Electric power asset life cycle management method based on cloud platform

Abstract

The invention provides a power asset life cycle management method based on a cloud platform, relates to the field of image recognition, and is particularly suitable for monitoring and managing early risks such as dynamic arc and corona of power equipment. The electric power asset life cycle management method based on the cloud platform specifically comprises the following steps: collecting multi-source image information of electric power asset equipment; identifying multi-target positions in the power asset equipment based on the multi-source image information; based on multi-source image information and the multi-target position, corona and arc appearing on the power asset equipment are identified; carrying out life cycle evaluation on the power asset equipment based on corona and arc identification results; through the above steps, the method achieves the efficient detection of the hidden risk of the electric power assets, and achieves the safety management and maintenance of the electric power assets.

Description

Technical Field

[0001] The present invention relates to the field of image recognition, and in particular to a cloud platform-based power asset lifecycle management method, which is particularly suitable for monitoring and managing early risks such as dynamic arc and corona of power equipment. Background Art

[0002] In the operation of modern society, electricity, as one of the most basic forms of energy, directly determines the normal operation of social production and life. The large-scale operation of the power system depends on a large number of power equipment, and the operating status of these equipment is directly related to the stability and security of the power grid. Therefore, the management of power equipment is not only a necessary means to ensure power supply, but also an important part of modern energy management. However, with the complexity of the power system and the expansion of equipment scale, traditional power equipment management methods have gradually exposed problems such as low efficiency and delayed response, which are difficult to meet the efficient operation requirements of modern power systems.

[0003] In the prior art, the life cycle management method of power equipment mainly relies on manual inspection. Manual inspection usually requires operation and maintenance personnel to regularly inspect power equipment and record the operating status of the equipment and changes in the external environment. However, this method has obvious limitations. First, the efficiency of manual inspection is low, and it is impossible to achieve real-time monitoring of a large number of power equipment. Secondly, due to the limited inspection frequency, many early abnormal signals in the operation of the equipment are difficult to detect in time. Although these signals may have little impact on the equipment in the early stage, they are often precursors to potential equipment failures. If they are not handled in time, the performance of the equipment may gradually deteriorate, eventually causing major failures. In addition, for the life cycle management of power assets, existing methods often lack systematic prediction and analysis methods. Usually, maintenance or even replacement measures are taken only when the equipment has obvious failures. This lag not only increases maintenance costs, but may also cause power supply interruptions, seriously threatening the safety and stability of the power grid.

[0004] In particular, existing management methods are almost powerless against early-stage power equipment risks such as dynamic arcs and coronas. Arcs and coronas are common abnormal phenomena of power equipment under high-voltage operating conditions, usually manifested as discharge phenomena on the surface or joints of power equipment. Arcs are accompanied by strong light, heat and noise, while coronas are characterized by weak ultraviolet light and ozone generation. Although these phenomena may not cause direct damage to the equipment in the early stages, they are early signals of problems such as equipment aging and insulation failure. If they are not effectively monitored and managed, they may lead to further deterioration of the equipment and increase the instability of the power system. Therefore, dynamic monitoring of arcs and coronas is a major technical difficulty in power equipment management. The current manual inspection method is difficult to capture these short-lived and weak abnormal signals, and lacks technical means to identify and evaluate the early risks of equipment, resulting in the management and maintenance of power assets lagging behind actual needs.

[0005] In order to address the above problems, the present invention proposes a power asset lifecycle management method based on a cloud platform. The method uses machine vision to detect arcs and coronas of power equipment in real time, combines the big data processing capabilities of the cloud platform, comprehensively analyzes the operating status of the equipment, predicts the life cycle of the equipment, and provides optimized maintenance suggestions. Summary of the invention

[0006] The present invention provides a method for managing the life cycle of electric power assets based on a cloud platform, the method specifically comprising the following steps: S1: Collect multi-source image information of power asset equipment; S2: Identify multiple target locations in power asset equipment based on multi-source image information; S3: Identify corona and arc occurring in power asset equipment based on multi-source image information and the multi-target positions; S4: Performing a life cycle assessment on the power asset equipment based on the corona and arc identification results.

[0007] The present invention also provides a cloud platform-based power asset lifecycle management system, the system comprising: Image acquisition device: the image acquisition device acquires multi-source image information of power asset equipment; Target recognition module: The target recognition module recognizes multiple target locations in the power asset equipment based on multi-source image information; Corona and arc recognition module: The corona and arc recognition module recognizes corona and arc occurring in power asset equipment based on multi-source image information and the multi-target positions; Life cycle assessment module: The life cycle assessment module performs a life cycle assessment on the power asset equipment based on the corona and arc identification results.

[0008] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned cloud platform-based power asset lifecycle management method when executing the computer program.

[0009] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned cloud platform-based power asset lifecycle management method.

[0010] Compared with the prior art, the present invention proposes a power asset lifecycle management method based on a cloud platform. The present invention obtains the location information of corona-prone locations in high-voltage switchgear based on visible light images, and effectively obtains the corona occurrence location by combining location priors and noise filtering. At the same time, visible light video information and ultraviolet image information are combined in arc detection. According to the arc development characteristics and the physical characteristics when it occurs, a multi-scale feature extraction network and an ultraviolet high-frequency information extraction module are designed to improve the accuracy of arc detection, and the life cycle of the equipment is evaluated based on the occurrence of corona and arc, thereby realizing efficient detection of hidden risks of power assets and realizing safe management and maintenance of power assets. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 It is a flow chart of the present invention for performing cloud platform-based power asset lifecycle management. DETAILED DESCRIPTION

[0013] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0014] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0015] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspect described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0016] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the examples can be practiced without these specific details.

[0017] The embodiment of this specification proposes a power asset lifecycle management method based on a cloud platform, which specifically includes the following steps: S1: Collect multi-source image information of power asset equipment; S2: Identify multiple target locations in power asset equipment based on multi-source image information; S3: Identify corona and arc occurring in power asset equipment based on multi-source image information and the multi-target positions; S4: Performing a life cycle assessment on the power asset equipment based on the corona and arc identification results.

[0018] The power asset equipment is specifically a high-voltage switchgear, and the multi-source image information includes visible light video and ultraviolet light image.

[0019] In the process of collecting specific multi-source image information, the visible light industrial camera preferably uses a high-speed industrial camera with a resolution of 1920×1080 pixels (1080P) or above and a frame rate of not less than 60 fps. The lens field of view is set between 90° and 120° to achieve a larger coverage range, and is equipped with an automatic aperture adjustment function to adapt to different lighting conditions in the switch cabinet. The ultraviolet imaging module preferably uses an ultraviolet sensor with a wavelength response range of 240nm to 280nm, and the sensitivity requirement is a minimum detectable ultraviolet signal power of 0.01 μW / cm², which can capture weak ultraviolet signals released by corona under strong ambient light conditions. The ultraviolet imaging module is equipped with a narrow-band filter to improve the response accuracy to the target ultraviolet signal.

[0020] In the process of selecting specific acquisition equipment, arc discharge is usually accompanied by strong light and heat, and its duration is short (milliseconds), but the light intensity is high. Therefore, the high frame rate and high dynamic range of the above-mentioned high-speed industrial camera can effectively record the rapid occurrence and disappearance of the arc, and capture its light intensity changes, arc length and expansion trend. In order to achieve accurate acquisition of arc transient discharge in high-voltage switchgear, for example, for shooting arc transient discharge, the high-speed industrial camera used can be PhotronFASTCAM Mini UX100 or Vision Research Phantom VEO 710. The former supports up to 4000 fps (resolution 1280×1024), while the latter supports 7000 fps (resolution 1280×800), which can capture the rapid optical dynamic changes of arc transient discharge and meet the needs of capturing arc strong light, arc light movement trajectory and duration.

[0021] The corona phenomenon is characterized by weak light intensity and uneven distribution, which is usually continuously released in the form of weak ultraviolet light on the surface of the insulator or the busbar joint area. Due to the weak characteristics of the corona signal, the equipment needs to have high sensitivity and narrow-band filtering function (ultraviolet bandwidth 2 nm) to accurately capture weak ultraviolet light and eliminate visible light interference. For the collection of corona phenomena, OFIL DayCor Superb or Corocam 8 UAV are used as examples. These two devices have high sensitivity and can detect ultraviolet light signals with a wavelength range of 240 nm to 280 nm. They also have good background noise suppression capabilities and are particularly suitable for corona monitoring under strong ambient light conditions.

[0022] The deployment location of the acquisition equipment is optimized based on the structural characteristics of the high-voltage switchgear and the occurrence law of the discharge phenomenon. The high-voltage switchgear consists of busbars, circuit breakers and terminals, among which arc discharge and corona discharge are mostly concentrated at the busbar connection points, circuit breaker joints, insulator surfaces and terminal areas. To achieve full coverage, the equipment is preferably installed at the top and side walls inside the switchgear. The visible light industrial camera is installed in the middle of the top of the switchgear, tilted downward by 30° to 45°, and the lens is aimed at the busbar connection points and circuit breaker joints to ensure that the key areas in the switchgear are within the field of view. The ultraviolet imaging module is preferably installed on the side wall of the switchgear, and the lens angle is adjusted to be perpendicular or slightly tilted to the target area to capture the clearest ultraviolet light signal. In order to avoid equipment obstruction or signal interference, the installation of the acquisition equipment needs to fully consider the spatial layout of the equipment inside the switchgear, and the outer shell of the acquisition equipment is insulated and protected to ensure that it can operate stably in high electromagnetic interference and high voltage environments.

[0023] To solve the problem of dark environment that may exist inside the high-voltage switch cabinet, this solution is equipped with low-interference LED lighting equipment. The lighting equipment uses a wide-spectrum LED light source, preferably with a wavelength range of 400nm to 700nm (visible light range) to avoid the ultraviolet spectrum interfering with the detection of the ultraviolet imaging module. LED lamps preferably use light sources with a high color rendering index (CRI ≥ 90) to ensure the uniformity and naturalness of the lighting light and avoid strong light spots or shadows. The lighting equipment is installed on the top or side wall of the switch cabinet and can be integrated with the visible light industrial camera to make the illumination direction consistent with the camera lens angle of view, thereby achieving the best lighting effect. To further reduce interference with ultraviolet detection, the LED lighting equipment can work in a controllable pulse mode, only lighting up for a short time when the visible light industrial camera collects video, and turning off when the ultraviolet imaging module collects images. In addition, the light intensity of the lighting equipment can be adjusted to meet the needs of different internal environment brightness of the switch cabinet.

[0024] The acquisition device realizes the synchronous acquisition of visible light video and ultraviolet light image through a preset acquisition program. During the acquisition process, the visible light industrial camera continuously records video at a preset frame rate to capture the optical characteristics of the dynamic arc inside the high-voltage switch cabinet in real time; the ultraviolet imaging module acquires static images in an interval shooting manner, which is mainly used to detect the distribution range and intensity of ultraviolet light of corona discharge. To ensure the synchronization of data, a unified timestamp can be set in the acquisition system to mark the time information of each frame of visible light video and each ultraviolet light image. The acquisition device transmits the collected data to the edge computing device through industrial Ethernet or wireless communication module for preliminary analysis. The edge computing device preferably uses a high-performance embedded computing platform (such as NVIDIA Jetson Xavier or Intel Movidius) to process the collected image data in real time, including denoising, enhancement and other operations, and the processed data is packaged and uploaded to the cloud platform for storage and analysis.

[0025] The data storage module of the cloud platform adopts a distributed database architecture. The data uploaded to the cloud platform is first authenticated and encrypted to ensure the security of data transmission. The cloud platform assigns a unique device number to each high-voltage switchgear and stores the collected data in the corresponding folder structure in chronological order. The storage module of the cloud platform automatically classifies and indexes the visible light video and ultraviolet image data to facilitate subsequent rapid retrieval and analysis. At the same time, the cloud platform will perform quality inspection on the uploaded data to eliminate invalid data caused by abnormal acquisition equipment or transmission errors. In order to save storage space, the visible light video can be compressed and the ultraviolet image can be stored in a high-quality lossless format to ensure the accuracy of subsequent analysis. The cloud platform is also equipped with data backup and disaster recovery functions, which regularly copies the collected data to a remote server to prevent data loss due to system failures.

[0026] Identify multiple target locations in power asset equipment based on multi-source image information, including identifying terminal blocks, busbar connection points, and insulators based on visible light video key frame images; key frame image recognition is implemented using the Yolo series network; Since the captured high-voltage switchgear is a static target, the main content of the video will not change. Therefore, the selection of key frames only needs to consider the quality of the image frame, which has no direct connection with the acquisition time. Therefore, the visible light video key frame can select the first frame of the video as the key frame or the video frame captured at a preset time point as the key frame. This application does not specifically limit the selection of key frames, and any frame in the visible light video can be used as a key frame.

[0027] Before inputting into the Yolo series network for recognition, the keyframes are first preprocessed and normalized by the preprocessing module to normalize the pixel values ​​to the [0,1] interval.

[0028] The feature extraction module of the Yolo series network used in the present invention adopts the improved CSPDarknet53 as the backbone network. The improved CSPDarknet53 extracts multi-scale features through cascaded convolutional layers and residual blocks, and can capture the image characteristics of the terminal, busbar connection point and insulator at different scales. For the terminal, its image characteristics are mainly regular metal structure, clear edges and small size, so 3×3 and 5×5 convolution kernels are added to the shallow features to enhance the edge feature extraction capability; for the busbar connection point, its image characteristics are obvious geometric shapes and are usually surrounded by insulators, so the local geometric information is extracted by combining the shallow and middle features; for the insulator, its image characteristics are strong symmetry, complex texture and single color, so the repeated texture pattern and symmetry are captured by the deep feature extraction module.

[0029] The specific feature extraction network structure is defined as follows: The characteristics of the terminal block are regular metal structure, clear edges, and small size. Feature extraction mainly relies on shallow features. 3×3 and 5×5 convolution kernels are used to extract edge information. The convolution operation is described as: ; and Respectively represent 3×3 and 5×5 convolution calculations, which are used to extract high-frequency edge features and larger-scale local features. The output Enhanced the ability to express terminal edge features in images. is the normalized key frame; The characteristics of busbar connection points are obvious geometric shapes and are usually surrounded by insulators. It is necessary to combine shallow and middle layer features to extract geometric information. Middle layer feature extraction is achieved through residual blocks: ; ; It means that after being processed by two residual modules, the output The residual block combines the detail information of shallow features and the geometric information of middle-level features to better express the position and shape of the busbar. The image characteristics of insulators are strong symmetry, complex texture, and single color. They mainly rely on deep feature extraction modules to capture their repeated texture patterns and symmetry. Deep feature extraction is achieved through further convolution and pooling operations: ; in, represents a 7×7 convolution kernel, which is used to capture a wide range of texture patterns and symmetries. The maximum pooling operation is used to reduce the size of the feature map and enhance the extraction of global information, outputting the feature Extracting expressions suitable for the global symmetry and repeated texture patterns of the insulator can capture the overall structural characteristics of the insulator; , and Input to the neck network of the Yolo series network for feature fusion, and then input to the prediction head for target classification and positioning; In the target classification and positioning module, the prediction head of the YOLO series detection framework is used to output the category and position coordinates of the target. The output of the prediction head includes category probability and bounding box parameters, where the category probability is calculated by the Softmax function, and the bounding box parameters include the center point coordinates (x, y) and width and height (w, h). The joint loss function including category loss, bounding box loss and confidence loss is used to optimize the model. The bounding box loss is calculated using CIoU loss (Complete IoU).

[0030] Based on the multi-source image information and the multi-target positions, the corona and arc occurring in the power asset equipment are identified, wherein the corona identification process specifically includes: S3-1-1: registering the visible light key frame with the ultraviolet light image; S3-1-2: Generate a target weight matrix according to the multi-target positions identified in step S2; S3-1-3: Combining UV image and target weight matrix for corona detection.

[0031] Among them, the target weight matrix generation process includes: For the jth target area in the UV image, take its center point Generate the corresponding Gaussian weight matrix : ; ; ; in, , is the proportional coefficient, which controls the reference value of the extended range; , is the width and height of the jth target area; is the shape correction factor, controlling the effect of aspect ratio on the extended range, , exp is the exponential function, and Represent the variance in x and y directions respectively; When the target area is very wide, expand the range horizontally Significantly larger and vertically extended range Keep it small due to aspect ratio constraints.

[0032] When the target area is very high, vertical expansion range will be significantly increased, and the horizontal expansion range, Keep the value small.

[0033] The horizontal and vertical expansion range formulas are symmetrical to each other, balancing the width and height characteristics of the target area and adapting to target areas of various shapes. This balance ensures that the Gaussian distribution can cover the key characteristics of the target area without unnecessary over-expansion.

[0034] Superimpose the Gaussian distribution weight functions of each target area to generate a global weight matrix ; ; α is the global scaling factor, which is used to adjust the overall strength of the weight matrix. is the minimum weight value of the non-target area, ensuring that the non-target area is not completely ignored, and M is the total number of target areas.

[0035] Combining UV images and target weight matrices for corona detection specifically includes: Calculate the collected multiple UV images Calculate the average brightness of the same pixel , extremely poor brightness and brightness standard deviation : ; ; ; ; ; and The brightest and darkest pixel values ​​of each pixel in all frames are extracted respectively. is the total number of UV images; Using the brightness characteristic map, filter out low brightness noise and fixed noise, and extract candidate corona areas , ; ； ; ; in, , , , are threshold parameters, , are the filter masks, is the initial candidate corona region; Corona and noise show significant differences in ultraviolet images, mainly in terms of brightness dynamics, spatial distribution characteristics, and temporal stability. Corona is usually a discharge phenomenon caused by an excessively strong local electric field on the surface of high-voltage equipment. Its bright spots appear as bright areas in the image and have certain dynamic fluctuations. This fluctuation includes changes in brightness and temporal intermittency, that is, the corona bright spots may disappear or weaken in some frames, but in multi-frame images, their positions are generally relatively stable. In addition, corona is usually concentrated in specific high-risk areas (such as wiring terminals, busbar connection points, insulators, etc.), and has certain brightness attenuation characteristics: the center brightness is high, and the edge brightness gradually decreases, showing a diffuse spatial distribution characteristic. In contrast, noise can be divided into two types: fixed noise and random noise. The brightness of fixed noise is highly stable in multi-frame images, with almost no changes. Typical examples are sensor defects or background light interference. Random noise is usually caused by the external environment (such as thermal noise or accidental light interference). Its brightness and position change irregularly between frames, usually appearing in isolation, and does not have the spatial concentration and persistence of corona. Random noise may suddenly increase in brightness in a certain frame, but its overall volatility is small and will not persist. Based on these characteristics, the present invention constructs an effective filtering logic to distinguish corona bright spots from noise. First, we define the candidate areas of corona bright spots as those pixels with high brightness and significant volatility in multiple frames. By calculating the brightness range and standard deviation of each pixel, the dynamic change characteristics of the bright spot can be captured. The range is used to measure the maximum amplitude of brightness change, while the standard deviation is used to quantify the overall volatility of brightness. In order to avoid false detection, both the large brightness range and high standard deviation must be met at the same time to be judged as a corona bright spot; if only a single condition is met, it may be a noise point. For example, the brightness of a fixed noise point is almost unchanged in multiple frames, and its range and standard deviation are small, so it can be eliminated; while the brightness of a random noise point occasionally increases in a certain frame, which may lead to a large range, but because it changes less in other frames, the standard deviation is usually low, so it can also be filtered. Finally, we combine the global weight matrix to give higher weights to key areas (such as wiring terminals) so that they are more easily retained in judgment, while non-key areas require more stringent filtering conditions. This logic, based on brightness dynamics, temporal stability and spatial distribution characteristics, can effectively distinguish between corona and noise, minimizing the risk of false detection and missed detection.

[0036] Based on the multi-source image information and the multi-target positions, the corona and arc occurring in the power asset equipment are identified, wherein the arc identification is realized by using a dual-channel identification network; The dual-channel recognition network is divided into a visible light video channel and an ultraviolet light image channel; The visible light video channel extracts the collected video images and performs differential calculation on the video images to extract the arc image sequence. : ; ; ; ; in, is the inter-frame difference intensity, , are the grayscale images of the tth and t-1th frames of the visible light video, H and W are the image height and width scales, is the arc index collection; Extracting the ultraviolet light image collected during the arc occurrence period as a key frame according to the arc image sequence, and when the corresponding ultraviolet light image is not collected during the arc occurrence period, extracting the last ultraviolet light image collected before the arc occurs as the key frame; The dual-channel recognition network is divided into three stages of feature extraction, where the first and third stage feature extraction modules are the same: ; ; ; ; in, and Represent the characteristic graphs of the first or third stage of the visible light channel and the ultraviolet light channel, and Corresponding to the second stage feature map of the visible light channel and ultraviolet light channel, To stitch by channel, is the input feature map of the first or third stage of the visible light channel, where the first stage input feature map is the differential image of the arc image sequence, and the third stage input feature map is , is the input feature map of the first or third stage of the UV channel, where the first stage input feature map is the weighted fusion of the UV keyframe and the candidate corona region, and the third stage input feature map is ; The dual-channel recognition network also includes three feature fusion stages, which are used to extract the visible light feature map and ultraviolet light feature map obtained from the three-stage feature extraction: Perform attention enhancement on the visible light feature map before fusion: In arc detection, the visible light video channel extracts multi-scale information from the image because the visible light representation of the arc may have different spatial scales and morphological characteristics, which may show significant differences in actual scenes due to distance, ambient lighting, and the intensity and development stage of the arc. The arc may appear in visible light video as a small and concentrated bright spot to a large diffuse halo, and may even be accompanied by complex dynamic changes, such as bright and dark flickering or diffusion. Therefore, information extraction at a single scale may not fully capture these features. For example, small-scale features help detect the initial concentration point of the arc, while large-scale features can capture the overall halo distribution or occlusion phenomenon when the arc spreads. In addition, visible light video is also affected by ambient light interference. For example, other bright spots in the background (such as reflections or lights) may be similar to the visual characteristics of the arc at a certain scale, but multi-scale analysis can more comprehensively capture the significant changes of the arc at different spatial scales, thereby enhancing the robustness to background interference.

[0037] ; At each scale s, the contextual relationship in the feature sequence is captured through a multi-head self-attention mechanism: ; ; ; ; ; ; ; Will The output of the attention heads is concatenated and the feature dimension is restored through linear mapping: ; ; For each scale 𝑠, the features of other scales 𝑠′ are used as Key and Value to perform cross-scale attention: ; ; By splicing and fusing features of all scales, we get the kth stage visible light features to be fused ; ; PatchEmbed(⋅) is a block embedding function. The feature map is obtained by feature extraction for the kth stage, k=1,2,3; represents the s-th resolution feature map, is a multi-scale feature sequence, totaling indivual, , and The projection matrix is ​​used to calculate the values ​​of Query, Key, and Value respectively; is the dimension of each attention head, is the output of the h-th attention head h=1,2,…, ; and Represent the normalization layer and the fully connected layer respectively; Before fusion, high-frequency information enhancement is performed on the UV feature map: ; ; Fusion of enhanced visible light feature map and ultraviolet light feature map: ; In arc detection, the ultraviolet image channel extracts high-frequency information because the occurrence of arcs is usually accompanied by obvious spatial texture changes and local intensity mutations, and these features are mainly concentrated in the high-frequency part of the image. High-voltage arc discharge is a localized and high-intensity phenomenon, which manifests itself as a light spot or highlight area with significant edges in the ultraviolet band, and has a significant contrast difference with the background ultraviolet radiation. This difference usually exists in the image in the form of high-frequency components. By extracting this high-frequency information, the edges and detail features of the arc area can be more effectively highlighted, while suppressing the low-frequency components in the background (such as uniformly distributed ambient ultraviolet noise or slowly changing radiation on the surface of the equipment). Extracting high-frequency information can effectively filter out these irrelevant or weakly correlated low-frequency components, focusing on the significant features of arc discharge, thereby improving the accuracy and robustness of arc detection. In this way, the ultraviolet image channel can not only capture the physical characteristics of the arc, but also distinguish it from the background environment. The three scales after fusion , and Input it into Yolov8's Head detection head to obtain the arc location area information.

[0038] In the arc detection of high-voltage switchgear, the present application combines the dual-modal information of visible light video sequence frames and ultraviolet images. The visible light video sequence frames can intuitively capture the bright spots or sparks when the arc occurs, which is a direct visual manifestation of arc discharge. Visible light imaging is easy to implement, the imaging is clear, and its video sequence can provide continuity in the time dimension, which is helpful for analyzing the dynamic behavior of the arc. On the other hand, ultraviolet images provide arc-related information in the ultraviolet band, especially the ultraviolet radiation characteristics when the arc occurs, which is a very important physical feature in arc detection. High-voltage arcs are usually accompanied by strong ultraviolet radiation, and ultraviolet imaging can effectively capture this feature while avoiding ambient light interference in the visible light band. Therefore, ultraviolet images have a certain robustness under complex lighting conditions. In addition, in the early stage before the arc occurs, ultraviolet imaging can also capture precursor signals such as corona discharge, which are precursor phenomena of arc discharge. Fusion of the dual-channel information of visible light and ultraviolet images can give full play to the complementary advantages of the two modes. UV images can provide the physical characteristics of arc discharge, while visible light videos can intuitively present the dynamic behavior and visual characteristics of arcs. By fusing the information of the two modalities, a more comprehensive arc detection model can be established in the spatial and temporal dimensions, while verifying each other, thereby helping to reduce the false detection rate.

[0039] The life cycle assessment of the power asset equipment based on the corona and arc identification results specifically includes: S4-1: Counting the corona occurrence area information and arc occurrence area information respectively; S4-2: Calculate the discrete distribution of corona generation and the discrete distribution of arc generation; S4-3: Determine whether the corona generation location area and the arc generation location area overlap; S4-4: Life cycle assessment based on the number of corona and arc occurrences, distribution dispersion and number of coincidences; When the discrete distribution of corona occurrence is greater than the preset threshold, it indicates that the corona phenomenon is widely distributed and the equipment may have multiple insulation deterioration. Arcs are usually more concentrated than corona. When the discrete distribution of arc occurrence is greater than the preset threshold, it indicates that the equipment has serious local fault diffusion. When the number of overlaps between the corona occurrence location area and the arc occurrence location area is greater than the threshold, it indicates that the insulation degradation of the equipment has developed to a serious level.

[0040] The present invention also provides a cloud platform-based power asset lifecycle management system, the system comprising: Image acquisition device: the image acquisition device acquires multi-source image information of power asset equipment; Target recognition module: The target recognition module recognizes multiple target locations in the power asset equipment based on multi-source image information; Corona and arc recognition module: The corona and arc recognition module recognizes corona and arc occurring in power asset equipment based on multi-source image information and the multi-target positions; Life cycle assessment module: The life cycle assessment module performs a life cycle assessment on the power asset equipment based on the corona and arc identification results.

[0041] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned cloud platform-based power asset lifecycle management method when executing the computer program.

[0042] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned cloud platform-based power asset lifecycle management method.

[0043] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0044] In this specification, the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments described later, the description is relatively simple, and the relevant parts can be referred to the partial description of the previous embodiments.

[0045] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A power asset lifecycle management method based on a cloud platform, characterized in that: The method comprises the following steps: S1: Collect multi-source image information of power asset equipment; S2: Identify multiple target locations in power asset equipment based on multi-source image information; S3: Identify corona and arc occurring in power asset equipment based on multi-source image information and the multi-target positions; S4: Performing a life cycle assessment on the power asset equipment based on the corona and arc identification results; The corona identification process specifically includes: S3-1-1: registering the visible light key frame with the ultraviolet light image; S3-1-2: Generate a target weight matrix according to the multi-target positions identified in step S2; S3-1-3: Combining UV image and target weight matrix for corona detection.

2. According to the cloud platform-based power asset lifecycle management method of claim 1, it is characterized in that: The identification of multiple target positions specifically includes identifying wiring terminals, busbar connection points, and insulators based on visible light video key frame images.

3. The power asset lifecycle management method based on a cloud platform according to claim 1 is characterized in that: For the jth target area in the UV image, take its center point Generate the corresponding Gaussian weight matrix : ; ; ; in, , is the proportionality coefficient, , is the width and height of the jth target area; is the shape correction factor, exp is the exponential function, and Represent the variance in the x and y directions respectively; Superimpose the Gaussian distribution weight functions of each target area to generate a global weight matrix ; ; α is the global scaling factor, is the minimum weight value of non-target areas, and M is the total number of target areas.

4. The power asset lifecycle management method based on a cloud platform according to claim 3 is characterized in that: Combining UV images and target weight matrices for corona detection specifically includes: Calculate the collected multiple UV images Calculate the average brightness of the same pixel , extremely poor brightness and brightness standard deviation : Using the brightness characteristic map, filter out low brightness noise and fixed noise, and extract candidate corona areas , ； ； ; ; in, , , , are threshold parameters, , are the filter masks, is the initial candidate corona region.

5. The method for managing the life cycle of power assets based on a cloud platform according to claim 4, characterized in that: Arc recognition is implemented using a dual-channel recognition network; the dual-channel recognition network is divided into three stages of feature extraction, where the first and third stage feature extraction modules are the same: ; ; ; ; in, and Represent the characteristic graphs of the first or third stage of the visible light channel and the ultraviolet light channel, and Corresponding to the second stage feature map of the visible light channel and ultraviolet light channel, is the input feature map of the first or third stage of the visible light channel, where the first stage input feature map is the differential image of the arc image sequence, and the third stage input feature map is , is the input feature map of the first or third stage of the UV channel, where the first stage input feature map is the weighted fusion of the UV keyframe and the candidate corona region, and the third stage input feature map is , To stitch by channel, and They are average pooling and maximum pooling, is the activation function, Represents a 3×3 convolution calculation.

6. The power asset lifecycle management method based on a cloud platform according to claim 1, characterized in that: The dual-channel recognition network also includes three feature fusion stages, which are used to extract the visible light feature map and ultraviolet light feature map obtained by the three-stage feature extraction.

7. A cloud-based power asset lifecycle management system, characterized in that: The system is used to execute a cloud platform-based power asset lifecycle management method as described in any one of claims 1 to 6, and the system includes: Image acquisition device: the image acquisition device acquires multi-source image information of power asset equipment; Target recognition module: The target recognition module recognizes multiple target locations in the power asset equipment based on multi-source image information; Corona and arc recognition module: The corona and arc recognition module recognizes corona and arc occurring in power asset equipment based on multi-source image information and the multi-target positions; Life cycle assessment module: the life cycle assessment module performs life cycle assessment on the power asset equipment based on the corona and arc identification results; The corona identification process specifically includes: S3-1-1: registering the visible light key frame with the ultraviolet light image; S3-1-2: Generate a target weight matrix according to the multi-target positions identified in step S2; S3-1-3: Combining UV image and target weight matrix for corona detection.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for managing the lifecycle of power assets based on a cloud platform is implemented.

9. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements a cloud platform-based power asset lifecycle management method as described in any one of claims 1 to 6.

Images