Method and device for detecting element distribution uniformity of MgO-based dispersion type nuclear fuel pellet

Abstract

The invention discloses a method and a device for detecting distribution uniformity of elements of an MgO-based dispersion type nuclear fuel pellet, relates to the field of transmutation fuel preparation technology and analysis, and mainly aims to improve the detection efficiency and the detection precision of the distribution uniformity of the elements of the dispersion type nuclear fuel pellet. Comprising the following steps: irradiating an alpha imaging bottom plate by using alpha rays generated by spontaneous decay of fuel particles in a nuclear fuel pellet to be detected, and obtaining a bottom plate image corresponding to the irradiated alpha imaging bottom plate; a plurality of tracks generated by irradiation of the fuel particles are recognized in the base plate image, track attribute information of each track and inter-track attribute information between the tracks are determined, and each track is a microscopic damage trace left after interaction of the alpha ray and the alpha imaging base plate; and based on the track attribute information and the inter-track attribute information, determining the distribution uniformity of the fuel particles in the nuclear fuel pellet to be detected.

Description

Technical Field

[0001] The present invention relates to the field of transmutation fuel preparation technology and analysis, and in particular to a method and device for detecting the uniformity of element distribution of MgO-based dispersed nuclear fuel pellets. Background Art

[0002] Currently, ceramic nuclear fuel is the most widely used of the many types of nuclear fuel due to its high melting point and strong radiation resistance. However, ceramic nuclear fuel suffers from low thermal conductivity, which can lead to excessively high temperatures inside the fuel pellets in the reactor, increasing the risk of core meltdown. MgO-based dispersed nuclear fuel, a type of nuclear fuel made by dispersing nuclear fuel particles within a MgO (magnesium oxide) matrix, improves thermal conductivity while mitigating the effects of fission fragments, pellet swelling, and fission gas on the fuel. This makes it more suitable for use as a nuclear fuel for transmutation of minor actinides in fast reactors and accelerator-driven subcritical systems. Therefore, the preparation and performance analysis of this type of nuclear fuel are currently hot topics in advanced nuclear fuel research. MgO-based dispersed nuclear fuel is a heterogeneous nuclear fuel. Its traditional preparation involves first preparing nuclear fuel particles, then mechanically mixing them with a non-radioactive inert dispersion medium and pressing them into fuel pellets. The final product is then sintered at high temperature. However, due to the significant differences in density and particle size between the nuclear fuel particles and the dispersion medium, mechanical mixing is difficult to achieve uniform mixing, inevitably leading to agglomeration of the nuclear fuel particles within the pellet. In dispersed nuclear fuel pellets, each nuclear fuel particle represents a heat source, and uneven distribution of nuclear fuel particles can lead to numerous issues with the thermal performance, neutron flux density distribution, and mechanical strength of the fuel pellet. The uniformity of nuclear fuel particle distribution within the pellet is a key parameter for dispersed nuclear fuel, making testing this uniformity crucial.

[0003] Currently, the process for testing the uniformity of elemental distribution in MgO-based dispersed nuclear fuel pellets involves cutting the pellets into thin slices, irradiating the slices with high-energy X-rays generated by an X-ray tube, and then detecting the energy released by the slices with a detector. The energy value is then used to determine the uniformity of elemental distribution. However, this method requires pre-slicing the nuclear fuel pellets, which is time-consuming and labor-intensive. Mechanical damage during the cutting process, oxidation, or contamination of the slice surface can affect the energy released by the slices, thereby interfering with the accurate determination of elemental uniformity. Furthermore, this method requires multiple devices, including X-ray tubes and detectors, resulting in high costs. The more equipment required, the greater the detection error. Summary of the Invention

[0004] The present invention provides a method and device for detecting uniformity of element distribution of MgO-based dispersed nuclear fuel pellets, which are mainly capable of improving the detection efficiency and detection accuracy of uniformity of element distribution of dispersed nuclear fuel pellets.

[0005] According to a first aspect of the present invention, there is provided a method for detecting element distribution uniformity of MgO-based dispersed nuclear fuel pellets, comprising:

[0006] irradiating an α imaging base plate using α rays generated by spontaneous decay of fuel particles in a nuclear fuel pellet to be detected, and acquiring a base plate image corresponding to the α imaging base plate after irradiation;

[0007] identifying a plurality of tracks generated by the irradiation of the fuel particles in the base plate image, and determining track attribute information of each track and inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction of the alpha ray with the alpha imaging base plate;

[0008] Based on the track attribute information and the inter-track attribute information, the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected is determined.

[0009] Optionally, obtaining a baseplate image corresponding to the irradiated α imaging baseplate includes:

[0010] Determining an etching liquid, and obtaining liquid property information of the etching liquid and base plate property information of the alpha imaging base plate;

[0011] Determining an etching time based on the liquid property information and the base plate property information, and based on the etching time, inserting the irradiated α imaging base plate into the etching liquid for etching to obtain the etched α imaging base plate;

[0012] The preset camera device is connected to the preset microscope. When the etched α imaging base plate is observed using the preset microscope, the preset camera device is controlled to shoot the observation results of the preset microscope to obtain a base plate image corresponding to the etched α imaging base plate.

[0013] Optionally, identifying a plurality of tracks generated by the irradiation of the fuel particles in the base plate image comprises:

[0014] Obtaining a target detection model, wherein the target detection model includes a backbone network for extracting image features, a neck network for fusing image features, and a head network for detecting targets, wherein the backbone network includes multiple feature extraction layers;

[0015] The base plate image is input into the target detection model, and image features of the base plate image are extracted through the backbone network to obtain image features corresponding to each feature extraction layer. Multiple image features are fused through the neck network to obtain fused features. Tracks are identified on the fused features through the head network to obtain multiple tracks in the base plate image.

[0016] Optionally, the track attribute information includes geometric dimension information of each track, and the inter-track attribute information includes the track spacing between every two tracks;

[0017] Determining the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected based on the track attribute information and the inter-track attribute information includes:

[0018] Determining track geometry evaluation information of the fuel particles based on the geometric size information, and determining track spacing evaluation information of the fuel particles based on the track spacing, wherein the track geometry evaluation information includes a track geometric size mean, a track geometric size variance, and a track geometric size standard deviation, and the track spacing evaluation information includes a track spacing mean, a track spacing variance, and a track spacing standard deviation;

[0019] determining a track geometry score of the fuel particles based on the track geometry evaluation information, and determining a track spacing score of the fuel particles based on the track spacing evaluation information;

[0020] The track geometry score and the track spacing score are weightedly fused to obtain a track comprehensive score, and the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected is determined based on the track comprehensive score.

[0021] Optionally, determining the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected based on the track attribute information and the inter-track attribute information includes:

[0022] Determining a track feature vector corresponding to the track attribute information and an inter-track feature vector corresponding to the inter-track attribute information;

[0023] Performing cross processing on the track feature vector and the inter-track feature vector to obtain a track cross feature vector;

[0024] The track intersection feature vector is input into a preset distribution detection model for distribution detection to obtain the distribution uniformity of the fuel particles in the nuclear fuel pellet to be detected, wherein the preset distribution detection model is pre-constructed based on a sample data set with a distribution uniformity label.

[0025] Optionally, performing cross processing on the track feature vector and the inter-track feature vector to obtain a track cross feature vector includes:

[0026] Performing feature-level cross processing on the track feature vector and the inter-track feature vector to obtain a feature cross vector;

[0027] Performing element-level cross processing on the track feature vector and the inter-track feature vector to obtain an element cross vector;

[0028] Performing low-order cross processing on the track feature vector and the inter-track feature vector to obtain a low-order cross vector;

[0029] The characteristic cross vector, the element cross vector, and the low-order cross vector are transformed using a preset transformation function to obtain the track cross characteristic vector.

[0030] Optionally, before identifying the plurality of tracks generated by the irradiation of the fuel particles in the base plate image, the method further comprises:

[0031] Performing image quality enhancement processing on the baseplate image to obtain an enhanced baseplate image;

[0032] A plurality of tracks resulting from the irradiation of the fuel particles are identified in the base plate image, including:

[0033] A plurality of tracks resulting from the irradiation of the fuel particles are identified in the enhanced floor image.

[0034] According to a second aspect of the present invention, there is provided a device for detecting element distribution uniformity of MgO-based dispersed nuclear fuel pellets, comprising:

[0035] an irradiation unit, configured to irradiate an α imaging base plate using α rays generated by spontaneous decay of fuel particles in the nuclear fuel pellets to be detected, and to obtain a base plate image corresponding to the α imaging base plate after irradiation;

[0036] an identification unit, configured to identify a plurality of tracks generated by the irradiation of the fuel particles in the base plate image, and determine track attribute information of each track and inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction between the α-rays and the α-imaging base plate;

[0037] A determination unit is configured to determine the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected based on the track attribute information and the inter-track attribute information.

[0038] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above method for detecting element distribution uniformity of MgO-based dispersed nuclear fuel pellets.

[0039] According to a fourth aspect of the present invention, there is provided a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for detecting the uniformity of element distribution of MgO-based dispersed nuclear fuel pellets is implemented.

[0040] According to a method and device for detecting the uniformity of element distribution of MgO-based dispersed nuclear fuel pellets provided by the present invention, compared with the current manual method of detecting the uniformity of element distribution of dispersed nuclear fuel pellets, the present invention irradiates an imaging base plate by using rays generated by the spontaneous decay of fuel particles in the nuclear fuel pellets to be detected, and obtains a base plate image corresponding to the irradiated imaging base plate; and identifies multiple tracks generated by the irradiation of the fuel particles in the base plate image, and determines the track attribute information of each track and the inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction between the rays and the imaging base plate; finally, based on the track attribute information and the inter-track attribute information, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be detected is determined. Therefore, by analyzing the track properties formed by the α-ray irradiation imaging base plate, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be tested can be determined, without the need to slice the pellets, which can improve the detection efficiency of the element distribution uniformity in the nuclear fuel pellets. At the same time, the detection can be completed by the ray irradiation imaging base plate, without causing any damage to the pellets themselves, realizing non-destructive testing, and does not require too many instruments and equipment, reducing the detection cost. At the same time, the ray irradiation imaging base plate method will not be interfered with by factors such as the external environment, thereby ensuring the detection accuracy of the uniform distribution of fuel particles in the nuclear fuel pellets. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0042] Figure 1 A flow chart of a method for detecting element distribution uniformity of MgO-based dispersed nuclear fuel pellets provided by an embodiment of the present invention is shown;

[0043] Figure 2 A flow chart of another method for detecting element distribution uniformity of MgO-based dispersed nuclear fuel pellets provided by an embodiment of the present invention is shown;

[0044] Figure 3 A schematic diagram showing a process for detecting uniformity of element distribution of a MgO-based dispersed nuclear fuel pellet provided by an embodiment of the present invention is shown;

[0045] Figure 4 A schematic structural diagram of a device for detecting element distribution uniformity of MgO-based dispersed nuclear fuel pellets provided by an embodiment of the present invention is shown;

[0046] Figure 5 A schematic structural diagram of another MgO-based dispersed nuclear fuel pellet element distribution uniformity detection device provided by an embodiment of the present invention is shown;

[0047] Figure 6 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0048] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0049] Currently, the core block is cut into thin slices, and the slices are irradiated with high-energy X-rays generated by an X-ray tube. The energy released by the slices is then detected by a detector, and the uniformity of element distribution is judged based on the energy value. This method is time-consuming and labor-intensive. Mechanical damage during the cutting process, oxidation or contamination of the slice surface, and other factors can affect the energy release of the slice, thereby interfering with the accurate judgment of the uniformity of element distribution. This method also requires multiple equipment such as X-ray tubes and detectors, which is costly. The more equipment is used, the greater the detection error.

[0050] In order to solve the above problems, the embodiment of the present invention provides a method for detecting the uniformity of element distribution of MgO-based dispersed nuclear fuel pellets, such as Figure 1 As shown, the method includes:

[0051] 101. Use alpha rays generated by spontaneous decay of fuel particles in the nuclear fuel pellets to be detected to irradiate the alpha imaging base plate, and obtain a base plate image corresponding to the irradiated alpha imaging base plate.

[0052] Among them, the nuclear fuel pellets to be detected can be dispersed nuclear fuel pellets, such as metal-metal dispersed nuclear fuel, ceramic-metal dispersed nuclear fuel, ceramic-ceramic dispersed nuclear fuel, etc.; the fuel particles are tiny fuel crystals in the nuclear fuel pellets to be detected; the α imaging base plate can be a carbon acrylate plastic base plate, a nuclear latex base plate, a polycarbonate plastic base plate, etc.

[0053] In an embodiment of the present invention, the surface of the nuclear fuel pellet to be inspected is wiped clean with a detergent, and the clean surface of the nuclear fuel pellet to be inspected is placed close to the α imaging base plate for a few seconds. During this process, certain uranium isotopes in the fuel particles will spontaneously undergo α decay, generating α particles. When the α particles (α rays) pass through the imaging base plate, they will interact with the base plate material, causing microscopic damage, thereby forming tracks. The irradiated α imaging base plate is placed in a heated etching solution for a period of time, taken out and cleaned, and the etched base plate is placed under a microscope for observation and photographed to obtain a base plate image. The embodiment of the present invention can complete the inspection by irradiating the imaging base plate with rays, without causing any damage to the pellet itself, achieving non-destructive inspection and reducing inspection costs. At the same time, the embodiment of the present invention observes and photographs the base plate through a microscope, avoiding direct contact between the microscope and the nuclear fuel, thereby avoiding damage to the microscope and other equipment caused by the nuclear fuel.

[0054] 102. Identify multiple tracks produced by fuel particle irradiation in the baseplate image, and determine track attribute information of each track and inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction of alpha rays with the alpha imaging baseplate.

[0055] Among them, track attribute information refers to track geometric attribute information, including track length, track area, track diameter and other information; inter-track attribute information refers to the distance between each two tracks.

[0056] In an embodiment of the present invention, a deep learning target detection method is used to detect each track in the base plate image, and the position information of each point in each track in the base plate image is determined. Based on the position information of each track, the distance between each two tracks is determined. At the same time, based on the position information of each point in each track, the geometric information such as the length, area and diameter of each track can also be determined.

[0057] 103. Based on the track attribute information and the inter-track attribute information, determine the distribution uniformity of the fuel particles in the nuclear fuel pellet to be tested.

[0058] For the embodiment of the present invention, when determining the track attribute information and the inter-track attribute information, it is necessary to analyze the distribution uniformity of the fuel particles in the nuclear fuel pellets to be detected based on the above information. Based on this, step 103 specifically includes: determining the track feature vector corresponding to the track attribute information and the inter-track feature vector corresponding to the inter-track attribute information; performing cross-processing on the track feature vector and the inter-track feature vector to obtain a track cross-feature vector; inputting the track cross-feature vector into a preset distribution detection model for distribution detection to obtain the distribution uniformity of the fuel particles in the nuclear fuel pellets to be detected, wherein the preset distribution detection model is pre-constructed based on a sample data set with a distribution uniformity label. Among them, the method for cross-processing the track feature vector and the inter-track feature vector includes: performing feature-level cross-processing on the track feature vector and the inter-track feature vector to obtain a feature cross-vector; performing element-level cross-processing on the track feature vector and the inter-track feature vector to obtain an element cross-vector; performing low-order cross-processing on the track feature vector and the inter-track feature vector to obtain a low-order cross-vector; and using a preset transformation function to transform the feature cross-vector, the element cross-vector, and the low-order cross-vector to obtain the track cross-feature vector.

[0059] Specifically, to improve the detection accuracy of a preset distribution detection model, it is first necessary to train and construct the preset distribution detection model. Based on this, the method includes: constructing a preset initial distribution detection model; obtaining a sample dataset, wherein the sample dataset includes track attribute information and inter-track attribute information of tracks in a sample baseplate image with distribution uniformity labels. The sample baseplate image is obtained by irradiating an alpha imaging baseplate with alpha rays generated by the spontaneous decay of fuel particles in a sample nuclear fuel pellet; dividing the sample dataset into training data and testing data, using the training data to train the preset initial distribution detection model, and testing the trained preset initial distribution detection model using the testing data. The trained preset initial distribution detection model that meets the test conditions is used as the preset distribution detection model. Specifically, download the sample dataset from an official website or a designated data source. Ensure that the sample dataset contains all necessary files. Convert the annotation file into a format that the model can understand (typically a txt file with annotation information for one sample per line). Finally, train and test the model. Specifically, the dataset can be divided into training data and testing data using random or specific strategies (such as stratified sampling). Retrain the model using the training data, monitoring metrics such as loss and mean average prediction accuracy (mAP) during training to evaluate model performance. Adjust training parameters such as the learning rate, optimizer, and regularization as needed to optimize training results. Finally, test the model: Use the test data to test the trained model and evaluate its performance on unseen data. Calculate and record metrics such as mAP, precision, and recall on the test data. If model performance does not meet expectations, return to the training phase for more iterations or adjustments.

[0060] Furthermore, word embedding and other methods are used to determine the track feature vector corresponding to the track attribute information and the inter-track feature vector corresponding to the inter-track attribute information. In order to make full use of the relationship between the data, extract more implicit features, and take into account both high-order and low-order processing, so that the data can be used more fully, the subsequent prediction results can be more accurate, and meet the needs of actual application scenarios, it is necessary to cross-process the track feature vector and the inter-track feature vector. The specific cross-processing method is as follows: if the track feature vector is (a1, a2) and the inter-track feature vector is (b1, b2), the specific cross-processing method includes: performing feature-level cross-processing between different feature vectors, that is, after performing Hadamard product on all elements between the vectors, performing convolution transformation under a certain weight w1, and obtaining a feature cross vector of f(w*(a1*b1, a2*b2) ); at the same time, perform element-level crossover on all eigenvector data, that is, after performing Hadamard product on each element between vectors, assign different weight values ​​w2 and w3 to the result of each product, and then perform linear transformation, and the obtained element crossover vector is f(w2*a1*b1,w3*a2*b2); in addition, perform low-order crossover processing on all eigenvectors, and then assign weight coefficient w4 to the result after crossover processing, and then perform linear transformation, and the obtained low-order crossover vector is f(w4(a1,a2,b1,b2)); finally, the above eigenvectors, element crossover vectors, and low-order crossover vectors are transformed using a preset transformation function to obtain a track crossover eigenvector. The preset transformation function here can be set according to actual conditions, and this embodiment does not limit this. It should be noted that the above examples are only illustrative and do not limit the embodiments of the present application. By cross-processing track feature vectors and inter-track feature vectors, different features can be automatically or explicitly combined to generate new feature combinations. These combined features may contain complex nonlinear relationships between the original features, allowing the model to capture more detailed and rich information in the data. In other words, it can fully utilize the relationships between various data to extract more implicit features, while taking into account both high-order and low-order processing, making data utilization more efficient and the subsequent prediction results more accurate, meeting the needs of practical application scenarios. Furthermore, the track cross-feature vectors are input into a preset distribution detection model, which can output the distribution uniformity of fuel particles in the nuclear fuel pellets to be tested.

[0061] According to a method for detecting the uniformity of element distribution of MgO-based dispersed nuclear fuel pellets provided by the present invention, compared with the current manual method of detecting the uniformity of element distribution of dispersed nuclear fuel pellets, the present invention irradiates an imaging base plate by using rays generated by the spontaneous decay of fuel particles in the nuclear fuel pellets to be detected, and obtains a base plate image corresponding to the irradiated imaging base plate; and identifies multiple tracks generated by the irradiation of the fuel particles in the base plate image, and determines the track attribute information of each track and the inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction between the rays and the imaging base plate; finally, based on the track attribute information and the inter-track attribute information, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be detected is determined. Therefore, by analyzing the track properties formed by the α-ray irradiation imaging base plate, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be tested can be determined without slicing the pellets, which can improve the detection efficiency of the element distribution uniformity in the nuclear fuel pellets. At the same time, the detection can be completed by irradiating the imaging base plate without causing any damage to the pellets themselves, realizing non-destructive detection, and does not require too many instruments and equipment, reducing the detection cost. At the same time, the irradiation imaging base plate method will not be interfered with by factors such as the external environment, thereby ensuring the detection accuracy of the uniform distribution of fuel particles in the nuclear fuel pellets.

[0062] Furthermore, in order to better illustrate the above detection process of the element distribution uniformity of the MgO-based dispersed nuclear fuel pellets, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another method for detecting the element distribution uniformity of the MgO-based dispersed nuclear fuel pellets, such as Figure 2 As shown, the method includes:

[0063] 201. Irradiate an α imaging base plate using α rays generated by spontaneous decay of fuel particles in a nuclear fuel pellet to be detected, and obtain a base plate image corresponding to the irradiated α imaging base plate.

[0064] like Figure 3The figure shows a process diagram for element uniformity detection according to an embodiment of the present invention. In order to enhance the clarity of radiation damage tracks in an α imaging substrate, the irradiated α imaging substrate needs to be etched. The method includes: determining an etching solution and obtaining liquid property information of the etching solution and substrate property information of the α imaging substrate; determining an etching time based on the liquid property information and the substrate property information; and, based on the etching time, inserting the irradiated α imaging substrate into the etching solution for etching to obtain the etched α imaging substrate; and connecting a preset camera device to a preset microscope. During observation of the etched α imaging substrate using the preset microscope, the preset camera device is controlled to capture the observation results of the preset microscope to obtain a substrate image corresponding to the etched α imaging substrate.

[0065] Among them, the liquid property information includes the composition, concentration, temperature, acidity and alkalinity of the etching liquid; the base plate property information includes the material type, radiation damage sensitivity, surface geometry, etc. of the α imaging base plate.

[0066] Specifically, a suitable etching solution is selected based on actual needs, and the etching time is reasonably determined based on the liquid property information and the substrate property information. For example, the etching solution and α imaging substrate with corresponding properties can be pre-fixed. Then, a relationship function between the etching time and the clarity of the radiation damage track is constructed through experimental methods, and the relationship function is optimized to maximize the track clarity. The optimal etching time is determined based on the optimization results. Furthermore, the α imaging substrate is immersed in the etching solution and etched within the etching time. The tracks of the etched substrate are observed under a microscope and photographed to obtain an image of the substrate with the radiation damage tracks. By etching the irradiated substrate, the embodiments of the present invention can increase the clarity of the tracks in the substrate, thereby improving the detection accuracy of the uniformity of element distribution in dispersed nuclear fuel pellets.

[0067] Furthermore, after obtaining the base plate image, it is necessary to enhance the quality of the base plate image. Based on this, the method includes: performing image quality enhancement processing on the base plate image to obtain the enhanced base plate image. The specific image quality enhancement method includes: inputting the base plate image into the large model for parameter prediction to obtain the quadratic parameter curve corresponding to the base plate image; determining each pixel value J(z i ); using the quadratic parameter curve to calculate each pixel value J(z i ) is remapped to obtain each mapped pixel value RE(J(z i )), where RE(J(z i ))=J(z i )+αJ(z i)(1-J(z i )), α is the curve parameter of the quadratic parametric curve, and each mapped pixel value RE(J(z i )) constitutes the enhanced base plate image.

[0068] Specifically, each pixel value in the baseplate image is substituted into the above-mentioned quadratic parameter curve to obtain the mapped pixel value corresponding to each pixel value, and finally the enhanced baseplate image is formed by each mapped pixel value. The embodiment of the present invention can change the dynamic range of the baseplate image by controlling the curve parameter α in the quadratic parameter curve. The embodiment of the present invention adjusts the dynamic range of the baseplate image through the quadratic parameter curve, which can realize automatic adjustment of the baseplate image and avoid the time-consuming and labor-intensive problem of manual adjustment, thereby improving the enhancement efficiency of the baseplate image; the parameter curve can accurately adjust the brightness, contrast and other parameters of the image, avoiding errors or subjective deviations that may occur during manual adjustment, thereby improving the enhancement accuracy of the baseplate image.

[0069] 202. Identify multiple tracks produced by fuel particle irradiation in the base plate image, and determine track attribute information of each track and inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction of α rays with the α imaging base plate, the track attribute information includes geometric size information of each track, and the inter-track attribute information includes the track spacing between every two tracks.

[0070] For the embodiment of the present invention, it is also necessary to identify multiple tracks generated by the fuel particles irradiating the imaging base plate in the enhanced base plate image. Based on this, step 202 specifically includes: obtaining a target detection model, wherein the target detection model includes a backbone network for extracting image features, a neck network for fusing image features, and a head network for detecting targets, and the backbone network includes multiple feature extraction layers; inputting the base plate image into the target detection model, performing image feature extraction on the base plate image through the backbone network to obtain image features corresponding to each feature extraction layer, performing feature fusion on multiple image features through the neck network to obtain fused features, and performing track identification on the fused features through the head network to obtain multiple tracks in the base plate image.

[0071] Specifically, to improve the detection accuracy of the target detection model, it is first necessary to train and construct the target detection model. Based on this, the method includes: constructing an initial target detection model; obtaining a sample dataset, wherein the sample dataset includes multiple sample images with annotated information, wherein the annotated information includes an annotated box with location information and track targets within the annotated box; dividing the sample dataset into a training set and a test set, using the training set to train the initial target detection model, and using the test set to test the trained initial target detection model, and finally selecting the trained initial target detection model that meets the test conditions as the target detection model. Furthermore, the base plate image is input into the target detection model for track detection, and the target detection model can directly output tracks with location information. Based on the track location information, combined with high-precision measurement tools, track geometric dimension information such as the length, diameter, and area of ​​each track, as well as track attribute information such as the distance between two tracks, can be determined.

[0072] 203. Based on the geometric size information, determine the track geometry evaluation information of the fuel particles, and based on the track spacing, determine the track spacing evaluation information of the fuel particles, wherein the track geometry evaluation information includes the track geometry mean, the track geometry variance, and the track geometry standard deviation, and the track spacing evaluation information includes the track spacing mean, the track spacing variance, and the track spacing standard deviation.

[0073] Specifically, determine the track geometry evaluation information such as the mean, variance, and standard deviation of the length of each track, the mean, variance, and standard deviation of the area of ​​each track, and the mean, variance, and standard deviation of the diameter of each track; and determine the track spacing evaluation information such as the mean, variance, and standard deviation of the track spacing.

[0074] 204. Determine a track geometry score of the fuel particles based on the track geometry evaluation information, and determine a track spacing score of the fuel particles based on the track spacing evaluation information.

[0075] Specifically, weights are assigned to the mean, variance, and standard deviation of track geometry based on actual needs. Based on the weights, the mean, variance, and standard deviation are summed to obtain a track geometry score. If multiple track geometries are included, the track geometry scores for each size are summed to obtain a comprehensive track geometry score. Similarly, weights are assigned to the mean, variance, and standard deviation of track spacing based on actual needs. Based on the weights, the mean, variance, and standard deviation are summed to obtain a track spacing score.

[0076] Perform weighted fusion of the track geometry score and the track spacing score to obtain a track comprehensive score, and determine the distribution uniformity of the fuel particles in the nuclear fuel pellet to be tested based on the track comprehensive score.

[0077] Specifically, weight coefficients are assigned to the track geometry score and the track spacing score, respectively. Based on the weight coefficients, the track geometry score and the track spacing score are weighted and summed to obtain a track comprehensive score. Finally, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be tested is determined based on the score interval of the track comprehensive score. For example, if the track comprehensive score is in a high score interval, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be tested is determined to be relatively good. If the track comprehensive score is in a medium score interval, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be tested is determined to be good. If the track comprehensive score is in a low score interval, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be tested is determined to be poor. The embodiment of the present invention converts the uniformity of element distribution into quantifiable values ​​through statistical quantities such as the mean, variance, and standard deviation of the track size and spacing, avoiding judgment errors caused by subjective judgment, thereby improving the detection accuracy of element distribution uniformity.

[0078] According to another method for detecting the uniformity of element distribution of MgO-based dispersed nuclear fuel pellets provided by the present invention, compared with the current manual method of detecting the uniformity of element distribution of dispersed nuclear fuel pellets, the present invention irradiates an imaging base plate by using rays generated by the spontaneous decay of fuel particles in the nuclear fuel pellets to be detected, and obtains a base plate image corresponding to the irradiated imaging base plate; and identifies multiple tracks generated by the irradiation of the fuel particles in the base plate image, and determines the track attribute information of each track and the inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction between the rays and the imaging base plate; finally, based on the track attribute information and the inter-track attribute information, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be detected is determined. Therefore, by analyzing the track properties formed by the α-ray irradiation imaging base plate, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be tested can be determined without slicing the pellets, which can improve the detection efficiency of the element distribution uniformity in the nuclear fuel pellets. At the same time, the detection can be completed by irradiating the imaging base plate without causing any damage to the pellets themselves, realizing non-destructive detection, and does not require too many instruments and equipment, reducing the detection cost. At the same time, the irradiation imaging base plate method will not be interfered with by factors such as the external environment, thereby ensuring the detection accuracy of the uniform distribution of fuel particles in the nuclear fuel pellets.

[0079] Further, as Figure 1 The embodiment of the present invention provides a device for detecting the uniformity of element distribution of MgO-based dispersed nuclear fuel pellets, such as Figure 4 As shown, the device includes: an irradiation unit 31 , an identification unit 32 , and a determination unit 33 .

[0080] The irradiation unit 31 can be used to irradiate the α imaging base plate using α rays generated by the spontaneous decay of fuel particles in the nuclear fuel pellets to be detected, and obtain a base plate image corresponding to the α imaging base plate after irradiation.

[0081] The identification unit 32 can be used to identify multiple tracks generated by the fuel particle irradiation in the base plate image, and determine the track attribute information of each track and the inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the α-ray interacts with the α-imaging base plate.

[0082] The determining unit 33 may be configured to determine the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected based on the track attribute information and the inter-track attribute information.

[0083] In a specific application scenario, in order to obtain the base plate image corresponding to the irradiated α imaging base plate, such as Figure 5 As shown, the irradiation unit 31 includes a first acquisition module 311 , an etching module 312 , and a shooting module 323 .

[0084] The first acquisition module 311 may be used to determine the etching liquid and acquire liquid property information of the etching liquid and substrate property information of the imaging substrate.

[0085] The etching module 312 can be used to determine the etching time based on the liquid property information and the base plate property information, and based on the etching time, immerse the irradiated α imaging base plate in the etching liquid for etching treatment to obtain the etched α imaging base plate.

[0086] The shooting module 323 can be used to connect a preset camera device with a preset microscope. When observing the etched α imaging base plate using the preset microscope, the preset camera device is controlled to shoot the observation results of the preset microscope to obtain a base plate image corresponding to the etched α imaging base plate.

[0087] In a specific application scenario, in order to identify multiple tracks generated by fuel particle irradiation in the bottom plate image, the identification unit 32 includes a second acquisition module 321 and a prediction module 322 .

[0088] The second acquisition module 321 can be used to obtain a target detection model, wherein the target detection model includes a backbone network for extracting image features, a neck network for fusing image features, and a head network for detecting targets, and the backbone network includes multiple feature extraction layers.

[0089] The prediction module 322 can be used to input the base plate image into the target detection model, perform image feature extraction on the base plate image through the backbone network to obtain image features corresponding to each feature extraction layer, perform feature fusion on multiple image features through the neck network to obtain fused features, and perform track recognition on the fused features through the head network to obtain multiple tracks in the base plate image.

[0090] In a specific application scenario, the track attribute information includes the geometric size information of each track, and the inter-track attribute information includes the track spacing between every two tracks; in order to determine the distribution uniformity of fuel particles in the nuclear fuel pellets to be detected, the determination unit 33 can be specifically used to determine the track geometry evaluation information of the fuel particles based on the geometric size information, and determine the track spacing evaluation information of the fuel particles based on the track spacing, wherein the track geometry evaluation information includes the track geometry mean, the track geometry variance, and the track geometry standard deviation, and the track spacing evaluation information includes the track spacing mean, the track spacing variance, and the track spacing standard deviation; based on the track geometry evaluation information, determine the track geometry score of the fuel particles, and based on the track spacing evaluation information, determine the track spacing score of the fuel particles; perform weighted fusion on the track geometry score and the track spacing score to obtain a track comprehensive score, and based on the track comprehensive score, determine the distribution uniformity of the fuel particles in the nuclear fuel pellets to be detected.

[0091] In a specific application scenario, in order to determine the distribution uniformity of fuel particles in the nuclear fuel pellets to be detected, the determination unit 33 includes a determination module 331 , a cross module 332 , and a detection module 333 .

[0092] The determining module 331 may be configured to determine a track feature vector corresponding to the track attribute information and an inter-track feature vector corresponding to the inter-track attribute information.

[0093] The cross module 332 may be configured to perform cross processing on the track feature vector and the inter-track feature vector to obtain a track cross feature vector.

[0094] The detection module 333 can be used to input the track intersection feature vector into a preset distribution detection model for distribution detection to obtain the distribution uniformity of the fuel particles in the nuclear fuel pellets to be detected, wherein the preset distribution detection model is pre-constructed based on a sample data set with a distribution uniformity label.

[0095] In a specific application scenario, in order to perform cross-processing on the track feature vector and the inter-track feature vector, the cross-module 332 can be specifically used to perform feature-level cross-processing on the track feature vector and the inter-track feature vector to obtain a feature cross-vector; perform element-level cross-processing on the track feature vector and the inter-track feature vector to obtain an element cross-vector; perform low-order cross-processing on the track feature vector and the inter-track feature vector to obtain a low-order cross-vector; use a preset transformation function to transform the feature cross-vector, element cross-vector, and low-order cross-vector to obtain the track cross-feature vector.

[0096] In a specific application scenario, in order to perform enhancement processing on the base plate image, the device further includes an image enhancement unit 34 .

[0097] The image enhancement unit 34 may be configured to perform image quality enhancement processing on the base plate image to obtain the enhanced base plate image.

[0098] The recognition unit 32 may also be used to recognize multiple tracks generated by the irradiation of the fuel particles in the enhanced bottom plate image.

[0099] It should be noted that for other corresponding descriptions of the functional modules involved in the device for detecting uniformity of element distribution of MgO-based dispersed nuclear fuel pellets provided in the embodiment of the present invention, reference can be made to Figure 1 The corresponding description of the method shown will not be repeated here.

[0100] Based on the above Figure 1 The method shown, accordingly, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the following steps when executed by a processor: irradiating an α imaging base plate with α rays generated by spontaneous decay of fuel particles in the nuclear fuel pellets to be detected, and obtaining a base plate image corresponding to the α imaging base plate after irradiation; identifying multiple tracks generated by the irradiation of the fuel particles in the base plate image, and determining track attribute information of each track and inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the α rays interact with the α imaging base plate; based on the track attribute information and the inter-track attribute information, determining the distribution uniformity of the fuel particles in the nuclear fuel pellets to be detected.

[0101] Based on the above Figure 1 The method shown and Figure 4 The embodiment of the device shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Figure 6As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43; when the processor 41 executes the program, the following steps are implemented: irradiating an α imaging base plate with α rays generated by spontaneous decay of fuel particles in the nuclear fuel pellets to be detected, and acquiring a base plate image corresponding to the α imaging base plate after irradiation; identifying multiple tracks generated by the irradiation of the fuel particles in the base plate image, and determining track attribute information of each track and inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the α rays interact with the α imaging base plate; determining the damage of the fuel particles in the base plate based on the track attribute information and the inter-track attribute information.

[0102] Describe the distribution uniformity in the nuclear fuel pellets to be tested.

[0103] Through the technical solution of the present invention, the present invention irradiates an imaging base plate by using rays generated by the spontaneous decay of fuel particles in the nuclear fuel pellets to be detected, and obtains a base plate image corresponding to the irradiated imaging base plate; and identifies multiple tracks generated by the irradiation of the fuel particles in the base plate image, and determines the track attribute information of each track and the inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction between the rays and the imaging base plate; finally, based on the track attribute information and the inter-track attribute information, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be detected is determined. Therefore, by analyzing the track properties formed by the α-ray irradiation imaging base plate, the distribution uniformity of the fuel particles in the nuclear fuel pellets to be tested can be determined without slicing the pellets, which can improve the detection efficiency of the element distribution uniformity in the nuclear fuel pellets. At the same time, the detection can be completed by irradiating the imaging base plate without causing any damage to the pellets themselves, realizing non-destructive detection, and does not require too many instruments and equipment, reducing the detection cost. At the same time, the irradiation imaging base plate method will not be interfered with by factors such as the external environment, thereby ensuring the detection accuracy of the uniform distribution of fuel particles in the nuclear fuel pellets.

[0104] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, centralized on a single computing device, or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computing device, which can then be stored in a storage device and executed by the computing device. In some cases, the steps shown or described can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0105] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for detecting element distribution uniformity of MgO-based dispersed nuclear fuel pellets, characterized in that: include: irradiating an α imaging base plate using α rays generated by spontaneous decay of fuel particles in a nuclear fuel pellet to be detected, and acquiring a base plate image corresponding to the α imaging base plate after irradiation; identifying a plurality of tracks generated by the irradiation of the fuel particles in the base plate image, and determining track attribute information of each track and inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction of the alpha ray with the alpha imaging base plate; Based on the track attribute information and the inter-track attribute information, the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected is determined.

2. The method according to claim 1, characterized in that The obtaining of a base plate image corresponding to the irradiated α imaging base plate includes: Determining an etching liquid, and obtaining liquid property information of the etching liquid and base plate property information of the alpha imaging base plate; Determining an etching time based on the liquid property information and the base plate property information, and based on the etching time, inserting the irradiated α imaging base plate into the etching liquid for etching to obtain the etched α imaging base plate; The preset camera device is connected to the preset microscope. When the etched α imaging base plate is observed using the preset microscope, the preset camera device is controlled to shoot the observation results of the preset microscope to obtain a base plate image corresponding to the etched α imaging base plate.

3. The method according to claim 1, characterized in that A plurality of tracks resulting from the irradiation of the fuel particles are identified in the base plate image, including: Obtaining a target detection model, wherein the target detection model includes a backbone network for extracting image features, a neck network for fusing image features, and a head network for detecting targets, wherein the backbone network includes multiple feature extraction layers; The base plate image is input into the target detection model, and image features of the base plate image are extracted through the backbone network to obtain image features corresponding to each feature extraction layer. Multiple image features are fused through the neck network to obtain fused features. Tracks are identified on the fused features through the head network to obtain multiple tracks in the base plate image.

4. The method according to claim 1, wherein The track attribute information includes the geometric size information of each track, and the inter-track attribute information includes the track spacing between every two tracks; Determining the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected based on the track attribute information and the inter-track attribute information includes: Determining track geometry evaluation information of the fuel particles based on the geometric size information, and determining track spacing evaluation information of the fuel particles based on the track spacing, wherein the track geometry evaluation information includes a track geometric size mean, a track geometric size variance, and a track geometric size standard deviation, and the track spacing evaluation information includes a track spacing mean, a track spacing variance, and a track spacing standard deviation; determining a track geometry score of the fuel particles based on the track geometry evaluation information, and determining a track spacing score of the fuel particles based on the track spacing evaluation information; The track geometry score and the track spacing score are weightedly fused to obtain a track comprehensive score, and the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected is determined based on the track comprehensive score.

5. The method according to claim 1, wherein The determining, based on the track attribute information and the inter-track attribute information, the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected includes: Determining a track feature vector corresponding to the track attribute information and an inter-track feature vector corresponding to the inter-track attribute information; Performing cross processing on the track feature vector and the inter-track feature vector to obtain a track cross feature vector; The track intersection feature vector is input into a preset distribution detection model for distribution detection to obtain the distribution uniformity of the fuel particles in the nuclear fuel pellet to be detected, wherein the preset distribution detection model is pre-constructed based on a sample data set with a distribution uniformity label.

6. The method according to claim 5, characterized in that The cross processing of the track feature vector and the inter-track feature vector to obtain a track cross feature vector includes: Performing feature-level cross processing on the track feature vector and the inter-track feature vector to obtain a feature cross vector; Performing element-level cross processing on the track feature vector and the inter-track feature vector to obtain an element cross vector; Performing low-order cross processing on the track feature vector and the inter-track feature vector to obtain a low-order cross vector; The characteristic cross vector, the element cross vector, and the low-order cross vector are transformed using a preset transformation function to obtain the track cross characteristic vector.

7. The method according to claim 1, characterized in that Before identifying the plurality of tracks produced by the irradiation of the fuel particles in the floor image, the method further comprises: Performing image quality enhancement processing on the baseplate image to obtain an enhanced baseplate image; A plurality of tracks resulting from the irradiation of the fuel particles are identified in the base plate image, including: A plurality of tracks resulting from the irradiation of the fuel particles are identified in the enhanced floor image.

8. A device for detecting element distribution uniformity of MgO-based dispersed nuclear fuel pellets, characterized in that: include: an irradiation unit, configured to irradiate an α imaging base plate using α rays generated by spontaneous decay of fuel particles in the nuclear fuel pellets to be detected, and to obtain a base plate image corresponding to the α imaging base plate after irradiation; an identification unit, configured to identify a plurality of tracks generated by the irradiation of the fuel particles in the base plate image, and determine track attribute information of each track and inter-track attribute information between each track, wherein each track is a microscopic damage trace left after the interaction between the α-rays and the α-imaging base plate; A determination unit is configured to determine the distribution uniformity of the fuel particles in the nuclear fuel pellet to be inspected based on the track attribute information and the inter-track attribute information.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images