Nickel-based alloy element spectrum library construction method, device, equipment and medium

Abstract

The invention relates to the technical field of energy spectrum measurement, particularly provides a nickel-based alloy element spectrum library construction method and device, equipment and a medium, and aims to solve the technical problem of low accuracy of a library spectrum obtained by an existing method. In order to achieve the purpose, the construction method of the nickel-based alloy element spectrum library comprises the steps that a target sample of a nickel-based alloy is obtained; performing a simulation experiment on the target sample to obtain a first simulation spectrum; performing an actual measurement experiment on the target sample to obtain an experiment spectrum; correcting the first simulation spectrum by using the experiment spectrum to obtain a second simulation spectrum; and constructing a nickel-based alloy element spectrum library based on the second simulation spectrum and the experiment spectrum. The Monte Carlo simulation is combined with the actual measurement experiment, and the first simulation spectrum is corrected by using the experiment spectrum, so that the more accurate second simulation spectrum can be obtained, and the accuracy of the spectrum library is improved.

Description

Technical Field

[0001] The invention relates to the technical field of energy spectrum measurement, and specifically provides a method, device, equipment and medium for constructing a nickel-based alloy element spectrum library. Background Art

[0002] Prompt gamma-ray neutron activation analysis (PGNAA) is an important means of industrial online material composition analysis. It uses neutron beam to act on the material to be tested to produce (n, γ) activation reaction, records the gamma energy spectrum through the detector, and combines spectrum analysis software to perform qualitative and quantitative detection of material composition. The spectral library plays a key role in PGNAA detection. It provides the single-element gamma-ray energy spectrum of each element in the sample to be tested, and provides basic data for the spectrum solution software to solve the overdetermined equation through the least squares method. Its accuracy and completeness are crucial to ensure the reliability of the analysis results of the PGNAA method.

[0003] Different spectral libraries need to be produced for different fields and different detection equipment. However, most of the current spectral libraries are designed and constructed mainly for application fields such as coal, cement, metallurgy, soil and other large-volume samples. There is currently no elemental spectral library suitable for small-volume metal samples in the field of nickel-based alloy detection. At the same time, the traditional method of obtaining spectral libraries through manual experiments has problems such as long experimental cycle, incomplete coverage, and high sample cost. Monte Carlo simulation fails to fully consider the response functions of different detectors and cannot give completely consistent results for all different models and types of electronic systems. Summary of the invention

[0004] In order to overcome the above defects, the present application is proposed to provide a solution or at least partially solve the technical problem of low accuracy of library spectra obtained by existing methods. The present application provides a method, device, equipment and medium for constructing a nickel-based alloy elemental library.

[0005] In a first aspect, the present application provides a method for constructing a nickel-based alloy element spectral library, the method comprising:

[0006] Obtaining a target sample of a nickel-based alloy;

[0007] Performing a simulation experiment on the target sample to obtain a first simulation spectrum;

[0008] Performing an actual measurement experiment on the target sample to obtain an experimental spectrum;

[0009] Correcting the first simulation spectrum using the experimental spectrum to obtain a second simulation spectrum;

[0010] The nickel-based alloy element spectrum library is constructed based on the second simulated spectrum and the experimental spectrum.

[0011] In one embodiment of the present application, obtaining a target sample of a nickel-based alloy includes: superimposing a preset number of nickel-based alloy samples to obtain the target sample of the nickel-based alloy, wherein the nickel-based alloy sample contains a preset number of target elements, and the nickel-based alloy sample is composed of the target elements.

[0012] In one embodiment of the present application, using the experimental spectrum to correct the first simulation spectrum includes:

[0013] Obtaining a first Gaussian broadening parameter corresponding to the experimental spectrum;

[0014] Determining preset parameters based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameter;

[0015] The first simulation spectrum is modified based on the preset parameters.

[0016] In one embodiment of the present application, determining the preset parameters based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameter includes:

[0017] Acquire a second Gaussian broadening parameter based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameter;

[0018] Determining the half-width based on the second Gaussian broadening parameter;

[0019] The preset parameter is determined based on the half-width.

[0020] In one embodiment of the present application, the obtaining of the second Gaussian broadening parameter based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameter includes:

[0021] Get pre-built deep neural network models;

[0022] Inputting the experimental spectrum and the first simulated spectrum into the deep neural network model respectively to obtain a first eigenvector corresponding to the experimental spectrum and a second eigenvector corresponding to the first simulated spectrum;

[0023] Calculating the similarity between the first feature vector and the second feature vector;

[0024] Obtaining a weight corresponding to the target sample based on the similarity;

[0025] The second Gaussian stretching parameter is determined based on the weight and the first Gaussian stretching parameter.

[0026] In one embodiment of the present application, obtaining the weight corresponding to the target sample based on the similarity includes:

[0027] Calculating the function value corresponding to the similarity using a normalized exponential function;

[0028] The function value is used as the weight corresponding to the target sample.

[0029] In one embodiment of the present application, the modifying the first simulation spectrum based on the preset parameters includes:

[0030] Obtaining Gaussian function values ​​corresponding to the preset parameters;

[0031] The discrete points in the first simulated spectrum are replaced with the Gaussian function values.

[0032] In a second aspect, a device for constructing a nickel-based alloy element spectral library is provided, the device comprising:

[0033] An acquisition module, wherein the acquisition module is configured to acquire a target sample of a nickel-based alloy;

[0034] A simulation experiment module, wherein the simulation experiment module is configured to perform a Monte Carlo simulation experiment on the target sample to obtain a first simulation spectrum;

[0035] A measurement experiment module, wherein the measurement experiment module is configured to perform an actual measurement experiment on the target sample to obtain an experimental spectrum;

[0036] a correction module, wherein the correction module is configured to correct the first simulation spectrum using the experimental spectrum to obtain a second simulation spectrum;

[0037] A building module is configured to build the nickel-based alloy element spectrum library based on the second simulation spectrum and the experimental spectrum.

[0038] In a third aspect, an electronic device is provided, comprising:

[0039] at least one processor;

[0040] and, a memory communicatively coupled to the at least one processor;

[0041] Wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the aforementioned method for constructing a nickel-based alloy element spectral library is implemented.

[0042] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, wherein the program codes are suitable for being loaded and run by a processor to execute any of the aforementioned methods for constructing a nickel-based alloy elemental spectral library.

[0043] The above one or more technical solutions of the present application have at least one or more of the following beneficial effects:

[0044] The method for constructing a nickel-based alloy element spectrum library in the present application includes: obtaining a target sample of the nickel-based alloy; performing a simulation experiment on the target sample to obtain a first simulation spectrum; performing an actual measurement experiment on the target sample to obtain an experimental spectrum; using the experimental spectrum to correct the first simulation spectrum to obtain a second simulation spectrum; and constructing a nickel-based alloy element spectrum library based on the second simulation spectrum and the experimental spectrum. By combining the Monte Carlo simulation with the actual measurement experiment and correcting the first simulation spectrum with the experimental spectrum, a more accurate second simulation spectrum can be obtained, which improves the accuracy of the spectrum library and enables the spectrum library to more truly reflect the characteristics of the actual sample. Correcting the first simulation spectrum by the experimental spectrum makes the simulation results closer to the actual measurement results, improves the consistency between the simulation and the experiment, and ensures the reliability and validity of the data in the spectrum library. The constructed spectrum library contains the corrected second simulation spectrum and experimental spectrum, covering a wider range of composition and energy range, and enhancing the practicality of the spectrum library. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The disclosure of the present application will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present application. In addition, similar numbers in the drawings are used to represent similar components, among which:

[0046] Figure 1 It is a schematic diagram of the main process of the method for constructing a nickel-based alloy element spectral library in one embodiment of the present application;

[0047] Figure 2 is a schematic diagram of a target sample in one embodiment of the present application;

[0048] Figure 3 and Figure 4 It is a complete flow chart of a method for constructing a nickel-based alloy element library in one embodiment of the present application;

[0049] Figure 5 is a schematic diagram of a Monte Carlo simulation spectrum in one embodiment of the present application;

[0050] Figure 6 is a schematic diagram of an experimental spectrum in one embodiment of the present application;

[0051] Figure 7 This is a schematic diagram of the main structure of a device for constructing a nickel-based alloy element library in one embodiment of the present application;

[0052] Figure 8 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0053] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.

[0054] In the description of the present application, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, memory, and may also include software parts, such as program code, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program code, such as a disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B" and may include only A, only B or A and B. The singular terms "one" and "the" may also include plural forms.

[0055] Currently, there is no elemental spectral library suitable for small-volume metal samples in the field of nickel-based alloy detection. At the same time, the traditional method of obtaining spectral libraries through manual experiments has problems such as long experimental cycle, incomplete coverage, and high sample cost. Monte Carlo simulation fails to fully consider the response functions of different detectors and cannot give completely consistent results for all different models and types of electronic systems.

[0056] To this end, the present application proposes a method, device, equipment and medium for constructing a nickel-based alloy element library.

[0057] See attached Figure 1 , Figure 1 It is a schematic flow chart of the main steps of a method for constructing a nickel-based alloy elemental library according to an embodiment of the present application.

[0058] like Figure 1 As shown, the method for constructing a nickel-based alloy element library in the embodiment of the present application mainly includes the following steps S10 to S50.

[0059] Step S10: Obtain a target sample of nickel-based alloy.

[0060] The target sample is a new sample formed by stacking together a plurality of nickel-based alloy samples containing a preset amount of the target element.

[0061] In a specific embodiment of the present application, obtaining a target sample of a nickel-based alloy includes: superimposing a preset number of nickel-based alloy samples to obtain the target sample of the nickel-based alloy, wherein the nickel-based alloy sample contains a preset number of target elements, and the nickel-based alloy sample is composed of the target elements.

[0062] The preset number may be a pre-set number, which may be adaptively adjusted according to the actual usage scenario, and is not specifically limited to this.

[0063] Specifically, a plurality of nickel-based alloy samples are superimposed to form a new sample, and these nickel-based alloy samples contain a predetermined amount of target elements (such as Al, Co, Cr, etc.).

[0064] For example, in view of the high price of standard samples in nickel-based alloy testing and the insignificant (n,γ) effect caused by small sample volume, three samples are placed in a group as target samples, such as Figure 2 As shown in the figure, the volume of the target sample is considered to be three times the original volume, and the composition is equivalent to the average value of the original three sample components. In this way, the volume of the test sample is increased, and more experimental sample components can be obtained according to different combination methods, thereby reducing the number of standard samples and reducing the cost of library preparation.

[0065] Step S20: performing a Monte Carlo simulation experiment on the target sample to obtain a first simulation spectrum.

[0066] Specifically, first select a suitable Monte Carlo simulation software, such as MCNP (Monte Carlo N-ParticleTransport Code System), GEANT4, etc. Then input the geometric dimensions, material composition (including element types and contents) and other necessary physical parameters of the target sample, define the type of particle source (such as neutrons, gamma rays, etc.), energy distribution, emission direction, etc., and define the boundary conditions of the simulation domain, such as reflection boundary or absorption boundary, start the Monte Carlo simulation program, let it run according to the input parameters, and record all output data, especially gamma spectrum data. Finally, format the output gamma spectrum data into a form that is easy to analyze, and obtain the energy spectrum (i.e., the first simulation spectrum). Specifically, the energy spectrum is a graphical representation of the signal output by the gamma-ray detector after processing. In the energy spectrum, each channel address corresponds to a signal count, and the count represents the number of gamma-ray signals detected at the channel address (i.e., the energy channel). Therefore, the energy spectrum is actually a two-dimensional graph with the channel address as the horizontal coordinate and the signal count as the vertical coordinate.

[0067] Step S30: Performing an actual measurement experiment on the target sample to obtain an experimental spectrum.

[0068] Specifically, first select the appropriate detector type based on the experimental requirements and the characteristics of the target sample. For example, for the (n,γ) signal generated by the interaction between neutrons and samples, a highly sensitive γ-ray detector may be required. Parameters such as the intensity, energy distribution, and irradiation time of the neutron source can also be set to control the conditions for the interaction between neutrons and samples. Parameters such as the type, shape, size, and placement of the sample can also be set to ensure the consistency and repeatability of the experiment.

[0069] The detector can be fixed in place, calibrated and debugged according to the design requirements. The sample is placed in front of the detector or near the neutron source to ensure that the neutrons can fully interact with the sample. The detector is connected to the data acquisition system to ensure that the signal can be accurately transmitted and recorded.

[0070] After ensuring that all equipment is ready, start the neutron source and begin the experiment. Closely monitor the experimental process, observe the response of the detector and the real-time changes of the experimental data. Use the data acquisition system to record the experimental data such as the (n,γ) signal generated by the interaction between neutrons and samples, and finally make an experimental spectrum based on the experimental data.

[0071] Step S40: Correct the first simulated spectrum using the experimental spectrum to obtain a second simulated spectrum.

[0072] Step S50: constructing a nickel-based alloy element spectrum library based on the second simulation spectrum and the experimental spectrum.

[0073] Specifically, the final γ spectrum data (including the second simulation spectrum and the experimental spectrum) can actually be stored in a preset format to obtain a final nickel-based alloy element spectrum library. For example, the preset format can be an Excel format.

[0074] Based on the above steps S10 to S50, by combining the Monte Carlo simulation with the actual measurement experiment, and using the experimental spectrum to correct the first simulated spectrum, a more accurate second simulated spectrum can be obtained, which improves the accuracy of the spectral library and enables the spectral library to more truly reflect the characteristics of the actual sample. By correcting the first simulated spectrum with the experimental spectrum, the simulation results are closer to the actual measurement results, the consistency between the simulation and the experiment is improved, and the reliability and validity of the data in the spectral library are ensured. The constructed spectral library contains the corrected second simulated spectrum and the experimental spectrum, covering a wider range of components and energy ranges, and enhancing the practicality of the spectral library.

[0075] The above step S40 is further explained below.

[0076] Specifically, step S40 can be implemented through the following steps S401 to S402.

[0077] Step S401: Obtain the first Gaussian broadening parameter corresponding to the experimental spectrum.

[0078] Specifically, for the experimental spectrum obtained by experimental measurement, a peak detection algorithm (such as CWT continuous wavelet transform, derivative-based method, etc.) is used to identify each peak in the experimental spectrum, and the position (energy value) and intensity (count value) of each peak are recorded. For each identified peak, a Gaussian function is used for fitting to obtain the standard deviation A1 of the Gaussian function. The form of the Gaussian function is:

[0079] Where E0 is the peak position, A1 is the standard deviation of the Gaussian function, and C is the normalization constant.

[0080] For each fitted Gaussian peak, calculate its half-maximum width (FWHM). FWHM can be calculated by the following formula:

[0081] Since the Gaussian broadening model is in the form of:

[0082] Where E is the energy value, a1, b1, c1 are the first Gaussian broadening parameters.

[0083] Specifically, a nonlinear regression method (such as the least squares method) can be used to fit the data set to find the best a1, b1, and c1. For example, the best a1, b1, and c1 can be obtained through a scientific computing library in a programming language (such as Python's scipy.optimize.curve_fit), that is, the first Gaussian broadening parameter is obtained, that is, the first Gaussian broadening parameter is obtained based on the experimental spectrum.

[0084] Step S402: determining preset parameters based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameters.

[0085] The preset parameter refers to the standard deviation A2 of the Gaussian function obtained by calculating the half-height width.

[0086] Specifically, step S402 can be implemented through steps S4021 to S4023.

[0087] Step S4021: obtaining a second Gaussian broadening parameter based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameter.

[0088] Specifically, step S4021 can be implemented through the following steps S40211 to S40215.

[0089] Step S40211: Obtain a pre-built deep neural network model.

[0090] Specifically, a deep neural network model can be designed to extract key features of the gamma energy spectrum. For example, the deep neural network model can be a convolutional neural network CNN, but is not limited thereto.

[0091] The goal of the deep neural network model is to convert each spectral line into a feature vector of fixed length. Specifically, the deep neural network model can be trained using data from the historical dataset. During the training process, a contrast loss function (such as Triplet Loss or Contrastive Loss) can be used to ensure that the embedding vectors of similar samples are closer, while the embedding vectors of dissimilar samples are farther apart.

[0092] Step S40212: input the experimental spectrum and the first simulated spectrum into the deep neural network model respectively to obtain a first eigenvector corresponding to the experimental spectrum and a second eigenvector corresponding to the first simulated spectrum.

[0093] Specifically, the experimental spectrum and the first simulated spectrum are respectively input into the deep neural network model, and the deep neural network extracts the feature vectors corresponding to the experimental spectrum and the first simulated spectrum, and obtains the first feature vector corresponding to the experimental spectrum and the second feature vector corresponding to the first simulated spectrum. Exemplarily, the first feature vector can be recorded as a query vector Q, the second feature vector can be recorded as a key vector K, and the first Gaussian broadening parameter corresponding to each experimental spectrum can be recorded as a value vector V.

[0094] Step S40213: Calculate the similarity between the first feature vector and the second feature vector.

[0095] Specifically, the similarity between the first eigenvector and the second eigenvector can be calculated using the following formula:

[0096] Among them, K T is the transposed vector of the key vector K, d k is the dimension of the key vector and query vector.

[0097] Step S40214: Obtain the weight corresponding to the target sample based on the similarity.

[0098] In a specific implementation of the present application, obtaining the weight corresponding to the target sample based on the similarity includes: calculating the function value corresponding to the similarity using a normalized exponential function; and using the function value as the weight corresponding to the target sample.

[0099] Specifically, the function value corresponding to each target sample can be calculated by the following normalized exponential function, and the function value is used as the weight weights of the target sample. weights = softmax(scores)

[0100] Specifically, the similarity can be converted into weights through the softmax function.

[0101] Step S40215: Determine the second Gaussian stretch parameter (a2, b2, c2) based on the weight and the first Gaussian stretch parameter.

[0102] Specifically, by performing weighted summation on the first Gaussian broadening parameter V using the calculated weight, the final second Gaussian broadening parameter is obtained, and the calculation formula may be: Output=weight×V

[0103] Step S4022: Determine the half-width based on the second Gaussian stretch parameter.

[0104] Specifically, the second Gaussian broadening parameter is inserted into The half-maximum width FWHM2 is calculated.

[0105] Step S4023: Determine preset parameters based on the half-width.

[0106] Specifically, the preset parameters are further determined by the following formula:

[0107] Step S403: modifying the first simulation spectrum based on preset parameters.

[0108] Specifically, step S403 can be implemented by the following steps S4031 to S4032:

[0109] Step S4031: Obtain the Gaussian function value corresponding to the preset parameters.

[0110] Specifically, bring A2 into Get the Gaussian function value corresponding to the preset parameters.

[0111] Step S4032: Use Gaussian function values ​​to replace discrete points in the first simulation spectrum.

[0112] Finally, all discrete points in the first simulated spectrum can be replaced by Gaussian function values ​​at corresponding positions, thereby obtaining a modified second simulated spectrum.

[0113] In a specific embodiment of the present application, the method for constructing the nickel-based alloy element library can be as follows: Figure 3 and Figure 4 shown.

[0114] First, the macroscopic gradient section is used to determine the construction scheme of the spectral library. Take the construction of the spectral library of the Co element as an example. For example, the Co content in the nickel-based alloy sample that constitutes the Co element can contain 0.1%, 0.2%, 0.3%, etc. The so-called construction of the spectral library according to the gradient change of the macroscopic section is to construct the spectral library according to the gradient change law for the target element in the nickel-based alloy sample.

[0115] Then, the three samples are superimposed as target samples, so that multiple target samples can be obtained, and Monte Carlo simulation experiments are performed on the multiple target samples to obtain the first simulation spectrum. And actual measurement experiments are performed on the target samples to obtain experimental spectra.

[0116] Then, the first simulation spectrum is corrected by using the experimental spectrum to obtain the second simulation spectrum. In addition, during the correction process, part of the first simulation spectrum and the experimental spectrum can be used as a support set for correction, and the other part of the first simulation spectrum can be used as a verification set for final verification.

[0117] Finally, the corrected first simulation spectrum and experimental spectrum are stored in a specified location according to a preset format, thereby obtaining an element spectrum library for the nickel-based alloy sample.

[0118] For example, taking the detection object DD6 nickel-based alloy as an example, a spectral library is constructed for the main elements Al, Co, Cr, Mo, Nb, Ta, Ti, and W therein, wherein the main element composition range of the DD6 nickel-based alloy is shown in Table 1 below. Table 1 Data range of several elements to be tested in DD6 alloy

[0119] Based on the macro-gradient cross-section method, the sample data required to construct the spectral library are shown in Table 2 below. Table 2 DD6 alloy library construction plan

[0120] A model of the detection system is established in the MCNP software to perform a Monte Carlo simulation experiment on the target sample. For example, the Monte Carlo simulation spectrum obtained can be as follows Figure 5 shown.

[0121] Using several types of alloys, IARM-NiH214-18, IARM-Ni256Mo-18, IARM-68E, MBH-215X HC2 K, MBH-215XHC5 V, IARM-Ni718-20, IARM-Ni909-18, IARM-Ni282-18, IARM-57E, and IARM-287A, they are numbered 1-10 in sequence, and three of them form a target sample, for example, they can be (8,9,10), (7,8,10), (6,8,10), (6,7,9), (3,7,9), (1,4,10), (1,2,8), (2,3,6), (2,9,10), (1,7,8), (1,2,7), (3,9,10), (1,7,10), and the energy spectrum of each combination sample is measured in turn, and the following can be obtained: Figure 6 Experimental spectra shown.

[0122] The Monte Carlo simulation spectrum can be further modified using the deep neural network model and the experimental spectrum to obtain a modified Monte Carlo simulation spectrum. Finally, the element spectrum library of DD6 nickel-based alloy is constructed using the modified Monte Carlo simulation spectrum and the experimental spectrum.

[0123] The present application is a novel nickel-based alloy element spectral library construction method based on the combination of Monte Carlo simulation spectrum and experimental spectrum. According to the actual needs of users, the nickel-based alloy element spectral library can be constructed efficiently and accurately, which greatly reduces the cycle of manual experiments and the cost of purchasing experimental samples in the spectral library construction process, makes up for the problem that the Monte Carlo simulation spectral library does not fully consider the detector response function, and improves the efficiency and accuracy of spectral library construction.

[0124] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effect of the present application, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present application.

[0125] Furthermore, the present application also provides a device for constructing a nickel-based alloy element spectral library.

[0126] See attached Figure 7 , Figure 7 It is a main structural block diagram of a device for constructing a nickel-based alloy elemental library according to an embodiment of the present application.

[0127] like Figure 7As shown, the nickel-based alloy element library construction device in the embodiment of the present application mainly includes an acquisition module 11, a simulation experiment module 12, a measurement experiment module 13, a correction module 14 and a construction module 15. In some embodiments, one or more of the acquisition module 11, the simulation experiment module 12, the measurement experiment module 13, the correction module 14 and the construction module 15 can be combined into one module.

[0128] In some embodiments, the acquisition module 11 may be configured to acquire a target sample of a nickel-based alloy.

[0129] The simulation experiment module 12 may be configured to perform a Monte Carlo simulation experiment on the target sample to obtain a first simulation spectrum.

[0130] The measurement experiment module 13 may be configured to perform an actual measurement experiment on the target sample to obtain an experimental spectrum.

[0131] The correction module 14 may be configured to correct the first simulation spectrum using the experimental spectrum to obtain a second simulation spectrum.

[0132] The construction module 15 may be configured to construct the nickel-based alloy element spectrum library based on the second simulation spectrum and the experimental spectrum.

[0133] In one implementation, the description of the specific implementation functions can refer to steps S10-S50.

[0134] The nickel-based alloy element library construction device is used to execute Figure 1 The embodiment of the method for constructing a nickel-based alloy element spectrum library shown in the figure has similar technical principles, technical problems solved and technical effects produced. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the device for constructing a nickel-based alloy element spectrum library can refer to the contents described in the embodiment of the method for constructing a nickel-based alloy element spectrum library, which will not be repeated here.

[0135] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present application, the physical devices corresponding to these modules may be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only schematic.

[0136] It is understood by those skilled in the art that each module in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present application, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present application.

[0137] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above-mentioned embodiment of the present application can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code.

[0138] Furthermore, the present application also provides an electronic device, which may include at least one processor; and a memory connected to the at least one processor in communication; wherein a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method for constructing a nickel-based alloy elemental library described in any of the above embodiments is implemented. Figure 8 As shown, Figure 8 exemplarily shows the structure of an electronic device, which includes a processor 100 and a memory 200.

[0139] Further, the present application also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present application, the computer-readable storage medium can be configured to store a program for executing the nickel-based alloy element library construction method of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned nickel-based alloy element library construction method. For ease of explanation, only the parts related to the embodiments of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-temporary computer-readable storage medium.

[0140] So far, the technical solutions of the present application have been described in conjunction with the specific implementations shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific implementations. Without departing from the principles of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present application.

Claims

1. A method for constructing a nickel-based alloy element library, characterized in that: The method comprises: Obtaining a target sample of a nickel-based alloy; Performing a simulation experiment on the target sample to obtain a first simulation spectrum; Performing an actual measurement experiment on the target sample to obtain an experimental spectrum; Correcting the first simulation spectrum using the experimental spectrum to obtain a second simulation spectrum; The nickel-based alloy element spectrum library is constructed based on the second simulated spectrum and the experimental spectrum.

2. The method for constructing a nickel-based alloy element library according to claim 1, characterized in that: The method of obtaining a target sample of the nickel-based alloy comprises: stacking a preset number of nickel-based alloy samples to obtain the target sample of the nickel-based alloy, wherein the nickel-based alloy sample contains a preset number of target elements, and the nickel-based alloy sample is composed of the target elements.

3. The method for constructing a nickel-based alloy element library according to claim 1, characterized in that: Correcting the first simulation spectrum using the experimental spectrum includes: Obtaining a first Gaussian broadening parameter corresponding to the experimental spectrum; Determining preset parameters based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameter; The first simulation spectrum is modified based on the preset parameters.

4. The method for constructing a nickel-based alloy element library according to claim 3, characterized in that: The step of determining the preset parameters based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameter comprises: Acquire a second Gaussian broadening parameter based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameter; Determining the half-width based on the second Gaussian broadening parameter; The preset parameter is determined based on the half-width.

5. The method for constructing a nickel-based alloy element library according to claim 4, characterized in that: The obtaining a second Gaussian broadening parameter based on the experimental spectrum, the first simulation spectrum and the first Gaussian broadening parameter comprises: Get pre-built deep neural network models; Inputting the experimental spectrum and the first simulated spectrum into the deep neural network model respectively to obtain a first eigenvector corresponding to the experimental spectrum and a second eigenvector corresponding to the first simulated spectrum; Calculating the similarity between the first feature vector and the second feature vector; Obtaining a weight corresponding to the target sample based on the similarity; The second Gaussian stretching parameter is determined based on the weight and the first Gaussian stretching parameter.

6. The method for constructing a nickel-based alloy element library according to claim 5, characterized in that: The obtaining the weight corresponding to the target sample based on the similarity includes: Calculating the function value corresponding to the similarity using a normalized exponential function; The function value is used as the weight corresponding to the target sample.

7. The method for constructing a nickel-based alloy element library according to claim 3, characterized in that: The modifying the first simulation spectrum based on the preset parameters includes: Obtaining Gaussian function values ​​corresponding to the preset parameters; The discrete points in the first simulated spectrum are replaced with the Gaussian function values.

8. A device for constructing a nickel-based alloy element library, characterized in that: The device comprises: An acquisition module, wherein the acquisition module is configured to acquire a target sample of a nickel-based alloy; A simulation experiment module, wherein the simulation experiment module is configured to perform a Monte Carlo simulation experiment on the target sample to obtain a first simulation spectrum; A measurement experiment module, wherein the measurement experiment module is configured to perform an actual measurement experiment on the target sample to obtain an experimental spectrum; a correction module, wherein the correction module is configured to correct the first simulation spectrum using the experimental spectrum to obtain a second simulation spectrum; A building module is configured to build the nickel-based alloy element spectrum library based on the second simulation spectrum and the experimental spectrum.

9. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method for constructing a nickel-based alloy element spectral library according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the method for constructing a nickel-based alloy element spectrum library according to any one of claims 1 to 7.

Images