Substation unmanned aerial vehicle autonomous inspection system and method

Abstract

The invention discloses a transformer substation unmanned aerial vehicle autonomous inspection system which comprises an unmanned aerial vehicle platform, a three-dimensional modeling module, an inspection route setting module, an autonomous inspection module, a mobile monitoring platform, an image acquisition module, an image processing module, an alarm module, a visualization module, a data storage module and a wireless communication module. Wherein the three-dimensional modeling module comprises laser radar equipment and three-dimensional modeling software, the routing inspection route setting module is used for setting different routing inspection routes according to different routing inspection modes and corresponding routing inspection rules, the autonomous routing inspection module comprises a navigation system and a positioning base station, and the mobile monitoring platform comprises a remote controller and vehicle-mounted charging equipment. The image processing module is used for processing and analyzing different types of collected images and different purposes of collected images by using different algorithms so as to timely discover abnormity and give an alarm; the method has the advantages of being good in inspection abnormity processing effect, good in positioning effect, convenient to use and good in data processing effect.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicle inspection, and in particular relates to a substation unmanned aerial vehicle autonomous inspection system and method. Background Art

[0002] Compared with manual inspection, drone inspection has made qualitative improvements in safety, efficiency, quality, etc. Using drones for inspection has become an inevitable choice for intelligent power inspection. However, with the gradual application of drone inspection, some problems have gradually been exposed.

[0003] After drones were widely used in the power industry, more and more power supply companies began to apply drone inspection technology to the daily inspection of substations. From the practical application results, using drones to replace manual inspection tasks can not only significantly improve work efficiency, but also detect hidden faults in a timely manner, which provides good technical support for improving inspection and maintenance effects and subsequent maintenance of substation faults.

[0004] However, the existing UAV inspection functions are not perfect. For example, various anomalies that occur during the inspection process cannot be effectively monitored and processed, and the UAV positioning effect at the image acquisition point is insufficient. At the same time, the image data returned by the acquisition equipment is large in volume and difficult to process. There are generally problems such as high computational requirements, long calculation time, and poor generalization. In order to solve the above problems, it is necessary to develop a substation UAV autonomous inspection system and method. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of the prior art and to provide a substation drone autonomous inspection system and method with good inspection exception handling effect, good positioning effect, easy use, and good data processing effect. The drone can autonomously complete the effective inspection of each substation and its equipment on the set route.

[0006] The object of the present invention is achieved as follows: In a first aspect, a substation unmanned aerial vehicle autonomous inspection system is provided, comprising: UAV platforms, including UAVs and secure platforms for parking, taking off, landing and charging the UAVs; A three-dimensional modeling module, including a laser radar device and a three-dimensional modeling software provided therewith, for establishing a three-dimensional model of a substation; Inspection route setting module, used to set different inspection routes according to different inspection modes and corresponding inspection rules. The inspection routes include the inspection track inside each substation, the arrival track between multiple substations, and the return track. The autonomous inspection module includes a navigation system and positioning base stations that are set up at each substation in a one-to-one correspondence, which is used to ensure that the drone flies accurately according to the set inspection route and accurately locates during the inspection process; The mobile monitoring platform includes a remote control and an on-board charging device to follow up and monitor the UAV in flight. The remote control is used to take over the UAV on site in case of an accident, and the on-board charging device is used to stay at any time and provide charging function for the UAV. Image acquisition module, including laser radar equipment, high-definition camera, infrared thermal imager and ultraviolet thermal imager, used to collect all-round images of substation equipment and its surrounding environment; The image processing module uses different algorithms to process and analyze different types of collected images and images for different purposes, so as to judge the overall operating status of the substation equipment and the details corresponding to different inspection modes, and send an alarm module in time when an abnormality occurs; The alarm module is used to send the alarm information to the relevant responsible persons in a timely manner and issue an audible and visual alarm; The visualization module is used to visualize the three-dimensional model of the substation, the real-time inspection path of the drone and the real-time inspection status of the substation equipment, and highlight the abnormal situations that occur during the inspection process; The data storage module is used to store each inspection data in chronological order and establish an autonomous inspection route data archive; The wireless communication module is used to complete data transmission between the drone, mobile monitoring platform and remote inspection center.

[0007] Preferably, it also includes an obstacle avoidance module mounted on the drone, which is used to scan whether there are obstacles on the drone's flight path, and to analyze and determine whether a reliable safety strategy can be implemented. In case of an emergency, the remote control can be notified in time to immediately take over and control the flight status of the drone. This is specifically achieved using lidar equipment and flight control algorithms.

[0008] Preferably, it also includes a meteorological monitoring module mounted on the drone, which is used to monitor the flight environment. When it is found that the flight environment does not meet the safety inspection requirements, the inspection task is terminated and an abnormal instruction is sent to the remote control to notify it to take over immediately.

[0009] Preferably, the laser radar device has built-in point cloud data processing software for performing point cloud filtering, registration, segmentation and feature extraction on laser point cloud data.

[0010] Preferably, the inspection modes include routine inspection, comprehensive inspection, lights-off inspection, professional inspection and special inspection, and the inspection rules include overall inspection rules and specific rules corresponding to different inspection modes. The overall inspection rules are to check normal operation on time, focus on inspection during peak and high temperatures, check in time during sudden weather changes, conduct special inspections on key equipment and carefully check weak equipment.

[0011] Preferably, the algorithms include a point cloud registration algorithm, a segmentation algorithm and a surface reconstruction algorithm for images collected by a laser radar device, an image enhancement algorithm, a target detection algorithm and an image matching algorithm for images collected by a high-definition camera, a temperature threshold algorithm, a thermal field analysis algorithm and a comparative analysis algorithm for an infrared thermal imager, and an ultraviolet signal detection algorithm, an intensity analysis algorithm and a positioning algorithm for an ultraviolet thermal imager.

[0012] In a second aspect, a substation drone autonomous inspection method is provided, comprising the aforementioned substation drone autonomous inspection system and the following steps: S1: The staff selects the inspection mode through the remote control and sends a remote control signal to control the drone to take off from the safety platform with one click and perform the inspection task according to the set route; S2: During the flight, the drone completes autonomous flight, autonomous hovering and autonomous shooting tasks according to the set program; S3: During the autonomous hovering process, the drone adjusts its posture according to the settings to complete the autonomous shooting task, collects images and wirelessly sends them back to the remote inspection center to complete the image processing and storage functions; S4: During the image processing process, if any abnormality is found, the relevant responsible person will be notified in time, and the abnormality will be processed according to the set procedures and an audible and visual alarm will be issued; S5: When the drone reaches the set destination, the inspection mission is completed and the drone returns to the safety platform autonomously according to the set route. If there are no other tasks, the staff controls the drone to land on the safety platform with one click through the remote control, fully charges and waits for the next mission.

[0013] Preferably, during the flight, the drone autonomously detects its battery power. When it detects that the battery power drops to a safe threshold, it sends a charging instruction to the mobile monitoring platform, the vehicle stops, and the drone returns to its work station after being fully charged through the on-board charging equipment to continue subsequent inspection tasks. The vehicle starts and continues to follow up the drone.

[0014] Preferably, when the mobile monitoring platform follows up on the drone during the inspection mission, if a critical defect is found on site, the staff will immediately report it to the remote inspection center, take over the drone immediately, and suspend the inspection mission.

[0015] Preferably, when the drone is performing an inspection task, the remote inspection center monitors the drone's return signal in real time. When a link interruption occurs, a reconnection signal is sent in time. When the connection fails, a pause command is immediately sent to the on-board monitoring platform. The staff immediately takes over the drone on site through the remote control and suspends the inspection task.

[0016] Due to the adoption of the above technical solution, the beneficial effects of the present invention are: (1) The present invention uses a drone, a remote inspection center, an image acquisition module, an image processing module and an alarm module, which can promptly warn of abnormalities in the image acquisition and processing process. At the same time, the present invention uses a mobile monitoring platform, which can promptly detect and handle abnormal situations on site, thereby achieving the goal of responding to various abnormalities that occur during the inspection process and effectively monitoring and handling them; (2) The present invention uses a navigation system and a positioning base station installed in the substation to ensure the accuracy of the UAV inspection route flight and the accuracy of the positioning of the UAV point when collecting images during the inspection process; (3) The present invention adopts pre-set inspection routes corresponding to different inspection modes, which can be very conveniently adapted to various inspection requirements; (4) The present invention uses a laser radar device with built-in point cloud data processing software, which facilitates on-site processing of point cloud image data collected by the laser radar device. Only the processed valid image data needs to be sent back, which reduces the pressure of data transmission and the pressure of data processing in the background center. In general, the present invention has the advantages of good inspection abnormality handling effect, good positioning effect, easy use and good data processing effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the system composition of the present invention.

[0018] Figure 2 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention is further specifically described below through embodiments and in conjunction with the accompanying drawings.

[0020] like Figure 1 As shown, the present invention provides a substation UAV autonomous inspection system, which is mainly composed of a UAV platform, a three-dimensional modeling module, an inspection route setting module, an autonomous inspection module, a mobile monitoring platform, an image acquisition module, an image processing module, an alarm module, a visualization module, a data storage module and a wireless communication module.

[0021] Among them, the drone platform includes a drone and a safety platform for parking, taking off, landing and charging the drone. The safety platform is equipped with a number of drones depending on the actual inspection tasks undertaken.

[0022] Among them, the 3D modeling module includes a laser radar device and a matching 3D modeling software. The laser radar device is mounted on a drone, and the 3D modeling software is mounted on a remote inspection center server. The 3D modeling software is used to establish a 3D model of the substation. Through comparative analysis of the 3D model of the substation, the position, shape, etc. of the substation as a whole and each device in the substation are found. Anything above the threshold is judged as abnormal.

[0023] Among them, the inspection route setting module is used to set different inspection routes according to different inspection modes and corresponding inspection rules. The inspection routes include the inspection tracks within each substation, the arrival tracks between multiple substations, and the return tracks.

[0024] Inspection modes include routine inspection, comprehensive inspection, lights-off inspection, professional inspection and special inspection. Inspection rules include overall inspection rules and specific rules corresponding to different inspection modes. The overall inspection rules are to check normal operation on time, focus on peak and high temperature inspections, promptly check sudden weather changes, conduct special inspections on key equipment and carefully check weak equipment. All inspections can be carried out according to the existing relevant regulations of State Grid.

[0025] Among them, the autonomous inspection module includes a navigation system and a positioning base station set up one by one at each substation, which is used to ensure that the drone flies accurately according to the set inspection route and accurately locates during the inspection process.

[0026] The positioning base station can improve the positioning accuracy of the drone, especially in substation areas where the wireless communication signal is poor. When used in conjunction with the drone's navigation system, it can ensure that the drone flies accurately along the preset route.

[0027] Among them, the mobile monitoring platform includes a remote control and a vehicle-mounted charging device. The staff will follow and monitor the flying drone in the vehicle. When an accident occurs on the drone on site, the staff can take over the drone immediately through the remote control. The vehicle-mounted charging device can stop at any time and provide charging function for the drone to increase the drone's cruising range, ensure that the drone continues to perform inspection tasks, and improve inspection efficiency.

[0028] Among them, the image acquisition module includes lidar equipment, high-definition cameras, infrared thermal imagers and ultraviolet thermal imagers, which are used to collect all-round images of substation equipment and its surrounding environment.

[0029] The laser radar equipment has built-in point cloud data processing software, which is used to perform point cloud filtering, registration, segmentation and feature extraction on the laser point cloud data in real time. Through the processed effective image data, the amount of wireless communication data is reduced, and the data processing workload of the remote inspection center is reduced.

[0030] Among them, the image processing module uses different algorithms to process and analyze collected images of different categories and for different purposes, so as to judge the overall operating status of the substation equipment and the details corresponding to different inspection modes, and send an alarm module in time when an abnormality occurs.

[0031] The image analysis collected by the laser radar equipment adopts point cloud registration algorithm, segmentation algorithm and surface reconstruction algorithm. The point cloud registration algorithm is to register the point cloud data collected from different perspectives to obtain a complete three-dimensional model of the substation. The segmentation algorithm is to segment the three-dimensional point cloud data to distinguish different devices or objects. The surface reconstruction algorithm is based on the point cloud data to reconstruct the surface shape of the equipment for better visualization and analysis, so as to obtain the three-dimensional shape and size of the equipment for detecting abnormal conditions such as deformation and displacement of the equipment, and obtain the relative position relationship between the equipment to determine whether it complies with safety regulations. Point cloud data at different time points are obtained to monitor changes in the equipment.

[0032] The image analysis collected by high-definition cameras adopts image enhancement algorithm, target detection algorithm and image matching algorithm. The image enhancement algorithm is used to improve the contrast and clarity of the image in order to better observe the details of the equipment. The target detection algorithm is based on deep learning and is used to detect specific parts and logos on the equipment. The image matching algorithm is used to compare images taken at different times and detect changes in the equipment, so as to analyze the appearance of the equipment, such as whether it is damaged, rusted, etc., whether the logos and numbers on the equipment are clean and readable, and whether there are missing or loose parts of the equipment.

[0033] The infrared thermal imager collects and analyzes images using temperature threshold algorithms, thermal field analysis algorithms, and comparative analysis algorithms. The temperature threshold algorithm is used to set different temperature thresholds and mark high-temperature areas in the image. The thermal field analysis algorithm is used to analyze the temperature distribution in the thermal image and determine the hotspot location and temperature gradient. The comparative analysis algorithm is used to compare thermal images of different times or different devices and detect temperature changes, thereby discovering overheated parts of the equipment, such as joints, busbars, etc., indicating possible hidden faults, evaluating the heat dissipation of the equipment, determining whether it is operating normally, and analyzing the temperature change trend of the equipment through long-term testing.

[0034] The image analysis collected by the ultraviolet thermal imager adopts ultraviolet signal detection algorithm, intensity analysis algorithm and positioning algorithm. The ultraviolet signal monitoring algorithm is used to identify the discharge signal in the ultraviolet image, the intensity analysis algorithm is used to analyze the intensity of the electrical signal and judge the severity of the discharge, and the positioning algorithm is used to determine the specific location of the discharge on the equipment, thereby monitoring the local discharge phenomenon of the equipment, discovering insulation faults in advance, evaluating the severity of the discharge, providing a basis for equipment maintenance, determining the discharge location, and facilitating targeted maintenance.

[0035] Among them, the alarm module is used to send the alarm information to the relevant responsible persons in a timely manner and issue an audible and visual alarm. The location of the audible and visual alarm can be set as needed.

[0036] Among them, the visualization module is used to present the three-dimensional model of the substation, the real-time inspection path of the drone and the real-time inspection status of the substation equipment in a three-dimensional visual way, and highlight the abnormal situations that occur during the inspection process, which are displayed in the remote inspection center through a large-screen display.

[0037] Among them, the data storage module is used to store the data of each inspection in chronological order and establish an independent inspection route data archive to facilitate subsequent queries and big data analysis of historical data.

[0038] Among them, the wireless communication module is used to complete data transmission between the drone, mobile monitoring platform and remote inspection center.

[0039] During specific implementation, the drone can also be equipped with an obstacle avoidance module (implemented using ultrasonic sensors, millimeter-wave radars and other obstacle avoidance sensors) and a weather monitoring module (implemented using environmental sensors).

[0040] Among them, the obstacle avoidance module is used to scan whether there are obstacles on the UAV's flight path, and to analyze and judge whether a reliable and safe strategy can be implemented. In case of an emergency, it will promptly notify the remote control to immediately take over and control the UAV's flight status. It is specifically implemented using lidar equipment and flight control algorithms.

[0041] Among them, the meteorological monitoring module is used to monitor the flight environment. If it is found that the flight environment does not meet the safety inspection requirements, the inspection task will be terminated and the abnormal instructions will be sent to the mobile monitoring platform to notify the staff to take over on site immediately to protect the expensive drone from damage.

[0042] like Figure 2 As shown, the present invention provides a substation drone autonomous inspection method, including the above-mentioned substation drone autonomous inspection system and the following steps: S1: The staff selects the inspection mode through the remote control and sends a remote control signal to control the drone to take off from the safety platform with one click and perform the inspection task according to the set route; S2: During the flight, the drone completes autonomous flight, autonomous hovering and autonomous shooting tasks according to the set program; S3: During the autonomous hovering process, the drone adjusts its posture according to the settings to complete the autonomous shooting task, collects images and wirelessly sends them back to the remote inspection center to complete the image processing and storage functions; S4: During the image processing process, if any abnormality is found, the relevant responsible person will be notified in time, and the abnormality will be processed according to the set procedures and an audible and visual alarm will be issued; S5: When the drone reaches the set destination, the inspection mission is completed and the drone returns to the safety platform autonomously according to the set route. If there are no other tasks, the staff controls the drone to land on the safety platform with one click through the remote control, fully charges and waits for the next mission.

[0043] During the flight, the drone autonomously checks its battery power. When it detects that the battery power has dropped to a safe threshold, it sends a charging command to the mobile monitoring platform, the vehicle stops, and the drone returns to its work station after being fully charged through the on-board charging equipment to continue the subsequent inspection mission. The vehicle starts and continues to follow the drone.

[0044] When the mobile monitoring platform follows up on the drone's inspection mission and finds critical defects on site, the staff immediately reports it to the remote inspection center, takes over the drone immediately, and suspends the inspection mission.

[0045] When the drone is performing inspection tasks, the remote inspection center monitors the drone's return signal in real time. When a link interruption occurs, it sends a reconnection signal in time. When the connection fails, it immediately sends a pause command to the on-board monitoring platform. The staff immediately takes over the drone on site through the remote control and suspends the inspection task.

[0046] In summary, the present invention establishes a three-dimensional model of the substation, sets the inspection route for autonomous flight, autonomous hovering and autonomous photography, reduces manual intervention, combines the autonomous inspection route during the inspection process, implements one-key takeoff and one-key landing according to the autonomous inspection and photography methods, takes clear pictures of the equipment during the inspection, analyzes the picture data in real time to detect abnormalities, and establishes an autonomous inspection route data file.

[0047] 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 above embodiments, those skilled in the art should understand that the specific implementation modes of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A substation drone autonomous inspection system, characterized by: include UAV platforms, including UAVs and secure platforms for parking, taking off, landing and charging the UAVs; A three-dimensional modeling module, including a laser radar device and a three-dimensional modeling software provided therewith, for establishing a three-dimensional model of a substation; Inspection route setting module, used to set different inspection routes according to different inspection modes and corresponding inspection rules. The inspection routes include the inspection track inside each substation, the arrival track between multiple substations, and the return track. The autonomous inspection module includes a navigation system and positioning base stations that are set up at each substation in a one-to-one correspondence, which is used to ensure that the drone flies accurately according to the set inspection route and accurately locates during the inspection process; The mobile monitoring platform includes a remote control and an on-board charging device to follow up and monitor the UAV in flight. The remote control is used to take over the UAV on site in case of an accident, and the on-board charging device is used to stay at any time and provide charging function for the UAV. Image acquisition module, including laser radar equipment, high-definition camera, infrared thermal imager and ultraviolet thermal imager, used to collect all-round images of substation equipment and its surrounding environment; The image processing module uses different algorithms to process and analyze different types of collected images and images for different purposes, so as to judge the overall operating status of the substation equipment and the details corresponding to different inspection modes, and send an alarm module in time when an abnormality occurs; The alarm module is used to send the alarm information to the relevant responsible persons in a timely manner and issue an audible and visual alarm; The visualization module is used to visualize the three-dimensional model of the substation, the real-time inspection path of the drone and the real-time inspection status of the substation equipment, and highlight the abnormal situations that occur during the inspection process; Data storage module, used to store each inspection data in chronological order and establish autonomous inspection route data archive; The wireless communication module is used to complete data transmission between the drone, mobile monitoring platform and remote inspection center.

2. The substation drone autonomous inspection system according to claim 1 is characterized by: It also includes an obstacle avoidance module mounted on the drone, which is used to scan whether there are obstacles on the drone's flight path, and to analyze and determine whether a reliable safety strategy can be implemented. In case of an emergency, it will promptly notify the remote control to immediately take over and control the drone's flight status. This is specifically achieved using lidar equipment and flight control algorithms.

3. The substation drone autonomous inspection system according to claim 1 is characterized by: It also includes a meteorological monitoring module mounted on the drone, which is used to monitor the flight environment. If it is found that the flight environment does not meet the safety inspection requirements, the inspection task will be terminated and the abnormal instruction will be sent to the mobile monitoring platform to notify it to take over immediately.

4. The substation drone autonomous inspection system according to claim 1 is characterized by: The laser radar device has built-in point cloud data processing software for performing point cloud filtering, registration, segmentation and feature extraction on laser point cloud data.

5. The substation drone autonomous inspection system according to claim 1 is characterized by: The inspection modes include routine inspection, comprehensive inspection, lights-off inspection, professional inspection and special inspection. The inspection rules include general inspection rules and specific rules corresponding to different inspection modes. The general inspection rules are to check normal operation on time, focus on inspection during peak and high temperatures, check sudden weather changes in a timely manner, conduct special inspections on key equipment and carefully check weak equipment.

6. The substation drone autonomous inspection system according to claim 1 is characterized by: The algorithms include point cloud registration algorithm, segmentation algorithm and surface reconstruction algorithm for laser radar equipment to collect images, image enhancement algorithm, target detection algorithm and image matching algorithm for high-definition camera to collect images, temperature threshold algorithm, thermal field analysis algorithm and comparative analysis algorithm for infrared thermal imager, and ultraviolet signal detection algorithm, intensity analysis algorithm and positioning algorithm for ultraviolet thermal imager.

7. A substation drone autonomous inspection method, characterized in that: The invention comprises the substation drone autonomous inspection system according to any one of claims 1 to 6 and the following steps: S1: The staff selects the inspection mode through the remote control and sends a remote control signal to control the drone to take off from the safety platform with one click and perform the inspection task according to the set route; S2: During the flight, the drone completes autonomous flight, autonomous hovering and autonomous shooting tasks according to the set program; S3: During the autonomous hovering process, the drone adjusts its posture according to the settings to complete the autonomous shooting task, collects images and wirelessly sends them back to the remote inspection center to complete the image processing and storage functions; S4: During the image processing process, if any abnormality is found, the relevant responsible person will be notified in time, and the abnormality will be processed according to the set procedures and an audible and visual alarm will be issued; S5: When the drone reaches the set destination, the inspection mission is completed and the drone returns to the safety platform autonomously according to the set route. If there are no other tasks, the staff controls the drone to land on the safety platform with one click through the remote control, fully charges and waits for the next mission.

8. The substation drone autonomous inspection method according to claim 7 is characterized by: During the flight, the drone autonomously checks its battery power. When it detects that the battery power has dropped to a safe threshold, it sends a charging command to the mobile monitoring platform, the vehicle stops, and the drone returns to its work station after being fully charged through the on-board charging equipment to continue the subsequent inspection mission. The vehicle starts and continues to follow the drone.

9. The substation drone autonomous inspection method according to claim 7 is characterized by: When the mobile monitoring platform follows up on the drone's inspection mission and finds critical defects on site, the staff immediately reports it to the remote inspection center, takes over the drone immediately, and suspends the inspection mission.

10. The substation drone autonomous inspection method according to claim 7 is characterized by: When the drone is performing inspection tasks, the remote inspection center monitors the drone's return signal in real time. When a link interruption occurs, it sends a reconnection signal in time. When the connection fails, it immediately sends a pause command to the on-board monitoring platform. The staff immediately takes over the drone on site through the remote control and suspends the inspection task.

Images