A method for analyzing the distribution characteristics of porphyry polymetallic gold deposits

Abstract

The invention discloses a method for analyzing the dissemination characteristics of porphyry polymetallic gold deposits, and relates to the field of ore sample detection. The invention comprises the following steps: obtaining historical measured ore sample data and gold balance distribution data of the ore sample; generating an analysis model for the dissemination particle size characteristics of the gold ore, determining the proportion distribution data of gold in the mineral with gold balance distribution at different distribution rates, analyzing and calculating the proportion distribution data, analyzing the gold content changes of other minerals in the ore sample after selecting distribution rates of different step lengths for the gold proportion of a single mineral in the ore sample; calculating the gold distribution rate for the gold content change data of other minerals whose distribution rates of the single mineral are changed and meet the verification accuracy; outputting simulated measured ore sample data according to the proportion distribution data and inputting the data into the analysis model for continuous training; obtaining an analysis model for analyzing the gold balance distribution data of the measured ore sample data. The invention uses a classification model training method to simplify the process from measuring the ore sample data to analyzing the gold balance data, and adopts a model to efficiently and conveniently process data.

Description

Technical Field

[0001] The invention relates to the field of ore sample detection, and in particular to a method for analyzing the distribution characteristics of porphyry polymetallic gold deposits. Background Art

[0002] There are a lot of existing low-grade gold resources detected. During the detection process, it was found that the gold resources have the characteristics of uneven distribution of particle size, complex ore structure, incomplete dissociation, etc. Traditional mineralogical analysis is not easy to quickly and accurately determine the gold occurrence state and the distribution characteristics of gold-bearing minerals.

[0003] It is known that gold mainly exists in the form of free natural gold, with extremely fine embedded particles, mainly concentrated in the particle size of 0.01~0.02mm; gold with a particle size of less than 0.074mm accounts for 50.08% of the total gold in the ore, and the rest of the gold is dispersed in pyrite, magnetite, chalcopyrite and other gold-bearing minerals as fine inclusions. However, the gold-bearing minerals have fine particles, poor dissociation, and uneven embedding, which affects the gold recovery rate of the gold-bearing mineral dissociation degree.

[0004] Due to the complex intergenetic inclusion relationships and fine-grained distribution of polymetallic gold deposits in the tested area, poor dissociation of gold-bearing minerals and uneven distribution of grains, it is difficult to quickly and accurately determine the occurrence state of gold deposits through traditional mineralogical identification methods.

[0005] Therefore, there is an urgent need for an analysis method for the distribution characteristics of porphyry polymetallic gold deposits. Summary of the invention

[0006] The invention discloses a method for analyzing the distribution characteristics of porphyry polymetallic gold deposits, which solves the problems of the prior art.

[0007] In a first aspect, the present invention provides a method for analyzing the dissemination characteristics of porphyry polymetallic gold deposits, comprising:

[0008] Obtain historical ore sample data and gold balance distribution data of ore samples;

[0009] Generate an analytical model for the particle size characteristics of gold ore distribution: Use historical ore sample data to train the analytical model to generate an analytical model for the particle size characteristics of gold ore distribution, including free gold monomers and carrier mineral gold;

[0010] The gold balance distribution data in the mineral is determined by gold balance distribution with different distribution rates. Gold balance distribution refers to the content and distribution rate of gold in each mineral in the ore sample. The steps for analyzing and calculating the distribution data are as follows:

[0011] After selecting the distribution ratio of different step lengths for the gold ratio of a single mineral in the ore sample, the changes in the gold content of other minerals in the ore sample are analyzed;

[0012] The change in gold content of the single mineral at different distribution rates is introduced into the analysis model for verification, and the gold distribution rate is calculated for the gold content change data of other minerals whose distribution rate of the single mineral is changed to meet the verification accuracy;

[0013] Output simulated ore sample data based on the proportion distribution data and input it into the analysis model for continuous training;

[0014] An analysis model for analyzing gold equilibrium distribution data from measured ore sample data is obtained.

[0015] Furthermore, the acquisition of historical measured ore sample data and gold balance distribution data of the ore samples includes:

[0016] Select ore element composition data and analyze mineral composition characteristics;

[0017] Quantitative analysis of mineral types and contents of ore samples based on mineral composition;

[0018] Purify single minerals for chemical analysis, and calculate the equilibrium distribution of gold in the minerals based on the mineral composition and content;

[0019] Prepare ore samples, perform optical imaging analysis, determine the distribution size of gold particles in ore samples, and organize and output historical ore sample data and gold balance distribution data of ore samples.

[0020] Furthermore, the analysis model includes the following calculation of the training data: based on the results of the distribution grain size determination of the main minerals in the ore sample, the distribution grain size characteristics of the fine inclusions of natural gold in the main minerals are analyzed.

[0021] Furthermore, the analysis model also includes the following calculation and analysis of the training data: based on the mineral content and proportion of the ore sample, based on the percentage of free monomer gold in the total gold in the mineral, and according to the embedded particle size of the main minerals in the ore sample, the balanced distribution of gold in each mineral is analyzed, including the distribution rate and distribution amount of gold in each mineral.

[0022] Furthermore, the gold content changes of other minerals in the ore sample are analyzed after selecting the distribution ratio of different step lengths for the gold ratio of a single mineral in the ore sample, specifically including:

[0023] The minerals in the ore dressing sample data are selected in turn, including the main minerals and non-main minerals. The gold ratio is determined, including the distribution amount and distribution rate of gold in the selected minerals. The distribution amount is the content;

[0024] The gold distribution amount in the minerals under multiple groups of different distribution rates is obtained by changing the distribution rate step size except for the training data, wherein the changing distribution rate step size includes increasing or decreasing the distribution rate;

[0025] Based on the change in the proportion of gold in the selected mineral, adjust the proportion of the corresponding selected mineral in the ore sample, then calculate the data of the gold distribution amount in the selected mineral, and determine whether the data of the gold distribution amount in the selected mineral is greater than the content of the total gold in the ore sample in inclusions. When it is greater than, delete the corresponding calculated data of the gold distribution amount in the selected mineral, return to the previous level, and adjust the proportion of the corresponding selected mineral in the ore sample to re-check the correctness of the adjusted ratio.

[0026] Further, when it is judged that it is greater than, when it appears twice in succession on the judgment condition and the result is that it is judged that it is greater than, it directly skips and returns to the previous level to directly adjust the step size of the variable allocation rate.

[0027] Furthermore, the simulated data is adjusted to account for the changes in the proportion of gold in the different selected minerals;

[0028] When it is determined that the proportion of gold in non-major minerals changes, causing the non-major minerals to become major minerals, or when it is determined that the proportion of gold in major minerals changes, causing the major minerals to become non-major minerals, the adjustment step data is fed back to maintain the division rules of non-major minerals and major minerals, and the corresponding simulation data is deleted.

[0029] Furthermore, the rules for adjusting the gold content and proportion in different minerals are adjusted based on historical ore sample data, the gold content of each mineral in the ore sample is adjusted, the distribution rate is calculated based on the total amount of natural gold in the inclusion state, and it is determined whether the gold content in other minerals except the mineral whose gold content is currently adjusted is defaulted. When defaulted, the upper and lower limit gold content step data for each mineral are determined to be adjusted, wherein whether the gold content is defaulted means that the gold content in the corresponding mineral is negative or zero.

[0030] Furthermore, for the analysis model, a random forest model is generated according to the composition of the main minerals in different ore samples; different historical measured ore sample data are selected for training by different analysis models, and the selection method is: matching the corresponding historical measured ore sample data based on the main mineral characteristic values ​​of different analysis models, and then inputting the matched historical measured ore sample data into the corresponding analysis model for training.

[0031] Furthermore, it also includes generating gold balance distribution data in minerals with different distribution rates under different analysis models, obtaining corresponding simulated measurement data as derivative data based on historical measurement ore sample data, and loading them into analysis models of different mineral characteristics for continuous training and improvement.

[0032] The present invention provides a method for analyzing the distribution characteristics of porphyry polymetallic gold deposits. By using a classification model training method, the process from measuring ore sample data to analyzing gold balance data can be simplified, and the model can be used to efficiently and conveniently process data.

[0033] After the ore sample data is acquired by the AMICS mineral automatic analysis system, the present invention analyzes the gold balance ratio of a small amount of ore samples or calls the measured historical data, uses the data model method to perform cross-step analysis, and ensures low false alarm and low false alarm of the data based on multiple judgment conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0035] Figure 1 A flow chart of a method for analyzing the distribution characteristics of porphyry polymetallic gold deposits provided as an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0036] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of systems and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0037] Considering that porphyry deposits are evenly distributed, have stable mineral process properties, and contain a variety of recyclable components, but as veinlet-disseminated deposits, the separation cost is relatively difficult; however, there is a lack of research on the process mineralogy analysis of gold mines and gold-bearing minerals, which is not conducive to optimizing the production process. Traditional process mineralogy identification methods are difficult to quickly and accurately determine the occurrence state of gold mines;

[0038] By analyzing the data and the automatic mineral analysis system, the polymetallic gold deposits are analyzed, the characteristics of the embedded particles, the occurrence and filling, and the symbiotic state are analyzed, and the mineral dissociation degree is obtained. After data model analysis, the composition of the ore samples with different components and the dispersion equilibrium distribution of gold in the percentage are fuzzy quantitatively calculated. According to the composition of the ore samples and the percentage of free monomer natural gold, the proportion of natural gold in different ore sample components can be calculated.

[0039] The specific application scenario of the present invention is to analyze the equilibrium distribution of gold in different minerals in porphyry polymetallic gold deposits with different ore sample distributions.

[0040] The present invention provides a method for analyzing the distribution characteristics of porphyry polymetallic gold deposits, aiming to solve the above technical problems in the prior art.

[0041] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0042] Example 1: Figure 1 As shown, this embodiment provides a method for analyzing the distribution characteristics of porphyry polymetallic gold deposits, comprising the following steps:

[0043] A1. Generate an analysis model for the gold ore distribution granularity characteristics based on the acquired historical ore sample data and the gold balance distribution data of the ore sample; wherein the analysis model is trained with the historical ore sample data to obtain an analysis model for the gold ore distribution granularity characteristics including free gold monomer and carrier mineral gold, and the initial model can be a blank data model or an initial model with certain rules obtained based on the deep learning model commonly used in the field;

[0044] A2. Determine the distribution data of gold in minerals by gold equilibrium distribution with different distribution rates;

[0045] The steps to analyze and calculate the ratio distribution data are as follows:

[0046] A21. Analyze the changes in gold content of other minerals in the ore sample after selecting the distribution ratio of different step lengths for the gold ratio of a single mineral in the ore sample;

[0047] A22. The change of gold content of a single mineral at different distribution rates is imported into the analysis model for verification;

[0048] A23, calculating the gold distribution rate for the gold content change data of other minerals whose distribution rate of the single mineral is changed to meet the verification accuracy;

[0049] A3. Output simulated ore sample data based on the proportion distribution data and input it into the analysis model for continuous training;

[0050] A4. Obtain an analysis model for analyzing gold balance distribution data of the measured ore sample data.

[0051] Among them, in step A1, also includes the following steps B1-B5 to obtain the historical determination of the ore sample data and the gold balance distribution data of the ore sample;

[0052] B1. Select ore element composition data and analyze mineral composition characteristics;

[0053] B2. Quantitative analysis of mineral types and contents of ore samples based on mineral composition;

[0054] B3. Purify single minerals for chemical analysis and calculate the equilibrium distribution of gold in the minerals based on the mineral composition and content;

[0055] B4. Prepare slices of the ore samples and perform optical imaging analysis to obtain the measured distribution size of gold particles in the ore samples;

[0056] B5. Organize and output the historical measured ore sample data and the gold balance distribution data of the ore samples.

[0057] The analysis model also includes the following calculations of the training data: based on the results of the distribution grain size determination of the main minerals of the ore sample, the distribution grain size characteristics of the fine inclusions of natural gold in the main minerals are analyzed;

[0058] The analysis model also includes the following calculation and analysis of the training data: based on the mineral content and proportion of the ore sample, based on the percentage of free monomer gold in the total gold in the mineral, and according to the embedded grain size of the main minerals in the ore sample, the equilibrium distribution of gold in each mineral is analyzed, including the distribution rate and distribution amount of gold in each mineral;

[0059] In the analysis model, step A21 specifically includes the following implementation methods:

[0060] A211. The minerals in the ore dressing sample data are selected in turn, including the main minerals and non-main minerals. The gold ratio is determined, including the distribution amount and distribution rate of gold in the selected minerals. The distribution amount is the content;

[0061] A212, obtaining the gold distribution amount in the minerals under multiple groups of different distribution rates by changing the distribution rate step size excluding the training data, wherein the changing distribution rate step size includes increasing or decreasing the distribution rate;

[0062] A213. Based on the change in the proportion of gold in the selected mineral, adjust the proportion of the corresponding selected mineral in the ore sample, then calculate the data of the gold distribution amount in the selected mineral, and determine whether the data of the gold distribution amount in the selected mineral is greater than the content of the total gold in the ore sample in inclusions. If it is greater than, delete the corresponding calculated data of the gold distribution amount in the selected mineral, return to the previous level, and adjust the proportion of the corresponding selected mineral in the ore sample to re-check the correctness of the adjustment ratio; wherein, when it is judged that it is greater than, when it appears twice in a row on the judgment condition and the result is that it is judged that it is greater than, directly skip and return to the previous level to directly adjust the step size of the variable distribution rate.

[0063] In the process of outputting simulation data, the changes in the proportion of gold in different selected minerals in the simulation data are adjusted. When it is determined that the changes in the proportion of gold in non-major minerals cause the non-major minerals to become major minerals, or when it is determined that the changes in the proportion of gold in major minerals cause the major minerals to become non-major minerals, the adjustment step data is fed back to maintain the division rules between non-major minerals and major minerals, and the corresponding simulation data is deleted.

[0064] Embodiment 2: Based on Embodiment 1, the method further includes classifying and refining the analysis model, including:

[0065] The analysis model generates a random forest model according to the composition of the main minerals in different ore samples; different analysis models are selected for training based on different historical measured ore sample data, and the selection method is as follows: the main mineral characteristic values ​​based on different analysis models are matched with the corresponding historical measured ore sample data, and then the matched historical measured ore sample data are input into the corresponding analysis model for training; under different analysis models, the gold balance distribution data in the mineral is determined by different distribution rates of gold, and the corresponding simulated measurement data is obtained as the derivative data of the historical measured ore sample data, which is loaded into the analysis model of different mineral characteristics for continuous training and improvement.

[0066] In the embodiment of the present invention, the AMICS mineral automatic analysis system is used to refine the analysis area for the mineral types and mineral contents of the ore samples, and a new mineral boundary partitioning method and graphic processing technology are adopted based on component point analysis to determine the mineral composition, content, element distribution, particle size, intergrowth relationship, monomer dissociation degree, theoretical recovery rate estimation, porosity and other information in the ore and products. After obtaining the corresponding data, the technical concept of the present invention is used to derive the data, and a large amount of simulation data is obtained to enrich the training samples. When dealing with new and unfamiliar geological and geomorphological ore samples, when the data samples are inaccurate and incomplete, a large amount of scientific research time can be saved.

[0067] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0068] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0069] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0070] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods or systems. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0071] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0072] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention is indicated by the claims above.

Claims

1. A method for analyzing the distribution characteristics of porphyry polymetallic gold deposits, characterized in that: include: Obtain historical ore sample data and gold balance distribution data of ore samples; Generate an analytical model for the particle size characteristics of gold ore distribution: Use historical ore sample data to train the analytical model to generate an analytical model for the particle size characteristics of gold ore distribution, including free gold monomers and carrier mineral gold; The gold balance distribution data in the mineral is determined by gold balance distribution with different distribution rates. Gold balance distribution refers to the content and distribution rate of gold in each mineral in the ore sample. The steps for analyzing and calculating the distribution data are as follows: After selecting the distribution rate of different step lengths for the gold ratio of a single mineral in the ore sample, the gold content changes of other minerals in the ore sample are analyzed, specifically including: selecting the minerals in the ore sample data in turn, including selecting the main minerals and non-main minerals, determining the gold ratio includes determining the distribution amount and distribution rate of gold in the selected minerals, and the distribution amount is the content; The gold distribution amount in the minerals under multiple groups of different distribution rates is obtained by using the step length of the variable distribution rate excluding the training data, wherein the step length of the variable distribution rate includes increasing or decreasing the distribution rate; based on the change of the proportion of gold in the selected mineral, the proportion of the corresponding selected mineral in the ore sample is adjusted, and then the data of the gold distribution amount in the selected mineral is calculated, and it is determined whether the data of the gold distribution amount in the selected mineral is greater than the content of the total gold in the ore sample in the inclusions. When it is greater than, the data of the corresponding calculated gold distribution amount in the selected mineral is deleted, and the previous level is returned to adjust the proportion of the corresponding selected mineral in the ore sample to re-check the correctness of the adjustment ratio; when it appears twice in a row on the judgment condition, and the result is that it is judged to be greater than, it is directly skipped and returned to the previous level to directly adjust the step length of the variable distribution rate; Adjust the simulated data to account for changes in the proportion of gold in different selected minerals; When it is determined that the proportion of gold in non-main minerals changes, causing non-main minerals to become main minerals, or when it is determined that the proportion of gold in main minerals changes, causing main minerals to become non-main minerals, feedback is given to adjust the step length data, the division rules of non-main minerals and main minerals are maintained, and the corresponding simulation data are deleted; According to the historical determination of ore sample data, the gold content and the distribution ratio of different minerals are adjusted, the gold content of each mineral in the ore sample is adjusted, the distribution ratio is calculated based on the total amount of natural gold in the inclusion state, and it is determined whether the gold content of other minerals other than the mineral whose gold content is currently adjusted is defaulted. If it is defaulted, the upper and lower limit gold content step data of each mineral are determined, wherein the default gold content corresponds to a negative value or zero gold content in the mineral; The change in gold content of the single mineral at different distribution rates is introduced into the analysis model for verification, and the gold distribution rate is calculated for the gold content change data of other minerals whose distribution rate of the single mineral is changed to meet the verification accuracy; Output simulated ore sample data based on the proportion distribution data and input it into the analysis model for continuous training; An analysis model for analyzing gold equilibrium distribution data from measured ore sample data is obtained.

2. The method for analyzing the distribution characteristics of porphyry polymetallic gold deposits according to claim 1, characterized in that: The acquisition of historical measured ore sample data and gold balance distribution data of the ore samples includes: Select ore element composition data and analyze mineral composition characteristics; Quantitative analysis of mineral types and contents of ore samples based on mineral composition; Purify single minerals for chemical analysis, and calculate the equilibrium distribution of gold in the minerals based on the mineral composition and content; Prepare ore samples, perform optical imaging analysis, obtain the measured distribution size of gold particles in the ore samples, organize and output the historical measured ore sample data and the gold balance distribution data of the ore samples.

3. The method for analyzing the distribution characteristics of porphyry polymetallic gold deposits according to claim 2, characterized in that: The analysis model includes the following calculations on the training data: based on the results of the distribution grain size determination of the main minerals in the ore sample, the distribution grain size characteristics of the fine inclusions of natural gold in the main minerals are analyzed.

4. The method for analyzing the distribution characteristics of porphyry polymetallic gold deposits according to claim 3, characterized in that: The analysis model also includes the following calculation and analysis of the training data: based on the mineral content and proportion of the ore sample, based on the percentage of free monomer gold in the total gold in the mineral, and according to the embedded particle size of the main minerals in the ore sample, the balanced distribution of gold in each mineral is analyzed, including the distribution rate and distribution amount of gold in each mineral.

5. A method for analyzing the distribution characteristics of porphyry polymetallic gold deposits according to any one of claims 1 to 4, characterized in that: For the analysis model, the analysis model generates a random forest model corresponding to the composition of the main minerals in different ore samples; different historical measured ore sample data select different analysis models for training, and the selection method is: matching the corresponding historical measured ore sample data based on the main mineral characteristic values ​​of different analysis models, and then inputting the matched historical measured ore sample data into the corresponding analysis model for training.

6. The method for analyzing the distribution characteristics of porphyry polymetallic gold deposits according to claim 5, characterized in that: It also includes generating gold balance distribution data in minerals with different distribution rates under different analysis models, obtaining corresponding simulated measurement data as derivative data based on historical measurement ore sample data, and loading it into analysis models of different mineral characteristics for continuous training and improvement.

Images