A method for detecting discrete defects in a nuclear fuel pellet and related assemblies

Abstract

This application discloses a method, apparatus, device, and storage medium for detecting discrete defects in nuclear fuel pellets. The method includes: segmenting a defect region image of a nuclear fuel pellet using threshold segmentation and morphological processing to separate microcracks in the defect region image, obtaining a polygonal region corresponding to each microcrack; determining the skeleton of the microcrack within the polygonal region, determining the crack line corresponding to the microcrack based on the skeleton, and calculating the width of the microcrack within the polygonal region; and determining whether discrete defects exist within the defect region image based on the width, the crack line, and microcrack judgment rules. This method targets small, discrete, fine-stripe defects, accurately detecting the type of discrete defects in the pellet, avoiding false detections such as missing pieces or fragments, and improving the capability for detecting discrete defects in the pellet.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for detecting discrete defects in nuclear fuel pellets. Background Technology

[0002] Nuclear fuel pellets are the core components of nuclear fuel elements, typically small cylindrical blocks. During the pellet manufacturing process, due to temperature and other uncontrollable factors, surface defects such as breakage, chipping, and cracks may occur. Therefore, it is necessary to inspect the appearance of the pellets and assess their surface quality. Traditional methods for inspecting the appearance of nuclear fuel pellets mostly rely on manual visual inspection. However, it is difficult to quantitatively evaluate the surface quality of each pellet using manual visual inspection, and the judgment criteria are hard to control, leading to inconsistent results from different people. This seriously affects the accuracy and repeatability of the inspection results, and the efficiency of manual visual inspection is also relatively low.

[0003] In recent years, machine vision technology using 2D cameras has been gradually applied to the field of detecting defects in the appearance of fuel cells. Currently, in the nuclear industry, machine vision technology is generally used to automatically identify and calculate the area of ​​defects in the appearance of fuel cells under inspection, thereby achieving automatic detection and evaluation of the surface quality of fuel cells.

[0004] However, relying solely on the size of the surface defect area of ​​the chip cannot fully reflect its surface quality, resulting in low accuracy in assessing chip surface quality. Furthermore, traditional detection algorithms cannot accurately identify small, discrete fine stripe defects. These types of defects are often misidentified as missing pieces or other defect types, thus misleading subsequent improvements to the production process. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide a method, apparatus, device, and medium for detecting discrete defects in nuclear fuel pellets, capable of accurately detecting discrete defects in the pellets and avoiding false detections such as missing or broken pellets. The specific solution is as follows:

[0006] In a first aspect, this application discloses a method for detecting discrete defects in nuclear fuel pellets, including:

[0007] Threshold segmentation and morphological processing are used to segment the defect region image of nuclear fuel pellets in order to separate the microcracks in the defect region image and obtain the polygonal region corresponding to each microcrack.

[0008] The framework of the microcrack within the polygonal region is determined, the crack line corresponding to the microcrack is determined based on the framework, and the width of the microcrack within the polygonal region is calculated.

[0009] The presence of discrete defects within the defect region image is determined based on the width, the crack line, and the microcrack judgment rules.

[0010] Optionally, determining the framework of the microcrack within the polygonal region and determining the crack line corresponding to the microcrack based on the framework includes:

[0011] The skeleton of the microcrack in the polygonal region is extracted using a morphological skeleton method.

[0012] The two points on the skeleton that are farthest apart are determined, and a straight line corresponding to the skeleton is generated based on the two points to obtain the crack line corresponding to the microcrack.

[0013] Optionally, calculating the width of the microcrack within the polygonal region includes:

[0014] The crack line is divided into equal parts according to a preset number of divisions, so that each segment of the crack line corresponds to a segmented region in the polygonal region, thereby obtaining the preset number of segmented regions.

[0015] Calculate the width of each segment corresponding to each microcrack in each segmented region, calculate the average width of each segment based on all the segment widths, and use the average width of each segment as the width of the microcrack in the polygonal region.

[0016] Optionally, calculating the single-segment width corresponding to each microcrack in each segmented region includes:

[0017] Determine the maximum inscribed circle corresponding to each of the segmented regions, and calculate the radius of each maximum inscribed circle;

[0018] The width of each segment corresponding to each microcrack in each segmented region is obtained based on the radius.

[0019] Optionally, determining whether discrete defects exist within the defect region image based on the width, the crack line, and the microcrack judgment rules includes:

[0020] Determine whether the width is greater than a preset width threshold, and whether the length of the crack line is within a preset length range;

[0021] If the width is greater than the preset width threshold and the length of the crack line is within the preset length range, then the polygonal region is determined to have a defect.

[0022] If all of the preset number of polygonal regions have defects, then it is determined that there are discrete defects in the image of the defective region.

[0023] Optionally, before segmenting the defect region image of the nuclear fuel pellet using threshold segmentation and morphological processing to separate the microcracks in the defect region image, the method further includes:

[0024] Acquire images corresponding to nuclear fuel pellets; the acquired images include end face images and cylindrical face images;

[0025] The acquired images are processed, and suspected defect regions are extracted from the acquired images based on the image processing results; the image processing includes morphological processing and connected component analysis;

[0026] Based on the selection criteria, defective regions with cracks are selected from all the suspected defective regions as defective region images.

[0027] Optionally, calculating the width of the microcrack within the polygonal region includes:

[0028] By translating the crack line, two target crack lines that are tangent to the microcrack within the polygonal region are obtained;

[0029] The width of the microcrack within the polygonal region is determined based on the distance between the two target crack lines.

[0030] Secondly, this application discloses a discrete defect detection device for nuclear fuel pellets, comprising:

[0031] The segmentation module is used to segment the defect region image of nuclear fuel pellets using threshold segmentation and morphological processing in order to separate the microcracks in the defect region image and obtain the polygonal region corresponding to each microcrack.

[0032] A crack information determination module is used to determine the skeleton of the microcrack within the polygonal region, determine the crack line corresponding to the microcrack based on the skeleton, and calculate the width of the microcrack within the polygonal region.

[0033] The judgment module is used to determine whether there are discrete defects in the defect region image based on the width, the crack line, and the microcrack judgment rules.

[0034] Thirdly, this application discloses an electronic device, including:

[0035] Memory, used to store computer programs;

[0036] A processor is used to execute the computer program to implement the aforementioned method for detecting discrete defects in nuclear fuel pellets.

[0037] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the aforementioned method for detecting discrete defects in nuclear fuel pellets.

[0038] In this application, threshold segmentation and morphological processing are used to segment the defect region image of a nuclear fuel pellet to separate microcracks in the defect region image, obtaining a polygonal region corresponding to each microcrack. The skeleton of the microcrack within the polygonal region is determined, and the crack line corresponding to the microcrack is determined based on the skeleton. The width of the microcrack within the polygonal region is calculated. The presence of discrete defects within the defect region image is determined based on the width, the crack line, and microcrack judgment rules. Therefore, by segmenting the defect region image of a nuclear fuel pellet, obtaining a polygonal region corresponding to each microcrack within the defect region, determining the crack line corresponding to the microcrack within the polygonal region based on the skeleton, calculating the width of the microcrack, and finally determining the presence of discrete defects within the defect region image based on the width, crack line, and microcrack judgment rules, this method can accurately detect the type of discrete defects in the pellet, avoiding false detections such as missing pieces or fragments, and improving the detection capability of discrete defects in the pellet. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0040] Figure 1 A flowchart of a discrete defect detection method for nuclear fuel pellets provided in this application;

[0041] Figure 2 This application provides a specific schematic diagram of a discrete defect;

[0042] Figure 3 A flowchart illustrating a specific method for calculating the width of a microcrack provided in this application;

[0043] Figure 4 A flowchart illustrating another specific method for calculating the width of microcracks provided in this application;

[0044] Figure 5 A schematic diagram of a discrete defect detection device for nuclear fuel pellets provided in this application;

[0045] Figure 6 This application provides a structural diagram of an electronic device. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0047] In the existing technology, machine vision technology using 2D cameras has begun to be gradually applied to the field of detection of appearance defects in pellets. Currently, in the nuclear industry, machine vision technology is generally used to automatically identify and calculate the area of ​​appearance defects in the pellets to be inspected, thereby realizing the automatic detection and evaluation of the surface quality of the pellets.

[0048] However, relying solely on the size of the surface defect area of ​​the fuel pellet cannot fully reflect the surface quality of the pellet, resulting in low accuracy in assessing surface quality. Furthermore, traditional detection algorithms cannot accurately identify small, discrete fine-stripe defects, often misidentifying them as missing or fragmented defects. To overcome these technical problems, this application proposes a method for detecting discrete defects in nuclear fuel pellets, capable of accurately detecting discrete defects and avoiding misidentification as missing or fragmented defects.

[0049] This application discloses a method for detecting discrete defects in nuclear fuel pellets. See [link to relevant documentation]. Figure 1 As shown, the method may include the following steps:

[0050] Step S11: Using threshold segmentation and morphological processing, the defect region image of the nuclear fuel pellet is segmented to separate the microcracks in the defect region image, and obtain the polygonal region corresponding to each microcrack.

[0051] In this embodiment, threshold segmentation and morphological processing are first used to segment the defect region image of the nuclear fuel pellet in order to separate the microcracks in the defect region image and obtain the polygonal region corresponding to each microcrack. For example Figure 2As shown, by performing thresholding and morphological processing on the defect area image of nuclear fuel pellets, each microcrack is extracted based on the processing results. In this embodiment, polygons are used to select the microcracks, obtaining the polygonal region corresponding to each microcrack. The basic idea of ​​morphology is to use a special structuring element to measure or extract the corresponding shape or feature in the input image for further image analysis and target recognition. Thresholding is a region-based image segmentation technique. Its principle is to divide image pixels into several categories. Image thresholding is a traditional and commonly used image segmentation method. The purpose of image thresholding is to divide the pixel set according to gray levels, resulting in each subset forming a region corresponding to a real scene. Each region has consistent attributes, while adjacent regions do not. Therefore, by utilizing the pixel differences between cracked and non-cracked regions, the cracks are extracted.

[0052] In this embodiment, before segmenting the defect region image of the nuclear fuel pellet using threshold segmentation and morphological processing to separate the microcracks in the defect region image, the method further includes: acquiring a sampled image corresponding to the nuclear fuel pellet; the sampled image includes end face image and cylindrical image; performing image processing on the sampled image, and extracting suspected defect regions from the sampled image based on the image processing results; the image processing includes morphological processing and connected component analysis; and selecting defect regions with cracks from all the suspected defect regions as defect region images based on screening criteria.

[0053] Since nuclear fuel pellets are typically cylindrical, images are captured by cameras on the end faces and cylindrical surfaces of the fuel pellets to be inspected. These images are then subjected to morphological processing and connected component analysis. Morphological processing extracts image components that are meaningful for representing and depicting the shape of the region, enabling subsequent recognition to capture the most essential shape features of the target object, such as boundaries and connected regions. In computer vision, a connected component refers to a region within an image. Connected component analysis involves extracting and labeling connected components in the binary image after foreground / background separation. Each labeled connected component represents a foreground object, and relevant features such as area can then be calculated. Finally, suspected defect areas are extracted from the captured images based on the image processing results. After identifying suspected defect areas, target suspected defect areas are selected from all suspected defect areas based on various image feature information filtering conditions, such as the area and aspect ratio of shapes determined from the image, and according to the threshold configured in the filtering conditions. These are designated as defective regions, and the corresponding images are used as defect region images.

[0054] Step S12: Determine the skeleton of the microcrack within the polygonal region, determine the crack line corresponding to the microcrack based on the skeleton, and calculate the width of the microcrack within the polygonal region.

[0055] In this embodiment, the framework of microcracks within each polygonal region is determined, the crack lines corresponding to the microcracks are determined based on the framework, and the width of the microcracks within the polygonal region is calculated. The width of a microcrack is the vast width occupied by the microcrack; since microcracks are usually curved, the width of the microcrack is affected by the amplitude of the curve.

[0056] In this embodiment, determining the skeleton of the microcrack within the polygonal region and determining the corresponding crack line based on the skeleton may include: extracting the skeleton of the microcrack within the polygonal region using a morphological skeleton method; determining the two farthest points on the skeleton; and generating a straight line corresponding to the skeleton based on the two points to obtain the crack line corresponding to the microcrack. Skeleton extraction involves extracting a single-pixel representation of each connected region that approximates its contour. In this embodiment, the skeleton of the microcrack is obtained by extracting the skeleton of the polygonal region, and then the line connecting the two farthest points on the skeleton is used as the crack line corresponding to the microcrack.

[0057] Step S13: Determine whether there are discrete defects in the defect region image based on the width, the crack line, and the microcrack judgment rules.

[0058] In this embodiment, the presence of discrete defects in the defect region image is determined based on the width of the microcrack, the crack line, and the microcrack judgment rules.

[0059] In this embodiment, determining whether discrete defects exist within the defect region image based on the width, the crack line, and the microcrack judgment rule can include: determining whether the width is greater than a preset width threshold and whether the length of the crack line is within a preset length range; if the width is greater than the preset width threshold and the length of the crack line is within the preset length range, then the polygonal region is determined to have a defect; if a preset number of polygonal regions all have defects, then discrete defects exist within the defect region image. The width threshold can be 0.1 mm, and the preset length range can be 1 mm to 4 mm. That is, if the length of the crack line is L and the width of the microcrack is W, if 1 mm... <L<4mm,W> If the defect is 0.1mm, the corresponding polygonal region has a defect. If all of the preset number of polygonal regions have defects, then the image of the defective region is determined to have discrete defects. Identifying discrete defects can be used to provide feedback on the optimization direction of subsequent production processes.

[0060] As can be seen from the above, this embodiment utilizes threshold segmentation and morphological processing to segment the defect region image of nuclear fuel pellets to separate microcracks in the defect region image, obtaining a polygonal region corresponding to each microcrack; determining the skeleton of the microcrack within the polygonal region, determining the crack line corresponding to the microcrack based on the skeleton, and calculating the width of the microcrack within the polygonal region; and determining whether discrete defects exist in the defect region image based on the width, the crack line, and the microcrack judgment rule. It is evident that by segmenting the defect region image of nuclear fuel pellets, obtaining a polygonal region corresponding to each microcrack within the defect region, determining the crack line corresponding to the microcrack within the polygonal region based on the skeleton, calculating the width of the microcrack, and finally determining whether discrete defects exist in the defect region image based on the width, the crack line, and the microcrack judgment rule, the detection of small, discrete, fine-stripe defects can accurately detect the type of discrete defects in the pellet, avoiding false detections such as missing pieces or fragments, and improving the ability to detect discrete defects in the pellet.

[0061] This application discloses a specific method for calculating the width of microcracks, see [link to relevant documentation]. Figure 3 As shown, the method may include the following steps:

[0062] Step S21: Divide the crack line into equal parts according to a preset number of divisions, so that each segment of the crack line corresponds to a segmented region in the polygonal region, thereby obtaining the preset number of segmented regions.

[0063] In this embodiment, the determined crack line is divided into equal parts according to a preset number of divisions, and the divided region corresponding to each crack line segment in the polygonal region is obtained. That is, by dividing the crack line into equal parts, the polygonal region is divided at the same time, and the divided region with the same number of equal parts as the crack line is obtained.

[0064] Step S22: Calculate the single-segment width corresponding to each microcrack in each segmented region, calculate the average single-segment width based on all the single-segment widths, and use the average single-segment width as the width of the microcrack in the polygonal region.

[0065] In this embodiment, the width of each segment of microcrack in each segmented region is calculated, and the average value of the width of each segment is calculated based on the average value of all the widths of the segments to obtain the average width of the segment corresponding to the polygonal region. The average width of the segment is then used as the width of the microcrack in the polygonal region.

[0066] In this embodiment, calculating the single-segment width corresponding to each microcrack within each segmented region may include: determining the maximum inscribed circle corresponding to each segmented region and calculating the radius of each maximum inscribed circle; obtaining the single-segment width corresponding to each microcrack within each segmented region based on the radius. Specifically, in this embodiment, the radius of the maximum inscribed circle can be used to solve for the single-segment width corresponding to each microcrack. The preset number of segments can be 10, that is, each polygonal region is divided into 10 parts, and the maximum inscribed circle operation is performed on each equally divided region to obtain 10 maximum inscribed circle radii. The average of the 10 maximum inscribed circle radii is taken to obtain the average radius R0, which is considered as the width of the microcrack within that polygonal region.

[0067] As can be seen from the above, in this embodiment, the crack line is divided into equal parts according to a preset number of divisions, resulting in a segmented region corresponding to each segment of the crack line within the polygonal region, thus obtaining the preset number of segmented regions. The width of each microcrack within each segmented region is calculated, and the average width of each segment is calculated based on all the segment widths. This average width is then used as the width of the microcrack within the polygonal region. By dividing the cracks and using the radius of the largest inscribed circle to determine the width of each microcrack, and then taking the average of the radii of each largest inscribed circle as the width of the microcrack within the polygonal region, the accurate calculation of the width of the microcrack within the polygonal region is achieved.

[0068] This application discloses a specific method for calculating the width of microcracks, see [link to relevant documentation]. Figure 4 As shown, the method may include the following steps:

[0069] Step S31: By translating the crack line, two target crack lines that are tangent to the microcracks within the polygonal region are obtained.

[0070] In this embodiment, after determining the crack line, the crack line is translated to obtain two lines that are tangent to the microcrack. These two lines are taken as the target crack lines, that is, the crack is between these two parallel target crack lines.

[0071] Step S32: Determine the width of the microcrack within the polygonal region based on the distance between the two target crack lines.

[0072] In this embodiment, the shortest distance between the two parallel target crack lines is calculated and used as the width of the microcrack within the polygonal region.

[0073] As can be seen from the above, in this embodiment, by translating the crack line, two target crack lines tangent to the microcrack within the polygonal region are obtained; the width of the microcrack within the polygonal region is determined based on the distance between the two target crack lines. By directly translating the crack line, obtaining the two target crack lines tangent to the microcrack after translation, and finally determining the width of the microcrack based on the distance between these two target crack lines, the width of the microcrack is quickly calculated.

[0074] Accordingly, this application also discloses a device for detecting discrete defects in nuclear fuel pellets, see [link to relevant documentation]. Figure 5 As shown, the device includes:

[0075] The segmentation module 11 is used to segment the defect region image of the nuclear fuel pellet using threshold segmentation and morphological processing in order to separate the microcracks in the defect region image and obtain the polygonal region corresponding to each microcrack.

[0076] The crack information determination module 12 is used to determine the skeleton of the microcrack within the polygonal region, determine the crack line corresponding to the microcrack based on the skeleton, and calculate the width of the microcrack within the polygonal region.

[0077] The judgment module 13 is used to determine whether there are discrete defects in the defect region image based on the width, the crack line and the microcrack judgment rules.

[0078] As can be seen from the above, this embodiment utilizes threshold segmentation and morphological processing to segment the defect region image of nuclear fuel pellets to separate microcracks in the defect region image, obtaining a polygonal region corresponding to each microcrack; determining the skeleton of the microcrack within the polygonal region, determining the crack line corresponding to the microcrack based on the skeleton, and calculating the width of the microcrack within the polygonal region; and determining whether discrete defects exist in the defect region image based on the width, the crack line, and the microcrack judgment rule. It is evident that by segmenting the defect region image of nuclear fuel pellets, obtaining a polygonal region corresponding to each microcrack within the defect region, determining the crack line corresponding to the microcrack within the polygonal region based on the skeleton, calculating the width of the microcrack, and finally determining whether discrete defects exist in the defect region image based on the width, the crack line, and the microcrack judgment rule, the detection of small, discrete, fine-stripe defects can accurately detect the type of discrete defects in the pellet, avoiding false detections such as missing pieces or fragments, and improving the ability to detect discrete defects in the pellet.

[0079] In some specific embodiments, the crack information determination module 12 may specifically include:

[0080] The skeleton extraction unit is used to extract the skeleton of the microcrack in the polygonal region using a morphological skeleton method.

[0081] The crack line determination unit is used to determine the two points that are farthest apart on the skeleton, and generate a straight line corresponding to the skeleton based on the two points to obtain the crack line corresponding to the microcrack.

[0082] In some specific embodiments, the crack information determination module 12 may specifically include:

[0083] A segmentation unit is used to divide the crack line into equal parts according to a preset number of segments, so as to obtain the segmented region corresponding to each segment of the crack line in the polygonal region, thereby obtaining the preset number of segmented regions.

[0084] A width determination unit is used to calculate the single-segment width corresponding to each microcrack in each segmented region, calculate the average single-segment width based on all the single-segment widths, and use the average single-segment width as the width of the microcrack in the polygonal region.

[0085] In some specific embodiments, the width determination unit may specifically include:

[0086] The maximum inscribed circle radius determination unit is used to determine the maximum inscribed circle corresponding to each of the segmented regions and to calculate the radius of each maximum inscribed circle;

[0087] A single-segment width determination unit is used to obtain the single-segment width corresponding to each microcrack in each segmented region based on the radius.

[0088] In some specific embodiments, the determination module may specifically include:

[0089] The judgment unit is used to determine whether the width is greater than a preset width threshold and whether the length of the crack line is within a preset length range;

[0090] The defect determination unit is used to determine that there is a defect in the polygonal region if the width is greater than the preset width threshold and the length of the crack line is within the preset length range.

[0091] A discrete defect determination unit is used to determine that there is a discrete defect in the image of the defective region if a preset number of the polygonal regions all have defects.

[0092] In some specific embodiments, the discrete defect detection device for nuclear fuel pellets may specifically include:

[0093] An image acquisition unit is used to acquire images corresponding to nuclear fuel pellets; the acquired images include end face images and cylindrical face images.

[0094] A suspected defect region extraction unit is used to perform image processing on the acquired image and extract suspected defect regions from the acquired image based on the image processing results; the image processing includes morphological processing and connected component analysis;

[0095] The defect area image determination unit is used to select defect areas with cracks from all the suspected defect areas as defect area images according to the screening conditions.

[0096] In some specific embodiments, the crack information determination module may specifically include:

[0097] The translation unit is used to translate the crack line to obtain two target crack lines tangent to the microcrack within the polygonal region.

[0098] The distance calculation unit is used to determine the width of the microcrack within the polygonal region based on the distance between the two target crack lines.

[0099] Furthermore, this application also discloses an electronic device, see [link to relevant documentation]. Figure 6 As shown, the content in the figure should not be considered as any limitation on the scope of use of this application.

[0100] Figure 6 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the discrete defect detection method for nuclear fuel pellets disclosed in any of the foregoing embodiments.

[0101] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0102] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon include operating system 221, computer program 222 and data 223 including defect area image, etc. The storage method can be temporary storage or permanent storage.

[0103] The operating system 221 manages and controls the various hardware devices on the electronic device 20 and the computer program 222 to enable the processor 21 to perform calculations and processing on the massive data 223 in the memory 22. It can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the discrete defect detection method for nuclear fuel pellets executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0104] Furthermore, this application also discloses a computer storage medium storing computer-executable instructions. When the computer-executable instructions are loaded and executed by a processor, they implement the steps of the discrete defect detection method for nuclear fuel pellets disclosed in any of the foregoing embodiments.

[0105] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0106] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0107] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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 limitations, 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.

[0108] The present invention provides a detailed description of a method, apparatus, device, and medium for detecting discrete defects in nuclear fuel pellets. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method of detecting discrete defects of a nuclear fuel pellet, characterized by, include: Threshold segmentation and morphological processing are used to segment the defect region image of nuclear fuel pellets in order to separate the microcracks in the defect region image and obtain the polygonal region corresponding to each microcrack. The framework of the microcrack within the polygonal region is determined, the crack line corresponding to the microcrack is determined based on the framework, and the width of the microcrack within the polygonal region is calculated. The presence of discrete defects within the defect region image is determined based on the width, the crack line, and the microcrack judgment rules. The step of determining whether discrete defects exist within the defect region image based on the width, the crack line, and the microcrack judgment rules includes: Determine whether the width is greater than a preset width threshold, and whether the length of the crack line is within a preset length range; If the width is greater than the preset width threshold and the length of the crack line is within the preset length range, then the polygonal region is determined to have a defect. If all of the preset number of polygonal regions have defects, then it is determined that there are discrete defects in the image of the defective region. Prior to segmenting the defect region image of the nuclear fuel pellet using threshold segmentation and morphological processing to separate the microcracks in the defect region image, the method further includes: Acquire images corresponding to nuclear fuel pellets; the acquired images include end face images and cylindrical face images; The acquired images are processed, and suspected defect regions are extracted from the acquired images based on the image processing results; the image processing includes morphological processing and connected component analysis; Based on the selection criteria, defective regions with cracks are selected from all the suspected defective regions as defective region images.

2. The method of discrete flaw detection of nuclear fuel pellets according to claim 1, characterized in that, The step of determining the framework of the microcracks within the polygonal region and determining the crack lines corresponding to the microcracks based on the framework includes: The skeleton of the microcrack in the polygonal region is extracted using a morphological skeleton method. The two points on the skeleton that are farthest apart are determined, and a straight line corresponding to the skeleton is generated based on the two points to obtain the crack line corresponding to the microcrack.

3. The method for detecting discrete defects in nuclear fuel pellets according to claim 1, characterized in that, The calculation of the width of the microcrack within the polygonal region includes: The crack line is divided into equal parts according to a preset number of divisions, so that each segment of the crack line corresponds to a segmented region in the polygonal region, thereby obtaining the preset number of segmented regions. Calculate the width of each segment corresponding to each microcrack in each segmented region, calculate the average width of each segment based on all the segment widths, and use the average width of each segment as the width of the microcrack in the polygonal region.

4. The method for detecting discrete defects in nuclear fuel pellets according to claim 3, characterized in that, The calculation of the single-segment width corresponding to each microcrack in each segmented region includes: Determine the maximum inscribed circle corresponding to each of the segmented regions, and calculate the radius of each maximum inscribed circle; The width of each segment corresponding to each microcrack in each segmented region is obtained based on the radius.

5. The method for detecting discrete defects in nuclear fuel pellets according to any one of claims 1 to 4, characterized in that, The calculation of the width of the microcrack within the polygonal region includes: By translating the crack line, two target crack lines that are tangent to the microcrack within the polygonal region are obtained; The width of the microcrack within the polygonal region is determined based on the distance between the two target crack lines.

6. A device for detecting discrete defects in nuclear fuel pellets, characterized in that, include: The segmentation module is used to segment the defect region image of nuclear fuel pellets using threshold segmentation and morphological processing in order to separate the microcracks in the defect region image and obtain the polygonal region corresponding to each microcrack. A crack information determination module is used to determine the skeleton of the microcrack within the polygonal region, determine the crack line corresponding to the microcrack based on the skeleton, and calculate the width of the microcrack within the polygonal region. The judgment module is used to determine whether there are discrete defects in the defect region image based on the width, the crack line, and the microcrack judgment rules. The judgment module is used to determine whether the width is greater than a preset width threshold and whether the length of the crack line is within a preset length range; if the width is greater than the preset width threshold and the length of the crack line is within the preset length range, then the polygonal region is determined to have a defect; if a preset number of polygonal regions have defects, then the image of the defective region is determined to have discrete defects. Prior to segmenting the defect region image of the nuclear fuel pellet using threshold segmentation and morphological processing to separate the microcracks in the defect region image, the method further includes: Acquire images corresponding to nuclear fuel pellets; the acquired images include end face images and cylindrical face images; The acquired images are processed, and suspected defect regions are extracted from the acquired images based on the image processing results; the image processing includes morphological processing and connected component analysis; Based on the selection criteria, defective regions with cracks are selected from all the suspected defective regions as defective region images.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the discrete defect detection method for nuclear fuel pellets as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein the computer program, when executed by a processor, implements the discrete defect detection method for nuclear fuel pellets as described in any one of claims 1 to 5.

Images