Partial discharge detection method and device, electronic equipment and computer program product

Abstract

The invention discloses a partial discharge detection method and device, electronic equipment and a computer program product. The method comprises the steps that a to-be-detected image of the power transmission line is acquired, and the to-be-detected image at least comprises a visible light image, an ultraviolet image and an infrared image of the same part of the power transmission line; performing partial discharge qualitative analysis on the power transmission line by using the visible light image to obtain a partial discharge qualitative analysis result; performing partial discharge quantitative analysis on the power transmission line by using the ultraviolet image and the infrared image to obtain a partial discharge qualitative analysis result; the visible light image, the ultraviolet image and the infrared image are subjected to feature point matching, a target image is obtained, and the target image is used for displaying a discharge part determined according to the partial discharge qualitative analysis result and the discharge degree determined according to the partial discharge qualitative analysis result. According to the invention, the technical problem of low accuracy of anomaly detection is solved.

Description

Technical Field

[0001] The present invention relates to the field of power maintenance, and in particular to a partial discharge detection method, device, electronic equipment and computer program product. Background Art

[0002] The all-round development of today's society is based on the safe and reliable power supply provided by complex power networks. As the main artery of regional power transmission, line inspection is a key link in ensuring the safe operation of local power transmission and distribution networks. However, there are many types of equipment anomalies that occur during the operation of power transmission and transformation equipment. Among them, partial discharge is a very common phenomenon that can easily cause major hidden dangers. Partial discharge is an important cause of insulation breakdown of high-voltage transmission equipment and an important sign of insulation degradation.

[0003] Overhead transmission lines are prone to frequent abnormalities in transmission equipment during long-term operation in harsh outdoor environments. The traditional manual inspection of towers one by one not only has a large workload, low efficiency, and high investment costs, but the long-term power inspection work in complex geographical environments will also threaten the lives of operators.

[0004] At present, the partial discharge detection method using drones to fuse multi-spectrum is not yet mature. Traditional partial discharge detection methods usually rely on a single optical or electrical technology, which has limited detection accuracy, is prone to missed detection or misjudgment, and has the problem of low accuracy of abnormal detection.

[0005] Currently, no effective solution has been proposed to address the problem of low accuracy of anomaly detection. Summary of the invention

[0006] The embodiments of the present invention provide a partial discharge detection method, device, electronic device and computer program product to at least solve the technical problem of low accuracy of abnormality detection.

[0007] According to one aspect of an embodiment of the present invention, a partial discharge detection method is provided, comprising: acquiring an image to be detected of a transmission line, wherein the image to be detected includes at least: a visible light image, an ultraviolet image, and an infrared image of the same portion of the transmission line; performing a partial discharge qualitative analysis of the transmission line using the visible light image to obtain a partial discharge qualitative analysis result, wherein the partial discharge qualitative analysis is used to detect discharge features in the visible light image and determine a discharge location where discharge activity occurs in the transmission cable; performing a partial discharge quantitative analysis of the transmission line using the ultraviolet image and the infrared image to obtain a partial discharge qualitative analysis result, wherein the partial discharge quantitative analysis is used to detect a radiation value using the ultraviolet image, construct a temperature field using the infrared image, and determine a discharge degree where discharge activity occurs in the transmission cable according to the radiation value and the temperature field; performing feature point matching on the visible light image, the ultraviolet image, and the infrared image to obtain a target image, wherein the target image is used to display the discharge location determined according to the partial discharge qualitative analysis result and the discharge degree determined according to the partial discharge qualitative analysis result.

[0008] Optionally, using the visible light image to perform a qualitative analysis of local discharge of the transmission line to obtain a qualitative analysis result of local discharge includes: extracting a directional gradient histogram feature vector of the visible light image; using a preset feature recognition model to perform the qualitative analysis of local discharge on the directional gradient histogram feature vector to obtain the qualitative analysis result of local discharge, wherein the preset feature recognition model is a pre-trained neural network model for detecting the discharge feature in the directional gradient histogram feature vector, and the analysis result is used to mark the discharge location where the discharge feature appears when the discharge feature exists in the visible light image.

[0009] Optionally, extracting the directional gradient histogram feature of the visible light image includes: performing equalization processing on the original pixel value of each pixel point in the visible light image to obtain an equalized image, wherein the equalized image includes a plurality of cells of the same size; determining a feature block gradient histogram of each image feature block in the equalized image, wherein each image feature block includes a preset number of cells; and connecting all the feature block gradient histograms in the equalized image to obtain the directional gradient histogram feature.

[0010] Optionally, equalization processing is performed on the original pixel values ​​of each pixel point in the visible light image to obtain an equalized image, including: counting the number of times each original pixel value in the visible light image appears to obtain the frequency of each original pixel value; accumulating the frequencies of the original pixel values ​​that are less than the target pixel value to obtain the probability of the target pixel value appearing in the visible light image, wherein the target pixel value is obtained by traversing multiple original pixel values ​​of the visible light image; determining the mapping pixel value corresponding to each target pixel value according to the difference between the probability of each target pixel value in the visible light image and the probability of the minimum pixel value in the visible light image; and replacing the target pixel value in the visible light image with the corresponding mapping pixel value to obtain the equalized image.

[0011] Optionally, determining the feature block gradient histogram of each image feature block in the equalized image includes: determining the gradient amplitude and gradient direction of each pixel point in the equalized image; constructing a cell gradient histogram for each cell in the equalized image according to the gradient amplitude and the gradient direction, wherein, in the cell gradient histogram, the abscissa is a plurality of preset intervals to which the gradient direction belongs, and the ordinate is the gradient amplitude of a plurality of pixel points whose gradient direction is in the same preset interval; and normalizing the cell gradient histograms of a plurality of cells in each image feature block to obtain the feature block gradient histogram.

[0012] Optionally, using the ultraviolet image and the infrared image to perform a quantitative analysis of partial discharge of the transmission line to obtain a qualitative analysis result of partial discharge includes: detecting the radiation value corresponding to each pixel in the ultraviolet image, and counting the target ultraviolet pixels whose radiation values ​​exceed a preset radiation threshold to obtain an ultraviolet analysis result, wherein the radiation value is used to quantitatively describe the discharge activity of the transmission line, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; using the infrared image to construct a temperature field cloud map of the transmission line to obtain an infrared analysis result, wherein the temperature field cloud map is used to describe the temperature value corresponding to each pixel in the infrared image, and the temperature value is used to quantitatively describe the discharge activity of the transmission line, and the pixel whose temperature value exceeds the preset temperature threshold is the target infrared pixel, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; using a weighted evaluation strategy to perform a comprehensive quantitative analysis on the ultraviolet image and the infrared image to obtain the quantitative analysis result of partial discharge, wherein the comprehensive quantitative analysis is used to assign evaluation weights to the ultraviolet analysis result and the infrared analysis result and then superimpose them to obtain the quantitative analysis result of partial discharge.

[0013] Optionally, performing feature point matching on the visible light image, the ultraviolet image and the infrared image to obtain a target image includes: performing a first histogram matching on the ultraviolet image and the visible light image to obtain a first grayscale image, wherein the first histogram matching is used to make the grayscale distribution of the ultraviolet image and the visible light image similar; performing a second histogram matching on the infrared image and the visible light image to obtain a second grayscale image, wherein the second histogram matching is used to make the grayscale distribution of the infrared image and the visible light image similar; performing feature point matching on the visible light image, the first grayscale image and the second grayscale image to obtain the target image based on the same coordinate system, wherein the visible light image serves as the base map of the combined image, and the target image is used to display the radiation value determined based on the ultraviolet image and the temperature field determined based on the infrared image on the basis of displaying the visible light image.

[0014] According to another aspect of an embodiment of the present invention, there is also provided a partial discharge detection device, comprising: an acquisition module, used to acquire an image to be detected of a transmission line, wherein the image to be detected comprises at least: a visible light image, an ultraviolet image and an infrared image of the same part of the transmission line; a first analysis module, used to perform a qualitative analysis of partial discharge of the transmission line using the visible light image to obtain a result of the qualitative analysis of partial discharge, wherein the qualitative analysis of partial discharge is used to detect discharge features in the visible light image and determine the discharge part of the transmission cable where discharge activity occurs; a second analysis module, used to perform a qualitative analysis of partial discharge of the transmission line using the ultraviolet image and the infrared image; The infrared image is used to perform a quantitative analysis of partial discharge of the transmission line to obtain a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect the radiation value using the ultraviolet image, construct a temperature field using the infrared image, and determine the discharge degree of the discharge activity of the transmission cable according to the radiation value and the temperature field; a matching module is used to match the feature points of the visible light image, the ultraviolet image and the infrared image to obtain a target image, wherein the target image is used to display the discharge location determined according to the qualitative analysis result of partial discharge, and the discharge degree determined according to the qualitative analysis result of partial discharge.

[0015] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-mentioned partial discharge detection method through the computer program.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is provided, comprising computer instructions, which implement the steps of the above-mentioned partial discharge detection method when executed by a processor.

[0017] In an embodiment of the present invention, an image to be detected of a transmission line is obtained, wherein the image to be detected includes at least: a visible light image, an ultraviolet image, and an infrared image of the same part of the transmission line; a qualitative analysis of partial discharge of the transmission line is performed using the visible light image to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect discharge characteristics in the visible light image and determine the discharge position where the transmission cable has discharge activity; a quantitative analysis of partial discharge of the transmission line is performed using the ultraviolet image and the infrared image to obtain a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect the radiation value using the ultraviolet image and to construct the temperature field using the infrared image, and to determine the transmission cable according to the radiation value and the temperature field. The discharge degree of the discharge activity; the visible light image, the ultraviolet image and the infrared image are matched with feature points to obtain a target image, wherein the target image is used to display the discharge location determined according to the results of the qualitative analysis of the partial discharge, and the discharge degree determined according to the results of the qualitative analysis of the partial discharge, so as to respectively use the visible light image to perform the qualitative analysis of the partial discharge of the transmission line, and use the ultraviolet image and the infrared image to perform the quantitative analysis of the partial discharge of the transmission line, which can more accurately realize the partial discharge analysis of the transmission line, and can integrate the partial discharge analysis results into the target image for comprehensive display, thereby achieving the technical effect of improving the accuracy of partial discharge detection, and then solving the technical problem of low accuracy of abnormality detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 is a flow chart of a partial discharge detection method according to an embodiment of the present invention;

[0020] Figure 2 is a schematic diagram of a method for detecting partial discharge of a UAV power transmission line based on ultraviolet imaging according to an embodiment of the present invention;

[0021] Figure 3 is a schematic diagram of a partial discharge detection device according to an embodiment of the present invention;

[0022] Figure 4 It is a structural block diagram of a computer terminal according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] According to an embodiment of the present invention, an embodiment of a partial discharge detection method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Figure 1 is a flow chart of a partial discharge detection method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0027] Step S102, obtaining an image to be detected of the power transmission line, wherein the image to be detected includes at least: a visible light image, an ultraviolet image, and an infrared image of the same part of the power transmission line;

[0028] Step S104, using the visible light image to perform a qualitative analysis of partial discharge of the transmission line to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect discharge characteristics in the visible light image and determine the discharge location where the transmission cable has discharge activity;

[0029] Step S106, using the ultraviolet image and the infrared image to perform a quantitative analysis of partial discharge of the transmission line to obtain a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect the radiation value using the ultraviolet image, construct the temperature field using the infrared image, and determine the discharge degree of the discharge activity of the transmission cable according to the radiation value and the temperature field;

[0030] Step S108, matching the visible light image, the ultraviolet image and the infrared image by feature points to obtain a target image, wherein the target image is used to display the discharge location determined according to the partial discharge qualitative analysis result and the discharge degree determined according to the partial discharge qualitative analysis result.

[0031] In an embodiment of the present invention, an image to be detected of a transmission line is obtained, wherein the image to be detected includes at least: a visible light image, an ultraviolet image, and an infrared image of the same part of the transmission line; a qualitative analysis of partial discharge of the transmission line is performed using the visible light image to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect discharge characteristics in the visible light image and determine the discharge position where the transmission cable has discharge activity; a quantitative analysis of partial discharge of the transmission line is performed using the ultraviolet image and the infrared image to obtain a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect the radiation value using the ultraviolet image and to construct the temperature field using the infrared image, and to determine the transmission cable according to the radiation value and the temperature field. The discharge degree of the discharge activity; the visible light image, the ultraviolet image and the infrared image are matched with feature points to obtain a target image, wherein the target image is used to display the discharge location determined according to the results of the qualitative analysis of the partial discharge, and the discharge degree determined according to the results of the qualitative analysis of the partial discharge, so as to respectively use the visible light image to perform the qualitative analysis of the partial discharge of the transmission line, and use the ultraviolet image and the infrared image to perform the quantitative analysis of the partial discharge of the transmission line, which can more accurately realize the partial discharge analysis of the transmission line, and can integrate the partial discharge analysis results into the target image for comprehensive display, thereby achieving the technical effect of improving the accuracy of partial discharge detection, and then solving the technical problem of low accuracy of abnormality detection.

[0032] In the above step S102, a camera can be used to capture the image to be inspected of the transmission line, and the camera includes: a visible light camera for capturing visible light images, an ultraviolet camera for capturing ultraviolet images, and an infrared camera for capturing infrared images, wherein the visible light camera, the ultraviolet camera and the infrared camera can capture images of the same position of the transmission line.

[0033] In the above step S104, the qualitative analysis of partial discharge can be implemented by using image recognition technology. The specific solution can be: detecting whether there is a discharge feature in the optical image that is used to indicate the existence of partial discharge in the transmission line, wherein the discharge feature can be an arc generated by the discharge, or a burn mark caused by the heat of the discharge arc.

[0034] As an optional embodiment, using visible light images to perform a qualitative analysis of partial discharge of transmission lines to obtain a qualitative analysis result of partial discharge includes: extracting a directional gradient histogram feature vector of the visible light image; using a preset feature recognition model to perform a qualitative analysis of partial discharge on the directional gradient histogram feature vector to obtain a qualitative analysis result of partial discharge, wherein the preset feature recognition model is a pre-trained neural network model for detecting discharge features in the directional gradient histogram feature vector, and the analysis result is used to mark the discharge location where the discharge feature appears when there is a discharge feature in the visible light image.

[0035] In the above-mentioned embodiment of the present application, when performing discharge feature analysis on a visible light image, a directional gradient histogram method can be used to extract a directional gradient histogram feature vector of the visible light image, and then a preset feature recognition model based on a neural network structure can be used to detect whether there is a discharge feature in the directional gradient histogram feature vector. If there is a discharge feature, it indicates that there is a discharge activity in the visible light image, and then the position of the discharge feature is marked to achieve the marking of the discharge site.

[0036] It should be noted that the Histogram of Oriented Gradient (HOG) is a feature descriptor used in computer vision and image processing for target detection. This technology is used to calculate the statistical value of the directional information of local image gradients. This method has many similarities with edge orientation histograms, scale-invariant feature transform descriptors, and shape contexts, but the difference is that the HOG descriptor is calculated on a dense grid of uniformly spaced cells, and in order to improve performance, overlapping local contrast normalization is also used.

[0037] As an optional embodiment, extracting directional gradient histogram features of a visible light image includes: performing equalization processing on the original pixel values ​​of each pixel point in the visible light image to obtain an equalized image, wherein the equalized image includes multiple cells of the same size; determining a feature block gradient histogram of each image feature block in the equalized image, wherein each image feature block includes a preset number of cells; and connecting all feature block gradient histograms in the equalized image to obtain directional gradient histogram features.

[0038] In the above-mentioned embodiment of the present application, by equalizing the original pixel value of each pixel point in the visible light image, dividing the equalized image obtained by the equalization processing into multiple cells, and then combining the multiple cells into an image feature block, and obtaining the feature block gradient histogram in each image feature block, and then connecting the feature block gradient histograms extracted from the multiple image feature blocks, it is possible to obtain a directional gradient histogram feature that can accurately highlight the image features, and then, when there is a discharge feature in the visible light image, the discharge feature can be more obviously highlighted through the directional gradient histogram feature.

[0039] As an optional embodiment, the original pixel value of each pixel point in the visible light image is equalized to obtain an equalized image, including: counting the number of times each original pixel value in the visible light image appears to obtain the frequency of each original pixel value; accumulating the frequencies of original pixel values ​​that are less than the target pixel value to obtain the probability of the target pixel value appearing in the visible light image, wherein the target pixel value is obtained by traversing multiple original pixel values ​​of the visible light image; determining the mapping pixel value corresponding to each target pixel value according to the difference between the probability of each target pixel value in the visible light image and the probability of the minimum pixel value in the visible light image; and replacing the target pixel value in the visible light image with the corresponding mapping pixel value to obtain an equalized image.

[0040] In the above-mentioned embodiment of the present application, when the original pixel value of each pixel point in the visible light image is equalized, the cumulative distribution function CDF can be used to determine the probability of each target pixel value in the visible light image appearing in the visible light image, and the mapping pixel value corresponding to each target pixel value is determined based on the probability difference between each target pixel value and the minimum pixel value in the visible light image, and then the mapping pixel value is used to replace the target pixel value in the visible light image, so as to achieve equalization of the visible light image and obtain a balanced image.

[0041] As an optional example, accumulating the frequencies of original pixel values ​​that are smaller than the target pixel value to obtain the probability of the target pixel value appearing in the visible light image includes: using a cumulative distribution function CDF, accumulating the frequencies of original pixel values ​​that are smaller than the target pixel value to obtain the probability of the target pixel value appearing in the visible light image.

[0042] It should be noted that the cumulative distribution function CDF is the integral of the frequency distribution function PDF. The frequency distribution function PDF represents the probability that each pixel value (such as the target pixel value) appears in the original image (such as the visible light image). The CDF can be obtained by accumulating the PDF.

[0043] Optionally, for a gray value i (such as a target pixel value), the calculation formula of CDF(i) is: Wherein, P(j) represents the frequency of occurrence of a pixel with a gray value of j in the visible light image, and j is a pixel value less than i.

[0044] It should be noted that in the fields of image recognition and image processing, grayscale values ​​and pixel values ​​can be interchanged.

[0045] Optionally, each pixel value in the original image (ie, the visible light image) is mapped to a new pixel value, so that the equalized histogram is approximately a uniformly distributed histogram.

[0046] As an optional example, determining the mapping pixel value corresponding to each target pixel value according to the difference between the probability of each target pixel value in the visible light image and the probability of the minimum pixel value in the visible light image includes: using a mapping function to determine the mapping pixel value corresponding to each target pixel value according to the difference between the probability of each target pixel value in the visible light image and the probability of the minimum pixel value in the visible light image.

[0047] It should be noted that the mapping function is: Among them, H(i) represents the mapped pixel value (i.e., the mapped pixel value), M and N respectively represent the width and height of the image (such as a visible light image or a balanced image), L represents the range of the pixel value, and min represents the minimum pixel value in the original image (such as a visible light image).

[0048] As an optional embodiment, determining a feature block gradient histogram of each image feature block in an equalized image includes: determining a gradient amplitude and a gradient direction of each pixel in the equalized image; constructing a cell gradient histogram for each cell in the equalized image according to the gradient amplitude and the gradient direction, wherein in the cell gradient histogram, the horizontal axis is a plurality of preset intervals to which the gradient direction belongs, and the vertical axis is a gradient amplitude of a plurality of pixels whose gradient direction is in the same preset interval; and normalizing the cell gradient histograms of a plurality of cells in each image feature block to obtain a feature block gradient histogram.

[0049] In the above embodiment of the present application, the image features in each cell are represented in the form of a histogram to obtain a cell gradient histogram of each cell, and then the cell gradient histograms of multiple cells in the same image feature block are normalized to obtain a feature block gradient histogram of each image feature block, thereby determining the feature block gradient histogram.

[0050] As an optional embodiment, using ultraviolet images and infrared images to perform quantitative analysis on partial discharge of transmission lines to obtain the partial discharge qualitative analysis results includes: detecting the radiation value corresponding to each pixel in the ultraviolet image, and counting the target ultraviolet pixels whose radiation values ​​exceed a preset radiation threshold to obtain the ultraviolet analysis results, wherein the radiation value is used to quantitatively describe the discharge activity of the transmission line, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; using the infrared image to construct a temperature field cloud map of the transmission line to obtain the infrared analysis results, wherein the temperature field cloud map is used to describe the temperature value corresponding to each pixel in the infrared image, the temperature value is used to quantitatively describe the discharge activity of the transmission line, the pixel whose temperature value exceeds the preset temperature threshold is the target infrared pixel, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; using a weighted evaluation strategy to perform comprehensive quantitative analysis on the ultraviolet image and the infrared image to obtain the partial discharge quantitative analysis results, wherein the comprehensive quantitative analysis is used to assign evaluation weights to the ultraviolet analysis results and the infrared analysis results and then superimpose them to obtain the partial discharge quantitative analysis results.

[0051] In the above-mentioned embodiment of the present application, the qualitative analysis result of partial discharge can be performed in combination with the ultraviolet image and the infrared image, wherein, when discharge activity occurs in the transmission line, an arc will be generated, and temperature and radiation will be generated in the arc. Then, the radiation generated by the discharge activity in the transmission line can be represented by the ultraviolet image, and the temperature generated by the discharge activity in the transmission line can be represented by the infrared image. Thus, by performing ultraviolet analysis based on the radiation condition through the ultraviolet image, and performing infrared analysis based on the temperature condition through the infrared image, it is possible to capture the discharge activity in the transmission line, and then weighting and superimposing the infrared analysis results obtained based on the infrared image and the ultraviolet analysis results obtained based on the ultraviolet image, it is possible to achieve quantitative analysis of partial discharge of the transmission line.

[0052] It should be noted that in the case of local discharge in the transmission line, the radiation generated by the electric arc produced by the discharge is concentrated in the discharge location. Therefore, by detecting the radiation value of each pixel point in the ultraviolet image, the target ultraviolet pixel points whose radiation value exceeds the preset radiation threshold can be determined. According to the distribution of the target ultraviolet pixel points, the discharge location where the transmission cable has discharge activity can be determined; according to the number of target ultraviolet pixel points and the radiation difference value whose radiation value exceeds the preset radiation threshold, the discharge degree of the discharge activity in the transmission line can be indicated.

[0053] It should be noted that in the case of local discharge in the transmission line, the heat generated by the arc produced by the discharge is concentrated in the discharge location. Therefore, by constructing a temperature field cloud map of the transmission line based on the infrared image, the target area with higher temperature in the transmission line can be determined in the temperature field cloud map. For example, the target area is the area where the target infrared pixel points with a temperature value higher than the preset temperature threshold are located. Then, the target area can be determined as the discharge location where the transmission cable has discharge activity. Then, based on the temperature difference between the target area and other areas (or the preset temperature threshold), the discharge degree of the discharge activity in the transmission line can be indicated.

[0054] As an optional embodiment, matching feature points of a visible light image, an ultraviolet image and an infrared image to obtain a target image includes: matching the ultraviolet image with the visible light image by a first histogram to obtain a first grayscale image, wherein the first histogram matching is used to make the grayscale distributions of the ultraviolet image and the visible light image similar; matching the infrared image with the visible light image by a second histogram to obtain a second grayscale image, wherein the second histogram matching is used to make the grayscale distributions of the infrared image and the visible light image similar; matching feature points of the visible light image, the first grayscale image and the second grayscale image to obtain a target image based on the same coordinate system, wherein the visible light image serves as the base map of the combined image, and the target image is used to display the radiation value determined based on the ultraviolet image and the temperature field determined based on the infrared image on the basis of displaying the visible light image.

[0055] In the above-mentioned embodiment of the present application, feature points of the visible light image, the ultraviolet image and the infrared image are matched to realize the fusion of the visible light image, the ultraviolet image and the infrared image. Furthermore, in the fusion process, the grayscale normalization of the visible light image, the ultraviolet image and the infrared image can be realized by histogram matching to obtain a first grayscale image of the ultraviolet image and a second grayscale image of the infrared image. Feature points of the normalized grayscale visible light image, the ultraviolet image and the infrared image are then matched. The visible light image is used as the base map of the combined image, and the first grayscale image and the second grayscale image are overlaid on the visible light image based on the matched feature points to obtain a target image. The target image can display both the visible light image and the radiation value determined based on the ultraviolet image and the temperature field determined based on the infrared image.

[0056] The present invention also provides a preferred embodiment, which provides a UAV transmission line partial discharge detection method based on ultraviolet imaging, a transmission line partial discharge detection method using a fusion multi-spectrum, and partial discharge qualitative analysis and partial discharge quantitative analysis; through these two steps of analysis and processing, the transmission line fault detection capability and detection accuracy can be effectively improved.

[0057] Figure 2is a schematic diagram of a method for detecting partial discharge of a UAV power transmission line based on ultraviolet imaging according to an embodiment of the present invention, such as Figure 2 As shown, the following steps are included:

[0058] Step S202, acquiring an ultraviolet image, an infrared image, and a visible light image of the transmission line.

[0059] Step S204, partial discharge qualitative analysis, directional gradient histogram and neural network.

[0060] Step S206: quantitative analysis of partial discharge, light pixel spectrum analysis and thermal field evaluation.

[0061] Step S208, real scene partial discharge analysis, superposition and fusion of ultraviolet image, infrared image and visible light image.

[0062] Optionally, the input of partial discharge qualitative analysis is connected to the outputs of ultraviolet image, infrared image and visible light image, the output of partial discharge qualitative analysis is connected to the input of partial discharge quantitative analysis, and the input of real scene partial discharge analysis is connected to the input of partial discharge quantitative analysis.

[0063] As an optional example, the partial discharge qualitative analysis includes: statistically analyzing the histogram of the original image, calculating the cumulative distribution function (CDF), calculating the pixel value after equalization, pixel replacement, and extracting image features by using the Histogram of Directed Gradients (HOG).

[0064] As an optional example, the partial discharge quantitative analysis includes: ultraviolet image analysis, infrared image analysis, and comprehensive quantitative analysis; its features include: pixel-level analysis of ultraviolet images, temperature field analysis of infrared images, and comprehensive quantitative analysis.

[0065] As an optional example, the real-scene partial discharge analysis includes: a SIFT algorithm for feature point matching and a gamma correction method.

[0066] As an optional example, the partial discharge qualitative analysis includes the following steps:

[0067] Step S11, counting the histogram of the original image (ie, the visible light image), specifically, counting the number of occurrences of each pixel value, normalizing it, and obtaining the frequency of each pixel value.

[0068] Step S12, calculating the cumulative distribution function CDF.

[0069] It should be noted that the cumulative distribution function CDF is the integral of the frequency distribution function PDF, which represents the probability of each pixel value appearing in the original image (ie, the visible light image).

[0070] Optionally, the CDF can be obtained by accumulating the PDF. For a gray value i, the calculation formula of the CDF is as follows: Among them, P(j) represents the frequency of pixels with gray value j appearing in the image.

[0071] Step S13, calculating the equalized pixel value.

[0072] Optionally, each pixel value in the original image (ie, the visible light image) is mapped to a new pixel value so that the equalized histogram approximates a uniformly distributed histogram. The mapping function can be calculated by the following formula: Among them, H(i) represents the mapped pixel value, M and N represent the width and height of the image respectively, L represents the range of pixel values, and min represents the minimum pixel value in the original image (i.e., visible light image).

[0073] Step S14: pixel replacement. Specifically, the pixel values ​​in the original image (ie, the visible light image) are replaced with the mapped pixel values ​​to complete the histogram equalization.

[0074] Step S15: feature extraction. Specifically, image features are extracted by using the Histogram of Oriented Gradients (HOG).

[0075] As an optional example, image features are extracted by using the Histogram of Oriented Gradients (HOG). The specific steps are as follows:

[0076] Step S151, calculate the gradient magnitude m and gradient direction θ of each pixel in the image, where: Among them, I x and I y are the gradients of the image in the x and y directions.

[0077] Step S152, constructing a gradient histogram. Specifically, the original image (i.e., the visible light image) is divided into cells, the gradient is calculated for the pixels in each cell, and a histogram H(θ) of the gradient direction is constructed, where: ω(x,y) is the weight of the pixel (x,y), which is replaced by the gradient magnitude.

[0078] Step S153, block normalization. Specifically, 3*3 cells are selected for each image feature block, and the histogram in each image feature block is normalized, specifically: Among them, υ is the normalization factor of the gradient histogram in the image feature block; H i is the value of the gradient direction histogram of the cell in the image feature block; ε is a constant, which is 10 -5 ;H normalized is the normalized gradient histogram.

[0079] Step S154, forming a final feature vector. Specifically, the normalized histograms in all image feature blocks are connected to form a final HOG feature vector. The above HOG feature vector is used as a BP neural network input, and a qualitative analysis is performed through the neural network.

[0080] As an optional example, partial discharge quantitative analysis includes:

[0081] Step S21, pixel-level analysis of the UV image. Specifically, it includes: extracting the radiation value of each pixel from the UV image, using image processing techniques such as image segmentation and thresholding to select pixels above a preset threshold. Counting the number of pixels in these high-intensity discharge areas to reflect the intensity of the discharge activity. The intensity information of the UV radiation is used to quantitatively describe the local discharge activity.

[0082] Step S22, temperature field analysis of infrared images. Specifically, it includes: using infrared images to construct a temperature field cloud map, in which each pixel corresponds to the temperature value at the corresponding position. Using infrared cameras to capture infrared images to ensure the accuracy and reliability of the temperature field. Using image processing techniques such as temperature calibration and temperature distribution analysis, evaluate the temperature changes at different parts of the transmission line. Using the temperature information of infrared images, the thermal state of the power equipment can be comprehensively evaluated.

[0083] Step S23, comprehensive quantitative analysis. Specifically includes: integrating the analysis results of the ultraviolet image and the infrared image. According to the number of high-intensity discharge areas in the ultraviolet image and the temperature field information in the infrared image, the discharge degree is quantitatively evaluated. Combining the information of the two images, a comprehensive discharge degree evaluation result is obtained. Through this comprehensive quantitative analysis method, the degree and location of local discharge activities can be more accurately evaluated, providing a basis for preventive maintenance of power equipment. Ultimately, the technical means of using pixel-level analysis and temperature field analysis can more accurately evaluate the local discharge activities of transmission lines.

[0084] As an optional example, real-life partial discharge analysis includes: using an image registration algorithm, and using a SIFT (scale-invariant feature transform) algorithm based on feature point matching, to align the three images to the same coordinate system. Use the visible light image as the base map, and convert the infrared image and ultraviolet image into grayscale images respectively. Perform histogram matching on the grayscale image to make it similar to the grayscale distribution of the visible light image. Superimpose the matched infrared image and ultraviolet image on the visible light image to form an RGB color image. Adjust the brightness and contrast of the superimposed image, and use the gamma correction method to make the information of each layer clearly displayed. Map the brightness values ​​of the infrared image and the ultraviolet image to a suitable transparency range, so that the temperature and discharge information are displayed on the basis of the complete visible light information of the base map.

[0085] According to an embodiment of the present invention, a partial discharge detection device embodiment is also provided. It should be noted that the partial discharge detection device can be used to execute the partial discharge detection method in the embodiment of the present invention, and the partial discharge detection method in the embodiment of the present invention can be executed in the partial discharge detection device.

[0086] Figure 3 is a schematic diagram of a partial discharge detection device according to an embodiment of the present invention. Figure 3 As shown, the device may include: an acquisition module 32, used to acquire the image to be detected of the transmission line, wherein the image to be detected includes at least: a visible light image, an ultraviolet image and an infrared image of the same part of the transmission line; a first analysis module 34, used to perform a qualitative analysis of partial discharge of the transmission line using the visible light image to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect the discharge characteristics in the visible light image and determine the discharge location where the transmission cable has a discharge activity; a second analysis module 36, used to perform the qualitative analysis using the ultraviolet image and the infrared image A partial discharge quantitative analysis of a transmission line is performed to obtain a partial discharge qualitative analysis result, wherein the partial discharge quantitative analysis is used to detect the radiation value using the ultraviolet image, construct the temperature field using the infrared image, and determine the discharge degree of the discharge activity in the transmission cable according to the radiation value and the temperature field; a matching module 38 is used to match the feature points of the visible light image, the ultraviolet image and the infrared image to obtain a target image, wherein the target image is used to display the discharge location determined according to the partial discharge qualitative analysis result, and the discharge degree determined according to the partial discharge qualitative analysis result.

[0087] It should be noted that the acquisition module 32 in this embodiment can be used to execute step S102 in the embodiment of the present application, the first analysis module 34 in this embodiment can be used to execute step S104 in the embodiment of the present application, the second analysis module 36 in this embodiment can be used to execute step S106 in the embodiment of the present application, and the matching module 38 in this embodiment can be used to execute step S108 in the embodiment of the present application. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments.

[0088] In an embodiment of the present invention, an image to be detected of a transmission line is obtained, wherein the image to be detected includes at least: a visible light image, an ultraviolet image, and an infrared image of the same part of the transmission line; a qualitative analysis of partial discharge of the transmission line is performed using the visible light image to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect discharge characteristics in the visible light image and determine the discharge position where the transmission cable has discharge activity; a quantitative analysis of partial discharge of the transmission line is performed using the ultraviolet image and the infrared image to obtain a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect the radiation value using the ultraviolet image and to construct the temperature field using the infrared image, and to determine the transmission cable according to the radiation value and the temperature field. The discharge degree of the discharge activity; the visible light image, the ultraviolet image and the infrared image are matched with feature points to obtain a target image, wherein the target image is used to display the discharge location determined according to the results of the qualitative analysis of the partial discharge, and the discharge degree determined according to the results of the qualitative analysis of the partial discharge, so as to respectively use the visible light image to perform the qualitative analysis of the partial discharge of the transmission line, and use the ultraviolet image and the infrared image to perform the quantitative analysis of the partial discharge of the transmission line, which can more accurately realize the partial discharge analysis of the transmission line, and can integrate the partial discharge analysis results into the target image for comprehensive display, thereby achieving the technical effect of improving the accuracy of partial discharge detection, and then solving the technical problem of low accuracy of abnormality detection.

[0089] As an optional embodiment, the first analysis module includes: an extraction unit, used to extract the directional gradient histogram feature vector of the visible light image; a first analysis unit, used to use a preset feature recognition model to perform the local discharge qualitative analysis on the directional gradient histogram feature vector to obtain the local discharge qualitative analysis result, wherein the preset feature recognition model is a pre-trained neural network model, used to detect the discharge feature in the directional gradient histogram feature vector, and the analysis result is used to mark the discharge site where the discharge feature appears when the discharge feature exists in the visible light image.

[0090] As an optional embodiment, the extraction unit includes: a first processing subunit, used to equalize the original pixel value of each pixel point in the visible light image to obtain an equalized image, wherein the equalized image includes a plurality of cells of the same size; a first determination subunit, used to determine the feature block gradient histogram of each image feature block in the equalized image, wherein each image feature block includes a preset number of cells; a connection subunit, used to connect all the feature block gradient histograms in the equalized image to obtain the directional gradient histogram feature.

[0091] As an optional embodiment, the processing subunit includes: a statistical subunit, used to count the number of times each original pixel value in the visible light image appears, and obtain the frequency of each original pixel value; an accumulation subunit, used to accumulate the frequencies of the original pixel values ​​that are less than the target pixel value, and obtain the probability of the target pixel value appearing in the visible light image, wherein the target pixel value is obtained by traversing the multiple original pixel values ​​of the visible light image; a second determination subunit, used to determine the mapping pixel value corresponding to each target pixel value based on the difference between the probability of each target pixel value in the visible light image and the probability of the minimum pixel value in the visible light image; a replacement subunit, used to replace the target pixel value in the visible light image with the corresponding mapping pixel value, and obtain an equalized image.

[0092] As an optional embodiment, the first determination subunit includes: a third determination subunit, used to determine the gradient amplitude and gradient direction of each pixel point in the equalized image; a construction subunit, used to construct a cell gradient histogram for each cell in the equalized image according to the gradient amplitude and the gradient direction, wherein, in the cell gradient histogram, the horizontal axis is a plurality of preset intervals to which the gradient direction belongs, and the vertical axis is the gradient amplitude of a plurality of pixel points whose gradient direction is in the same preset interval; a second processing subunit, used to normalize the cell gradient histograms of the plurality of cells in each image feature block to obtain the feature block gradient histogram.

[0093] As an optional embodiment, the second analysis module includes: a detection unit, which is used to detect the radiation value corresponding to each pixel in the ultraviolet image, and count the target ultraviolet pixels whose radiation values ​​exceed a preset radiation threshold to obtain an ultraviolet analysis result, wherein the radiation value is used to quantitatively describe the discharge activity of the transmission line, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; a construction unit, which is used to construct a temperature field cloud map of the transmission line using the infrared image to obtain an infrared analysis result, wherein the temperature field cloud map is used to describe the temperature value corresponding to each pixel in the infrared image, and the temperature value is used to quantitatively describe the discharge activity of the transmission line, and the pixel whose temperature value exceeds the preset temperature threshold is the target infrared pixel, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; a second analysis unit, which is used to perform a comprehensive quantitative analysis on the ultraviolet image and the infrared image using a weighted evaluation strategy to obtain the partial discharge quantitative analysis result, wherein the comprehensive quantitative analysis is used to assign evaluation weights to the ultraviolet analysis result and the infrared analysis result and then superimpose them to obtain the partial discharge quantitative analysis result.

[0094] As an optional embodiment, the matching module includes: a first matching unit, used to perform a first histogram matching on the ultraviolet image and the visible light image to obtain a first grayscale image, wherein the first histogram matching is used to make the grayscale distribution of the ultraviolet image similar to that of the visible light image; a second matching unit, used to perform a second histogram matching on the infrared image and the visible light image to obtain a second grayscale image, wherein the second histogram matching is used to make the grayscale distribution of the infrared image and the visible light image similar; a third matching unit, used to perform feature point matching on the visible light image, the first grayscale image and the second grayscale image to obtain the target image based on the same coordinate system, wherein the visible light image serves as the base map of the combined image, and the target image is used to display the radiation value determined based on the ultraviolet image and the temperature field determined based on the infrared image on the basis of displaying the visible light image.

[0095] An embodiment of the present invention may provide an electronic device, which may be a computer terminal, and the computer terminal may be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced by a terminal device such as a mobile terminal.

[0096] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

[0097] In this embodiment, the computer terminal can execute the program code of the following steps in the partial discharge detection method: obtaining an image to be detected of the transmission line, wherein the image to be detected includes at least: a visible light image, an ultraviolet image and an infrared image of the same part of the transmission line; using the visible light image to perform a qualitative analysis of partial discharge of the transmission line to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect discharge features in the visible light image and determine a discharge position where discharge activity occurs in the transmission cable; using the ultraviolet image and the infrared image to perform a quantitative analysis of partial discharge of the transmission line to obtain a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect radiation values ​​using the ultraviolet image and to construct a temperature field using the infrared image, and to determine the discharge degree of discharge activity occurring in the transmission cable according to the radiation value and the temperature field; matching the visible light image, the ultraviolet image and the infrared image with feature points to obtain a target image, wherein the target image is used to display the discharge position determined according to the qualitative analysis result of partial discharge and the discharge degree determined according to the qualitative analysis result of partial discharge.

[0098] Figure 4 is a structural block diagram of a computer terminal according to an embodiment of the present invention. Figure 4As shown, the computer terminal 40 may include: one or more (only one is shown in the figure) processors 42 , and a memory 44 .

[0099] The memory can be used to store software programs and modules, such as program instructions / modules corresponding to the partial discharge detection method and device in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the partial discharge detection method described above is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal 40 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0100] The processor can call the information and application program stored in the memory through the transmission device to perform the following steps: obtaining the image to be detected of the transmission line, wherein the image to be detected includes at least: a visible light image, an ultraviolet image and an infrared image of the same part of the transmission line; using the visible light image to perform a qualitative analysis of partial discharge of the transmission line to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect the discharge characteristics in the visible light image and determine the discharge position where the transmission cable has discharge activity; using the ultraviolet image and the infrared image to perform a quantitative analysis of partial discharge of the transmission line to obtain a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect the radiation value using the ultraviolet image, construct the temperature field using the infrared image, and determine the discharge degree of the discharge activity of the transmission cable according to the radiation value and the temperature field; matching the visible light image, the ultraviolet image and the infrared image with feature points to obtain a target image, wherein the target image is used to display the discharge position determined according to the qualitative analysis result of partial discharge and the discharge degree determined according to the qualitative analysis result of partial discharge.

[0101] Optionally, the processor may also execute the program code of the following steps: extracting the directional gradient histogram feature vector of the visible light image; performing a local discharge qualitative analysis on the directional gradient histogram feature vector using a preset feature recognition model to obtain a local discharge qualitative analysis result, wherein the preset feature recognition model is a pre-trained neural network model for detecting discharge features in the directional gradient histogram feature vector, and the analysis result is used to mark the discharge location where the discharge feature appears when the discharge feature exists in the visible light image.

[0102] Optionally, the processor may also execute the program code of the following steps: performing equalization processing on the original pixel value of each pixel point in the visible light image to obtain an equalized image, wherein the equalized image includes a plurality of cells of the same size; determining a feature block gradient histogram of each image feature block in the equalized image, wherein each image feature block includes a preset number of cells; and connecting all feature block gradient histograms in the equalized image to obtain a directional gradient histogram feature.

[0103] Optionally, the processor may also execute the following steps of program code: counting the number of times each original pixel value in the visible light image appears to obtain the frequency of each original pixel value; accumulating the frequencies of original pixel values ​​that are less than the target pixel value to obtain the probability of the target pixel value appearing in the visible light image, wherein the target pixel value is obtained by traversing multiple original pixel values ​​of the visible light image; determining the mapping pixel value corresponding to each target pixel value based on the difference between the probability of each target pixel value in the visible light image and the probability of the minimum pixel value in the visible light image; and replacing the target pixel value in the visible light image with the corresponding mapping pixel value to obtain a balanced image.

[0104] Optionally, the processor may also execute the program code of the following steps: determining the gradient amplitude and gradient direction of each pixel in the equalized image; constructing a cell gradient histogram for each cell in the equalized image based on the gradient amplitude and gradient direction, wherein, in the cell gradient histogram, the horizontal axis is a plurality of preset intervals to which the gradient direction belongs, and the vertical axis is the gradient amplitude of a plurality of pixels whose gradient directions are in the same preset interval; and normalizing the cell gradient histograms of a plurality of cells in each image feature block to obtain a feature block gradient histogram.

[0105] Optionally, the processor may also execute the program code of the following steps: detecting the radiation value corresponding to each pixel in the ultraviolet image, and counting the target ultraviolet pixels whose radiation values ​​exceed a preset radiation threshold, to obtain an ultraviolet analysis result, wherein the radiation value is used to quantitatively describe the discharge activity of the transmission line, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; using the infrared image to construct a temperature field cloud map of the transmission line to obtain an infrared analysis result, wherein the temperature field cloud map is used to describe the temperature value corresponding to each pixel in the infrared image, and the temperature value is used to quantitatively describe the discharge activity of the transmission line, and the pixel whose temperature value exceeds the preset temperature threshold is the target infrared pixel, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; using a weighted evaluation strategy to perform a comprehensive quantitative analysis on the ultraviolet image and the infrared image to obtain a partial discharge quantitative analysis result, wherein the comprehensive quantitative analysis is used to assign evaluation weights to the ultraviolet analysis result and the infrared analysis result, and then superimpose them to obtain a partial discharge quantitative analysis result.

[0106] Optionally, the processor may also execute the program code of the following steps: performing a first histogram matching on the ultraviolet image and the visible light image to obtain a first grayscale image, wherein the first histogram matching is used to make the grayscale distributions of the ultraviolet image and the visible light image similar; performing a second histogram matching on the infrared image and the visible light image to obtain a second grayscale image, wherein the second histogram matching is used to make the grayscale distributions of the infrared image and the visible light image similar; performing feature point matching on the visible light image, the first grayscale image and the second grayscale image to obtain a target image based on the same coordinate system, wherein the visible light image serves as the base map of the combined image, and the target image is used to display the radiation value determined based on the ultraviolet image and the temperature field determined based on the infrared image on the basis of displaying the visible light image.

[0107] According to an embodiment of the present invention, a partial discharge detection scheme is provided. In the embodiment of the present invention, an image to be detected of a transmission line is obtained, wherein the image to be detected includes at least: a visible light image, an ultraviolet image, and an infrared image of the same part of the transmission line; a partial discharge qualitative analysis of the transmission line is performed using the visible light image to obtain a partial discharge qualitative analysis result, wherein the partial discharge qualitative analysis is used to detect the discharge characteristics in the visible light image and determine the discharge location where the transmission cable has discharge activity; a partial discharge quantitative analysis of the transmission line is performed using the ultraviolet image and the infrared image to obtain a partial discharge qualitative analysis result, wherein the partial discharge quantitative analysis is used to detect the radiation value using the ultraviolet image, construct the temperature field using the infrared image, and determine the transmission cable according to the radiation value and the temperature field. The discharge degree of the discharge activity; the visible light image, the ultraviolet image and the infrared image are matched with feature points to obtain a target image, wherein the target image is used to display the discharge location determined according to the results of the qualitative analysis of the partial discharge, and the discharge degree determined according to the results of the qualitative analysis of the partial discharge, so as to respectively use the visible light image to perform the qualitative analysis of the partial discharge of the transmission line, and use the ultraviolet image and the infrared image to perform the quantitative analysis of the partial discharge of the transmission line, which can more accurately realize the partial discharge analysis of the transmission line, and can integrate the partial discharge analysis results into the target image for comprehensive display, thereby achieving the technical effect of improving the accuracy of partial discharge detection, and then solving the technical problem of low accuracy of abnormality detection.

[0108] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the computer terminal may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 4 The structure of the electronic device is not limited. For example, the computer terminal 40 may also include Figure 4More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations are shown.

[0109] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a computer program. The computer program can be stored in a non-volatile medium. The non-volatile storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0110] The embodiment of the present invention further provides a non-volatile storage medium. Optionally, in this embodiment, the non-volatile storage medium can be used to store the program code executed by the partial discharge detection method provided by the above embodiment.

[0111] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0112] Optionally, in this embodiment, the non-volatile storage medium is configured to store program codes for executing the following steps: obtaining an image to be detected of a transmission line, wherein the image to be detected includes at least: a visible light image, an ultraviolet image, and an infrared image of the same portion of the transmission line; performing a qualitative analysis of partial discharge of the transmission line using the visible light image to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect discharge features in the visible light image and determine a discharge location where discharge activity occurs in the transmission cable; performing a quantitative analysis of partial discharge of the transmission line using the ultraviolet image and the infrared image to obtain a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect radiation values ​​using the ultraviolet image and to construct a temperature field using the infrared image, and to determine a discharge degree of discharge activity occurring in the transmission cable based on the radiation values ​​and the temperature field; performing feature point matching on the visible light image, the ultraviolet image, and the infrared image to obtain a target image, wherein the target image is used to display a discharge location determined based on the qualitative analysis result of partial discharge and a discharge degree determined based on the qualitative analysis result of partial discharge.

[0113] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: extracting a directional gradient histogram feature vector of a visible light image; performing a local discharge qualitative analysis on the directional gradient histogram feature vector using a preset feature recognition model to obtain a local discharge qualitative analysis result, wherein the preset feature recognition model is a pre-trained neural network model for detecting discharge features in the directional gradient histogram feature vector, and the analysis result is used to mark the discharge location where the discharge feature appears when the discharge feature exists in the visible light image.

[0114] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: performing equalization processing on the original pixel value of each pixel point in the visible light image to obtain an equalized image, wherein the equalized image includes a plurality of cells of the same size; determining a feature block gradient histogram of each image feature block in the equalized image, wherein each image feature block includes a preset number of cells; and connecting all feature block gradient histograms in the equalized image to obtain a directional gradient histogram feature.

[0115] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: counting the number of times each original pixel value appears in the visible light image to obtain the frequency of each original pixel value; accumulating the frequencies of original pixel values ​​that are less than the target pixel value to obtain the probability of the target pixel value appearing in the visible light image, wherein the target pixel value is obtained by traversing multiple original pixel values ​​of the visible light image; determining the mapping pixel value corresponding to each target pixel value based on the difference between the probability of each target pixel value in the visible light image and the probability of the minimum pixel value in the visible light image; and replacing the target pixel value in the visible light image with the corresponding mapping pixel value to obtain a balanced image.

[0116] Optionally, in this embodiment, the non-volatile storage medium is configured to store program codes for executing the following steps: determining the gradient amplitude and gradient direction of each pixel point in the equalized image; constructing a cell gradient histogram for each cell in the equalized image based on the gradient amplitude and gradient direction, wherein, in the cell gradient histogram, the horizontal axis is a plurality of preset intervals to which the gradient direction belongs, and the vertical axis is the gradient amplitude of a plurality of pixel points whose gradient direction is in the same preset interval; and normalizing the cell gradient histograms of a plurality of cells in each image feature block to obtain a feature block gradient histogram.

[0117] Optionally, in this embodiment, the non-volatile storage medium is configured to store program codes for executing the following steps: detecting the radiation value corresponding to each pixel in the ultraviolet image, and counting the target ultraviolet pixels whose radiation values ​​exceed a preset radiation threshold, to obtain an ultraviolet analysis result, wherein the radiation value is used to quantitatively describe the discharge activity of the transmission line, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; using the infrared image to construct a temperature field cloud map of the transmission line to obtain an infrared analysis result, wherein the temperature field cloud map is used to describe the temperature value corresponding to each pixel in the infrared image, and the temperature value is used to quantitatively describe the discharge activity of the transmission line, and the pixel whose temperature value exceeds the preset temperature threshold is the target infrared pixel, and the target ultraviolet pixel is used to reflect the discharge location where the discharge activity occurs; using a weighted evaluation strategy to perform a comprehensive quantitative analysis on the ultraviolet image and the infrared image to obtain a partial discharge quantitative analysis result, wherein the comprehensive quantitative analysis is used to assign evaluation weights to the ultraviolet analysis result and the infrared analysis result and then superimpose them to obtain a partial discharge quantitative analysis result.

[0118] Optionally, in this embodiment, the non-volatile storage medium is configured to store program codes for executing the following steps: performing a first histogram matching on the ultraviolet image and the visible light image to obtain a first grayscale image, wherein the first histogram matching is used to make the grayscale distributions of the ultraviolet image and the visible light image similar; performing a second histogram matching on the infrared image and the visible light image to obtain a second grayscale image, wherein the second histogram matching is used to make the grayscale distributions of the infrared image and the visible light image similar; performing feature point matching on the visible light image, the first grayscale image, and the second grayscale image to obtain a target image based on the same coordinate system, wherein the visible light image serves as the base map of the combined image, and the target image is used to display the radiation value determined based on the ultraviolet image and the temperature field determined based on the infrared image on the basis of displaying the visible light image.

[0119] The embodiment of the present invention further provides a computer program product, including a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, the steps of the partial discharge detection method provided in the above embodiment are implemented.

[0120] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0121] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0122] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0124] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0125] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a non-volatile storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0126] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A partial discharge detection method, characterized in that: include: Acquire an image to be detected of the transmission line, wherein the image to be detected includes at least: a visible light image, an ultraviolet image, and an infrared image of the same part of the transmission line; Using the visible light image to perform a qualitative analysis of partial discharge of the transmission line to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect discharge features in the visible light image and determine a discharge location where discharge activity occurs in the transmission cable; Using the ultraviolet image and the infrared image to perform a quantitative analysis of partial discharge of the transmission line, and obtaining a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect the radiation value using the ultraviolet image, construct the temperature field using the infrared image, and determine the discharge degree of the discharge activity of the transmission cable according to the radiation value and the temperature field; The visible light image, the ultraviolet image and the infrared image are matched with feature points to obtain a target image, wherein the target image is used to display the discharge location determined according to the partial discharge qualitative analysis result and the discharge degree determined according to the partial discharge qualitative analysis result.

2. The method according to claim 1, characterized in that The visible light image is used to perform a qualitative analysis of partial discharge of the transmission line, and the results of the partial discharge qualitative analysis include: Extracting a directional gradient histogram feature vector of the visible light image; The local discharge qualitative analysis is performed on the directional gradient histogram feature vector using a preset feature recognition model to obtain the local discharge qualitative analysis result, wherein the preset feature recognition model is a pre-trained neural network model for detecting the discharge feature in the directional gradient histogram feature vector, and the analysis result is used to mark the discharge site where the discharge feature appears when the discharge feature exists in the visible light image.

3. The method according to claim 2, characterized in that Extracting the directional gradient histogram feature of the visible light image includes: Performing equalization processing on the original pixel value of each pixel point in the visible light image to obtain an equalized image, wherein the equalized image includes a plurality of cells of the same size; Determine a feature block gradient histogram of each image feature block in the equalized image, wherein each of the image feature blocks includes a preset number of cells; All the feature block gradient histograms in the equalized image are connected to obtain the directional gradient histogram feature.

4. The method according to claim 3, characterized in that Performing equalization processing on the original pixel value of each pixel point in the visible light image to obtain an equalized image includes: Counting the number of occurrences of each original pixel value in the visible light image to obtain the frequency of each original pixel value; Accumulating the frequencies of the original pixel values ​​that are smaller than the target pixel value to obtain the probability of the target pixel value appearing in the visible light image, wherein the target pixel value is obtained by traversing the multiple original pixel values ​​of the visible light image; Determining a mapping pixel value corresponding to each of the target pixel values ​​according to a difference between a probability of each of the target pixel values ​​in the visible light image and a probability of a minimum pixel value in the visible light image; The target pixel value in the visible light image is replaced with the corresponding mapped pixel value to obtain the balanced image.

5. The method according to claim 3, characterized in that: Determining a feature block gradient histogram of each image feature block in the equalized image comprises: Determine the gradient magnitude and gradient direction of each pixel in the equalized image; Constructing a cell gradient histogram for each cell in the equalized image according to the gradient amplitude and the gradient direction, wherein in the cell gradient histogram, the abscissa is a plurality of preset intervals to which the gradient direction belongs, and the ordinate is the gradient amplitude of a plurality of pixel points whose gradient direction is in the same preset interval; The cell gradient histograms of the plurality of cells in each of the image feature blocks are normalized to obtain the feature block gradient histogram.

6. The method according to claim 1, characterized in that The partial discharge quantitative analysis of the transmission line is performed using the ultraviolet image and the infrared image, and the partial discharge qualitative analysis results obtained include: Detecting the radiation value corresponding to each pixel in the ultraviolet image, and counting the target ultraviolet pixel points whose radiation values ​​exceed a preset radiation threshold, to obtain an ultraviolet analysis result, wherein the radiation value is used to quantitatively describe the discharge activity of the transmission line, and the target ultraviolet pixel points are used to reflect the discharge location where the discharge activity occurs; The infrared image is used to construct a temperature field cloud map of the transmission line to obtain an infrared analysis result, wherein the temperature field cloud map is used to describe the temperature value corresponding to each pixel point in the infrared image, and the temperature value is used to quantitatively describe the discharge activity of the transmission line. The pixel point whose temperature value exceeds a preset temperature threshold is a target infrared pixel point, and the target ultraviolet pixel point is used to reflect the discharge location where the discharge activity occurs; A weighted evaluation strategy is used to perform a comprehensive quantitative analysis on the ultraviolet image and the infrared image to obtain the partial discharge quantitative analysis result, wherein the comprehensive quantitative analysis is used to assign evaluation weights to the ultraviolet analysis result and the infrared analysis result and then superimpose them to obtain the partial discharge quantitative analysis result.

7. The method according to claim 1, characterized in that Matching feature points of the visible light image, the ultraviolet image, and the infrared image to obtain a target image includes: Performing a first histogram matching on the ultraviolet image and the visible light image to obtain a first grayscale image, wherein the first histogram matching is used to make the grayscale distributions of the ultraviolet image and the visible light image similar; Performing a second histogram matching on the infrared image and the visible light image to obtain a second grayscale image, wherein the second histogram matching is used to make the grayscale distribution of the infrared image and the visible light image similar; The visible light image, the first grayscale image and the second grayscale image are matched with feature points to obtain the target image based on the same coordinate system, wherein the visible light image serves as the base map of the combined image, and the target image is used to display the radiation value determined based on the ultraviolet image and the temperature field determined based on the infrared image on the basis of displaying the visible light image.

8. A partial discharge detection device, characterized in that: include: An acquisition module, used for acquiring an image to be detected of the power transmission line, wherein the image to be detected at least includes: a visible light image, an ultraviolet image and an infrared image of the same part of the power transmission line; A first analysis module is used to perform a qualitative analysis of partial discharge of the transmission line using the visible light image to obtain a qualitative analysis result of partial discharge, wherein the qualitative analysis of partial discharge is used to detect discharge features in the visible light image and determine a discharge location where discharge activity occurs in the transmission cable; A second analysis module is used to perform a quantitative analysis of partial discharge of the transmission line using the ultraviolet image and the infrared image to obtain a qualitative analysis result of partial discharge, wherein the quantitative analysis of partial discharge is used to detect the radiation value using the ultraviolet image, construct the temperature field using the infrared image, and determine the discharge degree of the discharge activity of the transmission cable according to the radiation value and the temperature field; A matching module is used to match the feature points of the visible light image, the ultraviolet image and the infrared image to obtain a target image, wherein the target image is used to display the discharge location determined according to the partial discharge qualitative analysis result and the discharge degree determined according to the partial discharge qualitative analysis result.

9. An electronic device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to execute the partial discharge detection method according to any one of claims 1 to 7 through the computer program.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the partial discharge detection method according to any one of claims 1 to 7 are implemented.

Images