Autonomous trajectory deduction system and method for unmanned aerial vehicle in complex substation environment

Abstract

The present invention relates to the field of drone cruise technology, and discloses a drone autonomous track deduction system and method in a complex environment of a substation. The system includes: a management module manages basic information of the substation and patrol equipment information; a storage module stores basic information of the substation, patrol equipment information and point cloud data; a point cloud preprocessing module preprocesses and finely processes point cloud data; a visualization module visualizes and renders point cloud data; a business application analysis module specifies a target to be inspected, analyzes the blind area of ​​the target to be inspected in combination with the parameter information of a ground robot and a fixed pan-tilt camera, and automatically analyzes the photographing points of the blind area of ​​the target to be inspected in combination with the parameter information of a drone, and finally generates the track of the drone patrol. The present invention can reduce the problem of a large number of overlapping inspection points of different patrol equipment, reduce resource waste, and improve the coverage, flexibility and reliability of inspection.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) cruising technology, and in particular to an autonomous trajectory deduction system and method for an unmanned aerial vehicle (UAV) in a complex substation environment. Background Art

[0002] At present, an online intelligent inspection system for substations has been built. Fixed PTZ cameras and ground robots carry out regular equipment inspections and drone inspections, providing multi-source video data, supplemented by deep learning-based target recognition and defect detection technology, to monitor equipment status and equipment defects, and monitor equipment operation abnormalities. Under the existing inspection mode, robots have partially replaced manual inspection tasks, and carried out intelligent inspections of substations with the idea of ​​"machine inspection as the main and human inspection as the auxiliary". At the same time, fixed PTZ cameras and robots are uniformly accessed, issued, controlled, and analyzed for inspection results, forming inspection results and inspection reports. UAVs have flexible positions and wide viewing angles. They can flexibly change their positions according to needs. For high-altitude operations, they can provide a horizontal view, which can not only take panoramic views from a high altitude, but also focus on local details to magnify the details of the site. It can effectively make up for the shortcomings of the current limited viewing angle of daily inspections, and serve as an effective supplement to operation and maintenance work, and make up for the shortcomings of current remote monitoring and on-site work.

[0003] However, although the existing technology combines drones, ground robots and other joint inspections, there are still the following problems:

[0004] 1. The inspection systems of drones, ground robots, and fixed PTZ cameras are independent of each other. There is a large overlap of inspection points in different inspection systems, resulting in duplication of data collection and defect detection model training processes and waste of resources.

[0005] 2. The inspection points and photo taking points of drones can only be set based on manual experience. The inspection points cannot be automatically associated with the equipment ledger, and the coverage rate of manually set photo taking points cannot be evaluated. It is very easy to have blind spots in inspections, poor flexibility and low reliability.

[0006] Therefore, there is an urgent need for an autonomous trajectory simulation system and method for UAVs in the complex environment of substations, which can reduce the problem of a large number of overlapping inspection points of different patrol equipment, reduce resource waste, and improve the coverage, flexibility and reliability of inspections. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides an autonomous trajectory simulation system and method for UAVs in the complex environment of a substation, which can reduce the problem of a large number of overlapping inspection points of different patrol equipment, reduce resource waste, and improve the coverage, flexibility and reliability of inspections.

[0008] The present invention provides an autonomous trajectory deduction system for unmanned aerial vehicles in a complex substation environment, comprising:

[0009] Management module, storage module, visualization module, point cloud pre-processing module and business application analysis module;

[0010] The management module is used to manage the basic information of the substation, patrol equipment information and patrol tasks; the basic information includes equipment design information, equipment acceptance information, equipment ledger information and equipment patrol information; the patrol equipment includes drones, ground robots and fixed pan-tilt cameras;

[0011] The storage module is connected to the management module and is used to store basic information of the substation, patrol equipment information, safety specifications, substation site cloud data and equipment single point cloud data;

[0012] The point cloud preprocessing module is connected to the storage module and is used to preprocess the substation cloud data to obtain the equipment single point cloud data, and to finely process the equipment single point cloud data in combination with the visualization module; wherein the preprocessing includes gross error elimination, point cloud thinning, point cloud classification, and equipment single-unitization, and the fine processing includes classification labeling, single-unitization labeling, association of single-unitization with equipment ledger, and inspection point labeling;

[0013] The visualization module is connected to the point cloud preprocessing module and is used to visualize and render the substation cloud data and the equipment single point cloud data;

[0014] The business application analysis module is connected to the visualization module and is used to specify the target to be inspected. It analyzes the blind spots of the target to be inspected by combining the parameter information of the ground robot and the fixed gimbal camera. It also automatically analyzes the photo taking points of the blind spots of the target to be inspected by combining the parameter information of the drone, the point cloud data of the target to be inspected and the safety specifications, and finally generates the track of the drone inspection.

[0015] Further, the management module includes: a substation management unit, a user management unit, a design data management unit, a safety specification management unit, a task management unit, and a patrol equipment management unit;

[0016] Substation management unit, used to manage basic information of substation;

[0017] User management unit, used to manage permissions of different users;

[0018] Design data management unit, used to manage and store parameter information of different equipment in the substation;

[0019] The safety specification management unit is used to store the safety specifications of the substation; the safety specifications include equipment design specifications, equipment acceptance specifications, and equipment inspection specifications;

[0020] Task management unit, used to manage autonomous inspection tasks of substations; autonomous inspection tasks include inspection targets, inspection points, and flight paths;

[0021] The patrol equipment management unit is used to manage the parameter information of the patrol equipment in the substation.

[0022] Furthermore, the storage module includes: a point cloud data storage unit, an image data storage unit, a patrol point and photo point storage unit, a database storage unit, a track file storage unit, a track deduction related file storage unit, and other file storage units;

[0023] A point cloud data storage unit is used to store substation cloud data files; wherein the substation cloud data files include substation cloud data and equipment single point cloud data;

[0024] An image data storage unit, used to store image data acquired during the process of collecting point cloud data;

[0025] Inspection point and photo point storage unit, used to store inspection points and photo points of equipment units;

[0026] A database storage unit is used to store various parameter information; wherein the parameter information includes point cloud rendering parameters, equipment classification parameters, safety specifications, equipment parameter information, and patrol equipment parameter information;

[0027] A track file storage unit, used to store the track information of the UAV;

[0028] A track deduction file storage unit is used to store track deduction process files; the track deduction process files include photographing effect files;

[0029] Other file storage units are used to store report files and photo point visualization files.

[0030] Furthermore, the point cloud preprocessing module includes: a gross error elimination unit, a point cloud thinning unit, a point cloud classification unit, a classification labeling unit, an equipment unitization unit, a unitization labeling unit, a unitization and equipment ledger association unit, and a patrol point labeling unit;

[0031] Gross error elimination unit, used to eliminate gross error points in point cloud data;

[0032] Point cloud thinning unit, used to thin point cloud data;

[0033] A point cloud classification unit, used to classify and identify point cloud data according to equipment classification parameters;

[0034] A classification and labeling unit, used to assist in classification and labeling of point cloud data according to equipment classification parameters;

[0035] The device monomer unit is used to perform monomer recognition on the classified point cloud data;

[0036] The individualized annotation unit is used to assist in individualized annotation of the classified point cloud data;

[0037] The unit for associating the monomer and the equipment ledger is used to establish the corresponding relationship between the point cloud data of the equipment monomer and the equipment ledger information;

[0038] The patrol point marking unit is used to mark the patrol points of the equipment.

[0039] Furthermore, the visualization module includes: a substation massive point cloud data rendering unit, a point cloud category visualization unit, a device unit visualization unit, a patrol point visualization unit, a photo point visualization unit, a photo effect simulation visualization unit, a track visualization unit, and a database information visualization unit;

[0040] Substation massive point cloud data rendering unit, used to render point cloud data;

[0041] A point cloud category visualization unit, used to visualize point cloud data according to device classification parameters;

[0042] The equipment unit visualization unit is used to visualize the point cloud data of the equipment unit according to the equipment ledger information;

[0043] Inspection point visualization unit, used to visualize the inspection points of the equipment unit;

[0044] The photo point visualization unit is used to visualize the photo points and photo view volume of the equipment unit;

[0045] A photographic effect simulation and visualization unit, used to visualize the photographic effect;

[0046] A track visualization unit, used to visualize the track of the UAV;

[0047] The database information visualization unit is used to preview and modify various parameter information stored in the database storage unit.

[0048] Furthermore, the business application analysis module includes: a patrol target designation unit, a blind spot analysis unit, an automatic photo point calculation unit, a photo point adjustment unit, a track automatic generation unit, a track reverse deduction unit, a track adjustment unit, and a track publishing unit;

[0049] Specify patrol target unit, which is used to specify one or more equipment units as patrol targets;

[0050] Blind spot analysis unit, used to analyze the blind spots of the target to be inspected by combining the parameter information of the ground robot and the fixed PTZ camera;

[0051] Automatically calculate the photo point unit, which is used to automatically analyze the photo points in the blind area of ​​the target to be inspected by combining the parameter information of the drone, the point cloud data of the equipment unit, and the equipment inspection specifications;

[0052] A photo point adjustment unit is used to adjust the photo parameters of the drone based on the visual volume information of the photo point;

[0053] The automatic track generation unit is used to generate the track of the drone inspection according to the blind area of ​​the target to be inspected;

[0054] The track reverse deduction unit is used to generate inspection and photography effects based on the generated track using the track simulation function;

[0055] A track adjustment unit, used to adjust the track according to the inspection and photography results;

[0056] The track publishing unit is used to publish the final track file to the UAV management center.

[0057] The present invention also provides a method for autonomous trajectory deduction of a UAV in a complex environment of a substation, which is implemented by any of the above-mentioned systems for autonomous trajectory deduction of a UAV in a complex environment of a substation, and specifically comprises the following steps:

[0058] S1. Obtain basic information of the substation, patrol equipment information and patrol task information; the basic information includes equipment design information, equipment acceptance information, equipment ledger information and equipment patrol information; patrol equipment includes drones, ground robots and fixed pan-tilt cameras;

[0059] S2, obtaining substation cloud data;

[0060] S3. Preprocess the substation cloud data to obtain the equipment point cloud data, and perform fine processing on the equipment point cloud data to determine the inspection points of the equipment;

[0061] S4. Designate one or more equipment units as the inspection targets, and determine the blind spots of the inspection targets according to the parameter information of the ground robot, the fixed PTZ camera, and the inspection points of the equipment units;

[0062] S5. Automatically calculate the photographing points corresponding to the inspection points in the blind area of ​​the target to be inspected according to the parameter information of the drone and the equipment inspection specifications;

[0063] S6. Automatically generate a blind spot inspection track based on the drone's parameter information, the point cloud data of the target to be inspected, the photo-taking points of the target to be inspected, and the equipment inspection specifications;

[0064] S7. Perform reverse deduction based on the blind spot patrol track to simulate the photographic effect, and adjust the blind spot patrol track based on the photographic effect. When the blind spot patrol track meets the photographic requirements, the final blind spot patrol track is published to the UAV management center, and the UAV management center assigns UAVs to conduct autonomous inspections based on the final blind spot patrol track.

[0065] Furthermore, in S3, the substation cloud data is preprocessed to obtain the equipment unit point cloud data, and the equipment unit point cloud data is finely processed, wherein the preprocessing includes: gross error elimination, point cloud thinning, point cloud classification, and equipment unitization; the fine processing includes: classification labeling, unitization labeling, association of unitization with equipment ledger, and inspection point labeling.

[0066] The embodiments of the present invention have the following technical effects:

[0067] The autonomous trajectory deduction system for unmanned aerial vehicles in the complex environment of substations proposed in the present invention manages the ledger data and equipment data of the substation, establishes a high-definition three-dimensional model of the substation using lidar point cloud and image data, completes the classification of substations, the association of equipment units with substation equipment through point cloud data processing, and completes the control of the patrol area by marking patrol points; completes the blind spot analysis of the patrol area through the management of existing patrol equipment, and combines the relevant parameters of the unmanned aerial vehicle and the mounted camera equipment to carry out autonomous trajectory planning and deduction of the target patrol area, thereby improving the three-dimensional collaborative operation and maintenance capability of the substation multi-inspection system, reducing the problem of a large number of overlapping inspection points of different patrol equipment, reducing resource waste, and improving the coverage, flexibility and reliability of patrol. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0069] Figure 1 It is a structural schematic diagram of a UAV autonomous trajectory deduction system in a complex substation environment provided by an embodiment of the present invention;

[0070] Figure 2 It is a flow chart of a method for autonomous trajectory deduction of a UAV in a complex substation environment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0072] The present invention proposes an autonomous trajectory deduction system for UAVs in complex substation environments. Figure 1 is a schematic diagram of the structure of the UAV autonomous trajectory deduction system in the complex environment of the substation provided by the embodiment of the present invention, see Figure 1 , the system includes:

[0073] Management module, storage module, visualization module, point cloud preprocessing module and business application analysis module.

[0074] The management module is used to manage the basic information of the substation, patrol equipment information and patrol tasks.

[0075] Among them, basic information includes equipment design information, equipment acceptance information, equipment ledger information, equipment inspection information, etc.; inspection equipment includes drones, ground robots and fixed gimbal cameras.

[0076] The storage module is connected to the management module and is used to store various data such as basic information of the substation, patrol equipment information, safety specifications, substation site cloud data and equipment single point cloud data.

[0077] The point cloud preprocessing module is connected to the storage module and is used to preprocess the substation cloud data to obtain the equipment single point cloud data, and to perform fine processing on the equipment single point cloud data in combination with the visualization module.

[0078] Among them, preprocessing includes gross error elimination, point cloud thinning, point cloud classification, and equipment individualization; fine processing includes classification labeling, individualization labeling, association of individualization with equipment ledger, and inspection point labeling.

[0079] The visualization module is connected to the point cloud preprocessing module and is used to visualize and render the substation cloud data and the equipment single point cloud data.

[0080] The business application analysis module is connected to the visualization module and is used to specify the target to be inspected. It analyzes the blind spots of the target to be inspected by combining the parameter information of the ground robot and the fixed gimbal camera. It also automatically analyzes the photo taking points of the blind spots of the target to be inspected by combining the parameter information of the drone, the point cloud data of the target to be inspected and the safety specifications, and finally generates the track of the drone inspection.

[0081] Furthermore, the management module includes: a substation management unit, a user management unit, a design data management unit, a safety specification management unit, a task management unit, and a patrol equipment management unit.

[0082] Specifically, the substation management unit is used to manage basic information of the substation.

[0083] The user management unit is used to manage the permissions of different users.

[0084] Design data management unit, used to manage and store parameter information of different equipment in the substation.

[0085] For example, the size, material and other information of the equipment.

[0086] The safety specification management unit is used to store the safety specifications of the substation.

[0087] Among them, safety specifications include equipment design specifications, equipment acceptance specifications, equipment inspection specifications, etc.

[0088] The task management unit is used to manage the autonomous inspection tasks of the substation.

[0089] Among them, autonomous inspection tasks include information such as inspection targets, inspection points, and flight routes.

[0090] The patrol equipment management unit is used to manage the parameter information of the patrol equipment in the substation.

[0091] Furthermore, the storage module includes: a point cloud data storage unit, an image data storage unit, a patrol point and photo point storage unit, a database storage unit, a track file storage unit, a track deduction related file storage unit, and other file storage units.

[0092] Specifically, the point cloud data storage unit is used to store substation cloud data files.

[0093] Among them, the substation cloud data file includes substation cloud data, equipment single point cloud data, etc.

[0094] The image data storage unit is used to store the image data obtained during the process of collecting point cloud data.

[0095] The inspection point and photo point storage unit is used to store the inspection points and photo points of the equipment unit.

[0096] The database storage unit is used to store various parameter information.

[0097] Among them, parameter information includes point cloud rendering parameters, equipment classification parameters, safety specifications, equipment parameter information, patrol equipment parameter information, etc.

[0098] The track file storage unit is used to store the track information of the UAV.

[0099] Each time the track information is modified or adjusted, the updated track information will overwrite the historical track information.

[0100] The track deduction file storage unit is used to store track deduction process files.

[0101] Among them, the track simulation process files include photo effect files, etc.

[0102] Other file storage units are used to store report files, photo point visualization files, etc.

[0103] Furthermore, the point cloud preprocessing module includes: a gross error elimination unit, a point cloud thinning unit, a point cloud classification unit, a classification labeling unit, an equipment unitization unit, a unitization labeling unit, a unitization and equipment inventory association unit, and a patrol point labeling unit.

[0104] Specifically, the gross error elimination unit is used to eliminate gross error points in the point cloud data.

[0105] The point cloud thinning unit is used to thin the point cloud data.

[0106] Among them, the gross error removal and point cloud thinning operations can be selected based on actual conditions.

[0107] The point cloud classification unit is used to classify and identify point cloud data according to device classification parameters.

[0108] Exemplarily, point cloud data belonging to the category of "transformer" are uniformly identified as point cloud data classified as transformers, point cloud data belonging to the category of "disconnector" are uniformly identified as point cloud data classified as disconnectors, and so on. All point cloud data of the substation are classified and identified, and point cloud data of different categories are distinguished by different colors, different rendering methods, different point cloud sizes, etc.

[0109] The classification and labeling unit is used to assist in the classification and labeling of point cloud data according to the equipment classification parameters.

[0110] Specifically, after the point cloud classification unit automatically classifies and identifies the point cloud data according to the equipment classification parameters, the classification and labeling unit manually determines whether there are incorrectly labeled or missing point cloud data, and performs auxiliary classification and labeling for the incorrectly labeled or missing point cloud data.

[0111] The device individualization unit is used to perform individualization recognition on the classified point cloud data.

[0112] Exemplarily, taking the point cloud data of transformer classification as an example, the point cloud data belonging to "transformer No. 1" is uniformly identified as the point cloud data of transformer No. 1, and the point cloud data belonging to "transformer No. 2" is uniformly identified as the point cloud data of transformer No. 2, and so on. The classified point cloud data are identified as individual units, and different point cloud data are distinguished by different colors, different rendering methods, different point cloud sizes, etc.

[0113] The individualized annotation unit is used to assist in individualized annotation of the classified point cloud data.

[0114] Specifically, after the device individualization unit automatically performs individualization recognition on the classified point cloud data, the individualization labeling unit manually determines whether there are incorrectly labeled or missing point cloud data, and performs auxiliary individualization labeling on the incorrectly labeled or missing point cloud data.

[0115] The unit for associating the monomer and the equipment ledger is used to establish the corresponding relationship between the point cloud data of the equipment monomer and the equipment ledger information.

[0116] That is, the point cloud data of each device unit is associated with each device unit recorded in the equipment ledger information to facilitate the management of the point cloud data.

[0117] The patrol point marking unit is used to mark the patrol points of the equipment.

[0118] Furthermore, the visualization module includes: a substation massive point cloud data rendering unit, a point cloud category visualization unit, a single equipment visualization unit, a patrol point visualization unit, a photo point visualization unit, a photo effect simulation visualization unit, a track visualization unit, and a database information visualization unit.

[0119] The substation massive point cloud data rendering unit is used to render the point cloud data.

[0120] The point cloud category visualization unit is used to visualize point cloud data according to device classification parameters.

[0121] The equipment unit visualization unit is used to visualize the point cloud data of the equipment unit according to the equipment ledger information.

[0122] The patrol point visualization unit is used to visualize the patrol points of the equipment unit.

[0123] The photo point visualization unit is used to visualize the photo points and photo view volume of the device unit, where the photo view volume is the range of the photo.

[0124] The photographing effect simulation visualization unit is used to visualize the photographing effect.

[0125] The track visualization unit is used to visualize the track of the UAV.

[0126] The database information visualization unit is used to preview and modify various parameter information stored in the database storage unit.

[0127] Furthermore, the business application analysis module includes: a patrol target designation unit, a blind spot analysis unit, an automatic photo point calculation unit, a photo point adjustment unit, a track automatic generation unit, a track reverse deduction unit, a track adjustment unit, and a track publishing unit.

[0128] Specify the inspection target unit, which is used to specify one or more equipment units as the inspection targets.

[0129] The blind spot analysis unit is used to analyze the blind spots of the target to be inspected by combining the parameter information of the ground robot and the fixed pan-tilt camera.

[0130] Specifically, according to the shooting parameters and sizes of the ground robot and the fixed pan-tilt camera, the shooting range of the ground robot and the fixed pan-tilt camera, the area that can be photographed, and the patrol points included in the area that can be photographed are analyzed, and the area where the remaining patrol points that cannot be photographed are located is the blind spot of the target to be inspected.

[0131] The automatic calculation unit for taking photos is used to automatically analyze the photo points in the blind spots of the target to be inspected by combining the parameter information of the drone, the point cloud data of the equipment unit, and the equipment inspection specifications.

[0132] Specifically, the camera automatically analyzes the blind spots of the inspected targets based on the drone's size parameters, mounted camera parameters, point cloud data of the equipment unit, and equipment inspection specifications. Compared with manually setting the photo points, this method provides more comprehensive coverage, avoids inspection blind spots, and has higher reliability.

[0133] The photographing point adjustment unit is used to adjust the photographing parameters of the drone in combination with the visual volume information of the photographing point.

[0134] The automatic track generation unit is used to generate the track of the drone inspection according to the blind area of ​​the target to be inspected.

[0135] Furthermore, the automatic track generation unit will automatically generate and display the track's safety buffer zone according to the equipment inspection specifications, that is, the safe distance range within which accidents such as collisions will not occur between the drone and each equipment unit.

[0136] The track reverse deduction unit is used to generate inspection and photography effects based on the generated track using the track simulation function.

[0137] The track adjustment unit is used to adjust the track according to the inspection and photography results.

[0138] Specifically, according to the inspection photo effect generated by the track simulation function, it is judged whether the photo effect meets the requirements. If not, the track route is adjusted through the track visualization window until the photo effect meets the requirements, and the final track file is obtained.

[0139] The track publishing unit is used to publish the final track file to the UAV management center.

[0140] The autonomous trajectory deduction system for unmanned aerial vehicles in the complex environment of substations proposed in the present invention manages the ledger data and equipment data of the substation, establishes a high-definition three-dimensional model of the substation using lidar point cloud and image data, completes the classification of substations, the association of equipment units with substation equipment through point cloud data processing, and completes the control of the patrol area by marking patrol points; completes the blind spot analysis of the patrol area through the management of existing patrol equipment, and combines the relevant parameters of the unmanned aerial vehicle and the mounted camera equipment to carry out autonomous trajectory planning and deduction of the target patrol area, thereby improving the three-dimensional collaborative operation and maintenance capability of the substation multi-inspection system, reducing the problem of a large number of overlapping inspection points of different patrol equipment, reducing resource waste, and improving the coverage, flexibility and reliability of patrol.

[0141] Figure 2 is a flow chart of a method for autonomous trajectory deduction of a UAV in a complex substation environment provided by an embodiment of the present invention. The method is implemented by the above-mentioned system for autonomous trajectory deduction of a UAV in a complex substation environment. Figure 2 As shown, the specific steps include:

[0142] S1. Obtain basic information of the substation, patrol equipment information and patrol task information.

[0143] Specifically, the basic information includes equipment design information, equipment acceptance information, equipment inventory information, equipment inspection information, etc. The inspection equipment includes drones, ground robots and fixed gimbal cameras.

[0144] S2. Obtain substation cloud data.

[0145] Specifically, the point cloud data of the substation is collected by laser radar, and the collected point cloud data is uploaded to the storage module.

[0146] S3. Pre-process the substation cloud data to obtain the equipment unit point cloud data, and finely process the equipment unit point cloud data to determine the inspection points of the equipment unit.

[0147] Specifically, after uploading is completed, the substation cloud data is preprocessed through the point cloud preprocessing module and the visualization module. The preprocessing includes: gross error elimination, point cloud thinning, point cloud classification, and equipment individualization. After obtaining the equipment individual point cloud data, the equipment individual point cloud data is then finely processed. The fine processing includes: classification labeling, individualization labeling, association of individualization with equipment ledgers, and inspection point labeling, and finally the inspection points of the equipment individual are determined.

[0148] Among them, after the preprocessing process is completed, the point cloud data is three-dimensionally rendered through the substation massive point cloud data rendering unit, and the point cloud editing mode is entered. On the basis of the preprocessed point cloud data, the category of the selected point cloud data set and the data information of the equipment unit to which the selected point cloud data belongs can be set through polygon selection, box selection, point selection, etc., the inspection points of the equipment units are marked, the classification and unitization results are improved, and the association relationship between the point cloud data of the equipment units and the equipment ledger is established. After marking the inspection points, the improved point cloud data category, unit point cloud data, and inspection point data are stored in the storage module.

[0149] S4. Designate one or more equipment units as targets to be inspected, and determine the blind spots of the targets to be inspected based on the parameter information of the ground robot, the fixed PTZ camera, and the inspection points of the equipment units.

[0150] Specifically, according to the shooting parameters and sizes of the ground robot and the fixed pan-tilt camera, the shooting range of the ground robot and the fixed pan-tilt camera, the area that can be photographed, and the patrol points included in the area that can be photographed are analyzed, and the area where the remaining patrol points that cannot be photographed are located is the blind spot of the target to be inspected.

[0151] S5. According to the parameter information of the UAV and the equipment inspection specification, the photographing points corresponding to the inspection points in the blind area of ​​the target to be inspected are automatically calculated.

[0152] Specifically, the photographing points corresponding to the inspection points in the blind spots of the inspected target are automatically calculated according to the parameter information of the UAV, the point cloud data of the equipment unit and the equipment inspection specification, wherein the photographing points are the automatically calculated points with the best photographing effect.

[0153] S6. Automatically generate a blind spot inspection track based on the drone's parameter information, the point cloud data of the target to be inspected, the photo taking points of the target to be inspected, and the equipment inspection specifications.

[0154] Specifically, the size parameters of the UAV, the parameters of the mounted camera, the point cloud data of the equipment unit, and the equipment inspection specifications are combined to automatically analyze the photo-taking points in the blind spots of the target to be inspected, and the blind spot inspection track is automatically generated according to the photo-taking points in the blind spots of the target to be inspected. In addition, the safety buffer zone of the track is automatically generated and displayed according to the equipment inspection specifications, that is, the safe distance range within which accidents such as collisions will not occur between the UAV and each equipment unit.

[0155] S7. Perform reverse deduction based on the blind spot patrol track to simulate the photographic effect, and adjust the blind spot patrol track based on the photographic effect. When the blind spot patrol track meets the photographic requirements, the final blind spot patrol track is published to the UAV management center, and the UAV management center assigns UAVs to conduct autonomous inspections based on the final blind spot patrol track.

[0156] Specifically, the track simulation function is used to reversely deduce the blind spot patrol track to simulate the photo effect, and based on the inspection photo effect generated by the track simulation function, it is judged whether the photographed photo effect meets the requirements. If it does not meet the requirements, the track route is adjusted through the track visualization window until the photographed photo effect meets the requirements, and the final blind spot patrol track is obtained and published to the UAV management center. The UAV management center assigns UAVs to conduct autonomous inspections based on the final blind spot patrol track.

[0157] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0158] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0159] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. The autonomous trajectory deduction system of UAV in the complex environment of substation is characterized by: include: Management module, storage module, visualization module, point cloud pre-processing module and business application analysis module; The management module is used to manage the basic information of the substation, patrol equipment information and patrol tasks; the basic information includes equipment design information, equipment acceptance information, equipment ledger information and equipment patrol information, and the patrol equipment includes drones, ground robots and fixed pan-tilt cameras; The storage module is connected to the management module and is used to store basic information of the substation, patrol equipment information, safety specifications, substation site cloud data and equipment single point cloud data; The storage module includes: a point cloud data storage unit, an image data storage unit, a patrol point and photo point storage unit, a database storage unit, a track file storage unit, a track deduction related file storage unit, and other file storage units; The point cloud data storage unit is used to store substation cloud data files; wherein the substation cloud data files include substation cloud data and equipment single point cloud data; The image data storage unit is used to store the image data acquired during the process of collecting point cloud data; The inspection point and photo point storage unit is used to store the inspection points and photo points of the equipment unit; The database storage unit is used to store various parameter information; wherein the parameter information includes point cloud rendering parameters, equipment classification parameters, safety specifications, equipment parameter information, and patrol equipment parameter information; The track file storage unit is used to store the track information of the UAV; The track deduction file storage unit is used to store track deduction process files; the track deduction process files include photo effect files; The other file storage unit is used to store report files and photo point visualization files; The point cloud preprocessing module is connected to the storage module, and is used to preprocess the substation cloud data to obtain the equipment monomer point cloud data, and finely process the equipment monomer point cloud data in combination with the visualization module; wherein the preprocessing includes gross error elimination, point cloud thinning, point cloud classification, and equipment monomerization, and the fine processing includes classification labeling, monomerization labeling, association of monomerization with equipment ledger, and inspection point labeling; The visualization module is connected to the point cloud preprocessing module and is used to visualize and render the substation cloud data and the equipment single point cloud data; The business application analysis module is connected to the visualization module and is used to specify the target to be inspected, analyze the blind spots of the target to be inspected in combination with the parameter information of the ground robot and the fixed pan-tilt camera, and automatically analyze the photo taking points of the blind spots of the target to be inspected in combination with the parameter information of the drone, the point cloud data of the target to be inspected and the safety specifications, and finally generate the track of the drone inspection; The method for autonomous trajectory deduction of unmanned aerial vehicles in a complex substation environment is realized by the autonomous trajectory deduction system of unmanned aerial vehicles in a complex substation environment, comprising the following steps: S1. Obtain basic information of the substation, patrol equipment information and patrol task information; the basic information includes equipment design information, equipment acceptance information, equipment ledger information and equipment patrol information; patrol equipment includes drones, ground robots and fixed pan-tilt cameras; S2, obtaining substation cloud data; S3, pre-processing the substation cloud data to obtain equipment unit point cloud data, and finely processing the equipment unit point cloud data to determine the inspection points of the equipment unit; S4. Designate one or more equipment units as the inspection targets, and determine the blind spots of the inspection targets according to the parameter information of the ground robot, the fixed PTZ camera, and the inspection points of the equipment units; S5. Automatically calculate the photographing points corresponding to the inspection points in the blind area of ​​the target to be inspected according to the parameter information of the drone and the equipment inspection specifications; S6. Automatically generate a blind spot inspection track based on the drone's parameter information, the point cloud data of the target to be inspected, the photo-taking points of the target to be inspected, and the equipment inspection specifications; S7. Perform reverse deduction based on the blind spot patrol track to simulate the photographic effect, and adjust the blind spot patrol track according to the photographic effect. When the blind spot patrol track meets the photographic requirements, the final blind spot patrol track is published to the UAV management center, and the UAV management center assigns UAVs to perform autonomous inspections based on the final blind spot patrol track.

2. The autonomous trajectory deduction system for unmanned aerial vehicles in a complex substation environment according to claim 1 is characterized in that: The management module includes: a substation management unit, a user management unit, a design data management unit, a safety specification management unit, a task management unit, and a patrol equipment management unit; The substation management unit is used to manage basic information of the substation; The user management unit is used to manage the permissions of different users; The design data management unit is used to manage and store parameter information of different equipment in the substation; The safety specification management unit is used to store the safety specifications of the substation; wherein the safety specifications include equipment design specifications, equipment acceptance specifications, and equipment inspection specifications; The task management unit is used to manage the autonomous inspection tasks of the substation; the autonomous inspection tasks include the inspection targets, inspection points, and track routes; The patrol equipment management unit is used to manage parameter information of patrol equipment in the substation.

3. The autonomous trajectory deduction system for unmanned aerial vehicles in a complex substation environment according to claim 1 is characterized in that: The point cloud preprocessing module includes: a gross error elimination unit, a point cloud thinning unit, a point cloud classification unit, a classification labeling unit, an equipment unitization unit, a unitization labeling unit, a unitization and equipment ledger association unit, and a patrol point labeling unit; The gross error elimination unit is used to eliminate gross error points in the point cloud data; The point cloud thinning unit is used to thin the point cloud data; The point cloud classification unit is used to classify and identify the point cloud data according to the device classification parameters; The classification and labeling unit is used to perform auxiliary classification and labeling on the point cloud data according to the equipment classification parameters; The device individualization unit is used to perform individualization recognition on the classified point cloud data; The individualization annotation unit is used to perform auxiliary individualization annotation on the classified point cloud data; The unit for associating the monomerization and equipment ledger is used to establish a corresponding relationship between the point cloud data of the equipment monomer and the equipment ledger information; The patrol point marking unit is used to mark the patrol points of the equipment unit.

4. The autonomous trajectory deduction system for unmanned aerial vehicles in a complex substation environment according to claim 3 is characterized in that: The visualization module includes: a substation massive point cloud data rendering unit, a point cloud category visualization unit, a device unit visualization unit, a patrol point visualization unit, a photo point visualization unit, a photo effect simulation visualization unit, a track visualization unit, and a database information visualization unit; The substation massive point cloud data rendering unit is used to render the point cloud data; The point cloud category visualization unit is used to visualize the point cloud data according to the device classification parameters; The device unit visualization unit is used to visualize the point cloud data of the device unit according to the device ledger information; The patrol point visualization unit is used to visualize the patrol points of the equipment unit; The photographing point visualization unit is used to visualize the photographing points and photographing view volume of the equipment unit; The photographic effect simulation and visualization unit is used to visualize the photographic effect; The track visualization unit is used to visualize the track of the UAV; The database information visualization unit is used to preview and modify various parameter information stored in the database storage unit.

5. The autonomous trajectory deduction system for unmanned aerial vehicles in a complex substation environment according to claim 4 is characterized in that: The business application analysis module includes: a patrol target designation unit, a blind spot analysis unit, an automatic photo point calculation unit, a photo point adjustment unit, a track automatic generation unit, a track reverse deduction unit, a track adjustment unit, and a track publishing unit; The designated inspection target unit is used to designate one or more equipment units as inspection targets; The blind spot analysis unit is used to analyze the blind spot of the target to be inspected by combining parameter information of the ground robot and the fixed pan-tilt camera; The automatic calculation unit for taking photos is used to automatically analyze the photo points of the blind spots of the target to be inspected by combining the parameter information of the drone, the point cloud data of the equipment unit, and the equipment inspection specification; The photographing point adjustment unit is used to adjust the photographing parameters of the drone in combination with the visual volume information of the photographing point; The automatic track generation unit is used to generate the track of the drone patrol according to the blind area of ​​the target to be inspected; The track reverse deduction unit is used to generate inspection photography effects based on the generated track using the track simulation function; The track adjustment unit is used to adjust the track according to the inspection and photography effect; The track publishing unit is used to publish the final track file to the UAV management center.

6. The autonomous trajectory deduction system for unmanned aerial vehicles in a complex substation environment according to claim 1 is characterized in that: In S3, the substation cloud data is preprocessed to obtain equipment unit point cloud data, and the equipment unit point cloud data is finely processed, wherein the preprocessing includes: gross error elimination, point cloud thinning, point cloud classification, and equipment unitization; the fine processing includes: classification labeling, unitization labeling, association of unitization with equipment ledger, and inspection point labeling.

Images