A multi-parameter integrated ultraviolet image defect assessment system and method for power external insulation equipment

Abstract

The present invention belongs to the technical field of power systems, and discloses a multi-parameter integrated ultraviolet image defect assessment system for external insulation equipment of electric power, comprising: a visible light channel positioning information extraction network for obtaining equipment area information; ultraviolet channel spot information for extracting ultraviolet discharge spot information; a photoelectric detection module for obtaining parameters that affect the spot area captured by the ultraviolet imager; and an assessment network that fuses the information extracted by the visible light channel positioning information extraction network, the ultraviolet channel spot information extraction network, and the photoelectric detection module to obtain the final assessment result. The assessment system of the embodiment of the present invention can effectively eliminate the influence of various factors such as noise, small spot, humidity, detection distance, etc., and provides a reliable judgment basis for defect diagnosis of ultraviolet images. The embodiment of the present invention also provides a multi-parameter integrated ultraviolet image defect assessment method for external insulation equipment of electric power.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a multi-parameter integrated ultraviolet image defect assessment system and method for power external insulation equipment. Background Art

[0002] In recent years, solar-blind UV imagers, designed to detect ultraviolet light generated by corona discharge, have begun to be used in discharge detection for high-voltage power equipment. Solar-blind UV imaging technology can detect ultraviolet light in the 240-280nm band generated by discharge radiation while simultaneously shielding against interference from solar UV. Compared to other detection methods, such as infrared imaging, ultrasonic partial discharge detection, and leakage current detection, UV imaging offers a more intuitive approach to corona discharge detection. It can provide real-time corona discharge status monitoring for live high-voltage power equipment while maintaining a safe distance.

[0003] The imaging system of the solar-blind UV imager consists of a visible light imaging channel and an ultraviolet imaging channel. The beam splitter inside the instrument splits the incident light signal into two light signals, one of which directly enters the visible light channel to form a visible light image; the other light signal enters the ultraviolet light channel to image the discharge luminous area. The instrument uses an image fusion algorithm to superimpose the ultraviolet image on the visible light image, thereby showing the discharge location. Figure 1a is the visible light channel image, Figure 1b is the UV channel image, Figure 1c It is the fused image after superimposing the two.

[0004] Actual field applications show that when a solar-blind ultraviolet imager is used to inspect high-voltage power equipment, due to the presence of ultraviolet light scattering and inherent noise, continuous discrete small-area ultraviolet light spots will appear on the ultraviolet imager display, which will be counted in the ultraviolet imager's photon counting area, causing inspectors using the ultraviolet imager to misjudge the discharge intensity.

[0005] Therefore, how to effectively and quantitatively evaluate the degree of UV image defects of external insulation equipment of power equipment is an urgent problem to be solved. Summary of the Invention

[0006] To address the aforementioned shortcomings of the prior art, embodiments of the present invention provide a multi-parameter UV image defect assessment system for power external insulation equipment. To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is provided below. This summary is not intended to be a comprehensive review, identify key or important elements, or delineate the scope of protection for these embodiments. Its sole purpose is to present some concepts in a simplified form, serving as a prelude to the detailed description that follows.

[0007] According to a first aspect of an embodiment of the present invention, a multi-parameter integrated ultraviolet image defect assessment system for power external insulation equipment is provided.

[0008] In one embodiment, the multi-parameter integrated UV image defect assessment system for power external insulation equipment includes:

[0009] Visible light channel positioning information extraction network, ultraviolet channel spot information extraction network, photoelectric detection module and evaluation network;

[0010] Among them, the visible light channel positioning information extraction network receives the visible light channel image output by the ultraviolet imager and uses the neural network model to detect the location of the external insulation equipment to obtain the equipment area information;

[0011] The ultraviolet channel spot information extraction network is used to input the ultraviolet channel image output by the ultraviolet imager into the neural network model, segment the ultraviolet discharge spot, and obtain the ultraviolet discharge spot information;

[0012] The photoelectric detection module is used to obtain parameters that affect the area of ​​the light spot captured by the ultraviolet imager;

[0013] The evaluation network integrates the information extracted by the visible light channel positioning information extraction network, the ultraviolet channel spot information extraction network, and the photoelectric detection module to obtain the final evaluation result.

[0014] Optionally, the equipment area information of the tested power external insulation equipment obtained by the visible light channel positioning information extraction network includes: body area location information, fitting area location information, and body area area.

[0015] Optionally, the ultraviolet discharge spot information includes: the area of ​​the spot region, the area of ​​the overlapping region with the device under test, and the coordinates of the center point of the spot region.

[0016] Optionally, the coordinates of the center point of the light spot area represent the center position of the discharge.

[0017] Optionally, the area of ​​the light spot region is obtained according to the number of pixels in the largest light spot region.

[0018] Optionally, the spot area is increased by B times for every 10% increase in gain. The standard gain value is set to q, and the spot area is equivalent to the equivalent spot area under the gain q, as follows:

[0019]

[0020] Where A is the area of ​​the detected light spot and the gain is p.

[0021] Optionally, the equivalent spot area is normalized to the distance D, where the unit of D is m, and the final equivalent spot area is

[0022]

[0023] d is the actual detection distance, in meters.

[0024] Optionally, the evaluation network is configured to determine the state of the power external insulation device according to the number of photons output by the ultraviolet imager.

[0025] Optionally, the evaluation network is specifically configured as follows: when the number of photons is less than a set threshold, the evaluation network judges that the state of the external power insulation device is normal; when the number of photons is greater than or equal to the set threshold, the evaluation network judges that the state of the external power insulation device is abnormal.

[0026] Optionally, the evaluation network is specifically configured to: for an abnormal situation, determine that the state of the external power insulation equipment is low-intensity discharge based on the discharge position being on the hardware.

[0027] Optionally, the evaluation network is specifically configured to: for abnormal situations, based on the discharge location on the body, further determine the discharge intensity of the power external insulation equipment based on the discharge area ratio; the discharge area ratio is:

[0028]

[0029] Where, is the final equivalent spot area calculated by the overlapping area A2, A e is the area of ​​the main body.

[0030] According to a second aspect of an embodiment of the present invention, a method for evaluating defects of an external insulation device using ultraviolet images integrating multiple parameters is provided.

[0031] In one embodiment, the multi-parameter integrated UV image defect assessment method for power external insulation equipment includes the following steps:

[0032] Extract equipment area information of power external insulation equipment;

[0033] The ultraviolet channel image output by the ultraviolet imager is input into the neural network model to segment the ultraviolet discharge spot and obtain the ultraviolet discharge spot information;

[0034] Detect parameter information that affects the spot area captured by the UV imager;

[0035] The equipment area information, UV discharge spot information and parameter information are integrated to obtain the final evaluation result.

[0036] Optionally, the method determines the state of the power external insulation device based on the number of photons output by the ultraviolet imager.

[0037] Optionally, if the number of photons is less than a set threshold, the state of the power external insulation device is determined to be normal;

[0038] If the number of photons is greater than or equal to the set threshold, the state of the power external insulation device is judged to be abnormal;

[0039] For abnormal situations, if the discharge location is on the hardware, the state of the power external insulation equipment is judged to be low-intensity discharge; if the discharge location is on the body, the discharge intensity of the power external insulation equipment is further judged based on the proportion of the discharge area; the proportion of the discharge area is:

[0040]

[0041] According to a third aspect of an embodiment of the present invention, a solar-blind ultraviolet imager is provided.

[0042] In one embodiment, the solar-blind ultraviolet imager comprises the system described in any one of the above embodiments.

[0043] According to a fourth aspect of embodiments of the present invention, a computer device is provided.

[0044] In one embodiment, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method described in any one of the above embodiments when executing the computer program.

[0045] The present invention has the following beneficial effects:

[0046] The present invention proposes a multi-parameter integrated ultraviolet image defect assessment system and method for external insulation equipment of electric power. Unlike traditional methods that rely on photon counts and descriptive judgment criteria, the present invention combines multiple neural networks to automatically extract discharge information related to external insulation equipment in steps, and obtains clear diagnostic rules through decision trees. It can effectively eliminate the influence of various factors such as noise, small light spots, humidity, and detection distance, providing a reliable judgment basis for defect diagnosis of ultraviolet images, and is of great value for the quantitative diagnosis of ultraviolet image defects of external insulation equipment of electric power.

[0047] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0049] Figure 1a It is the visible light channel image of the solar-blind ultraviolet imager;

[0050] Figure 1b It is the UV channel image of the solar-blind UV imager;

[0051] Figure 1c It is a fusion image of a solar-blind ultraviolet imager;

[0052] Figure 2 is a schematic diagram of an evaluation system according to an exemplary embodiment;

[0053] Figure 3 is a schematic diagram showing a discharge position determination principle according to an exemplary embodiment;

[0054] Figure 4 is a schematic diagram showing the overlapping area of ​​the light spot area and the device area according to an exemplary embodiment;

[0055] Figure 5 is a diagram showing a principle of defect classification rules according to an exemplary embodiment;

[0056] Figure 6 is a schematic structural diagram of an ultraviolet channel spot information extraction network according to an exemplary embodiment;

[0057] Figure 7 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0058] The following description and accompanying drawings sufficiently illustrate the specific embodiments herein to enable those skilled in the art to practice them. Portions and features of some embodiments may be included in or substituted for portions and features of other embodiments. The scope of the embodiments herein includes the entire scope of the claims, including all available equivalents thereof. Herein, the terms "first," "second," and the like are used solely to distinguish one element from another and do not require or imply any actual relationship or order between these elements. In practice, the first element can also be referred to as the second element, and vice versa. Furthermore, the terms "comprise," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a structure, device, or apparatus comprising a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such structure, device, or apparatus. Without further limitation, an element defined by the phrase "comprising a..." does not preclude the presence of other identical elements in the structure, device, or apparatus comprising the element. The various embodiments herein are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Similar or identical parts between the various embodiments can be referenced to each other.

[0059] The terms "longitudinal", "transverse", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like used herein to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are intended only to facilitate the description of this document and simplify the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the present invention. In the description herein, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, they can be mechanical or electrical connections, or they can be internal connections between two elements, they can be directly connected, or they can be indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to the specific circumstances.

[0060] As used herein, unless otherwise specified, the term "plurality" means two or more.

[0061] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0062] In this article, the term "and / or" is used to describe the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0063] Figure 2 An embodiment of the present invention's ultraviolet image defect assessment system for power external insulation equipment integrating multiple parameters is shown.

[0064] In this embodiment, a multi-parameter UV image defect assessment system for external power insulation equipment includes a visible light channel positioning information extraction network, an UV channel spot information extraction network, a photoelectric detection module, and an assessment network. The external insulation equipment primarily includes insulators, bushings, and other equipment, with insulators being particularly important.

[0065] The visible light channel positioning information extraction network receives visible light channel images from the UV imager and uses a neural network model (such as the SSD deep learning model) to detect the location of external insulation equipment and extract equipment area information. The equipment area consists of two main areas: the main body and hardware. This provides important information for determining the type of external insulation equipment causing discharge and the severity of the discharge. Hardware includes metal parts such as connectors and grading rings.

[0066] The visible light channel location information extraction network extracts device area information for the tested external power insulation equipment, including the main body area location information, the hardware area location information, and the main body area area (Ae). The main body area and hardware area are detected using a neural network model and represented by a detection box. Therefore, the main body area location information and hardware area location information may include vertex coordinates, center point coordinates, inclination angle, length and width, and other information.

[0067] The UV channel spot information extraction network is used to input the UV channel image output by the UV imager into a neural network model, such as a fully convolutional neural network model, to segment the UV discharge spot and obtain UV discharge spot information. The extracted UV discharge spot information includes the spot area, the area of ​​overlap with the device under test, and the coordinates of the area's center point, Xc. The segmentation result of the spot area is an irregular binary region. The relevant attributes of this region are used to calculate the area of ​​overlap with the device under test and further determine whether the coordinates of the spot area's center point, Xc, fall within the device.

[0068] The coordinates Xc of the center point of the spot area represent the center of the discharge. By comparing the coordinates of the center point Xc of the spot area with the device area extracted by the visible light channel, the relative position of the coordinates of the center point Xc of the spot area to the device area and the hardware area can be divided into the following three situations: in the device area, in the hardware area, and outside the device. The situations of in the device area and in the hardware area can be directly determined by determining whether the coordinates of the center point Xc of the spot area fall within the corresponding area.

[0069] When the coordinate Xc of the center point of the spot area is outside the device, it is necessary to determine whether the discharge position is on the device body or the hardware based on the relative position relationship between the coordinate Xc of the center point of the spot area and the device body or the hardware. For example, Figure 3 As shown, X1 = (x1, y1) is the coordinate of the center point of the body area, and X2 = (x2, y2) is the coordinate of the center point of the hardware area. The two coordinates can be directly obtained through the vertex coordinates. (x c ,y c ) is the coordinate Xc of the center point of the spot area.

[0070]

[0071]

[0072] When d1<d2, the discharge position can be equivalently considered to be in the body area, otherwise it is in the hardware position.

[0073] Optionally, the area of ​​the light spot region is obtained according to the number of pixels in the largest light spot region.

[0074] The spot area A1 is used to equivalently represent the discharge intensity.

[0075] The calculation of the area of ​​the overlapping area with the device under test needs to be obtained by comparing the spot area and the body area. If the discharge position is in the hardware area, the overlapping area is 0. Only when the discharge position is in the body area does it need to be calculated, such as Figure 4 By using the visible light channel positioning information to extract the detection information of the device in the network, the overlapping area of ​​the light spot area and the device area can be calculated, that is, the overlapping area A2 with the device under test, which represents the coverage area of ​​the discharge area on the device.

[0076] The photoelectric detection module is used to obtain parameters that affect the light spot area, such as contamination level, gain, observation distance, and humidity, to eliminate the influence of these factors on the light spot area. Contamination level is determined based on the pollution level of the detection location. Gain and observation distance are instrument measurement parameters. Humidity is measured using a hygrometer or a sensor module installed on the instrument.

[0077] Assume that the spot area increases by B times for every 10% increase in gain. To eliminate the influence of gain on the final detected spot area, assume that the detected spot area is A (obtained based on the number of pixels in the maximum spot area), the gain is p, and the standard gain value is q. The spot area is then converted to the equivalent spot area under the gain q, as follows:

[0078]

[0079] For example, for every 10% increase in gain, the spot area increases by 1.5 to 2 times. To eliminate the influence of gain on the final detected spot area, assuming that the detected spot area is A and 70% is the standard gain value, the spot area is equivalent to the equivalent spot area under 70% gain, as follows:

[0080]

[0081] Furthermore, the spot area of ​​the ultraviolet channel and the main image size of the visible light channel decrease in approximately the same proportion as the observation distance increases. In order to eliminate the influence of the observation distance on the final detected spot area, the relationship between the spot area and the detection distance under the standard gain value can be approximated as a proportional change relationship between the spot area and the detection distance based on the pinhole imaging principle. Assuming that the actual detection distance is d, the spot area is further normalized to the distance D, and the unit of D is m. The final equivalent spot area is:

[0082]

[0083] For example, if the spot area is further normalized to 10m, the final equivalent spot area is:

[0084]

[0085] Define r as the proportion of discharge area

[0086]

[0087] is the final equivalent spot area calculated by the overlapping area A2, A e is the area of ​​the main body.

[0088] The evaluation network integrates the information extracted by the above-mentioned visible light channel positioning information extraction network, ultraviolet channel spot information extraction network, and photoelectric detection module, and combines historical data and decision trees to obtain the final classification results.

[0089] The evaluation system of the present embodiment uses test data under different test conditions to obtain diagnostic rules. For example, 2,000 images are selected. The test equipment information in each image can be obtained from the device under test, such as the device type (porcelain insulator, composite insulator, bushing, etc.). The selected images are manually classified into defect levels by an experienced team of experts. The principle of manual labeling is to judge the defect level based on expert experience, and the defect level is divided into four levels: normal, low-intensity discharge under abnormal conditions, medium-intensity discharge, and high-intensity discharge.

[0090] First, through the visible light channel positioning information extraction network, the ultraviolet channel spot information extraction network, and the photoelectric detection module, the three parameters of the ultraviolet image, namely the number of photons, the discharge position, and the proportion of the discharge area, can be obtained. Since the discharge position is a descriptive parameter, it is necessary to add attribute tags as shown in Table 1 below.

[0091] Table 1

[0092]

[0093] When there is no discharge spot in the UV channel, the photon count is 0 and the default discharge position is set to 0.

[0094] Combining the parameters automatically obtained from 2000 images and the manually marked defect grade labels, the defect classification rules were obtained by training using the decision tree algorithm.

[0095] The classification rules obtained by the ID3 algorithm are as follows Figure 5 As shown, the evaluation network first determines the status of the power external insulation device based on the photon count. If the photon count is less than a set threshold, it is considered normal; if the photon count is greater than or equal to the threshold, it is considered abnormal. For example, if the threshold is set to 100, a photon count less than 100 is considered normal, while a photon count greater than or equal to 100 is considered abnormal. Of course, the above classification rules also apply to other algorithms.

[0096] Next, the evaluation network combines the equipment area information of the power external insulation equipment extracted by the visible light channel positioning information extraction network and the ultraviolet discharge spot information extracted by the ultraviolet channel spot information extraction network to obtain the final classification result.

[0097] Specifically, if the discharge location is on the hardware, it is determined to be a low-intensity discharge.

[0098] For discharges located on the body, the discharge intensity is determined based on the discharge area ratio. When the discharge area ratio is greater than or equal to the first threshold, it's considered a high-intensity discharge; when the discharge area ratio is less than the second threshold, it's considered a low-intensity discharge; and when the discharge area ratio is less than the first threshold but greater than or equal to the second threshold, it's considered a medium-intensity discharge. For example, if r < 0.15, it's considered a low-intensity discharge; if r ≥ 0.5, it's considered a high-intensity discharge; and if 0.15 ≤ r < 0.5, it's considered a medium-intensity discharge.

[0099] In one embodiment, the visible light channel positioning information extraction network uses YOLO-V3 to better identify horizontal or vertical insulators in an image. Therefore, when selecting the insulator device location information for the visible light channel, the YOLO-V3 model is used to provide the location information of horizontal or vertical insulators in the image, and the R2CNN model is used to provide the location information of tilted insulators in the image. Furthermore, in the automatic selection of the background algorithm of the visible light channel positioning information extraction network, the width W2 of the prediction box generated by YOLO-V3 is compared with the width W1 of the prediction box generated by the R2CNN model. If W1 = W2, the insulator is determined to be in a non-tilted orientation, and the location information provided by the YOLO-V3 model is used; if W1 < W2, the insulator is determined to be in a tilted orientation, and the location information provided by the R2CNN model is used.

[0100] In one embodiment, the UV channel spot information extraction network achieves pixel-level binary classification of the main UV discharge spots in the input UV image and non-discharge main spots (primarily small UV noise spots) in the UV image. Specifically, the UV channel spot information extraction network replaces the fully connected layers in the convolutional neural network with convolutional layers through a fully convolutional neural network, and simultaneously upsamples the feature map of the last convolutional layer to restore it to the same size as the input image. While retaining the spatial information of the original input image, each pixel of the input is classified and a predicted value is output, achieving segmentation and extraction of the largest discharge spot. Figure 6 An embodiment of the overall structure of a fully convolutional neural network is shown.

[0101] In one embodiment, a multi-parameter integrated ultraviolet image defect assessment method for power external insulation equipment is provided, comprising the following steps:

[0102] Obtain equipment area information of power external insulation equipment;

[0103] The ultraviolet channel image output by the ultraviolet imager is input into the neural network model to segment the ultraviolet discharge spot and extract the ultraviolet discharge spot information;

[0104] Obtain parameters that affect the spot area captured by the ultraviolet imager;

[0105] The equipment area information, UV discharge spot information and parameter information are integrated to obtain the final evaluation result.

[0106] The working principle of the evaluation method in this embodiment is the same as the working principle of the evaluation system in the above embodiment, and will not be repeated here.

[0107] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment are implemented.

[0108] Those skilled in the art will understand that Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0109] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiment when executing the computer program.

[0110] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0111] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program. 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 by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0112] The present invention is not limited to the structures described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A multi-parameter integrated ultraviolet image defect assessment system for power external insulation equipment, characterized by: include: Visible light channel positioning information extraction network, ultraviolet channel spot information extraction network, photoelectric detection module and evaluation network; Among them, the visible light channel positioning information extraction network receives the visible light channel image output by the ultraviolet imager, uses the neural network model to detect the location of the external insulation equipment, and obtains the equipment area information; The ultraviolet channel spot information extraction network is used to input the ultraviolet channel image output by the ultraviolet imager into the neural network model, segment the ultraviolet discharge spot, and obtain ultraviolet discharge spot information, wherein the ultraviolet discharge spot information includes: the area of ​​the spot region, the area of ​​the overlapping area with the device under test, and the coordinates of the center point of the spot region; the spot area is equivalent to the equivalent spot area under the gain q; and the spot area is further normalized to the distance D; The photoelectric detection module is used to obtain parameters that affect the area of ​​the light spot captured by the ultraviolet imager; The evaluation network integrates the information extracted by the visible light channel positioning information extraction network, the ultraviolet channel spot information extraction network, and the photoelectric detection module to obtain the final evaluation result; Define r as the proportion of the discharge area, Where, is the final equivalent spot area calculated based on the overlapping area A2, A e is the area of ​​the main body; The evaluation network first determines the status of the external power insulation equipment based on the number of photons; if the number of photons is less than the set threshold, it is judged to be normal; if the number of photons is greater than or equal to the set threshold, it is judged to be abnormal; next, if the discharge location is on the hardware, it is judged to be low-intensity discharge; if the discharge location is on the main body, the discharge intensity is judged based on the proportion of the discharge area; when the proportion of the discharge area is greater than or equal to the first set threshold, it is judged to be high-intensity discharge; when the proportion of the discharge area is less than the second set threshold, it is judged to be low-intensity discharge; when the proportion of the discharge area is less than the first set threshold and greater than or equal to the second set threshold, it is judged to be medium-intensity discharge.

2. The multi-parameter UV image defect assessment system for power external insulation equipment according to claim 1, characterized in that: The equipment area information of the tested power external insulation equipment acquired by the visible light channel positioning information extraction network includes: main body area position information, hardware area position information, and main body area area.

3. The multi-parameter UV image defect assessment system for power external insulation equipment according to claim 1, characterized in that: The coordinates of the center point of the light spot area represent the center position of the discharge.

4. The multi-parameter integrated ultraviolet image defect assessment system for power external insulation equipment according to claim 1, characterized in that: The area of ​​the light spot region is obtained according to the number of pixels in the largest light spot region.

5. The multi-parameter integrated ultraviolet image defect assessment system for power external insulation equipment according to claim 1, characterized in that: For every 10% increase in gain, the spot area increases by B times. The standard gain value is set to q, and the spot area is equivalent to the equivalent spot area under the gain q, as follows: Where A is the area of ​​the detected light spot and the gain is p.

6. The multi-parameter integrated ultraviolet image defect assessment system for power external insulation equipment according to claim 5, characterized in that: Normalize the equivalent spot area to the distance D, where the unit of D is m, and the final equivalent spot area is d is the actual detection distance, in meters.

7. The multi-parameter integrated ultraviolet image defect assessment system for power external insulation equipment according to claim 6, characterized in that: The evaluation network is configured to determine the state of the power external insulation device according to the number of photons output by the ultraviolet imager.

8. A multi-parameter UV image defect assessment method for power external insulation equipment, characterized in that: The following steps are involved: The visible light channel positioning information extraction network receives the visible light channel image output by the ultraviolet imager, uses the neural network model to detect the location of the external insulation equipment, and obtains the equipment area information of the power external insulation equipment; The ultraviolet channel image output by the ultraviolet imager is input into the neural network model, and the ultraviolet discharge spot is segmented to obtain ultraviolet discharge spot information, wherein the ultraviolet discharge spot information includes: the area of ​​the spot region, the area of ​​the overlapping area with the device under test, and the coordinates of the center point of the spot region; the spot area is equivalent to the equivalent spot area under the gain q; and the spot area is further normalized to the distance D; Detect parameter information that affects the spot area captured by the UV imager; The equipment area information, UV discharge spot information and parameter information are integrated to obtain the final evaluation results; Define r as the proportion of the discharge area, Where, is the final equivalent spot area calculated based on the overlapping area A2, A e is the area of ​​the main body; The evaluation network first determines the status of the external power insulation equipment based on the number of photons; if the number of photons is less than the set threshold, it is judged to be normal; if the number of photons is greater than or equal to the set threshold, it is judged to be abnormal; next, if the discharge location is on the hardware, it is judged to be low-intensity discharge; if the discharge location is on the main body, the discharge intensity is judged based on the proportion of the discharge area; when the proportion of the discharge area is greater than or equal to the first set threshold, it is judged to be high-intensity discharge; when the proportion of the discharge area is less than the second set threshold, it is judged to be low-intensity discharge; when the proportion of the discharge area is less than the first set threshold and greater than or equal to the second set threshold, it is judged to be medium-intensity discharge.

9. The method for evaluating defects of external insulation equipment using ultraviolet images integrating multiple parameters according to claim 8, characterized in that: The method determines the state of the power external insulation equipment according to the number of photons output by the ultraviolet imager.

10. The method for evaluating defects of external insulation equipment using ultraviolet images integrating multiple parameters according to claim 8, wherein: The equipment area information of the tested power external insulation equipment acquired by the visible light channel positioning information extraction network includes: main body area position information, hardware area position information, and main body area area.

11. The method for evaluating defects of external insulation equipment using ultraviolet images integrating multiple parameters according to claim 8, wherein: The coordinates of the center point of the light spot area represent the center position of the discharge.

12. The method for evaluating defects of external insulation equipment using ultraviolet images of electric power integrating multiple parameters as claimed in claim 8, characterized in that: The area of ​​the light spot region is obtained according to the number of pixels in the largest light spot region.

13. The method for evaluating defects of external insulation equipment using ultraviolet images integrating multiple parameters according to claim 8, wherein: For every 10% increase in gain, the spot area increases by B times. The standard gain value is set to q, and the spot area is equivalent to the equivalent spot area under the gain q, as follows: Where A is the area of ​​the detected light spot and the gain is p.

14. The method for evaluating defects of external insulation equipment using ultraviolet images integrating multiple parameters according to claim 13, wherein: Normalize the equivalent spot area to the distance D, where the unit of D is m, and the final equivalent spot area is d is the actual detection distance, in meters.

15. A solar-blind ultraviolet imager, characterized in that: Comprising a system as claimed in any one of claims 1 to 7.

16. 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 steps of the method according to any one of claims 8 to 14 are implemented.

Images