Method and device for synchronizing flight routes of unmanned aerial vehicle (UAV) inspection of power distribution lines

Abstract

The present invention provides a method and device for synchronizing the inspection route of a distribution network line drone, which belongs to the field of drone inspection technology. The method includes: obtaining historical inspection data of the distribution network line in the inspection area; extracting features of the inspection data contained in n historical sub-inspection data to form n inspection data matrix sets M={M1, M2, ...Mn}; determining the inspection data matrix Mi corresponding to the drone that is performing the inspection task; when the real-time inspection matrix G matches the inspection data matrix Mi, using the eigenvalue λi of the inspection data matrix Mi as the synchronization data of the current drone inspection route, and sending the synchronization data to the ground server control center. By adopting this solution, the drone inspection route synchronization can be quickly performed in a lightweight manner.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle inspection, and in particular to a method and device for synchronizing a distribution network line unmanned aerial vehicle inspection route. Background Art

[0002] Drone system solutions are used for power line inspections, transmission tower inspections, substation and cooling tower inspections, and more. Survey drone services aided by thermal imaging sensors can provide a more in-depth and comprehensive assessment of drone power line inspections. Drones are able to quickly map out an area and traverse power lines while avoiding towers and other potential hazards. Because drones are agile, small, and lightweight, they can cover many areas that traditional aircraft cannot. And, because they are unmanned, they do not put workers in danger. It has many benefits, including restoring safety, reducing downtime, optimizing data output, and improving operational efficiency.

[0003] With 3D mapping systems, drones can determine the most efficient route through a larger installation. They can fly a complete circuit between areas and complete complex data collection, including photography and laser scanning. After the data is recorded, operators can review it and identify any potential problems. Drones can even be equipped with sensors so that they can detect anomalies, such as unusual heat signatures.

[0004] During the drone inspection of distribution network lines, it is necessary to synchronize the route shooting information in real time. Since the inspection data is usually large in volume, how to quickly complete the data synchronization of the drone inspection route has become a problem that needs to be solved. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method for synchronizing a distribution network line drone inspection route, which at least partially solves the problems existing in the prior art.

[0006] In a first aspect, an embodiment of the present invention provides a method for synchronizing a distribution network line drone inspection route, comprising:

[0007] Obtain historical inspection data of the distribution network lines in the inspection area, and divide the historical inspection data into n historical sub-inspection data according to the inspection points included in the inspection area;

[0008] Extract features from the inspection data contained in the n historical sub-inspection data to form a set of n inspection data matrices M = {M1, M2, ...Mn}, where the inspection data includes the location information, time information, and shooting information collected by the inspection sensor during the inspection route of the drone;

[0009] Based on the current position information of the drone that is performing the inspection task, determine the inspection data matrix Mi corresponding to the drone that is performing the inspection task, 1≤i≤n;

[0010] The inspection sensor on the inspection drone is controlled to collect information on the distribution network line at the current location, forming an inspection data packet stored on the inspection drone. By extracting features from the inspection data packet, a real-time inspection matrix G corresponding to the inspection data packet is obtained. When the real-time inspection matrix G matches the inspection data matrix Mi, the eigenvalue λi of the inspection data matrix Mi is used as the synchronization data of the current drone inspection route, and the synchronization data is sent to the ground server control center.

[0011] According to a specific implementation of the embodiment of the present disclosure, the obtaining of historical inspection data of distribution network lines in the inspection area includes:

[0012] Obtaining the starting position coordinate value and the end point coordinate value of the inspection area;

[0013] Based on the starting position coordinate value and the end point coordinate value, historical inspection data corresponding to the value is searched in the ground server control center.

[0014] According to a specific implementation of the embodiment of the present disclosure, the historical inspection data is divided into n historical sub-inspection data according to the inspection points included in the inspection area, including:

[0015] Obtain the position coordinates of the inspection points included in the interval between the starting position coordinate value and the end point coordinate value to form a set of inspection point position coordinates;

[0016] The historical inspection data is divided into n historical sub-inspection data according to the inspection point position coordinate set.

[0017] According to a specific implementation of the embodiment of the present disclosure, the historical inspection data is divided into n historical sub-inspection data according to the inspection points included in the inspection area, and further includes:

[0018] Determine whether any adjacent inspection points contain a safe inspection area;

[0019] If so, the identification of the safety inspection area is added to the corresponding historical sub-inspection data.

[0020] According to a specific implementation of the embodiment of the present disclosure, the feature extraction of the inspection data contained in the n historical sub-inspection data to form n inspection data matrix sets M={M1, M2, ...Mn} includes:

[0021] The location information, time information contained in the historical sub-inspection data and the shooting information collected by the inspection sensor are respectively used as element values ​​in the inspection data matrix to form a set of n inspection data matrices M = {M1, M2, ...Mn}.

[0022] According to a specific implementation of an embodiment of the present disclosure, the method of determining the inspection data matrix Mi corresponding to the drone that is performing the inspection task based on the current position information of the drone that is performing the inspection task includes:

[0023] Based on the current location information of the drone, determine the two adjacent inspection points closest to the current location;

[0024] Find the historical sub-inspection data corresponding to the two closest adjacent inspection points, and then determine the inspection data matrix Mi corresponding to the drone that is performing the inspection task.

[0025] According to a specific implementation of the embodiment of the present disclosure, the inspection sensor on the inspection drone is controlled to collect information on the distribution network line at the current location to form an inspection data packet stored on the inspection drone, including:

[0026] Get the location coordinates corresponding to the current location;

[0027] Control the inspection sensor to perform image acquisition operations on the distribution network line to form an image set;

[0028] An inspection data packet is formed based on the position coordinates corresponding to the current position, the acquisition time of the image set, and the image set.

[0029] According to a specific implementation of the embodiment of the present disclosure, the real-time inspection matrix G corresponding to the inspection data packet is obtained by extracting features from the inspection data packet, including:

[0030] Performing feature extraction on a plurality of images contained in the inspection package to obtain a feature set containing a plurality of objects of different types;

[0031] The eigenvalue set corresponding to the feature set is calculated, and the calculated eigenvalue set is used as a constituent element in the real-time inspection matrix G.

[0032] According to a specific implementation of the embodiment of the present disclosure, the eigenvalue λi of the inspection data matrix Mi is used as the synchronization data of the current UAV inspection route, and the synchronization data is sent to the ground server control center, including:

[0033] The UAV establishes a communication connection with the ground server control center through the wireless communication network, and after the communication connection is successful, sends a data sending request to the ground server control center;

[0034] After obtaining the data sending permission response sent by the ground server control center, the characteristic value λi is synchronized to the ground server control center.

[0035] In a second aspect, an embodiment of the present invention provides a distribution network line drone inspection route synchronization device, comprising:

[0036] A segmentation module is used to obtain historical inspection data of distribution network lines in an inspection area, and to segment the historical inspection data into n historical sub-inspection data according to the inspection points contained in the inspection area;

[0037] An extraction module is used to extract features from the inspection data contained in the n historical sub-inspection data to form a set of n inspection data matrices M = {M1, M2, ...Mn}, wherein the inspection data includes the location information, time information and shooting information collected by the inspection sensor during the inspection route of the drone;

[0038] Determination module, the user determines the inspection data matrix Mi corresponding to the drone that is performing the inspection task based on the current location information of the drone that is performing the inspection task, 1≤i≤n;

[0039] The synchronization module is used to control the inspection sensor on the inspection drone to collect information on the distribution network line at the current location, form an inspection data packet stored on the inspection drone, and obtain the real-time inspection matrix G corresponding to the inspection data packet by extracting features from the inspection data packet. When the real-time inspection matrix G matches the inspection data matrix Mi, the eigenvalue λi of the inspection data matrix Mi is used as the synchronization data of the current drone inspection route, and the synchronization data is sent to the ground server control center.

[0040] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0041] at least one processor; and,

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the distribution network line drone inspection route synchronization method in any of the first aspects or any of the implementations of the first aspect.

[0044] In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the distribution network line drone inspection route synchronization method in the aforementioned first aspect or any implementation method of the first aspect.

[0045] In the fifth aspect, an embodiment of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the distribution network line drone inspection route synchronization method in the aforementioned first aspect or any implementation of the first aspect.

[0046] The present invention provides a method for synchronizing a distribution network line unmanned aerial vehicle inspection route, comprising: obtaining historical inspection data of distribution network lines in an inspection area, dividing the historical inspection data into n historical sub-inspection data according to the inspection points contained in the inspection area; performing feature extraction on the inspection data contained in the n historical sub-inspection data to form a set of n inspection data matrices M = {M1, M2, ... Mn}, wherein the inspection data includes position information, time information and shooting information collected by inspection sensors during the unmanned aerial vehicle inspection route; based on the current position information of the unmanned aerial vehicle that is performing the inspection task, Information, determine the inspection data matrix Mi corresponding to the drone that is performing the inspection task, 1≤i≤n; control the inspection sensor on the inspection drone to collect information on the distribution network line at the current location, form an inspection data packet stored on the inspection drone, and extract features from the inspection data packet to obtain a real-time inspection matrix G corresponding to the inspection data packet. When the real-time inspection matrix G matches the inspection data matrix Mi, use the eigenvalue λi of the inspection data matrix Mi as the synchronization data of the current drone inspection route, and send the synchronization data to the ground server control center. Through the solution of the present application, it is possible to calculate the information of the drone inspection route based on the effective division of the inspection area and the use of feature extraction, thereby reducing the amount of data transmission and being able to quickly perform drone inspection route synchronization. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A schematic diagram of a method for synchronizing a distribution network line drone inspection route provided by an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the structure of a distribution network line drone inspection route synchronization device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0051] See also Figure 1 The embodiment of the present invention provides a method for synchronizing a distribution network line UAV inspection route, comprising:

[0052] S201, obtaining historical inspection data of distribution network lines in an inspection area, and dividing the historical inspection data into n historical sub-inspection data according to the inspection points included in the inspection area.

[0053] Historical inspection data is a historical summary of the inspection data of drones on distribution network lines. Historical inspection data is usually stored in the ground server control center. Inspection points are fixed inspection points pre-set on the distribution network lines. By counting the number of inspection points, historical inspection data can be segmented.

[0054] During the segmentation process, the starting position coordinate value and the end point coordinate value of the inspection area can be obtained, and based on the starting position coordinate value and the end point coordinate value, the historical inspection data corresponding to the value can be searched in the ground server control center.

[0055] Furthermore, the position coordinates of the inspection points included in the interval of the starting position coordinate value and the end position coordinate value can be obtained to form an inspection point position coordinate set, and the historical inspection data can be divided into n historical sub-inspection data through the inspection point position coordinate set.

[0056] S202, extract features from the inspection data contained in the n historical sub-inspection data to form a set of n inspection data matrices M = {M1, M2, ...Mn}, wherein the inspection data includes the location information, time information contained in the UAV inspection route, and shooting information collected by the inspection sensor.

[0057] The n historical sub-inspection data are still a massive amount of storage data. Therefore, feature extraction can be performed on the inspection data contained in the n historical sub-inspection data to form a set of n inspection data matrices M = {M1, M2, ...Mn}.

[0058] Specifically, a feature extraction function can be set to extract features from the inspection data contained in the n historical sub-inspection data. The location information, time information and shooting information collected by the inspection sensor contained in the historical sub-inspection data are used as element values ​​in the inspection data matrix to form a set of n inspection data matrices M = {M1, M2, ... Mn}

[0059] S203, based on the current position information of the drone that is performing the inspection task, determine the inspection data matrix Mi corresponding to the drone that is performing the inspection task, 1≤i≤n.

[0060] Specifically, based on the current location information of the drone, the two adjacent inspection points closest to the current location can be determined; the historical sub-inspection data corresponding to the two closest adjacent inspection points can be found, and then the inspection data matrix Mi corresponding to the drone that is performing the inspection task can be determined.

[0061] S204, control the inspection sensor on the inspection drone to collect information on the distribution network line at the current location, form an inspection data packet stored on the inspection drone, and obtain a real-time inspection matrix G corresponding to the inspection data packet by extracting features from the inspection data packet. When the real-time inspection matrix G matches the inspection data matrix Mi, the eigenvalue λi of the inspection data matrix Mi is used as the synchronization data of the current drone inspection route, and the synchronization data is sent to the ground server control center.

[0062] Specifically, the position coordinates corresponding to the current position can be obtained; the inspection sensor is controlled to perform image acquisition operations on the distribution network line to form an image set; based on the position coordinates corresponding to the current position, the acquisition time of the image set and the image set, an inspection data packet is formed.

[0063] Furthermore, feature extraction can be performed on multiple images contained in the inspection package to obtain a feature set containing multiple different types of objects; the eigenvalue set corresponding to the feature set is calculated, and the calculated eigenvalue set is used as a constituent element in the real-time inspection matrix G.

[0064] The UAV establishes a communication connection with the ground server control center through the wireless communication network, and after the communication connection is successful, it sends a data sending request to the ground server control center; after obtaining the data sending permission response sent by the ground server control center, the characteristic value λi is synchronized to the ground server control center.

[0065] As another method, after the drone completes the route inspection and lands at the ground server control center, the inspection data packet stored on the inspection drone can be copied or transmitted to the ground server control center to form the latest supplementary data of the historical inspection data.

[0066] Through the method in the above embodiment, the inspection route data can be processed in a lightweight manner, thereby facilitating the drone to send synchronization data to the ground server control center through limited wireless transmission bandwidth.

[0067] According to a specific implementation of the embodiment of the present disclosure, the obtaining of historical inspection data of distribution network lines in the inspection area includes:

[0068] Obtaining the starting position coordinate value and the end point coordinate value of the inspection area;

[0069] Based on the starting position coordinate value and the end point coordinate value, historical inspection data corresponding to the value is searched in the ground server control center.

[0070] According to a specific implementation of the embodiment of the present disclosure, the historical inspection data is divided into n historical sub-inspection data according to the inspection points included in the inspection area, including:

[0071] Obtain the position coordinates of the inspection points included in the interval between the starting position coordinate value and the end point coordinate value to form a set of inspection point position coordinates;

[0072] The historical inspection data is divided into n historical sub-inspection data according to the inspection point position coordinate set.

[0073] According to a specific implementation of the embodiment of the present disclosure, the historical inspection data is divided into n historical sub-inspection data according to the inspection points included in the inspection area, and further includes:

[0074] Determine whether any adjacent inspection points contain a safe inspection area;

[0075] If so, the identification of the safety inspection area is added to the corresponding historical sub-inspection data.

[0076] According to a specific implementation of the embodiment of the present disclosure, the feature extraction of the inspection data contained in the n historical sub-inspection data to form n inspection data matrix sets M={M1, M2, ...Mn} includes:

[0077] The location information, time information contained in the historical sub-inspection data and the shooting information collected by the inspection sensor are respectively used as element values ​​in the inspection data matrix to form a set of n inspection data matrices M = {M1, M2, ...Mn}.

[0078] According to a specific implementation of an embodiment of the present disclosure, the method of determining the inspection data matrix Mi corresponding to the drone that is performing the inspection task based on the current position information of the drone that is performing the inspection task includes:

[0079] Based on the current location information of the drone, determine the two adjacent inspection points closest to the current location;

[0080] Find the historical sub-inspection data corresponding to the two closest adjacent inspection points, and then determine the inspection data matrix Mi corresponding to the drone that is performing the inspection task.

[0081] According to a specific implementation of the embodiment of the present disclosure, the inspection sensor on the inspection drone is controlled to collect information on the distribution network line at the current location to form an inspection data packet stored on the inspection drone, including:

[0082] Get the location coordinates corresponding to the current location;

[0083] Control the inspection sensor to perform image acquisition operations on the distribution network line to form an image set;

[0084] An inspection data packet is formed based on the position coordinates corresponding to the current position, the acquisition time of the image set, and the image set.

[0085] According to a specific implementation of the embodiment of the present disclosure, the real-time inspection matrix G corresponding to the inspection data packet is obtained by extracting features from the inspection data packet, including:

[0086] Performing feature extraction on a plurality of images contained in the inspection package to obtain a feature set containing a plurality of objects of different types;

[0087] The eigenvalue set corresponding to the feature set is calculated, and the calculated eigenvalue set is used as a constituent element in the real-time inspection matrix G.

[0088] According to a specific implementation of the embodiment of the present disclosure, the eigenvalue λi of the inspection data matrix Mi is used as the synchronization data of the current UAV inspection route, and the synchronization data is sent to the ground server control center, including:

[0089] The UAV establishes a communication connection with the ground server control center through the wireless communication network, and after the communication connection is successful, sends a data sending request to the ground server control center;

[0090] After obtaining the data sending permission response sent by the ground server control center, the characteristic value λi is synchronized to the ground server control center.

[0091] Corresponding to the above method embodiment, see Figure 2 The present disclosure also provides a distribution network line drone inspection route synchronization device, including:

[0092] A segmentation module 201 is used to obtain historical inspection data of distribution network lines in an inspection area, and to segment the historical inspection data into n historical sub-inspection data according to the inspection points contained in the inspection area;

[0093] The extraction module 202 is used to extract features from the inspection data contained in the n historical sub-inspection data to form a set of n inspection data matrices M = {M1, M2, ...Mn}, wherein the inspection data includes the location information, time information and shooting information collected by the inspection sensor during the inspection route of the drone;

[0094] Determination module 203, the user determines the inspection data matrix Mi corresponding to the drone that is performing the inspection task based on the current location information of the drone that is performing the inspection task, 1≤i≤n;

[0095] The synchronization module 204 is used to control the inspection sensor on the inspection drone to collect information on the distribution network line at the current location, form an inspection data packet stored on the inspection drone, and obtain a real-time inspection matrix G corresponding to the inspection data packet by extracting features from the inspection data packet. When the real-time inspection matrix G matches the inspection data matrix Mi, the eigenvalue λi of the inspection data matrix Mi is used as the synchronization data of the current drone inspection route, and the synchronization data is sent to the ground server control center.

[0096] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for synchronizing the route of a distribution network line drone inspection, characterized in that: include: Obtain historical inspection data of the distribution network lines in the inspection area, and divide the historical inspection data into n historical sub-inspection data according to the inspection points included in the inspection area; Extract features from the inspection data contained in the n historical sub-inspection data to form n inspection data matrix sets M={M1,M2,…Mn}, where the inspection data includes the location information, time information, and shooting information collected by the inspection sensor during the inspection route of the drone; Based on the current position information of the drone that is performing the inspection task, determine the inspection data matrix Mi corresponding to the drone that is performing the inspection task, 1≤i≤n; Control the inspection sensor on the inspection drone to collect information on the distribution network line at the current location, form an inspection data packet stored on the inspection drone, extract features from the inspection data packet, and obtain a real-time inspection matrix G corresponding to the inspection data packet. When the real-time inspection matrix G matches the inspection data matrix Mi, use the eigenvalue λi of the inspection data matrix Mi as the synchronization data of the current drone inspection route, and send the synchronization data to the ground server control center; The feature extraction of the inspection data contained in the n historical sub-inspection data to form n inspection data matrix sets M={M1, M2, ...Mn} includes: The location information, time information and shooting information collected by the inspection sensor contained in the historical sub-inspection data are respectively used as element values ​​in the inspection data matrix to form a set of n inspection data matrices M={M1,M2,…Mn}; The method of determining the inspection data matrix Mi corresponding to the drone that is performing the inspection task based on the current position information of the drone that is performing the inspection task includes: Based on the current location information of the drone, determine the two adjacent inspection points closest to the current location; Find the historical sub-inspection data corresponding to the two closest adjacent inspection points, and then determine the inspection data matrix Mi corresponding to the drone that is performing the inspection task.

2. The method according to claim 1, characterized in that: The acquisition of historical inspection data of the distribution network lines in the inspection area includes: Obtaining the starting position coordinate value and the end point coordinate value of the inspection area; Based on the starting position coordinate value and the end point coordinate value, historical inspection data corresponding to the value is searched in the ground server control center.

3. The method according to claim 2, characterized in that The historical inspection data is divided into n historical sub-inspection data according to the inspection points included in the inspection area, including: Obtain the position coordinates of the inspection points included in the interval between the starting position coordinate value and the end point coordinate value to form a set of inspection point position coordinates; The historical inspection data is divided into n historical sub-inspection data according to the inspection point position coordinate set.

4. The method according to claim 3, characterized in that: The method of dividing the historical inspection data into n historical sub-inspection data according to the inspection points included in the inspection area also includes: Determine whether any adjacent inspection points contain a safe inspection area; If so, the identification of the safety inspection area is added to the corresponding historical sub-inspection data.

5. The method according to claim 4, characterized in that The control of the inspection sensor on the inspection drone to collect information on the distribution network line at the current location to form an inspection data packet stored on the inspection drone includes: Get the location coordinates corresponding to the current location; Control the inspection sensor to perform image acquisition operations on the distribution network line to form an image set; An inspection data packet is formed based on the position coordinates corresponding to the current position, the acquisition time of the image set, and the image set.

6. The method according to claim 5, characterized in that The method of extracting features from the inspection data packet to obtain a real-time inspection matrix G corresponding to the inspection data packet includes: Performing feature extraction on a plurality of images contained in the inspection package to obtain a feature set containing a plurality of objects of different types; The eigenvalue set corresponding to the feature set is calculated, and the calculated eigenvalue set is used as a constituent element in the real-time inspection matrix G.

7. The method according to claim 6, characterized in that The method uses the eigenvalue λi of the inspection data matrix Mi as the synchronization data of the current UAV inspection route, and sends the synchronization data to the ground server control center, including: The UAV establishes a communication connection with the ground server control center through the wireless communication network, and after the communication connection is successful, sends a data sending request to the ground server control center; After obtaining the data sending permission response sent by the ground server control center, the characteristic value λi is synchronized to the ground server control center.

8. A distribution network line drone inspection route synchronization device, which implements the distribution network line drone inspection route synchronization method according to any one of claims 1 to 7, characterized in that: include: A segmentation module is used to obtain historical inspection data of distribution network lines in an inspection area, and to segment the historical inspection data into n historical sub-inspection data according to the inspection points contained in the inspection area; An extraction module is used to extract features from the inspection data contained in the n historical sub-inspection data to form a set of n inspection data matrices M={M1,M2,…Mn}, wherein the inspection data includes the location information, time information and shooting information collected by the inspection sensor during the inspection route of the drone; Determination module, the user determines the inspection data matrix Mi corresponding to the drone that is performing the inspection task based on the current location information of the drone that is performing the inspection task, 1≤i≤n; The synchronization module is used to control the inspection sensor on the inspection drone to collect information on the distribution network line at the current location, form an inspection data packet stored on the inspection drone, and obtain the real-time inspection matrix G corresponding to the inspection data packet by extracting features from the inspection data packet. When the real-time inspection matrix G matches the inspection data matrix Mi, the eigenvalue λi of the inspection data matrix Mi is used as the synchronization data of the current drone inspection route, and the synchronization data is sent to the ground server control center.

Images