An ion adsorption type rare earth mining monitoring and early warning system

Abstract

The invention discloses an ion adsorption type rare earth mining monitoring and early warning system, relates to the technical field of mining mining, and is used to solve the problem that a single high-concentration ammonium sulfate leaching agent may cause an increase in ammonia nitrogen concentration, soil pollution and waste of resources. By collecting the distribution concentration of the leaching agent in the ore body and the leaching agent concentration difference, the rare earth leaching rate in the historical area, the average efficiency of the leaching agent penetration, and the difference between the outflow rate of the outlet solution and the component concentration ratio, a data weighted analysis model is used to obtain the permeability coefficient and compare it with the permeability threshold to obtain the complete permeability and incomplete permeability results corresponding to each area, the leaching agent concentration difference of each adjacent area is compared with the difference threshold to obtain the leaching agent concentration evaluation result, the leaching agent concentration is predicted and analyzed by a time series model, and the leaching agent concentration adjustment plan is dynamically adjusted to reduce soil enrichment and potential environmental pollution risks.

Description

Technical Field

[0001] The present invention relates to the technical field of mining, and more specifically, to an ion adsorption type rare earth mining monitoring and early warning system. Background Art

[0002] Ion-adsorption rare earth ore is an important type of rare earth ore. Rare earth ions are adsorbed on newly generated clay minerals in the form of hydrated ions or hydroxyl hydrated ions, forming ion-adsorption rare earth ore. Most of its rare earth elements are adsorbed on the surface of clay minerals in the form of ions. Compared with other rare earth deposits, the mining process of ion-adsorption rare earth ore is relatively simple, and rare earth elements are mainly recovered through high-concentration ammonium sulfate leaching agent leaching technology.

[0003] The prior art has the following deficiencies:

[0004] At present, rare earth is dissolved from the surface of minerals through a series of chemical reactions. Excessive use of a single high-concentration ammonium sulfate leaching agent may lead to an increase in ammonia nitrogen concentration and soil pollution. At the same time, the single high-concentration leaching agent does not penetrate evenly, and the remaining rare earth resources are lost with the residue, resulting in resource waste. Therefore, an ion adsorption type rare earth mining monitoring and early warning system is proposed.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an ion adsorption type rare earth mining monitoring and early warning system, which solves the problems raised in the above-mentioned background technology by using different product inspection methods.

[0007] To achieve the above object, the present invention provides the following technical solution: an ion adsorption type rare earth mining monitoring and early warning system, comprising a data acquisition module, a data processing module, a permeation analysis module and a concentration prediction module; the modules are signal connected;

[0008] The data acquisition module is used to collect ore body characteristic information and permeability information, and obtains the distribution concentration and concentration difference of the leaching agent in the ore body, the rare earth leaching rate in the historical area, the average efficiency of the leaching agent penetration, and the difference between the outflow rate of the outlet solution and the component concentration ratio through data processing, and sends them to the data processing module;

[0009] The data processing module is used to obtain the distribution concentration and concentration difference of the leaching agent in the ore body, the rare earth leaching rate in the historical area, the average efficiency of the leaching agent penetration, and the difference between the outflow rate of the outlet solution and the ratio of the component concentration. Through the data weighted analysis model, the permeability coefficient is obtained and sent to the permeability analysis module;

[0010] The permeability analysis module is used to obtain the permeability coefficient and compare it with the permeability threshold to obtain the complete permeability and incomplete permeability results corresponding to each area. The three-dimensional distribution model is used to find the results corresponding to each area, count the number of inconsistent results in adjacent areas and calculate the difference in leaching agent concentration in each adjacent area. The difference in leaching agent concentration in each adjacent area is compared with the difference threshold to obtain the leaching agent concentration evaluation result and send it to the concentration prediction module;

[0011] The concentration prediction module is used to obtain the evaluation results of the leaching agent concentration. By analyzing the leaching agent concentration values ​​in various areas of the ore body, the difference between the highest and lowest leaching agent concentrations inside the mineral and the current leaching agent concentration are obtained. The leaching agent concentration prediction and analysis is performed through the time series model to further refine and optimize the leaching agent concentration adjustment plan.

[0012] In a preferred embodiment, the ore body characteristic information includes the distribution concentration and concentration difference of the leaching agent in the ore body and the rare earth leaching rate in the historical area; the permeability information includes the average permeability efficiency of the leaching agent and the difference between the outflow rate of the outlet solution and the concentration ratio of the component;

[0013] The leaching agent concentration data of each sampling area is subtracted from the leaching agent concentration to obtain the leaching agent distribution concentration in the ore body and the leaching agent concentration difference. ; Where i is the area within the i-th ore body;

[0014] The historical regional rare earth leaching rate is calculated by comparing the mass of each rare earth successfully extracted during the historical period with the total rare earth reserves in each region. ;

[0015] The average efficiency of leaching agent penetration is obtained by comprehensively analyzing the leaching agent concentration distribution, rare earth leaching rate and penetration time in each area of ​​the ore body. ;

[0016] The difference between the outflow rate and the concentration of the component at the outlet is obtained by subtracting the ratio of the outflow rate to the concentration at the previous time point from the ratio of the outflow rate to the concentration at the current time point. ; where t is the tth time point.

[0017] In a preferred embodiment, the distribution concentration of the leaching agent in the ore body and the difference in the leaching agent concentration are obtained. , Historical regional rare earth leaching rate , Average penetration efficiency of leaching agent And the difference between the outflow rate of the solution at the outlet and the concentration ratio of the components , generating the permeability coefficient , based on the formula:

[0018] ;

[0019] In the formula, is the permeability coefficient, , , as well as are the preset proportional coefficients of the distribution concentration and concentration difference of the leaching agent in the ore body, the rare earth leaching rate in the historical area, the average penetration efficiency of the leaching agent, and the difference between the outflow rate of the outlet solution and the ratio of the component concentration, and , , as well as Both are greater than 0.

[0020] In a preferred embodiment, after obtaining the permeability coefficient, the permeability coefficient is compared and analyzed with the iterative permeability threshold;

[0021] If the permeability coefficient is greater than or equal to the permeability threshold, the corresponding area in the current ore body is marked as fully permeable and a uniform signal is generated;

[0022] If the permeability coefficient is less than the permeability threshold, the corresponding area in the current ore body is marked as incomplete permeability and an uneven signal is generated;

[0023] Count the number of inconsistent results in adjacent areas. For each marked point, calculate its specific position in the ore body and find the leaching agent concentration result of the area through the three-dimensional distribution model. According to the data distribution in the three-dimensional distribution model, calculate the difference of leaching agent concentration in each adjacent area in turn.

[0024] The difference in leaching agent concentration between adjacent areas is compared with the difference threshold to obtain the leaching agent concentration evaluation result; specifically, if the difference in leaching agent concentration between adjacent areas is greater than or equal to the difference threshold, an early warning alarm is generated and the leaching agent concentration is adjusted; otherwise, the leaching agent concentration remains unchanged.

[0025] In a preferred embodiment, the leaching agent concentration evaluation result includes the leaching agent concentration value of each area in the ore body and the adjustment information of the leaching agent concentration; the leaching agent concentration prediction analysis is performed through the time series model to determine the leaching agent concentration adjustment plan;

[0026] The current leaching agent concentration is the leaching agent concentration currently set by the system;

[0027] The difference between the highest and lowest leachant concentrations inside the mineral is obtained by subtracting the area with the highest leachant concentration from the area with the highest leachant concentration.

[0028] In a preferred embodiment, the time series model adopts an LSTM model, and the specific steps of predicting and analyzing the adjustment of the leaching agent concentration by the time series model are as follows:

[0029] Step A1, obtaining prediction data;

[0030] Step A2, constructing an input sequence for LSTM model training based on the preprocessed data arranged in chronological order;

[0031] Step A3, input the input time series data and the corresponding target data into the LSTM network, and use the back propagation algorithm (BPTT) to train the model parameters;

[0032] Step A4, evaluating the goodness of fit of the model through residual analysis and other methods;

[0033] Step A5, using the trained LSTM model to predict the future concentration of the leaching agent, and taking the maximum value of the predicted result as the maximum value of the leaching agent concentration in the future time period.

[0034] In a preferred embodiment, the LSTM network includes three gates to control data flow, including an input gate, a forget gate, and an output gate; the specific forget gate calculation formula is: ;

[0035] In the formula, is the output of the previous time step, is the output of the current time step, The output value of the forget gate, The weight matrix of the forget gate, Bias term, is the activation function;

[0036] The specific input gate calculation process is: ;

[0037] At the same time, generate candidate memory update information:

[0038] ;

[0039] In the formula, is the output value of the input gate, is the weight matrix of the input gate, The candidate memory value generated for the current time step is used Function nonlinear activation, is the weight matrix updated for the candidate memory, and are the bias terms of the input gate and candidate memory, respectively. is the hyperbolic tangent function;

[0040] The specific output gate combines the current memory state to output:

[0041] ;

[0042] The final output is: ;

[0043] In the formula, The output value of the output gate, The weight matrix of the output gate, The bias term of the output gate, is the output of the model, is the memory cell state at the current time step.

[0044] In a preferred embodiment, in the LSTM network , , , , , , as well as The adjustments were calculated by the mean square error (MSE) method.

[0045] Technical effects and advantages of the present invention:

[0046] 1. The present invention collects the distribution concentration of leaching agent in the ore body and the difference in leaching agent concentration, the rare earth leaching rate in the historical area, the average efficiency of leaching agent penetration, and the difference between the outflow rate of the solution at the outlet and the ratio of the component concentration, and obtains the permeability coefficient through a data weighted analysis model and compares it with the permeability threshold to obtain the complete permeability and incomplete permeability results corresponding to each area, compares the difference in leaching agent concentration in each adjacent area with the difference threshold, obtains the leaching agent concentration evaluation result, accurately monitors the permeability effect, avoids blindly adjusting the leaching agent concentration to increase the ammonia nitrogen concentration of soil resources or insufficient replacement of rare earth resources; and improves resource utilization efficiency.

[0047] 2. The present invention analyzes the leaching agent concentration values ​​of various areas in the ore body through the leaching agent concentration evaluation results, performs leaching agent concentration prediction and analysis through a time series model, and obtains a leaching agent concentration adjustment plan. According to the maximum, minimum and average values ​​of the predicted results, the leaching agent concentration adjustment plan is dynamically adjusted to reduce soil enrichment and potential environmental pollution risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a module schematic diagram of an ion adsorption type rare earth mining monitoring and early warning system of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] The main component of ion-adsorbed rare earth minerals is clay minerals. Rare earth ions are adsorbed on the surface of rare earth minerals in the form of a stationary phase. Its structure is expressed as The extraction principle is to use more active cations in the electrolyte solution to replace rare earth ions, so that the exchangeable rare earth ions are leached out, and the rare earths eventually form rare earth-containing mother liquor, and pure rare earth products are obtained through precipitation, separation, and purification steps;

[0051] Usually, the commonly used leaching agent is ammonium sulfate solution. The present invention establishes a data analysis weighted algorithm by monitoring resource characteristic parameters and leaching agent characteristic parameters, evaluates the current high-concentration leaching agent penetration uniformity, predicts and analyzes the remaining rare earth resources through a time series model, generates an alarm signal, and gradient adjusts the leaching agent concentration to reduce the loss of remaining rare earth resources.

[0052] Example 1

[0053] The present invention discloses an ion adsorption type rare earth mining monitoring and early warning system, such as Figure 1 As shown, it includes a data acquisition module, a data processing module, a permeation analysis module and a concentration prediction module; and the modules are connected by signals;

[0054] The data acquisition module is used to collect ore body characteristic information and permeability information, and obtains the distribution concentration and concentration difference of the leaching agent in the ore body, the rare earth leaching rate in the historical area, the average efficiency of the leaching agent penetration, and the difference between the outflow rate of the outlet solution and the component concentration ratio through data processing, and sends them to the data processing module;

[0055] Specifically, data processing refers to the preprocessing of ore body characteristic information and permeability information, including but not limited to data type conversion, missing value processing, data standardization, feature extraction, etc. (all existing technologies), the purpose of which is to improve the quality and usability of the distribution concentration and concentration difference of leaching agents in the ore body, the rare earth leaching rate in the historical area, the average efficiency of leaching agent penetration, and the difference between the outflow rate of the outlet solution and the concentration ratio of the component, which will not be elaborated here;

[0056] Among them, the ore body characteristic information includes the distribution concentration and concentration difference of the leaching agent in the ore body and the rare earth leaching rate in the historical area; the permeability information includes the average permeability efficiency of the leaching agent and the difference between the outflow rate of the outlet solution and the concentration ratio of the component;

[0057] Among them, for the internal structure of the ore body, sampling at different depths and lateral positions revealed that there are multiple regions in the ore body. It can be understood by those skilled in the art that the porosity and saturation of the ore body in different regions have different values, and the distribution concentration of the leaching agent in different regions of the ore body is different;

[0058] The logic of obtaining the distribution concentration and concentration difference of the leaching agent in the ore body is to sample the different depths and lateral positions of the internal structure of the ore body through sensors, record the concentration data of the leaching agent in each sampling area, and use the collected concentration data to establish a three-dimensional distribution model of the leaching agent in the ore body. The concentration value of each point in the model will show the distribution of the leaching agent in different areas. The leaching agent concentration data of each sampling area is subtracted from the leaching agent concentration to obtain the distribution concentration and concentration difference of the leaching agent in the ore body. ; Where i is the area within the i-th ore body;

[0059] Among them, the three-dimensional distribution model refers to a three-dimensional structure model that reflects the distribution of leaching agent concentration inside the ore body by spatially mapping the leaching agent concentration data at different depths and lateral positions of the ore body. There is no limitation on the application of this model, but it is set by the experimenters according to the specific actual situation, and will not be repeated here;

[0060] It should be noted that the concentration of the leaching agent refers to the ammonium sulfate solution put into the ore body, and this value is usually a fixed value. For example, the concentration of the low-concentration leaching agent is usually 0.1%-0.5%, and the concentration of the high-concentration leaching agent is 0.6%-1% to enhance the leaching effect;

[0061] The logic of obtaining the rare earth leaching rate in the historical region is to record the rare earth mining output and its corresponding leaching agent dosage and time in each region, and monitor the changes in the concentration of rare earth elements, including the leaching amount and residual amount of rare earth in each time period. According to the historical data, the total rare earth reserves in each region are calculated, and the number of rare earths successfully extracted in each time period is calculated and added by analyzing the solution composition at the outlet. The historical regional rare earth leaching rate is obtained by calculating the ratio of the mass of each rare earth successfully extracted in the historical time period to the total rare earth reserves in each region. ;

[0062] Among them, the historical time period refers to the integration of all time periods or the integration of specified time periods. It is understandable that the system usually sets a log record for the time period data retention. Too much time period data may cause the system to run slowly. Therefore, the system retention time is set by the experimenter based on historical mineral output values ​​and other parameters, and is not limited here.

[0063] It should be noted that for the historical regional rare earth leaching rates of each region, the length of the historical time period of each region is unified to balance the accuracy of the historical regional rare earth leaching rates;

[0064] The average penetration efficiency of the leaching agent refers to the average effect of the leaching agent penetrating in each area of ​​the ore body, reflecting the uniformity and effectiveness of the contact between the leaching agent and the ore body. The acquisition logic is through a comprehensive analysis of the leaching agent concentration distribution, rare earth leaching rate and penetration time in each area of ​​the ore body. The specific formula is as follows:

[0065] ;

[0066] In the formula, is the average penetration efficiency of the leaching agent, represents the penetration efficiency of the ith region, represents the volume of the ith region, Indicates the total volume;

[0067] The difference in the ratio of the outflow rate of the solution at the outlet to the concentration of the component refers to the change in the ratio between the outflow rate of the solution at the outlet within a preset time and the concentration of the rare earth component in the solution. This ratio difference determines whether the leaching agent has evenly penetrated into the ore body during the mining process and whether the rare earth component has been effectively leached. The acquisition logic is to monitor the outflow rate of the outlet solution and the concentration of the rare earth component in the solution in real time, and calculate the ratio of the outflow rate of the outlet solution to the concentration at each time point, and subtract the ratio of the outflow rate to the concentration at the current time point from the ratio of the outflow rate to the concentration at the previous time point to obtain the difference in the ratio of the outflow rate to the concentration of the solution at the outlet. ; Where t is the tth time point;

[0068] Among them, the number of time points is set to be consistent with the number of each area in the ore body; it is not the same as the above historical time period; it should be understood by those skilled in the art that the more areas are divided in the ore body, the more it can reflect the degree of penetration of the leaching agent and the amount of replaced rare earth ions. Therefore, the number of each area in the ore body and the number of time points are set by the experimenters according to the specific size of the ore body and the water output at the water outlet, and are not limited here;

[0069] It should be noted that if the difference between the outflow rate of the solution at the outlet and the ratio of the component concentration is large, it indicates that the leaching agent has uneven penetration, resulting in a decrease in the rare earth leaching efficiency; on the contrary, it indicates that the relationship between the outflow rate and the concentration is stable, and the leaching process is relatively uniform and efficient.

[0070] The data processing module is used to obtain the distribution concentration and concentration difference of the leaching agent in the ore body, the rare earth leaching rate in the historical area, the average efficiency of the leaching agent penetration, and the difference between the outflow rate of the outlet solution and the ratio of the component concentration. Through the data weighted analysis model, the permeability coefficient is obtained and sent to the permeability analysis module;

[0071] Obtain the distribution concentration and concentration difference of leaching agent in the ore body , Historical regional rare earth leaching rate , Average penetration efficiency of leaching agent And the difference between the outflow rate of the solution at the outlet and the concentration ratio of the components , generating the permeability coefficient , based on the formula:

[0072] ;

[0073] In the formula, is the permeability coefficient, , , as well as are the preset proportional coefficients of the distribution concentration and concentration difference of the leaching agent in the ore body, the rare earth leaching rate in the historical area, the average penetration efficiency of the leaching agent, and the difference between the outflow rate of the outlet solution and the ratio of the component concentration, and , , as well as All are greater than 0;

[0074] Among them, the distribution concentration of leaching agent in the ore body and the difference in leaching agent concentration, the rare earth leaching rate in the historical area, the average efficiency of leaching agent penetration, and the difference in the ratio of the outflow rate of the outlet solution and the concentration of the components are all data that directly express the degree of leaching agent penetration and the corresponding amount of replaced rare earth ions.

[0075] It can be seen from the above formula that when the rare earth leaching rate and the average efficiency of the leaching agent penetration in the historical area are higher, it means that the current leaching agent penetration is more uniform, and the distribution of the leaching agent in the ore body is more uniform, the penetration is more sufficient, and the rare earth minerals can be brought out more effectively, and the permeability coefficient is larger; on the contrary, if the difference between the leaching agent distribution concentration in the ore body and the leaching agent concentration difference and the difference between the outlet solution outflow rate and the component concentration ratio are larger, the permeability coefficient is smaller;

[0076] The permeability analysis module is used to obtain the permeability coefficient and compare it with the permeability threshold to obtain the complete permeability and incomplete permeability results corresponding to each area. The three-dimensional distribution model is used to find the results corresponding to each area, count the number of inconsistent results in adjacent areas and calculate the difference in leaching agent concentration in each adjacent area. The difference in leaching agent concentration in each adjacent area is compared with the difference threshold to obtain the leaching agent concentration evaluation result and send it to the concentration prediction module;

[0077] The logic of obtaining the permeability threshold is to collect a distribution sample set of the historical leaching agent concentration and its permeability information database, divide the data set into a training set and a test set, set the evaluation index and clustering algorithm, and in each round of cross-validation, train the model on the training set and evaluate the model performance on the test set. Then, adjust the permeability threshold according to the performance of the validation set. Therefore, the permeability threshold is constantly updated;

[0078] In the present invention, clustering algorithm is a type of unsupervised learning algorithm used to divide data points in a data set into groups or clusters with similarities; a common one is K-means clustering, which divides the data points in a data set into K clusters so that the distance between the data point of each curve and the center point (centroid) of the cluster to which it belongs is minimized, and finally the effect of the adjusted permeation threshold is measured by the Euclidean distance, so as to set the permeation threshold;

[0079] After obtaining the permeability coefficient, the permeability coefficient is compared and analyzed with the iterative permeability threshold;

[0080] If the permeability coefficient is greater than or equal to the permeability threshold, the corresponding area in the current ore body is marked as fully permeable and a uniform signal is generated;

[0081] If the permeability coefficient is less than the permeability threshold, the corresponding area in the current ore body is marked as incomplete permeability and an uneven signal is generated;

[0082] Count the number of inconsistent results in adjacent areas. For each marked point, calculate its specific position in the ore body and find the leaching agent concentration result of the area through the three-dimensional distribution model. According to the data distribution in the three-dimensional distribution model, calculate the difference of leaching agent concentration in each adjacent area in turn.

[0083] Among them, the adjacent area refers to the area where the results of a certain area (X, Y, Z) in the three-dimensional distribution model are inconsistent with those of the surrounding areas. For example, for the coordinate (X1, Y1, Z1), there are 6 coordinates in the surrounding area, namely (X1+1, Y1, Z1), (X1, Y1+1, Z1), (X1, Y1, Z1+1), (X1-1, Y1, Z1), (X1, Y1-1, Z1) and (X1, Y1, Z1-1). If the results of one of the coordinates are inconsistent with those of the coordinate (X1, Y1, Z1), the concentration of the leaching agent of the coordinate (X1, Y1, Z1) is subtracted from the concentration of the leaching agent of the corresponding area with inconsistent results to obtain the concentration difference of the leaching agent in each adjacent area;

[0084] The difference in leaching agent concentration between adjacent areas is compared with the difference threshold to obtain the leaching agent concentration evaluation result; specifically, if the difference in leaching agent concentration between adjacent areas is greater than or equal to the difference threshold, an early warning alarm is generated and the leaching agent concentration is adjusted; otherwise, the leaching agent concentration remains unchanged;

[0085] The difference threshold is obtained through the current permeability coefficient and the historical leaching agent permeability information;

[0086] It should be noted that by comparing the difference in leaching agent concentrations in each adjacent area with the difference threshold, an early warning alarm signal is generated, and a response broadcast is triggered or sent to a visualization port for display and broadcast. The specific early warning measures are not limited, but are set by the experimenter according to the needs of the experimental site, and will not be repeated here;

[0087] The present invention collects the distribution concentration of leaching agent in the ore body and the difference in leaching agent concentration, the rare earth leaching rate in the historical area, the average efficiency of leaching agent penetration, and the difference between the outflow rate of the solution at the outlet and the ratio of the component concentration, and obtains the permeability coefficient through a data weighted analysis model and compares it with the permeability threshold to obtain the complete permeability and incomplete permeability results corresponding to each area, compares the difference in leaching agent concentration in each adjacent area with the difference threshold to obtain the leaching agent concentration evaluation result, accurately monitors the permeability effect, avoids the situation where blindly adjusting the leaching agent concentration increases the ammonia nitrogen concentration of soil resources or the replacement amount of rare earth resources is insufficient, and improves the resource utilization efficiency.

[0088] Example 2

[0089] In Example 1 of the present invention, an example is given to illustrate the operation strategy of collecting the distribution concentration of the leaching agent in the ore body and the difference in the leaching agent concentration, the rare earth leaching rate in the historical area, the average efficiency of the leaching agent penetration, and the difference between the outflow rate of the outlet solution and the component concentration ratio, and obtaining the permeability coefficient and comparing it with the permeability threshold through the data weighted analysis model, obtaining the complete permeability and incomplete permeability results corresponding to each area, and comparing the difference in the leaching agent concentration of each adjacent area with the difference threshold to obtain the evaluation result of the leaching agent concentration; however, in Example 1, it is only necessary to adjust the current leaching agent concentration from the warning point, but the specific adjustment concentration is not limited. Obviously, too high an adjustment will lead to aggravated soil enrichment, and too low an adjustment will reduce the replacement amount of rare earth resources. It is necessary to repeatedly replace the outlet solution and the remaining residue inside the reaction tank, resulting in multiple infiltration and infiltration, resulting in excessive water output and inevitably further aggravating soil enrichment; in view of the above problems, Example 2 of the present invention is further refined;

[0090] The concentration prediction module is used to obtain the evaluation results of the leaching agent concentration. By analyzing the leaching agent concentration values ​​in various areas of the ore body, the difference between the highest and lowest leaching agent concentrations in the mineral and the current leaching agent concentration are obtained. The leaching agent concentration is predicted and analyzed through the time series model to further refine and optimize the leaching agent concentration adjustment plan;

[0091] The leaching agent concentration evaluation results include the leaching agent concentration values ​​of each area in the ore body and the adjustment information of the leaching agent concentration;

[0092] Among them, the difference between the highest and lowest concentrations of the leaching agent inside the mineral refers to the difference between the maximum and minimum concentrations of the leaching agent distribution in different areas inside the ore body. The acquisition logic is to obtain the difference between the highest and lowest concentrations of the leaching agent inside the mineral by subtracting the area with the highest concentration of the leaching agent from the area with the highest concentration of the leaching agent.

[0093] Among them, if the difference between the highest and lowest leachant concentrations inside the mineral is greater, it further indicates that there are obvious differences in the penetration effects of leachants in different areas, and the penetration process needs to be optimized;

[0094] The current leaching agent concentration refers to the leaching agent concentration currently set by the system, wherein the definition of the leaching agent concentration has been described in Example 1 and will not be repeated here;

[0095] Specifically, the concentration of the leaching agent is predicted and analyzed through the time series model, and the concentration scheme is further refined and optimized by setting gradient limits on the concentration of the leaching agent (for example, 0.1%-0.25% is the first gradient concentration, 0.26%-0.5% is the second gradient concentration, 0.51%-0.75% is the third gradient concentration, and 0.76%-1% is the fourth gradient concentration); in fact, the experimenter can set multiple gradients to accurately adjust the concentration of the leaching agent to meet the needs of rare earth mining operations;

[0096] It should be noted that the time series model of this embodiment adopts an LSTM model, and refining and optimizing the leaching agent concentration scheme means making the leaching agent concentration more scientific and reasonable under the condition of determining the current leaching agent concentration adjustment, so as to achieve the maximum replacement amount of rare earth resources mining;

[0097] The LSTM network solves the problem that early information cannot be effectively transmitted to the later stage in a long sequence by designing memory cells. For example, the historical rare earth leaching rate information of some key areas cannot be effectively transmitted to the later stage, which causes the problem of inaccurate prediction. The core of the LSTM network is to control the data flow by three gates:

[0098] Specifically, the input gate determines whether new information should be added to the current memory unit;

[0099] Specifically, the forget gate determines whether the old information in the current memory unit should be forgotten;

[0100] Specifically, the output gate determines whether the state of the memory cell will affect the output of the current time step;

[0101] Furthermore, the specific steps of predicting and analyzing the concentration adjustment of leaching agent through time series model are as follows:

[0102] Step A1, obtaining prediction data;

[0103] Step A2, constructing an input sequence for LSTM model training based on the preprocessed data arranged in chronological order;

[0104] Step A3, input the input time series data and the corresponding target data into the LSTM network, and use the back propagation algorithm (BPTT) to train the model parameters;

[0105] Step A4, evaluating the goodness of fit of the model through residual analysis and other methods;

[0106] Step A5, using the trained LSTM model to predict the future concentration of the leaching agent, and taking the maximum value of the predicted result as the maximum value of the leaching agent concentration in the future time period;

[0107] Specifically, the prediction data include the difference between the highest leaching agent concentration and the lowest leaching agent concentration inside the mineral corresponding to each time point, the difference between the outflow rate of the solution at the outlet and the ratio of the component concentration, and the leaching agent concentration data; wherein, the difference between the outflow rate of the solution at the outlet and the ratio of the component concentration corresponding to each time point has been exemplified in Example 1 and will not be repeated here;

[0108] For each time step in the time series, LSTM decides whether to discard the information of the previous moment through the forget gate. The calculation formula is:

[0109] ;

[0110] In the formula, is the output of the previous time step, is the output of the current time step, The output value of the forget gate, The weight matrix of the forget gate, Bias term, is the activation function, usually function;

[0111] The input gate determines what new information needs to be stored in the memory cell. The calculation process is as follows:

[0112] ;

[0113] At the same time, generate candidate memory update information:

[0114] ;

[0115] In the formula, is the output value of the input gate, is the weight matrix of the input gate, The candidate memory value generated for the current time step is used Function nonlinear activation, is the weight matrix updated for the candidate memory, and are the bias terms of the input gate and candidate memory, respectively. is a hyperbolic tangent function used to generate candidate memory update information, which compresses the input value into The interval makes the memory update have a stronger nonlinear representation ability;

[0116] Continue to update the memory unit state. During the update process of the memory unit, the memory state is updated through the weighted combination of the forget gate and the input gate:

[0117] ;

[0118] In the formula, is the memory state of the previous moment, is the forgetting ratio of the memory unit state from the previous time step to the current time step, which is determined by the forget gate control, New memory information for the current time step, is the candidate memory state at the current moment;

[0119] The output gate determines the information to be output at the current moment and outputs it in combination with the current memory state:

[0120] ;

[0121] The final output is: ; In the formula, is the output value of the output gate, is the weight matrix of the output gate, is the bias term of the output gate, is the output of the model, is the memory cell state at the current time step;

[0122] It should be noted that in step A3, the back propagation algorithm calculates the loss function through the difference between the predicted value and the target data, specifically the mean square error (MSE), which is expressed as:

[0123] ;

[0124] in, is the actual observed value, is the model's predicted value, is the number of samples;

[0125] Specifically, the model parameters are adjusted by gradient descent method ( , , , , , , as well as ), thereby gradually reducing the value of the loss function and optimizing the model performance;

[0126] Dynamically adjust the leaching agent concentration adjustment plan by predicting the maximum, minimum and average values ​​of the results;

[0127] This embodiment exemplifies as follows:

[0128] The maximum value of the predicted result It represents the maximum value of the leaching agent concentration in the future time period. A peak value adjustment plan is formulated to adjust the peak value of the leaching agent concentration at the predicted peak value (i.e. close to or equal to At the time point of the experiment, the concentration is increased by a gradient to ensure the maximum efficiency of replacing rare earth resources and avoid repeated infiltration of the ore body;

[0129] According to the lowest value of the predicted results Represents the minimum concentration of the leaching agent in the future period of time, formulates a low peak adjustment plan, and At the time point of the experiment, the concentration of the leaching agent is decreased by a gradient to avoid the aggravation of soil enrichment;

[0130] According to the average of the predicted results , formulate a plan for adjusting the equilibrium value, keep the current concentration of the leaching agent unchanged during the period when the concentration of the leaching agent is close to the average value, and ensure the efficiency of the leaching agent concentration in replacing rare earth resources;

[0131] The settings of the high peak value, the balanced value, and the low peak value are obtained by the experimenters themselves, and the boundaries of the divisions are not limited.

[0132] The present invention analyzes the leaching agent concentration values ​​of various areas in the ore body through the leaching agent concentration evaluation result, performs leaching agent concentration prediction and analysis through a time series model, obtains the leaching agent concentration adjustment plan, and dynamically adjusts the leaching agent concentration adjustment plan according to the maximum value, minimum value and average value of the predicted results, thereby improving the accuracy and efficiency of ore body mining and reducing soil enrichment and potential environmental pollution risks.

[0133] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0134] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0135] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0136] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0138] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0139] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0141] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0142] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An ion adsorption type rare earth mining monitoring and early warning system, characterized in that: It includes data acquisition module, data processing module, permeation analysis module and concentration prediction module; signal connection between each module; The data acquisition module is used to collect ore body characteristic information and permeability information, and obtains the distribution concentration and concentration difference of the leaching agent in the ore body, the rare earth leaching rate in the historical area, the average efficiency of the leaching agent penetration, and the difference between the outflow rate of the outlet solution and the component concentration ratio through data processing, and sends them to the data processing module; The data processing module is used to obtain the distribution concentration and concentration difference of the leaching agent in the ore body, the rare earth leaching rate in the historical area, the average efficiency of the leaching agent penetration, and the difference between the outflow rate of the outlet solution and the ratio of the component concentration. Through the data weighted analysis model, the permeability coefficient is obtained and sent to the permeability analysis module; The permeability analysis module is used to obtain the permeability coefficient and compare it with the permeability threshold to obtain the complete permeability and incomplete permeability results corresponding to each area. The three-dimensional distribution model is used to find the results corresponding to each area, count the number of inconsistent results in adjacent areas and calculate the difference in leaching agent concentration in each adjacent area. The difference in leaching agent concentration in each adjacent area is compared with the difference threshold to obtain the leaching agent concentration evaluation result and send it to the concentration prediction module; The concentration prediction module is used to obtain the evaluation results of the leaching agent concentration. By analyzing the leaching agent concentration values ​​in various areas of the ore body, the difference between the highest and lowest leaching agent concentrations in the mineral and the current leaching agent concentration are obtained. The leaching agent concentration is predicted and analyzed through the time series model to further refine and optimize the leaching agent concentration adjustment plan; Ore body characteristic information includes the distribution concentration and concentration difference of leaching agent in the ore body and the rare earth leaching rate in the historical area; permeability information includes the average permeability efficiency of the leaching agent and the difference between the outflow rate of the outlet solution and the concentration ratio of the component; The leaching agent concentration data of each sampling area is subtracted from the leaching agent concentration to obtain the leaching agent distribution concentration in the ore body and the leaching agent concentration difference. ; Where i is the area within the i-th ore body; The historical regional rare earth leaching rate is calculated by comparing the mass of each rare earth successfully extracted during the historical period with the total rare earth reserves in each region. ; The average efficiency of leaching agent penetration is obtained by comprehensively analyzing the leaching agent concentration distribution, rare earth leaching rate and penetration time in each area of ​​the ore body. ; The difference between the outflow rate and the concentration of the component at the outlet is obtained by subtracting the ratio of the outflow rate to the concentration at the previous time point from the ratio of the outflow rate to the concentration at the current time point. ; Where t is the tth time point; Obtain the distribution concentration and concentration difference of leaching agent in the ore body , Historical regional rare earth leaching rate , Average penetration efficiency of leaching agent And the difference between the outflow rate of the solution at the outlet and the concentration ratio of the components , generating the permeability coefficient , based on the formula: ； In the formula, is the permeability coefficient, , , as well as are the preset proportional coefficients of the distribution concentration and concentration difference of the leaching agent in the ore body, the rare earth leaching rate in the historical area, the average penetration efficiency of the leaching agent, and the difference between the outflow rate of the outlet solution and the ratio of the component concentration, and , , as well as All are greater than 0; After obtaining the permeability coefficient, the permeability coefficient is compared and analyzed with the continuously iterated permeability threshold; If the permeability coefficient is greater than or equal to the permeability threshold, the corresponding area in the current ore body is marked as fully permeable and a uniform signal is generated; If the permeability coefficient is less than the permeability threshold, the corresponding area in the current ore body is marked as incomplete permeability and an uneven signal is generated; Count the number of inconsistent results in adjacent areas. For each marked point, calculate its specific position in the ore body and find the leaching agent concentration result of the area through the three-dimensional distribution model. According to the data distribution in the three-dimensional distribution model, calculate the difference of leaching agent concentration in each adjacent area in turn. The difference in leaching agent concentration between adjacent areas is compared with the difference threshold to obtain the leaching agent concentration evaluation result; specifically, if the difference in leaching agent concentration between adjacent areas is greater than or equal to the difference threshold, an early warning alarm is generated and the leaching agent concentration is adjusted; otherwise, the leaching agent concentration remains unchanged.

2. The ion adsorption type rare earth mining monitoring and early warning system according to claim 1 is characterized in that: The results of the leaching agent concentration assessment include the leaching agent concentration values ​​of each area in the ore body and the information on adjusting the leaching agent concentration; the leaching agent concentration prediction analysis is carried out through the time series model to determine the leaching agent concentration adjustment plan; The current leaching agent concentration is the leaching agent concentration currently set by the system; The difference between the highest and lowest leachant concentrations inside the mineral is obtained by subtracting the area with the highest leachant concentration from the area with the highest leachant concentration.

3. The ion adsorption type rare earth mining monitoring and early warning system according to claim 2 is characterized in that: The time series model uses the LSTM model. The specific steps for predicting and analyzing the concentration adjustment of leaching agents through the time series model are as follows: Step A1, obtaining prediction data; Step A2, constructing an input sequence for LSTM model training based on the preprocessed data arranged in chronological order; Step A3, input the input time series data and the corresponding target data into the LSTM network, and use the back propagation algorithm to train the model parameters; Step A4, evaluating the goodness of fit of the model by residual analysis method; Step A5, using the trained LSTM model to predict the future concentration of the leaching agent, and taking the maximum value of the predicted result as the maximum value of the leaching agent concentration in the future time period.

4. The ion adsorption type rare earth mining monitoring and early warning system according to claim 3 is characterized in that: The LSTM network includes three gates to control data flow, including input gate, forget gate and output gate; the specific forget gate calculation formula is: ; In the formula, is the output of the previous time step, is the output of the current time step, The output value of the forget gate, The weight matrix of the forget gate, Bias term, is the activation function; The specific input gate calculation process is: ; At the same time, generate candidate memory update information: ； In the formula, is the output value of the input gate, is the weight matrix of the input gate, The candidate memory value generated for the current time step is used Function nonlinear activation, is the weight matrix updated for the candidate memory, and are the bias terms of the input gate and candidate memory, respectively. is the hyperbolic tangent function; The specific output gate combines the current memory state to output: ； The final output is: ; In the formula, is the output value of the output gate, is the weight matrix of the output gate, is the bias term of the output gate, is the output of the model, is the memory cell state at the current time step.

5. The ion adsorption type rare earth mining monitoring and early warning system according to claim 4 is characterized in that: In LSTM network , , , , , , as well as The adjustments were calculated by the mean square error method.

Images