A copper alloy grade identification method, device and equipment
Patent Information
- Application Number
- CN202611211185.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-10
- Publication Date
- 2026-11-03
AI Technical Summary
In the current copper alloy production field, the identification efficiency of copper alloy grades is low and the accuracy is poor, resulting in high material recycling and processing costs, and there is a lack of automated identification methods.
A database of copper alloy standard samples was constructed. By combining X-ray fluorescence characteristic curves and elemental ratios with fuzzy membership functions and genetic algorithms, the automatic identification of copper alloy grades in the material flow was achieved. High-speed XRF acquisition equipment, vibrating feeders, and flow guiding devices were used for preprocessing to ensure accurate signal acquisition.
It enables rapid and accurate differentiation of copper alloy grades, reduces reliance on manual labor, improves identification efficiency, and is suitable for recycled copper recovery and copper alloy processing pretreatment, with sorting purity increased to over 98%.
Smart Images
Figure CN123033622A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of alloy testing technology, and in particular to a method, apparatus and equipment for identifying copper alloy grades. Background Technology
[0002] In the field of copper alloy recycling, precise differentiation of different grades of materials is crucial to reduce the costs of subsequent material recycling processes. Ensuring accurate recycling of materials of the same grade conserves metal resources and reduces production costs is essential. Currently, most copper alloy production processes using recycled copper for recasting rely on manual methods, employing handheld X-ray fluorescence (XRF) instruments to identify and classify each piece of recycled copper. This method, while ensuring accurate recycling of copper alloy grades, is inefficient and lacks accuracy. Summary of the Invention
[0003] The purpose of this application is to provide a method, apparatus, and equipment for identifying copper alloy grades, which can improve the efficiency of copper alloy grade identification.
[0004] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a method for identifying copper alloy grades, including: A database of copper alloy standard samples was constructed; each data entry in the database includes the grade, X-ray fluorescence characteristic curve, and elemental composition. The X-ray fluorescence signals of each material in the material flow are acquired and converted into data to be analyzed; the data to be analyzed is the X-ray fluorescence characteristic curve to be analyzed. The similarity between the data to be analyzed and each data entry in the copper alloy standard sample database is calculated. Based on the similarity of each data point, the copper alloy grade of the corresponding material is determined.
[0005] Optionally, a database of copper alloy standard samples is constructed, specifically including: Obtain copper alloy standard samples of various grades; X-ray fluorescence characteristic curves of each copper alloy standard sample were collected; Calculate the elemental composition of each copper alloy standard sample based on the characteristic curves of each X-ray fluorescence. The copper alloy standard sample database is constructed by using the grade, X-ray fluorescence characteristic curve, and elemental ratio of each copper alloy standard sample.
[0006] Optionally, the elements in the element ratio include major elements, trace elements, and micro-elements.
[0007] Optionally, based on the characteristic X-ray fluorescence curves, the elemental composition of each copper alloy standard sample is calculated, specifically including: Based on the intensity of the characteristic peaks in each X-ray fluorescence characteristic curve, the elemental ratio of the major elements in the corresponding copper alloy standard sample is calculated using the calibration curve method. The feature matrix, including linear and nonlinear principal components, was extracted from each X-ray fluorescence characteristic curve through two-stage principal component analysis. The feature matrix is input into the element ratio prediction module to obtain the element ratio of trace elements and minor elements of the corresponding copper alloy standard sample; the element ratio prediction module is obtained by training a width learning system.
[0008] Optionally, based on the intensity of the characteristic peaks in each X-ray fluorescence characteristic curve, the elemental composition of the major elements in the corresponding copper alloy standard sample is calculated using the calibration curve method, specifically including: Based on the known linear regression relationship between characteristic peak intensity and element content, the element content is determined by the characteristic peak intensity in the X-ray fluorescence characteristic curve, and the element ratio is determined based on the content of each element.
[0009] Optionally, a feature matrix, including linear and nonlinear principal components, is extracted from each X-ray fluorescence characteristic curve through two-stage principal component analysis, specifically including: Linear principal components were extracted from the X-ray fluorescence characteristic curves through the first-stage principal component analysis. The nonlinear component is calculated based on the relationship between the linear principal components and the element content. Nonlinear principal components are extracted from the nonlinear part through principal component analysis in the second stage.
[0010] Optionally, the similarity calculation is performed between the data to be analyzed and each data entry in the copper alloy standard sample database, specifically including: A data fitting strategy combining fuzzy membership function and genetic algorithm is adopted to calculate the similarity between the data to be analyzed and each data in the copper alloy standard sample database.
[0011] Optionally, a data fitting strategy combining fuzzy membership functions and genetic algorithms is employed to calculate the similarity between the data to be analyzed and each data entry in the copper alloy standard sample database, specifically including: The population is initialized based on the data to be analyzed. The initialized population includes N individuals with real-number encodings. Each individual includes a set of optimization parameters for the data to be analyzed, where N is a positive integer. Based on the initial population, with the goal of maximizing the membership degree of the data to be analyzed, a genetic algorithm is used to determine the similarity between the data to be analyzed and each data item; wherein, in each iteration of the genetic algorithm, a weighted fuzzy membership function constructed by a Gaussian membership function is used to calculate the membership degree of the data to be analyzed to each data item.
[0012] Secondly, this application provides a copper alloy grade identification device, including an X-ray fluorescence acquisition device, a vibrating feeder, a flow guiding device, and a copper alloy grade identification module; The vibrating feeder is used to uniformly transfer each material in the material flow to the guiding device. The flow guiding device is used to guide each material to the collection area of the X-ray fluorescence acquisition device; The X-ray fluorescence acquisition device is used to acquire X-ray fluorescence signals of various materials; The copper alloy grade identification module is used to receive the X-ray fluorescence signals of each material collected by the X-ray fluorescence acquisition device, and to determine the copper alloy grade of each material using the copper alloy grade identification method.
[0013] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the copper alloy grade identification method described in any one of the above.
[0014] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, apparatus, and equipment for identifying copper alloy grades. The method acquires X-ray fluorescence signals of each material in a material flow and converts them into data to be analyzed. It then calculates the similarity between the data to be analyzed and each data entry in a copper alloy standard database. Based on the similarity of each data entry, the method determines the copper alloy grade of the corresponding material. This reduces reliance on manual labor, achieves automated and accurate grade identification of each material in the material flow, and improves identification efficiency. Attached Figure Description
[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 This is a flowchart illustrating a method for identifying copper alloy grades according to an embodiment of this application.
[0017] Figure 2 This is a schematic diagram of a material flow transmission structure provided in an embodiment of this application.
[0018] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.
[0019] Figure label: 1-Vibrating feeder spreading area, 2-Vibrating motor, 3-Vibrating feeder support, 4-Vibrating chute queuing area. Detailed Implementation
[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0021] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0022] In one exemplary embodiment, such as Figure 1 As shown, this application provides a method for identifying copper alloy grades, including steps 101-104.
[0023] Step 101: Construct a copper alloy standard sample database; each data entry in the copper alloy standard sample database includes the grade, X-ray fluorescence characteristic curve, and elemental ratio.
[0024] Step 102: Acquire the X-ray fluorescence signals of each material in the material flow and convert them into data to be analyzed; the data to be analyzed is the X-ray fluorescence characteristic curve to be analyzed.
[0025] Step 103: Calculate the similarity between the data to be analyzed and each data entry in the copper alloy standard sample database.
[0026] Step 104: Determine the copper alloy grade of the corresponding material based on the similarity of each data point.
[0027] This application acquires X-ray fluorescence signals of various materials in the material flow and converts them into data to be analyzed. Based on a copper alloy standard sample database, it identifies copper alloy grades, which can efficiently solve the problem of rapid and accurate differentiation of copper alloy grades in industrial scenarios. It is especially suitable for large-scale sorting needs such as recycled copper recovery and copper alloy processing pretreatment.
[0028] In an exemplary embodiment, step 101 specifically includes steps 201-204.
[0029] Step 201: Obtain copper alloy standard samples of various grades.
[0030] The selection of copper alloy standard samples must be representative and comprehensive. The categories mentioned include copper alloy standard samples of commonly used industrial grades such as brass (e.g., H65), bronze (e.g., QAl5), and cupronickel (e.g., B30).
[0031] Step 202: Collect X-ray fluorescence characteristic curves of each copper alloy standard sample. Specifically, this includes: collecting data for each copper alloy standard sample at different angles, distances, and excitation energies. After marking the spectral data of the same sample under different excitation conditions, the data are processed, calculated, and compared sequentially to ensure data stability and accuracy. For example, the characteristic X-rays excited at different angles and distances with the same energy may have different overall signal intensities, but the proportions of each element in the alloy are the same. If the overall signal intensities are different, the different occurrence positions are determined, and it is judged whether the coefficients can be adjusted to facilitate the comparison of the spectra collected from unknown samples to determine the grade.
[0032] Step 203: Calculate the elemental composition of each copper alloy standard sample based on the characteristic curves of each X-ray fluorescence.
[0033] Step 204: Construct the copper alloy standard sample database by using the grade, X-ray fluorescence characteristic curve and elemental ratio of each copper alloy standard sample.
[0034] The elements in the elemental composition include major elements, trace elements, and minor elements. The major elements, trace elements, and minor elements are different in different copper alloys. Taking tin bronze in copper alloys as an example: the major elements are copper and tin. Depending on the grade, the internal elements may include lead and zinc in different amounts. Lead and zinc are trace elements, and minor elements are elements with even lower content, which may be impurities, etc.
[0035] This application acquires XRF characteristic curves of each standard sample using a high-speed XRF signal acquisition device. Based on the energy value and intensity of the characteristic peaks in the XRF characteristic curves, it analyzes and calculates the content and proportion of major elements (Cu, Zn, etc.), trace elements (Ni, Sn, etc.) and minor elements in the alloy, establishes and stores the correspondence between "grade-XRF curve-element ratio", and forms a copper alloy standard sample database.
[0036] This application preprocesses the material flow (the copper alloy material to be tested) using a vibrating feeder and a flow guide device configured with a high-speed XRF acquisition device. This ensures that the material forms a uniformly distributed material flow, which passes through the XRF data acquisition area sequentially in a queue-like pseudo-free fall motion. This ensures that only one material is in the detection range at a time, avoiding signal interference. The XRF acquisition device captures the characteristic fluorescence signal of the material in real time and converts it into data to be analyzed, increasing the recognition efficiency and speed.
[0037] In an exemplary embodiment, when analyzing and calculating the content and proportion of different levels of elements in a copper alloy standard sample, a combined method of "graded quantification + interference correction" is adopted, combining the characteristics of XRF technology and differences in element concentration. For major elements, the calibration curve method is used to focus on accuracy calculation, while for trace elements and micro-elements, a machine learning algorithm using a width learning system (BLS-Net) optimized by dual principal component analysis (PCA) is used to focus on sensitivity calculation. Interference correction refers to reducing the influence of one element's absorption of characteristic X-rays of another element. Step 203 specifically includes the following steps 301-303.
[0038] Step 301: Based on the intensity of the characteristic peaks in each X-ray fluorescence characteristic curve, calculate the elemental ratio of the major elements of the corresponding copper alloy standard sample using the calibration curve method.
[0039] Step 302: Extract the feature matrix, including linear principal components and nonlinear principal components, from each X-ray fluorescence characteristic curve through two-stage principal component analysis.
[0040] Step 303: Input the feature matrix into the element ratio prediction module to obtain the element ratio of trace elements and micro-elements of the corresponding copper alloy standard sample; the element ratio prediction module is obtained by training the width learning system.
[0041] In an exemplary embodiment, step 301 specifically includes: determining the element content by analyzing the characteristic peak intensity in the X-ray fluorescence characteristic curve based on the known linear regression relationship between characteristic peak intensity and element content; and determining the element ratio based on the content of each element. Each copper alloy standard sample corresponds to a regression curve, and each element of a copper alloy standard sample is represented by a prominent peak on the regression curve. The characteristic peak corresponds to the element content; the higher the peak, the higher the element content.
[0042] More specifically, based on the known linear regression relationship between characteristic peak intensity and elemental content, the content can be directly inferred from the characteristic peak intensity of the sample (material) to be tested, with a relative error controllable within ±0.3%. The formula is as follows: ; Relative error: ; Where I represents the intensity of the characteristic peaks of the main elements in the sample to be tested, and C represents the element content to be calculated. i Let I be the elemental content of the i-th standard sample (the standard sample in the copper alloy standard sample database). i Let be the characteristic peak intensity of the i-th standard sample, n be the number of standard sample collections, and RE be the relative error. This indicates the calculated element content. This indicates the actual elemental content of the standard sample.
[0043] In an exemplary embodiment, trace elements and ultra-trace elements are analyzed using a dual PCA-optimized width learning system machine learning algorithm to capture the nonlinear relationship between spectral intensity and low-concentration elements, while preserving weakly linear variable signals. The detection limit can be as low as ppm, meeting the analytical requirements for trace impurity elements in recycled copper. Step 302 specifically includes steps 401-403.
[0044] Step 401: Extract linear principal components from the X-ray fluorescence characteristic curve through principal component analysis in the first stage.
[0045] The first stage of principal component analysis removes background noise and redundant information from the X-ray fluorescence characteristic curve.
[0046] First, using the formula Standardize the sample data to be tested (data to be analyzed).
[0047] in, and The first i The first of the data to be analyzed j Data before and after standardization of element feature data. and The first j The maximum and minimum values of the characteristic elements.
[0048] Then, substitute the standardized data (the standardized data to be analyzed) into the covariance matrix to calculate the linear correlation between each channel: ; Where m is the number of standard samples. The sample covariance matrix (n1 is the number of spectral energy channels). This is the standardized spectral data matrix (the standardized data to be analyzed). Here is the transposed, normalized spectral data matrix, where I is the identity matrix. It is an m-order all-1 square matrix.
[0049] right Perform eigenvalue decomposition =UΛU T , where U is the eigenvector matrix and Λ is the eigenvalue matrix.
[0050] Finally, the principal components were selected by decomposing the eigenvalues. .
[0051] The features retained by the first-stage PCA still include nonlinear disturbances caused by matrix effects, requiring a second PCA to separate the linear and nonlinear components.
[0052] Step 402: Calculate the nonlinear component based on the relationship between the linear principal components and elemental content, specifically including: fitting the model using a linear model. The relationship with element content is used to calculate the residual matrix, i.e., the nonlinear part.
[0053] .
[0054] in, The residual matrix is... It is a linear principal component. This is the linear regression coefficient matrix.
[0055] Step 403: Extract nonlinear principal components from the nonlinear part through the second stage of principal component analysis. Specifically, this includes: repeatedly decomposing the residual matrix into covariance and screening the principal components to obtain the nonlinear feature matrix Z2. Finally, the linear principal components and the nonlinear principal components are concatenated to form the feature matrix Z after double PCA optimization: Z=[Z1,Z2].
[0056] In an exemplary embodiment, the element ratio prediction module trained on the width learning system in step 303 is a width learning system of nonlinear mapping and fast learning.
[0057] The width learning system consists of an input layer, an augmentation node layer, a feature fusion layer, and an output layer.
[0058] The input layer is used to receive the feature matrix Z after double PCA optimization.
[0059] Enhanced node layer: Maps the input to a high-dimensional nonlinear space using a random weight matrix to generate enhanced features. : Where W2 is the random weight matrix and b is the bias vector. This is the activation function.
[0060] Feature fusion layer: splices the original feature Z with the enhanced feature This forms a wide-dimensional feature matrix M: M=[Z,H].
[0061] Output layer: Predicts element content by solving for linear weights using pseudo-inverse. ,in Let β be the predicted content vector, where β is the output weight vector. Where y is the true content vector, λ=10 -6 This is the regularization parameter.
[0062] In an exemplary embodiment, step 103 specifically includes: employing a data fitting strategy combining fuzzy membership functions and genetic algorithms to calculate the similarity between the data to be analyzed and each data entry in the copper alloy standard sample database; using a genetic algorithm to adaptively calibrate the detection parameters of all materials to be analyzed to offset individual differences in the equipment; and accurately determining the copper alloy grade of the sample to be tested when the data fitting degree is ≥95%, providing a basis for subsequent sorting and achieving industrial-grade high-efficiency sorting with a processing capacity of 25-35 t / h and a sorting purity of over 98%.
[0063] A data fitting strategy combining fuzzy membership functions and genetic algorithms is employed to calculate the similarity between the data to be analyzed and each data item in the copper alloy standard sample database. Specifically, this includes: initializing a population based on the data to be analyzed, comprising N individuals with real-number encodings, each individual including a set of optimization parameters for the data to be analyzed. These optimization parameters specifically include: X-ray excitation source tube voltage correction coefficient, detector (XRF signal acquisition device) detection distance correction amount, material thickness self-absorption attenuation correction coefficient, spectral baseline background shift, characteristic peak energy drift correction coefficient, and spectral line overlap interference correction weight; N is a positive integer. Based on the initialized population, with the goal of maximizing the membership degree of the data to be analyzed, a genetic algorithm is used to determine the similarity between the data to be analyzed and each data item. In each iteration of the genetic algorithm, a weighted fuzzy membership function constructed using a Gaussian membership function is used to calculate the membership degree of the data to be analyzed to each data item; this membership degree is the similarity.
[0064] The weighted fuzzy membership function highlights key features by introducing a weight matrix.
[0065] ; in, Let represent the membership degree (similarity) of the test sample to the i-th standard sample, with a value range of [0,1]. The standardized feature vector, For the k-th standardized feature, Let be the standardized value of the k-th feature (feature of the k-th element) of the i-th standard sample. The feature weight of the k-th feature. Let be the feature tolerance of the k-th feature.
[0066] When the characteristics of the sample to be tested are completely consistent with those of the standard sample The greater the deviation, The closer it is to 0.
[0067] The execution process of the genetic algorithm is as follows: N individuals are randomly generated using real-number encoding, and the probability of a single individual being selected is positively correlated with its fitness. Then, perform arithmetic crossover to preserve the physical meaning of the parameters, for the parent generation. , Generate offspring: Using Gaussian mutation Adding small perturbations avoids local optima when continuous Output the optimal matching degree at the time of generation. Indicates the individual after mutation. Indicates before mutation, Indicates that it follows a normal distribution random numbers, Let represent the variance of the Gaussian variation.
[0068] in, For the first j The probability of an individual being selected. It is a set of XRF spectral correction optimization parameter vectors, including tube voltage correction coefficients, detection distance correction amounts, baseline offset, etc. Let be the fitness function of the j-th individual during the iteration of the genetic algorithm, and N be the total number of individuals in the population; The sum of the fitness values of all individuals in the population. Indicates the first j Chromosomal codes of each individual (optimization parameters for the data to be analyzed). Indicates the first t The chromosome code of each individual.
[0069] The specific expression is X is the optimization parameter vector corresponding to the individual; The membership degree of the test sample to the i-th group of standard sample data is calculated by the weighted Gaussian fuzzy membership function after the spectrum is corrected using the optimized parameter vector X. δ is the penalty coefficient; V0 and D0 are the equipment's baseline operating parameters, and V and D are the corrected operating parameters; δ is the standard deviation of the penalty term.
[0070] Based on the same inventive concept, this application also provides a copper alloy grade identification device for implementing the copper alloy grade identification method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more embodiments of the copper alloy grade identification device provided below can be found in the limitations of the copper alloy grade identification method described above, and will not be repeated here.
[0071] In one exemplary embodiment, a copper alloy grade identification device is provided, including an X-ray fluorescence acquisition device, a vibrating feeder, a flow guiding device, and a copper alloy grade identification module.
[0072] The vibrating feeder is used to uniformly transfer each material in the material flow to the guiding device.
[0073] The flow guiding device is used to guide each material to the collection area of the X-ray fluorescence acquisition device.
[0074] The X-ray fluorescence acquisition device is used to acquire X-ray fluorescence signals of various materials.
[0075] The copper alloy grade identification module is used to receive the X-ray fluorescence signals of each material collected by the X-ray fluorescence acquisition device, and to determine the copper alloy grade of each material using the copper alloy grade identification method.
[0076] In one exemplary embodiment, such as Figure 2 As shown, the high-speed XRF acquisition equipment is equipped with a vibrating feeder and guide device for pre-processing. The material is conveyed to the vibrating feeder spreading area 1 by an external conveyor belt, so that the material is evenly spread and then evenly conveyed to the vibrating chute queuing area 4. The material queues up under the action of gravity and the excitation force of the vibrating motor 2, so that the material forms a uniformly distributed material flow. The material undergoes pseudo-free fall motion in a queuing manner and passes through the XRF data acquisition area in sequence, ensuring that only one piece of material is in the detection range at a time, avoiding signal interference. The XRF detector captures the characteristic fluorescence signal of the material in real time and converts it into data to be analyzed.
[0077] The high-speed XRF acquisition equipment is equipped with a vibrating feeder and guide device. The overall device consists of, for example, the following components: Figure 2 The vibrating feeder is supported by a bracket 3.
[0078] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a method for identifying copper alloy grades.
[0079] Those skilled in the art will understand that Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0080] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.
[0081] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0082] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
[0083] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchain. The processors involved in the embodiments provided in this application may be, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc.
[0084] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0085] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for identifying copper alloy grades, characterized in that, include: Construct a database of copper alloy standard samples; Each data entry in the copper alloy standard sample database includes the grade, X-ray fluorescence characteristic curve, and elemental ratio; The X-ray fluorescence signals of each material in the material flow are acquired and converted into data to be analyzed; the data to be analyzed is the X-ray fluorescence characteristic curve to be analyzed. The similarity between the data to be analyzed and each data entry in the copper alloy standard sample database is calculated. Based on the similarity of each data point, the copper alloy grade of the corresponding material is determined.
2. The method for identifying copper alloy grades according to claim 1, characterized in that, Constructing a copper alloy standard sample database, specifically including: Obtain copper alloy standard samples of various grades; X-ray fluorescence characteristic curves of each copper alloy standard sample were collected; Calculate the elemental composition of each copper alloy standard sample based on the characteristic curves of each X-ray fluorescence. The copper alloy standard sample database is constructed by using the grade, X-ray fluorescence characteristic curve, and elemental ratio of each copper alloy standard sample.
3. The method for identifying copper alloy grades according to claim 2, characterized in that, The elements in the element ratio include major elements, trace elements, and micro-elements.
4. The method for identifying copper alloy grades according to claim 3, characterized in that, Based on the characteristic X-ray fluorescence curves, the elemental composition of each copper alloy standard sample was calculated, specifically including: Based on the intensity of the characteristic peaks in each X-ray fluorescence characteristic curve, the elemental ratio of the major elements in the corresponding copper alloy standard sample is calculated using the calibration curve method. The feature matrix, including linear and nonlinear principal components, was extracted from each X-ray fluorescence characteristic curve through two-stage principal component analysis. The feature matrix is input into the element ratio prediction module to obtain the element ratio of trace elements and minor elements of the corresponding copper alloy standard sample; the element ratio prediction module is obtained by training a width learning system.
5. The method for identifying copper alloy grades according to claim 4, characterized in that, Based on the intensity of the characteristic peaks in each X-ray fluorescence characteristic curve, the elemental composition of the major elements in the corresponding copper alloy standard sample is calculated using the calibration curve method, specifically including: Based on the known linear regression relationship between characteristic peak intensity and element content, the element content is determined by the characteristic peak intensity in the X-ray fluorescence characteristic curve, and the element ratio is determined based on the content of each element.
6. The method for identifying copper alloy grades according to claim 4, characterized in that, Characteristic matrices, including linear and nonlinear principal components, were extracted from each X-ray fluorescence characteristic curve using two-stage principal component analysis. Specifically, these included: Linear principal components were extracted from the X-ray fluorescence characteristic curves through the first-stage principal component analysis. The nonlinear component is calculated based on the relationship between the linear principal components and the element content. Nonlinear principal components are extracted from the nonlinear part through principal component analysis in the second stage.
7. The method for identifying copper alloy grades according to claim 1, characterized in that, The similarity calculation between the data to be analyzed and each data entry in the copper alloy standard sample database specifically includes: A data fitting strategy combining fuzzy membership function and genetic algorithm is adopted to calculate the similarity between the data to be analyzed and each data in the copper alloy standard sample database.
8. The method for identifying copper alloy grades according to claim 7, characterized in that, A data fitting strategy combining fuzzy membership functions and genetic algorithms is employed to calculate the similarity between the data to be analyzed and each data entry in the copper alloy standard sample database. Specifically, this includes: The population is initialized based on the data to be analyzed. The initialized population includes N individuals with real-number encodings. Each individual includes a set of optimization parameters for the data to be analyzed, where N is a positive integer. Based on the initial population, with the goal of maximizing the membership degree of the data to be analyzed, a genetic algorithm is used to determine the similarity between the data to be analyzed and each data item; wherein, in each iteration of the genetic algorithm, a weighted fuzzy membership function constructed by a Gaussian membership function is used to calculate the membership degree of the data to be analyzed to each data item.
9. A copper alloy grade identification device, characterized in that, Includes X-ray fluorescence acquisition equipment, vibrating feeder, flow guiding device and copper alloy grade identification module; The vibrating feeder is used to uniformly transfer each material in the material flow to the guiding device. The flow guiding device is used to guide each material to the collection area of the X-ray fluorescence acquisition device; The X-ray fluorescence acquisition device is used to acquire X-ray fluorescence signals of various materials; The copper alloy grade identification module is used to receive the X-ray fluorescence signals of each material collected by the X-ray fluorescence acquisition device, and to determine the copper alloy grade of each material using the copper alloy grade identification method according to any one of claims 1-8.
10. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the copper alloy grade identification method according to any one of claims 1-8.