A method and device for dynamic analysis of conductor sag of a power transmission line

Abstract

The application relates to the technical field of power transmission line analysis, and particularly provides a power transmission line conductor sag dynamic analysis method and device, which comprises the following steps: obtaining a power transmission line target detection result; adopting an edge detection algorithm to perform edge detection on the power transmission line detection result to obtain conductor edge information; performing linear fitting on the conductor edge information to obtain a fitting function curve corresponding to the conductor edge information; and selecting a fitting function curve with a cross-correlation coefficient between a static balance linear function corresponding to the power transmission line exceeding a preset value as a dynamic linear function of the conductor. The technical scheme provided by the application takes the static balance linear function corresponding to the power transmission line as an initial boundary condition for finding the dynamic linear function of the conductor, can improve the calculation speed and calculation precision of the dynamic linear function of the conductor and the dynamic sag corresponding to the lowest point of the conductor, and improves the instantaneity of the conductor sag online real-time analysis.

Description

Technical Field

[0001] This invention relates to the field of power transmission line analysis technology, specifically to a method and apparatus for dynamic analysis of conductor sag in power transmission lines. Background Technology

[0002] Online monitoring of conductor sag is crucial to the conductor's current carrying capacity. Only through accurate monitoring and real-time response analysis can the current carrying capacity of the line be maximized while ensuring line safety.

[0003] Currently, real-time online measurement of conductor sag can be carried out through video monitoring. However, the fitting and optimization of conductor shape and the search range of the lowest point are affected by the initial shape-finding function and parameter settings. This inevitably leads to untimely completion of the analysis work, which cannot match the adjustment time cycle of conductor current carrying capacity. It may also lead to the linearity and sag measurement obtained by fitting not being very accurate, thus causing deeper power grid transmission safety problems. Summary of the Invention

[0004] To overcome the above-mentioned defects, this invention proposes a method and device for dynamic analysis of conductor sag in power transmission lines.

[0005] Firstly, a method for dynamic analysis of conductor sag in transmission lines is provided, the method comprising:

[0006] The collected conductor line point cloud data of the transmission line is used as the input of a pre-trained machine learning-based target detection model to obtain the transmission line detection results output by the pre-trained machine learning-based target detection model.

[0007] An edge detection algorithm is used to perform edge detection on the detection results of the transmission line to obtain conductor edge information;

[0008] The conductor edge information is linearly fitted to obtain the fitting function curve corresponding to the conductor edge information;

[0009] The fitted function curve with a cross-correlation coefficient exceeding a preset value between the static equilibrium alignment function corresponding to the transmission line is selected as the dynamic alignment function of the conductor.

[0010] Preferably, the training process of the pre-trained machine learning-based object detection model includes:

[0011] Training data was constructed using conductor line point cloud data of transmission lines and conductor line point cloud data with background removed.

[0012] The machine learning-based object detection model is trained using the training data to obtain the pre-trained machine learning-based object detection model.

[0013] Preferably, the edge detection algorithm includes: Roberts algorithm, Sobel algorithm, Gauss-Laplace algorithm, and Canny algorithm.

[0014] Preferably, the preset value is 0.5.

[0015] Preferably, the static equilibrium alignment function corresponding to the transmission line is as follows:

[0016] The length of the conductor is determined based on the temperature rise of the conductor.

[0017] The horizontal stress of the conductor is determined based on its length.

[0018] The sag at any point on the conductor is determined based on the horizontal stress of the conductor.

[0019] Furthermore, the temperature rise of the conductor is as follows:

[0020]

[0021] In the above formula, ΔT represents the temperature rise of the conductor, and T c0 T0 is the initial temperature of the conductor, and W is the ambient temperature. c Let α be the heat loss per unit length of the conductor, α be the heat absorption coefficient of the conductor surface, D be the conductor diameter, and E be the heat loss per unit length of the conductor. e Let A be the solar radiation intensity, A be the heat dissipation area per unit length of the conductor, and A = πD, α h λ is the heat dissipation coefficient of the conductor surface, π is pi, λ is the thermal conductivity of the air film in contact with the conductor, Eu is the Euler number, C is the heat capacity of the conductor, and t is the current time.

[0022] Furthermore, the Euler number is as follows:

[0023] Eu = 0.65 (65000νD) 0.2 +0.23(65000νD) 0.61

[0024] In the above formula, ν is the wind speed;

[0025] The heat loss per unit length of the conductor is as follows:

[0026] W c =I 2 R T

[0027] In the above formula, R T Let I be the AC resistance per unit length of conductor at the operating temperature, and let I be the current in the conductor.

[0028] Furthermore, the length of the wire is as follows:

[0029] l c =l0+α l ΔTl0

[0030] In the above formula, l c Let l0 be the length of the conductor, l0 be the initial length of the conductor, and α be the initial length of the conductor. l is the comprehensive linear temperature expansion coefficient of the conductor.

[0031] Furthermore, the horizontal stress σ0 of the conductor can be obtained by solving the following equation:

[0032]

[0033] In the above formula, g is the self-weight load per unit length of conductor, l is the horizontal distance between the suspension points of the main tower and the auxiliary tower, and l d1 Here, sh is the equivalent span corresponding to the suspension point of the main tower, ch is a hyperbolic sine function, and ch is a hyperbolic cosine function, wherein the height of the suspension point of the main tower is greater than the height of the suspension point of the auxiliary tower.

[0034] Furthermore, the sag at any point on the conductor is as follows:

[0035]

[0036] In the above formula, x2 is the distance between the suspension point of the main tower and any point x, and h is the distance between the suspension point of the main tower and any point x. x Let x be the sag at any point x on the conductor.

[0037] Secondly, a dynamic analysis device for conductor sag of a transmission line is provided, the device comprising:

[0038] The target detection module is used to take the collected conductor line shape point cloud data of the transmission line as input to a pre-trained machine learning-based target detection model, and obtain the transmission line detection results output by the pre-trained machine learning-based target detection model.

[0039] The edge detection module is used to perform edge detection on the detection results of the transmission line using an edge detection algorithm to obtain conductor edge information;

[0040] The linear fitting module is used to perform linear fitting on the conductor edge information to obtain the fitting function curve corresponding to the conductor edge information;

[0041] The analysis module is used to select the fitted function curve whose cross-correlation coefficient with the static equilibrium alignment function corresponding to the transmission line exceeds a preset value as the dynamic alignment function of the conductor.

[0042] Thirdly, a computer device is provided, comprising: one or more processors;

[0043] The processor is used to execute one or more programs;

[0044] When the one or more programs are executed by the one or more processors, the method for dynamic analysis of conductor sag in transmission lines is implemented.

[0045] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, wherein when the computer program is executed, the method for dynamic analysis of conductor sag of the transmission line is implemented.

[0046] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0047] This invention provides a method and apparatus for dynamic analysis of conductor sag in transmission lines, comprising: using collected conductor alignment point cloud data of the transmission line as input to a pre-trained machine learning-based target detection model to obtain transmission line detection results output by the pre-trained machine learning-based target detection model; performing edge detection on the transmission line detection results using an edge detection algorithm to obtain conductor edge information; performing linear fitting on the conductor edge information to obtain a fitting function curve corresponding to the conductor edge information; and selecting the fitting function curve whose cross-correlation coefficient with the static equilibrium alignment function corresponding to the transmission line exceeds a preset value as the dynamic alignment function of the conductor. The technical solution provided by this invention, using the static equilibrium alignment function corresponding to the transmission line as the initial boundary condition for finding the dynamic alignment of the conductor, can improve the calculation speed and accuracy of the dynamic alignment of the conductor and the dynamic sag corresponding to the lowest point of the conductor, and improve the immediacy of online real-time analysis of conductor sag, wherein:

[0048] The static equilibrium alignment function of the transmission line in this embodiment of the invention performs accurate sag calculation on the conductor based on online monitoring data such as temperature, wind speed, and solar radiation intensity. The subsequent dynamic sag fitting is performed on the basis of the static equilibrium alignment function of the transmission line, which can reduce the fitting time required for fitting and shorten the response time, providing a reliable basis for the dynamic analysis of conductor sag of the transmission line. Attached Figure Description

[0049] Figure 1 This is a schematic diagram of the main steps of the dynamic analysis method for conductor sag of transmission lines according to an embodiment of the present invention;

[0050] Figure 2 This is a circuit diagram captured by an online monitoring high-definition camera according to an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of the transmission line detection results according to an embodiment of the present invention;

[0052] Figure 4This is a line diagram obtained after line edge detection according to an embodiment of the present invention;

[0053] Figure 5 This is a graph of the linear function of the conductor at a certain moment according to an embodiment of the present invention. Detailed Implementation

[0054] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] As disclosed in the background section, online monitoring of conductor sag is related to the conductor's current carrying capacity. Only through accurate monitoring and real-time response analysis can the current carrying capacity of the line be increased as much as possible while ensuring line safety.

[0057] Currently, real-time online measurement of conductor sag can be carried out through video monitoring. However, the fitting and optimization of conductor shape and the search range of the lowest point are affected by the initial shape-finding function and parameter settings. This inevitably leads to untimely completion of the analysis work, which cannot match the adjustment time cycle of conductor current carrying capacity. It may also lead to the linearity and sag measurement obtained by fitting not being very accurate, thus causing deeper power grid transmission safety problems.

[0058] To address the aforementioned problems, this invention provides a method and apparatus for dynamic analysis of conductor sag in transmission lines, comprising: using collected conductor alignment point cloud data of the transmission line as input to a pre-trained machine learning-based target detection model to obtain transmission line detection results output by the pre-trained machine learning-based target detection model; performing edge detection on the transmission line detection results using an edge detection algorithm to obtain conductor edge information; performing linear fitting on the conductor edge information to obtain a fitting function curve corresponding to the conductor edge information; and selecting the fitting function curve whose cross-correlation coefficient with the static equilibrium alignment function corresponding to the transmission line exceeds a preset value as the dynamic alignment function of the conductor. The technical solution provided by this invention, using the static equilibrium alignment function corresponding to the transmission line as the initial boundary condition for finding the dynamic alignment of the conductor, can improve the calculation speed and accuracy of the dynamic alignment of the conductor and the dynamic sag corresponding to the lowest point of the conductor, improve the immediacy of online real-time analysis of conductor sag, and further:

[0059] The static equilibrium alignment function of the transmission line in this embodiment of the invention performs accurate sag calculation on the conductor based on online monitoring data such as temperature, wind speed, and solar radiation intensity. The subsequent dynamic sag fitting is performed on the basis of the static equilibrium alignment function of the transmission line, which can reduce the fitting time required for fitting and shorten the response time, providing a reliable basis for the dynamic analysis of conductor sag of the transmission line.

[0060] The above plan will be explained in detail below.

[0061] Example 1

[0062] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a dynamic analysis method for conductor sag in a transmission line according to an embodiment of the present invention. Figure 1 As shown, the dynamic analysis method for conductor sag of transmission lines in this embodiment of the invention mainly includes the following steps:

[0063] Step S101: Use the collected conductor line point cloud data of the transmission line as input to the pre-trained machine learning-based target detection model to obtain the transmission line detection result output by the pre-trained machine learning-based target detection model.

[0064] In this embodiment, the conductor line shape point cloud data of the transmission line can be extracted from line images captured by online monitoring high-definition cameras, such as... Figure 2 As shown;

[0065] Step S102: Use an edge detection algorithm to perform edge detection on the detection results of the transmission line to obtain conductor edge information;

[0066] Step S103: Perform linear fitting on the conductor edge information to obtain the fitting function curve corresponding to the conductor edge information;

[0067] Step S104: Select the fitting function curve whose cross-correlation coefficient with the static equilibrium alignment function corresponding to the transmission line exceeds the preset value as the dynamic alignment function of the conductor.

[0068] The preset value is 0.5.

[0069] In this embodiment, the training process of the pre-trained machine learning-based object detection model includes:

[0070] Training data was constructed using conductor line point cloud data of transmission lines and conductor line point cloud data with background removed.

[0071] The machine learning-based object detection model is trained using the training data to obtain the pre-trained machine learning-based object detection model.

[0072] In this embodiment, machine learning-based object detection models, represented by the YOLO (You Only Look Once) algorithm, can accurately detect the target of interest and extract key areas, thereby eliminating as much irrelevant information as possible, such as clouds, rivers, and forests. Figure 3 As shown.

[0073] In this embodiment, the edge detection process is divided into the following three parts:

[0074] 1) Filtering: Using filters to reduce the impact of noise on the detection results;

[0075] 2) Enhancement: Filtering not only eliminates the influence of noise, but also weakens the image intensity near the target. It is necessary to use relevant enhancement algorithms to make the parts with drastic changes in image intensity more drastic to facilitate subsequent edge detection.

[0076] 3) Detection: Intensity variations are widespread in images; however, not all intensity variations indicate the edges of objects. Therefore, it is necessary to set appropriate thresholds to support the detection of image edges.

[0077] In one implementation, the edge detection algorithms proposed in Matlab include: Roberts algorithm, Sobel algorithm, Gaussian-Laplace algorithm, and Canny algorithm.

[0078] In one specific implementation, the Canny algorithm is selected for wire edge detection, and its implementation process is as follows:

[0079] 1. Using a Gaussian smoothing filter for noise reduction essentially involves extracting features from the image using convolution for noise reduction;

[0080] 2. Calculate the gradient magnitude and direction. Similar to the Sobel operator, perform a smoothing operation and then solve for the derivative.

[0081] 3. Non-maximum suppression: Discard smaller values ​​and retain only some edges that show finer edges in the image as candidate edges to prepare for the next step;

[0082] 4. Lag Threshold: Two thresholds, one low and one high, are used for judgment. Pixels above the high threshold are retained. Pixels above the low threshold but below the high threshold are retained when they are judged to be connected to pixels with the high threshold. Other pixels are discarded.

[0083] The line image obtained after edge detection is as follows Figure 4 As shown.

[0084] In this embodiment, the static equilibrium alignment function corresponding to the transmission line is as follows:

[0085] The length of the conductor is determined based on the temperature rise of the conductor.

[0086] The horizontal stress of the conductor is determined based on its length.

[0087] The sag at any point on the conductor is determined based on the horizontal stress of the conductor.

[0088] In one embodiment, the temperature rise of the conductor is as follows:

[0089]

[0090] In the above formula, ΔT represents the temperature rise of the conductor, and T c0 T0 is the initial temperature of the conductor, and W is the ambient temperature. c The value is denoted as α, where α is the heat loss per unit length of conductor, α is the heat absorption coefficient of the conductor surface (0.23–0.46 for bright new conductors and 0.9–0.95 for blackened old conductors), D is the conductor diameter, and E is the conductor diameter. e Let A be the solar radiation intensity, A be the heat dissipation area per unit length of the conductor, and A = πD, α h Let λ be the heat dissipation coefficient of the conductor surface, π be pi, λ be the thermal conductivity of the air film in contact with the conductor (λ is assumed to be constant and equal to 0.02585 W / (m·K), Eu be the Euler number, C be the heat capacity of the conductor, and t be the current time.

[0091] In one implementation, the Euler number is as follows:

[0092] Eu = 0.65 (65000νD) 0.2 +0.23(65000νD) 0.61

[0093] In the above formula, ν is the wind speed;

[0094] The heat loss per unit length of the conductor is as follows:

[0095] W c =I 2 R T

[0096] In the above formula, R T Let I be the AC resistance per unit length of conductor at the operating temperature, and let I be the current in the conductor.

[0097] In one embodiment, the length of the wire is as follows:

[0098] l c =l0+α l ΔTl0

[0099] In the above formula, l cLet l0 be the length of the conductor, l0 be the initial length of the conductor, and α be the initial length of the conductor. l is the comprehensive linear temperature expansion coefficient of the conductor.

[0100] In one implementation, the horizontal stress σ0 of the conductor is obtained by solving the following equation:

[0101]

[0102] In the above formula, g is the self-weight load per unit length of conductor, l is the horizontal distance between the suspension points of the main tower and the auxiliary tower, and l d1 Here, sh is the equivalent span corresponding to the suspension point of the main tower, ch is a hyperbolic sine function, and ch is a hyperbolic cosine function, wherein the height of the suspension point of the main tower is greater than the height of the suspension point of the auxiliary tower.

[0103] In one implementation, the sag at any point on the conductor is as follows:

[0104]

[0105] In the above formula, x2 is the distance between the suspension point of the main tower and any point x, and h is the distance between the suspension point of the main tower and any point x. x Let x be the sag at any point x on the conductor.

[0106] In one specific implementation, online monitoring data for a certain line during a certain period was collected, including an air temperature of 17℃, a wind speed of 7m / s, a horizontal span of 340m, and a conductor type of LGJ400 / 50 with a diameter of 27.63mm and a cross-sectional area of ​​451.55mm². 2 The solar radiation intensity E in this region e 0.55 W / m 2 R T It is 14.2 Ω / m, α h Taken as 9J / (m 2 ·K), α l Take 20.5 × 10 -6 (1 / ℃), Eu is 77.12, and λ is taken as 0.02585W / (m·K).

[0107] By substituting the initial parameters into the calculation formula of this invention, we can obtain the lowest point sag of the statically balanced conductor under a horizontal span of 340m, which is 7.51m, and the conductor shape function, which is the function corresponding to the sag at any point of the conductor.

[0108] In one specific implementation, during the linear fitting process of the conductor edge information, a quadratic polynomial function can be used as the basis function. The coordinate data of the edge object is fitted using the least squares method to ultimately obtain the conductor's linear shape function at different times. The linear shape function at a certain time is as follows: Figure 5 As shown.

[0109] Example 2

[0110] Based on the same inventive concept, the present invention also provides a dynamic analysis device for conductor sag of transmission lines, the dynamic analysis device for conductor sag of transmission lines comprising:

[0111] The target detection module is used to take the collected conductor line shape point cloud data of the transmission line as input to a pre-trained machine learning-based target detection model, and obtain the transmission line detection results output by the pre-trained machine learning-based target detection model.

[0112] The edge detection module is used to perform edge detection on the detection results of the transmission line using an edge detection algorithm to obtain conductor edge information;

[0113] The linear fitting module is used to perform linear fitting on the conductor edge information to obtain the fitting function curve corresponding to the conductor edge information;

[0114] The analysis module is used to select the fitted function curve whose cross-correlation coefficient with the static equilibrium alignment function corresponding to the transmission line exceeds a preset value as the dynamic alignment function of the conductor.

[0115] Preferably, the training process of the pre-trained machine learning-based object detection model includes:

[0116] Training data was constructed using conductor line point cloud data of transmission lines and conductor line point cloud data with background removed.

[0117] The machine learning-based object detection model is trained using the training data to obtain the pre-trained machine learning-based object detection model.

[0118] Preferably, the edge detection algorithm includes: Roberts algorithm, Sobel algorithm, Gauss-Laplace algorithm, and Canny algorithm.

[0119] Preferably, the preset value is 0.5.

[0120] Preferably, the static equilibrium alignment function corresponding to the transmission line is as follows:

[0121] The length of the conductor is determined based on the temperature rise of the conductor.

[0122] The horizontal stress of the conductor is determined based on its length.

[0123] The sag at any point on the conductor is determined based on the horizontal stress of the conductor.

[0124] Furthermore, the temperature rise of the conductor is as follows:

[0125]

[0126] In the above formula, ΔT represents the temperature rise of the conductor, and T c0 T0 is the initial temperature of the conductor, and W is the ambient temperature. c Let α be the heat loss per unit length of the conductor, α be the heat absorption coefficient of the conductor surface, D be the conductor diameter, and E be the heat loss per unit length of the conductor. e Let A be the solar radiation intensity, A be the heat dissipation area per unit length of the conductor, and A = πD, α h λ is the heat dissipation coefficient of the conductor surface, π is pi, λ is the thermal conductivity of the air film in contact with the conductor, Eu is the Euler number, C is the heat capacity of the conductor, and t is the current time.

[0127] Furthermore, the Euler number is as follows:

[0128] Eu = 0.65 (65000νD) 0.2 +0.23(65000νD) 0.61

[0129] In the above formula, ν is the wind speed;

[0130] The heat loss per unit length of the conductor is as follows:

[0131] W c =I 2 R T

[0132] In the above formula, R T Let I be the AC resistance per unit length of conductor at the operating temperature, and let I be the current in the conductor.

[0133] Furthermore, the length of the wire is as follows:

[0134] l c =l0+α l ΔTl0

[0135] In the above formula, l c Let l0 be the length of the conductor, l0 be the initial length of the conductor, and α be the initial length of the conductor. l is the comprehensive linear temperature expansion coefficient of the conductor.

[0136] Furthermore, the horizontal stress σ0 of the conductor can be obtained by solving the following equation:

[0137]

[0138] In the above formula, g is the self-weight load per unit length of conductor, l is the horizontal distance between the suspension points of the main tower and the auxiliary tower, and l d1 Here, sh is the equivalent span corresponding to the suspension point of the main tower, ch is a hyperbolic sine function, and ch is a hyperbolic cosine function, wherein the height of the suspension point of the main tower is greater than the height of the suspension point of the auxiliary tower.

[0139] Furthermore, the sag at any point on the conductor is as follows:

[0140]

[0141] In the above formula, x2 is the distance between the suspension point of the main tower and any point x, and h is the distance between the suspension point of the main tower and any point x. x Let x be the sag at any point x on the conductor.

[0142] Example 3

[0143] Based on the same inventive concept, this invention also provides a computer device, which includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor 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. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, thereby realizing the steps of the dynamic analysis method for conductor sag of a transmission line in the above embodiments.

[0144] Example 4

[0145] Based on the same inventive concept, this invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of the dynamic analysis method for conductor sag of a transmission line in the above embodiments.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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. A method for dynamic analysis of conductor sag in transmission lines, characterized in that, The method includes: The collected conductor line point cloud data of the transmission line is used as the input of a pre-trained machine learning-based target detection model to obtain the transmission line detection results output by the pre-trained machine learning-based target detection model. An edge detection algorithm is used to perform edge detection on the detection results of the transmission line to obtain conductor edge information; The conductor edge information is linearly fitted to obtain the fitting function curve corresponding to the conductor edge information; The fitted function curve with a cross-correlation coefficient exceeding a preset value between the static equilibrium alignment function corresponding to the transmission line is selected as the dynamic alignment function of the conductor. The static equilibrium geometry function corresponding to the transmission line is as follows: The length of the conductor is determined based on the temperature rise of the conductor. The horizontal stress of the conductor is determined based on its length. The sag at any point on the conductor is determined based on the horizontal stress of the conductor. The temperature rise of the conductor is as follows: In the above formula, The temperature rise of the conductor. The initial temperature of the conductor. For ambient temperature, The heat loss per unit length of wire, The heat absorption coefficient of the conductor surface. The diameter of the wire. For solar radiation intensity, The heat dissipation area per unit length of wire surface. A = πD , The heat dissipation coefficient of the conductor surface. Pi The thermal conductivity of the air film in contact with the conductor. For Euler number, For the heat capacity of the wire, The current moment; The Euler number is as follows: In the above formula, Wind speed; The heat loss per unit length of the conductor is as follows: W c ＝ I 2 R T In the above formula, R T The AC resistance per unit length of conductor at the operating temperature. I The current in the conductor; The length of the wire is as follows: In the above formula, The length of the wire, Let be the initial length of the conductor. The comprehensive linear temperature expansion coefficient of the conductor; The horizontal stress of the conductor can be obtained by solving the following formula. : In the above formula, This is the self-weight load per unit length of conductor. The horizontal distance between the suspension points of the main tower and the auxiliary tower. The equivalent span corresponding to the suspension point of the main tower. It is a hyperbolic sine function. The function is a hyperbolic cosine function, wherein the height of the suspension point of the main tower is greater than the height of the suspension point of the auxiliary tower; The sag at any point on the conductor is as follows: In the above formula, Let x be the distance between the suspension point of the main tower and any point x. Let x be the sag at any point x on the conductor.

2. The method as described in claim 1, characterized in that, The training process of the pre-trained machine learning-based object detection model includes: Training data was constructed using conductor line point cloud data of transmission lines and conductor line point cloud data with background removed. The machine learning-based object detection model is trained using the training data to obtain the pre-trained machine learning-based object detection model.

3. The method as described in claim 1, characterized in that, The edge detection algorithms include: Roberts algorithm, Sobel algorithm, Gauss-Laplace algorithm, and Canny algorithm.

4. The method as described in claim 1, characterized in that, The preset value is 0.

5.

5. An apparatus for dynamic analysis of conductor sag in transmission lines based on any one of claims 1-4, characterized in that, The device includes: The target detection module is used to take the collected conductor line shape point cloud data of the transmission line as input to a pre-trained machine learning-based target detection model, and obtain the transmission line detection results output by the pre-trained machine learning-based target detection model. The edge detection module is used to perform edge detection on the detection results of the transmission line using an edge detection algorithm to obtain conductor edge information; The linear fitting module is used to perform linear fitting on the conductor edge information to obtain the fitting function curve corresponding to the conductor edge information; The analysis module is used to select the fitted function curve whose cross-correlation coefficient with the static equilibrium alignment function corresponding to the transmission line exceeds a preset value as the dynamic alignment function of the conductor.

6. A computer device, characterized in that, include: One or more processors; The processor is used to store one or more programs; When the one or more programs are executed by the one or more processors, the method for dynamic analysis of conductor sag of transmission lines as described in any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements the method for dynamic analysis of conductor sag of transmission lines as described in any one of claims 1 to 4.

Images