Power transmission line insulator windage yaw detection method and system, medium and computer equipment

Abstract

The invention provides a power transmission line insulator windage yaw detection method and system, a medium and computer equipment, and belongs to the technical field of electric power. Taking Y coordinates of the key point coordinates as indexes, matching the key point coordinates in the to-be-detected image with the key point coordinates in the reference image, and obtaining a lead offset pixel number under each Y coordinate according to a matching result; converting the wire offset pixel number under each Y coordinate into the insulator wind deflection angle under the Y coordinate according to the quantization coefficient of the wire offset pixel number and the insulator wind deflection angle; and obtaining a final insulator windage yaw angle according to the insulator windage yaw angles under all Y coordinates, when the absolute value of the final insulator windage yaw angle is greater than or equal to an insulator windage yaw angle threshold value, determining that insulator windage yaw occurs, otherwise, determining that insulator windage yaw does not occur. The insulator chain body does not need to be analyzed, the problem that an existing detection method cannot be applied to a scene where the insulator chain is difficult to distinguish is solved, and the detection efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of power technology, specifically to a method for detecting wind deflection of insulators in transmission lines, a system for detecting wind deflection of insulators in transmission lines, a computer device, a computer-readable storage medium, and a computer program product. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Wind-induced insulator deflection in transmission lines refers to the phenomenon where insulator strings deviate from their ideal vertical suspension state under the influence of natural wind. When this occurs, it reduces the gaps between electrical components on the towers, increasing the risk of flashover short circuits. It also generates additional mechanical stress on the insulator strings, potentially leading to string breakage and line faults. Monitoring wind-induced insulator deflection helps in the early detection of hazards and ensures power grid safety.

[0004] One existing technology proposes an insulator string edge feature matching algorithm based on image edge feature matching. First, median adaptive filtering is applied to color images acquired from transmission line towers to remove noise. Then, the images are processed by grayscale conversion, inter-frame differencing, and binarization to extract the edge features of the insulator string. Finally, the image edge feature matching algorithm matches the local features of the insulator string against edge feature templates stored in a database to determine the coordinates of the two endpoints of the insulator string, thereby calculating the wind deflection angle. Another existing technology proposes a device and method for measuring the wind deflection attitude of transmission line insulator strings. An online video monitoring device is installed at the bottom of the tower, with the camera of the online video monitoring device pointing obliquely upwards. In one approach, video images of insulator strings during online operation are collected and transmitted to an image processing and recognition unit for analysis. Image processing technology is used to automatically monitor the swaying of the insulator strings. After analysis and processing by image processing algorithms, the frequency, direction, amplitude, and stress of the swaying of the insulator strings are calculated and determined. Another existing technology provides a method for monitoring the wind deflection of suspension insulator strings based on ellipse feature fitting. This method extracts the edge contour of the insulator string through image preprocessing, image segmentation, and edge detection algorithms. Then, by setting ellipse fitting control conditions, the optimal ellipse is obtained, and the geometric parameters of the ellipse are solved. Finally, based on the actual wind deflection of the transmission line insulators, a wind deflection calculation model for the insulators is established. Linear fitting is used to obtain the spatial equation of the insulator string, and the wind deflection angle of the insulator string is calculated.

[0005] The methods described in the prior art all require analysis of the insulator string itself in the image to calculate its state and determine whether wind deflection has occurred. Their drawback is that the detection relies on the insulator string being clearly visible in the image; otherwise, they are not applicable. This necessitates close-range monitoring of the insulator string or the use of telephoto lenses for long-distance monitoring, inevitably leading to a small field of view. Furthermore, for cameras and their installation methods commonly used in power transmission visualization, they typically monitor a wide transmission channel area between two towers. In this case, the insulator string occupies very few pixels in the image, making accurate identification difficult and thus limiting the applicability of the aforementioned prior art. Summary of the Invention

[0006] To address the poor applicability of existing insulator wind deflection detection methods, this invention proposes a method, system, medium, and computer equipment for detecting wind deflection of insulators in transmission lines. By calculating the offset of the conductor in the transmission scene image, it is further converted into the angle of insulator wind deflection for detecting the insulator wind deflection phenomenon. This eliminates the need to analyze the insulator string itself, solving the problem that existing detection methods are not applicable in scenarios where insulator strings are difficult to distinguish.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a method for detecting wind deflection of insulators in power transmission lines.

[0009] A method for detecting wind deflection of insulators in transmission lines includes the following steps:

[0010] Obtain the coordinates of all key points on each line of the image to be detected and the reference image. The coordinates of the key points are in the image Cartesian coordinate system, where the X-axis of the image Cartesian coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image Cartesian coordinate system is the vertical coordinate axis of the image.

[0011] Using the Y-coordinate of each key point as an index, the key point coordinates in the image to be detected and the key point coordinates in the reference image are matched, and the number of wire offset pixels under each Y-coordinate is obtained according to the matching result.

[0012] Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate;

[0013] The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred.

[0014] As a further limitation of the first aspect of the present invention, the reference image is an image taken in the same scene as the image to be detected under conditions of no wind or wind speed below a set threshold. The reference image and the image to be detected are taken by the same camera from the same perspective. Both the reference image and the image to be detected include a conductor.

[0015] As a further limitation of the first aspect of the present invention, using the Y coordinate of any one of the key point coordinates in the image to be detected or the reference image as an index, the key point sets in the image to be detected and the reference image that have the same Y coordinate are respectively extracted, the key point set in the image to be detected is the first point set, and the key point set in the reference image is the second point set.

[0016] Calculate the distance between any two points in the first set of points and the second set of points, and construct a weighted bipartite graph;

[0017] Calculate the maximum matching of the weighted bipartite graph;

[0018] Based on the maximum match, the set of indexes of the points that were successfully matched in the first point set is obtained;

[0019] Based on the set of serial numbers, calculate the average distance between the first set of points and the successfully matched point pairs in the maximum match, and use the average distance as the number of wire offset pixels in the Y coordinate of the current key point coordinate;

[0020] By iterating through all the key point coordinates and using the Y-coordinate of each key point coordinate as an index, the number of wire offset pixels under the Y-coordinate of all the key point coordinates is obtained.

[0021] As a further limitation of the first aspect of the present invention, the insulator wind deflection angle at the Y coordinate of any of the key points in the image to be detected or the reference image is: the product of the quantization coefficient and the number of conductor offset pixels at this Y coordinate;

[0022] The quantization coefficient is: Where a and b are both fitting coefficients, K Y The value is the ratio of the width of the guide region at the Y-coordinate of this key point in the reference image to the width of the reference image.

[0023] As a further limitation of the first aspect of the present invention, the wind deflection angles of the insulators under all the Y coordinates are traversed, and the number of wind deflection angles of the insulators that need to be deleted is calculated as the set number of loops;

[0024] Calculate the mean of the insulator wind deflection angles under all the Y coordinates, delete the insulator wind deflection angle that deviates the most from the mean at each time, and repeat the loop a certain number of times. Then, take the mean of the remaining insulator wind deflection angles as the final insulator wind deflection angle.

[0025] As a further limitation of the first aspect of the present invention, when the number of insulator wind deflection angles under all the Y coordinates is less than or equal to a set threshold, the number of cycles is zero.

[0026] When the number of insulator wind deflection angles under all Y coordinates is greater than a set threshold, the number of cycles is the result of rounding down the ratio of the number of insulator wind deflection angles under all Y coordinates to the value 2.

[0027] Secondly, the present invention provides a wind deflection detection system for insulators of power transmission lines.

[0028] A power transmission line insulator wind deflection detection system includes:

[0029] The data acquisition unit is configured to acquire the coordinates of all key points on each line of the image to be detected and the reference image. The key point coordinates are coordinates in the image Cartesian coordinate system, where the X-axis of the image Cartesian coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image Cartesian coordinate system is the vertical coordinate axis of the image.

[0030] The wire offset pixel count calculation unit is configured to: use the Y coordinate of each of the key point coordinates as an index to match the key point coordinates in the image to be detected and the key point coordinates in the reference image, and obtain the wire offset pixel count under each Y coordinate based on the matching result;

[0031] The insulator wind deflection angle calculation unit is configured to convert the conductor offset pixel count in each Y coordinate into the insulator wind deflection angle in the Y coordinate according to the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle.

[0032] The insulator wind deflection judgment unit is configured to: obtain the final insulator wind deflection angle based on the insulator wind deflection angles under all the Y coordinates; when the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, determine that insulator wind deflection has occurred; otherwise, determine that insulator wind deflection has not occurred.

[0033] Thirdly, the present invention provides a wind deflection detection system for insulators of power transmission lines.

[0034] A wind deflection detection system for insulators of power transmission lines includes: a monitoring device and a processing terminal communicatively connected to the monitoring device, wherein the monitoring device is used to acquire images to be detected in a power transmission scenario in real time or at regular intervals;

[0035] The processing terminal is configured to execute the following process:

[0036] The system receives the image to be detected from the monitoring device, and extracts the key point coordinates from the received image to be detected and the pre-stored reference image, respectively, to obtain the key point coordinates on each line of the image to be detected and the reference image. The key point coordinates are coordinates in the image rectangular coordinate system, where the X-axis of the image rectangular coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image rectangular coordinate system is the vertical coordinate axis of the image.

[0037] Using the Y-coordinate of each key point as an index, the key point coordinates in the image to be detected and the key point coordinates in the reference image are matched, and the number of wire offset pixels under each Y-coordinate is obtained according to the matching result.

[0038] Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate;

[0039] The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred.

[0040] Fourthly, the present invention provides a wind deflection detection system for insulators of power transmission lines.

[0041] A wind deflection detection system for insulators of transmission lines includes: a monitoring device, a wind speed sensor, and a processing terminal, wherein the processing terminal is communicatively connected to the wind speed sensor and the monitoring device.

[0042] The monitoring device is used to acquire images to be detected in the power transmission scenario in real time or at regular intervals, and the wind speed sensor is used to acquire wind speed values ​​in the power transmission scenario in real time or at regular intervals.

[0043] The processing terminal is configured to execute the following process:

[0044] The wind speed value sent by the wind speed sensor is obtained, and the image captured by the monitoring device when the wind speed value is less than a set threshold is used as the reference image.

[0045] The system receives the image to be detected from the monitoring device, and extracts the key point coordinates from the received image to be detected and the reference image respectively, to obtain the key point coordinates on each line of the image to be detected and the reference image. The key point coordinates are coordinates in the image rectangular coordinate system, where the X-axis of the image rectangular coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image rectangular coordinate system is the vertical coordinate axis of the image.

[0046] Using the Y-coordinate of each key point as an index, the key point coordinates in the image to be detected and the key point coordinates in the reference image are matched, and the number of wire offset pixels under each Y-coordinate is obtained according to the matching result.

[0047] Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate;

[0048] The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred.

[0049] Fifthly, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium;

[0050] A processor, adapted to execute computer programs;

[0051] A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the wind deflection detection method for transmission line insulators as described in the first aspect of the present invention.

[0052] In a sixth aspect, the present invention provides a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed as described in the first aspect of the present invention for detecting wind deflection of transmission line insulators.

[0053] In a seventh aspect, the present invention provides a computer program product comprising a computer program that, when executed by a processor, implements the method for detecting wind deflection of transmission line insulators as described in the first aspect of the present invention.

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

[0055] 1. This invention innovatively proposes a wind deflection detection strategy for insulators of transmission lines. By calculating the offset of the conductor in the transmission scene image, it is further converted into the angle of wind deflection of the insulator, thereby realizing the detection of wind deflection phenomenon of insulators. There is no need to analyze the insulator string itself, which solves the problem that existing detection methods cannot be applied in scenarios where it is difficult to distinguish the insulator string.

[0056] 2. This invention reduces the limitations on the field of view and angle of the monitoring equipment, and can reuse existing power transmission channel monitoring equipment. The same equipment can be used to complete the monitoring and related detection of power transmission channel area, conductor area and insulator wind deflection phenomenon, thereby reducing costs.

[0057] 3. This invention traverses all key point coordinates, uses the Y-coordinate of each key point coordinate as an index, extracts the key point sets with the same Y-coordinate in the image to be detected and the reference image respectively, constructs a weighted bipartite graph, calculates the maximum matching of the weighted bipartite graph, and solves the number of wire offset pixels under the Y-coordinate based on the maximum matching, thus realizing the accurate calculation of the number of wire offset pixels.

[0058] 4. The insulator wind deflection angle in the Y coordinate of the present invention is the product of the quantization coefficient and the number of conductor offset pixels in the Y coordinate. The quantization coefficient is calculated based on the ratio of the width of the conductor region in the Y coordinate of the current key point coordinate in the reference image to the width of the reference image, thereby realizing the accurate conversion between the number of conductor offset pixels and the insulator wind deflection angle.

[0059] 5. This invention targets the insulator wind deflection angle under all Y coordinates, removes values ​​that deviate from the mean, and uses the average of the remaining values ​​as the final insulator wind deflection angle. It compares this value with the insulator wind deflection angle threshold to determine whether insulator wind deflection has occurred, thus eliminating the influence of abnormal data and further improving the accuracy of insulator wind deflection detection.

[0060] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0061] The accompanying drawings, which form part of this invention, 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 improper limitation of the invention.

[0062] Figure 1 This is a flowchart illustrating the wind deflection detection method for transmission line insulators provided in Embodiment 1 of the present invention.

[0063] Figure 2 A schematic diagram of the key point coordinates provided in Embodiment 1 of the present invention;

[0064] Figure 3 This is a schematic diagram of the quantization coefficient curve provided in Embodiment 1 of the present invention;

[0065] Figure 4 This is a schematic diagram of the principle of the transmission line insulator wind deflection detection system provided in Embodiment 2 of the present invention;

[0066] Figure 5 This is a schematic diagram of the principle of the transmission line insulator wind deflection detection system provided in Embodiment 3 of the present invention. Figure 1 ;

[0067] Figure 6 This is a schematic diagram of the principle of the transmission line insulator wind deflection detection system provided in Embodiment 3 of the present invention. Figure 2 ;

[0068] Figure 7 This is a schematic diagram of the principle of the transmission line insulator wind deflection detection system provided in Embodiment 4 of the present invention. Figure 1 ;

[0069] Figure 8 This is a schematic diagram of the principle of the transmission line insulator wind deflection detection system provided in Embodiment 4 of the present invention. Figure 2 ;

[0070] Figure 9 This is a schematic diagram of a computer device provided in Embodiment 5 of the present invention. Detailed Implementation

[0071] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0072] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0073] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0074] Example 1:

[0075] Transmission line insulators are an important component of the power system. They isolate exposed conductors from metal components such as supports, providing insulation, support, and fixation for the conductors, enabling the transmission line to operate safely and stably. Their main purpose is to prevent short circuits and electric arcs from occurring when conductors come into contact with metal components such as supports or towers, thus ensuring the reliability, safety, and stability of the power system.

[0076] When insulators experience wind deflection, the air gap between the lower live part of the insulator string and the tower can easily decrease. When the electrical strength of this gap cannot withstand the system operating voltage, discharge will occur, threatening the safe and stable operation of the power grid. Therefore, this implementation proposes a method for detecting wind deflection of transmission line insulators, including the following process:

[0077] S1: Obtain the coordinates of all key points on each line in the image to be detected and the reference image;

[0078] S2: Using the Y-coordinate of the key point coordinates as an index, match the key point coordinates in the image to be detected and the reference image, and obtain the number of wire offset pixels under each Y-coordinate based on the matching result;

[0079] S3: Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, convert the conductor offset pixel count in each Y coordinate into the insulator wind deflection angle in the Y coordinate;

[0080] S4: Obtain the final insulator wind deflection angle based on the insulator wind deflection angles under all Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred.

[0081] In step S1 of this implementation, the coordinates of each key point are either directly obtained or directly used as existing data input or data. Before step S1, both the image to be detected and the reference image are subjected to key point detection using the corresponding traverse detection model (an existing detection model can be used), obtaining the coordinates of all key points on each traverse in both the image to be detected and the reference image, such as... Figure 2 As shown.

[0082] In this implementation, the image to be detected is the current image of the power transmission scenario to be detected, and the reference image is a pre-prepared image of the same power transmission scenario under windless conditions. The detected key points are arranged in a grid form, and the step size of their Y coordinates is fixed (depending on the grid size of the conductor detection model used).

[0083] Understandably, in some other implementations, wind speed in the power transmission scenario can also be detected in real time, and the image of the power transmission scenario when the wind speed is less than a set threshold or the wind speed is zero can be used as a reference image and stored for later use.

[0084] It is understood that the image to be detected and the reference image in this implementation are images obtained from the same monitoring position and angle. For example, in this preferred implementation, the monitoring device can be installed on one tower and shot towards another tower, with a large and far field of view. The monitoring device is not shooting at the insulator string, and the conductor can be seen in the field of view. The specific position and orientation of the monitoring device can be selected according to the specific working conditions, which will not be elaborated here.

[0085] In some other implementations, the image to be detected and the reference image are the same size. The lower left corner of the image to be detected and the reference image are used as the origin O of the coordinate system. The horizontal direction of the image is used as the X-axis and the vertical direction of the image is used as the Y-axis to construct an XOY rectangular coordinate system. It is understood that the origin O of the coordinate system can also be selected according to the specific working conditions. For example, the lower right corner of the image or the center point of the image can be selected. Those skilled in the art can set it as needed, as long as the horizontal direction of the image is used as the X-axis and the vertical direction of the image is used as the Y-axis. This will not be elaborated here.

[0086] In step S2 of this implementation, the key point set of the guide is traversed using the Y-coordinate of the key point as the index, and the key point coordinates in the image to be detected and the reference image are matched. The number of pixels of guide offset under each Y-coordinate is calculated based on the matching result. Specifically, the following detailed process is included:

[0087] S2.1: Using the Y-coordinate of the keypoint coordinates as the index, extract the set of keypoints with the same Y-coordinate in the reference image and the image to be detected, denoted as J = {J}. i |i∈[1,P]∩N} (i.e., the first point set) and D={D j |j∈[1,Q]∩N} (i.e., the second point set), where N refers to the set of natural numbers, and P and Q are the number of key points in the reference image and the image to be detected under the selected Y coordinate, respectively;

[0088] S2.2: Calculate the distance between the x-coordinates of every pair of points in J and D, and construct a weighted bipartite graph G = (V, E), where:

[0089] V=J∪D (1);

[0090] E={(j i D j )|i∈[1,P]∩N,j∈[1,Q]∩N} (2);

[0091] The weight of E, W(J) i D j )=100000-|X(J i )-X(D j )| (3);

[0092] In the above formula, X(*) refers to the X coordinate of a specific point, |X(J) i )-X(D j )| is J i With D j The distance between two points.

[0093] The purpose of using "100000-X coordinate distance" in this implementation is to facilitate the calculation of the maximum matching of the weighted bipartite graph, so that the matching result satisfies the purpose of "minimum overall offset". Those skilled in the art can also use other weight calculation methods, which will not be elaborated here.

[0094] S2.3: Use the KM algorithm to calculate the maximum matching M = {M} in a weighted bipartite graph G. i |i∈[1,P]∩N}, where M i This represents the i-th point in point set D that is in point set J (i.e., J). i The index of the matched point, at this time M i ∈[1,Q]∩N; if J i If there is no matching point, then M i =-1.

[0095] In this implementation, the KM algorithm refers to the Kuhn-Munkres algorithm, also known as the Hungarian algorithm, which is a classic graph theory algorithm. It can be implemented using existing methods and will not be detailed here. Understandably, in other implementations, those skilled in the art can also use other algorithms to calculate the maximum matching of a weighted bipartite graph G. For example, the maximum flow algorithm can be used. The maximum flow algorithm is a classic algorithm for solving the maximum flow problem in flow networks. For the maximum matching problem of a weighted bipartite graph, the maximum flow algorithm can be applied by constructing a corresponding flow network model.

[0096] S2.4: Based on the maximum matching M, obtain the set I of the indices of the successfully matched points in set J: I = {index | index ∈ [1, P] ∩ N, M} index ≠-1}, where index represents the index of the successfully matched point in set J, and the average distance between the successfully matched point pairs in set J and set M is calculated and denoted as the offset in pixels of the conductor at the current Y coordinate. Y The calculation formula is:

[0097]

[0098] Where |I| represents the number of indices in set I. The calculation method in equation (4) does not take absolute values, and the number of pixels can be positive or negative.

[0099] S2.5: Iterate through all Y coordinates, repeatedly executing steps S2.1 to S2.4, to obtain the number of wire offset pixels at all Y coordinates {offset}. Y}

[0100] In step S3 of this implementation, the pixel offset obtained in step S2 is converted into the insulator wind deflection angle based on the conductor offset pixel - insulator wind deflection angle quantization coefficient. The calculation formula is as follows:

[0101] angle Y =offset Y *scale Y (5);

[0102] The quantization coefficient is calculated as follows:

[0103]

[0104] Parameters a and b are obtained by fitting image data of insulator wind deflection phenomena taken by cameras with the same FOV (Field of View). In this embodiment, a is set to 0.02563491 and b is set to 0.06633621. The quantization coefficient curve is shown below. Figure 3 As shown, the horizontal axis is K. Y The vertical axis represents the corresponding scale. Y .

[0105] In step S4 of this implementation, the insulator wind deflection angles at all Y coordinates obtained in step S3 are iterated. Y The process involves deleting values ​​that deviate from the mean, using the average of the remaining values ​​as the final insulator wind deflection angle, and comparing it with the insulator wind deflection angle threshold to determine whether insulator wind deflection has occurred. Specifically, this includes the following detailed steps:

[0106] S4.1: Calculate the number of insulator wind deflection angles that need to be deleted, including:

[0107]

[0108] Among them, |{angle Y}| represents {angle Y The number of insulator wind deflection angles in} Representative to Round down;

[0109] S4.2: Calculate {angle} Y The mean of the expression is calculated, and each time the value that deviates the most from the mean is deleted. This step is repeated del_num times (i.e., the number of iterations).

[0110] S4.3: Calculate {angle}Y The mean of the remaining values ​​in} is the final insulator wind deflection angle of the image to be detected;

[0111] S4.4: If the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, then the insulator wind deflection phenomenon is considered to have occurred; otherwise, it is considered that no insulator wind deflection phenomenon has occurred.

[0112] Understandably, the insulator wind deflection angle threshold here can be obtained from big data analysis or from multiple tests. It is an empirical setting value that can be specifically limited according to different usage environments, which will not be elaborated here.

[0113] Example 2:

[0114] like Figure 4 As shown, this implementation proposes a wind deflection detection system for transmission line insulators, including:

[0115] The data acquisition unit is configured to acquire the coordinates of all key points on each line of the image to be detected and the reference image. The key point coordinates are coordinates in the image Cartesian coordinate system, where the X-axis of the image Cartesian coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image Cartesian coordinate system is the vertical coordinate axis of the image. The specific limitations of the image to be detected and the reference image and the method of extracting the key point coordinates are detailed in the process in Embodiment 1, and will not be repeated here.

[0116] The wire offset pixel count calculation unit is configured to: use the Y coordinate of each of the key point coordinates as an index to match the key point coordinates in the image to be detected and the key point coordinates in the reference image, and obtain the wire offset pixel count under each Y coordinate according to the matching result. The specific working method of this unit is described in step S2 of embodiment 1, and will not be repeated here.

[0117] The insulator wind deflection angle calculation unit is configured to convert the number of conductor offset pixels in each Y coordinate into the insulator wind deflection angle in the Y coordinate according to the quantization coefficient of the number of conductor offset pixels and the insulator wind deflection angle. The specific working method of this unit is described in step S3 of embodiment 1, and will not be repeated here.

[0118] The insulator wind deflection judgment unit is configured to: obtain the final insulator wind deflection angle based on the insulator wind deflection angles under all the Y coordinates; when the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred. The specific working method of this unit is described in step S4 of embodiment 1, and will not be repeated here.

[0119] It is understood that the aforementioned units can be individually or entirely combined into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of this application. The aforementioned units are based on logical functional division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the insulator wind deflection detection system may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.

[0120] According to another embodiment of this application, the system described in this embodiment and the insulator wind deflection detection method of this application can be constructed by running a computer program (including program code) capable of performing the steps involved in the corresponding method described in Embodiment 1 on a general-purpose computing device including processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, loaded into the aforementioned computing device through the computer-readable recording medium, and run therein.

[0121] Example 3:

[0122] like Figure 5 As shown, the present invention provides a wind deflection detection system for insulators of power transmission lines, including: a monitoring device and a processing terminal communicatively connected to the monitoring device, wherein the monitoring device is used to acquire images to be detected in a power transmission scenario in real time or at regular intervals;

[0123] The processing terminal is configured to execute the following process:

[0124] The system receives the image to be detected from the monitoring device. It extracts the key point coordinates from the received image to be detected and the pre-stored reference image to obtain the coordinates of all key points on each line of the image to be detected and the reference image. The key point coordinates are coordinates in the image rectangular coordinate system. The X-axis of the image rectangular coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image rectangular coordinate system is the vertical coordinate axis of the image. The specific limitations of the image to be detected and the reference image and the method of extracting key point coordinates are described in the process in Example 1, and will not be repeated here.

[0125] Using the Y-coordinate of each key point as an index, the key point coordinates in the image to be detected and the key point coordinates in the reference image are matched. The number of wire offset pixels under each Y-coordinate is obtained according to the matching result. The specific working method of this step is described in step S2 of embodiment 1, and will not be repeated here.

[0126] Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate. The specific working method of this step is described in step S3 of embodiment 1, and will not be repeated here.

[0127] The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred. The specific working method of this step is described in step S4 of embodiment 1, and will not be repeated here.

[0128] Understandably, in some other implementations, the monitoring device and the processing terminal are connected via a wireless communication device, such as... Figure 6 As shown.

[0129] Example 4:

[0130] like Figure 7 As shown, this implementation provides a wind deflection detection system for insulators of transmission lines, including: a monitoring device, a wind speed sensor, and a processing terminal, wherein the processing terminal is communicatively connected to the wind speed sensor and the monitoring device.

[0131] The monitoring device is used to acquire images to be detected in the power transmission scenario in real time or at regular intervals, and the wind speed sensor is used to acquire wind speed values ​​in the power transmission scenario in real time or at regular intervals.

[0132] The processing terminal is configured to execute the following process:

[0133] The wind speed value sent by the wind speed sensor is obtained, and the image captured by the monitoring device when the wind speed value is less than a set threshold is used as the reference image.

[0134] The system receives the image to be detected from the monitoring device. It then extracts the key point coordinates from both the received image to be detected and the reference image, obtaining the coordinates of all key points on each line of the image to be detected and the reference image. The key point coordinates are in a Cartesian coordinate system, where the X-axis is the horizontal axis and the Y-axis is the vertical axis. Specific details regarding the limitations of the image to be detected and the reference image, as well as the key point coordinate extraction method, are detailed in Example 1 and will not be repeated here.

[0135] Using the Y-coordinate of each key point as an index, the key point coordinates in the image to be detected and the key point coordinates in the reference image are matched. The number of wire offset pixels under each Y-coordinate is obtained according to the matching result. The specific working method of this step is described in step S2 of embodiment 1, and will not be repeated here.

[0136] Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate. The specific working method of this step is described in step S3 of embodiment 1, and will not be repeated here.

[0137] The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred. The specific working method of this step is described in step S4 of embodiment 1, and will not be repeated here.

[0138] Understandably, in some other implementations, both the monitoring device and the wind speed sensor are connected to the processing terminal via wireless communication devices, such as... Figure 8 As shown.

[0139] Example 5:

[0140] like Figure 9 As shown, this implementation provides an electronic device including a processor 1001, a communication interface 1002, and a computer-readable storage medium 1003. The processor 1001, communication interface 1002, and computer-readable storage medium 1003 can be connected via a bus or other means.

[0141] The communication interface 1002 is used to receive and send data. The computer-readable storage medium 1003 can be stored in the memory of the electronic device. The computer-readable storage medium 1003 is used to store computer programs, which include program instructions. The processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.

[0142] The processor 1001 (or CPU (Central Processing Unit)) is the computing and control core of electronic devices. It is suitable for implementing one or more instructions, specifically for loading and executing one or more instructions to achieve corresponding methods or functions.

[0143] The processor 1001 is configured to perform the following process:

[0144] Obtain the coordinates of all key points on each line of the image to be detected and the reference image. The coordinates of the key points are coordinates in the image Cartesian coordinate system. The X-axis of the image Cartesian coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image Cartesian coordinate system is the vertical coordinate axis of the image. The specific limitations of the image to be detected and the reference image and the method of extracting the key point coordinates are detailed in the process in Example 1, and will not be repeated here.

[0145] Using the Y-coordinate of each key point as an index, the key point coordinates in the image to be detected and the key point coordinates in the reference image are matched. The number of wire offset pixels under each Y-coordinate is obtained according to the matching result. The specific working method of this step is described in step S2 of embodiment 1, and will not be repeated here.

[0146] Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate. The specific working method of this step is described in step S3 of embodiment 1, and will not be repeated here.

[0147] The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred. The specific working method of this step is described in step S4 of embodiment 1, and will not be repeated here.

[0148] Example 6:

[0149] This implementation provides a computer-readable storage medium (Memory), which is a memory device in an electronic device used to store programs and data. It is understood that the computer-readable storage medium here can include both built-in storage media in the electronic device and extended storage media supported by the electronic device. The computer-readable storage medium provides storage space that stores the processing system of the electronic device.

[0150] Furthermore, this storage space also contains one or more instructions suitable for loading and execution by the 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 high-speed RAM memory or non-volatile memory, such as at least one disk storage device; optionally, it can also be at least one computer-readable storage medium located remotely from the aforementioned processor.

[0151] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to perform the following process:

[0152] Obtain the coordinates of all key points on each line of the image to be detected and the reference image. The coordinates of the key points are coordinates in the image Cartesian coordinate system. The X-axis of the image Cartesian coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image Cartesian coordinate system is the vertical coordinate axis of the image. The specific limitations of the image to be detected and the reference image and the method of extracting the key point coordinates are detailed in the process in Example 1, and will not be repeated here.

[0153] Using the Y-coordinate of the key point coordinates as an index, the key point coordinates in the image to be detected and the reference image are matched. The number of wire offset pixels under each Y-coordinate is obtained according to the matching result. The specific working method of this step is described in step S2 of embodiment 1, and will not be repeated here.

[0154] Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate. The specific working method of this step is described in step S3 of embodiment 1, and will not be repeated here.

[0155] The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred. The specific working method of this step is described in step S4 of embodiment 1, and will not be repeated here.

[0156] Example 7:

[0157] This implementation provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the following process:

[0158] Obtain the coordinates of all key points on each line of the image to be detected and the reference image. The coordinates of the key points are coordinates in the image Cartesian coordinate system. The X-axis of the image Cartesian coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image Cartesian coordinate system is the vertical coordinate axis of the image. The specific limitations of the image to be detected and the reference image and the method of extracting the key point coordinates are detailed in the process in Example 1, and will not be repeated here.

[0159] Using the Y-coordinate of the key point coordinates as an index, the key point coordinates in the image to be detected and the reference image are matched. The number of wire offset pixels under each Y-coordinate is obtained according to the matching result. The specific working method of this step is described in step S2 of embodiment 1, and will not be repeated here.

[0160] Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate. The specific working method of this step is described in step S3 of embodiment 1, and will not be repeated here.

[0161] The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred. The specific working method of this step is described in step S4 of embodiment 1, and will not be repeated here.

[0162] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0163] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0164] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for detecting wind deflection of insulators in transmission lines, characterized in that, Includes the following processes: Obtain the coordinates of all key points on each line of the image to be detected and the reference image. The coordinates of the key points are in the image Cartesian coordinate system, where the X-axis of the image Cartesian coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image Cartesian coordinate system is the vertical coordinate axis of the image. Using the Y-coordinate of each key point as an index, the key point coordinates in the image to be detected and the key point coordinates in the reference image are matched, and the number of wire offset pixels under each Y-coordinate is obtained according to the matching result. Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate; The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred.

2. The method for detecting wind deflection of insulators in transmission lines as described in claim 1, characterized in that, The reference image is an image taken in the same scene as the image to be detected under conditions of no wind or wind speed below a set threshold. The reference image and the image to be detected are taken by the same camera from the same perspective. Both the reference image and the image to be detected include a conductor.

3. The method for detecting wind deflection of insulators in transmission lines as described in claim 1, characterized in that, Using the Y-coordinate of any one of the key points in the image to be detected or the reference image as an index, extract the key point sets in the image to be detected and the reference image that have the same Y-coordinate, respectively, and take the key point set in the image to be detected as the first point set and the key point set in the reference image as the second point set; Calculate the distance between any two points in the first set of points and the second set of points, and construct a weighted bipartite graph; Calculate the maximum matching of the weighted bipartite graph; Based on the maximum match, the set of indexes of the points that were successfully matched in the first point set is obtained; Based on the set of serial numbers, calculate the average distance between the first set of points and the successfully matched point pairs in the maximum match, and use the average distance as the number of wire offset pixels in the Y coordinate of the current key point coordinate; By iterating through all the key point coordinates and using the Y-coordinate of each key point coordinate as an index, the number of wire offset pixels under the Y-coordinate of all the key point coordinates is obtained.

4. The method for detecting wind deflection of insulators in transmission lines as described in claim 1, characterized in that, The insulator wind deflection angle at the Y coordinate of any of the key points in the image to be detected or the reference image is: the product of the quantization coefficient and the number of conductor offset pixels at this Y coordinate; The quantization coefficient is: Where a and b are both fitting coefficients, K Y The value is the ratio of the width of the guide region at the Y-coordinate of this key point in the reference image to the width of the reference image.

5. The method for detecting wind deflection of insulators in transmission lines as described in any one of claims 1-4, characterized in that, Iterate through all the insulator wind deflection angles under the Y coordinate, and calculate the number of insulator wind deflection angles that need to be deleted as the set number of iterations; Calculate the mean of the insulator wind deflection angles under all the Y coordinates, delete the insulator wind deflection angle that deviates the most from the mean at each time, and repeat the loop a certain number of times. Then, take the mean of the remaining insulator wind deflection angles as the final insulator wind deflection angle.

6. The method for detecting wind deflection of insulators in transmission lines as described in claim 5, characterized in that, When the number of insulator wind deflection angles under all Y coordinates is less than or equal to a set threshold, the number of cycles is zero; When the number of insulator wind deflection angles under all Y coordinates is greater than a set threshold, the number of cycles is the result of rounding down the ratio of the number of insulator wind deflection angles under all Y coordinates to the value 2.

7. A system for detecting wind deflection of insulators in transmission lines, characterized in that, include: The data acquisition unit is configured to acquire the coordinates of all key points on each line of the image to be detected and the reference image. The key point coordinates are coordinates in the image Cartesian coordinate system, where the X-axis of the image Cartesian coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image Cartesian coordinate system is the vertical coordinate axis of the image. The wire offset pixel count calculation unit is configured to: use the Y coordinate of each of the key point coordinates as an index to match the key point coordinates in the image to be detected and the key point coordinates in the reference image, and obtain the wire offset pixel count under each Y coordinate based on the matching result; The insulator wind deflection angle calculation unit is configured to convert the conductor offset pixel count in each Y coordinate into the insulator wind deflection angle in the Y coordinate according to the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle. The insulator wind deflection judgment unit is configured to: obtain the final insulator wind deflection angle based on the insulator wind deflection angles under all the Y coordinates; when the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, determine that insulator wind deflection has occurred; otherwise, determine that insulator wind deflection has not occurred.

8. A system for detecting wind-induced deflection of insulators in transmission lines, characterized in that, include: The monitoring device and the processing terminal that are communicatively connected to the monitoring device are used to acquire images to be detected in power transmission scenarios in real time or at regular intervals. The processing terminal is configured to execute the following process: The system receives the image to be detected from the monitoring device, and extracts the key point coordinates from the received image to be detected and the pre-stored reference image, respectively, to obtain the key point coordinates on each line of the image to be detected and the reference image. The key point coordinates are coordinates in the image rectangular coordinate system, where the X-axis of the image rectangular coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image rectangular coordinate system is the vertical coordinate axis of the image. Using the Y-coordinate of each key point as an index, the key point coordinates in the image to be detected and the key point coordinates in the reference image are matched, and the number of wire offset pixels under each Y-coordinate is obtained according to the matching result. Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate; The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred.

9. A system for detecting wind-induced deflection of insulators in transmission lines, characterized in that, include: The system includes a monitoring device, a wind speed sensor, and a processing terminal, wherein the processing terminal is communicatively connected to the wind speed sensor and the monitoring device, respectively. The monitoring device is used to acquire images to be detected in the power transmission scenario in real time or at regular intervals, and the wind speed sensor is used to acquire wind speed values ​​in the power transmission scenario in real time or at regular intervals. The processing terminal is configured to execute the following process: The wind speed value sent by the wind speed sensor is obtained, and the image captured by the monitoring device when the wind speed value is less than a set threshold is used as the reference image. The system receives the image to be detected from the monitoring device, and extracts the key point coordinates from the received image to be detected and the reference image respectively, to obtain the key point coordinates on each line of the image to be detected and the reference image. The key point coordinates are coordinates in the image rectangular coordinate system, where the X-axis of the image rectangular coordinate system is the horizontal coordinate axis of the image, and the Y-axis of the image rectangular coordinate system is the vertical coordinate axis of the image. Using the Y-coordinate of each key point as an index, the key point coordinates in the image to be detected and the key point coordinates in the reference image are matched, and the number of wire offset pixels under each Y-coordinate is obtained according to the matching result. Based on the quantization coefficient of the conductor offset pixel count and the insulator wind deflection angle, the conductor offset pixel count under each Y coordinate is converted into the insulator wind deflection angle under the Y coordinate; The final insulator wind deflection angle is obtained based on the insulator wind deflection angles under all the Y coordinates. When the absolute value of the final insulator wind deflection angle is greater than or equal to the insulator wind deflection angle threshold, it is determined that insulator wind deflection has occurred; otherwise, it is determined that insulator wind deflection has not occurred.

10. A computer device, characterized in that, include: Processor and computer-readable storage media; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the method for detecting wind deflection of transmission line insulators as described in any one of claims 1 to 6.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed as described in any one of claims 1 to 6.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method for detecting wind deflection of transmission line insulators as described in any one of claims 1 to 6.

Images