Outdoor open-type power equipment-based partial discharge detection method and system

Abstract

The invention discloses a partial discharge detection method and system based on outdoor open-type power equipment. The method comprises the following steps: synchronously acquiring a visible light image sequence and an infrared image sequence of the power equipment under the same visual angle; obtaining a non-uniform heat area based on the spatial features and the time features of the infrared image pixels; determining whether the projection position of the non-uniform heat area in the visible light image has a visible defect or not, and determining an environmental influence value; and determining a partial discharge type based on the environmental influence value and whether visible defects exist. The method comprises the following steps: firstly, determining whether an abnormal temperature region of partial discharge exists in an infrared image or not through spatial features and time change features of pixels; secondly, the infrared image and the visible light image are combined, abnormal parts of the infrared image and the visible light image are matched, and the real local generation reason is judged by combining environmental influence factors, so that the defect of high false alarm rate of infrared image-based partial discharge detection in the prior art is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of power equipment status detection, and in particular to a partial discharge detection method and system based on outdoor open-type power equipment. Background Art

[0002] With the continuous expansion of the scale of power systems and the increasing requirements for power supply reliability, outdoor open power equipment plays a key role in the process of power transmission and distribution. However, these devices have been operating in complex outdoor environmental conditions for a long time, and are subject to various stresses such as electricity, heat, and mechanical stresses, which are prone to problems such as insulation aging and partial discharge. Partial discharge is often an early manifestation of equipment insulation degradation. If partial discharge cannot be detected in a timely and accurate manner and corresponding measures cannot be taken, it may further develop into serious faults such as insulation breakdown, leading to power outages, affecting the stability and safety of power supply, and causing significant losses to social production and life.

[0003] In the existing technology, the partial discharge detection of outdoor open-type power equipment has many defects due to the complex and changeable outdoor environment and the large number of interference sources. For example, the pulse current method in the electrical detection method has complex wiring and weak anti-interference ability; the optical detection method and infrared or ultraviolet imaging detection method are greatly affected by the environment and have a high false detection rate; the ultrasonic detection method has obvious signal attenuation and is easily affected by noise. Summary of the invention

[0004] In response to the problems existing in the above-mentioned prior art, the present invention provides a partial discharge detection method and system based on outdoor open power equipment, with the aim of compensating for the high false alarm rate of single infrared image detection through the image features of visible light images, and combining historical trend judgment to improve the accuracy and reliability of partial discharge monitoring.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a method for detecting partial discharge of outdoor open-type power equipment, comprising:

[0007] Synchronously collect visible light image sequences and infrared image sequences of power equipment at the same viewing angle;

[0008] Determine an abnormal area based on the local difference of pixels in the infrared image in space, and screen the abnormal area based on the temporal variation characteristics of pixels in the infrared image sequence to obtain an uneven heat area;

[0009] Determine whether there is a visible defect at a corresponding position where the uneven heat area is projected into the visible light image; determine an environmental impact value based on the uneven heat area in the infrared image;

[0010] The type of partial discharge is determined based on the environmental impact value and whether there is a visible defect.

[0011] Preferably, the determining of the abnormal area based on the local spatial difference of pixels in the infrared image comprises:

[0012] A single frame infrared image is preliminarily segmented into multiple area blocks based on the neighborhood features of pixels;

[0013] A region block in which the average temperature is greater than a preset temperature threshold is recorded as a high temperature region, and a plurality of region blocks adjacent to the high temperature region are recorded as a plurality of target regions;

[0014] Calculating the grayscale mean deviation of the high temperature area pixel points relative to the multiple target area pixel points, and the gradient mean deviation of the high temperature area pixel points relative to the multiple target area pixel points;

[0015] An abnormal area is determined based on the grayscale mean deviation and the gradient mean deviation.

[0016] Preferably, the screening of the abnormal area to obtain the uneven heat area based on the temporal variation characteristics of pixels in the infrared image sequence specifically includes:

[0017] Determining the area ratio of the abnormal region in adjacent frames of the infrared image sequence;

[0018] In the current frame infrared image, respectively calculating the grayscale centroids of the abnormal area and multiple target areas;

[0019] Connecting the grayscale centroid of the abnormal area with the grayscale centroids of multiple target areas respectively to obtain multiple transition lines;

[0020] Projecting the transition lines in the current frame of infrared image to the previous frame of infrared image of the current infrared image;

[0021] Calculate the difference in grayscale value of each pixel point on each transition line in the infrared images of the previous and next frames;

[0022] The abnormal area is screened based on the difference and the ratio of the area ratio to obtain an uneven heat area.

[0023] Preferably, the step of determining the environmental impact value according to the uneven heat area in the infrared image comprises:

[0024] Recording other areas in the infrared image except the uneven heat area as environmental areas;

[0025] Calculating the average temperature value of the environmental area;

[0026] Calculating a ratio of the average temperature value to a preset ambient temperature and a variation amplitude of the average temperature value in the infrared image sequence;

[0027] An environmental impact value is determined based on the ratio and the change magnitude.

[0028] Preferably, the partial discharge type includes an environmental factor type, a visible defect type, and a circuit factor type;

[0029] Determining the type of partial discharge based on the environmental impact value and whether there are visible defects includes:

[0030] When there is an uneven heat area and the environmental impact value is greater than a preset value, determining the partial discharge type as an environmental factor type;

[0031] When there is an uneven heat area and a visible defect exists at a corresponding position where the uneven heat area is projected into the visible light image, the partial discharge type is determined to be a visible defect type;

[0032] When there is an uneven heat area and the determination conditions of the environmental factor type and the visible defect type are not met, the partial discharge type is determined to be the circuit factor type.

[0033] Preferably, when there is an uneven heat area and there is no visible defect when the uneven heat area is projected onto the corresponding position in the visible light image, the method further includes: determining the historical change trend of the pixel features of the uneven heat area in the infrared image and the corresponding position in the visible light image based on the historical image sequence, and issuing a partial discharge warning if the historical change trends are consistent.

[0034] Preferably, the step of determining the historical change trend of the pixel features of the uneven heat area in the infrared image and the corresponding position in the visible light image based on the historical image sequence includes:

[0035] Acquire historical visible light image sequences and historical infrared image sequences of power equipment at the same viewing angle;

[0036] Acquire the uneven heat area of ​​each frame of infrared image in the historical infrared image sequence;

[0037] Recording the area change characteristics and direction change characteristics of the uneven heat area of ​​each frame of infrared image in the historical infrared image sequence;

[0038] Obtaining the highest temperature point of the uneven heat area in the first frame of infrared image in the historical infrared image sequence, projecting the highest temperature point into the first frame of visible light image in the historical visible light image sequence and recording it as a target point;

[0039] In the first visible light image frame, a square area with a preset area and a target point as the center is determined as a detection frame;

[0040] Expanding the detection frame with a preset expansion step length, and calculating the similarity between the grayscale values ​​of pixels in the expanded detection frame and the grayscale values ​​of pixels in the detection frame before the expansion;

[0041] If the similarity meets the threshold condition, continue to expand the detection frame with a preset expansion step, otherwise reduce the expansion step to expand the detection frame; when the preset number of iterations is reached or the expansion step is the minimum expansion step, output the current detection frame as the target frame;

[0042] In the historical visible light image sequence, recording the area change characteristics and direction change characteristics of the target frame;

[0043] The historical change trend is determined according to the area change characteristics and the direction change characteristics of the uneven heat area and the area change characteristics and the direction change characteristics of the target frame.

[0044] In a second aspect, the present invention provides a partial discharge detection system based on outdoor open-type power equipment, comprising:

[0045] An image acquisition module, used for synchronously acquiring a visible light image sequence and an infrared image sequence of the power equipment at the same viewing angle;

[0046] A heat analysis module, used to determine an abnormal area based on the local difference of pixels in the infrared image in space, and to screen the abnormal area to obtain an uneven heat area based on the temporal variation characteristics of pixels in the infrared image sequence;

[0047] A control inspection module is used to determine whether there is a visible defect at a corresponding position where the uneven heat area is projected into the visible light image; and to determine an environmental impact value according to the uneven heat area in the infrared image;

[0048] The partial discharge determination module is used to determine the partial discharge type based on the environmental impact value and whether there is a visible defect.

[0049] In a third aspect, the present invention provides an electronic device, comprising:

[0050] A memory for storing executable instructions;

[0051] The processor is used to implement a partial discharge detection method based on outdoor open-type power equipment as described above when running the executable instructions stored in the memory.

[0052] In a fourth aspect, the present invention provides a computer-readable storage medium storing executable instructions, which, when executed by a processor, implement a partial discharge detection method based on outdoor open-type power equipment as described above.

[0053] The present invention provides a method and system for detecting partial discharge of outdoor open-type power equipment, which has the following beneficial effects:

[0054] 1. The present invention monitors temperature anomalies through infrared images to trigger the thermal analysis module. The thermal analysis module processes the pixel features of the image in multiple steps to check for abnormal heat. When the thermal analysis module detects an uneven heat area, a partial discharge alarm signal is issued. It identifies whether there is an electrical defect in the projection area of ​​the uneven heat area in the visible light image and the degree of interference in the current environment reflected by the temperature, and decides whether the current partial discharge is caused by a defect in the power equipment or a harsh environment. Multi-step abnormality detection combined with joint analysis of infrared images and visible light images effectively reduces the false alarm rate of single image detection and provides specific type detection of partial discharge.

[0055] 2. The present invention first extracts the high temperature area, then selects the heat area that meets the local abnormality based on the degree of deviation of the high temperature area relative to the neighborhood in the image space, and then eliminates environmental interference from the abnormal heat from the time change characteristics of the continuous image frames, thereby extracting the effective uneven heat area. Through the three-step heat area analysis, the precise partial discharge occurrence area is identified, which improves the problem of environmental interference and inaccurate discharge source positioning in the partial discharge monitoring of outdoor open power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flow chart of a partial discharge detection method based on outdoor open-type power equipment of the present invention;

[0057] Figure 2 The present invention is a structural block diagram of a partial discharge detection system based on outdoor open-type power equipment. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] To facilitate understanding of this embodiment, a partial discharge detection method based on outdoor open-type power equipment disclosed in an embodiment of the present invention is first introduced in detail.

[0060] like Figure 1 As shown, the method includes:

[0061] S1, synchronously collect visible light image sequence and infrared image sequence of power equipment under the same viewing angle.

[0062] In this step, a visible light camera is used to capture visible light images of the outdoor open equipment to be inspected, and an infrared camera or infrared thermal imager is installed at the same position as the visible light camera to capture infrared images of the outdoor open equipment. Multiple visible light images and infrared images are continuously acquired, each image carries time information, and the visible light images and infrared images captured at the same time are a control group. Since they are captured at the same position and at the same time, the two images of a control group can be directly matched.

[0063] S2, determining an abnormal area based on the local difference of pixels in the infrared image in space, and screening the abnormal area based on the temporal variation characteristics of pixels in the infrared image sequence to obtain an uneven heat area.

[0064] Infrared images show the temperature information of objects. When partial discharge occurs in outdoor open equipment, heat is generated in the discharge area, causing uneven distribution of surface temperature. By using infrared images to monitor the surface temperature changes of equipment in real time, the degree of temperature abnormality is reflected through local differences in pixels, and the continuous change characteristics over time are combined to eliminate environmental interference factors and detect the presence of partial discharge.

[0065] S3, determining whether there is a visible defect at a corresponding position where the uneven heat area is projected into the visible light image; and determining an environmental impact value according to the uneven heat area in the infrared image.

[0066] S4, determining the type of partial discharge based on the environmental impact value and whether there are visible defects.

[0067] It should be understood that there are many causes of partial discharge, such as environmental factors such as high humidity and high temperature affecting the thermal expansion coefficient and hygroscopicity of insulating materials, visible electrical defects such as bubbles, cracks, stains, material aging, corrosion, deformation, etc. causing partial discharge, and circuit factors such as high voltage shocks inside the line.

[0068] Therefore, this embodiment analyzes the type of partial discharge by combining infrared images and visible light images. Specifically, it determines whether it is caused by visible defects by whether the abnormal part of the infrared image corresponds to the abnormal part of the visible light image, and analyzes environmental factors by using temperature to represent the severity of the environment.

[0069] Among them, the uneven heat area represents the abnormal part in the infrared image, and the power defect area represents the abnormal part in the visible light image.

[0070] This method sets up a multi-step anomaly detection of heat in infrared images to eliminate interference with infrared temperature detection caused by light sources, etc., and effectively reduces the false alarm rate of single image detection through joint analysis of infrared images and visible light images, and provides specific type detection of partial discharge.

[0071] As a preferred implementation, determining the abnormal area based on the local spatial difference of pixels in the infrared image in step S2 may include the following steps:

[0072] S21, preliminarily dividing the single frame infrared image into multiple area blocks based on the neighborhood features of pixels.

[0073] Clustering pixels with adjacent positions and similar features such as grayscale, brightness, and texture as a region can achieve image segmentation, and overall processing of pixels with similar features can simplify the image analysis and understanding process.

[0074] As a feasible implementation method, a super-pixel segmentation method may be used to segment the infrared image to obtain a plurality of regions. The super-pixel segmentation method is a prior art, and the specific steps are not described in detail in this embodiment.

[0075] S22, record a region block in which the average temperature is greater than a preset temperature threshold as a high temperature region, and record a plurality of region blocks adjacent to the high temperature region as a plurality of target regions.

[0076] The local discharge area will generate heat, making the local temperature higher than the normal area. Compared with the overload heat release of the power line, the local discharge overheating has the characteristics of small area and high temperature. Based on this, this embodiment sets a three-step heat analysis strategy.

[0077] First, the first step of screening is performed to preliminarily determine the area with higher temperature. Due to the multi-step screening strategy of this embodiment, a lower value can be selected as the preset temperature threshold to avoid abnormal omission.

[0078] S23, calculating the grayscale mean deviation of the high temperature area pixel points relative to the multiple target area pixel points, and the gradient mean deviation of the high temperature area pixel points relative to the multiple target area pixel points.

[0079] S24, determining an abnormal area based on the grayscale mean deviation and the gradient mean deviation.

[0080] The above steps are the second step of screening, which is used to determine the degree of local abnormality in the high-temperature area. Due to the small area of ​​local discharge overheating, the local difference in the infrared image is large. This embodiment calculates the deviation of the pixel features of the high-temperature area relative to the surrounding area to represent the degree of abnormality of the area. Specifically, in this embodiment, the degree of abnormality of the high-temperature area is determined based on the grayscale mean deviation and the gradient mean deviation, and the high-temperature area with an abnormality greater than a threshold is selected as the abnormal area. Optionally, the degree of abnormality of the high-temperature area is calculated using the following formula:

[0081]

[0082] Among them, AN represents the abnormal degree of the high temperature area; Sigmoid() is a normalization function, which means projecting the variable to (0,1); g represents the grayscale mean of all pixels in the high temperature area; g0 represents the grayscale mean of all pixels in the target area adjacent to the high temperature area; Represents the mean gradient of all pixels in the high temperature area; Represents the gradient mean of all pixels in the target area adjacent to the high temperature area.

[0083] Indicates how much the grayscale value of the high temperature area deviates from the surrounding target area. It indicates how much the gradient value of the high temperature area deviates from the surrounding target area, and the two together show the degree of abnormality of the high temperature area.

[0084] Temperature detection in infrared images is based on infrared radiation. Light sources in the surrounding environment can cause interference, and even the reflection of light from walls and glass can constitute an interference light source. However, this embodiment is aimed at outdoor open-type power equipment, and the surrounding interference environment is more complex. It is necessary to perform a third step of screening to remove the interference of ambient light sources. This embodiment compares the difference between the uneven heat areas in two adjacent image frames to capture the process of uneven heat spreading to the surroundings for discrimination.

[0085] As a preferred implementation, in step S2, screening the abnormal area to obtain the uneven heat area based on the temporal variation characteristics of the pixels in the infrared image sequence specifically includes:

[0086] S25, determining the area ratio of the abnormal region in adjacent frames of the infrared image sequence;

[0087] Since the light source remains basically stable, the area change in the infrared image sequence will not be too large, and the heat area generated by partial discharge will gradually spread to the surrounding area. Therefore, the area ratio of the minimum value to the maximum value in the abnormal area of ​​the latter frame and the abnormal area of ​​the previous frame is calculated in adjacent frames. The area ratio of the light source is basically 1, and the smaller the area ratio, the higher the possibility of uneven heat area.

[0088] S26, in the current frame infrared image, respectively calculating the grayscale centroids of the abnormal area and multiple target areas;

[0089] The grayscale centroid is the uniform convergence of all grayscales in the region and can represent the overall characteristics of the region.

[0090] S27, connecting the grayscale centroid of the abnormal area with the grayscale centroids of multiple target areas respectively to obtain multiple transition lines;

[0091] The line connecting the grayscale centroids represents the changing trend of the pixels from one area block to another area block, and shows how each pixel transitions to another area block.

[0092] S28, projecting the transition lines in the current frame of infrared image to the previous frame of infrared image of the current infrared image;

[0093] It should be noted that the infrared image and the visible light image are in one-to-one correspondence, and the “projection” refers to directly corresponding the position of the transition line on the infrared image to the same position in the visible light image of the control group.

[0094] S29, calculating the sum of the differences in the grayscale values ​​of each pixel point on each transition line in the infrared images of the previous and next frames;

[0095] S210, screening the abnormal area based on the difference sum and the ratio of the area ratio to obtain an uneven heat area.

[0096] From the above, it can be seen that the light source is relatively stable and changes less in adjacent frame images, that is, the difference and sum of the grayscale values ​​of each pixel on each transition line in the infrared images of the previous and next frames are small. However, the uneven heat area will spread to the surrounding area, and the grayscale value in the neighborhood will change unevenly, and the difference and sum are large.

[0097] Exemplarily, in this embodiment, the following formula is used to calculate the change characteristic value of the abnormal area based on the difference sum and the ratio of the area ratio:

[0098]

[0099] Where VC represents the change characteristic value of the abnormal area; i represents the i-th target area adjacent to the abnormal area; j represents the j-th pixel point on the transition line between the abnormal area and the i-th target area; n i represents the total number of pixels on the transition line between the abnormal area and the i-th target area; g ij g′ represents the gray value of the jth pixel on the transition line between the abnormal area and the i-th target area in the current image frame; ij It represents the gray value of the j-th pixel on the transition line between the abnormal area and the i-th target area in the previous image frame; min() represents the minimum value, and max() represents the maximum value; S is the area of ​​the abnormal area in the current image frame, and S′ is the area of ​​the abnormal area in the previous image frame.

[0100] It represents the difference in the grayscale values ​​of each pixel on the transition line in the infrared images of the previous and next frames; It represents the area ratio of the abnormal area in adjacent frames of the infrared image sequence.

[0101] When partial discharge is detected, it is necessary to further determine the cause of the partial discharge.

[0102] Generally speaking, partial discharge types include environmental factor type, visible defect type, and circuit factor type, and this implementation makes judgments in sequence.

[0103] First, determine whether it is caused by environmental factors. When the equipment is in a harsh environment, it will cause damage to the insulation material, which will cause partial discharge.

[0104] As a preferred implementation, the step of determining the environmental impact value according to the uneven heat area in the infrared image in step S3 includes:

[0105] S311, recording other areas in the infrared image except the uneven heat area as environmental areas.

[0106] In this step, the normal area in the infrared image is used as the background to represent the current environment of the infrared image.

[0107] S312, calculating the average temperature value of the environmental area.

[0108] S313, calculating the ratio of the average temperature value to the preset ambient temperature and the variation amplitude of the average temperature value in the infrared image sequence;

[0109] When the average temperature value is too high, it means that the current ambient temperature of the equipment is too high and it is easy to cause partial discharge; when the average temperature value changes greatly in the infrared image sequence, it means that the current ambient temperature changes dramatically; both indicate that the outdoor open equipment is in a relatively harsh environment.

[0110] S314: Determine an environmental impact value based on the ratio and the variation amplitude.

[0111] As a preferred implementation, determining in step S3 whether there is a visible defect at a corresponding position where the uneven heat area is projected into the visible light image may include:

[0112] S321, projecting the uneven heat area to a corresponding position in the visible light image;

[0113] S322, using a trained visible defect recognition model to extract the visible defects at the corresponding position.

[0114] The visible defect recognition model can be established using deep learning methods such as the YOLO series framework, AlexNet, VGG, etc. in the prior art, and the specific steps will not be repeated in this embodiment.

[0115] As a preferred implementation, step S4 determines the type of partial discharge based on the environmental impact value and whether there is a visible defect, including:

[0116] When there is an uneven heat area and the environmental impact value is greater than a preset value, determining the partial discharge type as an environmental factor type;

[0117] When there is an uneven heat area and a visible defect exists at a corresponding position where the uneven heat area is projected into the visible light image, the partial discharge type is determined to be a visible defect type;

[0118] When there is an uneven heat area and the determination conditions of the environmental factor type and the visible defect type are not met, the partial discharge type is determined to be a circuit factor type. Specifically, the current value and voltage value in the circuit can be detected to determine the operating state of the equipment and further analyze the line factors.

[0119] Generally speaking, the initial impact of partial discharge is small and difficult to detect, and its short-term existence does not affect the insulation strength of electrical equipment. However, if electrical equipment continues to experience partial discharges under operating voltage, these weak discharges will have a cumulative effect, gradually deteriorating the dielectric properties of the insulation and expanding local defects, eventually leading to the breakdown of the entire insulation. Therefore, the trend of changes in the historical status of the equipment can be analyzed to achieve early warning of partial discharge.

[0120] As a preferred embodiment, when there is an uneven heat area and there is no visible defect when the uneven heat area is projected onto the corresponding position in the visible light image, the method further includes: determining the historical change trend of the pixel features of the uneven heat area in the infrared image and the corresponding position in the visible light image based on the historical image sequence, and issuing a partial discharge warning if the historical change trends are consistent.

[0121] When uneven heat areas appear in infrared images, it indicates partial discharge. Each partial discharge will have some impact on the insulating medium. Slight partial discharge has little impact on the insulation of power equipment, and the insulation strength decreases slowly. However, as time goes by, the texture of the insulating material will gradually change in the visible light image. If the change trend is similar to that of the uneven heat area in the infrared image, it means that the heat has had a negative impact on the insulating material and needs to be dealt with in a timely manner.

[0122] As a preferred implementation, the step of determining the historical change trend of the pixel features of the uneven heat area in the infrared image and the corresponding position in the visible light image based on the historical image sequence includes:

[0123] S51, acquiring a historical visible light image sequence and a historical infrared image sequence of the power equipment at the same viewing angle.

[0124] In the aforementioned step S1, only a short-term image sequence is acquired to analyze the change characteristics in adjacent time frames. In this step S51, historical images with a longer interval between frames are acquired to analyze the change trend of the surface texture of the insulating material, which has a long time span and changes slowly.

[0125] S52, obtaining the uneven heat area of ​​each frame of infrared image in the historical infrared image sequence.

[0126] According to the aforementioned steps S21-S210, the uneven heat area of ​​each frame of infrared image is extracted.

[0127] S53, recording the area change characteristics and direction change characteristics of the uneven heat area of ​​each frame of infrared image in the historical infrared image sequence.

[0128] S54, obtaining the highest temperature point of the uneven heat area in the first frame of infrared image in the historical infrared image sequence, projecting the highest temperature point into the first frame of visible light image in the historical visible light image sequence and recording it as a target point.

[0129] The higher the temperature, the greater the impact on the insulating material. The point with the highest temperature is used as the initial detection point, which corresponds to the target point in the visible light image. Starting from the target point, the area is gradually expanded to find the local features of the target point.

[0130] S55: In the first visible light image frame, determine a square area with a preset area and the target point as the center as a detection frame.

[0131] S56, expanding the detection frame with a preset expansion step size, and calculating the similarity between the grayscale values ​​of pixels in the detection frame after the expansion and the grayscale values ​​of pixels in the detection frame before the expansion.

[0132] It can be understood that the preset extension step size can be determined according to the gradient change of pixels in the uneven heat area in the infrared image.

[0133] S57, if the similarity meets the threshold condition, continue to expand the detection frame with the preset expansion step size, otherwise reduce the expansion step size to expand the detection frame; when the preset number of iterations is reached or the expansion step size is the minimum expansion step size, output the current detection frame as the target frame.

[0134] When the similarity meets the threshold condition, the extended detection frame contains similar regional features and is consistent with the target point. When the threshold condition is not met, it means that the extended area has exceeded the local area where the target point is located, and it is necessary to return to the previous extended area and appropriately reduce the extended detection frame for re-detection.

[0135] S58, recording the area change characteristics and direction change characteristics of the target frame in the historical visible light image sequence.

[0136] S59, determining a historical change trend according to the area change characteristics and direction change characteristics of the uneven heat area and the area change characteristics and direction change characteristics of the target frame.

[0137] In this embodiment, the highest temperature point of the uneven heat area in the infrared image is used as the initial growth point, and the texture change trend in the visible light image is gradually expanded based on the idea of ​​regional growth. The texture change trend is compared with the spread trend of the uneven heat area to determine the impact of partial discharge, and a partial discharge warning is issued when the trends are consistent. In this way, the historical change trend analysis based on the combination of the two images can be used to provide early warning of partial discharge that is expanding damage, avoid the expansion of the abnormal range and cause greater losses, and reduce the possibility of accidents.

[0138] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0139] Based on the same inventive concept, the embodiment of the present application also provides a system for implementing the above-mentioned outdoor open-type power equipment partial discharge detection. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiment of the outdoor open-type power equipment partial discharge detection system provided below can refer to the limitations of the method above, and will not be repeated here.

[0140] like Figure 2 As shown, the present invention also provides a partial discharge detection system based on outdoor open-type power equipment, comprising:

[0141] In a second aspect, the present invention provides a partial discharge detection system based on outdoor open-type power equipment, comprising:

[0142] An image acquisition module, used for synchronously acquiring a visible light image sequence and an infrared image sequence of the power equipment at the same viewing angle;

[0143] A heat analysis module, used to determine an abnormal area based on the local difference of pixels in the infrared image in space, and to screen the abnormal area to obtain an uneven heat area based on the temporal variation characteristics of pixels in the infrared image sequence;

[0144] A control inspection module is used to determine whether there is a visible defect at a corresponding position where the uneven heat area is projected into the visible light image; and to determine an environmental impact value according to the uneven heat area in the infrared image;

[0145] The partial discharge determination module is used to determine the partial discharge type based on the environmental impact value and whether there is a visible defect.

[0146] In some embodiments, the system further comprises a trend warning module, which is used to:

[0147] When there is an uneven heat area and there is no visible defect at the corresponding position where the uneven heat area is projected into the visible light image, the historical change trend of the pixel features of the uneven heat area in the infrared image and the corresponding position in the visible light image is determined based on the historical image sequence. If the historical change trends are consistent, a partial discharge warning is issued.

[0148] It should be noted that: the partial discharge detection system based on outdoor open-type power equipment provided in this embodiment only uses the division of the above-mentioned functional modules as an example when performing partial discharge detection. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules. Each functional module can be composed of a single execution unit, or two or more execution units can be integrated into one functional module to realize all the functions of the functional module.

[0149] Those skilled in the art will appreciate that the above modules may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor may call and execute operations corresponding to the above modules.

[0150] An embodiment of the present invention further provides an electronic device, including:

[0151] A memory for storing executable instructions;

[0152] The processor is used to implement a partial discharge detection method based on outdoor open-type power equipment as described above when running the executable instructions stored in the memory. The processor can be a central processing unit, other general-purpose processors, digital signal processors, application-specific integrated circuits, field programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., or a combination of the above chips.

[0153] The specific details of the partial discharge detection performed by the above-mentioned computer device can be understood by referring to the relevant descriptions and effects corresponding to the above-mentioned methods, and will not be repeated here.

[0154] Another embodiment of the present invention further provides a computer-readable storage medium storing executable instructions, which, when executed by a processor, implements a partial discharge detection method based on outdoor open-type power equipment as described above.

[0155] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk, or an optical disk, or any other computer-readable storage medium that can store program codes.

[0156] The present invention is not limited to the above-mentioned specific implementation modes. Various changes made by ordinary technicians in this field based on the above-mentioned concepts without creative work are all within the protection scope of the present invention.

Claims

1. A method for detecting partial discharge of outdoor open-type power equipment, characterized in that: The steps include: Synchronously collect visible light image sequences and infrared image sequences of power equipment at the same viewing angle; Determine an abnormal area based on the local difference of pixels in the infrared image in space, and screen the abnormal area based on the temporal variation characteristics of pixels in the infrared image sequence to obtain an uneven heat area; Determine whether there is a visible defect at a corresponding position where the uneven heat area is projected into the visible light image; determine an environmental impact value based on the uneven heat area in the infrared image; The type of partial discharge is determined based on the environmental impact value and whether there is a visible defect.

2. The method for detecting partial discharge of outdoor open-type power equipment according to claim 1 is characterized in that: Determining the abnormal area based on the local difference of pixels in the infrared image in space includes: A single frame infrared image is preliminarily segmented into multiple area blocks based on the neighborhood features of pixels; A region block in which the average temperature is greater than a preset temperature threshold is recorded as a high temperature region, and a plurality of region blocks adjacent to the high temperature region are recorded as a plurality of target regions; Calculating the grayscale mean deviation of the high temperature area pixel points relative to the multiple target area pixel points, and the gradient mean deviation of the high temperature area pixel points relative to the multiple target area pixel points; An abnormal area is determined based on the grayscale mean deviation and the gradient mean deviation.

3. The method for detecting partial discharge of outdoor open-type power equipment according to claim 2 is characterized in that: The method of screening the abnormal area based on the temporal variation characteristics of pixels in the infrared image sequence to obtain the uneven heat area specifically includes: Determining the area ratio of the abnormal region in adjacent frames of the infrared image sequence; In the current frame infrared image, respectively calculating the grayscale centroids of the abnormal area and multiple target areas; Connecting the grayscale centroid of the abnormal area with the grayscale centroids of multiple target areas respectively to obtain multiple transition lines; Projecting the transition lines in the current frame of infrared image to the previous frame of infrared image of the current infrared image; Calculate the difference in grayscale value of each pixel point on each transition line in the infrared images of the previous and next frames; The abnormal area is screened based on the difference and the ratio of the area ratio to obtain an uneven heat area.

4. The method for detecting partial discharge of outdoor open-type power equipment according to claim 3 is characterized in that: The step of determining the environmental impact value according to the uneven heat area in the infrared image comprises: Recording other areas in the infrared image except the uneven heat area as environmental areas; Calculating the average temperature value of the environmental area; Calculating a ratio of the average temperature value to a preset ambient temperature and a variation amplitude of the average temperature value in the infrared image sequence; An environmental impact value is determined based on the ratio and the change magnitude.

5. The method for detecting partial discharge of outdoor open-type power equipment according to claim 4 is characterized in that: The partial discharge types include environmental factor types, visible defect types, and circuit factor types; Determining the type of partial discharge based on the environmental impact value and whether there are visible defects includes: When there is an uneven heat area and the environmental impact value is greater than a preset value, determining the partial discharge type as an environmental factor type; When there is an uneven heat area and a visible defect exists at a corresponding position where the uneven heat area is projected into the visible light image, the partial discharge type is determined to be a visible defect type; When there is an uneven heat area and the determination conditions of the environmental factor type and the visible defect type are not met, the partial discharge type is determined to be the circuit factor type.

6. The method for detecting partial discharge of outdoor open-type power equipment according to claim 5 is characterized in that: When there is an uneven heat area and there is no visible defect at the corresponding position where the uneven heat area is projected into the visible light image, the method further includes: determining the historical change trend of the pixel features of the uneven heat area in the infrared image and the corresponding position in the visible light image based on the historical image sequence, and issuing a partial discharge warning if the historical change trends are consistent.

7. The method for detecting partial discharge of outdoor open-type power equipment according to claim 6 is characterized in that: The step of determining the historical change trend of the pixel features of the uneven heat area in the infrared image and the corresponding position in the visible light image based on the historical image sequence includes: Acquire historical visible light image sequences and historical infrared image sequences of power equipment at the same viewing angle; Acquire the uneven heat area of ​​each frame of infrared image in the historical infrared image sequence; Recording the area change characteristics and direction change characteristics of the uneven heat area of ​​each frame of infrared image in the historical infrared image sequence; Obtaining the highest temperature point of the uneven heat area in the first frame of infrared image in the historical infrared image sequence, projecting the highest temperature point into the first frame of visible light image in the historical visible light image sequence and recording it as a target point; In the first visible light image frame, a square area with a preset area and a target point as the center is determined as a detection frame; Expanding the detection frame with a preset expansion step length, and calculating the similarity between the grayscale values ​​of pixels in the expanded detection frame and the grayscale values ​​of pixels in the detection frame before the expansion; If the similarity meets the threshold condition, continue to expand the detection frame with a preset expansion step, otherwise reduce the expansion step to expand the detection frame; when the preset number of iterations is reached or the expansion step is the minimum expansion step, output the current detection frame as the target frame; In the historical visible light image sequence, recording the area change characteristics and direction change characteristics of the target frame; The historical change trend is determined according to the area change characteristics and the direction change characteristics of the uneven heat area and the area change characteristics and the direction change characteristics of the target frame.

8. A partial discharge detection system based on outdoor open-type power equipment, characterized in that: include: An image acquisition module, used for synchronously acquiring a visible light image sequence and an infrared image sequence of the power equipment at the same viewing angle; A heat analysis module, used to determine an abnormal area based on the local difference of pixels in the infrared image in space, and to screen the abnormal area to obtain an uneven heat area based on the temporal variation characteristics of pixels in the infrared image sequence; A control inspection module is used to determine whether there is a visible defect at a corresponding position where the uneven heat area is projected into the visible light image; and to determine an environmental impact value according to the uneven heat area in the infrared image; The partial discharge determination module is used to determine the partial discharge type based on the environmental impact value and whether there is a visible defect.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement a partial discharge detection method based on outdoor open-type power equipment as described in any one of claims 1 to 7 when running the executable instructions stored in the memory.

10. A computer-readable storage medium storing executable instructions, characterized in that: When the executable instructions are executed by the processor, a partial discharge detection method based on outdoor open-type power equipment as described in any one of claims 1 to 7 is implemented.

Images