Apparatus and method for operating electrodialysis process in response to operation situation

Abstract

A method for operating an electrodialysis process in response to an operation situation, according to one embodiment, may comprise the steps of: collecting operation situation data including a lithium concentration and an impurity concentration in a produced base solution; determining, on the basis of the operation situation data, whether a defect occurs in process equipment; and deriving, from among process variables, a main process variable requiring control according to the occurrence of the defect, by determining importance of the process variables through an artificial intelligence model.

Description

Operating condition-sensitive electrodialysis process operation device and method

[0001] This application claims priority to Korean Patent Application No. 10-2024-0190708 filed on December 19, 2024, and all contents of said priority application are incorporated into this specification.

[0002] The present invention relates to an operating condition-sensitive electrodialysis process operation device and method, and more specifically, to an operating condition-sensitive electrodialysis process operation device and method that variably determines key process variables in response to defects within the electrodialysis facility.

[0003] BiPolar Electrodialysis (BPED) is an electrolysis process used to separate or concentrate specific ions from a solution using ion exchange materials. BPED is gaining prominence as a particularly important water separation and regeneration technology.

[0004] BPED operation data may include various data collected during the operation of the technology. BPED operation data may include, for example, current and voltage data, substance concentration data, temperature and pressure data, and time data.

[0005] The process operation method must be changed depending on the Li concentration and S concentration (impurities) in the produced Base (LiOH) solution. When BPED is operating normally, the operation is carried out mainly by controlling the circulation flow rate of each stage and the flow rate of the raw material solution (input flow rate). However, if physical defects occur in the BP membrane during operation, operating with the existing method results in poor operational outcomes such as low current efficiency, low product quality, and low Li production.

[0006] One embodiment of the present invention aims to provide an operating condition-sensitive electrodialysis process operation device and method, wherein, when a defect occurs in an electrodialysis facility, process variables are input into an artificial intelligence model to calculate their importance, a process variable of higher importance is selected and determined as a major process variable according to the calculated importance, and the process is operated based on the determined major process variable.

[0007] One embodiment of the present invention aims to provide an operating condition-sensitive electrodialysis process operation device and method that derives key process variables specialized for defect conditions using an artificial intelligence model-based importance calculation algorithm when a defect occurs within the equipment, even when the process is operated under normal conditions.

[0008] Among the embodiments, the method for operating an operation condition-sensitive electrodialysis process may include the steps of collecting operation condition data including lithium concentration and impurity concentration in a produced base solution, determining whether a defect has occurred in the process equipment based on the operation condition data, and deriving a key process variable among the process variables that requires control due to the occurrence of the defect through an importance determination using an artificial intelligence model.

[0009] The step of determining whether a defect has occurred within the process equipment based on the above operating condition data may include determining that the defect has occurred if at least one of the lithium concentration and the impurity concentration in the base solution deviates from the standard concentration of normal operating conditions.

[0010] The above operating status data may include operating result data such as lithium concentration and impurity concentration in the produced base solution, current efficiency, production quality, and lithium production volume.

[0011] The step of deriving key process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model described above may include the step of inputting the process variables into an XgBoost model and calculating permutation importance.

[0012] The step of deriving major process variables requiring control due to the occurrence of the defect among process variables through importance determination using the artificial intelligence model described above further includes the step of selecting the top n variables with the highest importance based on the permutation importance and determining them as major process variables, wherein n can be pre-set as a natural number greater than or equal to 1.

[0013] The step of deriving key process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model may further include the step of calculating the relative influence between the key process variables based on the importance of each of the key process variables.

[0014] The step of deriving major process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model described above may further include the step of detecting the major process variable with the greatest influence as the final major process variable.

[0015] The method may further include a step of operating with existing process variables when the above defect does not occur, and operating with the derived major process variables when it is determined that the above defect has occurred.

[0016] The above defects may include physical defects of the ion exchange membrane.

[0017] In the event that a physical defect occurs in the above ion exchange membrane, the above major process variables may include both the first circulation pressure difference between the base stage and the salt stage and the second circulation pressure difference between the acid stage and the salt stage.

[0018] Among the embodiments, the operating condition-sensitive electrodialysis process operating device is an operating condition-sensitive electrodialysis process operating device that executes program code loaded into one or more memory devices through one or more processors to variably determine key process variables in response to defects within the electrodialysis facility, wherein the program code is executed to collect operating condition data including lithium concentration and impurity concentration in the produced base solution, determines whether a defect has occurred within the process facility based on the operating condition data, and when the defect occurs, derives key process variables among the process variables that require control due to the occurrence of the defect through an importance determination using an artificial intelligence model.

[0019] Determining whether a defect has occurred within the process equipment based on the above operating condition data may include determining that the defect has occurred when at least one of the lithium concentration and the impurity concentration in the base solution deviates from the standard concentration of normal operating conditions.

[0020] The above operating status data may include operating result data such as lithium concentration and impurity concentration in the produced base solution, current efficiency, production quality, and lithium production volume.

[0021] Deriving key process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model described above may include inputting the process variables into an XgBoost model and calculating permutation importance.

[0022] Deriving major process variables that require control due to the occurrence of the defect among the process variables through the importance determination using the artificial intelligence model described above further includes selecting the top n variables with the highest importance based on the permutation importance and determining them as major process variables, wherein n may be a natural number greater than or equal to 1 that is pre-set.

[0023] Deriving key process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model described above may further include calculating the relative influence between the key process variables based on the importance of each of the key process variables.

[0024] Deriving key process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model described above may further include detecting the key process variable with the greatest influence as the final key process variable.

[0025] It may further include operating with existing process variables when the above defect does not occur, and operating with the derived major process variables when it is determined that the above defect has occurred.

[0026] The above defects may include physical defects of the ion exchange membrane.

[0027] In the event that a physical defect occurs in the above ion exchange membrane, the above major process variables may include both the first circulation pressure difference between the base stage and the salt stage and the second circulation pressure difference between the acid stage and the salt stage.

[0028] An operating condition-sensitive electrodialysis process operation device and method according to one embodiment of the present invention can achieve high operating indicators (improved current efficiency, high product quality, and high Li production volume) by operating the process, identifying key process operation variables suitable for special situations (such as when a physical defect occurs in the BP membrane) when special situations occur, and operating the process while reflecting these variables.

[0029] FIG. 1 is a drawing showing the configuration of an electrodialysis facility according to one embodiment of the present invention.

[0030] FIG. 2 is a drawing showing one end of an electrodialysis facility according to one embodiment of the present invention.

[0031] FIG. 3 is a block diagram of an operating condition-sensitive electrodialysis process operation device according to one embodiment of the present invention.

[0032] FIGS. 4 and FIGS. 5 are flowcharts of an operation method for an operating condition-sensitive electrodialysis process according to an embodiment of the present invention.

[0033] FIG. 6 is a diagram illustrating a method for operating an electrodialysis process that is responsive to operating conditions according to an embodiment of the present invention.

[0034] FIG. 7 is a table for explaining the effects according to one embodiment of the present invention.

[0035] FIG. 8 is a drawing for explaining a computing device according to an embodiment of the present invention.

[0036] A method for operating an operation-condition-sensitive electrodialysis process may include the steps of collecting operation condition data including lithium concentration and impurity concentration in a produced base solution, determining whether a defect has occurred in the process equipment based on the operation condition data, and deriving key process variables that require control due to the occurrence of the defect among the process variables by determining the importance of the process variables through an artificial intelligence model.

[0037] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0038] Throughout the specification and claims, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another.

[0039] Terms such as "...part," "...unit," and "module" as used in the specification may refer to a unit capable of processing at least one function or operation described in this specification, and may be implemented as hardware or a circuit, software, or a combination of hardware or a circuit and software.

[0040] In addition, at least some components or functions of the operating condition-sensitive electrodialysis process operation device and method described below may be implemented as a program or software, and the program or software may be stored on a computer-readable medium.

[0041] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0042] 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.

[0043] In FIGS. 1 and 2, the electrodialysis equipment may be a Bipolar Electrodialysis (BPED) equipment. That is, the electrodialysis equipment may be a bipolar electrodialysis equipment. The electrodialysis equipment (BPED) may be a facility that converts an aqueous lithium sulfate 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 facility that simultaneously performs water splitting and ion separation using an electrodialysis membrane in an electric field.

[0044] Referring to FIGS. 1 and 2, the electrodialysis equipment (BPED) may include a cation exchange membrane (CEM), an anion exchange membrane (AEM), and a bipolar membrane (BPM).

[0045] Cation exchange membranes (CEMs) have internal anionic groups and can only allow cations (e.g., Li+) to pass through. Anion exchange membranes (AEMs) can only allow anions (e.g., SO42-) to pass through due to internal cation groups. Bipolar membranes (BPMs) consist of a cation membrane and an anionic membrane overlapping with a water splitting catalyst in between. Bipolar membranes (BPMs) can split water in an electric field to produce hydrogen ions (H+) and hydroxide ions (OH-).

[0046] That is, the electrodialysis facility (BPED) may be an aqueous solution treatment facility that simultaneously performs water splitting (decomposition into H+, OH-) and ion separation (Li+, SO42- ion separation) using an electrodialysis membrane (cation dialysis membrane, anion dialysis membrane, bipolar membrane) in an electric field.

[0047] In FIG. 1, in an electrodialysis (BPED) facility, 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 electrodialysis (BPED) facility, deionized water (DI Water) can be converted into the LH solution and sulfuric acid solution by coming into counter-flow contact with the LS solution. Here, the LS solution is lithium sulfate (Li2SO4), and the LH solution is lithium hydroxide (LiOH).

[0048] 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.

[0049] In each stage, the Salt room can supply lithium sulfate (Li2SO4) to produce desalted water after the reaction. The Acid room can supply deionized water (DI Water) to produce sulfuric acid (H2SO4) after the reaction. The Base room can supply deionized water (DI Water) to produce lithium hydroxide (LiOH) after the reaction.

[0050] The salt tank stores the produced demineralized water. The acid tank stores the produced sulfuric acid. The base tank stores the produced lithium hydroxide.

[0051] The production volume of the electrodialysis equipment (BPED) is determined by the discharge flow rates of sulfuric acid and lithium hydroxide. The production volume can be determined by the control of the input flow rate of water (H2O) and lithium sulfate in the electrodialysis equipment (BPED), the current and voltage of the rectifier, and the management of pH, conductivity, circulation flow rate, and circulation pressure within each room.

[0052] The fluid in each stage and each region (room) is circulated through the stack, and the amount is called the circulation flow rate. Additionally, the pressure applied to each room when the fluid is circulated is called the circulation pressure.

[0053] The input flow rate of the solution, rectifier current, voltage, pH, conductivity, circulation flow rate, and circulation pressure corresponding to the control and management elements can be detected through internal sensors installed in each room. The control and management elements may correspond to variables (process variables) that determine the concentration of lithium hydroxide and sulfuric acid produced.

[0054] FIG. 3 is a block diagram of an operating condition-sensitive electrodialysis process operation device according to one embodiment of the present invention.

[0055] An operating condition-sensitive electrodialysis process operating device (100) according to one embodiment can execute program code or instructions loaded into one or more memory devices through one or more processors.

[0056] For example, the operating condition-sensitive electrodialysis process operating device (100) may be implemented as a computing device (900) as described below in relation to FIG. 7. In this case, one or more processors may correspond to the processor (910) of the computing device (900), and one or more memory devices may correspond to the memory (930) of the computing device (900).

[0057] Program code or instructions are executed by one or more processors and can variably determine key process variables in response to defects within the electrodialysis facility. In this specification, the term "module" is used to logically distinguish these functions performed by the program code or instructions.

[0058] When the electrodialysis equipment (BPED) operates normally, the operation is carried out primarily by controlling the circulation flow rate of each stage and the flow rate of the raw material solution (input flow rate).

[0059] However, if physical defects occur in the BP membrane or ion exchange membrane while operating, operating with the conventional method may result in poor operation with low current efficiency, low product quality, and low Li production.

[0060] The operating condition-sensitive electrodialysis process operating device (100) analyzes key process variables under defective conditions to overcome this, and outputs a relatively appropriate operating result by reflecting the key process variables.

[0061] Referring to FIG. 3, the operation condition-sensitive electrodialysis process operation device (100) may include a data collection module (110), a defect determination module (120), a key process variable derivation module (130), and a process operation control module (140).

[0062] The data collection module (110) can collect operation status data including lithium concentration and impurity concentration in the produced base solution.

[0063] Here, impurities can refer to sulfur (S).

[0064] Operation status data may include operation result data such as lithium concentration and impurity concentration (sulfur(S) concentration) in the produced base solution, current efficiency, production quality, and lithium production volume.

[0065] The defect determination module (120) can determine whether a defect has occurred in the process equipment based on operation status data.

[0066] For example, the defect determination module (120) can determine that a defect has occurred if at least one of the lithium concentration and the impurity concentration in the base solution deviates from the reference concentration of normal operating conditions.

[0067] The main process variable derivation module (130) can derive the main process variable that requires control due to the occurrence of a defect among the process variables by determining importance through an artificial intelligence model when a defect occurs.

[0068] The main process variable derivation module (130) inputs process variables into the XgBoost model and can calculate the permutation importance of the process variables.

[0069] The main process variable derivation module (130) predicts the lithium concentration of the Base product and the sulfur concentration of the Base product according to the process variable through an artificial intelligence model (XGBOOST).

[0070] The main process variable derivation module (130) can calculate the main process variables based on Permutation Importance through the prediction results.

[0071] The main process variable derivation module (130) can determine the main process variables by selecting the top n variables with the highest importance based on permutation importance. The above n can be pre-set as a natural number greater than or equal to 1.

[0072] The main process variable derivation module (130) can calculate the relative influence between the main process variables based on the importance of each of the main process variables.

[0073] Relative influence can be calculated in proportion to importance.

[0074] For example, the main process variable derivation module (130) can detect the main process variable with the greatest influence as the final main process variable.

[0075] The main process variable derivation module (130) can finally detect multiple main process variables.

[0076] The process operation control module (140) can operate with existing process variables when no defect occurs, and can operate with derived key process variables when it is determined that a defect has occurred.

[0077] FIGS. 4 and FIGS. 5 are flowcharts of an operation method for an operating condition-sensitive electrodialysis process according to an embodiment of the present invention.

[0078] FIG. 4 is a flowchart for explaining a method of operating an electrodialysis process that responds to operating conditions, and FIG. 5 is a flowchart for explaining the sub-steps of step S430 of FIG. 4.

[0079] The operation condition-sensitive electrodialysis process operation method of FIGS. 4 and 5 can be performed through the operation condition-sensitive electrodialysis process operation device (100) of FIG. 3.

[0080] In FIG. 4, the operation condition-sensitive electrodialysis process operation device (100) can collect operation condition data including lithium concentration and impurity concentration in the produced base solution (step S410).

[0081] Operation status data may include operation result data such as lithium concentration and impurity concentration in the produced base solution, current efficiency, production quality, and lithium production volume.

[0082] The operation condition-sensitive electrodialysis process operation device (100) can determine whether a defect has occurred in the process equipment based on operation condition data (step S420).

[0083] The operating condition-sensitive electrodialysis process operating device (100) can determine that a defect has occurred if at least one of the lithium concentration and impurity concentration in the base solution deviates from the standard concentration of normal operating conditions.

[0084] The operating condition-sensitive electrodialysis process operation device (100) can derive key process variables that require control due to the occurrence of defects among process variables through an artificial intelligence model of importance (step S430).

[0085] The operation situation-sensitive electrodialysis process operation device (100) can input process variables into an artificial intelligence model and calculate the importance of each process variable.

[0086] For example, an operating condition-sensitive electrodialysis process operation device (100) can input process variables into an XGBOOST model and calculate permutation importance for each process variable.

[0087] The operation condition-sensitive electrodialysis process operation device (100) can determine the top n variables with the highest importance among the process variables based on permutation importance as major process variables. Here, n can be pre-set as a natural number greater than or equal to 1.

[0088] That is, the operating condition-sensitive electrodialysis process operation device (100) predicts the lithium concentration of the Base product and the sulfur concentration of the Base product according to process variables through an artificial intelligence model (XGBOOST).

[0089] The operating condition-sensitive electrodialysis process operation device (100) can calculate major process variables based on Permutation Importance through the prediction results.

[0090] The operating condition-sensitive electrodialysis process operation device (100) can calculate the relative influence between major process variables based on the importance of each major process variable. Here, the influence can be determined in proportion to the importance of the major process variables.

[0091] The operation condition-sensitive electrodialysis process operation device (100) can detect the major process variable with the greatest influence as the final major process variable.

[0092] The operation condition-sensitive electrodialysis process operation device (100) can operate with existing process variables when no defect occurs, and can operate with derived major process variables when it is determined that a defect has occurred (step S440).

[0093] For example, the operating condition-sensitive electrodialysis process operating device (100) can determine the first circulation pressure difference between the base stage and the salt stage and the second circulation pressure difference between the acid stage and the salt stage as major process variables when a physical defect occurs in the ion exchange membrane.

[0094] In FIG. 5, the operation condition-sensitive electrodialysis process operation device (100) can input process variables into a tree model (XGBOOST) of a boosting series (step S431).

[0095] The operating condition-sensitive electrodialysis process operation device (100) can determine the importance of each process variable as Permutation importance (step S432).

[0096] The operation status-sensitive electrodialysis process operation device (100) can select the top 5 after removing lower-level factors of importance (step S433).

[0097] The operation status-sensitive electrodialysis process operation device (100) can calculate the relative influence based on the sum of the top 5 criteria importance (step S434).

[0098] That is, the operating condition-sensitive electrodialysis process operation device (100) can input process variables into the XGBOOST model as independent variables and calculate permutation importance to select the top 5 process variables based on importance criteria.

[0099] The operation situation-sensitive electrodialysis process operation device (100) can extract an influence based on the ratio of the top 5 variables and determine major process variables based on the influence.

[0100] For example, the operating condition-sensitive electrodialysis process operating device (100) can determine major process variables based on variables related to the input raw material under normal conditions. For example, under normal conditions, the major process variables may be the circulation flow rate of each stage and the input flow rate of the raw material solution.

[0101] When a physical defect occurs in the ion exchange membrane due to causes such as deterioration from long-term operation or physical shock from replacement work, the operating condition-sensitive electrodialysis process operating device (100) can determine the main process variable as a circulating pressure difference.

[0102] FIG. 6 is a diagram illustrating a method for operating an electrodialysis process that is responsive to operating conditions according to an embodiment of the present invention.

[0103] Figure 6 shows the deterioration state of the ion exchange membrane. Figure 6 is a diagram illustrating an electrodialysis process operation method for determining and controlling the circulating pressure difference as a major process variable in a situation where the ion exchange membrane is defective.

[0104] In Fig. 6, the main process variable may be the circulation pressure (pressure in the Acid, Salt, and Base rooms), that is, the circulation pressure difference determined by the pressure generated through the circulation flow rate in each zone (Acid, Salt, and Base).

[0105] The circulation pressure difference may be the difference between the circulation pressures of each room.

[0106] For example, deltaP_AS could be the difference between the Acid room circulation pressure and the Salt room circulation pressure. deltaP_SB could be the difference between the Salt room circulation pressure and the Base room circulation pressure.

[0107] The operating condition-sensitive electrodialysis process operation device (100) can perform process operation specialized for defects by controlling the circulating pressure difference derived as a major process variable as a result of determining importance through permutation importance in an electrodialysis facility including a first defect (10) that occurred in membrane A and a second defect (20) that occurred in membrane C.

[0108] For example, the operating condition-sensitive electrodialysis process operating device (100) can increase the circulation pressure of the base room and maintain it relatively higher than the circulation pressure of the salt room, thereby preventing a decrease in process result indicators due to physical defects created in the C film.

[0109] At the same time, the operating condition-sensitive electrodialysis process operating device (100) can increase the circulation pressure of the acid room and maintain it relatively higher than the circulation pressure of the salt room, thereby preventing a decrease in the process result indicator due to physical defects created in membrane A.

[0110] FIG. 7 is a table for explaining the effects according to one embodiment of the present invention.

[0111] In FIG. 7, the first test is a case where the process is operated with normal condition process variables under normal operating conditions, the second test is a case where the process is operated with normal condition process variables under special conditions where a defect occurs in the ion exchange membrane, and the third test is a case where the process is operated with major process variables derived according to one embodiment of the present invention under special conditions where a defect occurs in the ion exchange membrane.

[0112] Table 1 is a table showing the process variables, importance, and portion of the first test.

[0113] Control Item Major Process Variable Rank Item 1 2 3 4 5 Base Product Lithium Concentration Process Variable Stock Solution Lithium Concentration Stage 3 Acid Input Flow Rate Stage 2 Electrode Solution-Circulation Flow Rate Stage 1 Base Circulation Flow Rate Stage 2 BASE Circulation Flow Rate Importance 0.5 26 80.10 640.10 460.10 250.0 62 2 Portion (%) 58 1 2 1 2 1 1 7 Base Product Impurity (S) Concentration Process Variable Stage 1 Rectifier Voltage Stage 1 Electrode Solution+ Circulation Flow Rate Stage 2 Rectifier Voltage Stage 3 AS delta P Stage 3 Rectifier Voltage Importance 0.6 80 20.2 84 20.0 52 70.0 42 40.0 1 2 Portion (%) 63 27 5 4 1

[0114] AS delta P is the difference between the circulation pressure of the acid room and the circulation pressure of the salt room. Table 2 is a table showing the process variables, importance, and portion of the second test.

[0115] Control Item Major Process Variable Rank Item 1 2 3 4 5 Base Product Lithium Concentration Process Variable Stock Solution Lithium Concentration 2-Stage Electrode Solution + Circulation Flow Rate 2-Stage BASE Circulation Flow Rate 2-Stage Electrode Solution - Circulation Flow Rate 3-Stage Rectifier Voltage Importance 1.0 2 3 4 0.1 3 2 0.0 8 2 8 0.0 6 4 5 0.0 6 1 6 Portion (%) 7 5 10 6 5 5 Base Product Impurity (S) Concentration Process Variable 3-Stage Rectifier Voltage 3-Stage Electrode Solution + Circulation Flow Rate 2-Stage Salt Circulation Flow Rate 1-Stage Electrode Solution - Circulation Flow Rate 1-Stage AS delta Importance 0.3 8 9 3 0.0 9 5 0.0 5 1 1 0.0 3 9 6 0.0 3 5 1 Portion (%) 6 4 1 6 8 6 6

[0116] Table 3 shows the process variables, importance, and portion of the third test. In Table 3, it can be seen that the major process variables related to circulation pressure are listed in order of importance.

[0117] Control Item Major Process Variable Rank Item 1 2 3 4 5 Base Lithium Concentration of Product Process Variable 1st Stage AS delta P 3rd Stage Electrode Solution - Circulation Flow Rate 1st Stage SB delta P 3rd Stage Base Input Flow Rate 3rd Stage Electrode Solution + Circulation Flow Rate Importance 0.1 49 5 0.0 8 8 5 0.0 7 1 9 0.0 6 0 8 0.0 5 3 1 Portion (%) 3 5 2 1 1 7 1 4 1 3 Base Product Impurity (S) Concentration Process Variable 3rd Stage AS delta P 1st Stage Electrode Solution - Circulation Flow Rate 2nd Stage Electrode Solution + Circulation Flow Rate 1st Stage Rectifier Voltage 3rd Stage Acid Input Flow Rate Importance 0.9 1 3 4 0.0 46 0.0 46 3 0.0 45 5 0.0 2 1 6 Portion (%) 8 5 4 4 2

[0118] In FIG. 7, referring to Tables 1 to 3, it can be seen that the best operating indicators are obtained in the third case, where the circulating pressure difference control (AS delta P) as a major process variable when a defect occurs is controlled not only for the purity of the Base product but also for impurities in the Base product. (In other words, if it is not reflected in the control of the purity of the Base product, the same result as the second case is obtained.) FIG. 8 is a drawing for explaining a computing device according to an embodiment of the present invention.

[0119] Referring to FIG. 8, the operating condition-sensitive electrodialysis process operation device and method according to the embodiments can be implemented using a computing device (900).

[0120] The computing device (900) may include at least one of a processor (910), memory (930), user interface input device (940), user interface output device (950), and storage device (560) that communicate via a bus (920). The computing device (900) may also include a network interface (970) that is electrically connected to a network (90). The network interface (970) may transmit or receive signals to or from other entities via the network (90).

[0121] The processor (910) can be implemented in various types such as an MCU (Micro Controller Unit), AP (Application Processor), CPU (Central Processing Unit), GPU (Graphic Processing Unit), NPU (Neural Processing Unit), etc., and may be any semiconductor device that executes instructions stored in memory (930) or storage device (960). The processor (910) may be configured to implement the functions and methods described above in relation to FIGS. 1 to 7.

[0122] The memory (930) and storage device (960) may include various forms of volatile or non-volatile storage media. For example, the memory may include ROM (read-only memory) (931) and RAM (random access memory) (932). In this embodiment, the memory (930) may be located inside or outside the processor (910), and the memory (930) may be connected to the processor (910) through various known means.

[0123] In some embodiments, at least some components or functions of the operating condition-sensitive electrodialysis process operation device and method according to the embodiments may be implemented as a program or software executed on a computing device (900), and the program or software may be stored on a computer-readable medium.

[0124] In some embodiments, at least some components or functions of the operating condition-sensitive electrodialysis process operation device and method according to the embodiments may be implemented using hardware or circuits of the computing device (900), or may be implemented using separate hardware or circuits that can be electrically connected to the computing device (900).

[0125] Although 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 by those skilled in the art to which the present invention belongs, utilizing the basic concept of the present invention as defined in the following claims, also fall within the scope of the present invention.

[0126] The operating condition-sensitive electrodialysis process operation device and method according to one embodiment of the present invention has industrial applicability by identifying customized key process operation variables when special situations occur during operation and reflecting them to achieve high operating indicators (improved current efficiency, high product quality, and high Li production volume).

Claims

1. A step of collecting operational status data including lithium concentration and impurity concentration in the produced base solution; A step of determining whether a defect has occurred within the process equipment based on the above-mentioned operation status data; and A method for operating an operation-condition-sensitive electrodialysis process, comprising the step of deriving key process variables requiring control due to the occurrence of defects among process variables through an artificial intelligence model for determining the importance of process variables.

2. In Paragraph 1, The step of determining whether a defect has occurred within the process equipment based on the above-mentioned operating status data is: A step comprising determining that the defect has occurred when at least one of the lithium concentration and the impurity concentration in the base solution deviates from the reference concentration of normal operating conditions. Operation method for an electrodialysis process that responds to operating conditions.

3. In Paragraph 1, The above operating status data includes operating result data such as lithium concentration and impurity concentration in the produced base solution, and current efficiency, production quality, and lithium production volume. Operation method for an electrodialysis process that responds to operating conditions.

4. In Paragraph 1, The step of deriving key process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model above is, The above process variables include the step of inputting them into an XgBoost model and calculating permutation importance, Operation method for an electrodialysis process that responds to operating conditions.

5. In Paragraph 4, The step of deriving key process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model above is, It further includes a step of selecting the top n variables with the highest importance based on the above permutation importance and determining them as major process variables, and The above n is a natural number greater than or equal to 1 that is pre-set, Operation method for an electrodialysis process that responds to operating conditions.

6. In Paragraph 5, The step of deriving key process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model above is, A method further comprising the step of calculating the relative influence between the major process variables based on the importance of each of the major process variables. Operation method for an electrodialysis process that responds to operating conditions.

7. In Paragraph 6, The step of deriving key process variables requiring control due to the occurrence of the defect among the process variables through importance determination using the artificial intelligence model above is, A step further comprising detecting the major process variable with the greatest influence as the final major process variable, Operation method for an electrodialysis process that responds to operating conditions.

8. In Paragraph 1, A method further comprising the step of operating with existing process variables when the above defect does not occur, and operating with the derived key process variables when it is determined that the above defect has occurred. Operation method for an electrodialysis process that responds to operating conditions.

9. In Paragraph 1, The above defect includes physical defects of the ion exchange membrane. Operation method for an electrodialysis process that responds to operating conditions.

10. In Paragraph 9, In the event that a physical defect occurs in the above ion exchange membrane, The above major process variable includes at least one of a first circulation pressure difference between the base stage and the salt stage or a second circulation pressure difference between the acid stage and the salt stage, Operation method for an electrodialysis process that responds to operating conditions.

11. An operation condition-sensitive electrodialysis process operating device that executes program code loaded into one or more memory devices through one or more processors to variably determine key process variables in response to defects within the electrodialysis facility, The above program code is executed, Collecting operational status data including lithium concentration and impurity concentration in the produced base solution, and Based on the above operating status data, determine whether a defect has occurred within the process equipment, and An operation condition-sensitive electrodialysis process operation device that, upon the occurrence of the above defect, derives key process variables requiring control among process variables through importance determination using an artificial intelligence model.

12. In Paragraph 11, Determining whether a defect has occurred within the process equipment based on the above-mentioned operational status data is, Determining that the defect has occurred when at least one of the lithium concentration and the impurity concentration in the base solution deviates from the reference concentration of normal operating conditions, Operation status-sensitive electrodialysis process operation device.

13. In Paragraph 11, The above operating status data includes operating result data such as lithium concentration and impurity concentration in the produced base solution, and current efficiency, production quality, and lithium production volume. Operation status-sensitive electrodialysis process operation device.

14. In Paragraph 11, Deriving key process variables among the process variables that require control due to the occurrence of the aforementioned defect through importance determination using the aforementioned artificial intelligence model is, Inputting the above process variables into the XgBoost model and calculating permutation importance, Operation status-sensitive electrodialysis process operation device.

15. In Paragraph 14, Deriving key process variables among the process variables that require control due to the occurrence of the aforementioned defect through importance determination using the aforementioned artificial intelligence model is, It further includes selecting the top n variables with the highest importance based on the above permutation importance and determining them as major process variables, wherein n is a natural number greater than or equal to 1 that is pre-set. Operation status-sensitive electrodialysis process operation device.

16. In Paragraph 15, Deriving key process variables among the process variables that require control due to the occurrence of the aforementioned defect through importance determination using the aforementioned artificial intelligence model is, Further comprising calculating the relative influence between the major process variables based on the importance of each of the major process variables. Operation status-sensitive electrodialysis process operation device.

17. In Paragraph 16, Deriving key process variables among the process variables that require control due to the occurrence of the aforementioned defect through importance determination using the aforementioned artificial intelligence model is, Further including detecting the major process variable with the greatest influence as the final major process variable, Operation status-sensitive electrodialysis process operation device.

18. In Paragraph 11, A method further comprising operating with existing process variables when the above defect does not occur, and operating with the above-derived key process variables when it is determined that the above defect has occurred. Operation status-sensitive electrodialysis process operation device.

19. In Paragraph 11, The above defect includes physical defects of the ion exchange membrane. Operation status-sensitive electrodialysis process operation device.

20. In Paragraph 19, In the event that a physical defect occurs in the above ion exchange membrane, The above major process variable includes at least one of a first circulation pressure difference between the base stage and the salt stage or a second circulation pressure difference between the acid stage and the salt stage, Operation status-sensitive electrodialysis process operation device.

Images