Method and device for detecting optical anisotropy of coated fuel particles and computing equipment

Abstract

The invention discloses a coated fuel particle optical anisotropy detection method and device and computing equipment, and the method comprises the steps: traversing and collecting a plurality of first view metallographic section images covering a whole metallographic sample to determine the image position information of each coated fuel particle, and carrying out the coordinate splicing to obtain a global coordinate map; acquiring a second view metallographic section image of each coated fuel particle one by one based on the global coordinate map; performing coating definition on the second visual field metallographic section image by utilizing a semantic segmentation model, and further performing testability analysis on the coated fuel particles to screen out a plurality of target coated fuel particles; and extracting a dense pyrolytic carbon layer region from the second view metallographic cross-section image of the target coated fuel particle based on the layer definition image, selecting a region to be measured from the region, and performing reflectivity measurement on the region to be measured so as to determine the optical anisotropy of the target coated fuel particle. According to the invention, automation and intellectualization of the optical anisotropy detection process of the coated fuel particles can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of computer and visual detection, and in particular to a method for detecting optical anisotropy of coated fuel particles, a device for detecting optical anisotropy of coated fuel particles and a computing device. Background Art

[0002] Nuclear energy is the key to responding to the global energy crisis and an important means to ensure national energy security, economy and greenness. The high temperature gas-cooled reactor is a representative reactor type in the fourth generation of nuclear power. It has the characteristics of constitutive safety and modular design, and the related technologies are independently controllable. Coated fuel particles are the operating basis (smallest unit) of high temperature gas-cooled reactors. The number of coated fuel particles in each reactor module exceeds 4 billion. Their optical anisotropy affects the thermal conductivity and mechanical properties of nuclear fuel elements. Therefore, accurate detection of the optical anisotropy of coated fuel particles is an important guarantee for the safe operation of nuclear reactors.

[0003] In the prior art, metallographic method is usually used to perform cross-sectional inspection on coated fuel particles. However, since the coated fuel particles in the metallographic photographs are tiny and numerous, it is very difficult to detect the anisotropy of the coated fuel particles. In addition, manual inspection has low accuracy, low efficiency, and insufficient consistency of results, which cannot meet the inspection needs of coated fuel particles.

[0004] Therefore, a method for detecting optical anisotropy of coated fuel particles is needed to solve the problems existing in the above technical solutions. Summary of the invention

[0005] To this end, the present invention provides a method and device for detecting optical anisotropy of coated fuel particles to solve or at least alleviate the above problems.

[0006] According to one aspect of the present invention, there is provided a method for detecting optical anisotropy of coated fuel particles, which is executed in a computing device, the computing device being communicatively connected to a microscope, the electric stage of the microscope being suitable for placing a metallographic sample having a plurality of coated fuel particles, the method comprising: controlling the microscope to traverse and collect a plurality of first-field metallographic cross-sectional images covering the entire metallographic sample; determining image position information of a plurality of coated fuel particles contained in each of the first-field metallographic cross-sectional images; performing coordinate stitching on the image position information of all coated fuel particles contained in the plurality of first-field metallographic cross-sectional images to obtain a global coordinate map covering all coated fuel particles in the metallographic sample; based on the global coordinate map, controlling the microscope to collect the metallographic sample one by one; a second-field metallographic cross-sectional image of each coated fuel particle in the product; for each of the coated fuel particles, using a semantic segmentation model to perform coating definition on the second-field metallographic cross-sectional image of the coated fuel particle to obtain a corresponding coating definition image, and performing a measurability analysis on the coated fuel particles based on the coating definition image to screen out a plurality of target coated fuel particles that meet anisotropy measurement conditions; for each of the target coated fuel particles, extracting a dense pyrolytic carbon layer region from the second-field metallographic cross-sectional image of the target coated fuel particle based on the corresponding coating definition image, and selecting a region to be measured from the dense pyrolytic carbon layer region; performing reflectivity measurement on the region to be measured to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle.

[0007] Optionally, in the optical anisotropy detection method of coated fuel particles according to the present invention, a region to be tested is selected from the dense pyrolytic carbon layer region, including: determining the first black spot ratio in the dense pyrolytic carbon layer region, and judging whether the black spots are the essential attributes of the dense pyrolytic carbon layer region based on the first black spot ratio; extracting multiple reflectivity measurement areas from the dense pyrolytic carbon layer region, and determining the second black spot ratio in each of the reflectivity measurement areas; if the black spots are the essential attributes of the dense pyrolytic carbon layer region, then selecting the reflectivity measurement area with the largest second black spot ratio from the multiple reflectivity measurement areas as the region to be tested; if the black spots are not the essential attributes of the dense pyrolytic carbon layer region, then selecting the reflectivity measurement area with the smallest second black spot ratio from the multiple reflectivity measurement areas as the region to be tested.

[0008] Optionally, in the optical anisotropy detection method of coated fuel particles according to the present invention, multiple reflectivity measurement areas are extracted from the dense pyrolytic carbon layer area, including: on the coating boundary image of the target coated fuel particle, a target coordinate system is established with the core mass center of the target coated fuel particle as the target origin; two measurement lines are drawn along the X-axis and Y-axis directions of the target coordinate system, and multiple areas of predetermined sizes are respectively extracted from multiple intersections of the two measurement lines and the dense pyrolytic carbon layer area as multiple reflectivity measurement areas.

[0009] Optionally, in the method for detecting the optical anisotropy of coated fuel particles according to the present invention, the reflectivity of the area to be tested is measured to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particles, including: controlling the electric stage of the microscope to drive the metallographic sample to move so that the center of the area to be tested of the target coated fuel particles is located at the center of the collection area of ​​the microscope; controlling the microscope to switch to a third-magnification polarizing objective lens, and adjusting the field diaphragm to a minimum, so that the microscope automatically focuses to a clear border of the field diaphragm; adjusting the polarizer of the microscope to generate polarized light in two directions at 0° and 90°, respectively, and measuring the maximum reflectivity and minimum reflectivity of the area to be tested under the two polarized lights by a microphotometer as the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particles.

[0010] Optionally, in the method for detecting optical anisotropy of coated fuel particles according to the present invention, determining the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particles also includes: comparing the optical anisotropy of the dense pyrolytic carbon layer with the standard optical anisotropy of a standard substance with known reflectivity under the two polarized lights to determine the optical anisotropy factor of the dense pyrolytic carbon layer.

[0011] Optionally, in the optical anisotropy detection method of coated fuel particles according to the present invention, the microscope is controlled to traverse and collect multiple first-field metallographic section images covering the entire metallographic sample, including: obtaining a first-field metallographic section image of the central area of ​​the metallographic sample collected by the microscope, taking the core mass center of any coated fuel particle in the first-field metallographic section image as the absolute origin, and establishing an absolute coordinate system for the metallographic sample; determining a traversal collection path covering the entire metallographic sample based on the absolute coordinate system; controlling the microscope to traverse and collect multiple first-field metallographic section images covering the entire metallographic sample based on the traversal collection path with the absolute origin as the starting point.

[0012] Optionally, in the optical anisotropy detection method of coated fuel particles according to the present invention, based on the global coordinate map, the microscope is controlled to collect the second field of view metallographic section image of each coated fuel particle in the metallographic sample one by one, including: based on the global coordinate map and the traversal acquisition path, path planning is performed on each coated fuel particle in each first field of view metallographic section image to determine the global acquisition path; based on the global acquisition path, the microscope is controlled to collect the second field of view metallographic section image of each coated fuel particle in the metallographic sample one by one.

[0013] Optionally, in the optical anisotropy detection method of coated fuel particles according to the present invention, the image position information of multiple coated fuel particles contained in each of the first field of view metallographic section images is determined, including: using a particle intelligent positioning model to determine the image position information of multiple coated fuel particles contained in each of the first field of view metallographic section images, the particle intelligent positioning model includes a feature extraction network, an anchor frame generation network, a suggestion generation network, and a fully connected network coupled in sequence; wherein the feature extraction network is used to extract features from the first field of view metallographic section image to obtain a feature image; the anchor frame generation network is used to generate an anchor frame based on the feature image; the suggestion generation network is used to determine candidate suggestion areas based on the feature image and the anchor frame; the fully connected network is used to classify and refine the coordinates of the candidate suggestion areas to determine the image position information of multiple coated fuel particles, and eliminate one or more incomplete coated fuel particles, and output a positioning mark image corresponding to the first field of view metallographic section image.

[0014] Optionally, in the optical anisotropy detection method of coated fuel particles according to the present invention, a measurability analysis is performed on the coated fuel particles based on the coating definition image, including: performing an integrity analysis on the coated fuel particles based on the coating definition image to determine whether the coated fuel particles are intact; if it is determined that the coated fuel particles are intact, determining the tangent distance between the coated fuel particles and their adjacent coated fuel particles based on the coating definition image, and determining whether the cross-section of the coated fuel particles is close to the equatorial plane based on the tangent distance; if it is close to the equatorial plane, determining that the coated fuel particles meet the tangency requirements, and using the coated fuel particles as target coated fuel particles that meet the anisotropy measurement conditions.

[0015] Optionally, in the method for detecting optical anisotropy of coated fuel particles according to the present invention, controlling the microscope to traverse and collect multiple first-field metallographic cross-sectional images covering the entire metallographic sample includes: controlling the microscope to use a first-magnification objective lens to traverse and collect multiple first-field metallographic cross-sectional images covering the entire metallographic sample; controlling the microscope to collect the second-field metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one, including: controlling the microscope to use a second-magnification objective lens to collect the second-field metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one.

[0016] According to one aspect of the present invention, there is provided a device for detecting optical anisotropy of coated fuel particles, which is deployed in a computing device, the computing device is communicatively connected to a microscope, and the electric stage of the microscope is suitable for placing a metallographic sample having a plurality of coated fuel particles. The device comprises: a first acquisition unit, suitable for controlling the microscope to traverse and acquire a plurality of first-field-of-view metallographic cross-sectional images covering the entire metallographic sample; a determination unit, suitable for determining image position information of a plurality of coated fuel particles contained in each of the first-field-of-view metallographic cross-sectional images; a splicing unit, suitable for performing coordinate splicing on the image position information of all coated fuel particles contained in the plurality of first-field-of-view metallographic cross-sectional images to obtain a global coordinate map covering all coated fuel particles in the metallographic sample; and a second acquisition unit, suitable for controlling the microscope to acquire the image position information of the coated fuel particles one by one based on the global coordinate map. A second-field metallographic cross-sectional image of each coated fuel particle in the metallographic sample is collected; an analysis unit is adapted to perform coating definition on the second-field metallographic cross-sectional image of the coated fuel particle using a semantic segmentation model for each of the coated fuel particles to obtain a corresponding coating definition image, and perform measurability analysis on the coated fuel particles based on the coating definition image to screen out a plurality of target coated fuel particles that meet anisotropy measurement conditions; an extraction unit is adapted to extract a dense pyrolytic carbon layer region from the second-field metallographic cross-sectional image of the target coated fuel particle based on the corresponding coating definition image for each of the target coated fuel particles, and select a region to be measured from the dense pyrolytic carbon layer region; a measurement unit is adapted to perform reflectivity measurement on the region to be measured to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle.

[0017] According to one aspect of the present invention, there is provided a computing device, comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be suitable for execution by the at least one processor, and the program instructions include instructions for executing the optical anisotropy detection method of coated fuel particles as described above.

[0018] According to one aspect of the present invention, a computer program product is provided, comprising a computer program / instruction, wherein the computer program / instruction implements the method as described above when executed by a processor.

[0019] According to one aspect of the present invention, a readable storage medium storing program instructions is provided. When the program instructions are read and executed by a computing device, the computing device executes the method for detecting optical anisotropy of coated fuel particles as described above.

[0020] According to the technical solution of the present invention, a method for detecting the optical anisotropy of coated fuel particles is provided. The computing device first controls the microscope to traverse and collect multiple first-field metallographic cross-sectional images covering the entire metallographic sample, determines the image position information of multiple coated fuel particles contained in each first-field metallographic cross-sectional image, and coordinates the image position information of all coated fuel particles to obtain a global coordinate map covering all coated fuel particles in the metallographic sample. Then, based on the global coordinate map, the microscope can be controlled to collect the second-field metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one, and the second-field metallographic cross-sectional image is segmented to perform measurability analysis on the coated fuel particles. After that, the area to be tested is selected from the dense pyrolytic carbon layer area of ​​each target coated fuel particle that meets the anisotropy measurement condition. Finally, the reflectivity is measured for the area to be tested to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle. Based on this, the present invention can realize the automation and intelligence of the optical anisotropy detection process of the dense pyrolytic carbon layer of the coated fuel particle, the detection process is more efficient, and the detection accuracy and consistency of the detection results are improved. Among them, it realizes the automatic acquisition of high-quality images of multiple fields of view of each coated fuel particle; it can intelligently locate the coated fuel particles, intelligently analyze and screen the target coated fuel particles that meet the anisotropy measurement conditions, and intelligently screen the test area for optical anisotropy detection, and then realize the accurate measurement of the optical anisotropy of the coated fuel particles based on the test area.

[0021] In addition, by comparing the optical anisotropy of the dense pyrolytic carbon layer with the standard optical anisotropy of the standard substance, the optical anisotropy test results can be corrected, and then interfering factors such as environmental changes can be eliminated to ensure that the optical anisotropy test results are accurate and reliable.

[0022] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to achieve the above and related purposes, some illustrative aspects are described herein in conjunction with the following description and accompanying drawings, which indicate various ways in which the principles disclosed herein can be practiced, and all aspects and their equivalents are intended to fall within the scope of the claimed subject matter. By reading the following detailed description in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present invention will become more apparent. Throughout the present invention, the same reference numerals generally refer to the same parts or elements.

[0024] Figure 1 A schematic diagram of a computing device 100 provided according to an embodiment of the present invention is shown;

[0025] Figure 2 A schematic flow chart of a method 200 for detecting optical anisotropy of coated fuel particles provided in accordance with an embodiment of the present invention is shown;

[0026] Figure 3 A schematic diagram of establishing an absolute coordinate system for a metallographic sample according to an embodiment of the present invention is shown;

[0027] Figure 4 A schematic diagram of a traversal collection path according to an embodiment of the present invention is shown;

[0028] Figure 5 A schematic diagram showing a positioning mark image according to an embodiment of the present invention is shown;

[0029] Figure 6 A schematic diagram of a global acquisition path according to an embodiment of the present invention is shown;

[0030] Figure 7 A schematic diagram showing the effect of a coating definition image corresponding to a metallographic cross-section image of the second field of view according to an embodiment of the present invention is shown;

[0031] Figure 8 A schematic diagram showing the proportion of black spots in a dense pyrolytic carbon layer region according to an embodiment of the present invention is shown;

[0032] Fig. 9 A schematic diagram showing extracting multiple reflectivity measurement areas from a dense pyrolytic carbon layer area and selecting an area to be measured according to an embodiment of the present invention;

[0033] Fig.10 A schematic diagram showing a visualized metallographic map of a metallographic sample generated according to an embodiment of the present invention;

[0034] Fig.11 A schematic diagram of the structure of a particle intelligent positioning model 1100 provided according to an embodiment of the present invention is shown;

[0035] Fig.12A schematic diagram of a particle intelligent positioning model provided according to an embodiment of the present invention is shown;

[0036] Fig.13 A schematic diagram of the structure of a semantic segmentation model 1300 provided according to an embodiment of the present invention is shown;

[0037] Fig.14 A schematic diagram showing tangency analysis of coated fuel particles according to an embodiment of the present invention is shown;

[0038] Fig.15 A schematic diagram of an optical anisotropy detection device 1500 for coated fuel particles provided according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0039] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0040] In view of the problems in the prior art that anisotropy detection of coated fuel particles is very difficult, has low detection accuracy, low efficiency, and insufficient result consistency, the embodiments of the present invention propose a method for detecting optical anisotropy of coated fuel particles, which can realize the automation and intelligence of the optical anisotropy detection process of coated fuel particles, make the detection process more efficient, and improve the detection accuracy and consistency of the detection results.

[0041] The method for detecting optical anisotropy of coated fuel particles in the embodiment of the present invention may be executed in a computing device.

[0042] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0043] Figure 1 FIG. 1 is a schematic diagram of a computing device 100 provided according to an embodiment of the present invention. Figure 1 As shown, in a basic configuration, the computing device 100 includes at least one processing unit 102 and a system memory 104. According to one aspect, depending on the configuration and type of the computing device, the processing unit 102 can be implemented as a processor. The system memory 104 includes, but is not limited to, volatile storage (e.g., random access memory), non-volatile storage (e.g., read-only memory), flash memory, or any combination of such memories. According to one aspect, the system memory 104 includes an operating system 105.

[0044] According to one aspect, operating system 105 is suitable for controlling the operation of computing device 100, for example. Furthermore, examples are practiced in conjunction with graphics libraries, other operating systems, or any other application programs, and are not limited to any particular application or system. Figure 1 The basic configuration is shown in FIG. 1 by those components within the dashed lines. According to one aspect, computing device 100 has additional features or functionality. For example, according to one aspect, computing device 100 includes additional data storage devices (removable and / or non-removable), such as magnetic disks, optical disks, or tapes. Such additional storage Figure 1 1 is illustrated by a removable storage device 109 and a non-removable storage device 110.

[0045] As stated above, according to one aspect, a program module 103 is stored in the system memory 104. According to one aspect, the program module 103 may include one or more application programs, and the present invention does not limit the type of application program, for example, the application program may include: email and contact application programs, word processing application programs, spreadsheet application programs, database application programs, slide show application programs, drawing or computer-aided application programs, web browser application programs, etc.

[0046] According to one aspect, the program module 103 may include a plurality of program instructions suitable for executing the coated fuel particle optical anisotropy detection method 200 of the present invention, so that the computing device 100 is configured to execute the coated fuel particle optical anisotropy detection method 200 of the present invention.

[0047] According to one aspect, the program module 103 may include a coated fuel particle optical anisotropy detection device 1500 , and the coated fuel particle optical anisotropy detection device 1500 may be configured to execute the coated fuel particle optical anisotropy detection method 200 of the present invention.

[0048] According to one aspect, the examples may be practiced on a circuit comprising discrete electronic components, a packaged or integrated electronic chip containing logic gates, a circuit utilizing a microprocessor, or a single chip containing electronic components or a microprocessor. Figure 1Each or many components shown in can be integrated into a system on a chip (SOC) on a single integrated circuit to practice examples. According to one aspect, such a SOC device may include one or more processing units, a graphics unit, a communication unit, a system virtualization unit, and various application functions, all of which are integrated (or "burned") into a chip substrate as a single integrated circuit. When operated via SOC, the functions described in this article can be operated via a dedicated logic integrated with other components of the computing device 100 on a single integrated circuit (chip). Embodiments of the present invention can also be practiced using other technologies capable of performing logical operations (such as AND, OR, and NOT), including but not limited to mechanical, optical, fluid, and quantum technologies. In addition, embodiments of the present invention can be practiced in a general-purpose computer or in any other circuit or system.

[0049] According to one aspect, the computing device 100 may also have one or more input devices 112, such as a keyboard, a mouse, a pen, a voice input device, a touch input device, etc. Output devices 114 may also be included, such as a display, a speaker, a printer, etc. The aforementioned devices are examples and other devices may also be used. The computing device 100 may include one or more communication connections 116 that allow communication with other computing devices 118. Examples of suitable communication connections 116 include, but are not limited to: RF transmitter, receiver and / or transceiver circuits; Universal Serial Bus (USB), parallel and / or serial ports.

[0050] The term computer-readable medium as used herein includes computer storage media. Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (e.g., computer-readable instructions, data structures, or program modules 103). System memory 104, removable storage device 109, and non-removable storage device 110 are all examples of computer storage media (i.e., memory storage). Computer storage media may include random access memory (RAM), read-only memory (ROM), electrically erasable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, cassettes, tapes, disk storage or other magnetic storage devices, or any other products that can be used to store information and can be accessed by computing device 100. According to one aspect, any such computer storage medium can be a part of computing device 100. Computer storage media do not include carrier waves or other propagated data signals.

[0051] According to one aspect, communication media is implemented by computer readable instructions, data structures, program modules 103, or other data in a modulated data signal (e.g., a carrier wave or other transport mechanism), and includes any information delivery media. According to one aspect, the term "modulated data signal" describes a signal that has one or more characteristics set or changed in such a manner as to encode information in the signal. By way of example and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, radio frequency (RF), infrared, and other wireless media.

[0052] In an embodiment according to the present invention, the computing device 100 is configured to execute the coated fuel particle optical anisotropy detection method 200 of the present invention. The computing device 100 includes one or more processors and one or more readable storage media storing program instructions, and when the program instructions are configured to be executed by one or more processors, the computing device executes the coated fuel particle optical anisotropy detection method 200 in the embodiment of the present invention.

[0053] Figure 2 The flowchart of a method 200 for detecting optical anisotropy of coated fuel particles according to an embodiment of the present invention is shown. The method 200 for detecting optical anisotropy of coated fuel particles may be executed in a computing device (eg, the aforementioned computing device 100).

[0054] In an embodiment of the present invention, the computing device 100 is connected to the microscope in communication, and the computing device 100 can cooperate with the microscope to automatically detect the optical anisotropy of the dense pyrolytic carbon layer (including the inner dense pyrolytic carbon layer and the outer dense pyrolytic carbon layer) of the coated fuel particles. Before executing the method 200, a metallographic sample having a plurality of coated fuel particles can be placed on the electric stage of the microscope in advance.

[0055] It should be noted that the coated fuel particles include a core (uranium dioxide core) and multiple coating layers coated outside the core, and the multiple coating layers include a loose pyrolytic carbon layer, an inner dense pyrolytic carbon layer, a pyrolytic silicon carbide layer, and an outer dense pyrolytic carbon layer from the outside to the inside.

[0056] like Figure 2 As shown, the method 200 for detecting optical anisotropy of coated fuel particles includes the following steps 210-270.

[0057] Step 210: The computing device 100 may control the microscope to traverse and collect a plurality of first field of view metallographic cross-sectional images covering the entire metallographic sample (metallographic photograph). It should be noted that the metallographic sample contains a plurality of coated fuel particles.

[0058] Specifically, the computing device 100 can control the microscope to use a first magnification objective lens to traverse and collect multiple first field of view metallographic cross-sectional images covering the entire metallographic sample. The first magnification objective lens corresponds to the first field of view metallographic cross-sectional image. For example, the first magnification objective lens can be a 5-fold objective lens, and accordingly, the first field of view can be a 5-fold field of view.

[0059] In some embodiments, before executing step 210 , the computing device 100 may pre-establish an absolute coordinate system of the metallographic sample. Figure 3 FIG. 2 is a schematic diagram showing an absolute coordinate system for establishing a metallographic sample according to an embodiment of the present invention. Figure 3 , the computing device 100 can control the microscope to collect a first field of view metallographic cross-sectional image of the central area of ​​the metallographic sample (the first field of view is, for example, a 5-fold field of view), and obtain the first field of view metallographic cross-sectional image of the central area of ​​the metallographic sample collected by the microscope. Subsequently, the core mass center of any coated fuel particle in the first field of view metallographic cross-sectional image can be used as the absolute origin (i.e., the origin of the absolute coordinate system of the metallographic sample) to establish the absolute coordinate system of the metallographic sample. It should be noted that in order to distinguish it from the target coordinate system below, the origin of the absolute coordinate system is referred to as the "absolute origin" here.

[0060] Subsequently, the computing device 100 may determine a traversal acquisition path covering the entire metallographic sample based on the absolute coordinate system. The traversal acquisition path is used to instruct the microscope to traverse the entire metallographic sample to acquire a plurality of first field of view metallographic cross-sectional images covering the entire metallographic sample. Here, Figure 4 A schematic diagram of the traversal acquisition path in an embodiment of the present invention is shown. Afterwards, the computing device 100 can control the microscope to take the absolute origin as the starting point, and based on the traversal acquisition path, traverse and acquire multiple first field of view metallographic cross-sectional images covering the entire metallographic sample. Here, it should be noted that before imaging, each acquisition point of the metallographic sample can be moved to the laser sensor of the microscope for focusing calibration to avoid a decrease in image clarity due to the uneven surface of the metallographic sample.

[0061] Step 220: The computing device 100 may determine the image position information (coordinates) of the plurality of coated fuel particles contained in each first field of view metallographic cross-sectional image. In addition, in step 220, some incomplete coated fuel particles in the first field of view metallographic cross-sectional image may be removed at the same time.

[0062] It should be noted that, by determining the image position information of a plurality of coated fuel particles included in the metallographic cross-sectional image of the first field of view, a positioning mark image corresponding to the metallographic cross-sectional image of the first field of view can be obtained. Figure 5 A schematic diagram of a positioning mark image according to an embodiment of the present invention is shown.

[0063] In some embodiments, in step 220, the computing device 100 may use a particle intelligent positioning model to determine the image position information of multiple coated fuel particles contained in each first field of view metallographic cross-sectional image, and may remove some incomplete coated fuel particles. The particle intelligent positioning model will be described in the following embodiments.

[0064] Step 230, the computing device 100 can perform coordinate stitching on the image position information of all coated fuel particles contained in multiple first-field-of-view metallographic cross-sectional images to obtain a global coordinate map covering all coated fuel particles in the metallographic sample (all coated fuel particles remaining after excluding some incomplete coated fuel particles).

[0065] Step 240: The computing device 100 may control the microscope to collect the second field of view metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one based on the global coordinate map. It should be noted that the second field of view metallographic cross-sectional image only contains a single complete coated fuel particle.

[0066] Specifically, the computing device 100 can control the microscope to use the second magnification objective lens based on the global coordinate map to collect the second field of view metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one. Here, the second magnification objective lens corresponds to the second field of view metallographic cross-sectional image. In an embodiment of the present invention, the second magnification is greater than the first magnification, and correspondingly, the second field of view is smaller than the first field of view. For example, the first magnification can be 5 times, and the second magnification can be 10 times, that is, the first magnification objective lens can be a 5-fold objective lens, and the second magnification objective lens can be a 10-fold objective lens, and correspondingly, the second field of view can be a 10-fold field of view.

[0067] In some embodiments, the computing device 100 may perform path planning for each coated fuel particle in each first field of view metallographic cross-sectional image based on the global coordinate map and the above-mentioned traversal acquisition path to determine the global acquisition path. Figure 6 A schematic diagram of a global acquisition path in an embodiment of the present invention is shown. It should be noted that the global acquisition path is used to instruct the microscope to collect the second field of view metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one. Furthermore, the computing device 100 can control the microscope (using the second magnification objective lens) to collect the second field of view metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one based on the global acquisition path.

[0068] Step 250, the computing device 100 can use the semantic segmentation model to perform coating definition on the second field of view metallographic cross-sectional image of each coated fuel particle to obtain a corresponding coating definition image (i.e., a segmentation mask image). Furthermore, based on the coating definition image, a measurability analysis (including integrity analysis and tangency analysis) can be performed on the coated fuel particle to screen out multiple target coated fuel particles that meet the anisotropy measurement conditions from all the coated fuel particles in the metallographic sample.

[0069] here, Figure 7 A schematic diagram showing the effect of the coating definition image corresponding to the metallographic cross-section image of the second field of view according to an embodiment of the present invention is shown. Figure 7 As shown, the coating definition image includes multiple segmented coatings (corresponding to the core of the coated fuel particle and each coating layer respectively).

[0070] Specifically, when performing the measurability analysis in step 250, the computing device 100 can first perform an integrity analysis on the coated fuel particles (the coated fuel particles in the second field of view metallographic cross-section image) based on the corresponding coating definition image to determine whether the coated fuel particles are intact (whether they meet the integrity requirements). Here, the integrity requirements are as follows: the core of the coated fuel particles has not fallen off and is intact, each coating layer has no obvious falling off and cracks, and the boundary lines of each coating layer are clear and tightly combined. In other words, if it is determined that the core of the coated fuel particles has not fallen off and is intact, each coating layer has no obvious falling off and cracks, and the boundary lines of each coating layer are clear and tightly combined, it can be determined that the coated fuel particles are intact.

[0071] If it is determined that the coated fuel particles are intact, the coated fuel particles can continue to be analyzed for tangency based on the coating definition image, as follows: the tangent distance between the coated fuel particles (i.e., the coated fuel particles to be tested) and their adjacent coated fuel particles can be determined based on the coating definition image, and whether the cross section (processed surface) of the coated fuel particles to be tested is close to the equatorial plane can be determined based on the tangent distance. If it is close to the equatorial plane, it is determined that the coated fuel particles to be tested meet the tangency requirements, and the coated fuel particles to be tested are used as target coated fuel particles that meet the anisotropic measurement conditions. It should be noted that when the tangent distance between the coated fuel particles to be tested and their adjacent coated fuel particles is small enough, it can be determined that the processed surface of the coated fuel particles to be tested is close to its equatorial plane, and at this time, the thickness measurement value is close to its true value, meeting the tangency requirements.

[0072] Step 260, the computing device 100 can extract the dense pyrolytic carbon layer area from the second field of view metallographic cross-section image of the target coated fuel particle for each target coated fuel particle based on the corresponding layer definition image, and select the area to be tested (i.e., the area to be tested of the target coated fuel particle) from the dense pyrolytic carbon layer area.

[0073] Step 270: For each target coated fuel particle, the computing device 100 can measure the reflectivity of the target coated fuel particle's test area (specifically, the reflectivity of the test area under polarized light in different directions can be measured) to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle. In this way, the optical anisotropy detection of the target coated fuel particle is realized automatically and intelligently.

[0074] Figure 8 A schematic diagram of determining the proportion of black spots in a dense pyrolytic carbon layer region according to an embodiment of the present invention is shown. Fig. 9 A schematic diagram is shown of extracting multiple reflectivity measurement areas from a dense pyrolytic carbon layer area and selecting an area to be measured according to an embodiment of the present invention.

[0075] In some embodiments, reference Figure 8 and Fig. 9 In step 260, the specific method of selecting the area to be measured from the dense pyrolytic carbon layer area is as follows: First, determine the proportion of black spots in the dense pyrolytic carbon layer area (the first black spot proportion), and judge whether the black spots are the essential attributes of the dense pyrolytic carbon layer area based on the first black spot proportion. For example, if the first black spot proportion is within the target proportion interval, it can be determined that the black spots are the essential attributes of the dense pyrolytic carbon layer area; otherwise, it is determined that the black spots are not the essential attributes of the dense pyrolytic carbon layer area. It should be pointed out that the target proportion interval can be set according to actual conditions, and the present invention does not impose specific restrictions on this. Subsequently, multiple reflectivity measurement areas can be extracted from the dense pyrolytic carbon layer area. Afterwards, the black spot ratio analysis can be performed on each reflectivity measurement area in the following manner: determine the black spot ratio (second black spot ratio) in each reflectivity measurement area; if it is determined in the above steps that black spots are the essential attributes of the dense pyrolytic carbon layer area, then the reflectivity measurement area with the second largest black spot ratio can be selected from multiple reflectivity measurement areas as the area to be tested; if it is determined in the above steps that black spots are not the essential attributes of the dense pyrolytic carbon layer area, then the reflectivity measurement area with the second smallest black spot ratio can be selected from multiple reflectivity measurement areas as the area to be tested.

[0076] In a specific embodiment, referring to Fig. 9 , the specific method of extracting multiple reflectivity measurement areas from the dense pyrolytic carbon layer area is as follows: First, on the coating boundary image of the target coated fuel particle, a target coordinate system is established with the core mass center of the target coated fuel particle as the target origin. Then, two measurement lines can be drawn along the X-axis and Y-axis directions of the target coordinate system, and multiple (8) predetermined size areas are extracted from multiple (8) intersections of the two measurement lines and the dense pyrolytic carbon layer area as multiple reflectivity measurement areas. The predetermined size is, for example, 4μm*4μm.

[0077] In addition, if all of the above-mentioned reflectivity measurement areas do not meet the measurement requirements, the two measurement lines can be rotated simultaneously with the target origin of the target coordinate system as the center (ensuring that the two measurement lines are perpendicular to each other) to obtain two new measurement lines, and based on the intersection of the two new measurement lines and the dense pyrolytic carbon layer area, a new reflectivity measurement area of ​​a predetermined size is re-extracted, and a black spot ratio analysis is performed on the new reflectivity measurement area until the area to be measured that meets the measurement requirements is obtained.

[0078] In some embodiments, in step 270, the computing device 100 measures the reflectivity of the target coated fuel particle in the region to be tested to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle in the following specific manner:

[0079] First, the computing device 100 can control the electric stage of the microscope to drive the metallographic sample to move, so that the center of the target coated fuel particle to be tested is located at the center of the collection area of ​​the microscope.

[0080] Subsequently, the computing device 100 can control the microscope to switch to the third-magnification polarized objective lens, and adjust the field aperture to the minimum, so that the microscope automatically focuses until the field aperture border is clear. It should be noted that the third magnification is greater than the second magnification, for example, the third magnification can be 50 times, and the third-magnification polarized objective lens is a 50-times polarized objective lens.

[0081] Furthermore, the computing device 100 can adjust the polarizer of the microscope to generate polarized light in two directions at 0° and 90° respectively, and can measure the maximum reflectivity and minimum reflectivity of the test area of ​​the target coated fuel particles under the two polarized lights through a microphotometer, obtain the maximum reflectivity and the minimum reflectivity from the microphotometer, and use the maximum reflectivity and the minimum reflectivity as the optical anisotropy A1 of the dense pyrolytic carbon layer of the target coated fuel particles.

[0082] In addition, the optical anisotropy A1 of the dense pyrolytic carbon layer can be compared with the standard optical anisotropy A of the standard substance with known reflectivity under the above two polarized lights to determine the optical anisotropy factor of the dense pyrolytic carbon layer. Specifically, the optical anisotropy factor can be determined by the following formula: OPTAF=A1 / A. Among them, A1 represents the optical anisotropy of the dense pyrolytic carbon layer, and A represents the standard optical anisotropy of the standard substance. In this way, by comparing the optical anisotropy of the dense pyrolytic carbon layer with the standard optical anisotropy of the standard substance, the optical anisotropy test results can be corrected, and then interference factors such as environmental changes can be eliminated to ensure that the optical anisotropy test results are accurate and reliable.

[0083] Fig.10 Schematic diagram of a visualized metallographic map of a metallographic sample generated according to an embodiment of the present invention is shown. Fig.10 As shown, after performing optical anisotropy detection on each target coated fuel particle in the metallographic sample, the optical anisotropy detection data of the target coated fuel particle (including the optical anisotropy degree and optical anisotropy factor of the dense pyrolytic carbon layer of the target coated fuel particle) can be recorded, and a visual metallographic map of the metallographic sample can be generated based on the optical anisotropy detection data of all target coated fuel particles in the metallographic sample, so as to trace each target coated fuel particle based on the visual metallographic map.

[0084] Fig.11 A schematic structural diagram of a particle intelligent positioning model 1100 provided according to an embodiment of the present invention is shown. Fig.12 A schematic diagram of an intelligent particle positioning model provided according to an embodiment of the present invention is shown.

[0085] like Fig.11 and Fig.12 As shown, the particle intelligent positioning model 1100 includes a feature extraction network (ie, a backbone network), an anchor box generation network, a suggestion generation network, and a fully connected network coupled in sequence.

[0086] Among them, the feature extraction network is used to extract features from the metallographic cross-section image of the first field of view to obtain a feature image. The anchor frame generation network is used to generate sparse anchor frames based on the feature image. The suggestion generation network is used to determine the candidate suggestion area based on the feature image and the anchor frame. The fully connected network is used to classify and refine the coordinates of the candidate suggestion area to determine the image position information of multiple coated fuel particles (complete coated fuel particles), and at the same time, one or more incomplete coated fuel particles can be eliminated, and then, the positioning mark image corresponding to the metallographic cross-section image of the first field of view can be output.

[0087] That is, in step 220, the computing device 100 uses the particle intelligent positioning model 1100 to determine the specific process of the image position information of multiple coated fuel particles contained in each first field of view metallographic cross-sectional image as follows: the first field of view metallographic cross-sectional image is input into the particle intelligent positioning model, and the first field of view metallographic cross-sectional image is firstly subjected to feature extraction through the feature extraction network to obtain a feature image. The feature image output by the feature extraction network is used as the input of the anchor frame generation network, and the anchor frame generation network can generate a sparse anchor frame based on the feature image. The feature image and the anchor frame can be used as the input of the suggestion generation network, and the suggestion generation network can determine the candidate suggestion area based on the feature image and the anchor frame. The candidate suggestion area can be used as the input of the fully connected network, and the fully connected network can classify and refine the coordinates of the candidate suggestion area (using a classifier and a position regression network) to determine the image position information (positioning marks) of multiple coated fuel particles, and at the same time, one or more incomplete coated fuel particles can be eliminated, and then, the positioning mark image corresponding to the first field of view metallographic cross-sectional image can be output.

[0088] It can be seen that the particle intelligent positioning model in the embodiment of the present invention can realize accurate intelligent positioning of coated fuel particles and precise removal of some incomplete particles.

[0089] Fig.13 FIG. 1 shows a schematic diagram of the structure of a semantic segmentation model 1300 provided according to an embodiment of the present invention. Fig.13 As shown, the semantic segmentation model 1300 includes a feature extraction module, a context fusion module and a boundary refinement module coupled in sequence.

[0090] The second field of view metallographic cross-section image of the coated fuel particles is input into the semantic segmentation model 1300, and the second field of view metallographic cross-section image is subjected to region segmentation processing by the semantic segmentation model 1300 (feature extraction module, context fusion module, boundary refinement module), so as to obtain a coating boundary image corresponding to the second field of view metallographic cross-section image. Figure 7 As shown, the coating definition image includes multiple segmented coatings (corresponding to the core of the coated fuel particle and each coating layer respectively).

[0091] It should be noted that the present invention stacks the convolutional layers in the channel direction and designs a context fusion module in combination with a residual structure to achieve multi-scale feature extraction and deep fusion of local image information. On this basis, a weight map considering the coated fuel particle data set is introduced, and the context fusion module and the boundary refinement module are integrated together to achieve the step-by-step refinement and segmentation of the coated fuel particle image. In this way, the semantic segmentation model of the present invention can achieve the refinement and segmentation of the coated fuel particle image (the second field of view metallographic cross-section image), and accurately extract the boundary contours of the core of the coated fuel particle and each coating layer.

[0092] Fig.14 A schematic diagram of tangency analysis of coated fuel particles according to an embodiment of the present invention is shown.

[0093] like Fig.14 As shown, in some embodiments, when the coated fuel particles are subjected to tangency analysis based on the coating definition image, the following method can be used to determine the tangent distance between the coated fuel particles (i.e., the coated fuel particles to be tested) and their adjacent coated fuel particles: First, on the metallographic sample, with the center of gravity of the coated fuel particles to be tested as the center, multiple adjacent coated fuel particles of the coated fuel particles to be tested are searched from the top with a radius of 1.38mm. Subsequently, from the multiple adjacent coated fuel particles, the three adjacent coated fuel particles closest to the coated fuel particles to be tested and the angle between each adjacent coated fuel particle and the coated fuel particles to be tested are determined and recorded. Then, on the coating definition image, three rays are emitted based on the above-mentioned center and the three recorded angles, and the intersection of each ray and the outermost layer of each coated fuel particle is determined. Wherein, each ray forms two adjacent intersections with the outermost layer of the coated fuel particles to be tested and the adjacent coated fuel particles, and the shortest distance between the two adjacent intersections can be determined as the tangent distance between the coated fuel particles to be tested and their adjacent coated fuel particles. Finally, the angles recorded above can be slightly changed and traversed in the form of small angle changes to obtain different intersection points, ensuring that the tangent distance is the shortest distance between the two arcs of the outer edges of adjacent particles.

[0094] Furthermore, the minimum tangent distance can be used to determine whether the cross section (processed surface) of the coated fuel particle to be measured is close to its equatorial plane, thereby ensuring the reliability of the measurement result. If it is close to the equatorial plane, it can be determined that the coated fuel particle to be measured meets the tangency requirement, and the coated fuel particle to be measured is used as the target coated fuel particle that meets the anisotropy measurement condition.

[0095] Fig.15 A schematic diagram of a coated fuel particle optical anisotropy detection device 1500 provided according to an embodiment of the present invention is shown. The coated fuel particle optical anisotropy detection device 1500 can be deployed in the computing device 100, and the coated fuel particle optical anisotropy detection device 1500 is configured to execute the coated fuel particle optical anisotropy detection method 200 of the present invention.

[0096] In an embodiment of the present invention, the computing device 100 is communicatively connected to a microscope, and a metallographic sample having a plurality of coated fuel particles can be placed on the motorized stage of the microscope.

[0097] like Fig.15As shown, in an embodiment of the present invention, the optical anisotropy detection device 1500 for coated fuel particles includes a first acquisition unit 1510, a determination unit 1520, a splicing unit 1530, a second acquisition unit 1540, an analysis unit 1550, an extraction unit 1560 and a measurement unit 1570 which are sequentially communicatively connected.

[0098] The first acquisition unit 1510 is used to control the microscope to traverse and acquire a plurality of first field of view metallographic cross-section images covering the entire metallographic sample.

[0099] The determination unit 1520 is used to determine the image position information of the plurality of coated fuel particles contained in each first field of view metallographic cross-sectional image.

[0100] The stitching unit 1530 is used to perform coordinate stitching on the image position information of all coated fuel particles contained in the multiple first field of view metallographic cross-sectional images to obtain a global coordinate map covering all coated fuel particles in the metallographic sample.

[0101] The second acquisition unit 1540 is used to control the microscope to acquire the second field of view metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one based on the global coordinate map.

[0102] The analysis unit 1550 is used to perform coating definition on the second field of view metallographic cross-sectional image of each coated fuel particle using a semantic segmentation model to obtain a corresponding coating definition image, and perform measurability analysis on the coated fuel particle based on the coating definition image to screen out multiple target coated fuel particles that meet the anisotropy measurement conditions.

[0103] The extraction unit 1560 is used to extract the dense pyrolytic carbon layer area from the second field of view metallographic cross-section image of the target coated fuel particle based on the corresponding layer definition image for each target coated fuel particle, and select the area to be tested from the dense pyrolytic carbon layer area.

[0104] The measuring unit 1570 is used to measure the reflectivity of the measured area to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particles.

[0105] It should be noted that the first acquisition unit 1510, the determination unit 1520, the splicing unit 1530, the second acquisition unit 1540, the analysis unit 1550, the extraction unit 1560, and the measurement unit 1570 are respectively used to execute the aforementioned steps 210 to 270. Here, the specific execution logic of each unit can be found in the description of steps 210 to 270 in the method 200 above, which will not be repeated here.

[0106] According to the optical anisotropy detection method 200 of coated fuel particles in the embodiment of the present invention, the computing device first controls the microscope to traverse and collect multiple first-field metallographic cross-sectional images covering the entire metallographic sample, determines the image position information of multiple coated fuel particles contained in each first-field metallographic cross-sectional image, and coordinates the image position information of all coated fuel particles to obtain a global coordinate map covering all coated fuel particles in the metallographic sample. Then, based on the global coordinate map, the microscope can be controlled to collect the second-field metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one, and the second-field metallographic cross-sectional image is segmented to perform measurability analysis on the coated fuel particles. After that, the area to be tested is selected from the dense pyrolytic carbon layer area of ​​each target coated fuel particle that meets the anisotropy measurement condition. Finally, the reflectivity is measured for the area to be tested to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle. Based on this, the present invention can realize the automation and intelligence of the optical anisotropy detection process of the dense pyrolytic carbon layer of the coated fuel particle, the detection process is more efficient, and the detection accuracy and consistency of the detection results are improved. Among them, it realizes the automatic acquisition of high-quality images of multiple fields of view of each coated fuel particle; it can intelligently locate the coated fuel particles, intelligently analyze and screen the target coated fuel particles that meet the anisotropy measurement conditions, and intelligently screen the test area for optical anisotropy detection, and then realize the accurate measurement of the optical anisotropy of the coated fuel particles based on the test area.

[0107] In addition, by comparing the optical anisotropy of the dense pyrolytic carbon layer with the standard optical anisotropy of the standard substance, the optical anisotropy test results can be corrected, and then interfering factors such as environmental changes can be eliminated to ensure that the optical anisotropy test results are accurate and reliable.

[0108] In addition, an embodiment of the present invention also discloses: A9, a method as described in any one of A1-A8, wherein a measurability analysis is performed on the coated fuel particles based on the coating definition image, comprising: performing an integrity analysis on the coated fuel particles based on the coating definition image to determine whether the coated fuel particles are intact; if it is determined that the coated fuel particles are intact, determining the tangent distance between the coated fuel particles and their adjacent coated fuel particles based on the coating definition image, and determining whether the cross-section of the coated fuel particles is close to the equatorial plane based on the tangent distance; if it is close to the equatorial plane, determining that the coated fuel particles meet the tangency requirements, and using the coated fuel particles as target coated fuel particles that meet the anisotropy measurement conditions. A10. A method as described in any one of A1-A9, wherein controlling the microscope to traverse and collect multiple first-field metallographic cross-sectional images covering the entire metallographic sample comprises: controlling the microscope to use a first-magnification objective lens to traverse and collect multiple first-field metallographic cross-sectional images covering the entire metallographic sample; controlling the microscope to collect the second-field metallographic cross-sectional images of each coated fuel particle in the metallographic sample one by one, comprising: controlling the microscope to use a second-magnification objective lens to collect the second-field metallographic cross-sectional images of each coated fuel particle in the metallographic sample one by one. B13. A computer program product, comprising a computer program / instruction, wherein the computer program / instruction implements the method as described in any one of A1-A10 when executed by a processor. C14. A readable storage medium storing program instructions, which, when the program instructions are read and processed by a computing device, enables the computing device to process the method as described in any one of A1-A10.

[0109] The various techniques described herein may be implemented in combination with hardware or software, or a combination thereof. Thus, the method and apparatus of the present invention, or some aspects or parts of the method and apparatus of the present invention may be in the form of program codes (i.e., instructions) embedded in a tangible medium, such as a removable hard disk, a USB flash drive, a floppy disk, a CD-ROM, or any other machine-readable storage medium, wherein when the program is loaded into a machine such as a computer and executed by the machine, the machine becomes a device for practicing the present invention.

[0110] In the case where the program code is executed on a programmable computer, the mobile terminal generally includes a processor, a storage medium readable by the processor (including volatile and non-volatile memory and / or storage element), at least one input device, and at least one output device. The memory is configured to store the program code; the processor is configured to execute the optical anisotropy detection method of coated fuel particles of the present invention according to the instructions in the program code stored in the memory.

[0111] By way of example and not limitation, readable media include readable storage media and communication media. Readable storage media stores information such as computer readable instructions, data structures, program modules or other data. Communication media generally embody computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and include any information transfer medium. Any combination of the above is also included within the scope of readable media.

[0112] In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the examples of the present invention. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to implement the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0113] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0114] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof.

[0115] Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

[0116] Unless otherwise specified, the use of ordinal numbers "first", "second", "third", etc. to describe common objects merely indicates that different instances of similar objects are involved and is not intended to imply that the objects so described must have a given order in time, space, order or in any other manner.

Claims

1. A method for detecting optical anisotropy of coated fuel particles, executed in a computing device, the computing device being communicatively connected to a microscope, the motorized stage of the microscope being adapted to place a metallographic sample having a plurality of coated fuel particles, the method comprising: Controlling the microscope to traverse and collect a plurality of first-field-of-view metallographic cross-section images covering the entire metallographic sample; Determining image position information of a plurality of coated fuel particles contained in each of the first field of view metallographic cross-sectional images; Coordinate stitching is performed on the image position information of all coated fuel particles contained in the plurality of first field of view metallographic cross-sectional images to obtain a global coordinate map covering all coated fuel particles in the metallographic sample; Based on the global coordinate map, controlling the microscope to collect the second field of view metallographic cross-section image of each coated fuel particle in the metallographic sample one by one; For each of the coated fuel particles, a semantic segmentation model is used to perform coating definition on the second field of view metallographic cross-sectional image of the coated fuel particle to obtain a corresponding coating definition image, and a measurability analysis is performed on the coated fuel particles based on the coating definition image to screen out a plurality of target coated fuel particles that meet anisotropy measurement conditions; For each of the target coated fuel particles, extracting a dense pyrolytic carbon layer region from the second field of view metallographic cross-sectional image of the target coated fuel particle based on the corresponding layer definition image, and selecting a region to be measured from the dense pyrolytic carbon layer region; The reflectivity of the area to be measured is measured to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle.

2. The method of claim 1, wherein: Selecting a region to be tested from the dense pyrolytic carbon layer region includes: Determining a first black spot ratio in the dense pyrolytic carbon layer region, and judging whether the black spot is an essential attribute of the dense pyrolytic carbon layer region based on the first black spot ratio; Extracting a plurality of reflectivity measurement areas from the dense pyrolytic carbon layer region, and determining the proportion of the second black spots in each of the reflectivity measurement areas; If the black spots are the essential properties of the dense pyrolytic carbon layer area, then selecting the reflectivity measurement area with the largest second black proportion from the multiple reflectivity measurement areas as the area to be measured; If the black spots are not an essential attribute of the dense pyrolytic carbon layer area, then the reflectivity measurement area with the second smallest black proportion is selected from the multiple reflectivity measurement areas as the area to be measured.

3. The method of claim 2, wherein: Extracting a plurality of reflectivity measurement areas from the dense pyrolytic carbon layer region includes: On the coating definition image of the target coated fuel particle, a target coordinate system is established with the core mass center of the target coated fuel particle as the target origin; Two measurement lines are drawn along the X-axis and Y-axis directions of the target coordinate system, and multiple areas of predetermined sizes are respectively extracted from multiple intersections of the two measurement lines and the dense pyrolytic carbon layer area as multiple reflectivity measurement areas.

4. The method according to any one of claims 1 to 3, wherein: Measuring the reflectivity of the area to be measured to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle includes: Controlling the electric stage of the microscope to drive the metallographic sample to move so that the center of the target coated fuel particle to be tested is located at the center of the collection area of ​​the microscope; Controlling the microscope to switch to a third-power polarizing objective lens, and adjusting the field diaphragm to a minimum, so that the microscope automatically focuses until the field diaphragm border is clear; The polarizer of the microscope is adjusted to generate polarized light in two directions at 0° and 90° respectively, and the maximum reflectivity and minimum reflectivity of the test area under the two polarized lights are measured by a microphotometer as the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particles.

5. The method of claim 4, wherein: Determining the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle also includes: The optical anisotropy of the dense pyrolytic carbon layer is compared with the standard optical anisotropy of a standard material with known reflectivity under the two polarized lights to determine the optical anisotropy factor of the dense pyrolytic carbon layer.

6. The method according to any one of claims 1 to 5, wherein: Controlling the microscope to traverse and collect a plurality of first-field metallographic cross-sectional images covering the entire metallographic sample, including: Acquire a first-field metallographic cross-sectional image of the central area of ​​the metallographic sample collected by the microscope, take the core mass center of any coated fuel particle in the first-field metallographic cross-sectional image as the absolute origin, and establish an absolute coordinate system of the metallographic sample; Determine a traversal acquisition path covering the entire metallographic sample based on the absolute coordinate system; The microscope is controlled to take the absolute origin as a starting point, and based on the traversal acquisition path, a plurality of first field of view metallographic cross-section images covering the entire metallographic sample are traversed and acquired.

7. The method according to any one of claims 1 to 6, wherein: Based on the global coordinate map, controlling the microscope to collect the second field of view metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one, including: Based on the global coordinate map and the traversal acquisition path, path planning is performed for each coated fuel particle in each first field of view metallographic cross-section image to determine a global acquisition path; Based on the global acquisition path, the microscope is controlled to acquire the second field of view metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one.

8. The method according to any one of claims 1 to 7, wherein: Determining image position information of a plurality of coated fuel particles contained in each of the first field of view metallographic cross-sectional images comprises: Determine the image position information of a plurality of coated fuel particles contained in each of the first field of view metallographic cross-sectional images by using a particle intelligent positioning model, wherein the particle intelligent positioning model comprises a feature extraction network, an anchor frame generation network, a suggestion generation network, and a fully connected network coupled in sequence; Wherein, the feature extraction network is used to extract features from the first field of view metallographic cross-section image to obtain a feature image; The anchor frame generation network is used to generate an anchor frame based on the feature image; The proposal generation network is used to determine a candidate proposal region based on the feature image and the anchor box; The fully connected network is used to classify and refine the coordinates of the candidate suggested regions to determine the image position information of multiple coated fuel particles, eliminate one or more incomplete coated fuel particles, and output a positioning mark image corresponding to the first field of view metallographic section image.

9. A device for detecting optical anisotropy of coated fuel particles, deployed in a computing device, the computing device being communicatively connected to a microscope, the motorized stage of the microscope being suitable for placing a metallographic sample having a plurality of coated fuel particles, the device comprising: A first acquisition unit, adapted to control the microscope to traverse and acquire a plurality of first field of view metallographic cross-section images covering the entire metallographic sample; a determination unit, adapted to determine image position information of a plurality of coated fuel particles contained in each of the first field of view metallographic cross-sectional images; a stitching unit adapted to stitch the image position information of all coated fuel particles contained in the plurality of first field of view metallographic cross-sectional images to obtain a global coordinate map covering all coated fuel particles in the metallographic sample; A second acquisition unit, adapted to control the microscope to acquire a second field of view metallographic cross-sectional image of each coated fuel particle in the metallographic sample one by one based on the global coordinate map; an analysis unit adapted to perform coating definition on the second field of view metallographic cross-sectional image of each coated fuel particle using a semantic segmentation model to obtain a corresponding coating definition image, and perform measurability analysis on the coated fuel particle based on the coating definition image to screen out a plurality of target coated fuel particles that meet anisotropy measurement conditions; An extraction unit, adapted to extract, for each of the target coated fuel particles, a dense pyrolytic carbon layer region from the second field of view metallographic cross-sectional image of the target coated fuel particle based on the corresponding layer definition image, and select a region to be measured from the dense pyrolytic carbon layer region; The measuring unit is adapted to measure the reflectivity of the area to be measured so as to determine the optical anisotropy of the dense pyrolytic carbon layer of the target coated fuel particle.

10. A computing device comprising: at least one processor; and A memory storing program instructions, wherein the program instructions are configured to be processed by the at least one processor, and the program instructions include instructions for processing the method according to any one of claims 1 to 8.

Images