Method and system for detecting transformer oil leakage based on fluorescent distribution area

Abstract

The present application relates to a kind of transformer oil leakage detection methods based on fluorescent distribution area, the method comprises the following steps: collecting transformer image and pre-processing, wherein the transformer image is fluorescent image with fluorescent substance concentration information;Transformer image is cut into area, and each fluorescent point area is obtained;Each fluorescent point area is connected, and first area is formed;Determine whether the fluorescent substance concentration in each fluorescent point area is greater than fluorescent threshold concentration, if yes, then the fluorescent point area is marked, and the marked area is connected, to form second area;The area S1 of first area, the area S2 of second area;Determine whether the ratio of the area S2 and the area S1 is less than first threshold, if the ratio is less than first threshold, then determine transformer oil leakage, if the ratio is greater than or equal to first threshold, then determine that transformer has no oil leakage.The present application also relates to corresponding system, storage medium.

Description

Technical Field

[0001] This invention relates to the fields of optics, computer vision, and transformer oil leakage detection technology, and specifically to a transformer oil leakage detection method based on fluorescence distribution regions. Background Technology

[0002] Transformers play an extremely important role in ensuring the stable operation of power systems. However, due to long-term operation or the influence of the external environment, transformers may experience various faults. Transformer oil leakage is a common fault in transformers. If it is not detected in time, it may lead to risks such as breakdown, short circuit, burnout, or even equipment explosion, which may cause serious power accidents and affect the reliable operation of the power system.

[0003] Therefore, oil leakage detection during transformer factory safety testing can eliminate oil leakage faults, better ensuring the safe operation of the transformer, and extending its service life. Currently, oil leakage fault detection before transformers leave the factory mainly involves checking for oil stains on the transformer surface or surrounding ground, measuring the temperature of the transformer surface using an infrared thermometer, checking for leaking noises during operation, and detecting abnormal oil levels. While these methods can detect oil leakage faults, they mostly rely on professional personnel for operation and judgment and can only detect external oil leaks, not internal ones. These methods have certain limitations and a risk of false detection, resulting in low detection efficiency and accuracy. Therefore, how to accurately and quickly identify and detect internal oil leakage faults in transformers, effectively improve the detection efficiency and accuracy, reduce the false alarm rate, and thus ensure the stability and reliability of transformer safe operation has become an urgent problem to be solved.

[0004] This application aims to establish a method and system for detecting transformer oil leakage in fluorescent distribution areas, in order to solve the above-mentioned problems. Summary of the Invention

[0005] To achieve the above-mentioned objectives and other advantages of the present invention, a first objective of the present invention is to provide a transformer oil leakage detection method based on fluorescence distribution regions, comprising the following steps: The transformer image is acquired and preprocessed, wherein the transformer image is a fluorescence image containing fluorescent substance concentration information; The transformer image is segmented to obtain the regions of each fluorescent dot; Connect each fluorescent dot region to form the first region; Determine whether the concentration of fluorescent substance in each fluorescent dot region is greater than the fluorescence threshold concentration. If so, mark the fluorescent dot region and connect the marked regions to form a second region. Calculate the area S1 of the first region and the area S2 of the second region; Determine whether the ratio of the area S2 to the area S1 is less than a first threshold. If the ratio is less than the first threshold, the transformer is determined to be leaking oil. If the ratio is greater than or equal to the first threshold, the transformer is determined to be not leaking oil.

[0006] Furthermore, it also includes the following steps: If the ratio is less than the first threshold, the following steps are also included: Determine whether the shape of the second region belongs to the first shape set; if the shape of the second region belongs to the first shape set, then the transformer is determined to be leaking oil; if the shape of the second region does not belong to the first shape set, then the transformer is determined to be not leaking oil.

[0007] Furthermore, the first set of shapes includes single teardrop shapes, double teardrop shapes, multiple teardrop shapes, pear shapes, olive shapes, triangles, rhombuses, and other shapes.

[0008] Furthermore, the preprocessing includes the following steps: The acquired transformer image is obtained, and the acquired transformer image is converted to grayscale using a weighted average method to obtain a grayscale image; A grayscale image is filtered by bilateral filtering to remove noise and obtain a filtered image. The filtered image is enhanced by histogram equalization to highlight details and features in the image, resulting in a contrast-enhanced image, which serves as the transformer image for region segmentation.

[0009] Furthermore, the region cutting includes the following steps: Obtain a contrast-enhanced image; The Sobel operator is used to calculate the gradient values ​​in the horizontal and vertical directions of the contrast-enhanced image, thereby obtaining the gradient intensity and direction of each pixel; The non-maximum suppression algorithm is used to compare the gradient values ​​between two adjacent pixels along the gradient direction to eliminate the blurring effect on the edges. Use dual thresholding to classify pixels into first edge, second edge, and third edge categories; Connect the second edge to the first edge around it to form a complete edge, thus completing the region segmentation.

[0010] Furthermore, the concentration of the fluorescent substance is calculated by detecting the fluorescence intensity of the region using a fluorescence detector.

[0011] Furthermore, the formula for calculating the concentration of the fluorescent substance is as follows: Where C represents the concentration of the fluorescent substance, I represents the fluorescence intensity, S is the wavelength of the fluorescence detector light source, P is the transmittance of the fluorescence light path, and K is the fluorescence coefficient of the fluorescent substance.

[0012] Furthermore, the fluorescence threshold concentration setting method includes the following steps: Acquire images of transformers that have been confirmed to have no oil leakage faults and perform preprocessing; The preprocessed transformer image is segmented to obtain several fluorescent dot regions; The fluorescence intensity of the transformer image at each fluorescence point is detected using a fluorescence detector, and the concentration of fluorescent material in each fluorescence point region is calculated based on the fluorescence intensity. The average concentration of the fluorescent substance in each fluorescent spot region is taken as the fluorescence threshold concentration.

[0013] Furthermore, the first threshold setting method includes the following steps: Acquire images of transformers that have been confirmed to have no oil leakage faults and perform preprocessing; The transformer image was segmented to obtain several fluorescent dot regions; After connecting each fluorescent dot region, a third region is obtained; Calculate the ratio of the area of ​​the third region to the internal area of ​​the transformer, and use it as the first threshold.

[0014] A second objective of this invention is to provide a transformer oil leakage detection system based on fluorescence distribution regions, comprising the following modules: An image acquisition module is configured to acquire and collect transformer images via an image acquisition device, wherein the transformer images are transformer fluorescence images containing fluorescent substance concentration information; An image preprocessing module is configured to preprocess the acquired transformer images; The image segmentation module is configured to segment the transformer image into regions to obtain each fluorescent dot region; connect each fluorescent dot region to form a first region; determine whether the concentration of fluorescent substance in each fluorescent dot region is greater than the fluorescence threshold concentration, and if so, mark the fluorescent dot region and connect the marked points to form a second region; calculate the area S1 of the first region and the area S2 of the second region. The detection module is configured to determine whether the ratio of the area S2 to the area S1 is less than a first threshold. If the ratio is less than the first threshold, the transformer is determined to be leaking oil. If the ratio is greater than or equal to the first threshold, the transformer is determined to be leaking oil.

[0015] A third objective of this invention is to provide a readable storage medium storing a computer program thereon, wherein when the computer program is executed by a processor, a transformer oil leakage detection method based on fluorescence distribution regions is implemented.

[0016] Compared with the prior art, the beneficial effects of the present invention are: This invention relates to a method, system, and storage medium for detecting transformer oil leakage based on fluorescence distribution regions. By preprocessing the transformer image and segmenting it into regions, a first region and a second region are obtained through connected fluorescent point regions and the concentration of fluorescent substances. The area ratio of the second region in the first region is calculated and its relationship with a set first threshold. Combined with the shape of the fluorescent regions, this method more accurately reflects the fluorescence distribution inside the transformer, thereby improving the accuracy of transformer oil leakage fault detection. This avoids missed or false detections that could damage the transformer due to oil leakage, ensuring the stability and reliability of transformer safe operation and ultimately guaranteeing the safe operation of the power system.

[0017] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific embodiments of the present invention are given in detail in the following embodiments and their accompanying drawings. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 This is a flowchart of the transformer oil leakage detection method based on fluorescence distribution area according to this application; Figure 2 This is a flowchart from Example 1 showing the process of determining whether the shape of the second region belongs to the first shape set for transformer oil leakage detection. Figure 3 This is a flowchart of the preprocessing process in Example 1; Figure 4 This is a flowchart of the bilateral filtering calculation method in Example 1; Figure 5 This is a flowchart of the region cutting method in Example 1; Figure 6 This is a flowchart of the fluorescence threshold concentration setting method in Example 1; Figure 7 This is a flowchart of the first threshold setting method in Example 1; Figure 8 This is a schematic diagram of the transformer oil leakage detection system based on fluorescence distribution area in Example 2; Figure 9 This is a schematic diagram of a computer-readable storage medium in Example 3. Detailed Implementation

[0019] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0020] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0021] Example 1

[0022] This invention provides a transformer oil leakage detection method based on fluorescence distribution regions, such as... Figure 1 As shown, the specific steps include the following: S101, Acquire a transformer image and preprocess it, wherein the transformer image is a fluorescent image with fluorescent substance concentration information; S102, Perform region segmentation on the transformer image to obtain the regions of each fluorescent dot; S103, connect each fluorescent dot region to form the first region; S104, Determine whether the concentration of fluorescent substance in each fluorescent dot region is greater than the fluorescence threshold concentration. If so, mark the fluorescent dot region and connect the marked regions to form a second region. S105, Calculate the area S1 of the first region and the area S2 of the second region; S106, determine whether the ratio of the area S2 to the area S1 is less than a first threshold. If the ratio is less than the first threshold, determine that the transformer is leaking oil. If the ratio is greater than or equal to the first threshold, determine that the transformer is not leaking oil.

[0023] In some embodiments, if the determination result in step S106 is that the ratio is less than the first threshold, the method further includes determining whether the shape of the second region belongs to the first shape set, such as... Figure 2 As shown, the specific steps are as follows: S107, determine whether the shape of the second region belongs to the first shape set; if the shape of the second region belongs to the first shape set, determine that the transformer is leaking oil; if the shape of the second region does not belong to the first shape set, determine that the transformer is not leaking oil.

[0024] In some embodiments, the first set of shape rules includes shapes such as single teardrop, double teardrop, multiple teardrop, pear, olive, triangle, and rhombus.

[0025] In a preferred embodiment, under normal conditions, the fluorescent regions in the transformer image are distributed in a scattered yet regular graphic shape, such as rectangles or circles. Under oil leakage conditions, the fluorescence in the fluorescent regions gradually converges towards the leakage point, resulting in a clustered fluorescent area that forms shapes such as teardrops, pears, olives, triangles, and rhombuses. The teardrop shape can further include single teardrops, double teardrops, and multiple teardrops. Therefore, a transformer oil leak can only be determined when the ratio is less than a first threshold and the shape of the second region belongs to one of the aforementioned shapes. If any condition is not met, the transformer is determined to have no oil leak.

[0026] In some embodiments, the acquisition of the transformer image in step S101 can be specifically acquired by an image acquisition device, which may be a camera, camcorder, video capture card, or other device with photographic capabilities. In a preferred embodiment, the image acquisition device used in this application is a camera with an ultraviolet light source or a fluorescent camera.

[0027] In some embodiments, the transformer images acquired in step S101 include images of the same transformer without oil leakage and images of the transformer with oil leakage. In a preferred embodiment, image data of the transformer at different angles when oil leakage occurs can also be acquired to achieve the effect of comprehensively acquiring transformer images.

[0028] In some embodiments, the fluorescent substance concentration information mentioned in step S101 is obtained by detecting the fluorescence intensity of the region using a fluorescence detector and calculating the fluorescent substance concentration based on the fluorescence intensity.

[0029] In a preferred embodiment, the formula for calculating the concentration of the fluorescent substance in step S101 is as follows: Where C represents the concentration of the fluorescent substance, I represents the fluorescence intensity, S is the wavelength of the fluorescence detector light source, P is the transmittance of the fluorescence light path, and K is the fluorescence coefficient of the fluorescent substance.

[0030] In some embodiments, the preprocessing described in step S101, such as Figure 3 As shown, the specific steps include the following: S131, Acquire the collected transformer image, and perform grayscale processing on the acquired transformer image using the weighted average method to obtain a grayscale image; S132, The grayscale image is filtered by bilateral filtering to eliminate noise in the image and obtain the filtered image; S133, Histogram equalization is used to enhance the contrast of the filtered image, highlighting the details and features in the image, resulting in a contrast-enhanced image, which serves as the transformer image for region segmentation.

[0031] In some embodiments, the weighted average grayscale calculation formula in step 121 is as follows: Where R, G, and B represent the vector matrices of the red, green, and blue colors of the original image, respectively, and H represents the grayscale value.

[0032] In some embodiments, the bilateral filtering calculation method described in step 122 is as follows: Figure 4 As shown, the specific steps include the following: S141, Calculate the spatial domain coefficient m, the specific calculation formula is as follows: Where (a, b) are the center coordinates of the spatial domain window, and (i, j) are the coordinates of other pixels in the spatial domain window. is the standard deviation of the Gaussian function.

[0033] S142, Calculate the range coefficient n, the specific calculation formula is as follows: Where c(i,j) represents the pixel value at point (i,j) in the image, (a,b) represents the center coordinates of the range window, and (i,j) represents the coordinates of other pixels in the range window. is the standard deviation of the Gaussian function.

[0034] S143, multiply the spatial domain template coefficients m and the value domain template coefficients n to obtain the weight coefficients r of the bilateral filter. The specific calculation formula is as follows: Right now: Where (a,b) represents the position of the neighboring pixel, and the weight coefficient r(i,j,a,b) is the product of the spatial domain coefficient m and the value domain coefficient n.

[0035] In some embodiments, the contrast enhancement using histogram equalization in step S123 specifically involves adjusting the grayscale values ​​using a cumulative function to enhance the contrast. In a preferred embodiment, histogram stretching can also be used, employing a non-linear method to stretch the histogram and adjust it, thereby widening the difference between the foreground and background grayscale values ​​and enhancing the contrast.

[0036] In some embodiments, the region cutting described in step S102, such as Figure 5 As shown, the specific steps include the following: S151, acquire contrast-enhanced image; S152, use the Sobel operator to calculate the gradient values ​​of the contrast-enhanced image in the horizontal and vertical directions, thereby obtaining the gradient intensity and gradient direction of each pixel; S153 uses a non-maximum suppression algorithm to compare the gradient values ​​between two adjacent pixels along the gradient direction, thus eliminating the blurring effect on the edges. S154, using dual thresholding to classify pixels into first edge, second edge and third edge; S155 connects the second edge and the surrounding first edge using a connectivity analysis algorithm to form a complete edge, thus completing the region segmentation.

[0037] By using edge detection algorithms to segment regions, areas with high concentrations of fluorescent material in the transformer image were connected, which more comprehensively considered the overall distribution of fluorescent material inside the transformer and effectively improved the efficiency of oil leak detection.

[0038] In some embodiments, the Sobel operator calculation formula in step S152 is as follows: in, This represents the gradient value in the horizontal direction. This represents the gradient value in the vertical direction.

[0039] In a preferred embodiment, the gradient intensity F(x,y) is calculated using the following formula: In a preferred embodiment, the gradient direction V(x,y) is calculated using the following formula: In some embodiments, the dual thresholding process in step S154 specifically involves classifying a pixel as a first edge when its gradient value is higher than a higher threshold, classifying it as a third edge when its gradient value is lower than a lower threshold, and classifying it as a second edge when its gradient value is between the higher and lower thresholds.

[0040] In some embodiments, the fluorescent dot regions described in step S103 are connected to form a first region, preferably forming a closed region.

[0041] In some embodiments, the fluorescence threshold concentration setting method described in step S104, such as Figure 6 As shown, the specific steps include the following: S161, Obtain and preprocess images of transformers that have been confirmed to have no oil leakage faults; S162, The preprocessed transformer image is segmented to obtain several fluorescent dot regions; S163, use a fluorescence detector to detect the fluorescence intensity of the transformer image at each fluorescence point, and calculate the concentration of fluorescent material in each fluorescence point region based on the fluorescence intensity; S164, take the average value of the fluorescent substance concentration in each obtained fluorescent spot region as the fluorescence threshold concentration.

[0042] In some embodiments, the formula for calculating the ratio of area S2 to area S1 in step S106 is as follows: Where S1 represents the area of ​​the first region, S2 represents the area of ​​the second region, and q represents the ratio of area S2 to area S1.

[0043] In some embodiments, the first threshold setting method described in step S106, such as Figure 7 As shown, the specific steps include the following: S171, Obtain images of transformers that have been confirmed to have no oil leakage faults and perform preprocessing; S172, The transformer image is segmented to obtain several fluorescent dot regions; S173, after connecting each fluorescent dot region, the third region is obtained; S174, calculate the ratio of the area of ​​the third region to the internal area of ​​the transformer, and use it as the first threshold.

[0044] In a preferred embodiment, the first threshold is set to 95%.

[0045] When the ratio q of the area S2 to the area S1 is less than the first threshold, a preliminary determination of transformer oil leakage is made, and then it is determined whether the shape of the second region belongs to the first region set. If the shape of the second region belongs to the first region set, the determination result is transformer oil leakage; otherwise, if the shape of the second region does not belong to the first shape set or the ratio q of the area S2 to the area S1 is greater than or equal to the first threshold, the determination result is that the transformer has no oil leakage. This increases the efficiency and accuracy of transformer oil leakage detection.

[0046] Example 2

[0047] This invention provides a transformer oil leakage detection system based on fluorescence distribution regions, which has the following features: Figure 8 As shown, the body includes the following modules: An image acquisition module is configured to acquire and collect transformer images via an image acquisition device, wherein the transformer images are transformer fluorescence images containing fluorescent substance concentration information; An image preprocessing module is configured to preprocess the acquired transformer images; The image segmentation module is configured to segment the transformer image into regions to obtain each fluorescent dot region; connect each fluorescent dot region to form a first region; determine whether the concentration of fluorescent substance in each fluorescent dot region is greater than the fluorescence threshold concentration, and if so, mark the fluorescent dot region and connect the marked points to form a second region; calculate the area S1 of the first region and the area S2 of the second region. The detection module is configured to determine whether the ratio of the area S2 to the area S1 is less than a first threshold. If the ratio is less than the first threshold, the transformer is determined to be leaking oil. If the ratio is greater than or equal to the first threshold, the transformer is determined to be leaking oil.

[0048] In some embodiments, the detection module is further configured to, if the ratio is less than a first threshold, further include determining whether the shape of the second region belongs to a first shape set; if the shape of the second region belongs to the first shape set, then the transformer is determined to be leaking oil; if the shape of the second region does not belong to the first shape set, then the transformer is determined to be leaking oil.

[0049] In some embodiments, the first set of shape rules includes shapes such as single teardrop, double teardrop, multiple teardrop, pear, olive, triangle, and rhombus.

[0050] In a preferred embodiment, under normal conditions, the fluorescent regions in the transformer image are distributed in a scattered yet regular graphic shape, such as rectangles or circles. Under oil leakage conditions, the fluorescence in the fluorescent regions gradually converges towards the leakage point, resulting in a clustered fluorescent area that forms shapes such as teardrops, pears, olives, triangles, and rhombuses. The teardrop shape can further include single teardrops, double teardrops, and multiple teardrops. Therefore, a transformer oil leak can only be determined when the ratio is less than a first threshold and the shape of the second region belongs to one of the aforementioned shapes. If any condition is not met, the transformer is determined to have no oil leak.

[0051] In some embodiments, the image acquisition device in the image acquisition module may specifically be a camera, camcorder, video capture card, or other devices with photographic capabilities.

[0052] In a preferred embodiment, the image acquisition device used in this application is a camera with an ultraviolet light source or a fluorescent camera, and the acquired transformer images include images of the same transformer without oil leakage and images of the transformer with oil leakage. In a preferred embodiment, image data from different angles can also be collected when the transformer experiences an oil leakage fault, so as to achieve the effect of comprehensively collecting transformer images.

[0053] In some embodiments, the fluorescent substance concentration information in the image acquisition module is obtained by detecting the fluorescence intensity of the region using a fluorescence detector and calculating the fluorescent substance concentration based on the fluorescence intensity.

[0054] The formula for calculating the concentration of fluorescent substances in the image acquisition module is the same as the formula for calculating the concentration of fluorescent substances in Example 1, and will not be repeated here.

[0055] The preprocessing steps in the image preprocessing module are the same as those in Example 1, and will not be repeated here.

[0056] The region cutting step in the image segmentation module is the same as the region cutting step in Example 1, and will not be described again here.

[0057] The method for setting the fluorescence threshold concentration in the image segmentation module is the same as the method for setting the fluorescence substance concentration in Example 1, and will not be repeated here.

[0058] The steps of the first threshold setting method in the detection module are the same as those in Example 1, and will not be repeated here.

[0059] Example 3

[0060] This invention also provides a computer-readable storage medium, such as... Figure 9 As shown, a computer program is stored therein, which is executed by a processor as described in Embodiment 1, the transformer oil leakage detection method based on fluorescence distribution area.

[0061] The program instructions are stored in a computer-readable storage medium (such as a CD-ROM, USB flash drive, or portable hard drive) or on a network, and include several computer program instructions to cause a computing device (such as a personal computer, server, or network device) to execute the above-described method according to the embodiments of this application.

[0062] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention, and other modifications can be easily made by those skilled in the art. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and examples shown and described herein.

[0063] The apparatus, electronic device, and non-volatile computer storage medium and method provided in the embodiments of this specification are corresponding. Therefore, the apparatus, electronic device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, electronic device, and non-volatile computer storage medium will not be repeated here.

[0064] Those skilled in the art will also know that, besides implementing the controller in the form of purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller take the form of logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices included within it for implementing various functions can also be considered structures within that hardware component. Alternatively, the devices for implementing various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0065] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0066] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0067] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects.

[0068] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0069] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0070] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0071] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0072] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0073] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0074] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside on local and remote computer storage media, including storage devices.

[0075] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0076] The above description is merely an embodiment of this specification and is not intended to limit the scope of one or more embodiments of this specification. Various modifications and variations can be made to one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of one or more embodiments of this specification.

Claims

1. A transformer oil leakage detection method based on fluorescent distribution area, characterized in that, Specifically, the following steps are included: The transformer image is acquired and preprocessed, wherein the transformer image is a fluorescence image containing fluorescent substance concentration information; The transformer image is segmented to obtain the regions of each fluorescent dot; Connect each fluorescent dot region to form the first region; Determine whether the concentration of fluorescent substance in each fluorescent dot region is greater than the fluorescence threshold concentration. If so, mark the fluorescent dot region and connect the marked regions to form a second region. Calculate the area S1 of the first region and the area S2 of the second region; Determine whether the ratio of the area S2 to the area S1 is less than a first threshold. If the ratio is greater than or equal to the first threshold, it is determined that the transformer has no oil leakage. If the ratio is less than the first threshold, it is determined whether the shape of the second region belongs to the first shape set. If the shape of the second region belongs to the first shape set, the transformer is determined to be leaking oil; if the shape of the second region does not belong to the first shape set, the transformer is determined to be not leaking oil. The shapes in the first shape set show a state in which fluorescent dots in the fluorescent dot region gradually converge toward the oil leak point; The first threshold setting method includes the following steps: Acquire images of transformers that have been confirmed to have no oil leakage faults and perform preprocessing; The transformer image was segmented to obtain several fluorescent dot regions; After connecting each fluorescent dot region, a third region is obtained; Calculate the ratio of the area of ​​the third region to the internal area of ​​the transformer, and use it as the first threshold.

2. The transformer oil leakage detection method based on fluorescence distribution area according to claim 1, characterized in that, The preprocessing includes the following steps: The acquired transformer image is obtained, and the acquired transformer image is converted to grayscale using a weighted average method to obtain a grayscale image; A grayscale image is filtered by bilateral filtering to remove noise and obtain a filtered image. The filtered image is enhanced by histogram equalization to highlight details and features in the image, resulting in a contrast-enhanced image, which serves as the transformer image for region segmentation.

3. The transformer oil leakage detection method based on fluorescence distribution area according to claim 2, characterized in that, The region cutting includes the following steps: Obtain a contrast-enhanced image; The Sobel operator is used to calculate the gradient values ​​in the horizontal and vertical directions of the contrast-enhanced image, thereby obtaining the gradient intensity and direction of each pixel; The non-maximum suppression algorithm is used to compare the gradient values ​​between two adjacent pixels along the gradient direction to eliminate the blurring effect on the edges. Use dual thresholding to classify pixels into first edge, second edge, and third edge categories; Connect the second edge to the first edge around it to form a complete edge, thus completing the region segmentation.

4. The transformer oil leakage detection method based on fluorescence distribution area according to claim 1, characterized in that, The concentration of the fluorescent substance is calculated based on the fluorescence intensity detected in the region using a fluorescence detector.

5. The transformer oil leakage detection method based on fluorescence distribution area according to claim 4, characterized in that, The formula for calculating the concentration of the fluorescent substance is as follows: Where C represents the concentration of the fluorescent substance, I represents the fluorescence intensity, S is the wavelength of the fluorescence detector light source, P is the transmittance of the fluorescence light path, and K is the fluorescence coefficient of the fluorescent substance.

6. The transformer oil leakage detection method based on fluorescence distribution area according to claim 1, characterized in that, The fluorescence threshold concentration setting method includes the following steps: Acquire images of transformers that have been confirmed to have no oil leakage faults and perform preprocessing; The preprocessed transformer image is segmented to obtain several fluorescent dot regions; The fluorescence intensity of the transformer image at each fluorescence point is detected using a fluorescence detector, and the concentration of fluorescent material in each fluorescence point region is calculated based on the fluorescence intensity. The average concentration of the fluorescent substance in each fluorescent spot region is taken as the fluorescence threshold concentration.

7. A transformer oil leakage detection system based on fluorescence distribution regions, characterized in that, The transformer oil leakage detection system based on fluorescence distribution region is used to implement the transformer oil leakage detection method based on fluorescence distribution region as described in any one of claims 1-6, and includes the following modules: An image acquisition module is configured to acquire and collect transformer images via an image acquisition device, wherein the transformer images are transformer fluorescence images containing fluorescent substance concentration information; An image preprocessing module is configured to preprocess the acquired transformer images; The image segmentation module is configured to segment the transformer image into regions to obtain each fluorescent dot region; connect each fluorescent dot region to form a first region; determine whether the concentration of fluorescent substance in each fluorescent dot region is greater than the fluorescence threshold concentration, and if so, mark the fluorescent dot region and connect the marked points to form a second region; calculate the area S1 of the first region and the area S2 of the second region. The detection module is configured to determine whether the ratio of the area S2 to the area S1 is less than a first threshold. If the ratio is greater than or equal to the first threshold, it is determined that the transformer has no oil leakage. If the ratio is less than the first threshold, it is determined whether the shape of the second region belongs to the first shape set. If the shape of the second region belongs to the first shape set, the transformer is determined to be leaking oil; if the shape of the second region does not belong to the first shape set, the transformer is determined to be not leaking oil.

8. A readable storage medium having a computer program stored thereon, characterized in that, The computer program is executed by a processor using the transformer oil leakage detection method based on fluorescence distribution area as described in any one of claims 1-6.

Images