Method and system for monitoring conductor sag of power transmission line under high temperature and heavy load conditions

Abstract

The embodiment of the application provides a kind of high temperature big load condition under transmission line conductor sag monitoring method and system, belong to transmission line conductor sag monitoring technical field.The monitoring method includes constructing the model for identifying the suspension point of the conductor sag image of the power pole tower hanging conductor, the vertex and bottom point of the power pole tower;Obtain the real-time image of multiple perspectives of the conductor sag to be monitored at present;The real-time image of the conductor sag is obtained, and the suspension point, fixed point and bottom point of the power pole tower in the real-time image are identified, the available image is filtered out first, then the lowest point of the conductor sag is obtained according to the conductor coordinates in the available image, and the sag value of the conductor can be obtained, which effectively obtains the sag value of the conductor, and the operation is simple, and the measuring efficiency is high.

Description

Technical Field

[0001] This invention relates to the field of transmission line conductor sag monitoring technology, specifically to a method and system for monitoring transmission line conductor sag under high temperature and high load conditions. Background Technology

[0002] Sag refers to the vertical distance between the lowest point of a conductor and the line connecting the two suspension points on adjacent poles at the same height on a flat surface. Generally, when the transmission distance is long, the conductor's own weight will cause slight sag, making the conductor resemble a catenary. Specifically, there are two cases of sag: one is when the suspension points of adjacent poles at both ends of the conductor are at the same height, in which case there is only one sag value; the other is when the suspension points of adjacent poles at both ends of the conductor are at different heights, in which case there are two sag values, namely the horizontal distance from each of the two suspension points of the conductor to the plumb line at the lowest point of the conductor.

[0003] Currently, to ensure the safe and stable operation of the power grid system, it is necessary to regularly inspect the sag of conductors. Sag measurement is generally performed on-site using auxiliary devices, but this method requires a significant investment of manpower, resources, and time, and is inefficient.

[0004] In the process of realizing this invention, the inventors of this application discovered that the above-mentioned solutions of the prior art have the drawbacks of requiring a lot of manpower, material resources and time, and having low calculation efficiency. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for monitoring the sag of transmission line conductors under high temperature and high load conditions. This method and system for monitoring the sag of transmission line conductors under high temperature and high load conditions is simple to calculate and highly efficient.

[0006] To achieve the above objectives, embodiments of the present invention provide a method for monitoring conductor sag in transmission lines under high-temperature and high-load conditions, comprising:

[0007] Construct a model to identify the suspension point of the conductor, the apex and the base of the power pole in the conductor sag image of the transmission line;

[0008] Acquire real-time images of the conductor sag from multiple perspectives currently being monitored;

[0009] Construct a coordinate system for each of the real-time images, wherein the origin of the coordinate system is located at the lower left corner of the real-time image;

[0010] The real-time image is input into the model to obtain the coordinates of the suspension point, vertex, and base of two adjacent power poles in the real-time image;

[0011] The available image is determined based on the coordinates of the apex and base of two adjacent power poles in the real-time image;

[0012] Obtain multiple conductor coordinates between two adjacent power poles in each available image;

[0013] The coordinates of the lowest point of the corresponding conductor sag are obtained based on the multiple conductor coordinates in each available image;

[0014] The conductor sag value is obtained based on the coordinates of the vertex and basal points of two adjacent power poles in each available image, as well as the coordinates of the lowest point of the conductor sag.

[0015] Optionally, constructing a model for identifying the suspension point of the conductor, the apex, and the base of the power pole in an image of conductor sag in a transmission line includes:

[0016] Construct a neural network model for conductor sag in power transmission lines;

[0017] Obtain a training sample set of the conductor sag images;

[0018] The neural network model of the conductor sag is trained based on the training sample set.

[0019] Optionally, determining the usable image based on the coordinates of the vertices and bases of two adjacent power poles in the real-time image includes:

[0020] Calculate the vertical height of one of the adjacent power poles according to formula (1).

[0021] h1 = y a1 -y b1 (1)

[0022] Where h1 is the vertical height of one of the adjacent power poles, y a1 Let y be the ordinate of the vertex of one of the adjacent power poles. b1 The ordinate of the base point of one of the adjacent power poles;

[0023] Calculate the vertical height of the other adjacent power pole according to formula (2).

[0024] h2=y a2 -y b2 (2)

[0025] Where h2 is the vertical height of the other adjacent power pole, y a2 Let y be the ordinate of the vertex of the adjacent power pole. b2 The coordinate is the ordinate of the base point of the other adjacent power pole.

[0026] Optionally, determining the usable image based on the coordinates of the vertices and bases of two adjacent power poles in the real-time image further includes:

[0027] Obtain the actual vertical height of two adjacent power poles;

[0028] The viewpoint error value of the real-time image is calculated according to formula (3).

[0029]

[0030] Wherein, H1 is the actual vertical height of one of the adjacent power poles, H2 is the actual vertical height of the other adjacent power pole, and σ is the viewpoint error value of the real-time image;

[0031] Determine whether the viewpoint error value of the real-time image is less than the error threshold;

[0032] When the viewpoint error value of the real-time image is determined to be less than the error threshold, the real-time image is determined to be a usable image;

[0033] If the viewpoint error value of the real-time image is greater than or equal to the error threshold, the real-time image is determined to be an unusable image.

[0034] Optionally, obtaining multiple conductor coordinates between two adjacent power poles in each available image includes:

[0035] Desaturate the available image;

[0036] Obtain the average depth value of the suspension point in the available image;

[0037] Pixel detection is performed on the sag region between two adjacent power poles in the available image;

[0038] Multiple adjacent pixels are pre-defined as a detection point;

[0039] Obtain the average depth value of the detection point;

[0040] The similarity between the average depth values ​​of the current detection point and the suspension point within the sag region is calculated according to formula (4).

[0041]

[0042] Where δ is the similarity between the average depth values ​​of the current detection point and the suspension point, and D i This represents the average depth value of the current i-th detection point, where i is an integer. The average depth of the suspension point is τ, which is an adjustment parameter, and τ>1;

[0043] Determine whether the similarity between the average depth values ​​of the current detection point and the suspension point is greater than or equal to a similarity threshold;

[0044] If the similarity between the average depth value of the current detection point and the suspension point is greater than or equal to the similarity threshold, the current detection point is determined to be a point to be verified.

[0045] If the similarity between the average depth value of the current detection point and the suspension point is less than the similarity threshold, then the current detection point is determined not to be a point to be verified.

[0046] Optionally, obtaining multiple conductor coordinates between two adjacent power poles in each of the available images further includes:

[0047] Obtain the coordinates of each of the points to be verified;

[0048] Determine whether the x-coordinates of the adjacent preset number of points to be verified gradually increase;

[0049] If the x-coordinates of the adjacent preset number of points to be verified gradually increase, then determine whether the y-coordinates of the adjacent preset number of points to be verified increase or decrease sequentially.

[0050] If the ordinates of adjacent preset number of points to be verified increase or decrease sequentially, the preset number of points to be verified are determined to be traverse coordinates.

[0051] Optionally, obtaining the coordinates of the lowest point of the corresponding conductor sag based on the multiple conductor coordinates in each available image includes:

[0052] A curve corresponding to the sag of the conductor is fitted based on multiple conductor coordinates of each available image;

[0053] The coordinates of the lowest point of the conductor sag are obtained based on the curve of the conductor sag in each available image.

[0054] Optionally, obtaining the conductor sag value based on the coordinates of the vertex and base of two adjacent power poles in each available image, as well as the coordinates of the lowest point of the guide sag, includes:

[0055] The height difference between the vertices of two adjacent power poles in the available image is calculated according to formula (5).

[0056]

[0057] Where ε is the height difference between the vertices of two adjacent power poles in the available image. The average height of the apex of one of the adjacent power poles in the available image. The average height of the apex of the other adjacent power pole in the available image;

[0058] Determine whether the height difference between the vertices of two adjacent power poles in the available image is less than or equal to a height difference threshold;

[0059] If the height difference between the vertices of two adjacent power poles in the available image is less than or equal to a height difference threshold,

[0060] Calculate the conductor sag value according to formula (6).

[0061]

[0062] Where f is the sag value of the conductor, α j The weight of the j-th available image, Let be the ordinate of any of the power poles in the j-th available image. Let be the ordinate of the lowest point of the conductor sag in the j-th available image, n be the number of available images, j be an integer number, and j≤n.

[0063] Optionally, obtaining the conductor sag value based on the coordinates of the vertex and base of two adjacent power poles in each available image, as well as the coordinates of the lowest point of the guide sag, further includes:

[0064] If it is determined that the height difference between the vertices of two adjacent power poles in the available image is greater than a height difference threshold,

[0065] Calculate the conductor sag value according to formula (7).

[0066]

[0067] Where f1 is the sag value of the first conductor and f2 is the sag value of the second conductor. Let be the ordinate of one of the adjacent power poles in the j-th available image. Let be the ordinate of the next adjacent power pole in the j-th available image.

[0068] On the other hand, the present invention also provides a monitoring system for conductor sag in transmission lines under high temperature and high load conditions, comprising:

[0069] Drones are used to capture images or videos of conductor sag in power transmission lines.

[0070] A central processing unit is used to execute any of the monitoring methods described above.

[0071] Through the above technical solution, the method and system for monitoring conductor sag of transmission lines under high temperature and high load conditions provided by the present invention acquires real-time images of conductor sag and identifies the suspension point, fixed point and bottom point of the power tower in the real-time images. It first filters out usable images, and then obtains the lowest point of conductor sag based on the conductor coordinates in the usable images. In this way, the conductor sag value can be obtained. This method effectively obtains the conductor sag value, and is simple to operate and has high measurement efficiency.

[0072] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0073] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0074] Figure 1 This is a flowchart of a method for monitoring conductor sag in transmission lines under high temperature and high load conditions according to an embodiment of the present invention.

[0075] Figure 2 This is a flowchart of a neural network model for training conductor sag in a method for monitoring conductor sag under high temperature and high load conditions according to an embodiment of the present invention.

[0076] Figure 3 This is a flowchart of a method for monitoring conductor sag in transmission lines under high temperature and high load conditions according to an embodiment of the present invention, which is used to select usable images.

[0077] Figure 4 This is a flowchart of a method for monitoring conductor sag under high temperature and high load conditions in a transmission line according to an embodiment of the present invention, which is used to obtain conductor coordinates.

[0078] Figure 5 This is a method for monitoring the sag of transmission line conductors under high temperature and high load conditions according to an embodiment of the present invention, which obtains the coordinates of the lowest point of the conductor sag.

[0079] Figure 6 This is a flowchart for calculating the conductor sag value in a method for monitoring conductor sag under high temperature and high load conditions according to an embodiment of the present invention. Detailed Implementation

[0080] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0081] Figure 1 This is a flowchart of a method for monitoring conductor sag in transmission lines under high-temperature, high-load conditions according to an embodiment of the present invention. Figure 1 In this context, the monitoring method may include:

[0082] In step S10, a model is constructed to identify the suspension point of the conductor hanging from the power pole, the apex of the power pole, and the base of the power pole in the conductor sag image of the transmission line. This model may include neural network models known to those skilled in the art.

[0083] In step S11, real-time images of the conductor sag from multiple perspectives are acquired. These real-time images of the conductor sag may include, but are not limited to, images obtained via drone photography.

[0084] In step S12, a coordinate system is constructed for each real-time image, with the origin of the coordinate system located at the lower left corner of the real-time image. The fact that the origin of the coordinate system is also located at the lower left corner of the real-time image indicates that all coordinates on the real-time image are positive.

[0085] In step S13, the real-time image is input into the model to obtain the coordinates of the suspension point, vertex, and base of two adjacent power poles in the real-time image.

[0086] In step S14, a usable image is determined based on the coordinates of the apex and base of two adjacent power poles in the real-time image. The drone acquires multiple images from different perspectives of the conductor during the shooting process. To improve the accuracy of conductor sag calculation, an image specific to the conductor's perspective is selected; this is the usable image.

[0087] In step S15, multiple conductor coordinates between two adjacent power poles in each available image are obtained.

[0088] In step S16, the coordinates of the lowest point of the corresponding conductor sag are obtained based on the multiple conductor coordinates in each available image.

[0089] In step S17, the conductor sag value is obtained based on the coordinates of the vertex and base points of two adjacent power poles and the lowest point of the conductor sag in each available image. Specifically, the conductor sag value can be calculated once the coordinates of the vertex and base points of two adjacent power poles and the lowest point of the conductor sag are obtained.

[0090] In steps S10 to S17, a model capable of identifying and locating suspension points, the top and bottom points of power poles is first constructed and pre-trained. Then, real-time images of the conductor are acquired and input into the model to obtain the suspension points, the top and bottom points of the power poles in the real-time images. Available images are selected based on the coordinates of these points. Finally, based on the coordinates of multiple conductors in the available images, the coordinates of the lowest point of the conductor sag are determined, and thus the conductor sag value can be calculated.

[0091] Traditional methods for measuring conductor sag typically involve on-site measurement using auxiliary devices. However, this method requires significant manpower, resources, and time, and is inefficient. In this embodiment of the invention, by acquiring real-time images and relevant coordinates of the conductor, the conductor sag value can be calculated effectively without requiring substantial manpower or resources, resulting in high measurement efficiency.

[0092] In this embodiment of the invention, in order to identify the suspension point of the conductor, the apex and basal point of the power pole in the image of conductor sag, it is also necessary to construct a neural network model for image recognition. Specific steps can be as follows: Figure 2 As shown. Specifically, in Figure 2 In addition, the monitoring method may also include:

[0093] In step S20, a neural network model of conductor sag in the transmission line is constructed.

[0094] In step S21, a training sample set of conductor sag images is obtained. This training sample set may include the conductor's suspension point, the apex and base of the power pole, etc. Specifically, the apex and base of the power pole refer to the top center and bottom center of the power pole, respectively.

[0095] In step S22, the neural network model of conductor sag is trained based on the training sample set.

[0096] In this embodiment of the invention, in order to eliminate the interference of the drone's viewing angle on the real-time image of the conductor and improve the accuracy of the conductor sag calculation, it is also necessary to filter the images captured by the drone. Specifically, the filtering method can be as follows: Figure 3 As shown. Specifically, in Figure 3 In addition, the monitoring method may also include:

[0097] In step S30, the vertical height of one of the adjacent power poles is calculated according to formula (1).

[0098] h1 = y a1 -y b1 (1)

[0099] Where h1 is the vertical height of one of the adjacent power poles, and y a1 Let y be the ordinate of the vertex of one of the adjacent power poles. b1 This represents the ordinate of the base point of one of the adjacent power poles.

[0100] In step S31, the vertical height of the other adjacent power pole is calculated according to formula (2).

[0101] h2=y a2 -y b2 (2)

[0102] Where h2 is the vertical height of the other adjacent power pole, and y a2 Let y be the ordinate of the vertex of the adjacent power pole. b2 This is the ordinate of the base point of the adjacent power pole.

[0103] In step S32, the actual vertical height of two adjacent power poles is obtained.

[0104] In step S33, the viewpoint error value of the real-time image is calculated according to formula (3).

[0105]

[0106] Where H1 is the actual vertical height of one of the adjacent power poles, H2 is the actual vertical height of the other adjacent power pole, and σ is the viewpoint error value of the real-time image.

[0107] In step S34, it is determined whether the viewpoint error value of the real-time image is less than the error threshold.

[0108] In step S35, if the viewing angle error value of the real-time image is less than the error threshold, the real-time image is determined to be a usable image. Specifically, if the viewing angle error value of the real-time image is less than the error threshold, it indicates that the two power poles are approximately scaled proportionally, meaning the two power poles are approximately parallel to the image's imaging plane, i.e., directly facing the two power poles. This method ensures that the two power poles and the conductors are located on the same plane, reducing interference from other viewing angles on the imaging and improving subsequent measurement accuracy.

[0109] In step S36, if the viewing angle error value of the real-time image is greater than or equal to the error threshold, the real-time image is determined to be unusable. If the viewing angle error value of the real-time image is too large, the images of the two power poles will be distributed front and back, indicating a measurement error.

[0110] In steps S30 to S36, the vertical height of two adjacent power poles in the real-time image is first calculated, and then the viewing angle error value of the real-time image is calculated. This viewing angle error value is compared with an error threshold. If the viewing angle error value is less than the error threshold, it indicates that the two adjacent power poles and the conductor are parallel to the image imaging plane, reducing interference from tilted viewing angles and other images, thus facilitating accurate subsequent calculations.

[0111] In this embodiment of the invention, in order to further determine the specific location of the conductor, it is also necessary to determine the coordinates of the conductor in the available image. Specifically, the determination method may include, for example... Figure 4 The steps are shown. Specifically, in Figure 4 In this context, the monitoring method may include:

[0112] In step S40, the available image is desaturated. This desaturates the available image into an image with multiple grayscale levels.

[0113] In step S41, the average depth value of the suspending points in the available image is obtained. Specifically, based on the identified suspending points, the average depth value of pixels within a preset range near them is calculated.

[0114] In step S42, pixel detection is performed on the sag region between two adjacent power poles in the available image. Pixel detection of the sag region between two poles further expands the detection range of the conductors, which helps improve detection efficiency. Furthermore, considering the efficiency of conductor pixel detection, images without background obstructions such as hills or bridges can be selected during image capture.

[0115] In step S43, multiple adjacent pixels are pre-defined as a detection point. The shape of the detection point can include a circle or a square, etc.

[0116] In step S44, the average depth value of the detection points is obtained. The average depth value of the detection points can be obtained by averaging over all pixels in the detection point.

[0117] In step S45, the similarity between the average depth values ​​of the current detection point and the suspension point within the sag region is calculated according to formula (4).

[0118]

[0119] Where δ represents the similarity between the average depth values ​​of the current detection point and the suspension point, and D... i This represents the average depth value of the current i-th detection point, where i is an integer. Let be the average depth of the suspension point, and τ be an adjustment parameter, where τ > 1.

[0120] In step S46, it is determined whether the similarity between the average depth values ​​of the current detection point and the suspension point is greater than or equal to the similarity threshold.

[0121] In step S47, if the similarity between the average depth values ​​of the current detection point and the suspension point is greater than or equal to a similarity threshold, the current detection point is determined to be a point to be verified. Specifically, if the similarity between the detection point and the suspension point is greater than or equal to the similarity threshold, it means that their depth values ​​are similar, i.e., they are points on the guide wire.

[0122] In step S48, if the similarity between the average depth values ​​of the current detection point and the suspension point is less than a similarity threshold, then the current detection point is determined not to be a point to be verified. Specifically, if the similarity between the detection point and the suspension point is less than the similarity threshold, it indicates that their depth values ​​differ significantly, and the detection point is not a point on the guide wire.

[0123] In step S49, the coordinates of each point to be verified are obtained.

[0124] In step S50, it is determined whether the x-coordinates of adjacent preset number of points to be verified gradually increase.

[0125] In step S51, if it is determined that the abscissa of the adjacent preset number of verification points gradually increases, it is determined whether the ordinate of the adjacent preset number of verification points increases or decreases sequentially. Specifically, if the abscissa of the preset number of verification points on the line gradually increases, it indicates that the verification point is moving along the X+ axis, i.e., from the left power pole to the right power pole.

[0126] In step S52, if the ordinates of adjacent preset number of points to be verified increase or decrease sequentially, the preset number of points to be verified are determined to be traverse coordinates. If the ordinates of adjacent preset number of points to be verified increase or decrease sequentially, it indicates that the points form an arc and are all points constituting the traverse.

[0127] In steps S40 to S52, the available image is first desaturated, and then the average depth value of the suspension points is obtained based on the depth values ​​of the pixels at the identified suspension points. A detection point is then preset, and pixel detection is performed on the sag region between two adjacent power poles to determine detection points with average depth values ​​similar to the suspension points. Finally, multiple adjacent detection points to be verified are judged to determine whether they are curves, i.e., whether they gradually increase or decrease, thereby obtaining multiple detection points on the conductor.

[0128] In this embodiment of the invention, after obtaining multiple detection points on the conductor, it is also necessary to calculate the lowest point of the conductor. The specific calculation steps can be as follows: Figure 5 As shown. Specifically, in Figure 5In addition, the monitoring method may also include:

[0129] In step S53, a curve for the sag of the corresponding conductor is fitted based on multiple conductor coordinates of each available image.

[0130] In step S54, the coordinates of the lowest point of the conductor sag are obtained according to the curve of the conductor sag of each available image.

[0131] In this embodiment of the invention, after determining the coordinates of the lowest point of the conductor sag, the conductor sag value can be obtained. Specifically, the steps for obtaining the sag can be as follows: Figure 6 As shown. Specifically, in Figure 6 In addition, the monitoring method may also include:

[0132] In step S60, the height difference between the vertices of two adjacent power poles in the available image is calculated according to formula (5).

[0133]

[0134] Where ε is the height difference between the vertices of two adjacent power poles in the available image. This represents the average height of the vertices of one of the adjacent power poles in the available image. This represents the average height of the apex of another adjacent power pole in the available image.

[0135] In step S61, it is determined whether the height difference between the vertices of two adjacent power poles in the available image is less than or equal to the height difference threshold.

[0136] In step S62, if it is determined that the height difference between the vertices of two adjacent power poles in the available image is less than or equal to the height difference threshold,

[0137] Calculate the conductor sag value according to formula (6).

[0138]

[0139] Where f is the conductor sag value, α j The weight of the j-th available image, Let be the ordinate of any power pole in the j-th available image. Let be the ordinate of the lowest point of the conductor sag in the j-th available image, n be the number of available images, j be the integer number, and j≤n.

[0140] In step S63, if it is determined that the height difference between the vertices of two adjacent power poles in the available image is greater than the height difference threshold,

[0141] Calculate the conductor sag value according to formula (7).

[0142]

[0143] Where f1 is the sag value of the first conductor and f2 is the sag value of the second conductor. Let be the ordinate of one of the adjacent power poles in the j-th available image. Let be the ordinate of the next adjacent power pole in the j-th available image.

[0144] In steps S60 to S63, to calculate the conductor sag value, it is necessary to first determine whether the apex heights of the two adjacent power poles are the same. If the heights of the two adjacent power poles are the same, a conductor sag value can be calculated; if the heights of the two adjacent power poles are different, two conductor sag values ​​are calculated separately.

[0145] On the other hand, the present invention also provides a monitoring system for conductor sag in transmission lines under high-temperature and high-load conditions. Specifically, the monitoring system may include a drone and a central processing unit. Specifically, the drone is used to capture images or images of conductor sag in the transmission line, and the central processing unit is used to execute any of the monitoring methods described above.

[0146] Through the above technical solution, the method and system for monitoring conductor sag of transmission lines under high temperature and high load conditions provided by the present invention acquires real-time images of conductor sag and identifies the suspension point, fixed point and bottom point of the power tower in the real-time images. It first filters out usable images, and then obtains the lowest point of conductor sag based on the conductor coordinates in the usable images. In this way, the conductor sag value can be obtained. This method effectively obtains the conductor sag value, and is simple to operate and has high measurement efficiency.

[0147] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0148] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, 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... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0149] 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.

[0150] 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.

[0151] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0152] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0153] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0154] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0155] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for monitoring conductor sag in transmission lines under high temperature and high load conditions, characterized in that, include: Construct a model to identify the suspension point of the conductor, the apex and the base of the power pole in the conductor sag image of the transmission line; Acquire real-time images of the conductor sag from multiple perspectives currently being monitored; Construct a coordinate system for each of the real-time images, wherein the origin of the coordinate system is located at the lower left corner of the real-time image; The real-time image is input into the model to obtain the coordinates of the suspension point, vertex, and base of two adjacent power poles in the real-time image; The available image is determined based on the coordinates of the apex and base of two adjacent power poles in the real-time image; Obtain multiple conductor coordinates between two adjacent power poles in each available image; The coordinates of the lowest point of the corresponding conductor sag are obtained based on the multiple conductor coordinates in each available image; The conductor sag value is obtained based on the coordinates of the vertex and basal points of two adjacent power poles in each available image, as well as the coordinates of the lowest point of the conductor sag.

2. The monitoring method according to claim 1, characterized in that, The model constructed to identify the suspension point of the conductor, the apex and base of the power pole in images of conductor sag in transmission lines includes: Construct a neural network model for conductor sag in power transmission lines; Obtain a training sample set of the conductor sag images; The neural network model of the conductor sag is trained based on the training sample set.

3. The monitoring method according to claim 1, characterized in that, The available images are determined based on the coordinates of the vertices and bases of two adjacent power poles in the real-time image, including: Calculate the vertical height of one of the adjacent power poles according to formula (1). h1=y a1 -and b1 , (1) Where h1 is the vertical height of one of the adjacent power poles, y a1 Let y be the ordinate of the vertex of one of the adjacent power poles. b1 The ordinate of the base point of one of the adjacent power poles; Calculate the vertical height of the other adjacent power pole according to formula (2). h2=y a2 -and b2 , (2) Where h2 is the vertical height of the other adjacent power pole, y a2 Let y be the ordinate of the vertex of the adjacent power pole. b2 The coordinate is the ordinate of the base point of the other adjacent power pole.

4. The monitoring method according to claim 3, characterized in that, The determination of usable images based on the coordinates of the vertices and bases of two adjacent power poles in the real-time image also includes: Obtain the actual vertical height of two adjacent power poles; The viewpoint error value of the real-time image is calculated according to formula (3). Wherein, H1 is the actual vertical height of one of the adjacent power poles, H2 is the actual vertical height of the other adjacent power pole, and σ is the viewpoint error value of the real-time image; Determine whether the viewpoint error value of the real-time image is less than the error threshold; When the viewpoint error value of the real-time image is determined to be less than the error threshold, the real-time image is determined to be a usable image; If the viewpoint error value of the real-time image is greater than or equal to the error threshold, the real-time image is determined to be an unusable image.

5. The monitoring method according to claim 1, characterized in that, Obtaining multiple conductor coordinates between two adjacent power poles in each of the available images includes: Desaturate the available image; Obtain the average depth value of the suspension point in the available image; Pixel detection is performed on the sag region between two adjacent power poles in the available image; Multiple adjacent pixels are pre-defined as a detection point; Obtain the average depth value of the detection point; The similarity between the average depth values ​​of the current detection point and the suspension point within the sag region is calculated according to formula (4). Where δ is the similarity between the average depth values ​​of the current detection point and the suspension point, and D i This represents the average depth value of the current i-th detection point, where i is an integer. The average depth of the suspension point is τ, which is an adjustment parameter, and τ>1; Determine whether the similarity between the average depth values ​​of the current detection point and the suspension point is greater than or equal to a similarity threshold; If the similarity between the average depth value of the current detection point and the suspension point is greater than or equal to the similarity threshold, the current detection point is determined to be a point to be verified. If the similarity between the average depth value of the current detection point and the suspension point is less than the similarity threshold, then the current detection point is determined not to be a point to be verified.

6. The monitoring method according to claim 5, characterized in that, Obtaining multiple conductor coordinates between two adjacent power poles in each of the available images further includes: Obtain the coordinates of each of the points to be verified; Determine whether the x-coordinates of the adjacent preset number of points to be verified gradually increase; If the x-coordinates of the adjacent preset number of points to be verified gradually increase, then determine whether the y-coordinates of the adjacent preset number of points to be verified increase or decrease sequentially. If the ordinates of adjacent preset number of points to be verified increase or decrease sequentially, the preset number of points to be verified are determined to be traverse coordinates.

7. The monitoring method according to claim 6, characterized in that, Obtaining the coordinates of the lowest point of the corresponding conductor sag based on multiple conductor coordinates in each available image includes: A curve corresponding to the sag of the conductor is fitted based on multiple conductor coordinates of each available image; The coordinates of the lowest point of the conductor sag are obtained based on the curve of the conductor sag in each available image.

8. The monitoring method according to claim 7, characterized in that, The conductor sag value is obtained based on the coordinates of the vertex and base of two adjacent power poles in each available image, as well as the coordinates of the lowest point of the conductor sag, including: The height difference between the vertices of two adjacent power poles in the available image is calculated according to formula (5). Where ε is the height difference between the vertices of two adjacent power poles in the available image. The average height of the apex of one of the adjacent power poles in the available image. The average height of the apex of the other adjacent power pole in the available image; Determine whether the height difference between the vertices of two adjacent power poles in the available image is less than or equal to a height difference threshold; If the height difference between the vertices of two adjacent power poles in the available image is less than or equal to a height difference threshold, Calculate the conductor sag value according to formula (6). Where f is the sag value of the conductor, α j The weight of the j-th available image, Let be the ordinate of any of the power poles in the j-th available image. Let be the ordinate of the lowest point of the conductor sag in the j-th available image, n be the number of available images, j be an integer number, and j≤n.

9. The monitoring method according to claim 8, characterized in that, Obtaining the conductor sag value based on the coordinates of the vertex and base of two adjacent power poles in each available image, as well as the coordinates of the lowest point of the conductor sag, further includes: If it is determined that the height difference between the vertices of two adjacent power poles in the available image is greater than a height difference threshold, Calculate the conductor sag value according to formula (7). Where f1 is the sag value of the first conductor and f2 is the sag value of the second conductor. Let be the ordinate of one of the adjacent power poles in the j-th available image. Let be the ordinate of the next adjacent power pole in the j-th available image.

10. A monitoring system for conductor sag in transmission lines under high temperature and high load conditions, characterized in that, include: Drones are used to capture images or videos of conductor sag in power transmission lines. A central processing unit for executing the monitoring method as described in any one of claims 1-9.

Images