A method for evaluating the occurrence forms and pollution risks of toxic elements in mining solid waste

Abstract

The present invention discloses a method for rapidly evaluating the occurrence forms and pollution risks of toxic elements in mining solid wastes, and the specific steps are as follows: sample collection and determination of physical and chemical properties; extraction of the total amount and occurrence forms of toxic elements in mining solid wastes to understand the biological effectiveness of toxic elements in mining solid wastes; forming a rapid prediction method for the occurrence forms of toxic elements in mining solid wastes based on artificial intelligence algorithms; and forming a method for assessing the pollution risks of toxic elements in mining solid wastes. The present invention uses the relationship between the occurrence forms of toxic elements in mining solid wastes and their chemical composition to establish a machine learning model, thereby predicting the corresponding content of each occurrence form of toxic elements in mining solid wastes, and then assessing the pollution risks of toxic elements in mining solid wastes. The method has high accuracy in judging the occurrence forms of toxic elements, simple process, and low cost, and is of great significance for the assessment of potential pollution risks of mining solid wastes, and at the same time provides a scientific basis for the rational treatment and utilization of mining solid wastes.

Description

Technical Field

[0001] The present invention relates to the technical field of pollution risk assessment, and in particular to an intelligent analysis method for the pollution risk of toxic elements in mining solid waste. Background Art

[0002] In recent years, environmental pollution problems have occurred frequently in mining areas, and the remediation of harmful element pollution has always attracted social attention. In previous studies on mining pollution, the environmental hazards caused by mining solid waste have always been taken seriously. After many mining operations, due to the failure to promptly handle mining solid waste or the failure to take any environmental control measures, over time, accompanied by the influence of climate factors (such as rain and wind), soil, water, air and biota are polluted. Efficient and reasonable assessment of the potential environmental risks of mining solid waste is the key to the disposal and utilization of mining solid waste.

[0003] At present, the potential environmental risks of mining solid waste are mostly measured through environmental indicators. Domestic and foreign scholars have proposed a variety of pollution evaluation methods for toxic elements from different perspectives. For example, the potential ecological index method proposed by the famous Swedish geochemist Hakanson is one of the most commonly used methods for evaluating the degree of pollution of toxic elements. One of the focuses of this method is to determine the toxicity coefficient of toxic elements. However, the current environmental pollution evaluation generally focuses on the total content of toxic elements in mining solid waste, and has not yet considered the impact of the occurrence form of toxic elements on their environmental risks; at the same time, most of these evaluation methods are time-consuming and labor-intensive, and the operation is complex and requires professional knowledge, which seriously hinders the comprehensive management of mining solid waste. Therefore, there is an urgent need for a fast and efficient mining solid waste pollution evaluation method to provide certain guidance for the analysis and management of mining solid waste. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method for rapidly evaluating the occurrence forms and pollution risks of toxic elements in mining solid wastes. The method uses artificial intelligence methods to rapidly, highly precisely and accurately predict the occurrence forms of toxic elements in mining solid wastes, thereby evaluating the potential pollution risks of toxic elements in mining solid wastes. This method has broad practical application significance and can provide strong technical support for my country's solid waste management field.

[0005] The objective of the present invention is achieved through the following technical solutions:

[0006] A method for evaluating the occurrence forms and pollution risks of toxic elements in mining solid wastes, comprising:

[0007] S1. Collect samples and determine the physical and chemical properties of mining solid waste;

[0008] S2. Extract the total amount and occurrence forms of toxic elements in mining solid waste samples, summarize the occurrence forms of toxic elements, physical and chemical properties of mining solid waste, and properties of toxic elements into a data set, and collect bioavailability indicators of toxic elements in mining solid waste;

[0009] S3. After preprocessing the data set, an artificial intelligence algorithm is selected to optimize the hyperparameters to obtain the final prediction model for the occurrence form of toxic elements in mining solid waste;

[0010] S4. Based on the content of toxic elements in mining solid waste, the occurrence form of toxic elements, the leaching risk coefficient of toxic elements, and the toxic response coefficient of toxic elements, the pollution risk of toxic elements in mining solid waste is evaluated. The calculation formula is as follows:

[0011]

[0012] Among them, PR represents the pollution risk value of mining solid waste, n represents the total number of toxic elements in mining solid waste, m represents the type of toxic element occurrence, F ji is the percentage of the i-th occurrence form of the j-th toxic element, M ji is the leaching risk coefficient of the i-th occurrence form of the j-th toxic element, M ji Between 0-1, W j is the content of the jth toxic element in mining solid waste, is the toxicity response coefficient of the jth toxic element; the leaching risk coefficient in the formula is based on the existing extraction technology level and refers to expert opinions.

[0013] Furthermore, in step S1, the physical and chemical properties of mining solid waste are determined through laboratory experiments, including density, water content, compressibility, ignition loss, particle size distribution, porosity, permeability, element or oxide content, phase composition, toxic element concentration, organic matter content, pH, alkalinity, redox properties, clay mineral content, and biological properties. The physical and chemical properties of mining solid waste directly affect the occurrence form of toxic elements in mining solid waste.

[0014] Furthermore, the properties of toxic elements include atomic number, relative atomic mass, ion radius, and number of outermost electrons; the bioavailability index refers to the toxic response coefficient T of the toxic element. r .

[0015] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of a method for evaluating the occurrence forms and pollution risks of toxic elements in mining solid waste are implemented.

[0016] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for evaluating the occurrence forms and pollution risks of toxic elements in mining solid waste.

[0017] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0018] 1. The present invention is a method based on artificial intelligence, which trains the known characteristic values ​​that affect the occurrence forms of toxic elements in mining solid waste, establishes a prediction model, and applies the prediction model in practice. It can make a highly accurate, efficient and rapid prediction of the occurrence forms of toxic elements in mining solid waste from different sources, and then evaluate the potential pollution risk of toxic elements in mining solid waste. It has a guiding role in the comprehensive management and utilization of mining solid waste.

[0019] 2. The present invention has the advantages of high efficiency, economy, environmental protection and high accuracy, which makes up for the shortcomings of the Tessier continuous extraction method and the BCR continuous extraction method, which are complicated and time-consuming. The present invention has strong practical applicability, fast and convenient operation, and only needs to train the training set to establish a highly accurate and efficient prediction model, and its economy and practicality are very significant.

[0020] 3. The data for evaluating toxic element pollution at present is the total amount of toxic elements obtained by chemical full analysis. However, toxic elements in the form of residues are difficult to be absorbed by plants and have a very limited impact on the food chain. Therefore, the content of toxic elements in different forms in mining solid waste should be tested separately to analyze the pollution degree of mining solid waste and then classify and manage the polluted mining solid waste. Therefore, this method establishes an effective method for evaluating the cause and degree of pollution of multiple forms of toxic elements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of the process of the present invention.

[0022] Figure 2 These are the laboratory test results of the occurrence forms of toxic elements such as V, Cr, and As in a certain mining solid waste.

[0023] Figure 3 It is a fitting result diagram between the actual value and the predicted value of the proportion of the toxic element occurrence form in Example 1.

[0024] Figure 4 It is a fitting result diagram between the actual value and the predicted value of the proportion of the toxic element occurrence form in Example 2. DETAILED DESCRIPTION

[0025] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0026] Example 1

[0027] A method for rapidly evaluating the occurrence forms and pollution risks of toxic elements in mining solid wastes, referring to Figure 1 As shown, it includes the following steps:

[0028] 1. Collect mining solid waste samples and determine their physical and chemical properties. The basic characteristics and component information of mining solid waste evaluated in this example include the concentration of toxic elements (including V, Cr, As, measured by inductively coupled plasma atomic emission spectrometry, unit: mg / kg), particle size distribution (D10, D30, D50, D60, D90, measured by laser particle size analyzer, unit: um), loss on ignition (measured by thermogravimetry, unit: %), and oxide content (MgO, Fe2O3, SO2, SiO2, CaO, P2O5, K2O, TiO2, Al2O3, measured by X-ray fluorescence spectroscopy, unit: %). Figure 2 These are the laboratory test results of the occurrence forms of toxic elements such as V, Cr, and As in a certain mining solid waste.

[0029] 2. Based on the characteristics determined in step 1, this example collected 10 samples of mining solid waste and extracted toxic elements in the mining solid waste through a continuous extraction method, where the continuous extraction method consists of the following five steps:

[0030] Step 201. Take 1 g of mining solid waste, put it into a 100 mL centrifuge tube, add 40 mL of pure water, shake it on a mechanical shaker at 25° C. for 16 hours, separate the solid residue from the extract, and obtain the extract B0 of the mining solid waste.

[0031] Step 202. Place the solid residue obtained in step 201 into a centrifuge tube and add 40 ml CH3COOH (0.11 mol·L -1 ), under acid-soluble conditions at 25° C., the extraction process is performed in the same manner as described in step 201 to obtain an extract B1 of the mining solid waste.

[0032] Step 203. Place the solid residue obtained in step 202 into a centrifuge tube and add 40 ml NH2OH·HCl (0.5 mol·L -1 ), adjust the solution pH to 1.5 with HNO3, and perform the extraction process in the same manner as described in step 201 at a reducing temperature of 25°C to obtain an extract B2 of the mining solid waste.

[0033] Step 204. Carefully add 10 mL of hydrogen peroxide (30%, pH 2.0) to the residue from step 203 and digest at room temperature for 1 hour, shaking occasionally by hand. Heat the container to 85°C in a water bath and continue digestion for 1 hour, then heat and evaporate to near dryness. Add another 10 mL of hydrogen peroxide (30%, pH 2.0) and repeat the digestion. Then, add 50 mL of CH3COONH4 (1.0 mol·L -1 ) is added to the residue, and the extraction process is performed in the same manner as described in step 201 at 25° C. (the pH is adjusted to 2.0 with HNO 3) to obtain an extract B3 of the mining solid waste.

[0034] Step 205. In a microwave oven at 220° C., add 7 ml HNO3 (60%), 2.5 ml HF (46%) and 0.5 ml H2O2 (30%) to a polytetrafluoroethylene container, continue digestion for 20 minutes, and filter to obtain the extract B4 of the mining solid waste. The content of each toxic element in the five extracts of each mining solid waste is measured by inductively coupled plasma atomic emission spectrometry and the percentage is calculated. The content of each toxic element in different extracts corresponds to the occurrence form of each toxic element in the mining solid waste. Solutions B0 to B4 correspond to water-extractable state, acid-extractable state, iron-manganese oxide-bound state, organic matter and sulfide-bound state, and residual lattice state, respectively. Figure 2 Shown are the laboratory experimental results of the occurrence forms of toxic elements V, Cr, and As in the first type of mining solid waste.

[0035] Based on the above experiments, the basic characteristics and component information of mining solid waste, the properties of toxic elements (atomic volume, electron affinity, covalent atomic radius, relative atomic mass, electronegativity and atomic number are used as representatives in this example), the total concentration of toxic elements in the sample, and the occurrence form of toxic elements are taken as input, and the proportion of the occurrence form is used as output to construct a data set.

[0036] Data on the bioavailability of toxic elements were collected. The toxic response coefficients of V, Cr, and As in the toxic elements tested in this example were 2, 2, and 10, respectively.

[0037] 3. The sample data collected by steps 1 and 2 need to be preprocessed by data normalization to improve the performance of the model. The convergence test determines that the division ratio of the training set and the test set is 7:3, that is, the division standard of the data set in this example is that the training set size accounts for 70% and the test set size accounts for 30%. This example selects the neural network regression algorithm as the machine learning algorithm model. In order to optimize the algorithm, this example uses the particle swarm algorithm to optimize the hyperparameters. In this example, the population size is 100 and the termination evolution generation of the particle swarm algorithm is 100. In order to avoid the randomness of the results, 10-fold cross validation is used. Substitute the optimized hyperparameters into the neural network algorithm and use the training set to build the final neural network model. The generalization ability of the neural network model is evaluated by the test set. This example uses R to evaluate the generalization ability of the neural network model. R is the correlation coefficient, and its value reflects the important statistic of the linear correlation between the variables of the neural network model. The normal value range is [-1, 1]. The closer the absolute value is to 1, the better the model fit. R can be calculated by the following formula.

[0038]

[0039] n is the number of samples, y i is the actual value, is the predicted value, is the average of the actual values ​​of the samples, is the mean of the sample predictions.

[0040] Figure 3 It is a fitting diagram between the actual value and the predicted value of the proportion of the toxic element occurrence form in Example 1. The fitting effect of the actual value and the predicted value in the training set and the test set is good, the R value in the training set is 0.989, and the R value in the test set is 0.955. Therefore, the prediction effect of this model is good.

[0041] 4. Based on the content of toxic elements in mining solid waste, the occurrence form of toxic elements, leaching risk coefficient, and toxic response coefficient of toxic elements, the pollution risk of toxic elements in mining solid waste is evaluated. The calculation formula is as follows:

[0042]

[0043] Among them, PR represents the pollution risk value of mining solid waste, n represents the total number of toxic elements in mining solid waste, m represents the total number of toxic elements divided into m types through continuous extraction method, and F ji is the percentage of the i-th occurrence form of the j-th toxic element, M ji is the leaching risk coefficient of the i-th occurrence form of the j-th toxic element (between 0 and 1), W j is the content of the jth toxic element in mining solid waste, is the toxic response coefficient of the jth toxic element. The leaching risk coefficient in the formula is based on the existing extraction technology level and reference to expert opinions.

[0044] The leaching risk coefficient in the formula is based on the current level of extraction technology. The difficulty of extracting toxic elements by direct immersion in water and by adsorption reaction by adding chemical components such as acid and alkali is very different. Based on the above concept analysis, this example sets the leaching risk coefficients of B0 to B4 as 1, 0.7, 0.5, 0.3, and 0.1. The toxic response coefficient T of the toxic element obtained in step 2 is r j As V=2, Cr=2, As=10, combined with Table 1 and PR calculation formula, the pollution risk value of mining solid waste No. 1 can be calculated as 298.4753. Similarly, the pollution risk values ​​of 10 types of mining solid wastes can be calculated, see Table 1. It can be seen that mining solid waste No. 9 has the highest pollution risk, and mining solid waste No. 3 has the lowest pollution risk.

[0045] Table 1 Pollution risk values ​​of 10 types of mining solid wastes

[0046]

[0047]

[0048] Example 2

[0049] This embodiment provides a method for quickly evaluating the occurrence form and pollution risk of toxic elements in mining solid waste. Figure 1 As shown, the specific implementation method includes the following steps:

[0050] 1. Collection of mining solid waste samples and determination of physical and chemical properties. The basic characteristics and component information of mining solid waste evaluated in this example include the concentration of toxic elements (including Zn, Cd, Cu, Ni, Pb, measured by inductively coupled plasma atomic emission spectrometry, unit: mg / kg), particle size distribution (D10, D30, D50, D60, D90, measured by laser particle size analyzer, unit: um), loss on ignition (measured by thermogravimetry, unit: %), and oxide content (MgO, Fe2O3, SO2, SiO2, CaO, P2O5, K2O, TiO2, Al2O3, measured by X-ray fluorescence spectroscopy, unit: %).

[0051] 2. Based on the characteristics determined in step 1, this example collected samples of two types of mining solid waste and extracted toxic elements in the mining solid waste using the Tessier continuous extraction method, where the continuous extraction method consists of the following five steps.

[0052] Accurately weigh 2 g of mining solid waste sample and carefully place it into a 100 mL hard plastic round-bottom centrifuge tube with a lid for step-by-step extraction.

[0053] (1) Add 16 mL of 1 mol / L MgCl2 solution, pH = 7.0, shake continuously at 25°C for 1 hour, centrifuge for 20 minutes, remove the supernatant and dilute to a 25 mL volumetric flask for testing. Wash the residue with deionized water, centrifuge, and then filter all the supernatant to determine the concentration of toxic elements.

[0054] (2) Carbonate-bound state: Add 16 mL of 1 mol / L NaAc solution to the residue in step (1), pH = 5.0, and shake continuously for 8 h at (25 ± 1) °C. Centrifuge for 20 min, aspirate the supernatant, and dilute to a 25 mL volumetric flask as the atomic absorption test solution. Wash the residue with deionized water, centrifuge, and then filter all the supernatant to determine the concentration of toxic elements.

[0055] (3) Iron and manganese oxide binding state: Add 16 mL of 0.04 mol / L NH2OH·HCl 25% HAc solution to the residue from the previous step, keep constant temperature at (96±3)℃ with intermittent shaking for 4 hours, centrifuge for 20 minutes, take out the supernatant, dilute to a 25 mL volumetric flask, and use it as the atomic absorption test solution. Wash the residue with ionized water, centrifuge, and then filter all the supernatant to determine the concentration of toxic elements.

[0056] (4) Organically bound and sulfide bound states - add 3 mL of 0.01 mol / L HNO3 and 5 mL of 30% H2O2 to the residue from the previous step, then adjust the pH to 2 with HNO3, heat the mixture to (85±2)°C in a water bath, shake it intermittently for 2 hours, then add 5 mL of H2O2 to adjust the pH to 2, place the mixture at (85±2)°C, heat it for 2 hours, shake it intermittently, cool it to (25±1)°C, add 5 mL of 3.2 mol / L NH4Ac in 20% HNO3 solution, dilute it to 20 mL, shake it continuously for 30 minutes, centrifuge it for 20 minutes, take out the supernatant, dilute it to a 25 mL volumetric flask, and use it as the atomic absorption test solution. Wash the residue with deionized water, centrifuge it, and then filter all the supernatant to determine the concentration of toxic elements.

[0057] (5) The residual state includes quartz, clay minerals, etc., which are digested by HCl+HNO3+HF+HClO4. The steps of residual state digestion are the same as those of the full extraction method. Then the solution is transferred to a 50mL volumetric flask and fixed to volume as the test solution for the flame atomic absorption spectrometer. Blank samples and standard samples are used in the experiment to control the quality of experimental data.

[0058] Through the above five steps, we can obtain the proportion of toxic elements in exchangeable state, carbonate-bound state, iron-manganese oxide-bound state, organic-bound state, sulfide-bound state and residual state. The five occurrence forms are recorded as F1 to F5.

[0059] Based on the above experiments, the basic characteristics and component information of mining solid waste, the properties of toxic elements (atomic volume, electron affinity, covalent atomic radius, relative atomic mass, electronegativity and atomic number are used as representatives in this example), the total concentration of toxic elements in the sample, and the occurrence form of toxic elements are taken as input, and the proportion of the occurrence form is used as output to construct a data set.

[0060] Data on the bioavailability of toxic elements were collected. Among the toxic elements tested in this example, the toxic response coefficients of Zn, Cd, Cu, Ni, and Pb were 1, 30, 5, 5, and 40, respectively.

[0061] 3. The sample data collected by steps 1 and 2 need to be preprocessed by data normalization to improve the performance of the model. The convergence test determines that the division ratio of the training set and the test set is 7:3, that is, the division standard of the data set in this example is that the training set size accounts for 70% and the test set size accounts for 30%. This example selects the neural network regression algorithm as the machine learning algorithm model. In order to optimize the algorithm, this example uses the particle swarm algorithm to optimize the hyperparameters. In this example, the population size is 100 and the termination evolution generation of the particle swarm algorithm is 100. In order to avoid the randomness of the results, 10-fold cross validation is used. Substitute the optimized hyperparameters into the neural network algorithm and use the training set to build the final neural network model. The generalization ability of the neural network model is evaluated by the test set. This example uses R to evaluate the generalization ability of the neural network model. R is the correlation coefficient, and its value reflects the important statistic of the linear correlation between model variables. The normal value range is [-1, 1]. The closer the absolute value is to 1, the better the neural network model fits. R can be calculated by the following formula.

[0062]

[0063] n is the number of samples, y i is the actual value, is the predicted value, is the average of the actual values ​​of the samples, is the mean of the sample predictions.

[0064] Figure 4 It is a fitting diagram between the actual value and the predicted value of the proportion of the toxic element occurrence form in this embodiment 2. The fitting effect of the actual value and the predicted value in the training set and the test set is good, the R value in the training set is 0.969, and the R value in the test set is 0.977. Therefore, the prediction effect of this model is good.

[0065] 4. Based on the content of toxic elements in mining solid waste, the occurrence form of toxic elements, leaching risk coefficient, and toxic response coefficient of toxic elements, the pollution risk of toxic elements in mining solid waste is evaluated. The calculation formula is as follows:

[0066]

[0067] Among them, PR represents the pollution risk value of mining solid waste, n represents the total number of toxic elements in mining solid waste, m represents the total number of toxic elements divided into m types through continuous extraction method, and F ji is the percentage of the i-th occurrence form of the j-th toxic element, M ji is the leaching risk coefficient of the i-th occurrence form of the j-th toxic element (between 0 and 1), W j is the content of the jth toxic element in mining solid waste, is the toxicity response coefficient of the jth toxic element.

[0068] The leaching risk coefficient in the formula is based on the existing extraction technology level. The difficulty of extracting toxic elements by direct immersion in water and extracting them by adding acid, alkali and other chemical components for adsorption reaction is very different. In this example, based on the above-mentioned conceptual analysis, the leaching risk coefficients of F1 to F5 are set to 1, 0.7, 0.5, 0.3, and 0.1. The toxic response coefficients of the toxic elements obtained in step 2 are Zn = 1, Cd = 30, Cu = 5, Ni = 5, and Pb = 40. Combined with Table 1 and the PR calculation formula, the pollution risk values ​​of the two types of mining solid waste can be calculated to be 3932.469 and 630.1092 respectively. This shows that the pollution risk of the first type of mining solid waste is much higher than that of the second.

[0069] Through the method provided in the embodiment of the present invention, not only can mining solid waste with pollution risk be selected from a variety of mining solid wastes; the metal recovery potential of a single mining solid waste can also be evaluated, for example, a threshold is set, and when the pollution risk value of the metal is greater than or equal to the threshold, it indicates that the mining solid waste has a pollution risk; in addition, multiple threshold ranges can be set, and the pollution risks corresponding to these multiple threshold ranges are: no pollution risk, low pollution risk, medium pollution risk and high pollution risk, respectively; for example, the threshold ranges are set to 0-50, 50-200, 200-300, >300; when the recovery potential value is between 0-50, it indicates that the mining solid waste has no pollution risk; when the pollution risk value is between 50-200, it indicates that the pollution risk of the mining solid waste is low; when the pollution risk is between 200-300, it indicates that the pollution risk of the mining solid waste is medium; when the pollution risk is greater than 300, it indicates that the pollution risk of the mining solid waste is high.

[0070] 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.

[0071] 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 evaluating the occurrence form and pollution risk of toxic elements in mining solid waste, characterized in that: include: S1. Collect samples and determine the physical and chemical properties of mining solid waste; S2. Extract the total amount and occurrence forms of toxic elements in mining solid waste samples, summarize the occurrence forms of toxic elements, physical and chemical properties of mining solid waste, and properties of toxic elements into a data set, and collect bioavailability indicators of toxic elements in mining solid waste; S3. After preprocessing the data set, an artificial intelligence algorithm is selected to optimize the hyperparameters to obtain the final prediction model for the occurrence form of toxic elements in mining solid waste; a neural network regression algorithm is specifically selected as the artificial intelligence algorithm model; and a particle swarm algorithm is used to optimize the hyperparameters; S4. Based on the content of toxic elements in mining solid waste, the occurrence form of toxic elements, the leaching risk coefficient of toxic elements, and the toxic response coefficient of toxic elements, the pollution risk of toxic elements in mining solid waste is evaluated. The calculation formula is as follows: Among them, PR represents the pollution risk value of mining solid waste, n represents the total number of toxic elements in mining solid waste, m represents the type of toxic element occurrence, F ji is the percentage of the i-th occurrence form of the j-th toxic element, M ji is the leaching risk coefficient of the i-th occurrence form of the j-th toxic element, M ji Between 0-1, W j is the content of the jth toxic element in mining solid waste, T r j is the toxicity response coefficient of the jth toxic element; the leaching risk coefficient in the formula is based on the existing extraction technology level and refers to expert opinions.

2. A method for evaluating the occurrence forms and pollution risks of toxic elements in mining solid waste according to claim 1, characterized in that: In step S1, the physical and chemical properties of mining solid waste are determined through laboratory experiments, including density, water content, compressibility, ignition loss, particle size distribution, porosity, permeability, element or oxide content, phase composition, toxic element concentration, organic matter content, pH, alkalinity, redox properties, clay mineral content, and biological properties. The physical and chemical properties of mining solid waste directly affect the occurrence form of toxic elements in mining solid waste.

3. The method for evaluating the occurrence form and pollution risk of toxic elements in mining solid waste according to claim 1 is characterized in that: The properties of toxic elements include atomic number, relative atomic mass, ionic radius, and number of outermost electrons; The bioavailability index refers to the toxic response coefficient T of the toxic element. r .

4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for evaluating the occurrence forms and pollution risks of toxic elements in mining solid wastes as described in any one of claims 1 to 3 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating the occurrence forms and pollution risks of toxic elements in mining solid wastes as described in any one of claims 1 to 3 are implemented.

Images