Copper concentrate sample tracing method based on X-ray fluorescence spectrum and isotope detection

Abstract

The invention provides a copper concentrate sample traceability method based on X-ray fluorescence spectrum and isotope detection, and relates to the technical field of copper concentrate traceability. Data sampling is carried out on subjective factors and objective factors in the copper concentrate sample sampling process, data storage is carried out based on a block chain to improve the safety and accuracy of data, discretization, standardization, abnormal value correction and principal component analysis processing are carried out on the data analysis result of the copper concentrate sample, and therefore data standardization is guaranteed, and the accuracy of the data analysis result is improved. Based on a first mining area feature fingerprint database set obtained through historical data mining, determining a target mining area to which the copper concentrate sample belongs and a corresponding first similarity; by means of the technical scheme, standardization processing of the copper concentrate analysis result can be achieved, then the consistency rule is extracted, the confidence probability is given out for the traceability result in combination with the sampling process data, and therefore the obtained traceability result is more accurate.

Description

Technical Field

[0001] The invention belongs to the technical field of mineral product traceability, and in particular relates to a copper concentrate sample traceability method based on X-ray fluorescence spectroscopy and isotope detection. Background Art

[0002] In recent years, with the continuous expansion of my country's foreign trade, the import volume of imported mineral raw materials has continued to grow. Among them, copper concentrate, as an important industrial raw material, has become increasingly prominent in terms of its quality and origin traceability. The existing technology has many technical problems that need to be solved in the field of copper concentrate traceability: First, the origin traceability of copper concentrate mainly relies on the declaration of exporters, and lacks effective technical means for verification. Especially when the sample is biased or maliciously concealed, it is difficult to accurately trace its true source; secondly, copper concentrate is usually transported in bulk, and there are factors that cannot be traced during the sample circulation process, which makes it difficult to identify the origin of the sample; in addition, the existing traceability technical means are mostly concentrated on elemental analysis, such as X-ray fluorescence spectroscopy. Although it can determine the elemental composition, the limitations of a single technical means are large, and it is difficult to fully reflect the origin characteristics of the sample. Although the origin traceability technology in the fields of animal and plant products, agricultural products, etc. has made certain progress at home and abroad, its application in the field of mineral products such as copper concentrate is still in its initial stage, lacking a systematic traceability model and technical means. Therefore, developing a copper concentrate origin traceability method that combines multiple analytical techniques (such as X-ray fluorescence spectroscopy and isotope detection) has important practical significance and application value. Summary of the invention

[0003] The object of the present invention is to provide a copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection to solve the above-mentioned technical problems existing in the prior art.

[0004] This application proposes a copper concentrate sample traceability method based on X-ray fluorescence spectroscopy and isotope detection, which includes: S0: Acquire first multi-source data of the copper concentrate sample, generate a first trustworthy value for each of the first multi-source data, generate first block data according to the first multi-source data and the first trustworthy value, and store the data on the blockchain; S1: Analyze the copper concentrate sample to obtain a plurality of first analysis results, and preprocess and discretize each of the first analysis results to obtain a first transaction database; S2: extracting a plurality of first data items from the first transaction database, and determining a target mining area feature fingerprint library and a first similarity from the plurality of first data items according to a first mining area feature fingerprint library set; wherein the first mining area feature fingerprint library is obtained after historical data analysis of a plurality of different copper concentrates; S3: Determine a first target mining area and a first confidence probability corresponding to the copper concentrate sample according to the first block data and the first similarity.

[0005] Preferably, the first multi-source data in S0 is obtained by the following steps: S01: Acquire first subjective sampling data and first objective sampling data of the copper concentrate sample; S02: Generate the first multi-source data according to the first subjective sampling data and the first objective sampling data.

[0006] Preferably, the first subjective sampling data includes the cumulative working hours and the number of historical errors of the sampler, and the first objective sampling data includes the sampling location point information and the sample resting time before sampling.

[0007] Preferably, the S0 further comprises the following steps: S03: inputting the first multi-source data into a first credibility determination model to obtain a first credibility corresponding to the first multi-source data; S04: Obtain first block data according to the first multi-source data and the first credibility, and store the first block data on-chain.

[0008] Preferably, S1 comprises the following steps: S11: storing the first analysis result in a table form to obtain a first data table; S12: performing standardization processing on each first data value stored in the first data table to obtain a first standardized data table; wherein each first analysis result is composed of a plurality of first data values; S13: performing anomaly correction processing on the first standardized data table to obtain a second standardized data table; S14: performing principal component analysis and dimensionality reduction processing on the second standardized data table to obtain a third standardized data table; S15: Discretize the third standardized data table to obtain a first transaction database.

[0009] Preferably, the first analysis result includes XRF element content and lead isotope ratio.

[0010] Preferably, the principal component analysis and dimensionality reduction processing in S14 includes: The standardized isotope ratio is reduced in dimension to generate principal component features to replace the original features; The original features in the second standardized data table are replaced according to the generated principal component features, thereby obtaining the third standardized data table.

[0011] Preferably, in S0, the first data item is a data combination including an element interval and an isotope interval.

[0012] Preferably, in S2, the first mining area characteristic fingerprint library set is obtained by analyzing historical data of multiple different copper concentrates, and specifically includes the following steps: The sample data is divided into multiple groups based on different copper concentrates; each piece of sample data contains element interval, isotope interval, and mining area label; For multiple groups of sample data, multiple first mining area feature fingerprint libraries are obtained respectively, and the first mining area feature fingerprint library set is obtained according to the multiple first mining area feature fingerprint libraries.

[0013] Preferably, the first mining area feature fingerprint library includes: Multiple frequent item sets consisting of element contents and isotope intervals in specified copper concentrates.

[0014] The copper concentrate sample traceability method based on X-ray fluorescence spectroscopy and isotope detection proposed in this application relates to the copper concentrate traceability technology field. Data sampling is performed on the subjective factors and objective factors in the copper concentrate sample sampling process, and data preservation is performed based on blockchain to improve the security and accuracy of the data. The data analysis results of the copper concentrate samples are discretized, standardized, outlier correction and principal component analysis are performed to ensure data standardization. Based on the first mining area feature fingerprint library set obtained through historical data mining, the target mining area to which the copper concentrate sample belongs and the corresponding first similarity are determined. Through the technical solution of this application, the standardized processing of the copper concentrate analysis results can be achieved, and then the consistency rules can be extracted, and the confidence probability of the traceability results can be given in combination with the sampling process data, so that the traceability results obtained are more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0016] Figure 1 It is an execution flow chart of the copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection in the present invention.

[0017] Figure 2 This is a flow chart for determining the first transaction database in step S1 of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0020] The copper concentrate sample traceability method based on X-ray fluorescence spectroscopy and isotope detection of the present invention is described in detail below. Figure 1 shown.

[0021] S0: Acquire first multi-source data of the copper concentrate sample, generate a first credible value for each of the first multi-source data, generate first block data according to the first multi-source data and the first credible value, and store the data on the chain.

[0022] The accuracy of copper concentrate sampling data will directly affect the accuracy of subsequent data analysis and traceability results. In the copper concentrate traceability process, the behaviors that may lead to inaccurate sampling due to human factors mainly include the following aspects: 1. Sampling deviation: Inhomogeneity problem: If the copper concentrate material itself is uneven (such as containing different proportions of metals and other impurities), and this is not taken into account during sampling, the sample may not represent the characteristics of the entire batch. 2. Improper sampling location: Choosing the wrong sampling point or depth, failing to fully cover the entire material pile, may ignore the composition changes in certain areas. 3. Improper use of tools: Using sampling tools that are not suitable for the current material characteristics, such as for materials with large particles or high viscosity, a specially designed sampler should be used instead of an ordinary shovel. 4. The tool is not cleaned, and the residual material from the last sampling will affect the purity of this sample. 5. Improper time management: The sampling time is wrong, such as sampling when the material has just arrived at the port and has not yet stabilized, which may cause distortion of the results due to the rapid evaporation of surface moisture. 6. Operational errors: Human errors in the sample handling process, including but not limited to inaccurate weighing, sample loss, uneven mixing, etc. 7. Failure to follow the standard operating procedures (SOP), such as failure to achieve the required particle size when grinding the sample, or arbitrarily discarding small particles and debris when sieving. 8. Recording and marking errors: Unclear recording of sample information or incorrect marking may cause sample confusion and affect the accuracy of subsequent analysis results. 9. Data entry errors, especially when manually recording data, are prone to transcription errors. 10. Intentional behavior: Deliberately tampering with samples or falsifying test reports to cover up the reality of low-quality products for economic reasons. 11. Lack of training: If staff lack the necessary professional training and do not understand the correct sampling techniques and procedures, then even with perfect equipment and technical support, the accuracy of sampling cannot be guaranteed.

[0023] The above reasons include the sampling point distribution of copper concentrate samples, the static time, the working experience of the sampler, etc. In order to make the data analysis and traceability results of copper concentrate more accurate, in this step, a credible probability value is first given for the credibility of the sample, so that the subsequent big data analysis can be more accurate and targeted.

[0024] The S0 comprises the following sub-steps: S01: Acquire first subjective sampling data and first objective sampling data of the copper concentrate sample.

[0025] The first subjective sampling data includes information such as the cumulative working time of the sampler, the number of historical errors, etc. The first objective sampling data may include information such as the sampling location point when the sampler performs data sampling, the sample static time before sampling, etc. The sampling location point information includes multiple first coordinate values, each of which is a three-dimensional coordinate value of each sampling point in a coordinate system with the geometric center of the copper concentrate sample as the origin.

[0026] S02: Generate the first multi-source data according to the first subjective sampling data and the first objective sampling data.

[0027] Preferably, the first multi-source data is in the form of a multi-dimensional vector, which contains all the information in the first subjective sampling data and the first objective sampling data.

[0028] S03: Inputting the first multi-source data into a first credibility determination model to obtain a first credibility corresponding to the first multi-source data.

[0029] The first credibility determination model is obtained through CNN training. During the training process, the sampling data of historical copper concentrate samples is used as the input data of the model, and the corresponding credibility is used as the output data to train and obtain the first credibility determination model.

[0030] S04: Obtain first block data according to the first multi-source data and the first credibility, and store the first block data on-chain.

[0031] In order to ensure the accuracy and security of the sampling information, the first block data is stored in a blockchain manner. Specifically, the first block data is consensus-based in the blockchain, and after the consensus is successful, it is saved in the blockchain account book to prevent the data from being tampered with.

[0032] S1: Analyze the copper concentrate sample to obtain a plurality of first analysis results, and preprocess and discretize each of the first analysis results to obtain a first transaction database.

[0033] The first analysis result is the XRF element content (such as Cu, Fe, Zn) and lead isotope ratio (206Pb / 204Pb, 207Pb / 204Pb) obtained by analyzing the copper concentrate sample. Since there are multiple copper concentrate samples, multiple first analysis results can be obtained. The preprocessing and discretization processing includes data standardization and binning. Specifically, the XRF element content (such as Cu, Fe, Zn) and lead isotope ratio (206Pb / 204Pb, 207Pb / 204Pb) are Z-score standardized to eliminate dimensional differences.

[0034] like Figure 2 As shown, S1 includes the following sub-steps: S11: storing the first analysis result in a table format to obtain a first data table.

[0035] The first multi-source data includes XRF element content and lead isotope ratio information. The data sources are as follows: XRF element content: the percentage content of Cu, Fe and Zn in the copper concentrate sample (such as Cu=16.85%, Fe=16.35%, etc.).

[0036] Lead isotope ratio: measured values ​​of 206Pb / 204Pb and 207Pb / 204Pb (e.g. 206Pb / 204Pb=18.656975). Original data format: Stored in a table format, each row represents a sample, and columns include fields such as Cu(%), Fe(%), Zn(%), 206Pb / 204Pb, and 207Pb / 204Pb.

[0037] S12: performing standardization processing on each first data value stored in the first data table to obtain a first standardized data table.

[0038] Before standardization, each feature (such as Cu content Cu i ) to obtain the mean and standard deviation. The calculation formulas for the mean and standard deviation are as follows: Mean, where N is the number of samples: ; Standard Deviation: ; After calculating the mean and standard deviation, the Z-score standardization formula is applied to obtain the standardized value of each of the first data values ​​in the first data table. Taking the Cu content as an example, the standardization formula is as follows: ; Among them, Cu i is the copper content, μCu is the mean copper content, and σCu is the standard deviation of the copper content.

[0039] Afterwards, each of the first data values ​​in the first data table is replaced with a standardized data value, thereby obtaining the first standardized data table.

[0040] S13: performing anomaly correction processing on the first standardized data table to obtain a second standardized data table.

[0041] In the first standardized data table, some data values ​​may be abnormal, so it is necessary to detect the abnormal values ​​and remove or correct the values ​​determined to be abnormal.

[0042] The outlier detection method is as follows: Boxplot analysis: Check the upper and lower quartiles (Q 1 =25%, Q 3 =75%), exceeding Q 1 −1.5I QR ,Q 3 +1.5I QR Samples outside the range are considered outliers (I QR =Q 3 -Q 1 ).

[0043] Processing method: If the outliers are caused by measurement errors, they should be directly eliminated; if they are real data, robust standardization should be used (such as median and interquartile range instead of mean standard deviation).

[0044] S14: performing principal component analysis and dimensionality reduction processing on the second standardized data table to obtain a third standardized data table.

[0045] Among the multiple data values ​​in the second standardized data table, lead isotope ratios (such as 206Pb / 204Pb and 207Pb / 204Pb) may be highly correlated. In order to avoid the problem of multicollinearity, it is necessary to perform principal component analysis on each type of data value in the second standardized data table and perform dimensionality reduction on data types with higher collinearity.

[0046] The solution is as follows: Principal component analysis (PCA): reduce the dimension of the standardized isotope ratios to generate principal components to replace the original features. Replace the original features in the database table according to the generated principal component features, thereby obtaining the third standardized data table.

[0047] S15: Discretize the third standardized data table to obtain a first transaction database.

[0048] In order to facilitate subsequent association rule mining, in this step, continuous data needs to be divided into intervals (for example, Cu content: 10%-15% is "low", 15%-20% is "medium", and 20%+ is "high") and converted into categorical variables, that is, discretized according to preset rules.

[0049] Feature labeling: constructing an "element interval-isotope interval" transaction database. That is, for the discretized third standardized data table, each row is used as a unit to form a data item, so as to obtain the first transaction database according to the determined multiple data items.

[0050] The first transaction database is used to characterize the association relationship between element intervals and isotope intervals.

[0051] S2: extracting a plurality of first data items from the first transaction database, and determining a target mining area feature fingerprint library and a first similarity from the plurality of first data items according to a first mining area feature fingerprint library set.

[0052] The first data item may be each row of data in the transaction database, that is, a data combination of an element interval and an isotope interval. In the subsequent steps, in order to determine whether the data combination has an association relationship with a specific mining area, each of the first data items needs to be input into the first frequent item set determination model one by one, so as to mine the matching degree between each data combination and the specific mining area through big data.

[0053] The first mining area characteristic fingerprint library is obtained after historical data analysis of multiple different copper concentrates, as follows: The sample data is divided into multiple groups based on different copper concentrates, that is, the sample data in each group comes from the same copper concentrate. In each group, each sample data contains element intervals, isotope intervals, and mining area labels. In each sample, the element intervals, isotope intervals, and mining area labels are all discretized values.

[0054] Set a dynamic support adjustment strategy: Since the number of historical copper concentrate data samples is often insufficient, for small samples (such as 24), set a lower support (such as 10%) and introduce weighted support to prioritize mining high-discrimination combinations (such as "high Cu content + specific Pb isotope ratio").

[0055] The weighted support is calculated as follows: Discrimination weight: The weight is calculated based on the chi-square value of the item set and the mining area. The chi-square value is calculated by selecting multiple sample data from the same copper concentrate, squaring the difference between the actual value and the expected value of each sample data, dividing it by the expected value, and finally adding all the results to get the chi-square value.

[0056] The calculation formula of weighted support is as follows: Weighted support = original support × (1 + chi-square value / chi-square threshold); Prioritize mining high-weight item sets: For example, if the chi-square value of the item set {Cu=high, 206Pb / 204Pb=18.6~18.7} is 15 (the chi-square threshold is 3.84), its weighted support is increased to 4 times the original value.

[0057] Rule screening and confidence optimization: The rules significantly associated with the mining area (e.g. {Cu=high, 206Pb / 204Pb=18.6~18.7} → COLLAHUASI (95% confidence level)) were screened by chi-square test or lift.

[0058] The rules with confidence level > 90% are retained to form the first mining area feature fingerprint library.

[0059] Thus, for multiple groups of sample data, multiple first mining area feature fingerprint libraries are obtained respectively, and the first mining area feature fingerprint library set is obtained according to the multiple first mining area feature fingerprint libraries.

[0060] Therefore, in the subsequent steps, the first mining area feature fingerprint library with the highest similarity to the copper concentrate sample can be determined based on the first similarity between the first transaction database and each of the first mining area feature fingerprint libraries in the first mining area feature fingerprint library set, and used as the target mining area feature fingerprint library.

[0061] The first similarity is calculated in the following manner: for all data items in the first transaction database, the second similarity with each of the first mining area feature fingerprint libraries is calculated, and the average value of all the second similarities is used as the first similarity.

[0062] S3: Determine a first target mining area and a first confidence probability according to the first block data and the first similarity.

[0063] In the target mining area characteristic fingerprint library, the copper concentrate area corresponding to the target mining area characteristic fingerprint library is indicated, so the determined copper concentrate area can be used as the first target mining area corresponding to the copper concentrate sample.

[0064] Furthermore, in order to determine the first confidence probability that the copper concentrate sample originates from the first target mining area, the first confidence probability can also be predicted based on the machine learning model according to the sampling related information represented in the first block data and the first similarity. When training the machine learning model for predicting the first confidence probability, historical data of other copper concentrates can be selected as samples, sample data of the same data type as the first block data, and its similarity with the mining area feature fingerprint library with the highest similarity can be used as input data, and the corresponding confidence probability can be used as output data to train and obtain a prediction model.

[0065] As an optional embodiment, the sampling information represented in the first block data and the first similarity may be evaluated based on artificial expert experience, so as to determine the first confidence probability based on preset rules.

[0066] The copper concentrate sample traceability method based on X-ray fluorescence spectroscopy and isotope detection proposed in this application relates to the copper concentrate traceability technology field. Data sampling is performed on the subjective factors and objective factors in the copper concentrate sample sampling process, and data preservation is performed based on blockchain to improve the security and accuracy of the data. The data analysis results of the copper concentrate samples are discretized, standardized, outlier correction and principal component analysis are performed to ensure data standardization. Based on the first mining area feature fingerprint library set obtained through historical data mining, the target mining area to which the copper concentrate sample belongs and the corresponding first similarity are determined. Through the technical solution of this application, the standardized processing of the copper concentrate analysis results can be achieved, and then the consistency rules can be extracted, and the confidence probability of the traceability results can be given in combination with the sampling process data, so that the traceability results obtained are more accurate.

[0067] The above description is only a preferred embodiment of the present invention, so all equivalent changes or modifications made according to the structure, characteristics and principles described in the scope of the patent application of the present invention are included in the scope of the patent application of the present invention.

Claims

1. A copper concentrate sample traceability method based on X-ray fluorescence spectroscopy and isotope detection, characterized in that: The method includes: S0: Acquire first multi-source data of the copper concentrate sample, generate a first credible value for each of the first multi-source data, generate first block data according to the first multi-source data and the first credible value, and store the data on the chain; S1: Analyze the copper concentrate sample to obtain a plurality of first analysis results, and preprocess and discretize each of the first analysis results to obtain a first transaction database; S2: extracting a plurality of first data items from the first transaction database, and determining a target mining area characteristic fingerprint library and a first similarity from the plurality of first data items according to a first mining area characteristic fingerprint library set; wherein the first mining area characteristic fingerprint library is obtained after historical data analysis of a plurality of different copper concentrates; S3: Determine a first target mining area and a first confidence probability corresponding to the copper concentrate sample according to the first block data and the first similarity.

2. The copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection according to claim 1 is characterized in that: The first multi-source data in S0 is obtained by the following steps: S01: Acquire first subjective sampling data and first objective sampling data of the copper concentrate sample; S02: Generate the first multi-source data according to the first subjective sampling data and the first objective sampling data.

3. The copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection according to claim 2 is characterized in that: The first subjective sampling data includes the cumulative working time and the number of historical errors of the sampler, and the first objective sampling data includes the sampling location point information and the sample static time before sampling.

4. The copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection according to claim 3 is characterized in that: The S0 further comprises the following steps: S03: inputting the first multi-source data into a first credibility determination model to obtain a first credibility corresponding to the first multi-source data; S04: Obtain first block data according to the first multi-source data and the first credibility, and store the first block data on-chain.

5. The copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection according to claim 4 is characterized in that: The S1 comprises the following steps: S11: storing the first analysis result in a table form to obtain a first data table; S12: performing standardization processing on each first data value stored in the first data table to obtain a first standardized data table; wherein each first analysis result is composed of a plurality of the first data values; S13: performing anomaly correction processing on the first standardized data table to obtain a second standardized data table; S14: performing principal component analysis and dimensionality reduction processing on the second standardized data table to obtain a third standardized data table; S15: Discretize the third standardized data table to obtain a first transaction database.

6. The copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection according to claim 5 is characterized in that: The first analysis result includes XRF element content and lead isotope ratio.

7. The copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection according to claim 6 is characterized in that: The principal component analysis and dimensionality reduction processing in S14 includes: The standardized isotope ratio is reduced in dimension to generate principal component features to replace the original features; The original features in the second standardized data table are replaced according to the generated principal component features, thereby obtaining the third standardized data table.

8. The copper concentrate sample traceability method based on X-ray fluorescence spectroscopy and isotope detection according to claim 1 is characterized in that: In the S0, the first data item is a data combination including an element interval and an isotope interval.

9. The copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection according to claim 1, characterized in that: In S2, the first mining area feature fingerprint library set is obtained by analyzing historical data of multiple different copper concentrates, and specifically includes the following steps: The sample data is divided into multiple groups based on different copper concentrates; each piece of sample data contains element interval, isotope interval, and mining area label; For multiple groups of sample data, multiple first mining area feature fingerprint libraries are obtained respectively, and the first mining area feature fingerprint library set is obtained according to the multiple first mining area feature fingerprint libraries.

10. The copper concentrate sample tracing method based on X-ray fluorescence spectroscopy and isotope detection according to claim 9, characterized in that: The first mining area feature fingerprint library includes: Multiple frequent item sets consisting of element contents and isotope intervals in specified copper concentrates.

Images