Model training method and device, analysis method and device, related equipment, storage medium and computer program product

Abstract

The invention discloses a model training method and device, an analysis method and device, related equipment, a storage medium and a computer program product. The method comprises the steps that multiple sets of sample data are obtained, an initial model is constructed, and each set of sample data in the multiple sets of sample data is related to burnup, initial uranium concentration, cooling time, curium-244 content and plutonium content corresponding to a spent fuel assembly; the initial model is trained through the multiple sets of sample data, a first model is obtained, and the first model is at least used for determining the plutonium content corresponding to the spent fuel assembly based on the burnup, the initial uranium concentration, the cooling time and the curium-244 content corresponding to the spent fuel assembly. The first model obtained through training can be used for accurately determining the plutonium content in the spent fuel assembly.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of nuclear material analysis, and in particular to a model training method, an analysis method, a device, related equipment, a storage medium and a computer program product. BACKGROUND

[0002] In the development process of nuclear energy technology, the three-step strategy is an implementation plan to accelerate the development of advanced nuclear energy technology, which specifically includes three technical stages of "thermal reactor-fast reactor-fusion reactor". Among them, the main role of fast reactor technology is to achieve nuclear fuel breeding. After the fast reactor reaction is over, dry reprocessing of the spent fuel assembly (which can also be understood as spent fuel) discharged from the reactor can achieve nuclear fuel cycle.

[0003] In the nuclear technology application scenario, nuclear material quantification is usually achieved by using nuclear material accounting and control technology to ensure that the nuclear facility can achieve nuclear material closed balance (which can also be understood as closed accounting) during operation, so as to realize the regulation of nuclear materials and ensure the safe and legal use of nuclear materials. For the fast reactor technology scenario, in order to achieve closed accounting, the plutonium (which can also be expressed as Pu) content (which can also be understood as plutonium material content) in the spent fuel assembly needs to be determined.

[0004] However, how to accurately analyze the plutonium content in the spent fuel assembly of the fast reactor has not yet been effectively solved. SUMMARY

[0005] To solve the related technical problems, the embodiments of the present application provide a model training method, an analysis method, a device, related equipment, a storage medium and a computer program product.

[0006] The technical scheme of the embodiments of the present application is implemented as follows:

[0007] The embodiments of the present application provide a model training method, comprising:

[0008] Obtain a plurality of sets of sample data, and construct an initial model, each set of sample data in the plurality of sets of sample data is associated with the burnup, initial uranium concentration, cooling time, cerium-244 content and plutonium content corresponding to the spent fuel assembly;

[0009] Train the initial model using the plurality of sets of sample data to obtain a first model, the first model is used at least to determine the plutonium content corresponding to the spent fuel assembly based on the burnup, initial uranium concentration, cooling time and cerium-244 content corresponding to the spent fuel assembly.

[0010] In the above scheme, the first factor associated with the plutonium content corresponding to the spent fuel assembly includes the burnup, initial uranium concentration, cooling time and cerium-244 content corresponding to the spent fuel assembly, and the initial model is constructed, comprising:

[0011] Based on the plurality of sets of sample data, for each first factor, a first relationship curve is determined, the first relationship curve representing a corresponding relationship between the first factor and the plutonium content corresponding to the spent fuel assembly; and for each interaction item in one or more interaction items, a second relationship curve is determined, the second relationship curve representing a corresponding relationship between the interaction item and the plutonium content corresponding to the spent fuel assembly, the interaction item representing the interaction between two different first factors;

[0012] All the first relationship curves and the second relationship curves are determined to determine the initial model.

[0013] In the above scheme, the method further comprises:

[0014] Significance analysis is performed on all interaction items formed between two first factors to obtain an analysis result;

[0015] The one or more interaction items are determined by using the analysis result.

[0016] In the above scheme, the analysis result at least includes a significance level corresponding to each interaction item, and the one or more interaction items are determined by using the analysis result, which includes:

[0017] Interaction items with a significance level less than a preset threshold in all interaction items are taken as the one or more interaction items.

[0018] In the above scheme, the initial model is trained by using the plurality of sets of sample data, which includes:

[0019] Based on multiple regression calculation and collinearity processing, parameters of the initial model are adjusted by using the plurality of sets of sample data.

[0020] In the above scheme, each set of sample data in the plurality of sets of sample data is associated with a set of values of a second factor, the second factor including burnup, initial uranium concentration, and cooling time corresponding to the spent fuel assembly, and the plurality of sets of sample data are obtained, which includes:

[0021] For each set of values of the second factor, the content of Cm-244 and the content of Pu in the spent fuel assembly corresponding to the set of values of the second factor are determined by using a second model; and the set of values of the second factor and the determined content of Cm-244 and the content of Pu are taken as a set of sample data.

[0022] Embodiments of the present application also provide an analysis method, which includes:

[0023] The burnup, the initial uranium concentration, the cooling time, and the content of Cm-244 corresponding to the spent fuel assembly to be analyzed are obtained.

[0024] Determine the plutonium content corresponding to the spent fuel assembly to be analyzed by using the first model and the burnup, initial uranium concentration, cooling time, and Cm-244 content corresponding to the spent fuel assembly to be analyzed, wherein the first model comprises a first model determined by any of the model training methods described above.

[0025] The embodiments of the present application also provide a model training device, comprising:

[0026] The construction unit is configured to obtain a plurality of groups of sample data, and construct an initial model, wherein each group of sample data in the plurality of groups of sample data is associated with the burnup, initial uranium concentration, cooling time, Cm-244 content, and plutonium content corresponding to a spent fuel assembly.

[0027] The training unit is configured to train the initial model by using the plurality of groups of sample data to obtain a first model, wherein the first model is used at least to determine the plutonium content corresponding to the spent fuel assembly based on the burnup, initial uranium concentration, cooling time, and Cm-244 content corresponding to the spent fuel assembly.

[0028] The embodiments of the present application also provide an analysis device, comprising:

[0029] The obtaining unit is configured to obtain the burnup, initial uranium concentration, cooling time, and Cm-244 content corresponding to the spent fuel assembly to be analyzed.

[0030] The analysis unit is configured to determine the plutonium content corresponding to the spent fuel assembly to be analyzed by using the first model and the burnup, initial uranium concentration, cooling time, and Cm-244 content corresponding to the spent fuel assembly to be analyzed, wherein the first model comprises a first model determined by any of the model training methods described above.

[0031] The embodiments of the present application also provide an electronic device, comprising:

[0032] The first processor is configured to obtain a plurality of groups of sample data, and construct an initial model, wherein each group of sample data in the plurality of groups of sample data is associated with the burnup, initial uranium concentration, cooling time, Cm-244 content, and plutonium content corresponding to a spent fuel assembly; and train the initial model by using the plurality of groups of sample data to obtain a first model, wherein the first model is used at least to determine the plutonium content corresponding to the spent fuel assembly based on the burnup, initial uranium concentration, cooling time, and Cm-244 content corresponding to the spent fuel assembly.

[0033] The embodiments of the present application also provide an electronic device, comprising:

[0034] The second communication interface is configured to obtain the burnup, initial uranium concentration, cooling time, and Cm-244 content corresponding to the spent fuel assembly to be analyzed.

[0035] A second processor is configured to determine the plutonium content corresponding to the spent fuel assembly to be analyzed by using the first model and the burnup, the initial uranium concentration, the cooling time and the content of Cm-244 corresponding to the spent fuel assembly to be analyzed, wherein the first model comprises the first model determined by any one of the model training methods.

[0036] The embodiments of the present application further provide an electronic device, which comprises a first processor and a first memory for storing a computer program capable of running on the processor,

[0037] The first processor is configured to execute the steps of any one of the model training methods when the computer program is run.

[0038] The embodiments of the present application further provide an electronic device, which comprises a second processor and a second memory for storing a computer program capable of running on the processor,

[0039] The second processor is configured to execute the steps of the analysis method when the computer program is run.

[0040] The embodiments of the present application further provide a storage medium, which has a computer program stored thereon, wherein the computer program is configured to implement the steps of any one of the methods when executed by a processor.

[0041] The embodiments of the present application further provide a computer program product, which comprises a computer program, wherein the computer program is configured to implement the steps of any one of the methods when executed by a processor.

[0042] The model training method, analysis method, apparatus, related equipment, storage medium, and computer program products provided in this application embodiment acquire multiple sets of sample data and construct an initial model. Each set of sample data is associated with the burnup, initial uranium concentration, cooling time, curium-244 content, and plutonium content of a spent fuel assembly. The initial model is trained using the multiple sets of sample data to obtain a first model. This first model is used at least to determine the plutonium content of the spent fuel assembly based on its burnup, initial uranium concentration, cooling time, and curium-244 content. The first model obtained through training can be used to accurately determine the plutonium content in the spent fuel assembly. It also acquires the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed. Using the first model and the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed, the plutonium content of the spent fuel assembly to be analyzed is determined. The first model includes the first model determined by the above-described model training method. In constructing the first model for analyzing plutonium content in spent fuel, in addition to the three factors of burnup, initial uranium concentration, and cooling time corresponding to the spent fuel assembly, the curium-244 content, which characterizes the ability of the fuel assembly to produce curium, was introduced as one of the factors to consider. This allows for a more accurate reflection of the impact of the initial state of the fuel assembly on the plutonium content in the spent fuel assembly, thereby improving the accuracy of plutonium content analysis. Thus, for each spent fuel assembly to be analyzed, the first model, along with the obtained burnup, initial uranium concentration, cooling time, and curium-244 content corresponding to that spent fuel assembly, can be used to accurately analyze the plutonium content in that spent fuel assembly, thereby ensuring a closed-loop balance for nuclear materials. Attached Figure Description

[0043] Figure 1 This is a schematic flowchart of the model training method in an embodiment of this application;

[0044] Figure 2 This is a flowchart illustrating the analysis method of an embodiment of this application;

[0045] Figure 3 A flowchart illustrating a method for analyzing plutonium content in spent fuel based on the radionuclide curium-244, serving as an application example of this application;

[0046] Figure 4 This is a schematic diagram of the model training device structure according to an embodiment of this application;

[0047] Figure 5 This is a schematic diagram of the analysis device structure according to an embodiment of this application;

[0048] Figure 6 This is a schematic diagram of an electronic device structure according to an embodiment of this application;

[0049] Figure 7This is a schematic diagram of another electronic device structure according to an embodiment of this application. Detailed Implementation

[0050] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0051] In related technologies, neutron measurement methods (which can also be understood as measurement methods applying neutron measurement and analysis techniques) are commonly used to analyze the plutonium content in spent fuel assemblies discharged from reactors. Specifically, since nuclides in spent fuel assemblies spontaneously fission to produce neutrons, and neutrons have strong penetrating power, the content of nuclides can be determined by measuring the number of neutrons in the neutron signal generated by nuclide fission (which can also be understood as detecting neutron counts). This method has the advantages of being fast, timely, and accurate.

[0052] However, in practical applications, fast reactors exhibit deep burnup (BU), resulting in highly radioactive spent fuel assemblies with a high content of long-lived fission products. This leads to a high gamma-ray emissivity and complex radioactive characteristics in fast reactor spent fuel assemblies, which can interfere with neutron counting. Furthermore, the heat release rate of fast reactor spent fuel assemblies is 2.6 times that of light water reactors during commissioning, and their spontaneous neutron emission rate is three times that of light water reactors of the same mass. The neutron signals generated by spontaneous neutron emission can mask the characteristic neutron signals of plutonium materials. Therefore, in fast reactor scenarios, due to both gamma signal interference and the complexity of neutron sources, it is difficult to accurately analyze the plutonium content in fast reactor spent fuel assemblies using conventional neutron measurement methods for direct neutron counting.

[0053] Because of the curium-244 (which can also be expressed as) in the spent fuel assembly of the fast reactor... 244 Curium (Cm) has a high spontaneous fission yield (i.e., the number of neutrons produced by spontaneous fission). In related technologies, a scheme has been proposed to indirectly analyze plutonium content based on the relationship between curium-244 neutron count and plutonium content (which can also be understood as a scheme to obtain plutonium content using curium-244). Specifically, this scheme determines the mass of curium-244 by measuring the neutron count in the spent fuel assembly of the fast reactor; then, using the mass of curium-244 and a model of the relationship between curium-244 and plutonium, the plutonium content in the spent fuel assembly of the fast reactor is determined.

[0054] In practical applications, the following prerequisites must be met to achieve accurate plutonium content analysis using the above method:

[0055] During the processing of spent fuel assemblies (i.e., the process of physically and / or chemically processing spent fuel), curium-244 is transferred together with plutonium (i.e., curium-244 and plutonium do not exist separately);

[0056] The materials in the spent fuel assembly are uniformly distributed, that is, the mass ratio of curium-244 to plutonium at all positions in the spent fuel assembly is uniform.

[0057] However, there is no test to prove that curium-244 will be transferred synchronously with plutonium at present, and the distribution of nuclides at different positions in the spent fuel assembly (including the spent fuel at different positions in the reactor and different axial and / or radial regions in the same spent fuel rod) is generally not uniform, that is, in actual application, the above-mentioned premise cannot be met, and therefore it is difficult to accurately analyze the content of plutonium in the spent fuel assembly by using the above-mentioned scheme.

[0058] Through analysis of the physical process of the burnup of the in-core assembly (which can also be referred to as the in-core fuel assembly), it can be determined that the mono-energy neutron diffusion equation of the in-core assembly can be expressed as formula (1):

[0059]

[0060] Wherein, S represents the generation rate of neutrons per unit volume of the in-core assembly, k eff represents the effective multiplication factor of the reactor, v represents the average speed of neutrons, Σ f represents the macroscopic fission cross section of the nuclide, Σ α represents the macroscopic absorption cross section of the nuclide, D represents the diffusion coefficient, and φ represents the neutron flux density in the reactor. In the case of testing the criticality of the reactor, the terms and in formula (1) are set to zero; in other cases, the terms

[0061] In actual application, S in formula (1) can be understood as the neutrons generated by the primary neutron source, can be understood as the neutrons induced by fission, -∑ α φ can be understood as the neutron absorption process, can be understood as the neutron leakage process, and can be understood as the rate of change of the neutron flux density with respect to time in the transient process multiplied by the average speed of neutrons. Here, the value of each term changes with the position of the fuel assembly.

[0062] In actual application, the neutron absorption process can include the absorption process that leads to fission and the absorption process that captures neutrons, and when the two absorption processes are expressed separately, the mono-energy neutron diffusion equation of the in-core assembly can be expressed as formula (2):

[0063]

[0064] Wherein, represents the net amount of neutrons produced by fission.

[0065] In practical applications, in the process of burning consumption, the geometry of the fuel assembly does not change, and the diffusion coefficient of each position in the fuel assembly remains unchanged. Therefore, relative to the change of neutron flux density with time and space, the leakage term in formula (2) (i.e. ) does not change with time and space during the reaction process, that is, the leakage term is a constant. At the same time, when the fuel assembly is measured by a non-destructive assay (NDA) measurement independent of time, the value of the time-dependent term in formula (2) (i.e. ) is 0; at the same time, when the fuel assembly is measured by a time-dependent (or time-dependent) NDA measurement (such as neutron coincidence counting or differential decay measurement, etc.), the characteristic decay time or differential decay time τ can be obtained by debugging and calculation according to the measurement instrument and the measurement site, and the time-dependent term in formula (2) (i.e. ) is a known quantity.

[0066] As can be seen from the above description, the two terms and in formula (2) are constants or known quantities, so the characteristics of the fuel assembly can be determined according to the remaining three terms in formula (2), that is, the characteristics of the fuel assembly determined by the neutron physics are three-dimensional.

[0067] Based on this, for the fast reactor scene, burnup, cooling time (English can be expressed as Cooling Time, abbreviated as CT), and initial uranium concentration (also known as initial concentration, English can be expressed as Initial Enrichment, abbreviated as IE) can be selected as three dimensions to represent the spent fuel assembly.

[0068] However, when the fuel assembly contains mixed oxide (MOX) fuel, plutonium isotopes are introduced during the loading process, which increases the yield of plutonium-240, curium-242, and curium-244 in the fuel assembly, thereby affecting the plutonium content and curium-244 content in the discharged spent fuel assembly.

[0069] Since the burnup is only associated with the reaction process and is independent of the initial conditions of the fuel assembly, and since the initial uranium concentration is only associated with the fissile isotopes (such as uranium isotopes) and is independent of the plutonium isotopes, and since the cooling time is only associated with the cooling process of the discharged spent fuel and is independent of the initial conditions of the fuel assembly. Therefore, it is difficult to represent the effect of the introduction of plutonium isotopes during the loading process on the plutonium content in the spent fuel assembly by selecting the three dimensions (i.e. burnup, cooling time, and initial uranium concentration).

[0070] Based on this, in various embodiments of the present application, when constructing the first model for analyzing the plutonium content in spent fuel, in addition to the burnup, initial uranium concentration, and cooling time of the spent fuel assembly, the cerium-244 content representing the ability of the fuel assembly to produce cerium is also introduced as one of the factors to be considered, which can more accurately reflect the influence of the initial state of the fuel assembly on the plutonium content in the spent fuel assembly, thereby improving the accuracy of the analysis of the plutonium content. In this way, for each spent fuel assembly to be analyzed, the first model can be used, and the burnup, initial uranium concentration, cooling time, and cerium-244 content of the spent fuel assembly are obtained, to accurately analyze the plutonium content in the spent fuel assembly, thereby ensuring the closed balance of nuclear materials.

[0071] The embodiment of the present application provides a model training method, as shown in the figure, applied to an electronic device, and the method comprises the following steps: Figure 1

[0072] Step 101: Obtain a plurality of groups of sample data, and construct an initial model, each group of sample data in the plurality of groups of sample data is associated with the burnup, initial uranium concentration, cooling time, cerium-244 content, and plutonium content of a spent fuel assembly;

[0073] Step 102: Train the initial model by using the plurality of groups of sample data to obtain a first model, the first model is used at least for determining the plutonium content corresponding to a spent fuel assembly based on the burnup, initial uranium concentration, cooling time, and cerium-244 content corresponding to the spent fuel assembly.

[0074] Here, in actual application, the electronic device can include a server, a computer, etc., and the electronic device can be used at least for analyzing a spent fuel assembly, and the specific implementation and name of the electronic device are not limited in the embodiment of the present application, as long as the function thereof is realized. The spent fuel assembly can also be referred to as spent fuel, that is, the fuel assembly obtained after the nuclear reactor core fuel assembly (such as a fuel rod assembly) is unloaded and cooled, which can specifically include a fast reactor spent fuel assembly, and the name of the spent fuel assembly is not limited in the embodiment of the present application.

[0075] In actual application, when the electronic device constructs the initial model, the burnup, initial uranium concentration, cooling time, and cerium-244 content corresponding to the spent fuel assembly are taken as four influencing factors (which can also be understood as factors or factors, etc.), so that the initial model constructed can accurately reflect the initial state of plutonium in the fuel assembly and the process of nuclide generation, cooling, etc. related to nuclear reactions, thereby improving the accuracy of the analysis of the plutonium content by using the model. Here, the initial model can also be referred to as an initial relationship model or a pre-training model, etc., and the present application is not limited thereto.

[0076] ​In order to improve the accuracy of constructing the initial model, in step 101, the electronic device acquires a plurality of sets of sample data in different scenarios, so that the initial model can be constructed based on the acquired plurality of sets of sample data. Each set of sample data corresponds to a set of burnup, initial uranium concentration, cooling time, cerium-244 content and plutonium content of the spent fuel assembly. The sample data can also be referred to as training data, etc., which is not limited in the embodiments of the present application.

[0077] Specifically, the electronic device acquires the plurality of sets of sample data in at least one of the following ways:

[0078] The plurality of sets of sample data are pre-configured in the electronic device.

[0079] The plurality of sets of sample data are received from a related device such as a measuring device or an analysis device.

[0080] The plurality of sets of sample data are generated based on a configured model (or program).

[0081] In actual application, the electronic device can acquire the plurality of sets of sample data in one of the above ways according to actual needs, which is not limited in the embodiments of the present application.

[0082] When the electronic device acquires the plurality of sets of sample data in the way of generating the plurality of sets of sample data based on a configured model (hereinafter referred to as a second model), the electronic device can determine the cerium-244 content and the plutonium content in the spent fuel assembly corresponding to each set of values of burnup, initial uranium concentration and cooling time of a given one or more sets (one or more sets can also be understood as at least one set) of spent fuel assemblies by using the second model. The second model can also be understood as a calculation program, which can also be referred to as a point burnup decay calculation program or a point burnup calculation program, etc., which is not limited in the embodiments of the present application. The second model can be used at least to simulate the nuclide generation process and the cooling process of the fuel assembly, that is, the electronic device can simulate the accumulation and decay of radioactive substances in the reactor (including a fast reactor in particular) by using the second model.

[0083] Based on this, in an embodiment, each set of sample data in the plurality of sets of sample data is associated with a set of values of a second factor, and the second factor includes burnup, initial uranium concentration and cooling time of the spent fuel assembly. The acquisition of the plurality of sets of sample data includes:

[0084] For each set of values of the second factor, the cerium-244 content and the plutonium content in the spent fuel assembly corresponding to the set of values of the second factor are determined by using the second model, and the set of values of the second factor and the determined cerium-244 content and plutonium content are taken as a set of sample data.

[0085] Here, in actual application, the second factor refers to a set of factors for inputting the second model to determine the corresponding content of Cm-244 and Pu, and the name of the second factor is not limited in the embodiments of the present application.

[0086] In actual application, the values of each set of second factors are different (it can also be understood that the values of all second factors in different sets of second factors are not completely the same), and the values of the second factors are related to the value range of burnup, initial uranium concentration and cooling time corresponding to the spent fuel assembly.

[0087] Exemplarily, as shown in Table 1, it is assumed that the optional values (which can also be understood as input values, i.e., values input into the second model) of burnup include {80, 100, 120, 140, 160, 180, 200} in units of GWd / tU (GigaWatt-day per ton of Uranium); the optional values of initial uranium concentration include {0.3, 0.5, 0.8, 1.3, 3.0, 4.5, 6.0, 7.5} in units of %; and the optional values of cooling time include {40, 60, 80, 100, 150, 365} in units of days, at this time, 336 (i.e., 7x8x6=336) combinations can be obtained based on the combination of all optional values of the three factors, i.e., 336 sets of values of the second factors; the electronic device can determine the content of Cm-244 and Pu by using the second model for each set of values, and obtain the corresponding sample data, so that all sample data obtained can more accurately represent the content of Cm-244 and Pu under different burnup, different initial uranium concentration and different cooling time in the entire value range, since the 336 sets of values cover the entire value range.

[0088]

[0089] Table 1

[0090] After obtaining the plurality of sets of sample data, in step 101, the electronic device can construct an initial model based on the plurality of sets of sample data obtained.

[0091] In actual application, the burnup, the initial uranium concentration, the cooling time, and the content of Cm-244 corresponding to the spent fuel assembly can be used as four first factors affecting the content of Pu corresponding to the spent fuel assembly, that is, the first factors associated with the content of Pu corresponding to the spent fuel assembly include the burnup, the initial uranium concentration, the cooling time, and the content of Cm-244 corresponding to the spent fuel assembly; at this time, the electronic device can construct the initial model based on the four first factors and the obtained multiple sets of sample data. Here, the first factors can also be understood as the influencing factors of the content of Pu in the spent fuel assembly, and the name of the first factors is not limited in the embodiments of the present application.

[0092] Specifically, since the relationship between the overall first factors and the content of Pu in the spent fuel assembly (which can also be understood as the influence of the overall first factors on the content of Pu in the spent fuel assembly) is relatively complex, it is difficult to directly determine a single function that can reflect the above relationship and use the function to represent the initial model. Therefore, the electronic device can first analyze the influence of each first factor on the content of Pu in the spent fuel assembly and the influence of the interaction (which can also be understood as the interaction) between the first factors on the content of Pu in the spent fuel assembly to obtain an analysis result; then, the electronic device can determine the influence of the overall first factors on the content of Pu in the spent fuel assembly based on the analysis result, thereby constructing the initial model.

[0093] Based on this, in an embodiment, the constructing the initial model comprises:

[0094] Based on the multiple sets of sample data, for each first factor, a first relationship curve is determined, the first relationship curve representing the corresponding relationship between the first factor and the content of Pu corresponding to the spent fuel assembly; and for each interaction item in one or more interaction items, a second relationship curve is determined, the second relationship curve representing the corresponding relationship between the interaction item and the content of Pu corresponding to the spent fuel assembly, the interaction item representing the interaction between two different first factors.

[0095] The initial model is determined by using all the determined first relationship curves and second relationship curves.

[0096] Here, in actual application, the first relationship curve corresponding to each first factor can also be understood as a unary regression model corresponding to the first factor, that is, a unary fitting result of the relationship between the first factor and the content of Pu in the spent fuel assembly, and the name of the first relationship curve is not limited in the embodiments of the present application.

[0097] In actual application, the electronic device can use the multiple sets of sample data to respectively establish, for each first factor, a first relationship curve between the first factor and the content of Pu in the spent fuel assembly.

[0098] Exemplarily, the first relationship curve corresponding to the burnup, the cooling time, the initial uranium concentration and the content of Cm-244 in the spent fuel assembly can be expressed as formula (3) to formula (6):

[0099] M Pu = -0.185267BU + 202.88 (3)

[0100] M Pu = -2.6867x10 -6 CT 2 + 0.00139CT + 176.83794 (4)

[0101] M Pu = -8.42065IE 2 + 2.29743IE + 176.88683 (5)

[0102] M Pu = -64.63251M Cm 2 + 484.73244M Cm - 719.30953 (6)

[0103] wherein, MPu represents the content of plutonium in the spent fuel assembly, BU represents the burnup, CT represents the cooling time, IE represents the initial uranium concentration, and MCm represents the content of Cm-244 in the spent fuel assembly.

[0104] In actual application, the content of plutonium in the spent fuel assembly can be associated with the interaction between two different first factors in addition to the association with each first factor alone, that is, one or more (one or more can also be understood as at least one) interaction terms between two different first factors.

[0105] Based on this, the electronic device can determine which interaction terms between different first factors will affect the content of plutonium in the spent fuel assembly through significance analysis.

[0106] Specifically, in an embodiment, the method can further include:

[0107] performing significance analysis on all interaction terms between two first factors to obtain an analysis result;

[0108] determining the one or more interaction terms using the analysis result.

[0109] Here, in actual application, when performing the significance analysis, the electronic device can test whether the interaction between different factors on the plutonium content in the spent fuel assembly is significant based on the plurality of sets of sample data in combination with the variance between different factors to obtain an analysis result. The analysis result can include degrees of freedom, significance, significance level, etc. Meanwhile, the significance analysis can also be used to test whether each factor has a significant impact on the plutonium content in the spent fuel assembly, so as to ensure that the selected factors for representing the spent fuel assembly can have an impact on the plutonium content, thereby ensuring the accuracy of the constructed model.

[0110] When the analysis result includes a significance level corresponding to each interaction term, in an embodiment, the determining the one or more interaction terms based on the analysis result includes:

[0111] The interaction term with a significance level less than a preset threshold value in all interaction terms is taken as the one or more interaction terms.

[0112] Here, in actual application, the preset threshold value can be set according to actual needs, and the embodiments of the present application do not limit it,

[0113] For example, based on the above example, it is assumed that the electronic device performs significance analysis based on the 336 sets of sample data, and the analysis result is shown in Table 2, and the preset threshold value corresponding to the significance level is 0.05. At this time, for the plutonium content in the spent fuel assembly, the statistical quantity F value (FBU) corresponding to the burnup satisfies F BU >>F(6,335)=2.12, the statistical quantity F value (FCT) corresponding to the cooling time satisfies F CT >>F(5,335)=2.23, the statistical quantity F value (FIE) corresponding to the initial uranium concentration satisfies F IE >>F(7,335)=2.03; and the significance levels corresponding to the burnup, the cooling time, and the initial uranium concentration are all less than 0.001, that is, less than the preset threshold value 0.05. Therefore, it can be determined that the burnup, the cooling time, and the initial uranium concentration have a significant impact on the plutonium content in the spent fuel assembly.

[0114] Meanwhile, for the interaction term (BU*CT) between the burnup and the cooling time, the statistical quantity F value (FBU*CT) corresponding to the interaction term satisfies F BU*CT >>F(42,280)=1.38, and the significance level corresponding to the interaction term is less than 0.01, indicating that the interaction term has a significant impact on the plutonium content in the spent fuel assembly; for the interaction term (BU*IE) between the burnup and the initial uranium concentration, the statistical quantity F value (FBU*IE) corresponding to the interaction term satisfies F BU*IE>> F(42, 294) = 1.38, and the significance level corresponding to this interaction term is less than 0.01, indicating that the influence of this interaction term on the plutonium content in the spent fuel assembly is relatively significant; for the interaction term (IE*CT) between the initial uranium concentration and the cooling time, the F value F of the statistic corresponding to this interaction term IE*CT = 1.002 < F(48, 288) = 1.38, and the significance level corresponding to this interaction term is 0.441, which is greater than the preset threshold of 0.05, indicating that the influence of this interaction term on the plutonium content in the spent fuel assembly is not significant. Therefore, based on the above analysis, the electronic device can use the interaction term between burnup and cooling time and the interaction term between burnup and initial uranium concentration as the interaction terms to be considered in the initial model.

[0115]

[0116] Table 2

[0117] After determining one or more interaction terms that have a significant impact on the plutonium content in the spent fuel assembly, the electronic device can determine a second relationship curve between each interaction term in the one or more interaction terms and the plutonium content. Here, the second relationship curve can also be understood as a fitting model of the relationship between the interaction term and the plutonium content, and the embodiment of the present application does not limit the name of the second relationship curve.

[0118] After determining all the first relationship curves and the second relationship curves, the electronic device can use all the determined relationship curves to construct the initial model, specifically including determining the expression of the initial model. In this way, the constructed initial model can accurately represent the relationship between the plutonium content in the spent fuel assembly and each first factor, as well as the relationship with the interaction terms that have a significant impact.

[0119] In actual application, in step 102, the electronic device uses the multiple sets of sample data to train the initial model, thereby further improving the accuracy of the initial model in analyzing the plutonium content.

[0120] Specifically, in one embodiment, the specific implementation of step 102 may include:

[0121] Using the multiple sets of sample data, based on multiple regression calculation and collinearity processing, adjust the parameters of the initial model.

[0122] In actual application, by adjusting the parameters of the initial model, the analysis accuracy of the initial model can be optimized, and the optimized model is used as the first model. In this way, for the subsequent task of analyzing a certain spent fuel assembly, the relevant device (which may include the electronic device) obtains the first model and uses the first model for analysis, and can accurately obtain the plutonium content in the spent fuel assembly.

[0123] Correspondingly, the embodiment of the present application further provides an analysis method, applied to an electronic device, such as Figure 2 as shown, the method comprises:

[0124] Step 201: obtaining the burnup, initial uranium concentration, cooling time and Cm-244 content corresponding to the spent fuel assembly to be analyzed;

[0125] Step 202: determining the plutonium content corresponding to the spent fuel assembly to be analyzed by using the first model and the burnup, initial uranium concentration, cooling time and Cm-244 content corresponding to the spent fuel assembly to be analyzed, wherein the first model comprises the first model determined by the above model training method.

[0126] Here, in actual application, the electronic device executing the above analysis method can include an electronic device executing the above model training method, or other related electronic devices, and the embodiment of the present application does not limit this.

[0127] In actual application, in step 201, the electronic device executing the above analysis method can obtain the related information capable of representing the spent fuel assembly to be analyzed, i.e., the burnup, initial uranium concentration, cooling time and Cm-244 content corresponding to the spent fuel assembly to be analyzed, by measurement or pre-configuration, and the like, and the embodiment of the present application does not limit this.

[0128] After obtaining the related information capable of representing the spent fuel assembly to be analyzed, in step 202, the electronic device executing the above analysis method analyzes by using the first model, and the accurate plutonium content can be obtained. The process of determining the first model has been described in detail above, and will not be repeated here.

[0129] The embodiments of this application provide a model training method, analysis method, apparatus, related equipment, storage medium, and computer program product. This method acquires multiple sets of sample data and constructs an initial model. Each set of sample data is associated with the burnup, initial uranium concentration, cooling time, curium-244 content, and plutonium content of a spent fuel assembly. The initial model is trained using the multiple sets of sample data to obtain a first model. This first model is used at least to determine the plutonium content of the spent fuel assembly based on its burnup, initial uranium concentration, cooling time, and curium-244 content. The first model obtained through training can be used to accurately determine the plutonium content in the spent fuel assembly. The method also acquires the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed. Using the first model and the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed, the plutonium content of the spent fuel assembly to be analyzed is determined. The first model includes the first model determined by the above-described model training method. In constructing the first model for analyzing plutonium content in spent fuel, in addition to the three factors of burnup, initial uranium concentration, and cooling time corresponding to the spent fuel assembly, the curium-244 content, which characterizes the ability of the fuel assembly to produce curium, was introduced as one of the factors to consider. This allows for a more accurate reflection of the impact of the initial state of the fuel assembly on the plutonium content in the spent fuel assembly, thereby improving the accuracy of plutonium content analysis. Thus, for each spent fuel assembly to be analyzed, the first model, along with the obtained burnup, initial uranium concentration, cooling time, and curium-244 content corresponding to that spent fuel assembly, can be used to accurately analyze the plutonium content in that spent fuel assembly, thereby ensuring a closed-loop balance for nuclear materials.

[0130] The following section provides a more detailed description of this application with reference to application examples.

[0131] This application provides an application example of a method for analyzing plutonium content in spent fuel based on the radionuclide curium-244 equilibrium. This method belongs to the NDA method and incorporates burnup (hereinafter referred to as BU), cooling time (hereinafter referred to as CT), initial uranium concentration (hereinafter referred to as IE), and curium-244 (hereinafter referred to as...) into the analysis. 244 The four dimensions of plutonium (Cm) content are used as a set to characterize spent fuel assemblies. A relationship model between these four dimensions and plutonium (hereinafter referred to as Pu) content (i.e., the first model mentioned above) is constructed for Pu content analysis, thereby improving the accuracy of plutonium content measurement in fast reactor spent fuel. Here, the characterization set of spent fuel assemblies includes the above four dimensions, and the physical properties of spent fuel assemblies include three dimensions. The relationship between the characterization set and the physical properties is a surjective function.

[0132] Specifically, such as Figure 3 As shown, the method may include the following steps:

[0133] Step 301: Obtain nuclide information (i.e., the sample data described above);

[0134] Here, in actual application, the initial composition of the fuel assembly (specifically including the metal fuel) can be obtained (or set) in advance. For example, 650 grams of uranium (hereinafter written as U, including isotopes 235 U and 238 U), 100 grams of zirconium (hereinafter written as Zr), and the remaining 250 grams of fuel composition containing Pu, americium (hereinafter written as Am), and neptunium (hereinafter written as Np) can be contained in every 1 kg of fuel assembly. The specific content is shown in Table 3, in grams.

[0135]

[0136] Table 3

[0137] In actual application, the accumulation and decay of radioactive substances in the fast reactor can be simulated by using the burnup-decay calculation program (i.e., the second model described above) in combination with the liquid metal cooled fast reactor database to calculate the plutonium content and 244 Cm content in the spent fuel assembly after cooling.

[0138] Specifically, a series of simulation data (i.e., the sample data described above) of specific burnup, initial uranium enrichment, and cooling time can be calculated by using the burnup-decay calculation program for the set value range.

[0139] Step 302: Significance analysis;

[0140] Here, in actual application, the significance analysis is performed by comparing the variances corresponding to the three factors BU, CT, and IE and the sum of squared errors (i.e., the difference between the total deviation sum of squares and the conditional deviation), and the analysis result is obtained to test whether the selected three factors for representing the physical characteristics of the spent fuel assembly have a significant impact on the Pu content, i.e., whether the selected three factors are appropriate, and whether the interaction between two of the three factors will have a significant impact on the Pu content. Then, based on the significance analysis result, it is determined that the selected three factors BU, CT, and IE have a significant impact on the Pu content and are suitable for representing the physical characteristics of the spent fuel assembly. At the same time, the interaction between BU and IE and the interaction between BU and CT have a significant impact on the Pu content, and these two interaction terms should be considered in the model construction.

[0141] Step 303: Determine the influence form and value of each factor;

[0142] Here, in actual application, a series of simulation data obtained by using the burnup-decay calculation program is used to determine the influence form and value of each factor BU, CT, IE, 244For each factor of the Cm content, a function expression is determined to indicate the influence mode of each factor on the Pu content. Specifically, a one-factor regression model and an initial value (i.e., an initial parameter of the model) of the influence of each factor on the Pu content can be obtained through a one-factor fitting.

[0143] Step 304: Establishing a model;

[0144] Here, in actual application, a relationship model (i.e., the initial model described above) is determined by using the one-factor regression model corresponding to each factor, considering the interaction terms of BU and IE, and the interaction terms of BU and CT. Exemplarily, the relationship model can be expressed as formula (7) (which can also be understood as an expression of the relationship model):

[0145]

[0146] wherein a represents a parameter corresponding to the BU term, the initial value of which can be determined by the one-factor regression model corresponding to BU; n1 and n2 represent parameters corresponding to the IE term, the initial values of which can be determined by the one-factor regression model corresponding to IE; k1 and k2 represent parameters corresponding to the CT term, the initial values of which can be determined by the one-factor regression model corresponding to CT; d1 and d2 represent parameters corresponding to the Cm content term, the initial values of which can be determined by the one-factor regression model corresponding to Cm content; and s represents a constant term, the initial value of which can be determined by all one-factor regression models. 244 244 244

[0147] m1 and m2 represent parameters corresponding to the interaction terms of BU and IE, the initial values of which can be set to 1; and f1 and f2 represent parameters corresponding to the interaction terms of BU and CT, the initial values of which can be set to 1.

[0148] After the multivariate regression calculation and the processing of the collinearity problem, a final relationship model (i.e., the first model described above, which can also be understood as a regression model) can be obtained, i.e., a trained relationship model, which can be expressed as formula (8):

[0149]

[0150] Step 305: Analyzing the Pu content.

[0151] Here, in actual application, the trained relationship model is used to determine the Pu content in combination with the BU, IE, CT and Cm content corresponding to the spent fuel assembly to be analyzed. 244

[0152] Exemplarily, for different BU, IE, CT and Cm content, the Pu content can be determined by using the trained relationship model. 244 ​​The Cm content is valued, Pu content is calculated by using the ignition consumption decay simulation and the relationship model respectively, the calculation results are obtained, as shown in Table 4, and the accuracy of the relationship model is verified based on the relative error of the two obtained calculation results. Among them, M_Pu represents the Pu content obtained by using the ignition consumption decay simulation, M_Pu_Reg represents the Pu content obtained by using the relationship model, and since the relative error is less than 1%, it can be determined that the established multiple regression model (i.e. the relationship model) can accurately describe 244 The relationship between Cm and Pu, and represent the spent fuel assembly within a certain limit.

[0153]

[0154]

[0155] Table 4

[0156] The scheme provided by the application example is based on 244 The Cm content and the burnup, the initial uranium concentration, and the cooling time, a relationship model is established; and the relationship model is used to analyze the plutonium content, which can improve the accuracy of the spent fuel plutonium content measurement for fast reactors.

[0157] In order to realize the model training method of the embodiments of the application, the embodiments of the application also provide a model training device arranged on an electronic device, as shown in Figure 4 The device comprises:

[0158] The construction unit 401 is configured to obtain a plurality of sets of sample data, and construct an initial model, each set of sample data in the plurality of sets of sample data is associated with the burnup, the initial uranium concentration, the cooling time, the Cm-244 content and the plutonium content corresponding to the spent fuel assembly;

[0159] The training unit 402 is configured to train the initial model by using the plurality of sets of sample data to obtain a first model, the first model is at least used to determine the plutonium content corresponding to the spent fuel assembly based on the burnup, the initial uranium concentration, the cooling time and the Cm-244 content corresponding to the spent fuel assembly.

[0160] In an embodiment, the first factor associated with the plutonium content corresponding to the spent fuel assembly includes the burnup, the initial uranium concentration, the cooling time and the Cm-244 content corresponding to the spent fuel assembly, and the construction unit 401 is specifically configured to:

[0161] determine, for each first factor, a first relationship curve based on the plurality of sets of sample data, the first relationship curve representing a correspondence between the first factor and a plutonium content corresponding to the spent fuel assembly; and determine, for each interaction term of one or more interaction terms, a second relationship curve, the second relationship curve representing a correspondence between the interaction term and the plutonium content corresponding to the spent fuel assembly, the interaction term representing an interaction between two different first factors.

[0162] determine the initial model based on all the determined first relationship curves and second relationship curves.

[0163] In an embodiment, the constructing unit 401 is further configured to:

[0164] perform a significance analysis on all the interaction terms formed between each pair of first factors to obtain an analysis result.

[0165] determine the one or more interaction terms based on the analysis result.

[0166] In an embodiment, the analysis result at least includes a significance level corresponding to each interaction term, and the constructing unit 401 is specifically configured to:

[0167] take, as the one or more interaction terms, interaction terms with a significance level less than a preset threshold among all the interaction terms.

[0168] In an embodiment, the training unit 402 is specifically configured to:

[0169] adjust parameters of the initial model based on multiple regression calculation and collinearity processing based on the plurality of sets of sample data.

[0170] In an embodiment, each set of sample data in the plurality of sets of sample data is associated with a set of values of a second factor, and the second factor includes a burnup of the spent fuel assembly, an initial uranium concentration, and a cooling time, and the constructing unit 401 is specifically configured to:

[0171] determine, for each set of values of the second factor, a content of Cm-244 and a content of Pu in the spent fuel assembly corresponding to the set of values of the second factor based on a second model; and take the set of values of the second factor and the determined content of Cm-244 and the content of Pu as a set of sample data.

[0172] In actual application, the constructing unit 401 can be implemented by a processor in a model training device in combination with a communication interface, and the training unit 402 can be implemented by the processor in the model training device.

[0173] It should be noted that the model training device provided in the above embodiments is only illustrated by the division of the above program units when performing model training, and in actual application, the above processing can be completed by different program units according to needs, that is, the internal structure of the device is divided into different program units to complete all or part of the above-described processing. In addition, the model training device and the model training method provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0174] To implement the analysis method of the embodiments of the present application, the embodiments of the present application also provide an analysis device arranged on an electronic device, as shown in Figure 5 The device includes:

[0175] The acquisition unit 501 is configured to acquire the burnup, the initial uranium concentration, the cooling time and the content of Cm-244 corresponding to the spent fuel assembly to be analyzed.

[0176] The analysis unit 502 is configured to determine the content of Pu corresponding to the spent fuel assembly to be analyzed by using the first model and the burnup, the initial uranium concentration, the cooling time and the content of Cm-244 corresponding to the spent fuel assembly to be analyzed, wherein the first model includes the first model determined by any one of the above model training methods.

[0177] In actual application, the acquisition unit 501 can be realized by a processor in combination with a communication interface in the analysis device, and the analysis unit 502 can be realized by a processor in the analysis device.

[0178] It should be noted that the analysis device provided in the above embodiments is only illustrated by the division of the above program units when performing analysis, and in actual application, the above processing can be completed by different program units according to needs, that is, the internal structure of the device is divided into different program units to complete all or part of the above-described processing. In addition, the analysis device and the analysis method provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0179] Based on the hardware implementation of the above program modules, and in order to implement the model training method of the embodiments of the present application, the embodiments of the present application also provide an electronic device, as shown in Figure 6 The electronic device 600 includes:

[0180] The first communication interface 601 is capable of information interaction with other devices;

[0181] The first processor 602 is connected with the first communication interface 601 to realize information interaction with other devices, and is configured to run a computer program to execute the method provided in one or more of the above technical solutions;

[0182] a first memory 603, wherein the computer program is stored in the first memory 603.

[0183] Specifically, the first processor 602 is configured to: acquire a plurality of sets of sample data by using the first communication interface 601, wherein each set of sample data is associated with burnup, initial uranium concentration, cooling time, Cm-244 content and Pu content corresponding to a spent fuel assembly; and train an initial model by using the plurality of sets of sample data to obtain a first model, wherein the first model is used to determine the Pu content corresponding to the spent fuel assembly based on the burnup, the initial uranium concentration, the cooling time and the Cm-244 content corresponding to the spent fuel assembly.

[0184] In an embodiment, the first factors associated with the Pu content corresponding to the spent fuel assembly include the burnup, the initial uranium concentration, the cooling time and the Cm-244 content corresponding to the spent fuel assembly, and the first processor 602 is specifically configured to:

[0185] determine, based on the plurality of sets of sample data, a first relationship curve for each first factor, wherein the first relationship curve represents a corresponding relationship between the first factor and the Pu content corresponding to the spent fuel assembly; and determine, for each interaction term in one or more interaction terms, a second relationship curve, wherein the second relationship curve represents a corresponding relationship between the interaction term and the Pu content corresponding to the spent fuel assembly, and the interaction term represents an interaction between two different first factors.

[0186] determine the initial model by using all the determined first relationship curves and second relationship curves.

[0187] In an embodiment, the first processor 602 is further configured to:

[0188] perform significance analysis on all the interaction terms formed between two first factors to obtain an analysis result.

[0189] determine the one or more interaction terms by using the analysis result.

[0190] In an embodiment, the analysis result at least includes a significance level corresponding to each interaction term, and the first processor 602 is specifically configured to:

[0191] take, as the one or more interaction terms, an interaction term in all the interaction terms whose significance level is less than a preset threshold.

[0192] In an embodiment, the first processor 602 is specifically configured to:

[0193] adjust parameters of the initial model based on multivariate regression calculation and collinearity processing by using the plurality of sets of sample data.

[0194] In an embodiment, each of the plurality of sets of sample data is associated with a set of values of a second factor, the second factor comprising burnup, initial uranium enrichment, cooling time corresponding to the spent fuel assembly, and the first processor 602 is specifically configured to:

[0195] For each set of values of the second factor, determine, by using a second model, the content of Cm-244 and the content of Pu in the spent fuel assembly corresponding to the set of values of the second factor; and take the set of values of the second factor and the determined content of Cm-244 and the content of Pu as a set of sample data.

[0196] It should be noted that the specific processing procedures of the first processor 602 and the first communication interface 601 can be understood with reference to the above method.

[0197] Of course, in actual application, each component in the electronic device 600 is coupled together through the bus system 604. It can be understood that the bus system 604 is used to realize the connection and communication between the components. In addition to including a data bus, the bus system 604 also includes a power bus, a control bus, and a status signal bus. However, in order to clearly illustrate the application, all kinds of buses are marked as the bus system 604 in the Figure 6

[0198] The first memory 603 in the embodiment of the application is used to store various types of data to support the operation of the electronic device 600. Examples of these data include: any computer programs used for operation on the electronic device 600.

[0199] The method disclosed in the above embodiments of the application can be applied to the first processor 602 or implemented by the first processor 602. The first processor 602 can be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware or the instruction in the form of software in the first processor 602. The first processor 602 described above can be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The first processor 602 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the application. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiments of the application, the hardware decoding processor can be directly embodied to execute the completion, or the combination of hardware and software modules in the decoding processor can be executed to complete. The software module can be located in the storage medium, which is located in the first memory 603, and the first processor 602 reads the information in the first memory 603 and combines the hardware to complete the steps of the above method. ​

[0200] In an exemplary embodiment, the electronic device 600 can be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field-Programmable Gate Arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors (Microprocessors), or other electronic elements for executing the foregoing methods.

[0201] Based on the hardware implementation of the above program modules, and in order to implement the analysis method of the embodiments of the present application, the embodiments of the present application further provide an electronic device, as shown in the figure, which comprises: Figure 7 As shown in the figure, the electronic device 700 comprises:

[0202] a second communication interface 701 capable of information interaction with other devices;

[0203] a second processor 702 connected with the second communication interface 701 to realize information interaction with the electronic device, for running a computer program, and executing the method provided by one or more technical solutions of the above-mentioned electronic device side;

[0204] a second memory 703, wherein the computer program is stored in the second memory 703.

[0205] Specifically, the second communication interface 701 is configured to obtain the burnup, initial uranium concentration, cooling time and Cm-244 content corresponding to the spent fuel assembly to be analyzed.

[0206] The second processor 702 is configured to determine the plutonium content corresponding to the spent fuel assembly to be analyzed by using a first model and the burnup, initial uranium concentration, cooling time and Cm-244 content corresponding to the spent fuel assembly to be analyzed, wherein the first model comprises a first model determined by any of the above model training methods.

[0207] It should be noted that the specific processing process of the second processor 702 and the second communication interface 701 can be understood with reference to the above method.

[0208] Of course, in actual applications, various components in the electronic device 700 are coupled together through the bus system 704. It can be understood that the bus system 704 is used to realize the connection communication between the components. The bus system 704 includes not only a data bus, but also a power supply bus, a control bus, and a status signal bus. However, for the purpose of clear illustration, all the buses are marked as the bus system 704 in the Figure 7

[0209] The second memory 703 in the embodiment of the present application is used to store various types of data to support the operation of the electronic device 700. Examples of the data include any computer programs used for operation on the electronic device 700.

[0210] The method disclosed in the above embodiment of the present application can be applied to the second processor 702 or implemented by the second processor 702. The second processor 702 can be an integrated circuit chip with a signal processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the second processor 702 or the instructions in the form of software. The second processor 702 mentioned above can be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The second processor 702 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiments of the present application, the hardware decoding processor can be directly embodied to execute the completion, or the hardware and software modules in the decoding processor are combined to execute the completion. The software module can be located in the storage medium, which is located in the second memory 703, and the second processor 702 reads the information in the second memory 703 and combines the hardware to complete the steps of the above method.

[0211] In the exemplary embodiments, the electronic device 700 can be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, Microprocessors, or other electronic elements, for executing the above method.

[0212] ​It can be understood that the memory (the first memory 603 and the second memory 703) of the embodiments of the present application can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM). The magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of RAM can be used, such as a static random access memory (SRAM), a synchronous static random access memory (SSRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a sync link dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM).The memory described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable types of memory.

[0213] In the example embodiments, the embodiments of the present application also provide a storage medium, specifically a computer readable storage medium, for example, the first memory 603 storing a computer program executable by the first processor 602 of the electronic device 600 to complete the steps of the aforementioned electronic device 600 side method, and the second memory 703 storing a computer program executable by the second processor 702 of the electronic device 700 to complete the steps of the aforementioned electronic device 700 side method. The computer readable storage medium can be FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM, etc.

[0214] In the example embodiments, the embodiments of the present application also provide a computer program product including a computer program executable by the first processor 602 of the electronic device 600 to complete the steps of the aforementioned sending end side method, or the computer program executable by the second processor 702 of the electronic device 700 to complete the steps of the aforementioned electronic device side method.

[0215] It should be noted that "first", "second", etc. are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0216] In addition, the technical solutions described in the embodiments of the present application can be arbitrarily combined without conflict.

[0217] The above is only a preferred embodiment of the present application, and is not intended to limit the protection scope of the present application.

Claims

1. A model training method, characterized in that, include: Multiple sets of sample data were acquired, and an initial model was constructed. Each set of sample data was associated with the burnup, initial uranium concentration, cooling time, curium-244 content, and plutonium content of the spent fuel assembly. The initial model is trained using the multiple sets of sample data to obtain a first model. The first model is used at least to determine the plutonium content of the spent fuel assembly based on the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly.

2. The method according to claim 1, characterized in that, The first factors associated with the plutonium content of the spent fuel assembly include burnup, initial uranium concentration, cooling time, and curium-244 content. The construction of the initial model includes: Based on the multiple sets of sample data, for each first factor, a first relationship curve is determined, which represents the correspondence between the first factor and the plutonium content corresponding to the spent fuel assembly; and for each interaction term in one or more interaction terms, a second relationship curve is determined, which represents the correspondence between the interaction term and the plutonium content corresponding to the spent fuel assembly, wherein the interaction term represents the interaction between two different first factors; The initial model is determined using all the identified first and second relationship curves.

3. The method according to claim 2, characterized in that, The method further includes: Significance analysis was performed on all interaction terms between each pair of first factors to obtain the analysis results; Using the analysis results, the one or more interaction items are determined.

4. The method according to claim 2, characterized in that, The analysis results include at least the salience level corresponding to each interaction item, and the determination of the one or more interaction items using the analysis results includes: Interactions with a salience level less than a preset threshold are considered as one or more interaction items.

5. The method according to claim 1, characterized in that, The step of training the initial model using the multiple sets of sample data includes: Using the multiple sets of sample data, the parameters of the initial model are adjusted based on multiple regression calculation and collinearity processing.

6. The method according to any one of claims 1 to 5, characterized in that, Each set of sample data in the multiple sets of sample data is associated with a set of values ​​of the second factor, which includes the burnup of the spent fuel assembly, the initial uranium concentration, and the cooling time. Obtaining the multiple sets of sample data includes: For each set of values ​​for the second factor, the second model is used to determine the curium-244 content and plutonium content in the spent fuel assembly corresponding to the value of the second factor; and the value of the second factor and the determined curium-244 content and plutonium content are used as a set of sample data.

7. An analytical method, characterized in that, include: Obtain the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed; Using a first model and the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed, the plutonium content of the spent fuel assembly to be analyzed is determined. The first model includes the first model determined by the method of any one of claims 1 to 6.

8. A model training device, characterized in that, include: A construction unit is used to acquire multiple sets of sample data and construct an initial model. Each set of sample data is associated with the burnup, initial uranium concentration, cooling time, curium-244 content, and plutonium content of the spent fuel assembly. The training unit is used to train the initial model using the multiple sets of sample data to obtain a first model. The first model is used at least to determine the plutonium content of the spent fuel assembly based on the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly.

9. An analytical apparatus, characterized in that, include: The acquisition unit is used to acquire the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed. An analysis unit is used to determine the plutonium content of the spent fuel assembly to be analyzed by using a first model and the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed. The first model includes a first model determined by the method of any one of claims 1 to 6.

10. An electronic device, characterized in that, include: A first communication interface and a first processor; wherein... The first processor is configured to acquire multiple sets of sample data through the first communication interface and construct an initial model, wherein each set of sample data is associated with the burnup, initial uranium concentration, cooling time, curium-244 content, and plutonium content of the spent fuel assembly; and to train the initial model using the multiple sets of sample data to obtain a first model, wherein the first model is at least used to determine the plutonium content of the spent fuel assembly based on the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly.

11. An electronic device, characterized in that, include: The second communication interface is used to obtain the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed. The second processor is used to determine the plutonium content of the spent fuel assembly to be analyzed by using the first model and the burnup, initial uranium concentration, cooling time, and curium-244 content of the spent fuel assembly to be analyzed. The first model includes the first model determined by the method of any one of claims 1 to 6.

12. An electronic device, characterized in that, include: A first processor and a first memory for storing computer programs capable of running on the processor. Wherein, when the first processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 6.

13. An electronic device, characterized in that, include: A second processor and a second memory for storing computer programs that can run on the processor. Wherein, when the second processor is used to run the computer program, it executes the steps of the method of claim 7.

14. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6, or the steps of the method according to claim 7.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6, or the steps of the method according to claim 7.

Images