Lithium production method and device

Abstract

A lithium production method according to an embodiment of the present invention comprises the steps of: calculating a main variable for determining a production amount of a production tank in an electrodialysis facility through an artificial intelligence model; setting a range of input conditions for the calculated main variable; and inputting, to the artificial intelligence model, input conditions within the set range to calculate a production amount and production results, which correspond to the input conditions, and if the calculated production amount and production results meet specific conditions, determining final operating conditions from the production amount and production results.

Description

Lithium production method and device

[0001] The present invention relates to a method and apparatus for producing lithium, and more particularly, to a method and apparatus for producing lithium that determine operating conditions for optimal production volume and production index.

[0002] Bipolar Electrodialysis (BPED) is an electrochemical separation process that uses ion exchange materials to separate or concentrate specific ions from a solution. BPED is gaining recognition as a particularly important water separation and regeneration technology. However, the efficiency and performance of BPED operations can vary significantly depending on various operating conditions. Therefore, finding optimal operating conditions can significantly improve the process's economic feasibility and efficiency.

[0003] One embodiment of the present invention provides a lithium manufacturing method and device that determines optimal operating conditions for each of the major variables produced by applying a boosting series artificial intelligence model in a preprocessing process.

[0004] One embodiment of the present invention provides a lithium manufacturing method and device that generates optimal operating conditions that satisfy optimal production volume and production results for key variables calculated through artificial intelligence-based preprocessing.

[0005] Among the embodiments, the lithium production method includes a step of calculating a key variable that determines the production amount of a production tank in an electrodialysis facility through an artificial intelligence model, a step of setting a range of input conditions for the calculated key variables, and a step of inputting input conditions within the range into the artificial intelligence model to calculate a production amount and a production result corresponding to the input conditions, and a step of determining final operating conditions from the production amount and the production result when the calculated production amount and the production result satisfy specific conditions.

[0006] The step of determining the final operating conditions may include a first step of generating input conditions randomly selected within the set range, a second step of inputting the generated input conditions into a boosting series artificial intelligence model to produce a production amount and a production result corresponding to the input conditions, a third step of determining the production amount and the input conditions as candidate operating conditions when the production result satisfies a preset constraint, and a step of determining one candidate operating condition that produces a production amount and a production result closest to a preset target condition among a plurality of candidate operating conditions determined by repeating the first to third steps as the final operating condition.

[0007] The step of calculating the above key variables may include a cleaning step of obtaining a plurality of first variables through data cleaning for a plurality of initial variables used in the electrodialysis equipment, a first preprocessing step of inputting the first variables into a boosting series artificial intelligence model to calculate the variable importance of each of the first variables, and obtaining a plurality of second variables through preprocessing based on the variable importance, and a second preprocessing step of inputting the second variables into the boosting series artificial intelligence model to obtain a plurality of key variables that satisfy a prediction consistency higher than a first criterion with a minimum number of variables.

[0008] The above variable importance may use permutation importance, and the first preprocessing step may include a step of removing first variables among the first variables whose permutation importance is less than a preset second criterion.

[0009] The second preprocessing step may include a step of calculating the predicted consistency through the mean absolute percentage error (MAPE).

[0010] The step of setting the range of the above input conditions may include a step of determining the range of the input conditions based on the upper and lower limits of the input conditions within the total operating period using the above electrodialysis equipment.

[0011] The above production tank includes a base tank and an acid tank, and the production amount may include lithium (Li) production amount, sulfur (S) production amount, and sulfur production amount and lithium production amount in the acid tank.

[0012] The above key variables may include a first key variable that determines the lithium production amount within the base tank, a second key variable that determines the sulfur production amount within the base tank, a third key variable that determines the sulfur production amount within the acid tank, and a fourth key variable that determines the lithium production amount within the acid tank.

[0013] The above production results include a plurality of production indices, and the plurality of production indices may include a sulfur (S) concentration in a base tank, a lithium concentration in an acid tank, current efficiency, and a lithium conversion rate.

[0014] The second step may include a step of calculating the production amount for each of the first to fourth major variables by inputting first to fourth input conditions randomly selected in response to each of the first to fourth major variables, and calculating the production result by combining the calculated production amounts for each of the first to fourth major variables.

[0015] Among the embodiments, the lithium production device includes a key variable calculation module that calculates key variables that determine the production volume of a production tank in an electrodialysis facility through an artificial intelligence model, an operation condition generation module that sets a range of input conditions for the calculated key variables, inputs input conditions selected within the range into the artificial intelligence model, and calculates the production volume and production results corresponding to the input conditions as operation conditions, and an operation condition optimization module that determines the calculated operation conditions as final operation conditions when the operation conditions satisfy specific conditions.

[0016] The above-mentioned operating condition generation module determines the production amount and the input conditions as candidate operating conditions when the production result satisfies the preset constraints, and the operating condition optimization module determines one candidate operating condition that produces the production amount and production result closest to the preset target conditions among the plurality of candidate operating conditions generated through the above-mentioned operating condition generation module as the final operating condition.

[0017] The above-mentioned key variable production module may include a cleaning unit that obtains a plurality of first variables through data cleaning for a plurality of initial variables used in an electrodialysis facility that produces lithium, a first preprocessing unit that inputs the first variables into a boosting series artificial intelligence model to calculate the variable importance of each of the first variables and obtains a plurality of second variables through preprocessing based on the variable importance, and a second preprocessing unit that inputs the second variables into the boosting series artificial intelligence model to obtain a plurality of key variables that satisfy a prediction consistency higher than a first criterion with a minimum number of variables.

[0018] The above variable importance uses permutation importance, and the first preprocessing unit can remove first variables among the first variables whose permutation importance is less than a preset second criterion.

[0019] The above second preprocessing unit can calculate the predicted consistency through the mean absolute percentage error (MAPE).

[0020] The above-mentioned operating condition generation module can determine the range of the input conditions based on the upper and lower limits of the input conditions within the total operating period using the above-mentioned electrodialysis equipment.

[0021] The above production tank includes a base tank and an acid tank, and the production amount may include lithium (Li) production amount, sulfur (S) production amount, and sulfur production amount and lithium production amount in the acid tank.

[0022] The above key variables may include a first key variable that determines the lithium production amount within the base tank, a second key variable that determines the sulfur production amount within the base tank, a third key variable that determines the sulfur production amount within the acid tank, and a fourth key variable that determines the lithium production amount within the acid tank.

[0023] The above production results include a plurality of production indices, and the plurality of production indices may include a sulfur (S) concentration in a base tank, a lithium concentration in an acid tank, current efficiency, and a lithium conversion rate.

[0024] The above-mentioned operating condition generation module can input first to fourth input conditions randomly selected in response to each of the first to fourth major variables, calculate the production amount for each of the first to fourth major variables, and calculate the production result by combining the calculated production amounts for each of the first to fourth major variables.

[0025] A lithium manufacturing method and device according to one embodiment of the present invention can determine optimal operating conditions for each of the major variables calculated by applying a boosting series artificial intelligence model in a preprocessing process.

[0026] The lithium production method and device according to one embodiment of the present invention can generate optimal operating conditions that satisfy optimal production volume and production results for key variables calculated through artificial intelligence-based preprocessing.

[0027] FIG. 1 is a drawing showing the configuration of an electrodialysis facility according to one embodiment of the present invention.

[0028] FIG. 2 is a drawing showing one end of an electrodialysis facility according to one embodiment of the present invention.

[0029] Figure 3 is a block diagram of a lithium manufacturing device according to one embodiment of the present invention.

[0030] Figure 4 is a flowchart of a step for calculating a main variable according to one embodiment of the present invention.

[0031] Figures 5 and 6 are flowcharts of a lithium manufacturing method according to one embodiment of the present invention.

[0032] Figures 7 to 10 are graphs showing the results of production volume calculations for major variables according to one embodiment of the present invention.

[0033] Figure 11 shows optimal operating conditions generated according to a lithium production method according to one embodiment of the present invention.

[0034] FIG. 12 is a drawing for explaining a computing device according to one embodiment of the present invention.

[0035] Below, with reference to the attached drawings, embodiments of the present invention are described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In addition, in the drawings, parts irrelevant to the description are omitted for clarity of description, and similar parts are designated with similar reference numerals throughout the specification.

[0036] Throughout the specification and claims, whenever a part is referred to as "comprising" a component, this does not exclude other components, but rather includes other components, unless otherwise stated. Terms including ordinal numbers, such as "first," "second," etc., may be used to describe various components, but these components are not limited by these terms. These terms are used solely to distinguish one component from another.

[0037] Terms such as “part,” “unit,” and “module” described in the specification may mean a unit capable of processing at least one function or operation described in the specification, which may be implemented by hardware or a circuit, software, or a combination of hardware or a circuit and software.

[0038] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0039] Fig. 1 is a drawing showing the configuration of an electrodialysis facility according to one embodiment of the present invention. Fig. 2 is a drawing showing one end of an electrodialysis facility according to one embodiment of the present invention.

[0040] In FIG. 1 and FIG. 2, the electrodialysis equipment may be a BPED (Bipolar ElectroDialysis) equipment. That is, the electrodialysis equipment may be a bipolar electrodialysis equipment. The electrodialysis equipment (BPED) may be equipment that converts a lithium sulfate aqueous solution into lithium hydroxide and sulfuric acid. Here, lithium sulfate is Li2SO4, lithium hydroxide is LiOH, and sulfuric acid is H2SO4. The electrodialysis equipment (BPED) may be an aqueous solution treatment equipment that simultaneously performs water decomposition / ion separation using an electrodialysis membrane in an electric field.

[0041] Referring to FIGS. 1 and 2, the electrodialysis device (BPED) may include a cation exchange membrane (CEM), an anion exchange membrane (AEM), and a bipolar membrane (BPM).

[0042] A cation exchange membrane (CEM) has an internal anionic group, allowing only cations (e.g., Li+) to pass through. An anion exchange membrane (AEM) allows only anions (e.g., SO42-) to pass through due to its internal cation group. A bipolar membrane (BPM) consists of a cation membrane and an anion membrane overlapping each other with a water-splitting catalyst in between. A bipolar membrane (BPM) can decompose water in an electric field to produce hydrogen ions (H+) and hydroxide ions (OH-).

[0043] That is, the electrodialysis equipment (BPED) may be an aqueous solution treatment equipment that simultaneously performs water splitting (decomposition into H+, OH-) / ion separation (ion separation of Li+, SO42-) using an electrodialysis membrane (cation dialysis membrane, anion dialysis membrane, bipolar membrane) in an electric field.

[0044] In Fig. 1, in a BPED device, the LS solution can transfer Li and SO4 ions to the LH solution and sulfuric acid (H2SO4) solution through a three-stage process (press) including the first to third stages. For example, in the BPED device, deionized water (DI water) can be converted into the LH solution and sulfuric acid solution by contacting the LS solution in a counterflow manner. Here, the LS solution is lithium sulfate (Li2SO4), and the LH solution is lithium hydroxide (LiOH).

[0045] The first to third stages may each include a salt room, an acid room, a base room, a salt tank, an acid tank, and a base tank.

[0046] In each stage, the Salt chamber supplies lithium sulfate (Li2SO4) to produce desalted water after the reaction. The Acid chamber supplies deionized water (DI water) to produce sulfuric acid (H2SO4) after the reaction. The Base chamber supplies deionized water (DI water) to produce lithium hydroxide (LiOH) after the reaction.

[0047] The salt tank stores the produced desalinated water. The acid tank stores the produced sulfuric acid. The base tank stores the produced lithium hydroxide.

[0048] The production volume of the BPED (Bioelectrodialysis Device) is determined by the discharge flow rates of sulfuric acid and lithium hydroxide. The production volume can be determined by controlling the input flow rates of water (H2O) and lithium sulfate, the current and voltage of the rectifier, and the management of the pH, conductivity, circulation flow rate, and circulation pressure within each chamber. The input flow rate of the solution, the current and voltage of the rectifier, pH, conductivity, circulation flow rate, and circulation pressure, which correspond to the control and management elements, can be detected through internal sensors installed in each chamber. The control and management elements can correspond to variables that determine the concentration of lithium hydroxide and sulfuric acid produced.

[0049] As a production result for determining the optimal operating conditions of a BPED (Bioelectrodialysis Equipment), the production index may include lithium production (kg / hr), current efficiency (%), sulfur (S) concentration ratio in the base solution, lithium (Li) concentration ratio in the acid solution, and lithium (Li) conversion rate (%).

[0050] The lithium concentration in the base solution in the base tank of the electrodialysis device (BPED), the sulfur concentration in the base solution in the base tank, the sulfur concentration in the acid solution in the acid tank, and the lithium concentration in the acid solution in the acid tank may be components for calculating the above production index.

[0051] That is, the first major variable for the lithium concentration in the base solution (LiOH) in the base tank of the electrodialysis device (BPED), the second major variable for the sulfur concentration in the base solution in the base tank, the third major variable for the sulfur concentration in the acid solution (H2SO4) in the acid tank, and the fourth major variable for the lithium concentration in the acid solution in the acid tank may be major variables that determine the production index. The first to fourth major variables may each be calculated through an artificial intelligence model of the boosting series.

[0052] Figure 3 is a block diagram of a lithium manufacturing device according to one embodiment of the present invention.

[0053] The lithium production device (1000) generates optimal operating conditions to achieve an objective formula (objective condition) for production indices including lithium production amount (kg / hr), current efficiency (%), S concentration ratio in base, Li concentration ratio in acid, and Li conversion rate (%).

[0054] The lithium production device (1000) can generate optimal operating conditions through the first to fourth major variables described above. Since the major variables are used as components of production indicators representing optimal operating conditions, they are calculated through an artificial intelligence model with a high degree of consistency. The lithium production device (1000) can generate a prediction model for each of the first to fourth major variables described above as a partial model.

[0055] The lithium production device (1000) includes a key variable output module (100), an operating condition generation module (200), and an operating condition optimization module (300).

[0056] The key variable output module (100) can output key variables through a boosting series artificial intelligence model. More specifically, the key variable output module (100) can output key variables through a boosting series artificial intelligence model that includes partial models that output the first to fourth key variables, respectively. The key variable output module (100) includes a cleaning unit (110), a first preprocessing unit (120), a second preprocessing unit (130), and a prediction verification unit (140).

[0057] The cleaning unit (110) can obtain a plurality of first variables through preprocessing of a plurality of initial variables used in a BPED (Blood Electrodialysis Device). For example, the number of initial variables may be 525. The cleaning unit (110) can remove missing values, outliers, duplicate data, non-identical data (non-operating sensor data), and data for processes other than the BPED process through preprocessing of data cleaning from the initial variables including all variables of the BPED process. The cleaning unit (110) can also remove data that moves identically as duplicate data based on correlation analysis for each data. The cleaning unit (110) can obtain a number of first variables reduced compared to the initial variables through data cleaning. For example, the number of first variables may be 400.

[0058] The first preprocessing unit (120) can input the first variables into a boosting series artificial intelligence model and calculate the variable importance of each of the first variables.

[0059] Boosting-type AI models can be AI models that utilize boosting algorithms. Boosting is a type of machine learning algorithm that combines weak learners to create a strong learner. Boosting can be used for classification and regression problems. Boosting algorithms train models sequentially. At each step, the boosting algorithm adds a new model that corrects the errors of previous models. The boosting algorithm combines all models to produce a final prediction.

[0060] The boosting family of AI models can be selected from the group consisting of AdaBoost, Random Forest, Catboost, Gradient Boosting Model, Light GBM, and XGBoost. The boosting family of AI models is preferably XGBoost.

[0061] AdaBoost (Adaptive Boosting) is one of the early boosting algorithms. It learns by assigning weights to each data point and giving more weight to misclassified data points.

[0062] Gradient Boosting Machines (GBM) train models to minimize errors. The error at each step is calculated using the gradient of the loss function.

[0063] XGBoost (Extreme Gradient Boosting) is an extended version of GBM, which includes features such as regularization, parallel processing, and missing value handling.

[0064] LightGBM is a boosting algorithm specialized for large datasets, featuring fast learning speed and efficient memory usage. Like XGBoost, it includes regularization and parallel processing capabilities.

[0065] CatBoost is a boosting algorithm specialized for categorical data, providing automatic categorical feature transformation and fast learning speed.

[0066] Boosting AI models, for regression problems like predicting production concentration, preprocess data, train models, and analyze performance and feature importance. Once a satisfactory model is obtained, boosting AI models are applied to real-world environments to predict concentration in real time and leverage this knowledge for production control and optimization.

[0067] In this process, the boosting series artificial intelligence model can identify which variables have the greatest influence on predicting production concentration by analyzing the importance of features or variables.

[0068] That is, the first preprocessing unit (120) can analyze the variable importance of the first variables through a boosting series artificial intelligence model and determine which variables among the first variables have a greater influence on the prediction of production volume including lithium and sulfur production concentration.

[0069] The first preprocessing unit (120) can use permutation importance to determine variable importance. Permutation importance is a methodology for estimating the importance of a feature by determining how much the value of a model performance indicator (accuracy, F1-score, R^2, etc.) decreases when a feature is excluded from an artificial intelligence model.

[0070] The first preprocessing unit (120) can obtain a plurality of second variables through the first preprocessing based on the calculated variable importance. For example, the first preprocessing unit (120) can remove first variables whose permutation importance is below a preset specific standard from among the first variables. That is, the first preprocessing unit (120) can assume that the lower the importance of a variable according to the permutation importance of each first variable, the lower the impact on the performance of the artificial intelligence model, and can improve the production prediction performance of the artificial intelligence model by reducing data noise by removing variables whose importance is lower than a specific standard. The second variables can include the remaining variables after removing variables whose permutation importance is below a specific standard from among the first variables. For example, the number of second variables can be 100.

[0071] The second preprocessing unit (130) inputs the second variables into a boosting-type artificial intelligence model, thereby obtaining a plurality of third variables that satisfy a predicted consistency level higher than the first criterion with a minimum number of variables. For example, the number of third variables may be determined differently for each submodel, such as 4, 10, 33, or 100.

[0072] Boosting-type AI models improve the predictive performance of models by generating models using preprocessed data and evaluating their performance. In one embodiment, the second preprocessing unit (130) evaluates the model's performance using second variables and, based on the evaluation results, obtains third variables with a predictive accuracy exceeding a certain threshold. For example, the second preprocessing unit (130) may use evaluation metrics such as MAE, RMSE, and MAPE.

[0073] MAE (Mean Absolute Error) is the average of the absolute values ​​of each prediction error. RMSE (Root Mean Square Error) is the square root of the average of the squares of each prediction error. MAPE (Mean Absolute Percentage Error) is the mean absolute error, which is calculated by dividing the absolute value of each prediction error by the actual value and then taking the average of the entire error. In other words, it is the percentage ratio of the difference between the actual value and the predicted value divided by the actual value. The result can be expressed as a percentage. MAPE is a tool for evaluating prediction consistency and is frequently used in regression problems / models. Because it represents the relative error ratio, it allows for intuitive interpretation of the prediction results.

[0074] The second preprocessing unit (130) can calculate the predicted consistency of the artificial intelligence model using the second variables using the mean absolute error (MAPE), and can obtain third variables included in the set consisting of the smallest number of variables among the sets of multiple variables that satisfy a predetermined specific criterion for the calculated predicted consistency. The third variables may be key variables. Key variables may be determined for each submodel. The key variables may be the first to fourth key variables described above.

[0075] The prediction verification unit (140) can calculate the variable importance for each of the acquired third variables. The prediction verification unit (140) can compare the predicted consistency when only one variable with the highest variable importance among the third variables is input into the boosting series artificial intelligence model with the predicted consistency when all of the third variables are input. The prediction verification unit (140) can confirm the third variables as final variables if the predicted consistency when all of the third variables are input is greater than the predicted consistency when the one variable with the highest variable importance is input.

[0076] The third variables may be any one of the conductivity, input flow rate, circulation flow rate and circulation pressure for any one of the lithium sulfate aqueous solution, sulfuric acid and lithium hydroxide.

[0077] The operating condition generation module (200) can set the range of input conditions for major variables.

[0078] The operating condition generation module (200) can determine the range of input conditions based on the upper and lower limits of the input conditions within the total operating period using the electrodialysis equipment. The operating condition generation module (200) verifies the lower and upper limits of the input conditions for each variable during the total operating period. Table 1 shows the lower and upper limits of each input condition for some of the 100 variables.

[0079] NumberTagNameLowerLimitUpperLimit1First flow rate value6.616.82Second flow rate value9.7163Third flow rate value4.814.14Fourth flow rate value04.65Fifth flow rate value07쪋쪋쪋쪋25First temperature value253726Second temperature value254527Third temperature value253828Fourth temperature value94729Fifth temperature value254030Sixth temperature value2546.5쪋쪋쪋쪋99First conductivity value0339100Third conductivity value35339

[0080] For example, the first to fifth flow rate values ​​of variable numbers 1 to 5 show the lower and upper limits of the flow rate values ​​detected (tagged) by the first to fifth sensors, respectively. The first temperature value of number 25 shows that the lower limit of the temperature (TT) detected (tagged) by the first temperature sensor during the total operation period is 25 degrees and the upper limit is 37 degrees. The third conductivity value of number 100 shows that the lower limit of the conductivity (CT) detected by the third current-voltage sensor is 35 and the upper limit is 339. The operation condition generation module (200) can set the range of the lower limit and upper limit of the input condition for each of the identified variables as the range of the input condition for each of the variables. The operation condition generation module (200) can randomly select the input condition within the set range. For example, the operating condition generation module (200) can set the temperature input condition for the first variable temperature value to 30 degrees, which is randomly selected from the range of 25 to 37 degrees. At the same time, the conductivity input condition for the third variable conductivity value can be set to 250, which is randomly selected from the range of 35 to 339. The operating condition generation module (200) can generate multiple input conditions by repeatedly selecting input conditions randomly.

[0081] The operating condition generation module (200) can input the selected input conditions into a boosting series artificial intelligence model to produce the corresponding production amount and production results.

[0082] For example, the operating condition generation module (200) can input a first input condition randomly selected as described above into each of the first major variables derived from the partial model for the lithium concentration (first major variable) in the base solution in the base tank, and can calculate the lithium concentration corresponding to the input input condition. The operating condition generation module (200) can also input second and third input conditions randomly selected for each of the second and third major variables, and can calculate the concentration of sulfur or lithium as the production amount.

[0083] The operating condition generation module (200) can produce a production result by combining the production amount for each of the first to fourth major variables produced. The production result can be expressed as a production index including lithium production amount (kg / hr), current efficiency (%), S concentration ratio in base, Li concentration ratio in acid, and Li conversion rate (%), as described above.

[0084] The operating condition generation module (200) can generate the corresponding production amount and the first to fourth input conditions as candidate operating conditions when the production result satisfies the preset constraints. The operating condition generation module (200) can generate multiple candidate operating conditions. That is, the operating condition generation module (200) can repeatedly generate input conditions randomly selected within the range of input conditions for major variables, and generate multiple candidate operating conditions based on the input conditions. The operating condition generation module (200) can repeat the generation of candidate operating conditions a preset number of times (m).

[0085] The operating condition optimization module (300) can determine, as the final operating condition, one candidate operating condition that produces the production amount and production result closest to the preset target condition among multiple candidate operating conditions generated through the operating condition generation module (200).

[0086] Figure 4 is a flowchart illustrating a step for calculating key variables according to one embodiment of the present invention. The step for calculating key variables can be performed through a key variable calculation module (100, see Figure 3). The key variable calculation module (100, see Figure 3) can calculate multiple key variables through the step for calculating key variables.

[0087] The steps for producing key variables include a cleaning step (step S100), a first preprocessing step (step S200), a second preprocessing step (step S300), and a verification step (step S400).

[0088] In Fig. 4, first, the cleaning step (step S100) may include a cleaning step for preparing and cleaning a dataset of BPED operation data (step S110). The cleaning step (step S100) obtains a first variable by cleaning the initial variables (step S120). Data cleaning may include removing missing values, outliers, duplicate data, non-identical data (non-operating sensor data), and data for processes other than the BPED process.

[0089] Thereafter, the first preprocessing step (step S200) may preprocess the first variable using XGBoost, a boosting series artificial intelligence model. The first preprocessing step (step S200) may input the first variable into XGBoost (step S210). The first preprocessing step (step S200) determines the variable importance of each first variable using permutation importance (step S220). The first preprocessing step (step S200) obtains the second variable by removing the subfactor of the permutation importance (step S230).

[0090] Afterwards, the second preprocessing step (step S300) inputs the second variable into XGBoost to obtain feedback on performance through the consistency (step S310). The second preprocessing step (step S300) searches for a condition in which the consistency criteria (e.g., 90% or 95%) or higher are achieved through consistency determination factors such as MAPE and the number of variables satisfying variable importance (e.g., permutation importance) is minimized (step S320). The second preprocessing step (step S300) derives and quantifies the main factors satisfying the above conditions as the minimum variables (main variables) that affect the process (step S330).

[0091] Subsequently, the verification step (step S400) trains and evaluates the AI ​​model using the derived key variables (step S410). The learning and evaluation step (step S400) can verify the influence of the key variables based on the predicted consistency of the evaluation results (step S420). The influence of the key variables can be verified through the graphs of Figures 7 to 10.

[0092] Figures 5 and 6 are flowcharts of a lithium manufacturing method according to one embodiment of the present invention. The lithium manufacturing method can be performed using a lithium manufacturing device (1000, see Figure 3).

[0093] The lithium manufacturing device (1000) can set the upper / lower limits of the search range of input conditions for each major variable calculated through the steps of FIG. 4 (step S610). The upper / lower limits of the search range can be set based on tag data measured during the total operation period.

[0094] The lithium manufacturing device (1000) can randomly generate input conditions within the search range for each major variable (step S620). For example, the lithium manufacturing device (1000) randomly generates input conditions for each major variable for multiple partial models (e.g., four prediction models (see FIG. 6)).

[0095] The lithium production device (1000) inputs the generated input conditions into an XGBoost prediction model for each major variable to calculate the values ​​of lithium production amount and production result, and can check whether the production result satisfies the constraints (step S630). The lithium production device (1000) can determine the input conditions and lithium production amount in cases where the constraints are satisfied as candidate operating conditions.

[0096] The lithium production device (1000) may replace the global optimal solution (step S640) with the final optimal solution for each major variable after repeating the above steps (steps S610 to S630). That is, the lithium production device (1000) may determine, as the final operating condition, one of the multiple candidate operating conditions determined by repeating the above steps (steps S610 to S630) that produces the production amount and production result closest to the preset target condition.

[0097] FIG. 6 is a drawing specifically showing the lithium manufacturing method of FIG. 5 according to one embodiment.

[0098] In Fig. 6, the tag data may include variables, and the variables may include manipulated variables and management variables. The manipulated variables may include control elements, and the management variables may include management elements. The control elements and management elements may include the input flow rate, current of the rectifier, voltage, pH, conductivity, circulation flow rate, and circulation pressure for each of the base solution and the acid solution. The Li concentration in Li2SO4 of the ICP data may be the lithium (Li) concentration of the original solution tank containing the LS input solution (Li2SO4).

[0099] n particles can represent variables with n different input conditions. The n input conditions can be randomly selected from the range of the lower and upper limits of each variable.

[0100] The objective formula includes the objective conditions that must be satisfied by maximizing lithium (Li) production and other production indicators. The constraint formula includes the constraints that must be satisfied by the facility at a minimum.

[0101] The lithium manufacturing method detects optimal operating conditions (optimal particles) that satisfy the objective and constraints.

[0102] The lithium production method can satisfy the objective conditions of the production indicators by using multiple (four) partial models (prediction models) and input variables in the objective formula. In the objective formula, the lithium production method can calculate the lithium concentration in the base solution (LiOH) in the base tank, the sulfur concentration in the base solution (LiOH) in the base tank, the sulfur concentration in the acid solution (H2SO4) in the acid tank, and the lithium concentration in the acid solution (H2SO4) in the acid tank through the prediction models.

[0103] The first prediction model calculates the lithium concentration in the base solution within the base tank. The second prediction model calculates the sulfur concentration in the base solution within the base tank. The third prediction model calculates the sulfur concentration in the acid solution within the acid tank. The fourth prediction model calculates the lithium concentration in the acid solution within the acid tank.

[0104] The first to fourth input conditions input to the first to fourth key variables corresponding to the first to fourth prediction models using the boosting series artificial intelligence model can be randomly generated within upper and lower bounds, respectively. The first to fourth key variables are each acquired through artificial intelligence-based preprocessing, as described in Fig. 4.

[0105] The current of rectifiers No. 1 to 6 can be the current value of each rectifier from 1 to 6. The LS solution is lithium sulfate (Li2SO4), and the LH solution is lithium hydroxide (LiOH).

[0106] In the objective conditions, production results can be produced through a combination of key variables and input variables of the first to fourth prediction models.

[0107] Lithium production is calculated using the first prediction model and the daily LH production. The S concentration (g / L) in the first-stage base is calculated using the first and second prediction models. The Li concentration (g / L) in the acid is calculated using the third and fourth prediction models. The lithium conversion rate can be calculated based on the first prediction model, the lithium (Li) concentration in the raw solution tank, and the input flow rate of the LS input solution. The current efficiency can be calculated based on the first prediction model and the current of rectifiers No. 1 to 6.

[0108] The lithium manufacturing method can be verified to satisfy constraints regarding key variables and input variables that satisfy the objective conditions. For example, the constraints include: the sulfur concentration in the base must be 0.065 g / L or less; the lithium concentration in the acid must be 0.1 g / L or less (maximum 0.2 g / L or less); the lithium conversion rate must be 85% or more (minimum 65%); the current efficiency must be 50% or more (minimum 40%); and the range of input conditions for each variable must be within the range of the lower limit and the upper limit.

[0109] The lithium manufacturing method can be repeated a preset number of times (maxiter = m). This method can generate optimized operating conditions through repeated execution. In other words, through m repetitions, the lithium manufacturing method can ultimately generate optimal operating conditions, including the lithium production amount and input conditions (variable values) of the ith particle, which produce a production result closer to the target conditions than the production result of the globally optimal particle.

[0110] Figures 7 to 10 are graphs showing the results of production calculations according to key variables according to one embodiment of the present invention. Figures 7 to 10 each show changes in the concentration of lithium or sulfur during the operation period.

[0111] Figure 7 is a graph showing the results of lithium concentration prediction based on the first major variable of the lithium concentration prediction model in the base solution in the base tank.

[0112] In Figure 7, the actual lithium concentration change (Real) and the predicted lithium concentration change (Pred) show similar patterns. The mean absolute error (MAPE) is 2.024, indicating a predicted agreement of approximately 98%, exceeding 90%. Therefore, the derived first primary variable is verified to be comprised of the minimum number of variables with an agreement above the standard (90% or higher).

[0113] Figure 8 is a graph showing the sulfur concentration prediction results based on the second main variable of the sulfur concentration prediction model in the base solution in the base tank.

[0114] In Figure 8, the actual lithium concentration change (Real) and the predicted lithium concentration change (Pred) show similar patterns. The mean absolute error (MAPE) is 5.223, indicating a predicted agreement of approximately 95%, exceeding 90%. In other words, the derived second primary variable appears to be comprised of the minimum variables with an agreement above the standard.

[0115] Figure 9 is a graph showing the sulfur concentration prediction results based on the third main variable of the sulfur concentration prediction model in the acid solution in the acid tank.

[0116] In Figure 9, the actual lithium concentration change (Real) and the predicted lithium concentration change (Pred) show similar patterns. The mean absolute error (MAPE) is 4.325, indicating a predicted agreement of approximately 96%, exceeding 90%. In other words, the derived third primary variable appears to be comprised of the minimum variables with an agreement above the standard.

[0117] Figure 10 is a graph showing the results of lithium concentration prediction based on the fourth main variable of the lithium concentration prediction model in the acid solution in the acid tank.

[0118] In Figure 10, the actual lithium concentration change (Real) and the predicted lithium concentration change (Pred) similarly show similar patterns. The mean absolute error (MAPE) is 4.325, indicating a predicted agreement of approximately 96%, exceeding 90%. In other words, the derived fourth primary variable appears to be comprised of the minimum variables with an agreement above the standard.

[0119] Figure 11 shows optimal operating conditions generated according to a lithium production method according to one embodiment of the present invention. Figure 11 shows optimal operating conditions generated according to the embodiment of Figure 6.

[0120] Referring to Figure 11, the table showing productivity targets includes the set values ​​(constraints) and resulting values ​​(production results) for each production indicator. Each production indicator represents the optimal production result that satisfies the constraints.

[0121] The manipulated and controlled variables show the input conditions for each key variable. Each key variable is calculated through preprocessing and a prediction model using a boosting-type artificial intelligence model. For example, key variables include input raw material, input flow rate, rectifier voltage, and circulating flow rate. The input conditions are randomly selected for each key variable and can be iterated to obtain optimal input conditions. For example, the input conditions can be selected as optimal values ​​within the range where the conductivity of the key variable of the input raw material is 1, with a maximum of 339 and a minimum of 0.

[0122] FIG. 12 is a drawing for explaining a computing device according to one embodiment of the present invention.

[0123] Referring to FIG. 12, the lithium manufacturing method and device according to the embodiments can be implemented using a computing device (900).

[0124] The computing device (900) may include at least one of a processor (910), a memory (930), a user interface input device (940), a user interface output device (950), and a storage device (560) that communicate via a bus (920). The computing device (900) may also include a network interface (970) electrically connected to a network (90). The network interface (970) may transmit or receive signals to or from other entities via the network (90).

[0125] The processor (910) may be implemented in various types such as an MCU (Micro Controller Unit), an AP (Application Processor), a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an NPU (Neural Processing Unit), etc., and may be any semiconductor device that executes instructions stored in a memory (930) or a storage device (960). The processor (910) may be configured to implement the functions and methods described above with respect to FIGS. 1 to 11.

[0126] The memory (930) and storage device (960) may include various types of volatile or non-volatile storage media. For example, the memory may include read-only memory (ROM) (931) and random access memory (RAM) (932). In the present embodiment, the memory (930) may be located inside or outside the processor (910), and the memory (930) may be connected to the processor (910) via various known means.

[0127] In some embodiments, at least some components or functions of the lithium manufacturing methods and devices according to the embodiments may be implemented as a program or software running on a computing device (900), and the program or software may be stored on a computer-readable medium.

[0128] In some embodiments, at least some components or functions of the lithium manufacturing methods and devices according to the embodiments may be implemented using hardware or circuitry of the computing device (900), or may be implemented as separate hardware or circuitry that can be electrically connected to the computing device (900).

[0129] Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements made by a person of ordinary skill in the art to which the present invention pertains using the basic concept of the present invention defined in the following claims also fall within the scope of the present invention.

[0130] [Explanation of symbols]

[0131] 1000: Lithium production device

[0132] 100: Key Variable Output Module

[0133] 200: Operating Conditions Generation Module

[0134] 300: Operating Condition Optimization Module

[0135] 110: Cleaning Department

[0136] 120: Preprocessing Unit 1

[0137] 130: Second preprocessing unit

[0138] 140: Prediction Verification Unit

Claims

1. A step of calculating key variables that determine the production volume of the production tank in the electrodialysis facility using an artificial intelligence model; A step for setting the range of input conditions for the above-mentioned key variables; and A lithium manufacturing method comprising the step of inputting input conditions within the above range into an artificial intelligence model, calculating production amounts and production results corresponding to the input conditions, and determining final operating conditions from the production amounts and production results when the calculated production amounts and production results satisfy specific conditions.

2. In paragraph 1, the step of determining the final operating conditions is: A first step of generating input conditions randomly selected within the set above range; A second step of inputting the generated input conditions into a boosting series artificial intelligence model to produce the production amount and production results corresponding to the input conditions; A third step of determining the production volume and the input conditions as candidate operating conditions if the above production results satisfy the preset constraints; and A lithium production method comprising a step of determining, as a final operating condition, one candidate operating condition that produces a production amount and production result closest to a preset target condition among a plurality of candidate operating conditions determined by repeating the first to third steps.

3. In the second paragraph, the step of calculating the main variable is as follows: A cleaning step for obtaining a plurality of first variables through data cleaning for a plurality of initial variables used in the above-mentioned electrodialysis equipment; A first preprocessing step of inputting the above first variables into a boosting series artificial intelligence model to calculate the variable importance of each of the first variables and obtaining a plurality of second variables through preprocessing based on the variable importance; and A lithium manufacturing method including a second preprocessing step of inputting the second variables into the boosting series artificial intelligence model to obtain a plurality of key variables that satisfy a prediction consistency higher than the first criterion with a minimum number of variables.

4. In the third paragraph, the variable importance uses permutation importance, A lithium manufacturing method, wherein the first preprocessing step includes a step of removing first variables among the first variables whose permutation importance is less than a preset second criterion.

5. A lithium manufacturing method in the third paragraph, wherein the second preprocessing step includes a step of calculating the predicted consistency through the mean absolute percentage error (MAPE).

6. A lithium production method in the second paragraph, wherein the step of setting the range of the input conditions includes the step of determining the range of the input conditions based on the upper and lower limits of the input conditions within the total operation period using the electrodialysis equipment.

7. In the second paragraph, the production tank includes a base tank and an acid tank, The above production amount includes lithium (Li) production amount, sulfur (S) production amount, and sulfur production amount in the acid tank, and lithium production amount.

8. A method for producing lithium in the 7th paragraph, wherein the main variables include a first main variable determining the lithium production amount in the base tank, a second main variable determining the sulfur production amount in the base tank, a third main variable determining the sulfur production amount in the acid tank, and a fourth main variable determining the lithium production amount in the acid tank.

9. In paragraph 8, the production result includes multiple production indicators, A lithium production method wherein the above multiple production indices include sulfur (S) concentration in a base tank, lithium concentration in an acid tank, current efficiency, and lithium conversion rate.

10. In paragraph 9, the second step is, Each of the first to fourth main variables is input by randomly selecting the first to fourth input conditions corresponding to each of the first to fourth main variables, and the production amount for each of the first to fourth main variables is calculated. A method for producing lithium, comprising a step of combining the production amounts for each of the above produced to produce the production result.

11. Key variable calculation module that calculates key variables that determine the production volume of the production tank in the electrodialysis facility through an artificial intelligence model; An operating condition generation module that sets the range of input conditions for the above-mentioned major variables and inputs input conditions selected within the above-mentioned range into an artificial intelligence model to generate the production amount and production results corresponding to the above-mentioned input conditions as operating conditions; and A lithium manufacturing device including an operating condition optimization module that determines the operating conditions as final operating conditions when the generated operating conditions satisfy specific conditions.

12. In paragraph 11, the operating condition generation module determines the production amount and the input conditions as candidate operating conditions when the production result satisfies the preset constraints. The above-mentioned operating condition optimization module is a lithium manufacturing device that determines, as the final operating condition, one candidate operating condition that produces the production amount and production result closest to the preset target condition among the multiple candidate operating conditions generated through the above-mentioned operating condition generation module.

13. In paragraph 12, the main variable calculation module, A cleaning unit for obtaining a plurality of first variables through data cleaning of a plurality of initial variables used in an electrodialysis facility for producing lithium; A first preprocessing unit that inputs the above first variables into a boosting series artificial intelligence model to calculate the variable importance of each of the first variables and obtains a plurality of second variables through preprocessing based on the variable importance; and A lithium manufacturing device including a second preprocessing unit that inputs the second variables into the boosting series artificial intelligence model to obtain a plurality of key variables that satisfy a prediction consistency higher than the first criterion with a minimum number of variables.

14. In the 13th paragraph, the variable importance uses permutation importance, A lithium manufacturing device wherein the first preprocessing unit removes first variables among the first variables whose permutation importance is less than a preset second criterion.

15. A lithium manufacturing device in accordance with claim 13, wherein the second preprocessing unit calculates the predicted accuracy through mean absolute percentage error (MAPE).

16. In the 12th paragraph, the operating condition generation module is a lithium production device that determines the range of the input conditions based on the upper and lower limits of the input conditions within the total operating period using the electrodialysis equipment.

17. In the 12th paragraph, the production tank includes a base tank and an acid tank, The above production amount is a lithium production device including lithium (Li) production amount, sulfur (S) production amount, and sulfur production amount in the acid tank and lithium production amount.

18. A lithium production device in accordance with claim 17, wherein the main variables include a first main variable that determines the lithium production amount in the base tank, a second main variable that determines the sulfur production amount in the base tank, a third main variable that determines the sulfur production amount in the acid tank, and a fourth main variable that determines the lithium production amount in the acid tank.

19. In paragraph 18, the production result includes multiple production indicators, A lithium production device wherein the above multiple production indices include sulfur (S) concentration in a base tank, lithium concentration in an acid tank, current efficiency, and lithium conversion rate.

20. In the 19th paragraph, the operating condition generation module inputs first to fourth input conditions randomly selected in response to each of the first to fourth major variables, and calculates the production amount for each of the first to fourth major variables. A lithium production device that produces the production result by combining the production amounts for each of the first to fourth major variables produced.

Images