A dry-type air-core reactor thermal fault detection method, device, equipment and medium

Abstract

The application discloses a dry-type hollow reactor thermal fault detection method, device, equipment and medium, in the method, a measured temperature distribution matrix is acquired; and a standard temperature distribution matrix; then, the measured temperature distribution matrix and the standard temperature distribution matrix are both divided into regions, and the variance square between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region is calculated, so that the region is determined as a thermal fault region or a further detection region according to the value of the variance square and a preset threshold value; when the region is the further detection region, whether the further detection region is a thermal fault region is determined based on the directional derivative of the measured temperature distribution matrix of the further detection region and the directional derivative of the standard temperature distribution matrix, so that the thermal fault of the dry-type hollow reactor is accurately positioned, the maintenance personnel can know the fault position in time and perform maintenance, and greater problems caused by the fault are avoided.

Description

Technical Field

[0001] This invention relates to the field of online monitoring technology for power equipment, and in particular to a method, apparatus, equipment, and medium for detecting thermal faults in dry-type air-core reactors. Background Technology

[0002] Reactors, as crucial transmission and transformation equipment in power systems, are primarily used for limiting short-circuit currents and reactive power compensation. Dry-type air-core reactors, characterized by low losses, low noise, simple structure, and convenient maintenance, play a vital role in transmission and distribution networks. Timely diagnosis and location of potential faults in dry-type air-core reactors are fundamental to ensuring the safe and reliable power supply of the power system. When a dry-type air-core reactor fails, a temperature rise often occurs at the fault point. Therefore, real-time monitoring of the overall temperature distribution of the dry-type air-core reactor is particularly important for diagnosing and locating thermal faults.

[0003] Accurately locating the thermal fault in a dry-type air-core reactor is no easy task. Infrared imaging technology, due to its strong anti-interference capabilities and the fact that it eliminates the need for additional equipment within the electrical equipment, has been widely applied in recent years for online monitoring and fault diagnosis of electrical equipment. However, traditional thermal fault diagnosis techniques, relying solely on infrared temperature distribution data, are clearly insufficient for diagnosing and locating thermal faults. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for detecting thermal faults in dry-type air-core reactors, enabling precise location of thermal faults in dry-type air-core reactors.

[0005] To achieve the above objectives, one embodiment of the present invention proposes a method for detecting thermal faults in a dry-type air-core reactor, comprising the following steps:

[0006] Infrared thermal images of the dry-type air-core reactor from various angles during normal operation are obtained, and the measured temperature distribution matrix is ​​obtained based on the infrared thermal images.

[0007] Based on the temperature distribution database of the dry-type air-core reactor under different loads and meteorological conditions, the surface temperature distribution data of the dry-type air-core reactor is obtained as a standard temperature distribution matrix.

[0008] Both the measured temperature distribution matrix and the standard temperature distribution matrix are divided into regions, and the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region is calculated. Based on the value of the squared variance and a preset threshold, the region is determined to be a thermal fault area or a further detection area.

[0009] When the region is a further detection region, it is determined whether the further detection region is a thermal fault region based on the directional derivative of the measured temperature distribution matrix of the further detection region and the directional derivative of the standard temperature distribution matrix.

[0010] Optionally, acquiring infrared thermal images of the dry-type air-core reactor from various angles during normal operation, and obtaining the measured temperature distribution matrix based on the infrared thermal images, includes:

[0011] Infrared thermal imagers arranged in all directions of the dry-type air-core reactor are used to acquire infrared thermal images from all directions.

[0012] An adaptive global weighted average method is used to perform grayscale processing on the infrared thermal image to obtain the grayscale image corresponding to the infrared thermal image.

[0013] The grayscale image is denoised to obtain a denoised grayscale image corresponding to the grayscale image;

[0014] The denoised grayscale image is enhanced by combining histogram equalization and block adaptive Canny edge detection algorithm to obtain an enhanced and denoised grayscale image.

[0015] Temperature distribution data is extracted from the enhanced and denoised grayscale image to form the measured temperature distribution matrix.

[0016] Optionally, the step of obtaining the surface temperature distribution data of the dry-type air-core reactor as a standard temperature distribution matrix based on a temperature distribution database of the dry-type air-core reactor under different loads and meteorological conditions includes:

[0017] Based on the three-dimensional temperature field finite element calculation model of the dry air reactor, temperature distribution maps were obtained under different load factors, different harmonic content rates, different harmonic orders, different solar radiation intensities, different ambient temperatures, different altitudes, and different ventilation conditions when the dry air reactor was operating normally.

[0018] Temperature distribution data is extracted based on the temperature distribution maps to form a temperature distribution database for the dry-type air-core reactor.

[0019] The surface temperature distribution data of the dry-type air-core reactor is obtained from the temperature distribution database as a standard temperature distribution matrix.

[0020] Optionally, the step of dividing both the measured temperature distribution matrix and the standard temperature distribution matrix into regions, and calculating the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region, to determine the region as a thermal fault area or a further detection area based on the value of the squared variance and a preset threshold, includes:

[0021] Calculate the first temperature mean of the region in the measured temperature distribution matrix, the second temperature mean of the corresponding region in the standard temperature distribution matrix, and obtain the squared variance between the first temperature mean and the second temperature mean;

[0022] When the squared variance is greater than a preset threshold, the region is determined to be a thermal fault region.

[0023] When the squared variance is less than or equal to the preset threshold, the region is determined to be a region for further detection.

[0024] Optionally, when the region is a further detection region, determining whether the further detection region is a thermal fault region based on the directional derivative of the measured temperature distribution matrix and the directional derivative of the standard temperature distribution matrix of the further detection region includes:

[0025] Taking each point in the measured temperature distribution matrix corresponding to the further detection area as the center, obtain N measured directional derivatives in N directions; and obtain the maximum value among the N measured directional derivatives;

[0026] Taking each point in the standard temperature distribution matrix corresponding to the further detection area as the center, obtain N standard directional derivatives in N directions; and obtain the maximum value among the N standard directional derivatives;

[0027] If the maximum value among the N standard directional derivatives is the same as the maximum value among the N measured directional derivatives, then the further detection area is determined to be a thermal fault area; if they are different, then the maximum value among the remaining N-1 measured directional derivatives and the maximum value among the remaining N-1 standard directional derivatives are obtained.

[0028] If the maximum value among the remaining N-1 measured directional derivatives is the same as the maximum value among the remaining N-1 standard directional derivatives, then the further detection area is determined to be a thermal fault area; if they are different, then the maximum value among the remaining N-2 measured directional derivatives and the maximum value among the remaining N-2 standard directional derivatives are obtained.

[0029] This process continues until the last measured directional derivative is compared with the standard directional derivative. If they are the same, the further detection area is determined to be a thermal fault area; if they are different, the further detection area is determined to be a non-thermal fault area. Here, N is a positive integer.

[0030] Optionally, the step of performing grayscale processing on the infrared thermal image using an adaptive global weighted average method to obtain the grayscale image corresponding to the infrared thermal image includes:

[0031] The red, green, and blue components of each pixel in the infrared thermal image are weighted and calculated, and the weighted values ​​are obtained through global adaptive calculation of the infrared image.

[0032] Grav ij =a R R ij +a B B ij +a G G ij ;

[0033]

[0034] In the formula, Gravij is the grayscale value of the pixel in the i-th row and j-th column of the grayscale image; Rij, Gij, and Bij are the red, green, and blue component values ​​of the pixel in the i-th row and j-th column of the infrared thermal image, respectively; a R a G a B These are the globally adaptive weighted values ​​of Rij, Gij, and Bij, respectively, and n and m are the total number of rows and columns of the infrared thermal image, respectively.

[0035] Optionally, the image enhancement processing of the denoised grayscale image by combining histogram equalization and block-adaptive Canny edge detection algorithm to obtain the enhanced denoised grayscale image includes the following histogram equalization processing:

[0036] Obtain the ratio of the number of pixels with a gray value of the first gray value in the denoised grayscale image to the total number of pixels in the denoised grayscale image;

[0037] Obtain the difference between the maximum and minimum grayscale values ​​in the denoised grayscale image;

[0038] The product of the difference and the ratio is used as the first grayscale value after contrast enhancement;

[0039] The process involves sequentially obtaining the contrast-enhanced grayscale values ​​of each grayscale value to acquire a contrast-enhanced grayscale image.

[0040] Optionally, the step of combining histogram equalization and block-adaptive Canny edge detection algorithm to perform image enhancement processing on the denoised grayscale image to obtain the enhanced and denoised grayscale image, wherein the block-adaptive Canny edge detection algorithm includes:

[0041] By comparing the grayscale gradient of each pixel in the ratio-enhanced grayscale image with the grayscale gradient of the center pixel in the ratio-enhanced grayscale image, multiple suspected edge pixels that are suspected to be edge pixels of the dry air-core reactor are selected.

[0042] The process divides the data into blocks and processes multiple suspected edge pixels, calculating the segmentation grayscale threshold, the minimum edge grayscale threshold, and the maximum edge grayscale threshold in the block.

[0043] If the gray value of one of the multiple suspected edge pixels is less than the minimum gray value threshold of the edge, then the suspected edge pixel is not an edge pixel.

[0044] If the gray value of one of the multiple suspected edge pixels is greater than the maximum gray value threshold of the edge, then the suspected edge pixel is an edge pixel.

[0045] If the gray value of one of the suspected edge pixels is greater than or equal to the minimum gray value threshold of the edge, and less than or equal to the maximum gray value threshold of the edge, then the block is expanded for iteration.

[0046] Obtain a contrast-enhanced edge image of the dry-type air-core reactor.

[0047] Optionally, the step of extracting temperature distribution data from the image-enhanced and denoised grayscale image to form the measured temperature distribution matrix includes:

[0048] Obtain the maximum and minimum gray values ​​in the contrast-enhanced edge image of the dry-type air-core reactor, and extract the temperature value corresponding to the maximum gray value and the temperature value corresponding to the minimum gray value.

[0049] The temperature value corresponding to each pixel in the contrast-enhanced edge image of the dry-type air-core reactor is formed by multiplying the gray value of the pixel by the difference between the temperature value corresponding to the maximum gray value and the temperature value corresponding to the minimum gray value, and dividing by the difference between the maximum gray value and the minimum gray value.

[0050] To achieve the above objectives, a second aspect of the present invention provides a thermal fault detection device for a dry-type air-core reactor, comprising:

[0051] The measured temperature distribution matrix acquisition module is used to acquire infrared thermal images of the dry-type air-core reactor from various directions during normal operation, and to acquire the measured temperature distribution matrix based on the infrared thermal images.

[0052] The standard temperature distribution matrix acquisition module is used to acquire the surface temperature distribution data of the dry air reactor as a standard temperature distribution matrix based on the temperature distribution database of the dry air reactor under different loads and different meteorological conditions.

[0053] The detection module is used to divide the measured temperature distribution matrix and the standard temperature distribution matrix into regions, and calculate the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region, so as to determine the region as a thermal fault area or a further detection area based on the value of the squared variance and a preset threshold.

[0054] The further detection module is used to determine whether the further detection area is a thermal fault area based on the directional derivative of the measured temperature distribution matrix and the directional derivative of the standard temperature distribution matrix of the further detection area when the area is a further detection area.

[0055] To achieve the above objectives, a third aspect of the present invention provides an electronic device, the electronic device comprising:

[0056] At least one processor; and

[0057] A memory communicatively connected to the at least one processor; wherein,

[0058] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the dry air-core reactor thermal fault detection method proposed in any embodiment of the present invention.

[0059] To achieve the above objectives, a fourth aspect of the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the dry-type air-core reactor thermal fault detection method proposed in any embodiment of the present invention.

[0060] According to embodiments of the present invention, a method, apparatus, device, and medium for detecting thermal faults in a dry-type air-core reactor are proposed. The method involves acquiring infrared thermal images of the dry-type air-core reactor from various angles during normal operation, and obtaining a measured temperature distribution matrix based on these images. Furthermore, a standard temperature distribution matrix is ​​obtained by using a database of temperature distribution data of the dry-type air-core reactor under different loads and meteorological conditions. Both the measured and standard temperature distribution matrices are then divided into regions, and the squared variance between the measured and standard temperature distribution matrices in any corresponding region is calculated. The region is then determined as a thermal fault zone or a further detection zone based on the squared variance and a preset threshold. When a region is a further detection zone, the directional derivative of the measured and standard temperature distribution matrices within the further detection zone is used to determine whether the further detection zone is indeed a thermal fault zone. This allows for precise location of thermal faults in the dry-type air-core reactor, enabling maintenance personnel to promptly identify the fault location and perform repairs, thus preventing the fault from causing further problems.

[0061] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a flowchart of the dry-type air-core reactor thermal fault detection method proposed in the embodiments of the present invention;

[0064] Figure 2 This is a flowchart of a method for detecting thermal faults in a dry-type air-core reactor according to an embodiment of the present invention;

[0065] Figure 3 This is a schematic diagram of the measured temperature distribution matrix block in the thermal fault detection method for dry-type air-core reactors proposed in this embodiment of the invention;

[0066] Figure 4 This is a schematic diagram of the standard temperature distribution matrix block in the thermal fault detection method for dry-type air-core reactors proposed in this embodiment of the invention;

[0067] Figure 5 This is a flowchart of a method for detecting thermal faults in a dry-type air-core reactor, as proposed in another embodiment of the present invention.

[0068] Figure 6 This is a block diagram of the dry-type air-core reactor thermal fault detection device proposed in the embodiments of the present invention;

[0069] Figure 7 This is a schematic diagram of the structure of the dry-type air-core reactor thermal fault detection device proposed in an embodiment of the present invention. Detailed Implementation

[0070] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0071] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0072] Example 1

[0073] Figure 1 This is a flowchart of the thermal fault detection method for dry-type air-core reactors proposed in an embodiment of the present invention. Figure 1 As shown, the method for detecting thermal faults in a dry-type air-core reactor includes the following steps:

[0074] S1, acquire infrared thermal images of the dry-type air-core reactor from all directions during normal operation, and obtain the measured temperature distribution matrix based on the infrared thermal images;

[0075] S2, based on the temperature distribution database of dry-type air-core reactors under different loads and meteorological conditions, obtain the surface temperature distribution data of dry-type air-core reactors as a standard temperature distribution matrix;

[0076] S3. Divide the measured temperature distribution matrix and the standard temperature distribution matrix into regions, and calculate the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region. Based on the value of the squared variance and the preset threshold, determine the region as a thermal fault area or a further detection area.

[0077] S4, when the region is a further detection region, determine whether the further detection region is a thermal fault region based on the directional derivative of the measured temperature distribution matrix of the further detection region and the directional derivative of the standard temperature distribution matrix.

[0078] It is understandable that infrared thermal imagers can be arranged at three different locations on the dry-type air-core reactor. The arrangement of the three infrared thermal imagers is as follows: with the center of the dry-type air-core reactor as the origin, three infrared thermal imagers are arranged on the same horizontal plane, with the angle between the line connecting each infrared thermal imager and the origin being 120 degrees, and ensuring that the distance between each infrared thermal imager and the origin is equal. This allows for the acquisition of infrared thermal images from all directions of the interferometric air-core reactor. Finally, the infrared thermal images are processed to obtain a measured temperature distribution matrix. Combined with a standard temperature distribution matrix, each region is compared one by one to ultimately locate the thermal fault area. This enables real-time judgment and location of the thermal fault position in the dry-type air-core reactor, improving the efficiency of thermal fault diagnosis. In other embodiments, if the above arrangement cannot completely capture the surface of the dry-type air-core reactor, more infrared thermal imagers can be set up to capture a more complete surface image of the dry-type air-core reactor.

[0079] Optionally, such as Figure 2 As shown, S1 acquires infrared thermal images of the dry-type air-core reactor from various locations during normal operation, and obtains the measured temperature distribution matrix based on the infrared thermal images, including:

[0080] S11, acquire infrared thermal images from all directions by infrared thermal imagers arranged in the dry air reactor.

[0081] S12, the adaptive global weighted average method is used to perform grayscale processing on the infrared thermal image to obtain the grayscale image corresponding to the infrared thermal image;

[0082] Optionally, an adaptive global weighted averaging method is used to perform grayscale processing on the infrared thermal image to obtain the corresponding grayscale image, including:

[0083] The red, green, and blue components of each pixel in the infrared thermal image are weighted and calculated. The weighted values ​​are obtained through global adaptive calculation of the infrared image.

[0084] Grav ij =a R R ij +a B Bij +a G G ij ;

[0085]

[0086] In the formula, Grav ij R represents the grayscale value of the pixel in the i-th row and j-th column of the grayscale image; ij G ij B ij These represent the red, green, and blue component values ​​of the pixel in the i-th row and j-th column of the infrared thermal image, respectively; a R a G a B R respectively ij G ij B ij The global adaptive weighting value is given by n and m, which represent the total number of rows and columns of the infrared thermal image, respectively.

[0087] In this process, infrared thermal images from various directions can be stitched together first and then processed into grayscale, or each infrared thermal image can be processed separately. This invention does not impose any specific limitations on this.

[0088] S13, Denoise the grayscale image to obtain the denoised grayscale image corresponding to the grayscale image;

[0089] S14, combine histogram equalization and block adaptive Canny edge detection algorithm to perform image enhancement processing on the denoised grayscale image to obtain an enhanced and denoised grayscale image.

[0090] Optionally, S14 combines histogram equalization and block-based adaptive Canny edge detection algorithm to perform image enhancement processing on the denoised grayscale image, obtaining the image enhancement and denoising grayscale image. The histogram equalization processing includes:

[0091] Obtain the ratio of the number of pixels with the first gray value in the denoised grayscale image to the total number of pixels in the denoised grayscale image;

[0092] Obtain the difference between the maximum and minimum grayscale values ​​in a denoised grayscale image;

[0093] The product of the difference and the ratio is used as the first gray value after contrast enhancement;

[0094] The process involves sequentially obtaining the contrast-enhanced grayscale values ​​of each grayscale value to acquire a contrast-enhanced grayscale image.

[0095] In other words,

[0096] In the formula, Grav (a’) For the processed grayscale value, bGrav(a) Let be the number of pixels with grayscale value 'a' in the denoised grayscale image, and let 'b' be the total number of pixels in the denoised grayscale image. (max) Grav (min) These represent the maximum and minimum grayscale values ​​in the denoised grayscale image, respectively; a contrast-enhanced grayscale image can be obtained using the method described above. The 3x3 area represents the divided region.

[0097] Optionally, S14 combines histogram equalization and block-adaptive Canny edge detection algorithm to perform image enhancement processing on the denoised grayscale image, obtaining the image enhancement and denoising grayscale image. The block-adaptive Canny edge detection algorithm includes:

[0098] By comparing the grayscale gradient of each pixel in the ratio-enhanced grayscale image with the grayscale gradient of the center pixel in the ratio-enhanced grayscale image, multiple suspected edge pixels that are suspected to be edge pixels of dry air-core reactors are screened out.

[0099] It is understandable that if grad(Grav) ij )<grad(Grav i′j′ If ), then pixel ij is not an edge pixel of the dry air-core reactor; if grad(Grav) ij )>grad(Grav i′j′ ); then pixel ij could be an edge pixel of a dry-type air-core reactor; where i'j' represents all points within a 3×3 block centered on pixel ij, excluding pixel ij, grad(Grav ij Let be the grayscale gradient at pixel ij. This is used to filter out multiple suspected edge pixels within a block that are suspected to be edge pixels of a dry-type air-core reactor. The aforementioned block is a manually defined value.

[0100] The system processes multiple suspected edge pixels in blocks, calculates the segmentation grayscale threshold in the block, and sets the minimum and maximum grayscale thresholds for edges.

[0101] Understandably, a 3×3 block is selected, and the grayscale threshold Grav0 for segmentation is calculated:

[0102]

[0103] In the formula, Gravmax (3×3) Gravmin (3×3) These are the maximum and minimum grayscale values ​​within the 3×3 block, respectively.

[0104] Calculate the minimum grayscale threshold Grav1 and the maximum grayscale threshold Grav2 at the edges within a 3×3 block:

[0105]

[0106]

[0107] If the gray value of one of the multiple suspected edge pixels is less than the minimum gray value threshold for an edge, then the suspected edge pixel is not an edge pixel.

[0108] If the gray value of one of the multiple suspected edge pixels is greater than the maximum gray value threshold of the edge, then the suspected edge pixel is an edge pixel.

[0109] If the gray value of one of the multiple suspected edge pixels is greater than or equal to the minimum gray value threshold of the edge, and less than or equal to the maximum gray value threshold of the edge, then the block is expanded and iterated.

[0110] Obtain contrast-enhanced edge images of dry air-core reactors.

[0111] In other words, if Grav ij(3×3) If ≤Grav1, then pixel ij is determined to be an edge pixel of a non-dry air-core reactor;

[0112] If Grav ij(3×3) If ≥Grav2, then pixel ij is determined to be an edge pixel of a dry air-core reactor.

[0113] If Grav1 ≤ Grav ij(3×3) If the value is less than or equal to Grav2, then expand the selected block to 5×5 and repeat the same steps as above.

[0114] S15. Extract temperature distribution data from the image based on the image enhancement and denoising grayscale image to form a measured temperature distribution matrix.

[0115] Optionally, temperature distribution data is extracted from the image-enhanced and denoised grayscale image to form a measured temperature distribution matrix, including:

[0116] Obtain the maximum and minimum gray values ​​in the contrast-enhanced edge image of the dry air-core reactor, and extract the temperature values ​​corresponding to the maximum and minimum gray values.

[0117] The temperature value corresponding to each pixel in the edge image of the contrast-enhanced dry air-core reactor is formed by multiplying the gray value of the pixel by the difference between the temperature value corresponding to the maximum gray value and the temperature value corresponding to the minimum gray value, and dividing by the difference between the maximum gray value and the minimum gray value.

[0118] Understandably, this involves calculating the temperature value corresponding to each pixel in the grayscale image and extracting the maximum grayscale value, Grav. (max) and minimum gray level Grav (min)And extract the temperature value T corresponding to the maximum gray level. max and the temperature value T corresponding to the minimum gray level min Then the temperature T corresponding to each pixel in the grayscale image ij for:

[0119]

[0120] Therefore, step S1 uses the corresponding algorithm to extract the measured temperature distribution matrix from the thermal image.

[0121] Optionally, S2 uses a database of temperature distribution data of dry-type air-core reactors under different loads and meteorological conditions to obtain surface temperature distribution data of the dry-type air-core reactor as a standard temperature distribution matrix, including:

[0122] Based on the three-dimensional temperature field finite element calculation model of the dry air reactor, temperature distribution maps were obtained under different load factors, different harmonic content rates, different harmonic orders, different solar radiation intensities, different ambient temperatures, different altitudes, and different ventilation conditions during normal operation of the dry air reactor.

[0123] Temperature distribution data is extracted from each temperature distribution map to form a temperature distribution database for dry-type air-core reactors.

[0124] The surface temperature distribution data of dry-type air-core reactors is obtained from a temperature distribution database and used as a standard temperature distribution matrix.

[0125] Understandably, by simulating the temperature field of a dry-type air-core reactor under various conditions using computer simulations, a standard temperature distribution matrix is ​​ultimately formed based on the temperature distribution data under these different conditions. For example, there are three types of load factor, three types of harmonic content, four types of different harmonic orders, two types of solar radiation intensity, five types of ambient temperature, two types of altitude, and three types of ventilation conditions. Therefore, it is necessary to obtain multiple temperature distribution data under any combination of the above conditions to form a temperature distribution database, which is then summarized into a standard temperature distribution matrix.

[0126] In one embodiment, the infrared measured temperature distribution matrix of a dry-type air-core reactor under rated load with an actual ambient temperature of 25°C, outdoor sunlight, ventilation of 4 m / s, altitude of 1000 m, can be obtained. The standard temperature distribution matrix under the current load and meteorological conditions can be found from the dry-type air-core reactor temperature distribution database under normal operation. The 3×3 blocks in the measured temperature distribution matrix and the standard temperature distribution matrix in the database under the current load and meteorological conditions are selected step by step.

[0127] Optionally, S3 divides both the measured temperature distribution matrix and the standard temperature distribution matrix into regions, and calculates the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region. Based on the value of the squared variance and a preset threshold, the region is determined as a thermal fault area or a further detection area, including:

[0128] Calculate the first temperature mean of the region in the measured temperature distribution matrix, the second temperature mean of the corresponding region in the standard temperature distribution matrix, and obtain the squared variance between the first temperature mean and the second temperature mean.

[0129] When the squared variance is greater than a preset threshold, the region is identified as a thermal fault region.

[0130] When the squared variance is less than or equal to a preset threshold, the region is determined as the region for further detection.

[0131] In other words, based on the above embodiments, 3×3 blocks in the standard temperature distribution matrix of the database under the current load and meteorological conditions are selected step by step. The mean temperature of the standard temperature distribution matrix of the selected blocks is calculated, and the variance of the measured temperature of the selected blocks is calculated using the mean temperature.

[0132]

[0133] In the formula, T Bij(3×3) The 3×3 block selected for the standard temperature distribution matrix, T Bav(3×3) The average standard temperature of the 3×3 block selected for the corresponding standard temperature distribution matrix.

[0134]

[0135] In the formula, T Cij(3×3) The 3×3 block selected for the measured temperature distribution matrix, T σ 2 The squared variance of the measured temperature matrix is ​​calculated using the standard temperature mean of the 3×3 block selected using the standard temperature distribution matrix.

[0136] Setting the thermal fault threshold ε for dry-type air-core reactors σ ,

[0137] like The selected 3×3 block has a thermal fault;

[0138] like Then, by step-by-step comparing the maximum directional derivative of the observed temperature points, it is further determined whether there is a thermal fault in the selected 3×3 block.

[0139] Optionally, when the region is a further detection region, whether the further detection region is a thermal fault region is determined based on the directional derivative of the measured temperature distribution matrix and the directional derivative of the standard temperature distribution matrix of the further detection region, including:

[0140] Taking each point in the corresponding measured temperature distribution matrix in the further detection area as the center, obtain N measured directional derivatives in N directions; and obtain the maximum value among the N measured directional derivatives;

[0141] Taking each point in the corresponding standard temperature distribution matrix in the further detection area as the center, obtain N standard directional derivatives in N directions; and obtain the maximum value among the N standard directional derivatives;

[0142] If the maximum value among the N standard directional derivatives is the same as the maximum value among the N measured directional derivatives, then the area to be further detected is determined to be a thermal fault area; if they are different, then the maximum value among the remaining N-1 measured directional derivatives and the maximum value among the remaining N-1 standard directional derivatives are obtained.

[0143] If the maximum value among the remaining N-1 measured directional derivatives is the same as the maximum value among the remaining N-1 standard directional derivatives, then the area to be further detected is determined to be a thermal fault area; if they are different, then the maximum value among the remaining N-2 measured directional derivatives and the maximum value among the remaining N-2 standard directional derivatives are obtained.

[0144] This process continues until the last measured directional derivative is compared with the standard directional derivative. If they are the same, the area to be further tested is determined to be a thermal fault area; if they are different, the area to be further tested is determined to be a non-thermal fault area, where N is a positive integer.

[0145] It is understandable that, such as Figure 3 and Figure 4 As shown, a 3×3 block is selected, and the directional derivatives in 8 directions are calculated. That is, the 8 directional angles α are set to 0°, 45°, 90°, 135°, 180°, 225°, 270°, and 315°.

[0146]

[0147]

[0148] In the formula, T Cij T Bij The measured temperature values ​​(T) corresponding to the midpoint (i,j) of the temperature distribution matrix and the standard temperature distribution matrix, respectively. Ci′j′ T Bi′j′ These represent the temperature values ​​within a 3×3 block centered at point (i,j), excluding point (i,j), as shown in the measured temperature distribution matrix and the standard temperature distribution matrix, respectively. These are the directional derivatives of the measured temperature distribution matrix and the corresponding standard temperature distribution matrix at the direction angle α.

[0149] Next, the directional derivatives of each temperature at point (i,j) in the measured temperature distribution matrix and the corresponding standard temperature distribution matrix are compared sequentially.

[0150]

[0151] At this point, the direction angle for obtaining the maximum directional derivative is set as α. Cmax1 ,

[0152]

[0153] At this point, the direction angle for obtaining the maximum directional derivative is set as α. Bmax1 ,

[0154] If α Bmax1 -α Cmax1 If the value is not equal to 0, it is determined that the dry-type air-core reactor has a thermal fault at this time; and the fault area is the selected 3×3 block point (i,j) with a direction angle of α. Cmax1 The area it points to. For example... Figure 3 and Figure 4 The image shows a fault location diagram for thermal fault location of the dry-type air-core reactor at this time. (The diagram is obtained through...) Figure 3 and Figure 4 It can be seen that the fault area of ​​the dry-type air-core reactor is the region between point (i,j) and (i-1,j+1).

[0155] If α Bmax1 -α Cmax1 =0, in the remaining directional derivatives, find the maximum directional derivative of the measured temperature matrix and the corresponding standard temperature matrix at point (i,j), as follows:

[0156]

[0157] At this point, the direction angle for obtaining the maximum directional derivative is set as α. Cmax2 ,

[0158]

[0159] At this point, the direction angle for obtaining the maximum directional derivative is set as α. Bmax2 ,

[0160] If α Bmax2 -α Cmax2 If the value is not equal to 0, it is determined that the dry-type air-core reactor has a thermal fault at this time; and the fault area is the selected 3×3 block point (i,j) with a direction angle of α. Cmax2 The area it points to.

[0161] If αBmax2 -α Cmax2 =0, in the remaining directional derivatives, find the maximum value of the directional derivative of the measured temperature matrix and the corresponding standard temperature matrix at point (i,j).

[0162] By comparing the directional derivatives at point (i,j) step by step in the above manner, it is possible to determine whether there is a thermal fault in the dry-type air-core reactor and locate the fault location.

[0163] According to a specific embodiment of the present invention, such as Figure 5 As shown, the detection method includes the following steps:

[0164] S101, acquire infrared thermal images of dry-type air-core reactors;

[0165] S102, an adaptive global weighted average method is used to perform grayscale processing on infrared thermal images;

[0166] S103, Denoise the grayscale image;

[0167] S104, combining histogram equalization and block-adaptive Canny edge detection algorithm to perform image enhancement processing on grayscale images;

[0168] S105, Calculate the surface temperature distribution of the dry-type air-core reactor under different loads and weather conditions during normal operation;

[0169] S106, construct the measured temperature distribution matrix and the standard temperature distribution matrix respectively;

[0170] S107: Calculate the measured variance using the standard mean and determine whether the variance is less than the set threshold; if yes, proceed to S108; otherwise, proceed to S113.

[0171] S108, calculate the azimuth derivatives of each temperature observation point;

[0172] S109, compare the maximum directional derivatives sequentially;

[0173] S110: Determine if the directions of the maximum directional derivatives are consistent; if yes, execute S111; otherwise, execute S113.

[0174] S111: Is the directional derivative comparison complete? If yes, proceed to S112; otherwise, return to S109.

[0175] S112, locate the thermal fault location;

[0176] S113, a thermal fault exists in the area.

[0177] Example 2

[0178] Figure 6This is a block diagram of the thermal fault detection device for dry-type air-core reactors proposed in an embodiment of the present invention, as shown below. Figure 6 As shown, it includes:

[0179] The measured temperature distribution matrix acquisition module 101 is used to acquire infrared thermal images of the dry-type air-core reactor from various directions during normal operation, and to acquire the measured temperature distribution matrix based on the infrared thermal images.

[0180] The standard temperature distribution matrix acquisition module 102 is used to acquire surface temperature distribution data of dry air reactors as a standard temperature distribution matrix based on a database of temperature distribution of dry air reactors under different loads and meteorological conditions.

[0181] The detection module 103 is used to divide the measured temperature distribution matrix and the standard temperature distribution matrix into regions, and calculate the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region, so as to determine the region as a thermal fault area or a further detection area based on the value of the squared variance and a preset threshold.

[0182] The further detection module 104 is used to determine whether the further detection area is a thermal fault area based on the directional derivative of the measured temperature distribution matrix of the further detection area and the directional derivative of the standard temperature distribution matrix when the area is a further detection area.

[0183] Optionally, the measured temperature distribution matrix acquisition module 101 includes:

[0184] The infrared thermal image acquisition module is used to acquire infrared thermal images from various directions by infrared thermal imagers arranged in the dry air reactor.

[0185] The grayscale image acquisition module is used to perform grayscale processing on the infrared thermal image using an adaptive global weighted average method to obtain the grayscale image corresponding to the infrared thermal image.

[0186] The denoised grayscale image acquisition module is used to denoise grayscale images and acquire the denoised grayscale image corresponding to the grayscale image.

[0187] The image enhancement and denoising grayscale image acquisition module is used to perform image enhancement processing on the denoised grayscale image by combining histogram equalization and block adaptive Canny edge detection algorithm to obtain the image enhancement and denoising grayscale image.

[0188] The first extraction module is used to extract temperature distribution data from the image based on the image enhancement and denoising grayscale image, and form a measured temperature distribution matrix.

[0189] Optionally, the standard temperature distribution matrix acquisition module 102 includes:

[0190] The temperature distribution map acquisition module is used to acquire temperature distribution maps under different load factors, different harmonic content rates, different harmonic orders, different solar radiation intensities, different ambient temperatures, different altitudes, and different ventilation conditions based on the three-dimensional temperature field finite element calculation model of the dry air reactor.

[0191] The temperature distribution database acquisition module is used to extract temperature distribution data based on various temperature distribution maps and form a temperature distribution database for dry-type air-core reactors.

[0192] The second extraction module is used to obtain surface temperature distribution data of dry-type air-core reactors based on the temperature distribution database as a standard temperature distribution matrix.

[0193] Optionally, the detection module 103 includes:

[0194] The first calculation module is used to calculate the first temperature mean of the region in the measured temperature distribution matrix, the second temperature mean of the corresponding region in the standard temperature distribution matrix, and obtain the squared variance between the first temperature mean and the second temperature mean.

[0195] The first judgment module is used to determine the area as a thermal fault area when the square of the variance is greater than a preset threshold.

[0196] It is also used to determine the region as a further detection region when the square of the variance is less than or equal to a preset threshold.

[0197] Optionally, the further detection module 104 includes:

[0198] The derivative acquisition module is used to obtain N measured directional derivatives in N directions, centered on each point in the corresponding measured temperature distribution matrix in the further detection area; and to obtain the maximum value among the N measured directional derivatives.

[0199] The derivative maximum value acquisition module is used to obtain N standard directional derivatives in N directions, centered on each point in the corresponding standard temperature distribution matrix in the further detection area; and to obtain the maximum value among the N standard directional derivatives.

[0200] The second judgment module is used to determine the further detection area as a thermal fault area if the maximum value among the N standard directional derivatives is the same as the maximum value among the N measured directional derivatives; otherwise, it obtains the maximum value among the remaining N-1 measured directional derivatives and the maximum value among the remaining N-1 standard directional derivatives.

[0201] It is also used to determine the further detection area as a thermal fault area if the maximum value among the remaining N-1 measured directional derivatives is the same as the maximum value among the remaining N-1 standard directional derivatives; if they are different, the maximum value among the remaining N-2 measured directional derivatives and the maximum value among the remaining N-2 standard directional derivatives are obtained.

[0202] This process continues until the last measured directional derivative is compared with the standard directional derivative. If they are the same, the area to be further tested is determined to be a thermal fault area; if they are different, the area to be further tested is determined to be a non-thermal fault area, where N is a positive integer.

[0203] Optionally, the grayscale image acquisition module includes:

[0204] The red, green, and blue components of each pixel in the infrared thermal image are weighted and calculated, and the weighted values ​​are obtained through global adaptive calculation of the infrared image.

[0205] Grav ij =a R R ij +a B B ij +a G G ij ;

[0206]

[0207] In the formula, Grav ij R represents the grayscale value of the pixel in the i-th row and j-th column of the grayscale image; ij G ij B ij These represent the red, green, and blue component values ​​of the pixel in the i-th row and j-th column of the infrared thermal image, respectively; a R a G a B R respectively ij G ij B ij The global adaptive weighting value is given by n and m, which represent the total number of rows and columns of the infrared thermal image, respectively.

[0208] Optionally, the contrast-enhanced grayscale image acquisition module includes:

[0209] The second calculation module is used to obtain the ratio of the number of pixels with a gray value of the first gray value in the denoised grayscale image to the total number of pixels in the denoised grayscale image.

[0210] It is also used to obtain the difference between the maximum and minimum grayscale values ​​in a denoised grayscale image;

[0211] It is also used to take the product of the difference and the ratio as the first grayscale value after contrast enhancement;

[0212] Then, the process of obtaining the contrast-enhanced grayscale values ​​of each grayscale value is performed sequentially to obtain a contrast-enhanced grayscale image.

[0213] Optionally, the image enhancement and denoising grayscale image acquisition module includes:

[0214] The filtering module is used to compare the grayscale gradient of each pixel in the contrast-enhanced grayscale image with the grayscale gradient of the center pixel in the contrast-enhanced grayscale image, and filter out multiple suspected edge pixels that are suspected to be edge pixels of dry air-core reactors.

[0215] The third calculation module is used to process multiple suspected edge pixels in blocks, calculate the segmentation grayscale threshold in the block, as well as the minimum grayscale threshold and the maximum grayscale threshold of the edge.

[0216] The third judgment module is used to determine whether a suspected edge pixel is not an edge pixel if the gray value of one of the multiple suspected edge pixels is less than the minimum gray value threshold of the edge.

[0217] It is also used to identify a suspected edge pixel as an edge pixel if the gray value of one of the multiple suspected edge pixels is greater than the maximum gray value threshold of the edge.

[0218] It is also used to expand the block and iterate if the gray value of one of the multiple suspected edge pixels is greater than or equal to the minimum gray value threshold of the edge and less than or equal to the maximum gray value threshold of the edge.

[0219] Finally, an edge image of the dry-type air-core reactor with enhanced contrast is obtained.

[0220] Optionally, the measured temperature distribution matrix acquisition module 102 includes:

[0221] The fourth calculation module is used to obtain the maximum and minimum gray values ​​in the contrast-enhanced edge image of the dry air reactor, and extract the temperature value corresponding to the maximum gray value and the temperature value corresponding to the minimum gray value.

[0222] The temperature value corresponding to each pixel in the edge image of the dry-type air-core reactor used for contrast enhancement is the gray value of the pixel, multiplied by the difference between the temperature value corresponding to the maximum gray value and the temperature value corresponding to the minimum gray value, and divided by the difference between the maximum gray value and the minimum gray value to form a measured temperature distribution matrix.

[0223] This avoids the limitations of determining thermal faults solely through infrared images and effectively enables accurate location of thermal faults via gradient direction.

[0224] The dry-type air-core reactor thermal fault detection device provided in this embodiment of the invention can execute the dry-type air-core reactor thermal fault detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution, which will not be described again in this embodiment.

[0225] Example 3

[0226] This invention provides an electronic device, which includes:

[0227] At least one processor; and

[0228] A memory that is communicatively connected to at least one processor; wherein,

[0229] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to execute the dry air-core reactor thermal fault detection method proposed in any embodiment of the present invention.

[0230] This invention also proposes a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the dry-type air-core reactor thermal fault detection method proposed in any embodiment of this invention.

[0231] Figure 7 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0232] like Figure 7As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0233] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0234] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the dry-type air-core reactor thermal fault detection method.

[0235] In some embodiments, the dry-type air-core reactor thermal fault detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the dry-type air-core reactor thermal fault detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the dry-type air-core reactor thermal fault detection method by any other suitable means (e.g., by means of firmware).

[0236] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0237] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0238] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0239] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0240] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0241] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0242] In summary, the method, apparatus, equipment, and medium for detecting thermal faults in dry-type air-core reactors proposed in this embodiment of the invention involve acquiring infrared thermal images of the dry-type air-core reactor from various angles during normal operation, and obtaining a measured temperature distribution matrix based on the infrared thermal images; and acquiring surface temperature distribution data of the dry-type air-core reactor as a standard temperature distribution matrix based on a temperature distribution database of the dry-type air-core reactor under different loads and meteorological conditions; furthermore, both the measured temperature distribution matrix and the standard temperature distribution matrix are divided into regions, and the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region is calculated, so as to determine whether the region is a thermal fault area or a further detection area based on the value of the squared variance and a preset threshold; thus, when the region is a further detection area, the directional derivative of the measured temperature distribution matrix and the directional derivative of the standard temperature distribution matrix of the further detection area are used to determine whether the further detection area is a thermal fault area, so as to achieve accurate location of thermal faults in dry-type air-core reactors, so as to facilitate maintenance personnel to know the fault location in time and carry out repairs, and avoid the fault from causing greater problems.

[0243] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0244] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting thermal faults in a dry-type air-core reactor, characterized in that, Includes the following steps: Infrared thermal images of the dry-type air-core reactor from various angles during normal operation are obtained, and the measured temperature distribution matrix is ​​obtained based on the infrared thermal images. Based on the temperature distribution database of the dry-type air-core reactor under different loads and meteorological conditions, the surface temperature distribution data of the dry-type air-core reactor is obtained as a standard temperature distribution matrix. Both the measured temperature distribution matrix and the standard temperature distribution matrix are divided into regions, and the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region is calculated. Based on the value of the squared variance and a preset threshold, the region is determined to be a thermal fault area or a further detection area. When the region is a further detection region, it is determined whether the further detection region is a thermal fault region based on the directional derivative of the measured temperature distribution matrix and the directional derivative of the standard temperature distribution matrix of the further detection region. When the region is a further detection region, determining whether the further detection region is a thermal fault region based on the directional derivative of the measured temperature distribution matrix and the directional derivative of the standard temperature distribution matrix of the further detection region includes: Taking each point in the measured temperature distribution matrix corresponding to the further detection area as the center, obtain N measured directional derivatives in N directions; and obtain the maximum value among the N measured directional derivatives; Taking each point in the standard temperature distribution matrix corresponding to the further detection area as the center, obtain N standard directional derivatives in N directions; and obtain the maximum value among the N standard directional derivatives; If the maximum value among the N standard directional derivatives is the same as the maximum value among the N measured directional derivatives, then the further detection area is determined to be a thermal fault area; if they are different, then the maximum value among the remaining N-1 measured directional derivatives and the maximum value among the remaining N-1 standard directional derivatives are obtained. If the maximum value among the remaining N-1 measured directional derivatives is the same as the maximum value among the remaining N-1 standard directional derivatives, then the further detection area is determined to be a thermal fault area; if they are different, then the maximum value among the remaining N-2 measured directional derivatives and the maximum value among the remaining N-2 standard directional derivatives are obtained. This process continues until the last measured directional derivative is compared with the standard directional derivative. If they are the same, the further detection area is determined to be a thermal fault area; if they are different, the further detection area is determined to be a non-thermal fault area. Here, N is a positive integer. In this process, both the measured temperature distribution matrix and the standard temperature distribution matrix are divided into multiple 3×3 sub-regions, and the variance square and directional derivative are calculated on the basis of each sub-region.

2. The method for detecting thermal faults in a dry-type air-core reactor according to claim 1, characterized in that, The process of acquiring infrared thermal images of the dry-type air-core reactor from various angles during normal operation, and obtaining the measured temperature distribution matrix based on the infrared thermal images, includes: Infrared thermal imagers arranged in all directions of the dry-type air-core reactor are used to acquire infrared thermal images from all directions. An adaptive global weighted average method is used to perform grayscale processing on the infrared thermal image to obtain the grayscale image corresponding to the infrared thermal image. The grayscale image is denoised to obtain a denoised grayscale image corresponding to the grayscale image; The denoised grayscale image is enhanced by combining histogram equalization and block adaptive Canny edge detection algorithm to obtain an enhanced and denoised grayscale image. Temperature distribution data is extracted from the enhanced and denoised grayscale image to form the measured temperature distribution matrix.

3. The method for detecting thermal faults in a dry-type air-core reactor according to claim 1, characterized in that, The step of obtaining the surface temperature distribution data of the dry-type air-core reactor as a standard temperature distribution matrix based on the temperature distribution database of the dry-type air-core reactor under different loads and meteorological conditions includes: Based on the three-dimensional temperature field finite element calculation model of the dry air reactor, temperature distribution maps were obtained under different load factors, different harmonic content rates, different harmonic orders, different solar radiation intensities, different ambient temperatures, different altitudes, and different ventilation conditions when the dry air reactor was operating normally. Temperature distribution data is extracted based on the temperature distribution maps to form a temperature distribution database for the dry-type air-core reactor. The surface temperature distribution data of the dry-type air-core reactor is obtained from the temperature distribution database as a standard temperature distribution matrix.

4. The method for detecting thermal faults in a dry-type air-core reactor according to claim 1, characterized in that, The process of dividing both the measured temperature distribution matrix and the standard temperature distribution matrix into regions, and calculating the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region, to determine whether the region is a thermal fault zone or a further detection zone based on the value of the squared variance and a preset threshold, includes: Calculate the first temperature mean of the region in the measured temperature distribution matrix, the second temperature mean of the corresponding region in the standard temperature distribution matrix, and obtain the squared variance between the first temperature mean and the second temperature mean; When the squared variance is greater than a preset threshold, the region is determined to be a thermal fault region. When the squared variance is less than or equal to the preset threshold, the region is determined to be a region for further detection.

5. The method for detecting thermal faults in a dry-type air-core reactor according to claim 2, characterized in that, The step of performing grayscale processing on the infrared thermal image using an adaptive global weighted average method to obtain the corresponding grayscale image includes: The red, green, and blue components of each pixel in the infrared thermal image are weighted and calculated, and the weighted values ​​are obtained through global adaptive calculation of the infrared thermal image. ； ； ； ； In the formula, Grav ij R represents the grayscale value of the pixel in the i-th row and j-th column of the grayscale image. ij G ij B ij These represent the red, green, and blue component values ​​of the pixel in the i-th row and j-th column of the infrared thermal image, respectively; a R a G a B R respectively ij G ij B ij The global adaptive weighting value, n and m are the total number of rows and columns of the infrared thermal image, respectively.

6. The method for detecting thermal faults in a dry-type air-core reactor according to claim 2, characterized in that, The image enhancement process of the denoised grayscale image, which combines histogram equalization and block-adaptive Canny edge detection algorithm, is performed to obtain the enhanced and denoised grayscale image. The histogram equalization process includes: Obtain the ratio of the number of pixels with a gray value of the first gray value in the denoised grayscale image to the total number of pixels in the denoised grayscale image; Obtain the difference between the maximum and minimum grayscale values ​​in the denoised grayscale image; The product of the difference and the ratio is used as the first grayscale value after contrast enhancement; The process involves sequentially obtaining the contrast-enhanced grayscale values ​​of each grayscale value to acquire a contrast-enhanced grayscale image.

7. The method for detecting thermal faults in a dry-type air-core reactor according to claim 6, characterized in that, The image enhancement process of the denoised grayscale image is performed by combining histogram equalization and block-adaptive Canny edge detection algorithms to obtain the enhanced and denoised grayscale image. The block-adaptive Canny edge detection algorithm includes: By comparing the grayscale gradient of each pixel in the ratio-enhanced grayscale image with the grayscale gradient of the center pixel in the ratio-enhanced grayscale image, multiple suspected edge pixels that are suspected to be edge pixels of the dry air-core reactor are selected. The process divides the data into blocks and processes multiple suspected edge pixels, calculating the segmentation grayscale threshold, the minimum edge grayscale threshold, and the maximum edge grayscale threshold in the block. If the gray value of one of the multiple suspected edge pixels is less than the minimum gray value threshold of the edge, then the suspected edge pixel is not an edge pixel. If the gray value of one of the multiple suspected edge pixels is greater than the maximum gray value threshold of the edge, then the suspected edge pixel is an edge pixel. If the gray value of one of the multiple suspected edge pixels is greater than or equal to the minimum gray value threshold of the edge, and less than or equal to the maximum gray value threshold of the edge, then the block is expanded for iteration. Obtain a contrast-enhanced edge image of the dry-type air-core reactor.

8. The method for detecting thermal faults in a dry-type air-core reactor according to claim 7, characterized in that, The step of extracting temperature distribution data from the enhanced and denoised grayscale image to form the measured temperature distribution matrix includes: Obtain the maximum and minimum gray values ​​in the contrast-enhanced edge image of the dry-type air-core reactor, and extract the temperature value corresponding to the maximum gray value and the temperature value corresponding to the minimum gray value. The temperature value corresponding to each pixel in the contrast-enhanced edge image of the dry-type air-core reactor is formed by multiplying the gray value of the pixel by the difference between the temperature value corresponding to the maximum gray value and the temperature value corresponding to the minimum gray value, and dividing by the difference between the maximum gray value and the minimum gray value.

9. A thermal fault detection device for a dry-type air-core reactor, characterized in that, include: The measured temperature distribution matrix acquisition module is used to acquire infrared thermal images of the dry-type air-core reactor from various directions during normal operation, and to acquire the measured temperature distribution matrix based on the infrared thermal images. The standard temperature distribution matrix acquisition module is used to acquire the surface temperature distribution data of the dry air reactor as a standard temperature distribution matrix based on the temperature distribution database of the dry air reactor under different loads and different meteorological conditions. The detection module is used to divide the measured temperature distribution matrix and the standard temperature distribution matrix into regions, and calculate the squared variance between the measured temperature distribution matrix and the standard temperature distribution matrix in any corresponding region, so as to determine the region as a thermal fault area or a further detection area based on the value of the squared variance and a preset threshold. The further detection module is used to determine whether the further detection area is a thermal fault area based on the directional derivative of the measured temperature distribution matrix and the directional derivative of the standard temperature distribution matrix when the area is a further detection area. The further detection module includes: The derivative acquisition module is used to acquire N measured directional derivatives in N directions, with each point in the measured temperature distribution matrix corresponding to the further detection area as the center; and to acquire the maximum value among the N measured directional derivatives. The derivative maximum value acquisition module is used to acquire N standard directional derivatives in N directions, with each point in the standard temperature distribution matrix corresponding to the further detection area as the center; and to acquire the maximum value among the N standard directional derivatives. The second judgment module is used to determine that the further detection area is a thermal fault area if the maximum value among the N standard directional derivatives is the same as the maximum value among the N measured directional derivatives; otherwise, it obtains the maximum value among the remaining N-1 measured directional derivatives and the maximum value among the remaining N-1 standard directional derivatives. It is also used to determine the further detection area as a thermal fault area if the maximum value among the remaining N-1 measured directional derivatives is the same as the maximum value among the remaining N-1 standard directional derivatives; if they are different, it obtains the maximum value among the remaining N-2 measured directional derivatives and the maximum value among the remaining N-2 standard directional derivatives. This process continues until the last measured directional derivative is compared with the standard directional derivative. If they are the same, the further detection area is determined to be a thermal fault area; if they are different, the further detection area is determined to be a non-thermal fault area. Here, N is a positive integer. In this process, both the measured temperature distribution matrix and the standard temperature distribution matrix are divided into multiple 3×3 sub-regions, and the variance square and directional derivative are calculated on the basis of each sub-region.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the dry air-core reactor thermal fault detection method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for detecting thermal faults in a dry-type air-core reactor as described in any one of claims 1-8.

Images