtain the final inspection path.

[0099] Specifically, firstly, a high-precision 3D point cloud model obtained using technologies such as laser scanning or photogrammetry provides a detailed spatial information foundation for the entire adjustment process. This model contains key data such as the geometry, dimensions, and location of the inspection environment. Simultaneously, the safe operating distances for each strong electromagnetic field area determined through electromagnetic field strength measurements and safety assessments provide crucial constraints for path adjustment.

[0100] The adjustment process begins by mapping the initial inspection path onto a 3D point cloud model. Then, for each strong electromagnetic field region, a spherical or cylindrical safety zone with a radius equal to the safe operating distance is constructed in the 3D model to visually clearly identify the hazardous areas to be avoided. Next, a path planning algorithm is used to adjust the initial path. This algorithm searches for feasible paths in 3D space while considering the constraint of avoiding safety zones. Specifically, the algorithm checks segment by segment whether the initial path intersects with any safety zones. If an intersection is found, alternative path segments that bypass the safety zones are searched. This process involves multiple iterations until a path that completely avoids all safety zones is found.

[0101] In practical implementation, Bézier curves or spline curves can be used to smooth path inflection points, ensuring that the UAV can fly smoothly along the path. Alternatively, a hierarchical optimization approach can be employed. First, a path avoiding all safe zones is quickly generated on a coarser grid. Then, based on this coarse path, local optimization is performed at a finer scale. This improves the algorithm's efficiency while maintaining safety.

[0102] The final inspection path is represented as a series of three-dimensional coordinate points or parametric curves. This data can be directly input into the navigation system of the inspection equipment, guiding the drone to complete the inspection task safely and efficiently. Simultaneously, this adjusted path can also be visualized in a three-dimensional point cloud model, facilitating operator review and necessary manual fine-tuning.

[0103] This embodiment is not only applicable to static environments, but can also dynamically adjust the route based on real-time monitoring data. For example, if the electromagnetic field strength in a certain area changes, the corresponding route can be quickly recalculated and adjusted to ensure that the inspection is always carried out within a safe range. This dynamic adaptability greatly enhances the robustness and practicality of the inspection system.

[0104] This embodiment first acquires point cloud data of the substation using a drone and constructs a 3D point cloud model, providing a precise spatial information foundation for subsequent path planning. Upon receiving an inspection command, an initial inspection path is generated based on the drone's start and end points, the 3D point cloud model, and the preset flight altitude, ensuring the target inspection object is located on the path and guaranteeing basic inspection coverage. Next, the electromagnetic detection device on the drone collects real-time data on power frequency electric and magnetic field strength, dividing the substation into multiple electromagnetic field regions, including strong electromagnetic field regions, standard electromagnetic field regions, and weak electromagnetic field regions, enabling accurate identification of potential high-risk areas. Subsequently, based on the drone's communication parameters and the specific electromagnetic field strength data for each strong electromagnetic field region, the safe operating distance of the drone in each strong electromagnetic field region is calculated. This allows for dynamic adjustment of the drone's safe distance according to the actual electromagnetic environment, significantly improving inspection safety. Finally, based on the 3D point cloud model and the calculated safe operating distance, the initial inspection path was adjusted to obtain the final inspection path. This path not only considered the avoidance of physical obstacles but also fully accounted for the influence of the electromagnetic environment, thus generating an optimal path that ensures both inspection effectiveness and UAV safety. By considering electromagnetic field strength as a crucial factor, the communication quality and operational stability of the UAV in strong electromagnetic field environments were improved, and the risk of discharge from the UAV's metal fuselage or exposed components was reduced. Simultaneously, the overall inspection efficiency and data quality were enhanced. Furthermore, the dynamic path planning method based on real-time electromagnetic field strength data provides a more comprehensive safety risk assessment mechanism for UAV inspections of substations, effectively improving the safety and efficiency of the inspections.

[0105] In one embodiment of this invention, an initial inspection path is generated based on a 3D point cloud model, a starting point, an ending point, and a preset flight altitude, including the following steps:

[0106] S210. A point cloud processing network is used to perform semantic segmentation on the 3D point cloud model, so as to divide the 3D point cloud model into n semantic regions, where each semantic region represents an element type.

[0107] S220. Use a pattern matching algorithm to compare the n semantic regions with a pre-built standard template library of substation equipment structures to determine the element features corresponding to each semantic region.

[0108] S230. Based on the preset knowledge graph, determine the spatial and functional relationships between each element in the substation;

[0109] S240. Obtain the 2D design document of the substation, determine the layout rules of the substation based on the 2D design document, and determine the properties of each element based on the layout rules of the substation.

[0110] S250. Map the element type, element features, spatial and functional relationships between each element, and the properties of each element to the 3D point cloud model to label each element in the 3D point cloud model.

[0111] S260. Map the target inspection subject to the elements marked in the 3D point cloud model to determine the target elements in the 3D point cloud model.

[0112] S270. Map the start point, end point, and flight altitude to a 3D point cloud model to obtain the UAV start point and UAV end point in the 3D point cloud model.

[0113] S280: Using a preset path planning algorithm, an initial inspection path is generated in the 3D point cloud model based on the UAV's starting point, ending point, and target elements.

[0114] Point cloud processing networks (hereinafter referred to as networks) are a type of deep learning technology. Their network architecture can be PointNet++ or PointCNN, used to process point cloud data. First, the raw point cloud data is converted into a format suitable for network input, typically including features such as the three-dimensional coordinates, normal vectors, and color information of the points. Then, the network extracts local and global features of the point cloud through multiple layers of convolution and pooling operations. Based on feature extraction, the network uses fully connected layers or deconvolutional layers to classify each point, assigning it to a predefined semantic category, such as transformer, switching equipment, or transmission line. This process requires multiple iterations to improve segmentation accuracy. Finally, each point is assigned a semantic label, forming n semantic regions. For example, in a substation point cloud model containing 1 million points, it might be segmented into 10 semantic regions, including transformer area, distribution equipment area, control room area, etc. Semantic segmentation can not only identify the main equipment and structure of the substation but also distinguish environmental elements such as the ground and vegetation, providing a rich semantic information foundation for subsequent path planning. This step gives the originally chaotic point cloud data a clear meaning, greatly improving the targeting and efficiency of subsequent processing.

[0115] Next, a pattern matching algorithm is used to compare the semantic regions with a pre-built standard template library of substation equipment structures. First, a template library containing standard 3D models of various substation equipment is constructed. These standard 3D models include detailed geometry, size proportions, and feature point information. Then, feature descriptors, such as SIFT (Scale-Invariant Feature Transform) or FPFH (Fast Point Feature Histograms), are extracted for each semantic region. Next, algorithms such as ICP (Iterative Closest Point) are used to register and match the semantic regions with the models in the template library. During the matching process, considering potential deformation or partial occlusion of actual equipment, a tolerance threshold can be set to allow for a certain degree of incomplete matching. For example, for a semantic region identified as a "transformer," it is first attempted to match it with various transformer models in the template library. By calculating the similarity of feature points and geometric consistency, the best matching model is found. If the matching degree exceeds a preset threshold (e.g., 85%), the specific equipment type and model of the semantic region are confirmed. It can not only determine the major categories of equipment (such as circuit breakers, disconnect switches, etc.), but also identify specific models and specifications. Through this step, each semantic region is given more detailed and accurate element features, greatly improving the targeting and efficiency of inspections.

[0116] Based on a pre-defined knowledge graph, the spatial and functional relationships between each element in the substation are determined. Specifically, the knowledge graph is a comprehensive knowledge base containing the substation equipment topology, functional associations, and spatial layout rules. First, a graph structure containing nodes (representing equipment) and edges (representing relationships) needs to be constructed. Nodes contain equipment attribute information, such as type, model, and rated parameters; edges represent physical connections, electrical connections, or spatial relative positions between equipment. For example, the electrical connection and protection relationship between transformers and circuit breakers is represented by edges with specific attributes in the knowledge graph. Next, graph traversal algorithms (such as depth-first search or breadth-first search) are used to query and reason about the knowledge graph. For example, given a high-voltage switch, graph traversal can be used to find all connected equipment and their functional relationships. Simultaneously, spatial relationship reasoning rules (such as "transformers are usually located downstream of disconnectors") can be used to verify and supplement the spatial layout information extracted from point cloud data.

[0117] Furthermore, the knowledge graph also includes logical relationships between devices, such as protection sequences and operation orders, which helps in understanding the substation's operating logic. This step not only establishes a complete relationship network of devices within the substation but also verifies and corrects any identification errors that may have occurred in the preceding steps.

[0118] Obtain the 2D design documents of the substation and determine the layout rules and element properties based on them. First, the 2D design documents need to be parsed, including but not limited to CAD drawings, floor plans, and electrical system diagrams. During parsing, image processing and optical character recognition (OCR) technologies are used to extract key information, such as equipment location coordinates, connection relationships, and technical parameters. Then, this information is compared and fused with the information extracted from the 3D point cloud model in the previous steps. For example, if the 2D drawings indicate that a specific type of circuit breaker should be located at a certain location, the 3D model is checked to ensure that the corresponding location of the equipment is indeed identified. This comparison can identify potential equipment replacements or layout changes, ensuring the timeliness of the data.

[0119] Next, based on the layout information in the 2D document, the overall layout rules of the substation are extracted, such as the minimum safe distance between equipment and the division of electrical isolation zones. These rules are encoded into a series of constraints for subsequent path planning. Simultaneously, according to the technical specifications in the design document, the specific properties of each element are determined, such as voltage level, rated current, and insulation level. For example, a 500kV main transformer can be marked as a high-risk area.

[0120] The process maps element types, features, relationships, and properties to a 3D point cloud model for annotation. First, a multi-level data structure is established to store and associate various information. At the bottom layer is the raw point cloud data, where each point contains its 3D coordinates and possible color information. Based on this, semantic segmentation results are added, dividing the point cloud into different semantic regions. Then, specific device information obtained through pattern matching is associated with these semantic regions, including device type and model. Next, spatial and functional relationships derived from a knowledge graph are added, represented as connecting lines or annotations between devices. Finally, property information extracted from 2D documents is added to the corresponding devices.

[0121] For example, for a semantic area identified as a circuit breaker, its type (e.g., SF6 circuit breaker), model (e.g., a specific model from ABB), other connected equipment (e.g., adjacent disconnect switches and busbars), and its voltage level, rated current, and other properties will be labeled. In practical applications, this labeling can employ various visual methods such as color coding, text labels, and icons to facilitate human-computer interaction and information retrieval.

[0122] The target inspection subject is mapped to the elements marked in the 3D point cloud model to determine the target elements in the 3D point cloud model.

[0123] First, the inspection command is parsed to extract the specific objects to be inspected. This could be a type of equipment (e.g., all circuit breakers), a specific area (e.g., the main transformer area), or a specific piece of equipment (e.g., main transformer No. 1). Then, a search and matching process is performed within the labeled 3D model. Specifically, equipment types are matched semantically, then the specific location is determined spatially, and finally, detailed information is confirmed at the attribute level. For example, if the inspection target is "all circuit breakers in the 500kV distribution area," the 500kV distribution area is first located in the model, and then all elements labeled as circuit breakers within that area are identified. During this process, the importance and current status of the equipment can also be considered. For example, if a circuit breaker has recently recorded anomalies, it might be given a higher inspection priority.

[0124] The starting point, ending point, and flight altitude are mapped to a 3D point cloud model. Specifically, the given starting and ending point coordinates are converted into coordinates in the 3D point cloud model, using a spatial transformation matrix to ensure accurate positioning. For example, if the given starting point is GPS coordinates (longitude, latitude, and altitude), it can be converted into XYZ coordinates in the point cloud model. Next, the flight altitude mapping needs to consider the substation's terrain and building height. A plane parallel to the ground can be created in the entire 3D model, with its height equal to the given flight altitude plus the average ground height. This plane will serve as the UAV's primary flight layer, and its height can also be the highest equipment in the substation plus a preset height value (e.g., 5m). For example, if the specified flight altitude is 20 meters, and the average ground elevation of the substation is 100 meters, the flight plane will be set at an absolute height of 120 meters. Finally, the determined starting and ending point coordinates are stored as input parameters for UAV path planning.

[0125] A pre-defined path planning algorithm is used to generate an initial inspection path in a 3D point cloud model based on the UAV's starting point, ending point, and target elements. The path planning algorithm can be a heuristic search algorithm. Specifically, first, the 3D point cloud model is discretized into a grid or graph structure, where each grid point or node represents a possible flight position. Then, considering the special characteristics of the substation environment, constraints can be set, such as safe distances (maintaining a certain distance from high-voltage equipment), no-fly zones (e.g., above the control room), and flight altitude restrictions. Next, the path planning algorithm begins searching for feasible paths from the starting point to the ending point. In the path planning algorithm, the node with the lowest estimated cost is selected for expansion at each step, where the cost function includes the distance traveled and the estimated remaining distance. To ensure the path passes through all target elements, the algorithm needs to perform multiple iterations, treating intermediate target points as sub-targets and planning the path segment by segment. The path planning algorithm can be the A* algorithm.

[0126] The initial inspection path of this embodiment not only considers the shortest distance but also includes obstacle avoidance, providing a reliable technical foundation for UAVs to carry out efficient and safe inspection tasks in complex environments, and effectively improving the feasibility and efficiency of UAV inspection tasks.

[0127] In one embodiment of this example, the steps for constructing the substation equipment structure standard template library include:

[0128] S310. Obtain on-site images of the substation, extract features from the on-site images, and obtain the geometric and texture features of each element in the substation, including buildings and equipment.

[0129] S320: Employs preset edge detection algorithms and preset corner detection algorithms to identify the contour and key points of each element;

[0130] S330. Based on the geometric features, texture features, contours and key points of each element, construct a standard template library for substation equipment structures.

[0131] After acquiring on-site images of the substation, image preprocessing is performed first. This includes operations such as denoising, contrast enhancement, and illumination equalization. Denoising can be achieved using methods such as Gaussian filtering or median filtering to reduce random noise in the image. Contrast enhancement can employ histogram equalization techniques to make the gray-level distribution of the image more uniform, which is beneficial for subsequent feature extraction. Illumination equalization can eliminate the effects of uneven lighting caused by factors such as shooting time and weather conditions.

[0132] Next is image segmentation, which aims to separate different elements (such as buildings and equipment) in an image. Thresholding algorithms can be used. For each segmented element, geometric and texture features are extracted. Geometric features include area, perimeter, aspect ratio, and roundness. For example, area can be obtained by calculating the number of pixels occupied by the element, and perimeter can be estimated by the number of edge pixels. Aspect ratio can be obtained by calculating the aspect ratio of the element's smallest bounding rectangle. Roundness can be calculated using 4π × area / perimeter. 2 This is used to calculate and distinguish between circular and non-circular elements.

[0133] Texture features can be extracted using the Gray-Level Co-occurrence Matrix (GLCM). This matrix calculates statistics such as energy, contrast, homogeneity, and entropy to describe the texture. For example, energy reflects the uniformity of the texture, and contrast reflects its sharpness.

[0134] In addition, color features, such as color histograms or color moments, can be extracted to distinguish different types of equipment or buildings. For example, the mean and variance of hue, saturation, and brightness in the HSV color space can be calculated.

[0135] Finally, all extracted features are organized into feature vectors, with each element corresponding to a feature vector. These feature vectors are used for subsequent element recognition and classification.

[0136] This system uses preset edge detection and corner detection algorithms to identify the contours and key points of each element in the substation. Edge detection is used to identify element contours. Commonly used edge detection algorithms include the Canny edge detector. Taking the Canny edge detector as an example, its workflow includes the following steps: 1. Smooth the image using a Gaussian kernel to reduce noise. 2. Calculate the horizontal and vertical gradients of the image using the Sobel operator, and then calculate the gradient magnitude and direction. 3. Compare the gradient magnitudes along the gradient direction and retain local maxima. 4. Filter edge pixels using both high and low thresholds. 5. Connect the edges using a hysteresis thresholding method.

[0137] Corner detection is used to identify key points of an element, which typically represent important features of the object's shape. Commonly used corner detection algorithms include the Harris corner detector; however, since corner detection algorithms are quite common, this application will not elaborate on them.

[0138] In practical applications, multiple edge detection and corner detection algorithms can be combined to obtain more accurate and stable results. For example, the Canny algorithm can be used first to obtain a preliminary edge map, and then the Hough transform can be applied to detect regular shapes such as straight lines or circles, which helps to identify columnar equipment or circular insulators in substations.

[0139] For the detected contours, shape descriptors, such as Fourier descriptors or shape context, can be further extracted. These descriptors can capture the global and local features of the contours, which is helpful for subsequent template matching.

[0140] For detected keypoints, local feature descriptors, such as SIFT descriptors or BRIEF (Binary Robust Independent Elementary Features) descriptors, can be calculated. These can be used for subsequent feature matching and object recognition.

[0141] Finally, a standard template library for substation equipment structures is constructed. First, the features extracted in the previous steps are normalized and standardized. This is because different types of features may have different numerical ranges and units. For example, the area in geometric features might be the number of pixels, while the energy of texture features like GLCM is dimensionless. Standardization can be achieved using the Z-score method, i.e., (x-μ) / σ, where x is the original value, μ is the mean, and σ is the standard deviation. Next, a standard template is created for each type of substation equipment. For example, for transformers, hundreds of images from different angles and under different lighting conditions can be collected. Statistical analysis is performed on the features extracted from these images, calculating the mean and standard deviation of each feature. The standard template can be represented as a feature vector, where each element is the mean of the corresponding feature, and the standard deviation is also recorded for subsequent similarity calculations.

[0142] To facilitate rapid retrieval and matching, template libraries are typically organized using tree or hash structures. For example, a kd-tree can be used to organize templates, making nearest neighbor searches efficient in large-scale template libraries. Template libraries also need to contain metadata, such as the device's model, specifications, and normal parameter ranges. For instance, for a specific model of surge arrester, the template might include its normal operating appearance and the normal ranges for electrical parameters such as leakage current and resistive current.

[0143] This implementation method realizes the conversion process from raw image data to a structured substation equipment standard template library, constructing a comprehensive standard template library. The substation equipment standard template library not only includes visual features but also incorporates the technical parameters and status information of the elements, facilitating automated inspection and monitoring of substation equipment and effectively improving the efficiency and accuracy of power system management.

[0144] In one embodiment of this invention, the substation is divided into m electromagnetic field regions based on the power frequency electric field strength data and power frequency magnetic field strength data of the point to be measured, including the following steps:

[0145] S410. Using a preset interpolation algorithm, interpolate the substation based on the power frequency electric field strength data and power frequency magnetic field strength data of all test points to obtain the electromagnetic field strength distribution map of the substation. The electromagnetic field strength distribution map includes multiple interpolation points and / or test points.

[0146] S420. Summarize the interpolation points and / or test points of the power frequency electric field intensity data that are greater than the preset electric field intensity threshold and the power frequency magnetic field intensity data that are greater than the preset magnetic field intensity threshold in the electromagnetic field intensity distribution map to obtain m electromagnetic field regions.

[0147] Using a preset interpolation algorithm, an electromagnetic field intensity distribution map of the entire substation is generated based on the power frequency electric field intensity data and power frequency magnetic field intensity data of the points to be measured in the substation. The interpolation algorithm can be the Kriging interpolation algorithm, which can take into account spatial correlation and is suitable for handling spatially uneven data.

[0148] In practical applications, it is necessary to interpolate the power frequency electric field strength and the power frequency magnetic field strength separately. For example, suppose there are 10 measurement points in a substation, each with measured values ​​of electric field strength E and magnetic field strength H. Using the Kriging method described above, the estimated values ​​of E and H at any point within the entire substation area can be obtained.

[0149] After interpolation, the results are visualized as an electromagnetic field intensity distribution map. This can be done using contour maps or heat maps. Contour maps clearly show the spatial variation trend of electromagnetic field intensity, while heat maps visually display the high and low intensity distribution.

[0150] When generating the distribution map, a coordinate system corresponding to the actual layout of the substation is used, and an appropriate scale is selected according to the size of the substation. A gradient color from blue to red is used to represent the change in intensity from low to high.

[0151] Through this step, discrete measurement data is transformed into a continuous spatial distribution, which not only fills the data gaps of unmeasured points, but also reveals the spatial variation law of electromagnetic field intensity.

[0152] The electromagnetic field intensity distribution map generated in S410 is analyzed and processed to identify and delineate regions with specific electromagnetic field intensity characteristics. First, all interpolation points and test points in the electromagnetic field intensity distribution map are traversed. For each point, its power frequency electric field intensity and power frequency magnetic field intensity are checked to see if they simultaneously exceed a preset threshold. After checking all points, adjacent points exceeding the threshold are grouped into regions. This can be implemented using a connected component labeling algorithm, such as the 8-connected component labeling algorithm. The basic idea of ​​this algorithm is: starting from an unlabeled point exceeding the threshold, check its eight neighboring points; if they are also exceeding the threshold, assign the same label; then recursively perform the same operation on newly labeled points until there are no new neighboring points exceeding the threshold.

[0153] In practice, either Depth-First Search (DFS) or Breadth-First Search (BFS) can be used for implementation. Taking BFS as an example, its pseudocode is as follows: Figure 2 As shown.

[0154] In this pseudocode, the number of markers m is first initialized to 0. Each unmarked point exceeding the threshold is iterated over. A queue Q is created. The current point (x, y) is added to queue Q. While queue Q is not empty, the following operations are performed:

[0155] Take a point (i,j) from queue Q. If point (i,j) is unmarked and exceeds the threshold, perform the following operation:

[0156] Mark point (i,j) as m. Iterate through the 8 neighboring points of point (i,j). Add the neighboring points to queue Q.

[0157] This process will divide all adjacent points exceeding the threshold into m distinct regions.

[0158] In practical applications, the size and shape of the region need to be considered. A minimum area threshold can be set; only regions exceeding this area are considered valid electromagnetic field regions. This can be achieved by calculating the number of points contained in each region. Meanwhile,

[0159] Finally, feature extraction and description are performed on the identified m electromagnetic field regions. This includes calculating the area, average electric field strength, average magnetic field strength, maximum electric field strength point, and maximum magnetic field strength point for each region.

[0160] This implementation method uses an interpolation algorithm to expand discrete measurement point data into a continuous electromagnetic field intensity distribution map, filling the data gaps in unmeasured areas and providing a comprehensive electromagnetic environment description for the entire substation. Based on this, it uses preset thresholds and spatial clustering methods to identify and delineate electromagnetic field regions with specific intensity characteristics. This not only visually displays the spatial distribution of the electromagnetic field but also accurately locates high-intensity areas, achieving a transformation from point to surface and from continuous to discrete, making the analysis and management of electromagnetic field distribution more precise and efficient.

[0161] In one embodiment of this invention, the communication parameters include communication signal frequency, antenna gain, bit error rate, and minimum acceptable signal strength. Based on the power frequency electric field strength data, power frequency magnetic field strength data, and communication parameters of each strong electromagnetic field region, the safe operating distance of the UAV in each strong electromagnetic field region is determined, including the following steps:

[0162] S510. For any strong electromagnetic field region, input the power frequency electric field strength data, power frequency magnetic field strength data, communication signal frequency and antenna gain of each test point in the strong electromagnetic field region into the pre-constructed communication interference model to obtain the signal attenuation value of the UAV at each test point in the strong electromagnetic field region.

[0163] S520. Determine the critical value of interference for the UAV in a strong electromagnetic field region based on the maximum signal attenuation value, bit error rate, and minimum acceptable signal strength.

[0164] S530. Determine the safe operating distance of the UAV in a strong electromagnetic field area based on the interference threshold.

[0165] First, for each strong electromagnetic field region, the power frequency electric field strength and power frequency magnetic field strength data of all test points within that region are acquired. Simultaneously, key parameters of the UAV communication system are obtained, including the communication signal frequency and antenna gain. The communication signal frequency typically refers to the frequency used for data transmission between the UAV and the ground control station, such as common frequency bands like 2.4 GHz or 5.8 GHz. Antenna gain reflects the antenna's ability to convert input power into radio waves, usually expressed in dBi. A communication interference model, built based on electromagnetic field theory and actual test data, simulates the impact of the electromagnetic environment on wireless communication. This model allows calculation of the signal attenuation value of the UAV at each test point in a strong electromagnetic field region. For example, assuming a test point has a power frequency electric field strength of 5 kV / m, a power frequency magnetic field strength of 100 μT, a communication signal frequency of 2.4 GHz, and an antenna gain of 3 dBi, the communication interference model yields a signal attenuation value of 20 dB at that point. This process needs to be performed on all test points within the strong electromagnetic field region to comprehensively assess the communication environment of that area.

[0166] Next, based on the signal attenuation value calculated in the previous step, it is necessary to determine the critical interference threshold for the UAV in a strong electromagnetic field region. In this step, in addition to using the maximum signal attenuation value, the bit error rate (BER) and the minimum acceptable signal strength also need to be considered. The BER refers to the ratio of the number of erroneous bits received to the total number of bits transmitted during data transmission, usually denoted by B (Bit Error Rate). For example, 10... -6 The "B" in this context means that on average, 1 bit is corrupted out of every million bits of data transmitted. The minimum acceptable signal strength refers to the lowest signal strength at which the receiver can function normally, usually expressed in dBm. For example, -90dBm might be a typical minimum acceptable signal strength value for some drone communication systems. The process of determining the interference threshold might be as follows: assuming a maximum signal attenuation of 30dB and a target bit error rate of 10... -6 The minimum acceptable signal strength is -90dBm. Considering that communication systems typically require a certain signal-to-noise ratio to ensure reliable communication, a safety margin, such as 10dB, can be added to the minimum acceptable signal strength. Therefore, the interference threshold can be set to -80dBm. This means that, considering a maximum signal attenuation of 30dB, the signal strength transmitted by the UAV must be at least -50dBm to ensure that, in the worst-case scenario, the receiver can still receive a -80dBm signal, thus maintaining reliable communication.

[0167] Finally, based on the previously determined interference threshold, the safe operating distance for the UAV in a strong electromagnetic field region needs to be determined. Generally, electromagnetic field strength decreases with increasing distance. In free space, electromagnetic field strength typically follows an inverse square law, meaning the strength decreases inversely with the square of the distance. In one embodiment, the process of determining the safe operating distance can be as follows: First, based on the UAV's communication system's transmit power and antenna characteristics, the theoretical maximum communication distance under the interference threshold condition is calculated. Then, considering the special characteristics of a strong electromagnetic field environment, a safety factor is introduced to further reduce this distance. For example, if the theoretical maximum communication distance is 100 meters, a safety factor of 0.8 can be used to set the safe operating distance to 80 meters. Furthermore, the physical layout and equipment distribution of the substation need to be considered to ensure that this safe operating distance will not cause the UAV to come into contact with high-voltage equipment or other obstacles. The final determined safe operating distance allows the UAV to approach the equipment to be inspected as closely as possible while ensuring communication quality and flight safety.

[0168] The safe operating distance of this implementation method can be used for subsequent path planning to ensure that the UAV always stays within a safe range when performing inspection tasks, so as to obtain high-quality detection data and maintain a stable and reliable communication link.

[0169] In one embodiment of this invention, determining the critical value of interference for the UAV in a strong electromagnetic field region based on the maximum signal attenuation value, the bit error rate, and the minimum acceptable signal strength includes the following steps:

[0170] S610. Add the minimum acceptable signal strength to the maximum signal attenuation value to obtain the minimum acceptable strength of the UAV under the maximum attenuation condition;

[0171] S620. Add the minimum acceptable intensity, the preset influence factor, and the preset safety margin to obtain the critical value of interference for the UAV in the strong electromagnetic field region. The influence factor is calculated based on the bit error rate.

[0172] Signal attenuation describes the reduction in signal strength during propagation. The causes of attenuation are varied, including free space loss, atmospheric absorption, and multipath effects. The maximum signal attenuation value is usually obtained through field testing or theoretical calculation, representing the most severe signal attenuation that may be encountered in a given environment.

[0173] The minimum acceptable signal strength is the lowest signal strength that a drone receiver can correctly demodulate. This value is directly related to the receiver's sensitivity and is usually determined by the equipment manufacturer. It reflects the minimum signal power required by the receiver to maintain acceptable communication quality (such as a bit error rate below a certain threshold). Adding these two values ​​essentially considers the worst-case signal transmission scenario. For example, assuming a minimum acceptable signal strength of -100dBm and a maximum signal attenuation of 80dB, then the minimum acceptable strength under maximum attenuation is -20dBm (-100dBm + 80dB). This means that to ensure signal reception under maximum attenuation conditions, the transmitter's signal strength needs to be at least -20dBm.

[0174] The impact factor is a parameter calculated based on the bit error rate (BER). The BER is a crucial performance indicator for digital communication systems, representing the proportion of erroneous bits in a received bitstream. In strong electromagnetic environments, external interference can increase the BER. The impact factor is used to quantify this impact.

[0175] One method for calculating the impact factor is to use the relationship between bit error rate (BER) and signal-to-noise ratio (SNR). For common modulation schemes, such as QPSK (Quadrature Phase Shift Keying), the relationship between BER and SNR is as follows:

[0176]

[0177] Here, ERFC is the complementary error function, BER is the bit error rate, and SNR is the signal-to-noise ratio. Using this relationship, the required SNR can be deduced from the target bit error rate, thus obtaining the influence factor. For example, if the target bit error rate is 10... -6 Calculations show that the required signal-to-noise ratio is approximately 10.5 dB. This value can be used as a reference for the impact factor.

[0178] Safety margin is an extra tolerance set to account for unforeseen circumstances and measurement errors. Its size is usually determined based on empirical values ​​or the requirements of the specific application, and may be set to 3 to 5 dB.

[0179] Adding these three values ​​together yields the critical value for interference to the drone in a strong electromagnetic field region. The calculation formula can be expressed as:

[0180] P t =P m +F i +M s ;

[0181] Where Pt is the threshold value for disturbance, Pm is the minimum acceptable intensity, Fi is the influence factor, and Ms is the safety margin.

[0182] For a concrete example, assuming the minimum acceptable strength is -20dBm (obtained from step S610), the impact factor calculated based on the bit error rate is 10dB, and the safety margin is set to 5dB, then the threshold for interference is -5dBm (-20dBm + 10dB + 5dB).

[0183] The interference threshold represents the maximum electromagnetic field strength that a drone can withstand in a strong electromagnetic field environment. When the ambient electromagnetic field strength exceeds this value, the drone's communication system may be significantly interfered with, affecting its normal operation.

[0184] In another embodiment, the formula for calculating the disturbance threshold is as follows:

[0185] C t =P min +M+10log 10 (-log 10 (B))+S;

[0186] Where: C t It is the threshold value for interference (dBm), P min is the minimum acceptable signal strength (dBm), M is the maximum signal attenuation (dB), B is the target bit error rate, and S is the safety margin (dB).

[0187] The formula starts from the minimum acceptable signal strength P. min Initially, this is the minimum signal strength required for the receiver to function properly. Add the maximum signal attenuation value M to ensure that even under maximum attenuation, the signal still reaches the minimum acceptable strength. (Item 10log) 10 (-log 10 (B) reflects the impact of the bit error rate on the required signal strength. This term is based on a variation of the Shannon-Hartley theorem and considers the signal-to-noise ratio required to achieve a specific bit error rate. The lower the bit error rate, the larger this term is, meaning a stronger signal is needed to ensure communication quality. The addition of a safety margin S provides extra reliability assurance.

[0188] This formula ensures that the receiver still receives a sufficiently strong signal even under maximum signal attenuation. By taking the bit error rate into account, the formula can automatically adjust the required signal strength according to different communication quality requirements. The lower the bit error rate, the higher the required signal strength. The introduction of a safety margin increases the system's robustness, providing a buffer against potential unforeseen circumstances.

[0189] Using this formula, a suitable interference threshold can be calculated based on specific communication system parameters and environmental conditions. This threshold can be used to guide the determination of safe operating distances for drones, ensuring the maintenance of reliable communication links in strong electromagnetic field environments.

[0190] For example, if P min =-90, M=30dB, B=10 -6 And S = 10dB, then:

[0191] C t = -90 + 30 + 10log 10 (-log 10 (10 -6 ))+10≈-80.

[0192] This is consistent with the previously described results, confirming the validity of the formula.

[0193] Determining the safe operating distance of a drone in a strong electromagnetic field region based on the interference threshold includes the following steps:

[0194] S630: Using a preset spatial path loss calculation formula, the theoretical maximum communication distance of the UAV in a strong electromagnetic field region is calculated based on the interference threshold.

[0195] S640. Determine the physical layout of the substation based on the 3D point cloud model, and determine the environmental constraint distance of the UAV based on the physical layout.

[0196] S650: Multiply the minimum of the theoretical maximum communication distance and the environmental constraint distance by the preset safety factor to obtain the safe operating distance of the UAV in the strong electromagnetic field area.

[0197] First, the theoretical maximum communication distance is determined using the spatial path loss calculation formula. Then, the environmental constraint distance is determined based on the physical layout of the substation. Next, the physical layout of the substation is determined using a 3D point cloud model. The 3D point cloud model consists of a large number of points, each with its own spatial coordinates (x, y, z). By analyzing the distribution of these points, the location, height, and spatial relationships between various equipment within the substation can be identified. For example, the specific locations and dimensions of high-voltage lines, transformers, and power distribution equipment can be identified.

[0198] Based on this physical layout, the environmental constraint distance for the drone can be determined. For example, it can be set that the drone must maintain a distance of at least 10 meters from all high-voltage equipment and at least 5 meters from buildings. By analyzing the positions of various devices and buildings in the 3D point cloud model, the minimum flight distance that satisfies these constraints can be calculated; this distance is the environmental constraint distance.

[0199] Finally, determine the safe operating distance for the drone in areas with strong electromagnetic fields. Specifically, compare the theoretical maximum communication distance with the environmentally constrained distance and select the minimum value. This is because the actual operation of the drone must simultaneously meet both communication and environmental safety requirements. Choosing the minimum value ensures that both conditions are satisfied.

[0200] In this embodiment, the formula is as follows:

[0201] D s = min(k·D t , D e )·S f ;

[0202] Where: Ds is the final safe operation distance, Dt is the theoretical maximum communication distance, k is the environmental complexity coefficient (0 < k ≤ 1), De is the environmental constraint distance, and Sf is the safety factor (0 < Sf ≤ 1).

[0203] The theoretical maximum communication distance is the maximum distance calculated based on the transmission power, antenna characteristics, and interference critical value of the UAV communication system. The free space path loss model can be used for calculation:

[0204]

[0205] Where, P t is the transmission power (dBm), Ct is the interference critical value (dBm), Gt and Gr are the transmission and reception antenna gains (dBi) respectively, and f is the signal frequency (MHz).

[0206] The environmental complexity coefficient k reflects the difference between the actual environment and the ideal free space. In a complex substation environment, due to factors such as multipath effect, reflection, and diffraction, the value of k will be less than 1. It can be determined through on-site testing or complex electromagnetic field simulation. The environmental constraint distance De is the maximum allowable distance considering the physical layout and equipment distribution of the substation. It ensures that the UAV does not come into contact with high-voltage equipment or other obstacles. The safety factor Sf is used to further reduce the working distance. The min() function selects the smaller value between the theoretically adjusted distance k·D t and the environmental constraint distance De, ensuring that the safe operation distance does not exceed any physical limit.

[0207] In this formula, first calculate the theoretical maximum communication distance Dt, which represents the maximum working range under ideal conditions. Use the environmental complexity coefficient k to adjust the theoretical distance, reflecting the influence of the actual environment. Compare the adjusted distance with the environmental constraint distance De, and select the smaller value to ensure that it does not exceed the physical limit. Finally, apply the safety factor Sf to further reduce the distance and increase an additional safety margin.

[0208] For example, assume Dt = 100 meters, k = 0.9, De = 95 meters, Sf = 0.8, then: D s = min(0.9·100, 95)·0.8 = 76 meters.

[0209] In this embodiment, steps S610 and S620 first consider signal transmission under worst-case conditions, ensuring communication can still be maintained even under maximum signal attenuation. They further consider the impact of bit error rate and additional safety margins, resulting in a more accurate critical value. These two steps provide a clear criterion for the safe operation of UAVs in strong electromagnetic field environments. This critical value can be used to assess whether the electromagnetic environment of a specific area is suitable for UAV operation, and it can also guide the design and optimization of UAV communication systems to improve their anti-interference capabilities in strong electromagnetic field environments.

[0210] The S630 and S640 steps consider several key factors: communication capability, environmental constraints, and safety margin. Through theoretical calculations and practical environmental analysis, the theoretical maximum communication distance and the environmentally constrained distance were obtained. These two distances limit the UAV's operational range from different perspectives. By combining these two distances and introducing a safety factor, a conservative and reliable safe operating distance was ultimately obtained. This approach considers both theoretical communication limitations and the physical constraints of the actual environment, while adding additional safety assurance through the introduction of a safety factor. The resulting safe operating distance effectively balances operational efficiency and safety, providing reliable operational guidance for UAV applications in strong electromagnetic field environments such as substations. It significantly improves the safety of UAV operations, reduces the risk of accidents, and simultaneously ensures communication quality and improves operational efficiency.

[0211] In one embodiment of this invention, the initial inspection path is adjusted based on the three-dimensional point cloud model and the safe operating distance for each strong electromagnetic field region to obtain the final inspection path, including the following steps:

[0212] S710. Divide the initial inspection path into multiple path segments based on m electromagnetic field regions, and determine the target path segment in the strong electromagnetic field region among the multiple path segments.

[0213] S720. For each target path segment, construct a spherical safety area with a safe working distance as the radius in the 3D point cloud model, with the center point of the target path segment located at the center of the spherical safety area.

[0214] S730. Determine whether the initial inspection path intersects with p spherical safety zones, where p is a positive integer;

[0215] S740. If there is an initial inspection path that intersects with p spherical safe zones, then determine the trajectory points on the initial inspection path that are located within the spherical safe zones.

[0216] S750. For any trajectory point, determine its corresponding replacement point, and convert all trajectory points into corresponding replacement points to obtain the final inspection path.

[0217] First, based on the 3D point cloud model and the safe operating distance for each strong electromagnetic field region, the initial inspection path is adjusted to obtain the final inspection path. The first step is to divide the initial inspection path into multiple path segments based on the m electromagnetic field regions, and then identify the target path segments located within the strong electromagnetic field regions. In practice, spatial analysis algorithms can be used to determine the positional relationship between the initial inspection path and each electromagnetic field region. For example, ray projection or polygon inclusion algorithms can be used to determine which parts of the path are located within the electromagnetic field regions. Assume an initial inspection path is 100 meters long and passes through 3 electromagnetic field regions. Through spatial analysis, it may be found that segments 20-30 meters, 55-65 meters, and 80-90 meters are located within these electromagnetic field regions. These path segments are then marked as target path segments.

[0218] The second step is to construct a spherical safety zone with a safe working distance as the radius in the 3D point cloud model for each target path segment, with the center point of the target path segment located at the center of the spherical safety zone. Figure 3 This illustration shows a schematic diagram of a spherical security area provided in an embodiment of this application, such as... Figure 3 As shown, AB represents the target path segment, O is the center point of the target path, and O is also the center of the spherical safety zone. OA and OB represent safe working distances. This embodiment utilizes 3D geometric modeling technology to create a virtual safety zone in a point cloud model. In practice, the coordinates of the center point of each target path segment must first be calculated. Taking the 20-30 meter path segment identified in the previous step as an example, its center point coordinates might be (25,0,0). Assuming the safe working distance for this area is 5 meters, a spherical safety zone is constructed with (25,0,0) as the center and a radius of 5 meters. 3D modeling functions, such as the createSphere() function, can be used.

[0219] The third step is to determine whether the initial inspection path intersects with p spherical safety zones, where p is a positive integer. This can be achieved using a line-plane intersection detection algorithm from computational geometry. In practice, the initial inspection path can be considered as a series of line segments, and then each segment can be checked to see if it intersects with each spherical safety zone. A common method is to first perform a fast bounding box test. If the bounding box of a line segment does not intersect with the bounding box of the sphere, it can be directly determined that they do not intersect; otherwise, the shortest distance from the line segment to the center of the sphere is calculated. If this distance is less than the radius of the sphere, it is determined that they intersect. For example, for the aforementioned spherical safety zone centered at (25,0,0) with a radius of 5 meters, we can check whether each line segment in the initial path intersects with this sphere. Suppose there is a line segment from (20,0,0) to (30,0,0); obviously, this line segment intersects with the sphere.

[0220] The fourth step, assuming the initial inspection path intersects with p spherical safety zones, is to identify the trajectory points on the initial inspection path that lie within the spherical safety zones. This can be based on the calculation and comparison of the distance from each point to the center of the sphere. In practice, sampling points can be taken at fixed intervals along the initial inspection path, and then it can be determined whether each sampling point lies within any of the spherical safety zones. The determination method is to calculate the distance from the sampling point to the center of the sphere; if this distance is less than the radius of the sphere, then the point is inside the sphere. For example, for the aforementioned spherical safety zones, a sampling point can be taken every 0.1 meters along a path segment of 20 to 30 meters. For the sampling point (23,0,0), its distance to the center of the sphere (25,0,0) is calculated to be 2 meters, which is less than the radius of the sphere (5 meters), therefore this point is marked as a trajectory point that needs adjustment. In this way, all trajectory points that need adjustment can be accurately identified, providing a basis for subsequent path optimization. This fine-grained analysis ensures the accuracy of path adjustments and avoids unnecessary over-adjustment.

[0221] The final step involves identifying a corresponding candidate point for any given trajectory point and converting all trajectory points into their corresponding candidate points to obtain the final inspection path. This can be implemented using a point migration algorithm based on safety distance constraints. Specifically, a spherical uniform sampling algorithm can be used to find suitable candidate points. In one embodiment, for each trajectory point requiring adjustment, multiple points are uniformly sampled on a sphere centered on that point and with a safety working distance as its radius. The point closest to the original path and not located within any safety zone is then selected as a candidate point. For example, for the trajectory point at (23,0,0), 100 points can be sampled on a sphere centered on this point with a radius of 5 meters. If a point (27,3,4) satisfies both the safety distance requirement and is closest to the original path among all sampled points, then this point is selected as a candidate point. This process is repeated for all trajectory points requiring adjustment, ultimately yielding a series of candidate points. Connecting these candidate points forms the final inspection path. This method ensures safety while maintaining the smoothness and closeness to the original path as much as possible.

[0222] This implementation method effectively identifies and avoids areas with strong electromagnetic fields, ensuring the safety of inspection operations. Through precise spatial analysis and geometric calculations, path adjustments can be minimized, preserving the characteristics of the original path as much as possible while ensuring safety. Utilizing a 3D point cloud model, it can adapt to complex terrain and environments. The final generated inspection path not only meets safety requirements but also maintains high inspection efficiency, providing a reliable path planning solution for actual inspection operations.

[0223] In one embodiment of this invention, determining the corresponding replacement point for any trajectory point includes the following steps:

[0224] S810. For any trajectory point, uniformly sample multiple candidate points on the spherical surface of the spherical safe region.

[0225] S820. Among multiple candidate points, select the point that is closest to the trajectory point and is not within any spherical safe area as the replacement point corresponding to the trajectory point.

[0226] A spherical safety zone is a spherical space with a certain radius centered at a specific point. In drone path planning, the spherical safety zone represents obstacles or dangerous areas that need to be avoided. Track points are points on the drone's original flight path; if these points fall within the spherical safety zone, alternative points need to be found to ensure flight safety.

[0227] In one embodiment, a spherical coordinate system can be used to generate uniformly distributed points by controlling the zenith angle θ and the azimuth angle φ. The specific implementation is as follows:

[0228] 1. Determine the number of sampling points N. Typically, 100 to 1000 points can be chosen. 2. Generate the sampling points using the spherical coordinate formula. For each sampling point, its coordinates can be expressed as:

[0229]

[0230] z = R × cos(θ);

[0231] Where R is the radius of the sphere, θ is the zenith angle (0 to π), and φ is the azimuth angle (0 to 2π).

[0232] 3. To achieve a uniform distribution, θ and φ can be generated using the following method:

[0233] θ=arccos(1-2×i / N),i:0→N-1

[0234]

[0235] Selecting the most suitable replacement point from multiple candidate points involves two main checks for each candidate point: 1. Calculating the distance from the candidate point to the original trajectory point. 2. Determining whether the candidate point lies within any other spherical safe area.

[0236] Distance can be calculated using the Euclidean distance formula. For two points P1(x1,y1,z1) and P2(x2,y2,z2) in three-dimensional space, the distance D between them can be calculated using the following formula:

[0237]

[0238] Next, it's necessary to check if each candidate point falls within another spherical safe zone. This can be done by calculating the distance from the candidate point to the center of each safe zone and comparing it to the radius of that safe zone. If the distance is less than the radius, the point is within a safe zone and should be excluded.

[0239] For example, suppose there is another spherical safety zone with center coordinates (10,10,10) and a radius of 5 meters. For the candidate point (12,8,7) mentioned above, calculate its distance to the center of this safety zone:

[0240] D = √[(12-10)] 2 +(8-10) 2 +(7-10) 2 ]=√(4+4+9)=√17≈4.12m;

[0241] Since 4.12 meters is less than the radius of the safe zone of 5 meters, this candidate point is located within the safe zone and cannot be used as a valid replacement point.

[0242] After calculating the distances and performing safety checks on all candidate points, the point closest to the original trajectory point needs to be selected from the remaining valid points as the replacement point. This can be achieved by comparing the distance values ​​of all valid points and selecting the point with the minimum value.

[0243] The specific steps are as follows: 1. Initialize a variable to store the minimum distance, with an initial value of infinity. 2. Initialize a variable to store the best replacement point, with an initial value of empty. 3. Iterate through each candidate point: a. Calculate the distance from the candidate point to the original trajectory point. b. Check if the candidate point is within any other safe area. c. If it is not within any safe area and the distance is less than the current minimum distance, update the minimum distance and the best replacement point. 4. After the iteration is complete, the best replacement point is the required replacement point.

[0244] In summary, an optimal replacement location can be found for each trajectory point that needs to be replaced. The replacement location satisfies two key conditions: it is not within any spherical safety area, and it is the closest candidate point to the original trajectory point. This ensures flight safety while preserving the characteristics of the original trajectory to the greatest extent possible.

[0245] This implementation provides a set of candidate points distributed across the surface of a spherical safety zone for each trajectory point requiring replacement. These candidate points form the basis for selecting the optimal replacement point. The uniform distribution ensures diverse options when choosing a replacement point, increasing the likelihood of finding a suitable one. Furthermore, it guarantees that the replacement point always lies on the boundary of the safety zone, neither entering a danger zone nor straying too far from the original trajectory point. By uniformly sampling the surface of the spherical safety zone, a widely distributed set of candidate points is provided. The optimal replacement point is selected from these candidates through distance calculation and safety checks. This approach considers both safety (ensuring the replacement point is not within any danger zone) and the continuity and smoothness of the trajectory (selecting the replacement point closest to the origin). The resulting new trajectory effectively avoids all danger zones while maintaining the characteristics of the original trajectory as much as possible. This significantly improves the safety of UAV flight while maintaining flight efficiency, making it suitable for path planning and dynamic obstacle avoidance in complex environments.

[0246] Example 2

[0247] Based on Example 1, after obtaining the final inspection path, the blind spots of the final inspection path can be identified, specifically including:

[0248] First, the entire inspection area is discretized into a 3D mesh, with each mesh cell representing a potential inspection point. Then, a simulated inspection is performed along the final inspection path, calculating the visibility and reachability of each mesh cell. This can be implemented using a ray tracing algorithm. Virtual rays are emitted from each point on the inspection path to surrounding mesh cells; if a ray reaches a mesh cell without being obstructed by obstacles, that mesh cell is considered visible.

[0249] In practice, a visibility threshold can be set. For example, if a grid cell is visible for less than 10% of the total inspection time, it can be marked as a potential blind spot. Simultaneously, the performance parameters of the inspection equipment, such as the camera's field of view and effective detection range, need to be considered. For instance, assuming the camera used for inspection has a 60-degree horizontal field of view and an effective detection range of 30 meters, these parameters must be included in the visibility analysis calculations.

[0250] In addition, spatial interpolation techniques can be used to assess the continuity of inspection coverage. For example, kriging interpolation can be used to interpolate sampling points along the inspection path to generate a continuous coverage intensity field. By analyzing the distribution of this intensity field, areas with weak coverage can be identified, which may be potential inspection blind spots.

[0251] For identified blind spots in the inspection process, the following measures can be taken: 1. Adjust the inspection path to get closer to or pass through the blind spot to improve coverage. Ant colony optimization can be used to find the optimal path. 2. Add static observation points or hovering points at key locations to supplement the monitoring of the blind spot. 3. When passing near the blind spot, design multiple observation angles and orientations to maximize coverage.

[0252] For unavoidable safe working distance issues, the following strategies can be adopted:

[0253] 1. Employ remote sensing technologies such as telephoto lenses, high-resolution sensors, or thermal imaging equipment to enhance detection capabilities while maintaining a safe distance. For example, if a conventional camera cannot obtain a sufficiently clear image beyond a 5-meter safe distance, consider using a camera with 30x optical zoom, which can achieve image clarity equivalent to 5 meters even at 15 meters. 2. Combine different types of sensors, such as visible light cameras, infrared cameras, and LiDAR, to obtain more comprehensive information. By fusing data from multiple sensors, the limitations of a single sensor in long-distance observation can be mitigated to some extent. 3. Dynamically adjust sampling frequency and accuracy based on real-time data acquisition. Increase data acquisition frequency and accuracy when approaching but not reaching the safe distance boundary; appropriately reduce sampling density to conserve resources when far from hazardous areas. 4. Construct a virtual 3D model of the inspection area based on the acquired data. Operators can conduct detailed inspections in a safe virtual environment, compensating for the limitations of close-range observation due to safe distance restrictions during actual inspections.

[0254] By comprehensively applying these strategies, blind spots in inspections can be effectively identified and addressed. Furthermore, even when unavoidable safety distance limitations are encountered, inspection quality and coverage can still be guaranteed to the greatest extent possible. This multi-layered, multi-faceted inspection strategy not only improves the comprehensiveness and accuracy of inspections but also ensures the safety of inspection personnel and equipment, providing more reliable technical support for the maintenance and management of power facilities.

[0255] This application embodiment also provides a central control host, including:

[0256] The memory is configured to store instructions; and

[0257] The processor is configured to retrieve instructions from memory and, when executing instructions, implement the aforementioned inspection path planning method for the substation inspection drone.

[0258] Reference Figure 4 This application also provides an inspection path planning system for a substation inspection drone, comprising:

[0259] Central control unit;

[0260] The drone is connected to the central control unit and is equipped with an electromagnetic detection device for detecting the strength of power frequency electric field and power frequency magnetic field.

[0261] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0262] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0263] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0264] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0265] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0266] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0267] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0268] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0269] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for planning the inspection path of a substation inspection drone, characterized in that, The method is applied to a central control unit, which is connected to a drone. The drone is equipped with an electromagnetic detection device, which is used to detect power frequency electric field strength and power frequency magnetic field strength. The method includes: The drone acquires point cloud data of the substation and constructs a three-dimensional point cloud model of the substation based on the point cloud data. In response to receiving an inspection command for the target inspection subject, the start point and end point of the UAV are obtained, and an initial inspection path is generated based on the three-dimensional point cloud model, the start point, the end point and the preset flight altitude, and the target inspection subject is located on the initial inspection path; In response to receiving the power frequency electric field strength data and power frequency magnetic field strength data of the test point of the substation transmitted by the UAV, the substation is divided into m electromagnetic field regions according to the power frequency electric field strength data and the power frequency magnetic field strength data of the test point, where m is an integer greater than 1, and the m electromagnetic field regions include at least one strong electromagnetic field region, at least one standard electromagnetic field region and / or at least one weak electromagnetic field region. The communication parameters of the UAV are obtained, and the safe operating distance of the UAV in each strong electromagnetic field region is determined based on the power frequency electric field strength data, the power frequency magnetic field strength data and the communication parameters in each strong electromagnetic field region. The initial inspection path is divided into multiple path segments based on the m electromagnetic field regions, and the target path segment located in the strong electromagnetic field region is determined among the multiple path segments. For each target path segment, a spherical safety region with the safe working distance as its radius is constructed in the three-dimensional point cloud model, and the center point of the target path segment is located at the center of the spherical safety region; Determine whether the initial inspection path intersects with p of the spherical safety zones, where p is a positive integer; If the initial inspection path intersects with p of the spherical safety zones, then determine the trajectory points on the initial inspection path that are located within the spherical safety zones; For any given trajectory point, determine its corresponding replacement point, and convert all the trajectory points into the corresponding replacement points to obtain the final inspection path; The final inspection path is sent to the drone so that the drone can inspect the substation according to the final inspection path.

2. The method according to claim 1, characterized in that, The process of generating an initial inspection path based on the 3D point cloud model, the starting point, the ending point, and the preset flight altitude includes: A point cloud processing network is used to perform semantic segmentation on the 3D point cloud model, so as to divide the 3D point cloud model into n semantic regions, wherein each semantic region represents an element type; A pattern matching algorithm is used to compare the n semantic regions with a pre-built standard template library of substation equipment structures to determine the element features corresponding to each semantic region; Based on a pre-defined knowledge graph, determine the spatial and functional relationships between each element in the substation; Obtain the 2D design document of the substation, determine the layout rules of the substation based on the 2D design document, and determine the properties of each element based on the layout rules of the substation. The element type, element features, spatial and functional relationships between each element, and properties of each element corresponding to each semantic region are mapped to the three-dimensional point cloud model to annotate each element in the three-dimensional point cloud model. The target inspection subject is mapped to the elements marked in the three-dimensional point cloud model to determine the target elements in the three-dimensional point cloud model; The starting point, the ending point, and the flight altitude are mapped to the three-dimensional point cloud model to obtain the UAV starting point and UAV ending point in the three-dimensional point cloud model. An initial inspection path is generated in the three-dimensional point cloud model using a preset path planning algorithm based on the UAV's starting point, the UAV's ending point, and the target element.

3. The method according to claim 2, characterized in that, The steps for constructing the substation equipment structure standard template library include: Acquire on-site images of the substation, extract features from the on-site images, and obtain the geometric and texture features of each element in the substation; The contours and key points of each element are identified by using a preset edge detection algorithm and a preset corner detection algorithm. Based on the geometric features, texture features, contours and key points of each element, a standard template library for substation equipment structures is constructed.

4. The method according to claim 2, characterized in that, The substation is divided into m electromagnetic field regions based on the power frequency electric field strength data and the power frequency magnetic field strength data of the test point, including: Using a preset interpolation algorithm, the substation is interpolated based on the power frequency electric field strength data and the power frequency magnetic field strength data of all the test points to obtain an electromagnetic field strength distribution map of the substation. The electromagnetic field strength distribution map includes multiple interpolation points and / or test points. The interpolation points and / or test points of the power frequency electric field intensity data that are greater than the preset electric field intensity threshold and the power frequency magnetic field intensity data that are greater than the preset magnetic field intensity threshold in the electromagnetic field intensity distribution map are summarized to obtain m electromagnetic field regions.

5. The method according to claim 1, characterized in that, The communication parameters include communication signal frequency, antenna gain, bit error rate, and minimum acceptable signal strength. Determining the safe operating distance of the UAV in each of the strong electromagnetic field regions based on the power frequency electric field strength data, the power frequency magnetic field strength data, and the communication parameters includes: For any given strong electromagnetic field region, the power frequency electric field strength data, power frequency magnetic field strength data, communication signal frequency, and antenna gain of each test point in the strong electromagnetic field region are input into a pre-constructed communication interference model to obtain the signal attenuation value of the UAV at each test point in the strong electromagnetic field region. Based on the maximum signal attenuation value, the bit error rate, and the minimum acceptable signal strength, the threshold value of interference for the UAV in the strong electromagnetic field region is determined. Based on the interference threshold, the safe operating distance of the UAV in the strong electromagnetic field region is determined.

6. The method according to claim 5, characterized in that, Determining the threshold for interference of the UAV in the strong electromagnetic field region based on the maximum signal attenuation value, the bit error rate, and the minimum acceptable signal strength includes: The minimum acceptable signal strength is added to the maximum signal attenuation value to obtain the minimum acceptable signal strength of the UAV under the maximum attenuation condition; The minimum acceptable intensity, the preset influence factor, and the preset safety margin are added together to obtain the critical value of interference of the UAV in the strong electromagnetic field region, wherein the influence factor is calculated based on the bit error rate; Determining the safe operating distance of the UAV in the strong electromagnetic field region based on the interference threshold includes: Using a preset spatial path loss calculation formula, the theoretical maximum communication distance of the UAV in the strong electromagnetic field region is calculated based on the interference threshold. The physical layout of the substation is determined based on the three-dimensional point cloud model, and the environmental constraint distance of the UAV is determined based on the physical layout. The safe operating distance of the UAV in the strong electromagnetic field region is obtained by multiplying the minimum value of the theoretical maximum communication distance and the environmental constraint distance by a preset safety factor.

7. The method according to claim 1, characterized in that, The step of determining the corresponding replacement point for any given trajectory point includes: For any given trajectory point, multiple candidate points are uniformly sampled on the spherical surface of the spherical safety region; Among the multiple candidate points, the point that is closest to the trajectory point and is not within any of the spherical safe areas is selected as the replacement point corresponding to the trajectory point.

8. A central control host, characterized in that, include: The memory is configured to store instructions; as well as The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the inspection path planning method for the substation inspection drone according to any one of claims 1 to 7.

9. A path planning system for a substation inspection drone, characterized in that, include: The central control unit according to claim 8; The drone is connected to the central control host, and the drone is equipped with an electromagnetic detection device for detecting the power frequency electric field strength and the power frequency magnetic field strength.

Images