Improved YOLOv8 power transmission line insulator fault detection method and system
By improving the YOLOv8 model, using GhostNet backbone network and MSA-GB feature extraction structure, the problems of time-consuming calculation and memory consumption in insulator fault detection are solved, and accurate detection and efficient detection of insulator defects in transmission line are achieved.
Patent Information
- Application Number
- CN202411632773.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-15
- Publication Date
- 2025-02-25
AI Technical Summary
The prior art has problems such as time-consuming calculation, high memory consumption, limited adaptability, and lack of strong generalization capabilities in insulator fault detection, making it difficult to meet the needs of target high-precision and high-efficiency detection under complex image backgrounds.
The YOLOv8 model is improved, the GhostNet backbone network and MSA-GB feature extraction structure are adopted, and the fully connected layer is decomposed into two separate feature extraction layers to simulate long-distance spatial information and enhance feature extraction capabilities.
It realizes accurate detection of insulator defects in transmission lines, reduces calculation time and memory consumption, improves adaptability and generalization capabilities, and meets the high-precision and high-efficiency detection requirements under complex image backgrounds.
Smart Images
Figure CN119515843A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power grid operation and maintenance, and in particular to a method and system for detecting insulator faults in a power transmission line based on an improved YOLOv8. Background Art
[0002] As an indispensable part of the power network architecture, overhead transmission line insulators are generally exposed to the changing and harsh natural environment outdoors for a long time, and are generally faced with severe tests of atmospheric pollution erosion, natural aging, and extreme weather conditions. In view of this, regular and accurate detection of the pollution status of the insulator surface and determination of its pollution category are crucial to ensure the safe and stable operation of the power grid. In the past, this work relied on traditional means such as telescope observation and infrared camera shooting for identification and detection. However, the operation process of these methods is cumbersome and complicated, and the efficiency is limited.
[0003] In recent years, drone technology has shown great application potential in the field of power inspection, especially in airborne imaging monitoring. By combining deep learning algorithms running on edge devices and using computer vision technology, it is expected to significantly improve the accuracy of outdoor object detection and classification, thereby providing a more efficient and accurate solution for insulator condition monitoring.
[0004] In terms of the current technical level, algorithms such as Bayesian classifiers, support vector machines (SVM), random forests, and extra trees in the field of machine learning are more common classification tools in insulator evaluation. However, the performance of these algorithms in practical applications is only moderate, and the detection accuracy needs to be improved. In addition, when processing data, they not only take a long time, but also consume a lot of memory, and urgently need to optimize the algorithm and data processing process. In actual operation, manual intervention is often required to achieve a more ideal detection effect. These traditional methods have limited adaptability and insufficient generalization ability, mainly because they can only work in simple backgrounds or large target images. What is more serious is that with the advancement of subsequent experiments, the accuracy of these methods has limited room for improvement, and it is difficult to meet the actual needs of high-precision and high-efficiency detection of targets under complex image backgrounds.
[0005] Therefore, it has become an urgent task to innovate and upgrade existing technologies.
[0006] The above information is presented as background information only to assist with understanding the present disclosure and no determination or admission is made as to whether any of the above may be used as prior art with respect to the present disclosure. Summary of the invention
[0007] The present invention provides a transmission line insulator fault detection method and system based on improved YOLOv8 to solve the problems existing in the prior art.
[0008] To achieve the above object, the present invention provides the following technical solutions:
[0009] In a first aspect, the present invention provides a method for detecting insulator faults in a power transmission line using an improved YOLOv8, the method comprising:
[0010] Acquire an insulator image;
[0011] The insulator image is input into an improved YOLOv8 model to obtain an insulator fault detection result; the improved YOLOv8 model includes a GhostNet backbone network, and the GhostNet backbone network includes an MSA-GB feature extraction structure.
[0012] Furthermore, in the improved YOLOv8 transmission line insulator fault detection method, the method further includes:
[0013] Use the GhostNet backbone network as the backbone network of the YOLOv8 model;
[0014] The fully connected layer is decomposed into two separate feature extraction layers in the horizontal and vertical directions to simulate long-distance spatial information, and the two fully connected layers are merged, and the enhanced features are fused with the original features to obtain weighted features to obtain an improved YOLOv8 model;
[0015] The improved YOLOv8 model is trained to obtain the trained improved YOLOv8 model.
[0016] Furthermore, in the improved YOLOv8 transmission line insulator fault detection method, the step of training the improved YOLOv8 model to obtain the trained improved YOLOv8 model includes:
[0017] Acquire an insulator image;
[0018] Adjusting the acquired insulator image with variable dimensions to obtain image data to be processed;
[0019] Labeling the image data to be processed to determine characteristic attributes of different image data; the labels include normal insulators, missing insulators, damaged insulators and flashover insulators;
[0020] The image data is input into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model.
[0021] Furthermore, in the improved YOLOv8 transmission line insulator fault detection method, before the step of inputting the image data into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model, the method further includes:
[0022] The ResPANet multi-scale fusion structure is used to perform feature fusion on image data. The ResPANet multi-scale fusion structure is obtained by adding a residual connection between the encoder and the decoder in the pyramid network.
[0023] In a second aspect, the present invention provides a transmission line insulator fault detection system based on an improved YOLOv8, the system comprising:
[0024] An image acquisition module, used for acquiring an insulator image;
[0025] A fault detection module is used to input the insulator image into an improved YOLOv8 model to obtain an insulator fault detection result; the improved YOLOv8 model includes a GhostNet backbone network, and the GhostNet backbone network includes an MSA-GB feature extraction structure.
[0026] Furthermore, in the improved YOLOv8 transmission line insulator fault detection system, the system also includes an improved model building module for:
[0027] Use the GhostNet backbone network as the backbone network of the YOLOv8 model;
[0028] The fully connected layer is decomposed into two separate feature extraction layers in the horizontal and vertical directions to simulate long-distance spatial information, and the two fully connected layers are merged, and the enhanced features are fused with the original features to obtain weighted features to obtain an improved YOLOv8 model;
[0029] The improved YOLOv8 model is trained to obtain the trained improved YOLOv8 model.
[0030] Furthermore, in the improved YOLOv8 transmission line insulator fault detection system, the improved model building module is specifically used for:
[0031] Acquire an insulator image;
[0032] Adjusting the acquired insulator image with variable dimensions to obtain image data to be processed;
[0033] Labeling the image data to be processed to determine characteristic attributes of different image data; the labels include normal insulators, missing insulators, damaged insulators and flashover insulators;
[0034] The image data is input into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model.
[0035] Furthermore, in the improved YOLOv8 transmission line insulator fault detection system, the improved model building module is also used for:
[0036] Before the step of inputting the image data into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model, the image data is feature fused using a ResPANet multi-scale fusion structure, where the ResPANet multi-scale fusion structure is obtained by adding a residual connection between the encoder and the decoder in the pyramid network.
[0037] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the improved YOLOv8 transmission line insulator fault detection method provided in the first aspect above.
[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions are executed by a computer processor to implement the improved YOLOv8 transmission line insulator fault detection method as provided in the first aspect above.
[0039] Compared with the prior art, the present invention has the following beneficial effects:
[0040] The present invention provides a transmission line insulator fault detection method and system based on improved YOLOv8. The YOLOv8 model is improved so that it includes a GhostNet backbone network, and the GhostNet backbone network includes an MSA-GB feature extraction structure. The improved YOLOv8 model is used in insulator fault detection, so that accurate detection of transmission line insulator defects can be achieved, and the problems of large computational time and memory consumption, limited adaptability, lack of strong generalization ability, etc. are solved, which is conducive to promotion and application.
[0041] The present invention has other features and advantages, which will be apparent from or will be described in detail in the accompanying drawings and the following detailed description incorporated herein, which together serve to explain the specific principles of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0043] Figure 1 It is a flow chart of a method for detecting insulator faults in a power transmission line using an improved YOLOv8 provided in the first embodiment of the present invention;
[0044] Figure 2 Schematic diagram of the GhostNet structure mentioned in the first embodiment of the present invention;
[0045] Figure 3 Schematic diagram of the MSA-GB feature extraction structure mentioned in the first embodiment of the present invention;
[0046] Figure 4 is an example diagram of the data set image mentioned in the first embodiment of the present invention;
[0047] Figure 5 Schematic diagram of the ResPANet structure mentioned in the first embodiment of the present invention;
[0048] Figure 6 is a schematic diagram of the feature fusion process mentioned in the first embodiment of the present invention;
[0049] Figure 7 is an example diagram of the detection results mentioned in the first embodiment of the present invention;
[0050] Figure 8 It is a functional module diagram of a transmission line insulator fault detection system of an improved YOLOv8 provided in Embodiment 2 of the present invention;
[0051] Fig. 9 It is a structural diagram of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION
[0052] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.
[0053] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.
[0054] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.
[0055] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.
[0056] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.
[0057] Without further limitations, in this application, the words "include", "comprises", "has" or other similar expressions used in the sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.
[0058] In this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.
[0059] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.
[0060] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms such as "install", "connect", "connect", "fix", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For technicians in the technical field to which the present application belongs, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.
[0061] Embodiment 1
[0062] Please refer to Figure 1 , is a flow chart of a method for detecting a transmission line insulator fault using an improved YOLOv8 provided in Embodiment 1 of the present invention. The method is applicable to a scenario of detecting a transmission line insulator fault. The method is executed by a transmission line insulator fault detection system using an improved YOLOv8. The method specifically comprises the following steps:
[0063] S101. Acquire an insulator image.
[0064] It should be noted that appropriate image acquisition equipment (such as drones, inspection robots, cameras, etc.) is used to capture images of insulators on transmission lines.
[0065] It is understandable that some preprocessing may be performed on the collected insulator images, including denoising, enhancement, normalization and other operations, to improve the accuracy of subsequent processing.
[0066] S102, inputting the insulator image into an improved YOLOv8 model to obtain an insulator fault detection result; the improved YOLOv8 model includes a GhostNet backbone network, and the GhostNet backbone network includes an MSA-GB feature extraction structure.
[0067] It should be noted that the detected insulator fault information (such as fault location, type, severity, etc.) is output in the form of visualization or data for further processing by the user or system.
[0068] In one implementation of this embodiment, the method further includes:
[0069] Use the GhostNet backbone network as the backbone network of the YOLOv8 model;
[0070] The fully connected layer is decomposed into two separate feature extraction layers in the horizontal and vertical directions to simulate long-distance spatial information, and the two fully connected layers are merged, and the enhanced features are fused with the original features to obtain weighted features to obtain an improved YOLOv8 model;
[0071] The improved YOLOv8 model is trained to obtain the trained improved YOLOv8 model.
[0072] It should be noted that in the target detection algorithm, the features extracted by the backbone network are more conducive to the subsequent model to learn effective targets from the features. Therefore, this embodiment first uses GhostNet as the basic backbone network for model research. GhostNet uses primary and secondary channels for feature extraction. The primary channel is usually used to capture the main information and features in the image, while the secondary channel usually contains fewer convolutional layers, which is designed to capture details and low-level features in the image, helping to prevent overfitting. In addition, the design of the secondary channel adopts depthwise separable convolution to make the model lighter, with fewer parameters and calculations, and the output is added to the output of the primary channel to generate the final feature representation. The structure of GhostNet is as follows Figure 2 shown.
[0073] The above process is expressed by the following equation:
[0074] ……(1);
[0075] ……(2);
[0076] Where X is the input image, F 1×1 is a convolution operation with a kernel size of 1, F dp It is a vertically separable convolution operation. The final output Y is the output feature, and Y' is the feature map after the convolution operation.
[0077] Since the insulator objects under study are distributed outdoors, the actual detection process is easily affected by complex backgrounds such as mountains and rivers. At present, this embodiment optimizes it through the attention mechanism. The channel-based attention mechanism effectively utilizes the correlation between channels by combining the feature map with the weighted matrix, enhances the weight of the target channel, and suppresses irrelevant channels.
[0078] The present invention combines the attention mechanism with the insulator characteristics of different types of faults. Considering that the insulator is a fault distributed in different distance regions, the backbone feature extraction is further optimized by establishing a modeling framework of different distance receptive fields. The original fully connected (FC) layer of Yolov8 is decomposed into two separate feature extraction layers in the horizontal and vertical directions to simulate long-distance spatial information. Finally, the two FC layers are merged. The enhanced features are fused with the original features to obtain weighted features. The feature extraction model finally designed is as follows: Figure 3 Shown
[0079] In one implementation of this embodiment, the step of training the improved YOLOv8 model to obtain the trained improved YOLOv8 model includes:
[0080] Acquire an insulator image;
[0081] Adjusting the acquired insulator image with variable dimensions to obtain image data to be processed;
[0082] Labeling the image data to be processed to determine characteristic attributes of different image data; the labels include normal insulators, missing insulators, damaged insulators and flashover insulators;
[0083] The image data is input into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model.
[0084] It should be noted that in order to realize the identification of insulators with various fault types in transmission lines, this embodiment constructs a related insulator dataset, and the data is collected using a DJI Mavic 2 drone with an effective pixel count of 12 million. In order to train the model, the collected data is adjusted in variable dimensions to better magnify different insulator targets. The dataset has a total of 4615 samples, each image contains one or more detection targets, and the same detection target can have multiple instances.
[0085] The labels include four categories: normal insulators (insulators for short), missing insulators (defects for short), damaged insulators (ruptures for short), and flashover insulators (flashovers for short). The samples are labeled using labeling software and a dataset is created in VOC format. In terms of sample size, this dataset has sufficient training capacity similar to the standard dataset. The data distribution of each target is shown in Table 1. Some sample contents are shown in Figure 4 shown.
[0086] Table 1:
[0087]
[0088] In one implementation of this embodiment, before the step of inputting the image data into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model, the method further includes:
[0089] The ResPANet multi-scale fusion structure is used to perform feature fusion on image data. The ResPANet multi-scale fusion structure is obtained by adding a residual connection between the encoder and the decoder in the pyramid network.
[0090] It should be noted that in the YOLOv8 model, PANet (feature pyramid) is used for multi-scale fusion in target detection. However, with the increase in image resolution and the complexity of target scenes, the general PANet structure cannot fully realize its potential, especially when extracting deeper features, because there is a risk of losing target information and failing to detect objects.
[0091] Therefore, the present invention proposes a feature fusion structure called ResPANet, which is a multi-resolution feature pyramid network with multiple residual connections, designed to utilize the rich feature information of the image at high resolution. The residual connection is used to reduce the path length during training, thereby improving the convergence speed of the model. In addition, the computational complexity of the model is not increased because the three scales are still maintained in the feature fusion stage. The overall design approach involves adding residual connections between the encoder and decoder in the pyramid network. Convolutions with a stride of 2 are used to unify the feature scales and improve spatial accuracy while maintaining effective feature representation. The designed ResPANet structure is shown in Figure 2. Figure 5 shown.
[0092] exist Figure 6 In the decoding part (e.g., Figure 6 (a) shows), the present invention performs feature fusion before training, aiming to better restore feature information by compensating for the deficiency of original data.
[0093] The specific calculation formula is as follows:
[0094] ……(3);
[0095] In formula (3), Concat (*) represents feature fusion, and UP (*) represents the process of feature collection.
[0096] like Figure 6 As shown in (b), feature fusion is performed after the encoding part is trained. The principle behind this is mainly because training is a process of information reduction, and the introduction of the residual structure effectively compensates for the loss of information.
[0097] The specific calculation formula is as follows:
[0098] ……(4);
[0099] In formula (4), Concat (*) represents feature fusion, and UP (*) represents the feature fusion process after training.
[0100] Model training and analysis:
[0101] (1) Training environment and parameters
[0102] The experiments were conducted on Ubuntu 18.04 using Python 3.8.0 and CUDA 11.2. The deep learning framework used for training and testing is based on PyTorch 1.8. Training was performed using two NVIDIA GeForce RTX3090 GPUs and 24GB RAM. The training model parameters are shown in Table 2.
[0103] Table 2:
[0104]
[0105] (2) Analysis of test results
[0106] When studying the detection of various defects on insulators, we first designed experiments to compare the existing basic target detection algorithms, mainly using the YOLO series of algorithms for comparative experiments. The experimental results are shown in Table 3. The average accuracy of the YOLOv8 series model is the highest at 95.2%. It is also observed that the main factors affecting the accuracy of the model are insulator defects and flashover targets, which are represented by "Defect" and "Flashover" respectively in the table. These two categories are mainly challenging due to their small size and dense distribution.
[0107] Table 3:
[0108]
[0109] Examples of test results are Figure 7 As shown, the red, pink, yellow and orange frames of the insulator object detection results represent the detection results of insulator, defect, fracture and flashover respectively.
[0110] According to the experimental results, the improved Yolov8 model proposed in the present invention has a very good detection effect in insulator fault detection compared with other classic detection models. Therefore, the method proposed in the present invention is an accurate and reliable technical method.
[0111] Although the terms such as model and backbone network are used more frequently in this application, the possibility of using other terms is not excluded. These terms are used only to more conveniently describe and explain the essence of the present invention; interpreting them as any additional restrictions is contrary to the spirit of the present invention.
[0112] An improved YOLOv8 transmission line insulator fault detection method provided by an embodiment of the present invention improves the YOLOv8 model so that it includes a GhostNet backbone network, and the GhostNet backbone network includes an MSA-GB feature extraction structure, and the improved YOLOv8 model is used in insulator fault detection, thereby accurately detecting defects in insulators of transmission lines, solving the problems of large computational time and memory consumption, limited adaptability, lack of strong generalization ability, etc., and is conducive to promotion and application.
[0113] Embodiment 2
[0114] Please refer to Figure 8 , Figure 8 This is a functional module diagram of a transmission line insulator fault detection system of an improved YOLOv8 provided in Embodiment 2 of the present invention. The system is suitable for executing the transmission line insulator fault detection method of the improved YOLOv8 provided in Embodiment 2 of the present invention. The system specifically includes the following modules:
[0115] An image acquisition module 201 is used to acquire an insulator image;
[0116] The fault detection module 202 is used to input the insulator image into the improved YOLOv8 model to obtain an insulator fault detection result; the improved YOLOv8 model includes a GhostNet backbone network, and the GhostNet backbone network includes an MSA-GB feature extraction structure.
[0117] Preferably, the system further comprises an improved model building module, for:
[0118] Use the GhostNet backbone network as the backbone network of the YOLOv8 model;
[0119] The fully connected layer is decomposed into two separate feature extraction layers in the horizontal and vertical directions to simulate long-distance spatial information, and the two fully connected layers are merged, and the enhanced features are fused with the original features to obtain weighted features to obtain an improved YOLOv8 model;
[0120] The improved YOLOv8 model is trained to obtain the trained improved YOLOv8 model.
[0121] Preferably, the improved model building module is specifically used for:
[0122] Acquire an insulator image;
[0123] Adjusting the acquired insulator image with variable dimensions to obtain image data to be processed;
[0124] Labeling the image data to be processed to determine characteristic attributes of different image data; the labels include normal insulators, missing insulators, damaged insulators and flashover insulators;
[0125] The image data is input into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model.
[0126] Preferably, the improved model building module is also used for:
[0127] Before the step of inputting the image data into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model, the image data is feature fused using a ResPANet multi-scale fusion structure, where the ResPANet multi-scale fusion structure is obtained by adding a residual connection between the encoder and the decoder in the pyramid network.
[0128] An embodiment of the present invention provides a transmission line insulator fault detection system based on an improved YOLOv8. The YOLOv8 model is improved so that it includes a GhostNet backbone network, and the GhostNet backbone network includes an MSA-GB feature extraction structure. The improved YOLOv8 model is used in insulator fault detection, thereby accurately detecting defects in transmission line insulators, solving the problems of high computational time and memory consumption, limited adaptability, and lack of strong generalization ability, and is conducive to promotion and application.
[0129] The above system can execute the method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0130] Embodiment 3
[0131] Fig. 9 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. Fig. 9 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Fig. 9 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0132] like Fig. 9 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).
[0133] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.
[0134] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.
[0135] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Fig. 9 not shown, usually called a "hard drive"). Although Fig. 9 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.
[0136] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.
[0137] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via a bus 18. It should be understood that although Fig. 9 Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0138] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing the improved YOLOv8 transmission line insulator fault detection method provided in the embodiment of the present invention.
[0139] Embodiment 4
[0140] Embodiment 4 of the present invention provides a computer-readable storage medium having computer-executable instructions stored thereon. When the instructions are executed by a processor, the improved YOLOv8 transmission line insulator fault detection method as provided in all the embodiments of the present application is implemented.
[0141] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with 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 document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.
[0142] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0143] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0144] Computer program code for performing the operations of the present invention may 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 may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., through the Internet using an Internet service provider).
[0145] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.
Claims
1. A method for detecting insulator faults in power transmission lines based on improved YOLOv8, characterized in that: The method comprises: Acquire an insulator image; The insulator image is input into an improved YOLOv8 model to obtain an insulator fault detection result; the improved YOLOv8 model includes a GhostNet backbone network, and the GhostNet backbone network includes an MSA-GB feature extraction structure.
2. The improved YOLOv8 transmission line insulator fault detection method according to claim 1 is characterized in that: The method further comprises: Use the GhostNet backbone network as the backbone network of the YOLOv8 model; The fully connected layer is decomposed into two separate feature extraction layers in the horizontal and vertical directions to simulate long-distance spatial information, and the two fully connected layers are merged, and the enhanced features are fused with the original features to obtain weighted features to obtain an improved YOLOv8 model; The improved YOLOv8 model is trained to obtain the trained improved YOLOv8 model.
3. The improved YOLOv8 transmission line insulator fault detection method according to claim 2 is characterized in that: The step of training the improved YOLOv8 model to obtain the trained improved YOLOv8 model comprises: Acquire an insulator image; Adjusting the acquired insulator image with variable dimensions to obtain image data to be processed; Labeling the image data to be processed to determine characteristic attributes of different image data; the labels include normal insulators, missing insulators, damaged insulators and flashover insulators; The image data is input into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model.
4. The improved YOLOv8 transmission line insulator fault detection method according to claim 3 is characterized in that: Before the step of inputting the image data into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model, the method further includes: The ResPANet multi-scale fusion structure is used to perform feature fusion on image data. The ResPANet multi-scale fusion structure is obtained by adding a residual connection between the encoder and the decoder in the pyramid network.
5. A transmission line insulator fault detection system based on improved YOLOv8, characterized in that: The system comprises: An image acquisition module, used for acquiring an insulator image; A fault detection module is used to input the insulator image into an improved YOLOv8 model to obtain an insulator fault detection result; the improved YOLOv8 model includes a GhostNet backbone network, and the GhostNet backbone network includes an MSA-GB feature extraction structure.
6. The improved YOLOv8 transmission line insulator fault detection system according to claim 5, characterized in that: The system further comprises an improved model building module, which is used to: Use the GhostNet backbone network as the backbone network of the YOLOv8 model; The fully connected layer is decomposed into two separate feature extraction layers in the horizontal and vertical directions to simulate long-distance spatial information, and the two fully connected layers are merged, and the enhanced features are fused with the original features to obtain weighted features to obtain an improved YOLOv8 model; The improved YOLOv8 model is trained to obtain the trained improved YOLOv8 model.
7. The improved YOLOv8 transmission line insulator fault detection system according to claim 6, characterized in that: The improved model building module is specifically used for: Acquire an insulator image; Adjusting the acquired insulator image with variable dimensions to obtain image data to be processed; Labeling the image data to be processed to determine characteristic attributes of different image data; the labels include normal insulators, missing insulators, damaged insulators and flashover insulators; The image data is input into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model.
8. The improved YOLOv8 transmission line insulator fault detection system according to claim 7, characterized in that: The improved model building module is also used for: Before the step of inputting the image data into the improved YOLOv8 model for training to obtain the trained improved YOLOv8 model, the image data is feature fused using a ResPANet multi-scale fusion structure, where the ResPANet multi-scale fusion structure is obtained by adding a residual connection between the encoder and the decoder in the pyramid network.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the improved YOLOv8 transmission line insulator fault detection method according to any one of claims 1 to 4 is implemented.
10. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: The computer executable instructions are executed by a computer processor to implement the improved YOLOv8 transmission line insulator fault detection method as described in any one of claims 1-4.