A rapid assessment method for metal recovery potential in mining solid waste

Abstract

The invention discloses a method for rapidly evaluating the metal recovery potential in mining solid waste; the method comprises: obtaining the particle size distribution, oxide content, burning vector and metal element concentration of the mining solid waste; inputting the particle size distribution, oxide content, burning vector and metal element concentration of the mining solid waste into an inversion model of metal occurrence forms of the mining solid waste, and outputting the occurrence form proportion of each metal in the mining solid waste; obtaining the recovery potential value of the mining solid waste by calculation according to the occurrence form proportion of each metal in the mining solid waste; the method can be used to rapidly, highly precisely and accurately predict the occurrence forms of metals in mining solid waste, and then evaluate the metal recovery potential in the mining solid waste, and the method has broad practical application significance, and can provide strong technical support for the field of solid waste utilization in my country.

Description

Technical Field

[0001] The invention belongs to the technical field of mining solid waste utilization, and in particular to a method for quickly evaluating the metal recovery potential in mining solid waste. Background Art

[0002] At present, enterprises pay more attention to the utilization of resources in the main process. Once the materials come out of the main process and form solid waste, they are usually disposed of as waste. However, after certain treatment or processing of solid waste, the useful substances contained in it can be extracted and continue to play a role in industrial and agricultural production processes. Some solid waste can also change its form and become new energy or resources. This transformation from solid waste to useful substances is called the comprehensive utilization of solid waste, or the resourceization of solid waste. Mining solid waste is one of the industrial waste residues with the largest emission and stacking volume. However, the utilization rate of mining solid waste in my country is less than 40%, and the remaining can only be stacked in large-scale yards, which not only pollutes the environment, but also occupies a large amount of land resources.

[0003] In recent years, the comprehensive utilization of mining solid waste has been increasingly favored by scholars. The recycling potential of metals in mining solid waste has aroused great interest in the academic community. However, to evaluate the recycling potential of metals in mining solid waste, it is first necessary to study the metal occurrence forms. At present, the main methods for identifying the metal occurrence forms are Tessier continuous extraction method and BCR continuous extraction method. However, these methods have not been widely promoted and used because they are complex, time-consuming, costly and require professional knowledge, which seriously hinders the re-extraction of metal resources from mining solid waste.

[0004] Therefore, how to conduct a more efficient, accurate and rapid assessment of the metal recovery potential in mining solid waste to provide certain guidance for the recycling of mining solid waste has become a key issue in current research. Summary of the invention

[0005] In view of the above problems, the present invention provides a method for rapid assessment of the metal recovery potential in mining solid waste, which at least solves some of the above technical problems. The method uses a machine learning method to quickly, highly precisely and accurately predict the occurrence forms of metals in mining solid waste, and then assesses the metal recovery potential in mining solid waste. The method has broad practical application significance and can provide strong technical support for my country's solid waste utilization field.

[0006] The embodiment of the present invention provides a method for quickly evaluating the metal recovery potential in mining solid waste, comprising:

[0007] S1. Obtain the particle size distribution, oxide content, burning vector and metal element concentration of mining solid waste;

[0008] S2. Input the particle size distribution, oxide content, burning vector and metal element concentration of the mining solid waste into the mining solid waste metal occurrence form inversion model, and output the occurrence form proportion of each metal in the mining solid waste;

[0009] S3. According to the proportion of the occurrence form of each metal in the mining solid waste, the recovery potential value of the mining solid waste is obtained by calculation.

[0010] Furthermore, the S1 specifically includes:

[0011] Use laser particle size analyzer to obtain particle size distribution of mining solid waste;

[0012] Using an X-ray fluorescence spectrometer to obtain the oxide content of the mining solid waste;

[0013] The burning vector and metal element concentration of the mining solid waste are obtained by using an inductively coupled plasma atomic emission spectrometry measuring instrument.

[0014] Furthermore, the mining solid waste metal occurrence morphology inversion model is generated by training the following steps, including:

[0015] Obtain the particle size distribution, oxide content, burning vector and metal element concentration of a large number of mining solid wastes respectively;

[0016] The BCR continuous extraction method is used to obtain the occurrence forms of various metals in the mining solid waste;

[0017] According to the occurrence forms of various metals in the mining solid waste, the occurrence form ratio of each metal in the mining solid waste is calculated by inductively coupled plasma atomic emission spectrometry;

[0018] The particle size distribution, oxide content, combustion vector and metal element concentration of the large amount of mining solid waste are taken as input, and the corresponding occurrence form proportion of each metal in the mining solid waste is taken as output, and an algorithm model based on machine learning is trained to generate an inversion model of metal occurrence form of mining solid waste.

[0019] Furthermore, the existing forms include water-soluble state, acid-soluble state, reducible state, oxidizable state and residual state.

[0020] Furthermore, in S3, the calculation formula corresponding to the recovery potential value of the mining solid waste is expressed as:

[0021]

[0022] Where RP represents the recovery potential value; n represents the type of metal in mining solid waste; m represents the type of occurrence form corresponding to various metals in mining solid waste; F jirepresents the proportion of the i-th occurrence form corresponding to the j-th metal in mining solid waste; D ji W represents the extraction convenience coefficient of the i-th occurrence form corresponding to the j-th metal in mining solid waste; j represents the content of the jth metal in mining solid waste; P j Represents the price of the jth metal in mining solid waste.

[0023] Compared with the prior art, the method for rapid assessment of metal recovery potential in mining solid waste described in the present invention has the following beneficial effects:

[0024] 1. The present invention is a method based on machine learning. It establishes a prediction model for metal occurrence forms based on the basic characteristics and component information of mining solid waste and the properties of metal elements. The prediction model is applied in practice to make a highly accurate, efficient and rapid prediction of the metal occurrence forms in mining solid waste with different basic characteristics and component information, and then to quickly evaluate the metal recovery potential in mining solid waste. It has a guiding role in the recovery and comprehensive treatment of metal resources in mining solid waste.

[0025] 2. The present invention has the advantages of high efficiency, economy, environmental protection and high accuracy, which makes up for the shortcomings of indoor continuous extraction method, such as complicated operation and time-consuming. The present invention has strong practical applicability and fast and convenient operation. It only needs to train the training set to establish a highly accurate and efficient prediction model, and its economy and practicality are very significant.

[0026] 3. The present invention innovatively utilizes the extraction difficulty of metals in different occurrence forms in mining solid waste to evaluate their recovery potential, which makes up for the current deficiency of directly evaluating the recovery potential by the total amount of metals, and can provide guidance for the subsequent metal recovery.

[0027] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0028] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0030] Figure 1 A flow chart of a method for rapidly assessing the metal recovery potential in mining solid waste provided in an embodiment of the present invention.

[0031] Figure 2 A comparison result diagram between the predicted value and the actual value of the metal occurrence form percentage provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0033] See also Figure 1 As shown, an embodiment of the present invention provides a method for quickly evaluating the metal recovery potential in mining solid waste, which specifically includes the following steps:

[0034] S1. Obtain the particle size distribution, oxide content, burning vector and metal element concentration of mining solid waste;

[0035] S2. Input the particle size distribution, oxide content, burning vector and metal element concentration of the mining solid waste into the mining solid waste metal occurrence form inversion model, and output the occurrence form proportion of each metal in the mining solid waste;

[0036] S3. According to the proportion of the occurrence form of each metal in the mining solid waste, the recovery potential value of the mining solid waste is obtained by calculation.

[0037] The following is a detailed description of each of the above steps.

[0038] In the above step S1, the basic characteristics and component information of the target mining solid waste are mainly obtained; wherein, the basic characteristics include particle size gradation, etc., and the component information includes oxide content, burning vector and metal element concentration, etc.; in the embodiment of the present invention, the target mining solid waste is selected as fly ash; specifically, a laser particle size analyzer is used to obtain the particle size gradation of the mining solid waste (D10, D30, D50, D60, D90, unit um); an X-ray fluorescence spectrometer is used to obtain the oxide content of the mining solid waste (SiO2, Al2O3, Fe2O3, K2O, CaO, MgO, P2O5, TiO2, SO2, etc., unit %); an inductively coupled plasma atomic emission spectrometry instrument is used to obtain the burning vector (unit %) and metal element concentration (wherein metals include Ca, Al, Mg, Fe, V, Cr, As, Mo, Sb, W, etc., unit mg / kg) of the mining solid waste.

[0039] In the above step S2, the particle size distribution, oxide content, burning vector and metal element concentration of the mining solid waste are input into the mining solid waste metal occurrence form inversion model, and the occurrence form proportion of each metal in the mining solid waste is output; wherein the metal occurrence forms include water-soluble state, acid-soluble state, reducible state, oxidizable state and residual state;

[0040] The specific training process of the mining solid waste metal occurrence morphology inversion model mentioned in this step is as follows: In the embodiment of the present invention, the mining solid waste is selected as fly ash, and 10 types of fly ash are used as samples;

[0041] First, it is necessary to obtain the particle size distribution, oxide content, burning vector and metal element concentration of each metal in the 10 fly ashes;

[0042] Secondly, the BCR continuous extraction method is used to obtain the occurrence form of each metal in the 10 fly ashes; for each fly ash, it specifically includes: the first step: take 40ml of pure water and 1g of fly ash, shake it under 25℃ pure water for 16 hours, and filter to obtain the water-soluble filtrate F1 of the fly ash, that is, the water-soluble state. The second step: add 40ml0.11mol·L-1CH3COOH to the solid obtained after filtering in the first step, and shake it under acid-soluble conditions at 25℃ for 16 hours, and filter to obtain the acid-soluble filtrate F2 of the fly ash, that is, the acid-soluble state. The third step: add 40ml 0.5mol·L-1NH2OH·HCl (pH=1.5, adjusted with HNO3) to the solid obtained after filtering in the second step, and shake it at a reducible temperature of 25℃ for 16 hours, and filter to obtain the reducible filtrate F3 of the fly ash, that is, the reducible state. Step 4: Add 10 mL of 30% H2O2 to the solid obtained after filtering in the third step, shake at 25°C for 1 hour, and then shake at 85°C for 1 hour to evaporate. Add 10 ml of 30% H2O2 again, shake at 85°C for 1 hour to evaporate. Then, add 50 mL of 1.0 mol·L-1 CH3COONH4 (pH=2, adjusted by HNO3), shake at 25° for 16 hours, and filter to obtain the oxidizable filtrate F4 of the fly ash, that is, the oxidizable state. Step 5: In a microwave oven at 220°C, add 7 ml of HNO3 (60%), 2.5 ml of 46% HF and 0.5 ml of 30% H2O2 to a polytetrafluoroethylene container for 20 minutes, and filter to obtain the residual filtrate F5 of the fly ash, that is, the residual state. The content of each metal in the above five filtrates was measured by inductively coupled plasma atomic emission spectrometry, and the proportion of the corresponding occurrence form of each metal was calculated. The content of each metal in different filtrates corresponds to the occurrence form of each metal in the fly ash.

[0043] Finally, the particle size distribution, oxide content, burning vector and metal element concentration of the fly ash obtained above are used as input, and the corresponding proportions of water-soluble, acid-soluble, reducible, oxidizable and residual states are used as output, and a data set is constructed based on this; the data set is preprocessed for data normalization; the preprocessed data set is divided into a training set and a test set by a convergence test; in an embodiment of the present invention, the ratio of the training set to the test set is 8:2; that is, the division standard of the data set in the example of the present invention is that the training set size accounts for 80% and the test set size accounts for 20%; then a machine algorithm model is established based on the random forest regression algorithm, and the hyperparameters in the model are optimized by a genetic algorithm; specifically, the population size is determined to be 100, the termination evolution generation of the genetic algorithm is determined to be 100, the crossover probability is determined to be 0.4, and the mutation probability is determined to be 0.01. In order to avoid the randomness of the results, a 10-fold cross validation is adopted. The optimized hyperparameters are substituted into the random forest algorithm, and the final random forest model is constructed using the training set, and the generalization ability of the model is evaluated by the test set. It is explained here that for the mining solid waste metal occurrence morphology inversion model provided in the embodiment of the present invention, the machine learning algorithm models used in the training process include but are not limited to decision trees, support vector machines, and neural networks; the hyperparameters of the machine learning model are determined by the optimization algorithm on the training set, wherein the optimization algorithm includes the gradient descent method, the Newton method, the artificial bee colony algorithm, and the heuristic optimization method; the test set is used to verify the effect of the prediction model, and when the final mining solid waste metal occurrence morphology inversion model is obtained, the parameters for testing the effect of the prediction model include but are not limited to the correlation coefficient (R), mean error (MSE), root mean square error (RMSE), mean absolute error (MAE), and R-Squared.

[0044] In the embodiment of the present invention, R2 is selected to evaluate the generalization ability of the model. R2 is the determination coefficient, and its value reflects an important statistic of the goodness of fit of the model, which is the ratio of the regression sum of squares to the total sum of squares. The normal value range is [0,1]. The closer to 1, the better the model fit. R2 can be calculated by the following formula:

[0045]

[0046] Where n represents the number of samples; y k Indicates actual value; represents the predicted value; represents the average value of the sample; k represents the kth sample data.

[0047] Figure 2 It is a fitting result diagram between the actual value and the predicted value of the percentage of metal occurrence state of fly ash in the embodiment of the present invention; Figure 2It can be concluded that in the embodiment of the present invention, the fitting effects of the true value and the predicted value in the training set and the test set are good. 2 The value is 0.981, and the R 2 The value is 0.878, which proves that the prediction effect of the model is good.

[0048] In the above step S3, Table 1 shows the content and occurrence ratio of each metal in the first type of mining solid waste.

[0049] Table 1: The content and occurrence ratio of each metal in the first type of fly ash

[0050]

[0051]

[0052] According to the proportion of the occurrence forms corresponding to each metal, the recycling potential value of the mining solid waste is calculated, and the calculation formula is expressed as:

[0053]

[0054] Where RP represents the recovery potential value; n represents the type of metal in mining solid waste; m represents the type of occurrence form corresponding to various metals in mining solid waste; F ji represents the proportion of the i-th occurrence form corresponding to the j-th metal in mining solid waste; D ji W represents the extraction convenience coefficient of the i-th occurrence form corresponding to the j-th metal in mining solid waste (between 0 and 1); j represents the content of the jth metal in mining solid waste; P j Represents the price of the jth metal in mining solid waste.

[0055] In the embodiment of the present invention, the extraction convenience coefficients of F1 to F5 are 1, 0.8, 0.6, 0.3, and 0.1; the metal prices are Ca=43600 yuan / ton, Al=22910 yuan / ton, Mg=43100 yuan / ton, Fe=4750 yuan / ton, V=160000 yuan / ton, Cr=78000 yuan / ton, As=9200 yuan / ton, Mo=181000 yuan / ton, Sb=83000 yuan / ton, W=315000 yuan / ton; combined with Table 1 and RP calculation formula, it can be calculated that the metal recovery potential value of fly ash 1 is 1143.062; similarly, the recovery potential values ​​of 10 kinds of fly ashes can be calculated and shown in Table 2. From Table 2, it can be concluded that among these 10 kinds of fly ashes, the recovery potential value of fly ash 7 is the highest. Therefore, it can be concluded that among these 10 kinds of fly ashes, fly ash 7 has the greatest recovery potential.

[0056] Table 2: Recycling potential values ​​of 10 types of fly ash

[0057] Fly ash RP Fly ash RP 1 1143.062 2 1064.822 3 526.0286 4 333.7782 5 1325.685 6 501.7088 7 1489.631 8 786.9561 9 334.2357 10 424.8629

[0058] Through the method provided in the embodiment of the present invention, not only can the mining solid waste with the highest recycling potential value be selected from a variety of mining solid wastes; the metal recycling potential of a single mining solid waste can also be evaluated, for example, a threshold is set, and when the recycling potential value of the metal is greater than or equal to the threshold, it indicates that the mining solid waste has recycling potential; in addition, multiple threshold ranges can be set, and the recycling potentials corresponding to these multiple threshold ranges are: no recycling potential, low recycling potential, and high recycling potential, respectively; for example, the threshold ranges are set to 0-500, 500-1000, and 1000-2000; when the recycling potential value is between 0-500, it indicates that the mining solid waste has no recycling value, that is, no recycling potential; when the recycling potential is between 500-1000, it indicates that the recycling value of the mining solid waste is low; when the recycling potential is between 1000-2000, it indicates that the recycling value of the mining solid waste is high.

[0059] Finally, it should be pointed out that the above examples are only used to illustrate the calculation process of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above examples, a person skilled in the art should understand that the calculation process described in the above examples can still be modified, or some parameters can be replaced by equivalents, and these modifications or replacements do not make the essence of the corresponding calculation method deviate from the spirit and scope of the calculation method of the present invention.

[0060] The present invention is not limited to the embodiments described above. The above description of the specific embodiments is intended to describe and illustrate the technical solution of the present invention. The above specific embodiments are merely illustrative and not restrictive. Without departing from the scope of the present invention and the scope of protection of the claims, a person of ordinary skill in the art can also make many forms of specific changes under the guidance of the present invention, which all fall within the scope of protection of the present invention.

Claims

1. A method for rapid assessment of metal recovery potential in mining solid waste, characterized in that: include: S1. Obtain the particle size distribution, oxide content, burning vector and metal element concentration of mining solid waste; S2. Input the particle size distribution, oxide content, burning vector and metal element concentration of the mining solid waste into the mining solid waste metal occurrence form inversion model, and output the occurrence form proportion of each metal in the mining solid waste; S3. Obtaining the recovery potential value of the mining solid waste by calculation according to the proportion of the occurrence form of each metal in the mining solid waste; The mining solid waste metal occurrence morphology inversion model is generated by training the following steps, including: Obtain the particle size distribution, oxide content, burning vector and metal element concentration of a large number of mining solid wastes respectively; The BCR continuous extraction method is used to obtain the occurrence forms of various metals in the mining solid waste; According to the occurrence forms of various metals in the mining solid waste, the occurrence form ratio of each metal in the mining solid waste is calculated by inductively coupled plasma atomic emission spectrometry; Taking the particle size distribution, oxide content, burning vector and metal element concentration of the large amount of mining solid waste as input, taking the corresponding occurrence form proportion of each metal in the mining solid waste as output, training the algorithm model based on machine learning, and generating the inversion model of the occurrence form of metals in mining solid waste; In S3, the calculation formula corresponding to the recovery potential value of the mining solid waste is expressed as: Where RP represents the recovery potential value; n represents the type of metal in mining solid waste; m represents the type of occurrence form corresponding to various metals in mining solid waste; F ji represents the proportion of the i-th occurrence form corresponding to the j-th metal in mining solid waste; D ji W represents the extraction convenience coefficient of the i-th occurrence form corresponding to the j-th metal in mining solid waste; j represents the content of the jth metal in mining solid waste; P j represents the price of the jth metal in mining solid waste.

2. A method for rapid assessment of metal recovery potential in mining solid waste according to claim 1, characterized in that: The S1 specifically includes: Use laser particle size analyzer to obtain particle size distribution of mining solid waste; Using an X-ray fluorescence spectrometer to obtain the oxide content of the mining solid waste; The burning vector and metal element concentration of the mining solid waste are obtained by using an inductively coupled plasma atomic emission spectrometry measuring instrument.

3. A method for rapid assessment of metal recovery potential in mining solid waste according to claim 1, characterized in that: The existing forms include water-soluble state, acid-soluble state, reducible state, oxidizable state and residual state.

Images