A method and system for recognizing conductor wind deflection based on infrared images

Abstract

The application provides a conductor wind deviation identification method and system based on an infrared image, and the method comprises the following steps: S1, acquiring an infrared image of a power transmission line in a detection area; S2, reading the infrared image, detecting an insulator area of the power transmission line based on a yolov5s target detection model, and further extracting the insulator area; S3, detecting the insulator area by an infrared temperature detection model, acquiring the temperature in the insulator area, and calculating the deflection degree of the insulator area by an image processing algorithm; and S4, judging whether the temperature of the insulator area conforms to a normal value, whether the insulator area is in a normal state, and whether the power transmission line produces wind deviation. By combining the infrared image with the visible light processing algorithm, the wind deviation phenomenon of the insulator can be more accurately judged.

Description

Technical Field

[0001] The present application belongs to the technical field of power transmission lines, and specifically relates to a method and system for identifying windage deviation of a conductor based on infrared images. Background Art

[0002] Wind-induced transmission line faults are a common grid incident, often resulting in line tripping, wind-induced discharges, conductor arc burns, and line breakage. Unlike lightning flashovers and switching impulse flashovers, the vast majority of wind-induced flashover faults occur below the operating voltage. Due to the constant wind flow, wind-induced flashovers often cannot be successfully reclosed after a trip, leading to transmission line outages and severely impacting grid reliability.

[0003] Wind-induced tripping faults are one of the most common types of wind damage on transmission lines. They occur primarily when conductors and insulators sway under wind, leading to discharge tripping due to insufficient electrical clearance. Wind-induced tripping faults, sometimes simply referred to as wind-induced faults, are often accompanied by severe weather conditions. Wind-induced tripping is often caused by strong winds and other adverse weather conditions while operating voltage is present. This results in a low reclosing success rate, severely impacting power supply reliability.

[0004] Windage detection primarily checks whether the distance between the insulator string and the tower is greater than the electrical air gap limit, and whether the distance between conductors is normal. However, existing methods of windage detection, which capture video images of transmission lines, can have certain errors.

[0005] In view of this, it is very meaningful to propose a wire windage deviation identification method and system based on infrared images.

[0006] Application Contents

[0007] In order to solve the problem of large errors in the existing windage detection of transmission lines, the present application provides a conductor windage identification method and system based on infrared images to solve the technical defects in the windage detection of transmission lines.

[0008] In one aspect, the present application proposes a method for identifying windage deviation of a conductor based on infrared images, the method comprising the following steps:

[0009] S1. Acquire an infrared image of the power transmission line in the area to be inspected;

[0010] S2. Read the infrared image, detect the transmission line insulator area based on the yolov5s target detection model, and further extract the insulator area;

[0011] S3, detecting the insulator region by an infrared temperature detection model to obtain the temperature in the insulator region, and calculating the deflection degree of the insulator region by an image processing algorithm; and

[0012] S4, judging whether the temperature of the insulator region conforms to a normal value, whether the insulator region is in a normal state, and whether the power transmission line produces wind deflection.

[0013] The infrared image of the power transmission line in the to-be-detected region is obtained by an infrared image acquisition device, the corresponding insulator region on the power transmission line is detected by a yolov5s target detection model, whether the insulator has temperature abnormities is analyzed by an infrared temperature detection model, and the deflection degree of the insulator is calculated by an image processing algorithm, and the infrared image and the visible light processing algorithm are combined, so that whether the insulator has wind deflection can be more accurately judged.

[0014] Preferably, the infrared image is detected based on the yolov5s target detection model in S2, and further comprising:

[0015] S21, a certain number of pictures of the insulator region are collected, and an image labeling tool Lbelme is used for manual labeling to obtain a data set;

[0016] S22, the obtained data set is divided into a training set and a test set in a ratio of 8:2;

[0017] S23, the yolov5s is used to read the training set for training, so as to obtain a yolov5s-based target detection model;

[0018] S24, the test set is used to detect the yolov5s-based target detection model.

[0019] The traditional algorithm is easy to be unstable under the interference of external light and shadow, while the advanced deep learning yolov5 algorithm adopted in the application has better robustness and stability compared with the traditional image processing method through a large amount of target learning and training.

[0020] Further preferably, the infrared temperature detection model is established in S3, and further comprising:

[0021] S31, infrared images of the insulator region at different times, same places and same angles are obtained, and the infrared images are classified according to time periods;

[0022] S32, the temperatures of each point in the insulator region in the infrared image are marked by a drone SDK;

[0023] S33, the infrared image is further converted into a gray image;

[0024] S34, fitting the grayscale value and temperature value corresponding to each point by using the naive Bayes algorithm;

[0025] S35: Establishing the infrared temperature detection model.

[0026] In order to avoid the influence of the external environment, three time periods, morning, noon and evening, were selected for infrared image acquisition, and three corresponding models were established. The shooting location and angle of the infrared image acquisition equipment were fixed each time to ensure good stability of infrared image acquisition.

[0027] Further preferably, the naive Bayes formula in S34 is expressed as follows:

[0028]

[0029] Where T represents temperature, G represents grayscale value, and the conditional distribution of temperature T can be expressed as,

[0030]

[0031] Get the classification model of grayscale value corresponding to temperature,

[0032] classify(g)=argmax p(T=t)

[0033]

[0034] Further preferably, the image processing of the insulator region in S3 includes:

[0035] S311. Preprocess the extracted image of the insulator area; S312. Segment the image of the insulator area and further perform morphological processing; S313. Extract the skeleton of the insulator string in the insulator area, and further calculate the endpoint coordinates at both ends of the skeleton; S314. Calculate the offset of the insulator string based on the endpoint coordinates, and further determine the degree of offset of the insulator area.

[0036] Further preferably, in S312, the morphological processing includes a dilation operation and an erosion operation in mathematical morphology.

[0037] Preferably, in S313, the offset of the insulator string is calculated using a windage angle calculation formula, and the windage angle calculation formula is specifically:

[0038]

[0039] Among them, (x1, y1) and (x2, y2) are the end points of the insulator string after wind deflection.

[0040] In a second aspect, the present application proposes a wire windage identification system based on infrared images, the system comprising:

[0041] an infrared image acquisition module configured to acquire an infrared image of the power transmission line in the area to be inspected;

[0042] an infrared image processing module configured to detect and extract the insulator region, and perform preprocessing, segmentation processing, and morphological processing on the extracted image of the insulator region;

[0043] an infrared temperature detection module, configured to detect the insulator region using an infrared temperature detection model and obtain the temperature within the insulator region;

[0044] a skeleton extraction module configured to extract the skeleton of the insulator string in the insulator area;

[0045] a calculation module configured to calculate the endpoint coordinates of both ends of the skeleton, and calculate the offset of the insulator string according to the endpoint coordinates;

[0046] The judgment module is configured to judge whether the temperature of the insulator area meets the normal value, judge whether the insulator area is in a normal state, and further judge whether the transmission line has wind deviation.

[0047] In a third aspect, an embodiment of the present application provides an electronic device comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0048] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

[0049] Compared with the prior art, the beneficial results of this application are:

[0050] (1) An infrared image of the transmission line in the area to be detected is obtained through an infrared image acquisition device. The corresponding insulator area on the transmission line is detected with the help of the yolov5s target detection model. The infrared temperature detection model is used to analyze whether there is temperature anomaly on the insulator, and the degree of insulator deflection is calculated through the image processing algorithm. By combining the infrared image with the visible light processing algorithm, it is possible to more accurately determine whether the insulator has wind deflection.

[0051] (2) Traditional algorithms are prone to instability under the interference of external light and shadows. The advanced deep learning yolov5 algorithm adopted in this application has better robustness and stability than traditional image processing methods through a large amount of target learning training. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are included to provide a further understanding of the embodiments and are incorporated into and constitute a part of this specification. The accompanying drawings illustrate the embodiments and, together with the description, serve to explain the principles of the present application. Other embodiments and many of the expected advantages of the embodiments will be readily apparent as they become better understood by reference to the following detailed description. The elements of the drawings are not necessarily to scale with respect to each other. Like reference numerals designate corresponding similar parts.

[0053] Figure 1 This is a flow chart of a method for identifying windage deviation of a conductor based on infrared images according to an embodiment of the present application;

[0054] Figure 2 This is a schematic diagram of an infrared image of a transmission line in a method for identifying windage deviation of a conductor based on an infrared image according to an embodiment of the present application;

[0055] Figure 3 This is a flowchart of processing infrared images of insulators in a method for identifying windage deviation of conductors based on infrared images according to an embodiment of the present application;

[0056] Figure 4 This is a schematic diagram of insulator skeleton extraction in a conductor windage identification method based on infrared images according to an embodiment of the present application;

[0057] Figure 5 This is a schematic diagram of a method system for identifying windage deviation of a conductor based on infrared images according to an embodiment of the present application;

[0058] Figure 6 It is a structural diagram of a computer device suitable for implementing the electronic device of the embodiment of the present application. DETAILED DESCRIPTION

[0059] In the following detailed description, reference is made to the accompanying drawings, which form a part of the detailed description and are shown by illustrative specific embodiments in which the present application can be practiced. In this regard, directional terms, such as "top", "bottom", "left", "right", "up", "down", etc., are used with reference to the orientation of the figures being described. Because the components of the embodiments can be positioned in several different orientations, directional terms are used for illustrative purposes and are in no way limiting. It should be understood that other embodiments can be utilized or logical changes can be made without departing from the scope of the present application. Therefore, the following detailed description should not be taken in a limiting sense, and the scope of the present application is defined by the appended claims.

[0060] In one aspect, the present application proposes a method for identifying windage deviation of a conductor based on infrared images, the method comprising the following steps:

[0061] Figure 1 FIG. 1 shows a flow chart of a method for identifying windage deviation of a conductor based on infrared images according to an embodiment of the present application. Figure 1 shown.

[0062] S1. Acquire an infrared image of the power transmission line in the area to be inspected;

[0063] The infrared image in this embodiment is obtained by capturing infrared image capturing equipment, including but not limited to infrared cameras, drones and other equipment.

[0064] S2. Read the infrared image, detect the transmission line insulator area based on the yolov5s target detection model, and further extract the insulator area;

[0065] In a specific embodiment, S2 detects the infrared image based on the yolov5s target detection model, and further includes:

[0066] S21, collecting a certain number of pictures of the insulator area, and manually annotating them using the image annotation tool Lbelme to obtain a data set;

[0067] S22, dividing the obtained data set into a training set and a test set in a ratio of 8:2;

[0068] S23, using yolov5s to read the training set training, and obtain a target detection model based on yolov5s;

[0069] S24. Use the test set to detect the target detection model based on yolov5s.

[0070] Traditional algorithms are prone to instability under the interference of external light and shadows. The advanced deep learning yolov5 algorithm adopted in this application has better robustness and stability than traditional image processing methods through a large amount of target learning training.

[0071] Yolov5s algorithm has the following advantages over other target detection methods: it uses adaptive image scaling, which can reduce the amount of calculation and improve the running speed during operation; Focus structure, the original 608*608*3 image is input into the Focus structure, and the slicing operation is used to first convert it into a 304*304*12 feature map, and then after a convolution operation with 32 convolution kernels, it finally becomes a 304*304*32 feature map; CSP structure, the gradient change is integrated into the feature map from beginning to end, which can reduce the amount of calculation while ensuring accuracy; Neck part, the CSP2 structure designed by CSPnet is used to enhance the ability of network feature fusion; Yolov5 uses GIOU_Loss as the loss function of Bounding box, first calculates the minimum closure area of ​​the two boxes, then calculates IoU, and then calculates the proportion of the area in the closure area that does not belong to the two boxes, and finally subtracts this proportion from IoU to get GIoU

[0072]

[0073] S3. Detecting the insulator region using an infrared temperature detection model to obtain the temperature within the insulator region, and calculating the degree of deflection of the insulator region using an image processing algorithm; and

[0074] S3 also includes establishing the infrared temperature detection model:

[0075] S31, obtaining infrared images of the insulator area taken at different times, at the same location, and at the same angle, and classifying the infrared images by time period;

[0076] S32. Marking the temperature of each point in the insulator area in the infrared image using the drone SDK;

[0077] S33, further converting the infrared image into a grayscale image;

[0078] S34, fitting the grayscale value and temperature value corresponding to each point by using the naive Bayes algorithm;

[0079] The naive Bayes formula described in S34 is expressed as follows:

[0080]

[0081] Where T represents temperature, G represents grayscale value, and the conditional distribution of temperature T can be expressed as,

[0082]

[0083] Get the classification model of grayscale value corresponding to temperature,

[0084] classify(g) = argmax p(T = t)

[0085]

[0086] S35, an infrared temperature detection model is established.

[0087] Figure 2 A schematic diagram of an infrared image of a power transmission line in the conductor wind deviation recognition method based on the infrared image of the embodiment of the application is shown, as shown in Figure 2

[0088] In specific embodiments, in order to avoid the influence of the external environment, the infrared image is collected in the morning, at noon and at night, three time periods are selected, three models are established, the shooting place and angle of the infrared image acquisition device are fixed during each collection, and the stability of the infrared image acquisition is good.

[0089] Next, taking the model establishment method of a certain time period as an example, the processing of other time periods is the same. Take 1000 infrared pictures taken in this time period, extract 10,000 temperature points using the SDK of the unmanned aerial vehicle, convert the infrared pictures to grayscale pictures, and fit the grayscale values and temperature values of each point through the Bayesian algorithm.

[0090] Figure 3 A flow chart of the processing of the insulator infrared image in the conductor wind deviation recognition method based on the infrared image of the embodiment of the application is shown, as shown in Figure 3

[0091] The image processing of the insulator region in S3 includes:

[0092] S311, preprocessing the extracted image of the insulator region;

[0093] S312, performing segmentation processing on the image of the insulator region, and further performing morphological processing;

[0094] Specifically, the preprocessing in this embodiment mainly refers to the denoising processing of the image of the insulator region. Since the images taken by the aerial photography of the unmanned aerial vehicle are mainly disturbed by Gaussian noise and salt and pepper noise, the median filter and PED filter are used for processing in the image preprocessing stage.

[0095] The segmentation processing mainly refers to the grayscale morphological segmentation. Since the insulator picture processed by the image processing may be disturbed by the interference of the iron tower, the power transmission line, the background vegetation, etc., in order to extract the insulator from the above interference, the grayscale morphological segmentation is mainly used for processing.

[0096] ​​In the specific embodiment S312, morphological processing includes dilation and erosion operations in mathematical morphology. The dilation operation is implemented by the OpenCV function dilate(), which uses a specified kernel element to dilate the source image. The kernel has a definable anchor point, called the kernel center point. During the dilation operation, the maximum pixel value in the kernel coverage area is obtained and replaced with the pixel at the anchor point. The maximum value is obtained using the following formula:

[0097]

[0098] The erosion operation is implemented by the OpenCV function erode(). The function uses a specified kernel element to erode the source image. The kernel has a definable anchor point, called the kernel center point. During the erosion operation, the minimum pixel value of the kernel coverage area is obtained and replaced with the pixel of the anchor point. The minimum value is obtained by the following formula:

[0099]

[0100] Figure 4 FIG. 1 shows a schematic diagram of extracting the insulator skeleton in the infrared image-based conductor windage identification method according to an embodiment of the present application. Figure 4 shown.

[0101] S313, extracting the skeleton of the insulator string in the insulator area, and further calculating and obtaining the coordinates of the endpoints at both ends of the skeleton;

[0102] Specifically, after the above steps, the skeleton of the insulator string can be obtained, and the coordinates of the two end points of the insulator string can be obtained by calculation. Assuming the width and height of the insulator region image are w and h, the pseudo code for traversing to obtain the upper end point is as follows:

[0103]

[0104] The obtained i and j are the coordinates of the upper endpoint, and the lower endpoint can be obtained in the same way.

[0105] In S313, the offset of the insulator string is calculated using a windage angle calculation formula, and the windage angle calculation formula is specifically:

[0106]

[0107] Among them, (x1, y1) and (x2, y2) are the end points of the insulator string after wind deflection.

[0108] S314: Calculate the offset of the insulator string according to the endpoint coordinates, and further determine the offset degree of the insulator region.

[0109] S4, judging whether the temperature of the insulator region conforms to a normal value, and judging whether the insulator region is in a normal state, and further judging whether the power transmission line produces wind deviation.

[0110] Figure 5 An embodiment of the present application is shown in a schematic diagram of a conductor wind deviation recognition method system based on an infrared image, as shown in Figure 5

[0111] In a second aspect, the present application provides a conductor wind deviation recognition system based on an infrared image, which comprises:

[0112] An infrared image acquisition module configured to acquire an infrared image of a power transmission line in a detection area;

[0113] An infrared image processing module configured to detect and extract the insulator region, and to pre-process, segment and morphologically process the extracted image of the insulator region;

[0114] An infrared temperature detection module configured to detect the insulator region by using an infrared temperature detection model, and to acquire the temperature in the insulator region;

[0115] A skeleton extraction module configured to extract the skeleton of an insulator string of the insulator region;

[0116] A calculation module configured to calculate the coordinates of the end points at both ends of the skeleton, and to calculate the offset of the insulator string according to the coordinates of the end points;

[0117] A judgment module configured to judge whether the temperature of the insulator region conforms to a normal value, and to judge whether the insulator region is in a normal state, and further to judge whether the power transmission line produces wind deviation.

[0118] The present application acquires an infrared image of a power transmission line in a detection area by using an infrared image acquisition device, detects a corresponding insulator region on the power transmission line by using a yolov5s target detection model, analyzes whether the insulator has temperature abnormalities by using an infrared temperature detection model, and calculates the degree of deflection of the insulator by using an image processing algorithm. By combining the infrared image with a visible light processing algorithm, it can more accurately judge whether the insulator has wind deviation phenomenon.

[0119] Reference is made to Figure 6 , which shows a structural schematic diagram of a computer device 600 of an electronic device (such as a server or terminal device shown in Figure 1 ) suitable for implementing embodiments of the present application. Figure 6 The electronic device shown is only an example, and should not impose any limitation on the functions and use range of embodiments of the present application. ​

[0120] like Figure 6 As shown, the computer device 600 includes a central processing unit (CPU) 601 and a graphics processing unit (GPU) 602, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 603 or the program loaded from the storage part 609 to the random access memory (RAM) 606. Various programs and data required for the operation of the device 600 are also stored in the RAM 604. The CPU 601, GPU 602, ROM 603 and RAM 604 are connected to each other via a bus 605. An input / output (I / O) interface 606 is also connected to the bus 605.

[0121] The following components are connected to the I / O interface 606: an input section 607 including a keyboard, a mouse, and the like; an output section 608 including a display such as a liquid crystal display (LCD), a speaker, and the like; a storage section 609 including a hard disk and the like; and a communication section 610 including a network interface card such as a LAN card or a modem. The communication section 610 performs communication processing via a network such as the Internet. A drive 611 may also be connected to the I / O interface 606 as needed. A removable medium 612, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like, is installed in the drive 611 as needed, so that a computer program read therefrom can be installed into the storage section 609 as needed.

[0122] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 610, and / or installed from a removable medium 612. When the computer program is executed by the central processing unit (CPU) 601 and the graphics processing unit (GPU) 602, the above-mentioned functions defined in the method of the present application are executed.

[0123] It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable medium, or any combination of the two. Computer-readable media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices, apparatuses, or components, or any combination thereof. More specific examples of computer-readable media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution device, apparatus, or component. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution apparatus, device, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical cable, RF, or any suitable combination thereof.

[0124] Computer program code for performing the operations of the present application can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the devices, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based device that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0126] The modules involved in the embodiments described in this application may be implemented in software or hardware, and may also be set in a processor.

[0127] As another aspect, the present application further provides a computer-readable medium, which may be included in the electronic device described in the above embodiments, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more programs, and when executed by the electronic device, the electronic device implements the method for identifying wire windage.

[0128] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned inventive concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for identifying windage deviation of a conductor based on infrared images, characterized in that: The method comprises the following steps: S1. Obtain an infrared image of the power transmission line in the area to be inspected; the infrared image is obtained by taking pictures with a device including an infrared camera or a drone; S2, read the infrared image, and detect the transmission line insulator area based on the yolov5s target detection model, and further extract the insulator area, wherein the detection process includes: S21, collect a certain number of pictures of the insulator area, and use the image annotation tool Lbelme to manually annotate to obtain a data set; S22, divide the obtained data set into a training set and a test set in a ratio of 8:2; S23, use yolov5s to read the training set training, and obtain the target detection model based on yolov5s; S24, then use the test set to detect the target detection model based on yolov5s; S3. Detect the insulator area using an infrared temperature detection model to obtain the temperature within the insulator area, and simultaneously calculate the degree of deflection of the insulator area using an image processing algorithm, wherein the steps of establishing the infrared temperature detection model include: S31. Obtain infrared images of the insulator area taken at different times, at the same location, and at the same angle, and classify the infrared images by time period; S32. Mark the temperature of each point in the insulator area in the infrared image using a drone SDK; S33. Further convert the infrared image into a grayscale image; S34. Fit the grayscale value and temperature value corresponding to each point using a naive Bayes algorithm; S35. Establish the infrared temperature detection model; The image processing algorithm includes: S311, pre-processing the extracted image of the insulator area; S312, segmenting the image of the insulator area and further performing morphological processing, wherein the morphological processing includes dilation and corrosion operations in mathematical morphology; S313, extracting the skeleton of the insulator string in the insulator area, and further calculating the endpoint coordinates of the two ends of the skeleton; S314, calculating the windage angle according to the endpoint coordinates using the windage angle calculation formula Calculate the offset of the insulator string, where: The end point of the insulator string after wind deflection is further used to determine the degree of deviation of the insulator area; and S4. Determine whether the temperature of the insulator region meets the normal value, determine whether the insulator region is in a normal state, and further determine whether the transmission line has wind deviation.

2. The method for identifying windage deviation of a conductor based on infrared images according to claim 1, characterized in that: The Naive Bayes formula described in S34 is expressed as follows: ， Where T represents temperature, G represents grayscale value, and the conditional distribution of temperature T can be further expressed as: ， Get the classification model of grayscale value corresponding to temperature: 。 3. A wire windage identification system based on infrared images, characterized in that: The method for identifying windage deviation of a conductor based on infrared images according to any one of claims 1 to 2 comprises: an infrared image acquisition module configured to acquire an infrared image of the power transmission line in the area to be inspected; an infrared image processing module configured to detect and extract the insulator region, and perform preprocessing, segmentation processing, and morphological processing on the extracted image of the insulator region; an infrared temperature detection module, configured to detect the insulator region using an infrared temperature detection model and obtain the temperature within the insulator region; a skeleton extraction module configured to extract the skeleton of the insulator string in the insulator area; a calculation module configured to calculate the endpoint coordinates of both ends of the skeleton, and calculate the offset of the insulator string according to the endpoint coordinates; The judgment module is configured to judge whether the temperature of the insulator area meets the normal value, and whether the insulator area is in a normal state, and further judge whether the transmission line has wind deviation.

4. An electronic device comprising: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 2 is implemented.

Images