Operation and maintenance method, system and device based on power big data and medium

Abstract

The application belongs to the field of operation and maintenance, and discloses an operation and maintenance system based on power big data, which comprises a UAV and an operation and maintenance platform, wherein the UAV comprises a flight control module, a shooting module and a distance measuring module; the flight control module is used for controlling the UAV to fly to a preset shooting coordinate A; the distance measuring module is used for obtaining a distance measuring direction according to the shooting coordinate A and obtaining a set B of N distances based on the distance measuring direction; the shooting module comprises a mode selection unit, an obtaining unit, a calculation unit and a shooting unit; the mode selection unit is used for calculating a shooting coefficient of the set B; the obtaining unit is used for obtaining shooting parameters containing a focal length C according to the shooting coordinate A; if the shooting coefficient is less than or equal to a set shooting coefficient threshold, a single shooting is performed on the line; if the shooting coefficient is greater than the set shooting coefficient threshold, the line is shot based on a focal length set D, and a set E of multiple images of the line at the shooting coordinate A is obtained. The application improves the probability of obtaining a clear line.

Description

Technical Field

[0001] This invention belongs to the field of power system operation and maintenance, and particularly relates to an operation and maintenance method, system, equipment and medium based on power big data. Background Technology

[0002] In existing technologies, when maintaining power lines, drones are typically used to capture images of the lines from various angles. These images are then used to analyze the lines, and maintenance is performed based on the analysis results. For example, patents with publication numbers CN109193468A and CN113034021A both disclose related technologies.

[0003] During drone photography of power lines, a safe distance must be maintained between the drone and the power line to ensure flight safety. However, the power line may still be swaying due to wind before the drone reaches the shooting position, making it difficult for the drone's lens to accurately focus on the line, as the distance between the drone and the line is constantly changing. This results in potentially blurry images of the power line, which may prevent the timely detection of defects.

[0004] Therefore, when using drones to acquire images of a line, how to increase the probability of obtaining a clear image of the line when the line is swaying becomes a technical problem that needs to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide an operation and maintenance method, system, equipment and medium based on power big data, to solve the problem of how to improve the probability of obtaining clear images of power lines when using drones to photograph power lines in a swinging state during the operation and maintenance of power lines.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides an operation and maintenance system based on power big data, including a drone and an operation and maintenance platform. The drone includes a flight control module, a shooting module, and a ranging module.

[0008] The flight control module is used to control the drone to fly to the preset shooting coordinates A;

[0009] The ranging module is used to obtain the ranging direction based on the shooting coordinates A, and obtain N distances based on the ranging direction, and save the obtained N distances to set B;

[0010] The shooting module includes a mode selection unit, an acquisition unit, a calculation unit, and a shooting unit;

[0011] The mode selection unit is used to calculate the shooting coefficients for set B;

[0012] The acquisition unit is used to obtain shooting parameters based on shooting coordinates A. The shooting parameters include the focal length C corresponding to shooting coordinates A.

[0013] If the shooting coefficient is less than or equal to the set shooting coefficient threshold, the shooting unit will take a single shot of the line according to the shooting parameters obtained by the acquisition unit to obtain image imgA;

[0014] If the shooting coefficient is greater than the set shooting coefficient threshold, the calculation unit calculates the focal length set D based on the focal length C, and the shooting unit uses each focal length in the focal length set D to shoot the line, thereby obtaining a set E of multiple images of the line at shooting coordinate A.

[0015] The operation and maintenance platform is used to select image imgA as the image for operation and maintenance identification when the drone only captures one image imgA at shooting coordinate A.

[0016] And when the drone obtains set E at coordinate A, it selects the image with the highest resolution in set E as the image for operation and maintenance identification.

[0017] Optionally, the operation and maintenance platform includes a filtering module, an identification module, and a prompting module;

[0018] The filtering module is used to select image imgA as the image for operation and maintenance identification when the drone only captures one image imgA at shooting coordinate A.

[0019] And when the drone obtains set E at coordinate A, it selects the image with the highest resolution in set E as the image for operation and maintenance identification.

[0020] The recognition module is used to identify images used for operation and maintenance identification and obtain recognition results;

[0021] The prompting module is used to provide prompts to maintenance personnel based on the recognition results.

[0022] Optionally, the identification result can be either "line normal" or "line abnormal".

[0023] Optionally, prompts can be sent to operations and maintenance personnel based on the identification results, including:

[0024] When the identification result indicates a line abnormality, a notification message is sent to the maintenance personnel through a pre-set prompt method. The notification message includes the coordinates of the line.

[0025] Optionally, the ranging module includes a retrieval unit, a ranging direction storage unit, and a ranging unit;

[0026] The ranging direction storage unit is used to pre-store the ranging direction of each shooting coordinate;

[0027] The retrieval unit is used to retrieve the ranging direction stored in the ranging direction storage unit based on the shooting coordinates A, and obtain the ranging direction randirA corresponding to the shooting coordinates A;

[0028] The ranging unit is used to perform N distance measurements with a preset acquisition interval and ranging direction randirA, obtain N distances, and save the N distances to set B.

[0029] Optionally, the function for calculating the shooting coefficient is:

[0030]

[0031] shocefA represents the shooting coefficient, dist i Let represent the value of element i in set B, middist represent the median of elements in set B, maxdist and mindist represent the maximum and minimum values ​​of elements in set B, respectively; α represents the set shooting coefficient weight, α∈(0, 3, 0, 8).

[0032] Optionally, the acquisition unit includes a retrieval subunit and a shooting parameter storage subunit;

[0033] The shooting parameter storage subunit is used to pre-store the shooting parameters for each shooting coordinate;

[0034] The retrieval subunit is used to retrieve the shooting parameters stored in the shooting parameter storage subunit based on the shooting coordinates A, and obtain the shooting parameters corresponding to shooting coordinates A.

[0035] Optionally, the focal length set D is calculated based on the focal length C, including:

[0036] S1. Sort the elements in set B in order of acquisition time from earliest to latest to obtain set F;

[0037] S2, initialize n to 1, where n is a positive integer, initialize m to 1, where m is a positive integer;

[0038] S3, for the nth element dis in set F n If dis n If the value is 0, then dis n Save to the zero-element collection m Enter S4; if dis n If the value is not 0, proceed to S5;

[0039] S4, increment the value of n by 1. If n is greater than N, proceed to S6; if n is less than N, proceed to S3.

[0040] S5, increment the value of m by 1, increment the value of n by 1, then proceed to S3;

[0041] S6, save the set of all obtained zero elements;

[0042] S7 calculates the upper limit value uppval and the lower limit value lowval of the focal length based on the set of zero elements;

[0043] S8 obtains multiple focal lengths in the interval [uppval, lowval] with an interval of 1 mm, and saves all obtained focal lengths to the focal length set D.

[0044] In a second aspect, the present invention provides an operation and maintenance method based on power big data, comprising the following steps:

[0045] Control the drone to fly to the preset shooting coordinates A;

[0046] The ranging direction is obtained based on the shooting coordinates A, and N distances are obtained based on the ranging direction. The N distances are then saved to set B.

[0047] Calculate the shooting coefficients for set B;

[0048] The shooting parameters are obtained based on the shooting coordinates A, including the focal length C corresponding to the shooting coordinates A; if the shooting coefficient is less than or equal to the set shooting coefficient threshold, the line is shot once according to the shooting parameters to obtain the image imgA.

[0049] If the shooting coefficient is greater than the set shooting coefficient threshold, then the focal length set D is calculated based on the focal length C, and the line is photographed based on the focal length set D to obtain a set E of multiple images of the line at shooting coordinate A.

[0050] When the drone captures only one image imgA at coordinate A, imgA will be selected as the image for maintenance identification.

[0051] And when the drone obtains set E at coordinate A, the image with the highest resolution in set E is selected as the image for operation and maintenance identification.

[0052] In a third aspect, the present invention provides an electronic device including a processor and a memory, the processor being configured to execute a computer program stored in the memory to implement the aforementioned operation and maintenance method.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium storing at least one instruction that, when executed by a processor, implements the aforementioned operation and maintenance method.

[0054] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0055] Compared with existing technologies, this invention determines the shooting method by calculating the shooting coefficient when photographing the power line. This allows for the acquisition of a set of multiple images of the power line using elements in the focal length set D, even when the line is in a swinging state, thus increasing the probability of obtaining a clear image of the line. The power big data-based operation and maintenance method, electronic device, and computer-readable storage medium provided by this invention also solve the problems raised in the background section. Attached Figure Description

[0056] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0057] Figure 1 This is a schematic diagram of an operation and maintenance system based on power big data according to the present invention.

[0058] Figure 2 This is a schematic diagram illustrating one possible shooting angle for the present invention.

[0059] Figure 3 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0060] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0061] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0062] Example 1

[0063] like Figure 1 As shown in one embodiment, the present invention provides an operation and maintenance system based on power big data, including a drone and an operation and maintenance platform. The drone includes a flight control module, a shooting module, and a ranging module.

[0064] The flight control module is used to control the drone to fly to the preset shooting coordinates A;

[0065] The ranging module is used to obtain the ranging direction based on the shooting coordinates A, and obtain N distances based on the ranging direction, and save the obtained N distances to set B;

[0066] The shooting module includes a mode selection unit, an acquisition unit, a calculation unit, and a shooting unit;

[0067] The mode selection unit is used to calculate the shooting coefficients for set B;

[0068] The acquisition unit is used to obtain shooting parameters based on shooting coordinates A. The shooting parameters include the focal length C corresponding to shooting coordinates A.

[0069] If the shooting coefficient is less than or equal to the set shooting coefficient threshold, the shooting unit will take a single shot of the line according to the shooting parameters obtained by the acquisition unit to obtain image imgA;

[0070] If the shooting coefficient is greater than the set shooting coefficient threshold, the calculation unit calculates the focal length set D based on the focal length C, and the shooting unit uses each focal length in the focal length set D to shoot the line, thereby obtaining a set E of multiple images of the line at shooting coordinate A.

[0071] The operation and maintenance platform is used to select image imgA as the image for operation and maintenance identification when the drone only captures one image imgA at shooting coordinate A.

[0072] And when the drone obtains set E at coordinate A, it selects the image with the highest resolution in set E as the image for operation and maintenance identification.

[0073] This invention determines the shooting method by calculating the shooting coefficient when photographing a line, thereby enabling the acquisition of a set of multiple images of the line using elements in the focal length set D when the line is in a swinging state, thus increasing the probability of obtaining a clear image of the line.

[0074] Specifically, because different focal lengths are used for shooting, the focal length corresponding to the captured image is exactly the distance between the current shooting unit and the line, increasing the probability of a clear image.

[0075] Because a longer focal length allows for shooting at greater distances, this invention calculates a set of focal lengths applicable to different shooting distances, thereby increasing the probability of obtaining a clear image.

[0076] Specifically, shooting parameters include aperture, shutter speed, ISO, and focal length.

[0077] When the shooting coefficient is less than the set shooting coefficient threshold, it indicates that the line is in a stationary state. Therefore, the present invention uses pre-saved shooting parameters to shoot, thereby improving the shooting efficiency. When the line is in a swinging state, the present invention uses the set D of focal lengths to shoot, thereby ensuring the probability of obtaining a clear image of the line. Therefore, the present invention can achieve a balance between shooting efficiency and shooting effect.

[0078] Specifically, the flight control module can control the drone to fly sequentially to each preset shooting coordinate. These preset shooting coordinates can be set manually. These coordinates allow the drone to photograph the line from various preset shooting angles (e.g., 0°, 90°, 180°, 270°), while maintaining a minimum safe distance (e.g., 5m) between the drone and the line.

[0079] In one implementation, such as Figure 2 As shown, the shooting angle is determined by setting a plane R perpendicular to the extension direction of the line, establishing a rectangular coordinate system in the plane with the point O where the line is located as the origin, and then selecting the direction of 0° to the right to obtain various shooting angles.

[0080] Optionally, the operation and maintenance platform includes a filtering module, an identification module, and a prompting module;

[0081] The filtering module is used to select image imgA as the image for operation and maintenance identification when the drone only captures one image imgA at shooting coordinate A.

[0082] And when the drone obtains set E at coordinate A, it selects the image with the highest resolution in set E as the image for operation and maintenance identification.

[0083] The recognition module is used to identify images used for operation and maintenance identification and obtain recognition results;

[0084] The prompting module is used to provide prompts to maintenance personnel based on the recognition results.

[0085] Specifically, the sharpness index (i.e. the function value of the corresponding function type) of each image in set E can be calculated using formulas such as the Brenner gradient function, Tenegrad gradient function, Laplace gradient function, variance function, and energy gradient function, thereby obtaining the image with the highest sharpness (maximum function value).

[0086] Specifically, when recognizing images, a trained neural network model can be used to identify whether the image contains a preset type of defect.

[0087] Preset defects include broken strands in the circuit and the circuit being covered by foreign objects.

[0088] During the training of the neural network, the dataset contains images of lines with various types of defects. The neural network model can be a Fast R-CNN model.

[0089] Optionally, the identification result can be either "line normal" or "line abnormal".

[0090] Specifically, when an image contains a defect of a preset type, the identification result is a circuit anomaly.

[0091] Optionally, prompts can be sent to operations and maintenance personnel based on the identification results, including:

[0092] When the identification result indicates a line abnormality, a notification message is sent to the maintenance personnel through a pre-set prompt method. The notification message includes the coordinates of the line.

[0093] Specifically, the coordinates of the route can be retrieved using the shooting coordinates of the images taken by the drone. Because the shooting coordinates are pre-set, different shooting coordinates correspond to different route coordinates.

[0094] The prompts can be text-based or voice-based.

[0095] Optionally, the ranging module includes a retrieval unit, a ranging direction storage unit, and a ranging unit;

[0096] The ranging direction storage unit is used to pre-store the ranging direction of each shooting coordinate;

[0097] The retrieval unit is used to retrieve the ranging direction stored in the ranging direction storage unit based on the shooting coordinates A, and obtain the ranging direction randirA corresponding to the shooting coordinates A;

[0098] The ranging unit is used to perform N distance measurements with a preset acquisition interval and ranging direction randirA, obtain N distances, and save the N distances to set B.

[0099] Specifically, the ranging direction is obtained by manually adjusting the emission angle of the ranging unit. Before the implementation of this invention, the drone can be manually controlled to fly to a preset shooting coordinate, and then the emission angle of the ranging unit can be adjusted in the shooting coordinate so that when the line is calm, the ranging unit can emit electromagnetic waves such as laser and infrared rays for ranging from the emission angle, so that the distance between the ranging unit and the line can be obtained.

[0100] The distance measurement direction can be represented by three-dimensional coordinates. That is, a three-dimensional coordinate system is established with the shooting coordinates as the origin, and the position of the line is represented as (x, y, z). When the shooting coordinates are captured, the distance measurement unit can obtain the distance between the distance measurement unit and the line by emitting electromagnetic waves in the direction of (x, y, z).

[0101] Specifically, the preset acquisition interval can be 0.01 seconds. When the line is in a swinging state, the numerical differences between the obtained N distances are relatively large. When the swing amplitude is large, distances with a value of 0 will appear intermittently among the obtained N distances. This is caused by the line being outside the detection path of the electromagnetic wave used for ranging. Since the ranging unit cannot receive the electromagnetic wave reflected back from the line or the time for the reflected electromagnetic wave is too long, the present invention will set the distance obtained in this ranging to 0. Because the distance between the line and the ranging module is within a small range of variation, that is, the time length between emitting the electromagnetic wave and receiving the reflected electromagnetic wave is also within a small range of variation, the present invention considers electromagnetic waves outside the range as invalid data, thereby avoiding false detection.

[0102] Optionally, the function for calculating the shooting coefficient is:

[0103]

[0104] shocefA represents the shooting coefficient, dist i Let represent the value of element i in set B, middist represent the median of elements in set B, maxdist and mindist represent the maximum and minimum values ​​of elements in set B, respectively; α represents the set shooting coefficient weight, α∈(0, 3, 0, 8).

[0105] Specifically, the shooting coefficient is calculated from two aspects: the variance of the elements in set B and the difference between the maximum and minimum values. Compared with the method of simply using variance for calculation, the shooting coefficient of the present invention can further highlight the differences between the elements in set B, so that the shooting coefficient of the present invention can more sensitively detect the existence of elements with a value of 0 in set B, which is beneficial to improving the accuracy of selecting the shooting method for the line.

[0106] Specifically, the shooting coefficient threshold can be set to 0.05.

[0107] Optionally, the acquisition unit includes a retrieval subunit and a shooting parameter storage subunit;

[0108] The shooting parameter storage subunit is used to pre-store the shooting parameters for each shooting coordinate;

[0109] The retrieval subunit is used to retrieve the shooting parameters stored in the shooting parameter storage subunit based on the shooting coordinates A, and obtain the shooting parameters corresponding to shooting coordinates A.

[0110] Optionally, the focal length set D is calculated based on the focal length C, including:

[0111] S1. Sort the elements in set B in order of acquisition time from earliest to latest to obtain set F;

[0112] S2, initialize n to 1, where n is a positive integer, initialize m to 1, where m is a positive integer;

[0113] S3, for the nth element dis in set F n If dis n If the value is 0, then dis n Save to the zero-element collection m Enter S4; if dis n If the value is not 0, proceed to S5;

[0114] S4, increment the value of n by 1. If n is greater than N, proceed to S6; if n is less than N, proceed to S3.

[0115] S5, increment the value of m by 1, increment the value of n by 1, then proceed to S3;

[0116] S6, save the set of all obtained zero elements;

[0117] S7 calculates the upper limit value uppval and the lower limit value lowval of the focal length based on the set of zero elements;

[0118] S8 obtains multiple focal lengths in the interval [uppval, lowval] with an interval of 1 mm, and saves all obtained focal lengths to the focal length set D.

[0119] Specifically, steps S1-S6 above are mainly to save the distances of adjacent and consecutive zero values ​​in set F to the same zero-element set, so as to facilitate the subsequent calculation of focal length set D based on the zero-element set.

[0120] Optionally, the upper limit value uppval and the lower limit value lowval of the focal length are calculated based on the set of zero elements, including:

[0121] The focal length change is calculated using the following function:

[0122]

[0123] focchg represents the focal length change value, G represents the set of all zero elements, and maxtim j and mintim j numG represents the latest and earliest values ​​of the time when the zero element is acquired in the set j, respectively; bstime represents the set time length; and bsfoc represents the set focal length.

[0124] The above calculation method uses the acquisition time of elements in the zero-element set to calculate the focal length change value. These elements are collected when the line is outside the detection path of the ranging electromagnetic wave, indicating that the line is in a swinging state. The larger the difference between the acquisition times in the zero-element set, the greater the swing amplitude of the line, and the greater the change in distance between the line and the ranging and imaging units. In this case, the invention will correspondingly increase the focal length change value, so that the focal length change value adapts to the change in the swing amplitude of the line, which is beneficial for obtaining a more reasonable focal length set D. That is, the smaller the swing amplitude of the line, the smaller the number of elements in the focal length set D, thus avoiding the need to capture too many images at the same shooting coordinate due to an excessive number of elements; the larger the swing amplitude of the line, the larger the number of elements in the focal length set D, thus ensuring that enough focal lengths are generated, increasing the probability of obtaining a clear image of the line.

[0125] Specifically, the value of bstime can be 10 seconds, and the value of bsfoc can be 10 millimeters.

[0126] Optionally, the line can be photographed separately using each focal length in the focal length set D, resulting in a set E of multiple images of the line at shooting coordinates A, including:

[0127] Before taking a picture, the ranging module continuously measures the distance in the ranging direction and obtains multiple distances. When the latest obtained distance changes from 0 to non-zero or from non-zero to 0, the shooting unit starts shooting.

[0128] Select a focal length from the set of focal lengths D in ascending order as the focal length to be used for shooting, and calculate the shutter speed using the following function:

[0129]

[0130] shtspd represents the shutter speed, focint represents the current focal length used for shooting, and aimval represents the preset safety factor;

[0131] Each focal length in set D is captured twice, and all the resulting images are saved to set E.

[0132] During the aforementioned shooting process, when the distance changes from 0 to non-zero or from non-zero to 0, it indicates that the line has passed along the path of the electromagnetic wave emitted by the ranging unit. At this point, the invention begins shooting. The focal length used during the shooting process increases from small to large, with each focal length being used twice before moving to the next focal length. Therefore, if the line moves towards the ranging module, as the focal length increases and the distance between the line and the ranging module decreases, the optimal shooting distance corresponding to the final focal length is the same as the current distance between the line and the ranging module, thus obtaining a clear image of the line. Conversely, if the line moves away from the ranging module, the optimal shooting distance increases with the focal length. When the line reaches the maximum distance between itself and the ranging module, it begins to move in the opposite direction towards the ranging module, and the optimal shooting distance corresponding to the final focal length is the same as the current distance between the line and the ranging module, thus obtaining a clear image of the line.

[0133] Specifically, the value of the safety factor can be... Setting a safety margin ensures that, if the focus is correct, every shot will produce a sharp image, thus increasing the probability of obtaining a sufficiently sharp image.

[0134] Specifically, during shooting, the shooting unit uses the same parameters as the shooting parameters corresponding to shooting coordinate A, except for the focal length and shutter speed.

[0135] Example 2

[0136] Based on the same inventive concept as the above embodiments, the present invention also provides an operation and maintenance method based on power big data, characterized by comprising the following steps:

[0137] Control the drone to fly to the preset shooting coordinates A;

[0138] The ranging direction is obtained based on the shooting coordinates A, and N distances are obtained based on the ranging direction. The N distances are then saved to set B.

[0139] Calculate the shooting coefficients for set B;

[0140] The shooting parameters are obtained based on the shooting coordinates A, including the focal length C corresponding to the shooting coordinates A; if the shooting coefficient is less than or equal to the set shooting coefficient threshold, the line is shot once according to the shooting parameters to obtain the image imgA.

[0141] If the shooting coefficient is greater than the set shooting coefficient threshold, then the focal length set D is calculated based on the focal length C, and the line is photographed based on the focal length set D to obtain a set E of multiple images of the line at shooting coordinate A.

[0142] When the drone captures only one image imgA at coordinate A, imgA will be selected as the image for maintenance identification.

[0143] And when the drone obtains set E at coordinate A, the image with the highest resolution in set E is selected as the image for operation and maintenance identification.

[0144] Example 3

[0145] like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing an operation and maintenance method based on power big data according to Embodiment 2;

[0146] The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0147] The memory 101 can be used to store the computer program 103. The processor 102 implements the operation and maintenance method steps based on power big data in Embodiment 2 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0148] The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0149] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0150] The memory 101 in the electronic device 100 stores multiple instructions to implement an operation and maintenance method based on power big data, and the processor 102 can execute multiple instructions to achieve the following:

[0151] Control the drone to fly to the preset shooting coordinates A;

[0152] The ranging direction is obtained based on the shooting coordinates A, and N distances are obtained based on the ranging direction. The N distances are then saved to set B.

[0153] Calculate the shooting coefficients for set B;

[0154] The shooting parameters are obtained based on the shooting coordinates A, including the focal length C corresponding to the shooting coordinates A; if the shooting coefficient is less than or equal to the set shooting coefficient threshold, the line is shot once according to the shooting parameters to obtain the image imgA.

[0155] If the shooting coefficient is greater than the set shooting coefficient threshold, then the focal length set D is calculated based on the focal length C, and the line is photographed based on the focal length set D to obtain a set E of multiple images of the line at shooting coordinate A.

[0156] When the drone captures only one image imgA at coordinate A, imgA will be selected as the image for maintenance identification.

[0157] And when the drone obtains set E at coordinate A, the image with the highest resolution in set E is selected as the image for operation and maintenance identification.

[0158] Example 4

[0159] If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0160] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0161] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0162] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0163] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0164] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not 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 modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An operation and maintenance system based on power big data, characterized in that, This includes drones and an operation and maintenance platform. The drones include flight control modules, shooting modules, and ranging modules. The flight control module is used to control the drone to fly to the preset shooting coordinates A; The ranging module is used to obtain the ranging direction based on the shooting coordinates A, and to perform N distance measurements at a preset acquisition interval based on the ranging direction to obtain N distances, and save the N distances to set B; The shooting module includes a mode selection unit, an acquisition unit, a calculation unit, and a shooting unit; The mode selection unit is used to calculate the shooting coefficients for set B, including: ; Indicates the shooting coefficient. This represents the value of element i in set B. Let represent the median of the elements in set B. and Let these represent the maximum and minimum values ​​of the elements in set B, respectively. This indicates the weighting of the shooting coefficients. ; The acquisition unit is used to obtain shooting parameters based on shooting coordinates A. The shooting parameters include the focal length C corresponding to shooting coordinates A. If the shooting coefficient is less than or equal to the set shooting coefficient threshold, the shooting unit will take a single shot of the line based on the shooting parameters obtained by the acquisition unit to obtain an image. ; If the shooting coefficient is greater than the set shooting coefficient threshold, the calculation unit calculates the focal length set D based on the focal length C, including: S1. Sort the elements in set B in order of acquisition time from earliest to latest to obtain set F; S2, initialize n to 1, where n is a positive integer, initialize m to 1, where m is a positive integer; S3, for the nth element in set F ,like If the value is 0, then... Save to zero element collection Enter S4; if If the value is not 0, proceed to S5; S4, increment the value of n by 1. If n is greater than N, proceed to S6; if n is less than N, proceed to S3. S5, increment the value of m by 1, increment the value of n by 1, then proceed to S3; S6, save the set of all obtained zero elements; S7, calculates the upper limit of focal length based on the set of zero elements. and lower limit value ,include: ; G represents the change in focal length, and G represents the set of all zero elements. and Let represent the latest and earliest values ​​at the time when the zero element is acquired, respectively. Represents the total number of elements in the set of zero. This indicates the set time length. Indicates the set focal length; , ; S8, in intervals of 1 millimeter in the range Multiple focal lengths are obtained within the range, and all obtained focal lengths are saved to the focal length set D; The shooting unit captures images of the line based on the focal length set D, obtaining a set E of multiple images of the line at shooting coordinates A. This includes: before shooting, the ranging module continuously measures the distance in the ranging direction, obtaining multiple distances; when the latest obtained distance changes from 0 to a non-zero value or from a non-zero value to 0, the shooting unit initiates shooting; a focal length is selected sequentially from the focal length set D in ascending order as the focal length for shooting, and the shutter speed is calculated based on the currently used focal length; each focal length in the focal length set D is captured at least once, and all the obtained images are saved to set E. The operation and maintenance platform is used when the drone only captures one image at shooting coordinate A. At that time, The image selected for operation and maintenance identification; And when the drone obtains set E at coordinate A, it selects the image with the highest resolution in set E as the image for operation and maintenance identification.

2. The operation and maintenance system based on power big data according to claim 1, characterized in that, The operation and maintenance platform includes a filtering module, an identification module, and a prompting module; The filtering module is used to filter images when the drone captures only one image at shooting coordinate A. At that time, The image selected for operation and maintenance identification; And when the drone obtains set E at coordinate A, it selects the image with the highest resolution in set E as the image for operation and maintenance identification. The recognition module is used to identify images used for operation and maintenance identification and obtain recognition results; the recognition results are either "line normal" or "line abnormal". The prompting module is used to provide prompts to maintenance personnel based on the recognition results.

3. The operation and maintenance system based on power big data according to claim 2, characterized in that, Based on the identification results, prompts will be made to the maintenance personnel, including: When the identification result indicates a line abnormality, a notification message is sent to the maintenance personnel through a pre-set prompt method. The notification message includes the coordinates of the line.

4. The operation and maintenance system based on power big data according to claim 1, characterized in that, The ranging module includes a retrieval unit, a ranging direction storage unit, and a ranging unit; The ranging direction storage unit is used to pre-store the ranging direction of each shooting coordinate; The retrieval unit is used to retrieve the ranging direction stored in the ranging direction storage unit based on the shooting coordinates A, and obtain the ranging direction corresponding to shooting coordinates A. ; The ranging unit is used to acquire distances at preset intervals and in the ranging direction. Perform N distance measurements to obtain N distances, and save the N distances to set B.

5. The operation and maintenance system based on power big data according to claim 1, characterized in that, The acquisition unit includes a retrieval subunit and a shooting parameter storage subunit; The shooting parameter storage subunit is used to pre-store the shooting parameters for each shooting coordinate; The retrieval subunit is used to retrieve the shooting parameters stored in the shooting parameter storage subunit based on the shooting coordinates A, and obtain the shooting parameters corresponding to shooting coordinates A.

6. A power big data-based operation and maintenance method, implemented based on the system described in claim 1, characterized in that, Includes the following steps: Control the drone to fly to the preset shooting coordinates A; The ranging direction is obtained based on the shooting coordinates A, and N distances are obtained based on the ranging direction. The N distances are then saved to set B. Calculate the shooting coefficients for set B; Shooting parameters are obtained based on shooting coordinates A, including the focal length C corresponding to shooting coordinates A. If the shooting coefficient is less than or equal to a set shooting coefficient threshold, a single shot is taken of the line based on the shooting parameters to obtain an image. ; If the shooting coefficient is greater than the set shooting coefficient threshold, then the focal length set D is calculated based on the focal length C, and the line is photographed based on the focal length set D to obtain a set E of multiple images of the line at shooting coordinate A. The drone only captured one image at coordinate A. At that time, The image selected for operation and maintenance identification; And when the drone obtains set E at coordinate A, the image with the highest resolution in set E is selected as the image for operation and maintenance identification.

7. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the operation and maintenance method as described in claim 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the operation and maintenance method as described in claim 6.

Images