Method and device for detecting defects of overhead transmission line, electronic equipment and storage medium

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for detecting defects in overhead transmission lines. Its features include: acquiring simulated sample images of a target transmission line and real sample images of the target transmission line; training a pre-established pre-detection model based on the simulated sample images and the real sample images to obtain a defect detection model; and determining the transmission line defects of the target transmission line based on the defect detection model and the real sample images. This invention enables the detection of defects in overhead transmission lines using unmanned aerial vehicles (UAVs), improving the accuracy of defect identification in overhead transmission lines.

Description

Technical Field

[0001] This invention relates to the field of power transmission line inspection, and more particularly to a method, apparatus, electronic device, and storage medium for detecting defects in overhead power transmission lines. Background Technology

[0002] The power transmission network plays a crucial role in the power grid by transmitting electrical energy. Overhead transmission lines are the most important lines within the network, and ensuring their safe transmission is of paramount importance to transmission network workers. These workers need to conduct regular inspections of the overhead transmission network. Currently, drones are commonly used for intelligent inspections, capturing numerous visible light images of the transmission lines using their cameras to identify defects. However, current technology has limitations in this area. Because the large number of images captured by drones requires manual examination by transmission network workers, and some defects are difficult to identify manually, the current technology's ability to identify defects in the power transmission network is insufficient. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, and storage medium for detecting defects in overhead power transmission lines, so as to achieve accurate identification of defects in overhead power transmission lines.

[0004] According to one aspect of the present invention, a method for detecting defects in overhead transmission lines is provided, comprising:

[0005] Obtain simulated sample images of the target transmission line and real sample images of the target transmission line;

[0006] The pre-established pre-detection model is trained based on the simulated sample images and the real sample images to obtain a defect detection model;

[0007] The defects of the target transmission line are determined based on the defect detection model and real sample images.

[0008] According to another aspect of the present invention, an overhead transmission line defect detection device is provided, comprising:

[0009] The data acquisition module is used to acquire simulated sample images of the target transmission line and real sample images of the target transmission line;

[0010] The model training module is used to train the pre-established pre-detection model based on the simulated sample images and the real sample images to obtain the defect detection model;

[0011] The defect detection module is used to determine the transmission line defects of the target transmission line based on the defect detection model and real sample images.

[0012] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the overhead transmission line defect detection method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the overhead transmission line defect detection method according to any embodiment of the present invention.

[0017] The technical solution of this invention acquires simulated sample images and real sample images of a target transmission line. The simulated sample images increase the sample data for identification, while the real sample images improve the accuracy of identification. A pre-established pre-detection model is trained using the simulated and real sample images to obtain a defect detection model. This defect detection model, based on both real and simulated sample images, improves the model's prediction accuracy. Based on the defect detection model and real sample images, transmission line defects are determined. The defect detection model detects real sample images to identify the transmission line defects. This achieves defect detection in overhead transmission lines using UAVs, improving the accuracy of defect identification and solving the problem of inefficient and inaccurate transmission line identification in existing technologies.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a defect detection method for overhead power transmission lines provided in Embodiment 1 of the present invention;

[0021] Figure 2 This is a flowchart of another method for detecting defects in overhead power transmission lines provided in Embodiment 2 of the present invention;

[0022] Figure 3 This is a schematic diagram of the structure of an overhead power transmission line defect detection device provided in Embodiment 3 of the present invention;

[0023] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the overhead power line defect detection method according to an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] Example 1

[0026] Figure 1 This is a flowchart of an overhead transmission line defect detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to defect detection of images of overhead transmission lines. The method can be executed by an overhead transmission line defect detection device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0027] S110. Obtain simulated sample images of the target transmission line and real sample images of the target transmission line.

[0028] Optionally, during the simulation process, a physical simulation model of the overhead transmission line is built at the test site to simulate the actual connection method and working environment of the overhead transmission line. The physical simulation model can be made of the same material and structure as the overhead transmission line. Then, a drone is used to collect images of the physical simulation model to obtain simulated sample images of the target transmission line.

[0029] The target transmission line can be an actual overhead transmission line to be detected. For example, the target transmission line can be an already installed and used transmission line.

[0030] Among them, real sample images can be real images taken by drones of the target power transmission line.

[0031] Specifically, when conducting defect detection on overhead power lines, a corresponding physical simulation model is established for the target power line. UAVs are used to take pictures of both the physical simulation model and the target power line to obtain simulated sample images and real sample images of the target power line.

[0032] S120. The pre-established pre-detection model is trained based on the simulated sample image and the real sample image to obtain the defect detection model.

[0033] The pre-detection model can be an image detection model that has been pre-built for image detection training.

[0034] Among them, the defect detection model can be an image detection model for detecting defects in transmission line images.

[0035] Specifically, the image detection model is trained by acquiring simulated and real sample images of the target transmission line. The simulated and real sample images are used as training data and input into a pre-established pre-detection model to train the model, determine the model parameters of the pre-detection model, and obtain the defect detection model.

[0036] For example, the defect detection module includes at least a backbone network, a feature fusion network, a classification network, and a regression network. The backbone network can be a residual convolutional neural network, which is responsible for forward feature extraction of the image. The feature fusion network adopts a feature pyramid network, which fused the top-level features with low resolution and high semantic information and the low-level features with high resolution and lack of semantic information by connecting them horizontally from top to bottom and from bottom to top to generate a large number of candidate regions. The classification network and the regression network determine the category of the defect at the output of the backbone network and identify the location of the defect in the image.

[0037] S130. Determine the transmission line defects of the target transmission line based on the defect detection model and real sample images.

[0038] Among these, transmission line defects can refer to defects present in overhead transmission lines during the power transmission process. For example, transmission line defects can include various issues such as overheating joints, wire defects, and loose pins.

[0039] Optionally, transmission line defects include transmission line defect type and transmission line defect location. The transmission line defect type can be any type of defect present in the transmission line; the transmission line defect location can be the location of the defect on the target transmission line.

[0040] Specifically, real sample images are input into the defect detection model, which detects power line defects in the real sample images. The defect detection model then identifies the real sample images and outputs the power line defects of the target power line.

[0041] The technical solution of this invention acquires simulated sample images and real sample images of a target transmission line. The simulated sample images increase the sample data for identification, while the real sample images improve the accuracy of identification. A pre-established pre-detection model is trained using the simulated and real sample images to obtain a defect detection model. This defect detection model, based on both real and simulated sample images, improves the model's prediction accuracy. Based on the defect detection model and real sample images, transmission line defects are determined. The defect detection model detects real sample images to identify the transmission line defects. This achieves defect detection in overhead transmission lines using UAVs, improving the accuracy of defect identification and solving the problem of inefficient and inaccurate transmission line identification in existing technologies.

[0042] Example 2

[0043] Figure 2 This is a flowchart of another overhead transmission line defect detection method provided in Embodiment 2 of the present invention. The relationship between this embodiment and the above embodiments is that this is a specific method for training a defect detection model. Figure 2 As shown, the method for detecting defects in overhead power transmission lines includes:

[0044] S210. Obtain simulated sample images of the target transmission line and real sample images of the target transmission line.

[0045] Optionally, in another optional embodiment of the present invention, obtaining a simulated sample image of the simulated target transmission line includes:

[0046] Obtain the connection structure and connection method of the target power transmission line; create a simulated power transmission line based on the connection structure and connection method, and simulate the power transmission line defects of the target power transmission line in the simulated power transmission line; obtain the simulated sample image by taking pictures of the power transmission line defects in the simulated power transmission line using a drone.

[0047] Among them, the drone can be a drone equipped with a camera.

[0048] The connection structure can be the line of the target transmission line and the structure of the transmission line.

[0049] The connection method can refer to the connection status of the lines and transmission line structure in the target transmission line.

[0050] The simulated transmission line can be a transmission line with the exact same connection structure and connection method as the target transmission line.

[0051] Specifically, in order to increase the number and accuracy of samples, a simulated transmission line identical to the target transmission line is established to obtain the connection structure and connection method of the target transmission line. Based on the connection structure and connection method of the target transmission line, a simulated transmission line is created to simulate the connection method and connection structure of the target transmission line. Defects are artificially set in the established simulated transmission line, and drones are used to photograph the defects in the simulated transmission line to obtain simulated sample images of the target transmission line.

[0052] It should be noted that the simulated transmission line and the target transmission line are exactly the same transmission line, which can ensure that the simulated transmission line and the target transmission line objects are completely consistent. In order to improve the generalization ability of the simulated sample images, it is necessary to adjust the position of the simulated transmission line model, control the background of the transmission line defects in the simulated transmission line, and take pictures of the simulated transmission line under different environments to ensure the diversity of the simulated sample images.

[0053] S220. Perform image sample mixing based on the simulated sample image and the real sample image to determine the mixed sample image set;

[0054] The mixed sample image set can be a collection of sample images that includes both simulated and real sample images. It should be noted that for images in the mixed sample image set, there is no need to label them to indicate their category.

[0055] Specifically, the richness of the sample is enriched by image sample mixing. Simulated sample images and real sample images are mixed to obtain a mixed sample image set.

[0056] S230. Input the mixed sample image set into the pre-established pre-detection model for model training to obtain the first preliminary detection model;

[0057] The first preliminary detection model can be an image detection model trained on a mixed sample image set.

[0058] Specifically, the mixed sample image set is input into a pre-established pre-detection model for training. The model parameters of the pre-detection model are trained to determine the first preliminary detection model for the mixed sample image set.

[0059] S240. Input the real sample image into the pre-established pre-detection model for model training to determine the second preliminary detection model;

[0060] The second preliminary detection model can be an image detection model trained on real sample images.

[0061] Specifically, real sample images are input into a pre-established pre-detection model for training. The model parameters of the pre-detection model are trained to determine the second preliminary detection model for the mixed sample image set.

[0062] S250. Determine the defect detection model based on the first preliminary detection model and the second preliminary detection model.

[0063] Specifically, after training to obtain the first preliminary detection model and the second preliminary detection model, the defect detection model is determined based on the first preliminary detection model and the second preliminary detection model.

[0064] Optionally, in another optional embodiment of the present invention, determining the defect detection model based on the first preliminary detection model and the second preliminary detection model includes:

[0065] The simulated sample image is input into the first preliminary detection model for model testing to determine the first test result; a target sample image is obtained from the real sample image; the target sample image is input into the second preliminary detection model for model testing to determine the second test result; and a defect detection model is determined based on the first test result and the second test result.

[0066] The first test result can be the test defect result output by the first preliminary detection model from the input of a simulated sample image, and the average accuracy change curve corresponding to the test defect result.

[0067] The target sample image can be a sample image of a specific defect category selected by the tester; the second test result can be the test defect result output by the second preliminary detection model from the target sample image and the average accuracy change curve corresponding to the test defect result.

[0068] Optionally, during the testing process, the first preliminary detection model or the second preliminary detection model outputs the defects present in each image sample, determines the corresponding test defect results, calculates the average accuracy of the first preliminary detection model and the second preliminary detection model respectively, and generates the change curve corresponding to the average accuracy.

[0069] Specifically, simulated sample images are input into the first preliminary detection model for model testing to determine the first test result. Testers then obtain target sample images from real sample images, input the target sample images into the second preliminary detection model for model testing to determine the second test result, and finally determine the defect detection model based on the first and second test results.

[0070] Optionally, in another optional embodiment of the present invention, obtaining the target sample image from the real sample image includes: performing image filtering in the real sample image according to a pre-set target transmission line defect to determine the target sample image corresponding to the target transmission line defect.

[0071] The target transmission line defect can be a transmission line defect pre-selected by the tester.

[0072] Specifically, testers pre-set target transmission line defects in the transmission line defects, and then filter real sample images based on the target transmission line defects to determine whether the real sample images contain the target transmission line defects, thus identifying the target sample images corresponding to the target transmission line defects.

[0073] Optionally, in another optional embodiment of the present invention, determining the defect detection model based on the first test result and the second test result includes:

[0074] The curve changes of the first test curve and the second test curve are compared to determine the curve comparison result; redundant images in the simulated sample images are determined based on the first test defect result, the second test defect result, and the curve comparison result; the simulated sample images are adjusted based on the redundant images to determine the adjusted simulated sample images and the number of adjustment times is recorded; if the number of adjustment times is less than a preset adjustment threshold, the operation of training the pre-established pre-detection model based on the simulated sample images and the real sample images is returned; if the number of adjustment times reaches the preset number threshold, the first preliminary detection model is determined as the defect detection model.

[0075] Wherein, the first test defect result can be the test defect result output by the first preliminary detection model; the first test curve can be the average accuracy change curve corresponding to the first test defect result.

[0076] The second test defect result can be the test defect result output by the second preliminary detection model; the second test curve can be the average accuracy change curve corresponding to the second test defect result.

[0077] Among them, curve change can be the curve trend.

[0078] The curve comparison result can be a comparison of the curve trends of the first test curve and the curve trends of the second test curve.

[0079] The redundant image can be redundant data in the simulated sample image.

[0080] The number of adjustments can refer to the number of times the simulated sample image is adjusted.

[0081] The preset adjustment threshold can be a pre-set judgment value for determining the number of adjustments.

[0082] Specifically, the curve changes of the first test curve and the second test curve are compared to determine the curve comparison result. Based on the curve comparison result and the first and second test defect results, redundant images in the simulated sample images are identified. The simulated sample images are then adjusted using the redundant images to determine the adjusted simulated sample images. The number of adjustments is recorded, and the relationship between the number of adjustments and a preset adjustment threshold is determined. If the number of adjustments is less than the preset adjustment threshold, the process returns to the operation of training the pre-established pre-detection model using simulated sample images and real sample images for the next round of model training. If the number of adjustments reaches the preset threshold, the first preliminary detection model is determined as the defect detection model.

[0083] S260. Determine the transmission line defects of the target transmission line based on the defect detection model and real sample images.

[0084] The technical solution of this invention acquires simulated sample images and real sample images of a target transmission line. The simulated sample images increase the sample data for identification, while the real sample images improve the accuracy of identification. A pre-established pre-detection model is trained using the simulated and real sample images to obtain a defect detection model. This defect detection model, based on both real and simulated sample images, improves the model's prediction accuracy. Based on the defect detection model and real sample images, transmission line defects are determined. The defect detection model detects real sample images to identify the transmission line defects. This achieves defect detection in overhead transmission lines using UAVs, improving the accuracy of defect identification and solving the problem of inefficient and inaccurate transmission line identification in existing technologies.

[0085] Example 3

[0086] Figure 3 This is a schematic diagram of the structure of an overhead power transmission line defect detection device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a data acquisition module 310, a model training module 320, and a defect detection module 330, wherein,

[0087] The data acquisition module 310 is used to acquire simulated sample images of the target transmission line and real sample images of the target transmission line;

[0088] The model training module 320 is used to train the pre-established pre-detection model based on the simulated sample image and the real sample image to obtain the defect detection model;

[0089] The defect detection module 330 is used to determine the transmission line defects of the target transmission line based on the defect detection model and real sample images.

[0090] The technical solution of this invention acquires simulated sample images and real sample images of a target transmission line. The simulated sample images increase the sample data for identification, while the real sample images improve the accuracy of identification. A pre-established pre-detection model is trained using the simulated and real sample images to obtain a defect detection model. This defect detection model, based on both real and simulated sample images, improves the model's prediction accuracy. Based on the defect detection model and real sample images, transmission line defects are determined. The defect detection model detects real sample images to identify the transmission line defects. This achieves defect detection in overhead transmission lines using UAVs, improving the accuracy of defect identification and solving the problem of inefficient and inaccurate transmission line identification in existing technologies.

[0091] Optionally, the data acquisition module is specifically used for:

[0092] Obtain the connection structure and connection method of the target power transmission line;

[0093] A simulated transmission line for simulating the target transmission line is created based on the connection structure and the connection method, and the transmission line defects of the target transmission line are simulated in the simulated transmission line.

[0094] The simulated sample image is obtained by taking pictures of the power transmission line defects in the simulated power transmission line using a drone.

[0095] Optionally, the model training module is specifically used for:

[0096] Based on the simulated sample images and the real sample images, image samples are mixed to determine a mixed sample image set;

[0097] The mixed sample image set is input into a pre-established pre-detection model for model training to obtain a first preliminary detection model;

[0098] The real sample images are input into a pre-established pre-detection model for model training to determine the second preliminary detection model;

[0099] The defect detection model is determined based on the first preliminary detection model and the second preliminary detection model.

[0100] Optionally, the model training module is further used for:

[0101] The simulated sample image is input into the first preliminary detection model for model testing to determine the first test result;

[0102] Obtain the target sample image from the real sample image;

[0103] The target sample image is input into the second preliminary detection model for model testing to determine the second test result;

[0104] The defect detection model is determined based on the first test result and the second test result.

[0105] Optionally, the model training module is further used for:

[0106] The curve changes of the first test curve and the curve changes of the second test curve are compared to determine the curve comparison result;

[0107] The redundant images in the simulated sample images are determined based on the first test defect results, the second test defect results, and the curve comparison results.

[0108] The simulated sample image is adjusted based on the redundant image to determine the adjusted simulated sample image, and the number of adjustments is recorded.

[0109] If the number of adjustments is less than a preset adjustment threshold, return to the operation of training the pre-established pre-detection model based on the simulated sample image and the real sample image;

[0110] If the number of adjustments reaches a preset threshold, then the first preliminary detection model is determined as the defect detection model.

[0111] Optionally, the model training module is further used for:

[0112] Based on a pre-defined target transmission line defect, the images in the real sample images are filtered to determine the target sample image corresponding to the target transmission line defect.

[0113] Optionally, the transmission line defect includes at least one of transmission line defect type and transmission line defect location.

[0114] The overhead transmission line defect detection device provided in this embodiment of the invention can execute the overhead transmission line defect detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0115] Example 4

[0116] Figure 4A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0117] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0118] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0119] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as overhead transmission line defect detection methods.

[0120] In some embodiments, the overhead transmission line defect detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the overhead transmission line defect detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the overhead transmission line defect detection method by any other suitable means (e.g., by means of firmware).

[0121] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0123] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0124] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0125] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0126] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0127] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0128] Example 5

[0129] This embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the steps of the overhead transmission line defect detection method provided in any embodiment of the present invention. The method includes:

[0130] Obtain simulated sample images of the target transmission line and real sample images of the target transmission line;

[0131] The pre-established pre-detection model is trained based on the simulated sample images and the real sample images to obtain a defect detection model;

[0132] The defects of the target transmission line are determined based on the defect detection model and real sample images.

[0133] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0135] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0136] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone 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 remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0137] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0138] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0139] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting defects in overhead transmission lines, characterized in that, include: Obtain simulated sample images of the target transmission line and real sample images of the target transmission line; The pre-established pre-detection model is trained based on the simulated sample images and the real sample images to obtain a defect detection model; The defects of the target transmission line are determined based on the defect detection model and real sample images. The step of training a pre-established pre-detection model based on the simulated sample image and the real sample image to obtain a defect detection model includes: Based on the simulated sample images and the real sample images, image samples are mixed to determine a mixed sample image set; The mixed sample image set is input into a pre-established pre-detection model for model training to obtain a first preliminary detection model; The real sample images are input into a pre-established pre-detection model for model training to determine the second preliminary detection model; Determine the defect detection model based on the first preliminary detection model and the second preliminary detection model; The step of determining the defect detection model based on the first preliminary detection model and the second preliminary detection model includes: The simulated sample image is input into the first preliminary detection model for model testing to determine the first test result; Obtain the target sample image from the real sample image; The target sample image is input into the second preliminary detection model for model testing to determine the second test result; Determine the defect detection model based on the first test result and the second test result; The first test result includes a first test curve and a first test defect result; the second test result includes a second test curve and a second test defect result; determining the defect detection model based on the first test result and the second test result includes: The curve changes of the first test curve and the curve changes of the second test curve are compared to determine the curve comparison result; wherein, the first test curve is the average accuracy change curve corresponding to the first test defect result, and the first test defect result is the test defect result output by the first preliminary detection model; the second test curve is the average accuracy change curve corresponding to the second test defect result, and the second test defect result is the test defect result output by the second preliminary detection model; the curve change is the trend of the curve, and the curve comparison result is the comparison result of the curve trend of the first test curve and the curve trend of the second test curve; Redundant images in the simulated sample images are determined based on the first test defect results, the second test defect results, and the curve comparison results; wherein, the redundant images are redundant data in the simulated sample images; The simulated sample image is adjusted based on the redundant image to determine the adjusted simulated sample image, and the number of adjustments is recorded. If the number of adjustments is less than a preset adjustment threshold, return to the operation of training the pre-established pre-detection model based on the simulated sample image and the real sample image; If the number of adjustments reaches a preset threshold, then the first preliminary detection model is determined as the defect detection model.

2. The method according to claim 1, characterized in that... The step of acquiring a simulated sample image of the simulated target transmission line includes: Obtain the connection structure and connection method of the target power transmission line; A simulated transmission line for the target transmission line is created based on the connection structure and the connection method, and the transmission line defects of the target transmission line are simulated in the simulated transmission line. The simulated sample image is obtained by taking pictures of the power transmission line defects in the simulated power transmission line using a drone.

3. The method according to claim 1, characterized in that, The step of obtaining the target sample image from the real sample image includes: Based on a pre-defined target transmission line defect, the images in the real sample images are filtered to determine the target sample image corresponding to the target transmission line defect.

4. The method according to claim 1, characterized in that, The transmission line defect includes at least one of the transmission line defect type and the transmission line defect location.

5. A defect detection device for overhead transmission lines, characterized in that, include: The data acquisition module is used to acquire simulated sample images of the target transmission line and real sample images of the target transmission line; The model training module is used to train the pre-established pre-detection model based on the simulated sample images and the real sample images to obtain the defect detection model; The defect detection module is used to determine the transmission line defects of the target transmission line based on the defect detection model and real sample images. The model training module is specifically used for: Based on the simulated sample images and the real sample images, image samples are mixed to determine a mixed sample image set; The mixed sample image set is input into a pre-established pre-detection model for model training to obtain a first preliminary detection model; The real sample images are input into a pre-established pre-detection model for model training to determine the second preliminary detection model; Determine the defect detection model based on the first preliminary detection model and the second preliminary detection model; The model training module is also specifically used for: The simulated sample image is input into the first preliminary detection model for model testing to determine the first test result; Obtain the target sample image from the real sample image; The target sample image is input into the second preliminary detection model for model testing to determine the second test result; Determine the defect detection model based on the first test result and the second test result; The model training module is also specifically used for: The curve changes of the first test curve and the curve changes of the second test curve are compared to determine the curve comparison result; wherein, the first test curve is the average accuracy change curve corresponding to the first test defect result, and the first test defect result is the test defect result output by the first preliminary detection model; the second test curve is the average accuracy change curve corresponding to the second test defect result, and the second test defect result is the test defect result output by the second preliminary detection model; the curve change is the trend of the curve, and the curve comparison result is the comparison result of the curve trend of the first test curve and the curve trend of the second test curve; Redundant images in the simulated sample images are determined based on the first test defect results, the second test defect results, and the curve comparison results; wherein, the redundant images are redundant data in the simulated sample images; The simulated sample image is adjusted based on the redundant image to determine the adjusted simulated sample image, and the number of adjustments is recorded. If the number of adjustments is less than a preset adjustment threshold, return to the operation of training the pre-established pre-detection model based on the simulated sample image and the real sample image; If the number of adjustments reaches a preset threshold, then the first preliminary detection model is determined as the defect detection model.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the overhead transmission line defect detection method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the overhead transmission line defect detection method according to any one of claims 1-4.

Images