System and method for manufacturing battery electrode plate

Abstract

The present disclosure relates to systems and methods for manufacturing battery electrode plates. The system includes a computing device configured to receive, from a client device, a target process factor of a plurality of process factors associated with manufacturing a battery electrode plate, predict, via a machine learning model, a change in a characteristic of the battery electrode plate based on a change in a design value of the target process factor, information for selecting a target process factor is generated based on the predicted change in the characteristics of the battery electrode plate, and the information is sent to a client device for manufacturing the battery electrode plate.

Description

Technical Field

[0001] The present disclosure relates to systems and methods for manufacturing battery electrode plates. Background Art

[0002] Typically, unlike primary batteries that are not designed to be recharged, secondary batteries are designed to discharge and recharge. Low-capacity secondary batteries are used in portable, small electronic devices such as smartphones, feature phones, notebook computers, digital cameras, camcorders, etc. High-capacity secondary batteries are used as power supplies and / or storage devices for driving motors in hybrid vehicles and electric vehicles, for example. Generally speaking, a secondary battery comprises an electrode assembly having a positive electrode and a negative electrode, a housing for accommodating the electrode assembly, and electrode terminals connected to the electrode assembly.

[0003] The positive electrode of a secondary battery is manufactured by coating a positive electrode active material onto a positive electrode current collector in the form of a metal film or metal mesh. The negative electrode of a secondary battery is manufactured by coating a negative electrode active material onto a negative electrode current collector in the form of a metal film or metal mesh. Secondary batteries are charged and discharged by repeatedly inserting and removing ions in the positive electrode active material layer of the positive electrode plate and the negative electrode active material layer of the negative electrode plate.

[0004] The ionic resistance characteristics of the electrode plates of secondary batteries can vary depending on the components configuring the electrode plates and the structural characteristics of the electrode plates. The curvature of the electrode plates can vary depending on the shape, distribution, and content of each particle in the particles configuring the active material layer. The curvature of the electrode plates can affect the migration path and migration length of ions and serve as a factor in determining the ionic resistance characteristics of the electrode plates.

[0005] The above information disclosed in this Background section is for enhancement of understanding of the background of the described technology and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] Embodiments of the present disclosure provide a system and method for manufacturing a battery electrode plate based on pre-predicting electrode plate characteristics according to design values of process factors during an electrode plate design process for a secondary battery.

[0007] The technical solutions that can be obtained from the present disclosure are not limited to the above-mentioned technical solutions. A person skilled in the art of the present disclosure can clearly understand other technical solutions not explicitly mentioned herein from the following description.

[0008] A system includes a computing device configured to receive a target process factor from a plurality of process factors associated with manufacturing a battery electrode plate from a client device, predict a change in a characteristic of the battery electrode plate based on a change in a design value of the target process factor via a machine learning model, generate information for selecting the target process factor based on the predicted change in the characteristic of the battery electrode plate, and send the information to the client device for use in manufacturing the battery electrode plate.

[0009] The machine learning model may be configured to output characteristic information of a battery electrode plate based on input design values corresponding to a plurality of process factors.

[0010] The computing device may also be configured to obtain a curvature of the battery electrode plate based on a machine learning model, and calculate the ionic resistance based on the curvature.

[0011] The computing device may also be configured to automatically set input design values corresponding to a plurality of process factors other than the target process factor to design values used in previous predictions of the machine learning model.

[0012] The computing device may be further configured to receive, from the client device, input design values corresponding to a plurality of process factors other than the target process factor.

[0013] The computing device may be further configured to receive design range information including a design value change range and a change interval of the target process factor from the client device, and increase or decrease the design value of the target process factor based on the design range information.

[0014] Based on determining that the multiple process factors include scores of multiple active substances and the target process factor is the score of at least one active substance among the multiple active substances, the computing device can also be configured to automatically adjust the scores of the multiple active substances in response to the design value of the target process factor being changed so that the sum of the scores of the multiple active substances is equal to 100.

[0015] The computing device may be further configured to select characteristic values of the battery electrode plate that meet conditions based on the predicted changes in the characteristics of the battery electrode plate, and generate information to include the selected characteristic values and design values of target process factors used to derive the characteristic values.

[0016] The computing device can also be configured to receive a target characteristic value from a client device, select at least one second characteristic value based on a predicted change in a characteristic of the battery electrode plate, the selection being based on the second characteristic value having a difference from the target characteristic value that satisfies a standard, and generate information to include the selected at least one second characteristic value and a design value of a target process factor for deriving the at least one second characteristic value.

[0017] The characteristic information may include an ionic resistance of the battery electrode plate. The computing device may be further configured to select at least one ionic resistance from a plurality of ionic resistances obtained based on the predicted change in the characteristic of the battery electrode plate, wherein the at least one ionic resistance has a minimum difference from a target ionic resistance received from the client device, and generate information including the at least one selected ionic resistance and a design value of a target process factor used to derive the at least one selected ionic resistance.

[0018] A system according to one embodiment includes a computing device configured to receive first information for manufacturing a battery electrode plate from a client device, predict characteristic information of the battery electrode plate using the first information and a prediction model based on machine learning, and send the characteristic information to the client device for use in manufacturing the battery electrode plate.

[0019] The characteristic information may include curvature and ionic resistance of the battery electrode plate. The computing device may also be configured to input the first information into a prediction model to obtain the curvature of the battery electrode plate, and calculate the ionic resistance based on the curvature.

[0020] The first information may include design values of multiple process factors for manufacturing the battery electrode plate, including the type of active material, the fraction and physical properties of the active material, the binder content, the conductive material content, the loading level, and the mixture density or process conditions.

[0021] The computing device may also be configured to construct a prediction model. The computing device may also be configured to perform a design of experiments (DOE) based on experimental data of a manufacturing process for a battery electrode plate, generate a process design table containing design values of process factors for a plurality of different process design conditions through the DOE, obtain curvature data of the battery electrode plate by performing a simulation based on the process design table using a discrete element method, and construct a prediction model using the process design table and the curvature data as learning data.

[0022] The computing device may be further configured to add the thickness data to the process design table using a linear regression model learned using actual process design data of the battery electrode plate and actual measured values of the thickness of the battery electrode plate.

[0023] A method includes receiving first information for manufacturing a battery electrode plate from a client device, using the first information and a machine learning-based prediction model to predict a curvature of the battery electrode plate, calculating an ionic resistance of the battery electrode plate based on the curvature, and sending feature information including at least one of the curvature or the ionic resistance of the battery electrode plate to the client device for use in manufacturing the battery electrode plate.

[0024] The first information may include design values of a plurality of process factors for manufacturing the battery electrode plate. The plurality of process factors may include at least one of the type of active material, the fraction and physical properties of the active material, the binder content, the conductive material content, the loading level, and the mixture density or the process conditions.

[0025] The method may also include constructing a predictive model.

[0026] Constructing a prediction model may include performing DOE based on experimental data of a manufacturing process of a battery electrode plate to generate a process design table containing design values of process factors for a plurality of different process design conditions, performing simulation based on the process design table using a discrete element method to obtain curvature data of the battery electrode plate, and constructing a prediction model using the process design table and the curvature data as learning data.

[0027] The method may also include receiving selection information for selecting a target process factor from a plurality of process factors from a client device, predicting a change in a characteristic of a battery electrode plate based on a change in a design value of the target process factor via a prediction model, generating information for designing the target process factor based on the predicted change in the characteristic of the battery electrode plate, and sending the first information to the client device for use in manufacturing the battery electrode plate.

[0028] Generating the first information may further include selecting characteristic values of the battery electrode plate that meet conditions based on predicted changes in the characteristics of the battery electrode plate, and generating information to include the selected characteristic values and design values of target process factors used to derive the characteristic values.

[0029] According to the present disclosure, in designing an electrode plate of a secondary battery, electrode plate characteristics according to design values of process factors and design values of process factors for obtaining desired electrode plate characteristics can be predicted in advance.

[0030] Therefore, the time required to derive optimal design conditions for obtaining desired electrode plate characteristics can be shortened, thereby reducing the cost and time required for the electrode plate manufacturing process of the secondary battery.

[0031] The effects that can be obtained from the present disclosure are not limited to the above-mentioned effects. In addition, other effects not described herein will become apparent to those skilled in the art from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings illustrate embodiments of the present disclosure and, together with the foregoing disclosure, are used to describe aspects, features, and technical spirit of the present disclosure. However, the present disclosure should not be construed as being limited to the accompanying drawings.

[0033] Figure 1 is a block diagram of a system for designing a manufacturing process for a battery electrode plate according to an embodiment of the present disclosure.

[0034] Figure 2 3D images of structural features of a negative electrode plate generated based on a discrete element method according to an embodiment of the present disclosure.

[0035] Figures 3A to 3D is a block diagram of an example user interface provided by a system for designing a manufacturing process for a battery electrode plate according to an embodiment of the present disclosure.

[0036] Figure 4 is a flowchart of a process for constructing a prediction model for predicting curvature of a battery electrode plate according to an embodiment of the present disclosure.

[0037] Figure 5 The present invention is a flowchart of a method for providing characteristic information of a battery electrode plate predicted according to process design conditions according to an embodiment of the present disclosure.

[0038] Figure 6 is a flow chart of a process for designing process factors for a manufacturing process for a battery electrode plate according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. The terms or words used in the specification and claims of the present disclosure should not be interpreted as limited to the typical or dictionary meanings, but should be interpreted in the best way based on the concept that the inventor can be his own lexicon compiler to appropriately define the terms to be interpreted as the meaning and concept that conforms to the technical spirit of the present disclosure. Therefore, it should be understood that the terms and words used in conjunction with the accompanying drawings should not be interpreted as limited to the typical or dictionary meanings. Figure 1 The detailed description disclosed herein is intended to describe embodiments of the present invention, but is not intended to represent all technical concepts, aspects, and features of the present invention. Therefore, it should be understood that various equivalents and modifications may exist that may replace the embodiments described when this application is filed.

[0040] As used herein, the terms "use," "using," and "used" may be considered synonymous with the terms "utilize," "utilizing," and "utilized," respectively. As used herein, the terms "substantially," "about," and similar terms are used as terms of approximation rather than terms of degree, and are intended to account for the inherent variations in measured or calculated values that one of ordinary skill in the art would recognize.

[0041] It will be understood that although the terms first, second, third, etc. may be used herein to describe various elements, components, regions, layers, and / or parts, these elements, components, regions, layers, and / or parts should not be limited by these terms. These terms are used to distinguish one element, component, region, layer, or part from another element, component, region, layer, or part. Therefore, without departing from the teachings of the exemplary embodiments, the first element, component, region, layer, or part discussed below may be referred to as a second element, component, region, layer, or part.

[0042] For ease of description, spatially relative terms such as "below," "beneath," "lower," "above," "upper," etc. may be used herein to describe the relationship of one element or feature to another element or feature as shown in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is flipped, an element described as being "below" or "below" other elements or features will be oriented as being "above" or "above" the other elements or features. Thus, the term "below" can encompass both above and below orientations. The device can be oriented in other ways (rotated 90 degrees or in other orientations), and the spatially relative descriptors used herein should be interpreted accordingly.

[0043] The terms used herein are for the purpose of describing the embodiments of the present disclosure and are not intended to limit the present disclosure. As used herein, the singular forms "a" and "an" are intended to also include the plural forms, unless the context clearly indicates otherwise. It will be further understood that when used in this specification, the terms "includes," "including," "comprises," and / or "comprising" specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0044] In addition, any numerical range disclosed and / or listed herein is intended to include all subranges of the same numerical precision that are included in the listed range. For example, the range of "1.0 to 10.0" is intended to include all subranges between the listed minimum value 1.0 and the listed maximum value 10.0 (and including endpoints), that is, with a minimum value equal to or greater than 1.0 and a maximum value equal to or less than 10.0, such as, for example, 2.4 to 7.6. Any maximum numerical value limit listed herein is intended to include all lower numerical limits included therein, and any minimum numerical value limit listed in this specification is intended to include all higher numerical limits included therein. Therefore, the applicant reserves the right to amend this specification (including claims) to explicitly list any subranges included in the range explicitly listed herein. All such ranges are intended to be inherently described in this specification so that modifications to explicitly list any such subranges will meet the requirements.

[0045] The embodiments of the present disclosure are described below with reference to block diagrams and flow charts. Therefore, it should be understood that each frame of block diagrams and flow charts can be realized in the form of a computer program product, a complete hardware embodiment, a combination of hardware and computer program product and / or execution on a computer-readable storage medium for instructions, operations, steps and similar words (for example, executable instructions, instructions for execution, program code, etc.) for execution, system, computing device, computing entity, etc. For example, the retrieval, loading and execution of code can be performed sequentially so that an instruction is retrieved, loaded and executed once. In some example embodiments, retrieval, loading and / or execution can be performed in parallel so that multiple instructions are retrieved, loaded and / or executed together. Therefore, such an embodiment can produce a specially configured machine for executing the steps or operations specified in the block diagrams and flow charts. Therefore, block diagrams and flow charts support various combinations of embodiments for executing specified instructions, operations or steps.

[0046] Furthermore, the features of the embodiments of the present disclosure may be partially or completely combined or combined with one or more other features and may be operated in various ways, and the embodiments may be implemented independently of or in combination with one or more other embodiments.

[0047] Furthermore, to facilitate understanding of the present disclosure, the drawings are not drawn to scale, and the dimensions of some components, layers, etc. may be exaggerated. Furthermore, the same reference numerals may be assigned to the same components.

[0048] Stating that two compared objects are "the same" means that they are "substantially the same." Thus, the phrase "substantially the same" can encompass deviations that are considered low in the art, e.g., less than 5%. In some embodiments, uniformity of a parameter in a region can refer to uniformity in terms of average value.

[0049] Throughout the specification, unless otherwise stated, each component may be singular or plural.

[0050] It will also be understood that when a first element or layer is referred to as being present (or located or positioned) “on” or “under” a second element or layer, the first element or layer can be directly disposed (or located or positioned) on or under the second element or layer, or can be indirectly disposed (or located or positioned) on or under the second element or layer, with a third element or layer disposed (or located or positioned) between the first element or layer and the second element or layer.

[0051] It should be noted that if the specification describes a component as being “connected,” “coupled,” or “engaged” to another component, a third component may be “connected,” “coupled,” or “engaged” between the first and second components, or the first component may be directly connected, coupled, or engaged to the second component. When an element is described as being “electrically coupled” to another element, the element may be “directly coupled” to the other element or “coupled” to the other element through a third element.

[0052] Throughout this specification, reference to "A and / or B" means A, B, or A and B, unless otherwise specified. That is, "and / or" includes all or any combination of multiple listed items. Reference to "C to D" means greater than or equal to C and less than or equal to D, unless otherwise specified.

[0053] Figure 1 FIG2 is a block diagram of a system 1 for designing a manufacturing process of a battery electrode plate according to an embodiment of the present disclosure. In one embodiment, the battery electrode plate may include a negative electrode plate or a positive electrode plate of a secondary battery.

[0054] refer to Figure 1 The system 1 for designing a manufacturing process of a battery electrode plate according to an embodiment may include a model building device 10, a design support device 20, and a user terminal (also referred to as a client device) 30. The model building device 10 and the design support device 20 may each be referred to as a computing device.

[0055] The model building device 10 can build a machine learning-based model (hereinafter referred to as a "prediction model" or machine learning model) that predicts electrode plate characteristics (such as tortuosity and ionic resistance) based on the design conditions of the manufacturing process of the battery electrode plate.

[0056] The model building device 10 may comprise a communication device 11, a storage device 12 and a control device 13. The storage device 12 may take the form of a volatile memory, a non-volatile memory, a persistent memory, a flash memory, a hard drive and / or the like.

[0057] The communication device 11 can perform a communication function between the model construction device 10 and an external device (for example, the design support device 20 ).

[0058] The storage device 12 can store various data and information processed by the model building device 10. For example, the storage device 12 can store a process design table generated by the control device 13, which will be described later. In some embodiments, the storage device 12 can store a prediction model built by the control device 13.

[0059] The storage device 12 may also store programs or computer instructions for operating the control device 13 .

[0060] The control device 13 may control the overall operation of the model building device 10. The control device 13 may build a prediction model to predict the structural characteristics (eg, curvature) of the battery electrode plate.

[0061] The control device 13 may include a data generator 131, a data supplementation portion 132, a simulation portion 133, and a model building portion 134. Although the various components 131-134 of the control device 13 are assumed to be separate functional units, those skilled in the art will recognize that the functions of the components 131-134 may be combined or integrated into a single component, or further subdivided into further subcomponents without departing from the spirit and scope of the present inventive concept.

[0062] The data generator 131 can generate a process design table. The process design table can include process design data, which includes design values of process factors that affect the structural characteristics of the battery electrode plate (e.g., factor values of process factors). The data generator 131 can generate process design data with reference to previously performed experimental results related to the manufacture of battery electrode plates. The data generator 131 can obtain design values of (e.g., each) process factor by performing a design of experiments (DOE) based on a full factorial design with reference to existing experimental results. For example, the data generator 131 can obtain design values such as active material type, active material fraction and physical properties, binder content, conductive material content, loading level, and mixture (or composition) density through DOE performance.

[0063] The data generator 131 may obtain process design data for one or more (e.g., multiple) different process design conditions and generate a process design table to include the obtained process design data. In some embodiments, the data generator 131 may generate a process design table to include design values of one or more (e.g., each) process factors for one or more (e.g., each) of the multiple process design conditions. The data generator 131 may store the generated process design table in the storage device 12.

[0064] The data supplementation section 132 can add process design data missing from the process design data used (e.g., required) to simulate the structural features of the battery electrode plate to the process design table. In some embodiments, the data supplementation section 132 can obtain process design data not obtained by the data generator 131 from the process design data used to perform the discrete element method (DEM) and store the process design data in the process design table. For example, the data supplementation section 132 can obtain the thickness of the electrode plate in a state where stress is removed by pressure during the electrode plate manufacturing process as process design data and add the thickness to the process design table.

[0065] The data supplementation section 132 can use values measured by previously performed experiments or predicted values based on machine learning to obtain process design data to be added to the process design table. In the latter case, the data supplementation section 132 can use a linear regression model such as Ridge or Lasso to prevent overfitting to obtain process design data. The linear regression model can be learned using DOE data as learning data, which contains actual process design information of the battery electrode plate and corresponding process factor values that have been measured. For example, the linear regression model can be a model learned using the actual process design information of the battery electrode plate and the actual measured value of the electrode plate thickness as learning data.

[0066] The simulation part 133 can retrieve process design data corresponding to one or more (e.g., each) process design conditions from the process design table, and simulate the structural features of the battery electrode plate corresponding to the process design conditions based on the data. The simulation part 133 can perform simulations based on the discrete element method. The simulation part 133 can use the process design data corresponding to the process design conditions to simulate the components (e.g., active materials, binders, conductive materials, current collectors, etc.), particle shapes (e.g., spherical, non-spherical, etc.), particle size distribution and / or verticality of the battery electrode plate. Those skilled in the art will recognize that in addition to or instead of the discrete element method, other numerical methods that simulate the behavior of other particle systems can be used to simulate the components of the battery electrode plate.

[0067] The simulation part 133 can obtain curvature data through simulation, where the curvature data is a structural feature of the battery electrode plate. Figure 2 3D images of structural features of a negative electrode plate generated based on a discrete element method according to an embodiment of the present disclosure.

[0068] When the curvature data of the battery electrode plate corresponding to one or more (eg, each) process design conditions is obtained through simulation, the simulation part 133 may store the data in the storage device 12 .

[0069] The model construction part 134 may construct a prediction model that predicts the curvature of the battery electrode plate based on the process design conditions through machine learning using the process design table and curvature data simulated using the process design table as learning data.

[0070] If the process design data is input, the prediction model can predict and output the curvature of the battery electrode plate based on the process design data. The model building part 134 can use a portion of the process data stored in the storage device 12 (for example, 80% of the total process data) as training data for the prediction model, and use the remaining portion (for example, 20% of the total process data) as verification data for the prediction model to build a prediction model. In one embodiment, the prediction model for predicting the curvature of the battery electrode plate can be a linear regression model, such as Ridge, Lasso or Elastic net. The prediction model for predicting the curvature of the battery electrode plate can also be a nonlinear model, such as a neural network, a random forest, a support vector machine, or a gradient boosting machine.

[0071] If the prediction model is constructed, the model construction component 134 may store the prediction model in the storage device 12 .

[0072] The control device 13 may include at least one processor. A processor may refer to a data processing device, such as a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), or a field-programmable gate array (FPGA), that is physically configured with circuitry to execute the functions expressed in code or instructions contained in a program (e.g., the functions of the data generator 131, the data supplementation section 132, the simulation section 133, and the model building section 134). The program instructions may be stored in a memory coupled to the processor.

[0073] The design support device 20 may receive process design conditions for a manufacturing process of a battery electrode plate from a user terminal 30, and use the prediction model constructed by the model construction device 10 to predict electrode plate characteristic information (e.g., curvature and ionic resistance) corresponding to the received process design conditions. The design support device 20 may also provide the predicted plate characteristic information to the user terminal 30 to support the user's process factor design.

[0074] The design support device 20 may receive information about a process factor selected as an object of interest (hereinafter referred to as a "target process factor") from the user terminal 30, and use a prediction model to simulate changes in the characteristics of the battery electrode plate according to changes in the design value of the target process factor. The design support device 20 may also provide design support information to the user terminal 30 to guide the design of the target process factor based on the simulation results.

[0075] The design support device 20 may include a communication device 21 , a storage device 22 , and a control device 23 .

[0076] The communication device 21 can perform a communication function between the design support apparatus 20 and an external apparatus (eg, the model construction apparatus 10 , the user terminal 30 , etc.).

[0077] The storage device 22 can store various data and information processed by the design support device 20. The storage device 22 can take the form of volatile memory, non-volatile memory, persistent memory, flash memory, a hard disk drive, and / or the like. For example, the storage device 22 can store a prediction model for predicting curvature. The prediction model can be constructed by the model construction device 10, then transmitted to the design support device 20 and stored in the storage device 22. In some embodiments, the storage device 22 can store data used to construct a user interface (UI) provided by the design support device 20 to the user terminal 30.

[0078] The storage device 22 may store programs or computer instructions for operating the control device 23 , which will be described later.

[0079] The control device 23 can control the overall operation of the design support device 20. The control device 23 can include a tortuosity determiner 231, an ionic resistance determiner 232, a reverse engineering portion 233, and an interface provider 234. Although the various components 231-234 of the control device 23 are assumed to be separate functional units, those skilled in the art will recognize that, without departing from the spirit and scope of the present inventive concept, the functions of the components 231-234 can be combined or integrated into a single component, or further subdivided into further subcomponents.

[0080] The curvature determiner 231 can predict the curvature of the battery electrode plate using the prediction model constructed by the model building device 10. The design support device 20 can receive process design information containing process factor design conditions (e.g., design values of active material type, active material fraction and physical properties, binder content, conductive material content, load level and mixture (or composition) density) of the manufacturing process for the battery electrode plate from the user terminal 30. If the process design information is received from the user terminal 30, the curvature determiner 231 can input the received process design information into the prediction model. In addition, if the prediction model outputs the curvature of the battery electrode plate in response to the input process design information, the curvature determiner 231 can determine the curvature as the curvature of the battery electrode plate obtained when the battery electrode plate is manufactured under the corresponding process design conditions.

[0081] Ionic resistance determiner 232 may receive the curvature predicted by the prediction model from curvature determiner 231. Ionic resistance determiner 232 may calculate an ionic resistance representing the electrochemical characteristics of the battery electrode plate from the received curvature. Equation 1 below represents the relationship between the curvature and ionic resistance of a battery electrode plate according to one embodiment of the present disclosure.

[0082] Equation 1

[0083] τ 2 =N M ×ε

[0084]

[0085] In Equation 1 above, τ represents the curvature of the battery electrode plate, N M represents the MacMullin number, σ0 represents the conductivity value of pure liquid electrolyte, σ eff represents the conductivity value when the separator and the liquid electrolyte are combined, ε represents the porosity of the separator, A represents the size of the battery electrode plate, d represents the thickness of the battery electrode plate, and Rion represents the ion resistance of the battery electrode plate.

[0086] The ionic resistance determiner 232 can calculate the ionic resistance from the curvature of the battery electrode plate based on the above equation 1. The ionic resistance determiner 232 can correct the ionic resistance calculated using equation 1 by referring to the ionic resistance previously measured through experiments. In one embodiment, the storage device 22 can store the curvature and ionic resistance of the battery electrode plate actually measured during the experiment of the battery electrode plate as reference data in the form of a lookup table. The ionic resistance determiner 232 can compare the reference data stored in the storage device 22 with the ionic resistance calculated using the above equation 1 and correct the ionic resistance based on the comparison result.

[0087] The reverse engineering part 233 may provide design support information that supports factor value design for a target process factor selected by a user as an object of interest among a plurality of process factors.

[0088] The reverse engineering part 233 can receive reverse engineering information containing selection information about the target process factor from the user terminal 30. If the reverse engineering information is received, the reverse engineering part 233 can sequentially change the design value of the target process factor and input it into the prediction model. As a result, the reverse engineering part 233 can obtain the characteristic values (bending, ionic resistance, etc.) of the battery electrode plate. In some embodiments, the reverse engineering part 233 can obtain the bending using the prediction model and obtain the ionic resistance using the obtained bending and equation 1 above. The reverse engineering part 233 can monitor the changes in the characteristics of the battery electrode plate according to the changes in the design value of the target process factor based on the information obtained about the characteristics of the battery electrode plate.

[0089] The reverse engineering information received from the user terminal 30 may further include design range information for the target process factor. The design range information may include, for example, the upper and lower limits of the corresponding process factor, as well as a change interval. The reverse engineering portion 233 may control the change range and change interval of the design value of the target process factor based on the received design range information. In some embodiments, the reverse engineering portion 233 may gradually increase or decrease the design value of the corresponding process factor within the design range consisting of the upper and lower limits, by a set change interval.

[0090] When there are multiple target process factors, the reverse engineering part 233 can generate one or more (e.g., all) design value combinations that may appear within the design range of the target process factor. In some embodiments, the reverse engineering part 233 can sequentially input the generated design value combinations into the prediction model.

[0091] Among the process factors input to the prediction model, the design values of the remaining process factors that are not the target process factors may be automatically set to default values. The design values of the remaining process factors other than the target process factors may be automatically set to the design values input from the previous prediction of the prediction model. The design values of the remaining process factors other than the target process factors may be set to the values received from the user terminal 30. In some embodiments, the reverse engineering part 233 may also receive design values of process factors that are not of interest from the user terminal 30.

[0092] If the target process factor is the score of the active substance, the reverse engineering part 233 may automatically adjust the score of each active substance so that the sum of the scores of the active substances becomes 100. In some embodiments, each time the reverse engineering part 233 changes the score of the active substance selected as the object of interest, the reverse engineering part 233 may also adjust the scores of the remaining active substances so that the sum of the scores of the active substances becomes 100.

[0093] The reverse engineering part 233 may analyze the characteristic information of the battery electrode plate obtained by changing the design value of the target process factor, and select at least one reference data to be included in the design support information provided to the user terminal 30. In some embodiments, the reverse engineering part 233 may change the design value of the target process factor, analyze the obtained characteristic information, select at least one piece of characteristic information that meets a specified condition, and select the design value of the target process factor used to derive the selected characteristic information as the reference data.

[0094] The reverse engineering information received from the user terminal 30 may further include target characteristic information of the battery electrode plate. The target characteristic information may indicate characteristic values of the battery electrode plate that the user wishes to obtain.

[0095] The reverse engineering part 233 may change the design value of the target process factor and select reference data by comparing the obtained characteristic information of the battery electrode plate with the target characteristic information.

[0096] The reverse engineering section 233 may arrange the acquired characteristic information of the battery electrode plate in order of least difference from the target characteristic information. In some embodiments, the reverse engineering section 233 may select at least one piece of characteristic information selected in order of least difference from the target characteristic information and the design value of the target process factor for deriving the selected at least one piece of characteristic information as reference data. For example, if the target characteristic information includes a target ionic resistance, the reverse engineering section 233 may change the design value of the target process factor and select at least one ionic resistance selected in order of least difference from the target ionic resistance from the acquired ionic resistance as reference data. In some embodiments, the reverse engineering section 233 may select the design value of the target process factor for deriving the ionic resistance selected as reference data.

[0097] The reverse engineering section 233 can modify the design value of the target process factor and arrange the obtained battery electrode plate characteristic information in order of size. In some embodiments, the reverse engineering section 233 can select at least one piece of characteristic information selected in order of smallest size or largest size and select the design value of the target process factor used to derive the at least one piece of characteristic information as reference data. For example, the reverse engineering section 233 can select at least one ionic resistance selected in order of smallest size from the ionic resistances obtained using the prediction model as reference data.

[0098] In some embodiments, the reverse engineering portion 233 may select, as reference data, a design value of a target process factor for deriving a selected ionic resistance.

[0099] If reference data is selected as described above, the reverse engineering part 233 may generate design support information to include the selected reference data.

[0100] The reverse engineering unit 233 may generate a graph showing a trend in which the characteristics of the battery electrode plate change according to changes in the design values of the target process factors based on the characteristic information of the battery electrode plate obtained by changing the design values of the target process factors. The reverse engineering unit 233 may also include graph data for visualizing such a graph in the design support information.

[0101] If the user terminal 30 is connected to the design support apparatus 20 , the interface provider 234 may provide a user interface (UI) to the user terminal 30 to support design of process factors of the battery electrode plate.

[0102] Figures 3A to 3D is a layout diagram of an example UI provided by a system for designing a manufacturing process of a battery electrode plate according to an embodiment of the present disclosure.

[0103] The interface provider 234 may provide the user terminal 30 with a UI for receiving design conditions of a manufacturing process of a battery electrode plate from the user terminal 30 .

[0104] Figure 3A is a layout diagram of an example UI 310 for receiving design conditions of a manufacturing process of a battery electrode plate.

[0105] refer to Figure 3A , UI 310 may include a list of process factors required to predict the curvature and ionic resistance of the battery electrode plate (see Figure 3A (For example, see the "Design Factors" section at the bottom of the UI 310). For example, UI 310 may include the fraction and physical properties of each active material, binder content, conductive material content, active material type, loading level, mixture density, process conditions, etc. as process factors. The process conditions may include process conditions (e.g., time, pressure, temperature) that affect the structural characteristics of the battery electrode plate. For example, using the negative electrode plate as an example, the process conditions may include the process conditions of the pressing process, which significantly affects the microstructure of the negative electrode plate.

[0106] The UI 310 may further include an input window 311 through which a user may input a desired design value of each process factor.

[0107] If the UI 310 is received from the design support apparatus 20, the user terminal 30 may display the UI 310 on the screen of the user terminal 30. In some embodiments, if a design value is input from the user through the input window 311 on the UI 310, the user terminal 30 may transmit the design value to the design support apparatus 20.

[0108] If the design value of each process factor is received from the user terminal 30, the interface provider 234 may store the design value in the storage device 22. The design value stored in the storage device 22 may be used by the curvature determiner 231 to predict the curvature.

[0109] The active material of the battery electrode plate can be used in the form of a mixture of several active materials. If the sum of the scores of the active materials received from the user terminal 30 is not 100, the interface provider 234 can automatically correct the score of each active material so that the sum of the scores becomes 100. If the score of each active material is corrected, the interface provider 234 can store the corrected score value in the storage device 22. Therefore, the curvature determiner 231 can use the corrected score value to perform curvature prediction. The interface provider 234 can also correct the input UI 310 to include the corrected score value and provide the corrected input UI 310 to the user terminal 30.

[0110] The interface provider 234 may provide the user terminal 30 with a UI for outputting the characteristics (curvature and ion resistance) of the battery electrode plate predicted by the design support apparatus 20 .

[0111] Figure 3B is a layout diagram of an example UI 320 for outputting characteristic information of a battery electrode plate predicted by the design support apparatus 20 .

[0112] refer to Figure 3B , the UI 320 may include a list of characteristic factors (eg, tortuosity and ion resistance) of the battery electrode plate whose values are predicted by the design support apparatus 20 , and an output window 321 displaying the predicted value of each characteristic factor.

[0113] If the UI 320 is received from the design support apparatus 20, the user terminal 30 may display the UI 320 on the screen of the user terminal 30. The user may verify the applicability of the process design conditions by checking characteristic information of the battery electrode plate according to the process design conditions through the UI 320 output on the user terminal 30.

[0114] The interface provider 234 may provide the user terminal 30 with a UI for receiving reverse engineering information from the user terminal 30 .

[0115] Figure 3C is a diagram of a layout of an example UI 330 for receiving reverse engineering information.

[0116] refer to Figure 3C , the UI 330 may include an input window 331 for receiving target characteristic information. For example, the UI 330 may include an input window 331 for receiving a target value of ionic resistance.

[0117] The UI 330 may further include an input window 332 for receiving a target process factor selected by a user (see Figure 3C For example, the UI 330 may further include an input window 332 for receiving input of a lower limit value, an upper limit value, and a change interval of the target process factor.

[0118] The UI 330 may further include an input / output window 333 for outputting or receiving remaining process factors other than the target process factor (see Figure 3C If the design values of the remaining process factors other than the target process factor are automatically set by the design support apparatus 20, the UI 330 may display the automatically set design values in the input / output window 333. If the user wishes to directly set the design values of the remaining process factors other than the target process factor, the UI 330 may receive the design values through the input / output window 333.

[0119] If the UI 330 is received from the design support device 20, the user terminal 30 may also display the UI 330 on the screen of the user terminal 30. The user terminal 30 may receive target feature information and design range information of the target process factor through input windows 331 and 332 on the UI 330. In some embodiments, the user terminal 30 may send reverse engineering information generated based on the input information to the design support device 20. When the reverse engineering information is received from the user terminal 30, the interface provider 234 may store the received reverse engineering information in the storage device 22. The reverse engineering information stored in the storage device 22 may be used by the reverse engineering unit 233 to generate design support information.

[0120] The user terminal 30 can receive design values of the remaining process factors other than the target process factor through the input / output window 333 on the UI 330. If the design value of the process parameter other than the target process factor is input into the input / output window 333, the user terminal 30 can also send the input design value to the design support device 20. The interface provider 234 that receives the input design value can store the received design value in the storage device 22. The design value stored in the storage device 22 can be used to generate design support information in the reverse engineering part 233.

[0121] The interface provider 234 may also provide the user terminal 30 with a UI for outputting the design support information obtained through reverse engineering.

[0122] Figure 3Dis a layout diagram of an example UI 340 for outputting design support information obtained through reverse engineering.

[0123] refer to Figure 3D , the UI 340 may include a table 341 and a chart 342 for outputting design support information.

[0124] In the 'Target Value' row of Table 341, the ionic resistance derived through reverse engineering that is closest to the target ionic resistance and the design values of the target process factors X1 and X2 used to derive the ionic resistance can be output as reference data. In the 'Optimum Value' row of Table 341, the minimum ionic resistance derived through reverse engineering and the design values of the target process factors X1 and X2 used to derive the minimum ionic resistance can be output as reference data.

[0125] The graph 342 may represent a change trend of the ionic resistance according to changes in the design values of the target process factors X1 and X2.

[0126] If the UI 340 containing the design support information is received from the design support apparatus 20 , the user terminal 30 may display the UI 340 on the screen of the user terminal 30 and provide the UI 340 to the user.

[0127] The control device 23 may include at least one processor. The at least one processor configuring the control device 23 may execute the functions of the tortuosity determiner 231, the ionic resistance determiner 232, the reverse engineering part 233, and the interface provider 234 represented by the codes or instructions included in the program.

[0128] The design support device 20 may provide the user terminal 30 with the above-mentioned process design support function for the manufacturing process of the battery electrode plate in the form of an online tool.

[0129] In the following, reference Figures 4 to 6 , a detailed description will be given of how the system 1 according to one or more embodiments supports process design for a manufacturing process of a battery electrode plate.

[0130] Figure 4 is a flowchart of a process for constructing a prediction model for predicting curvature of a battery electrode plate according to an embodiment of the present disclosure. Figure 4 The method can be referenced by Figure 1 The model building device 10 described performs.

[0131] refer to Figure 4 The model building apparatus 10 may obtain previously performed experimental data related to the manufacturing process of the battery electrode plate ( S11 ). The model building apparatus 10 may perform DOE based on the experimental data obtained in action S11 ( S12 ).

[0132] The model building apparatus 10 may obtain process design data for a plurality of different process design conditions from the results of the DOE performed in action S12, and generate a process design table to include the data (S13). The process design data may include design values for one or more (e.g., each) process factors. In some embodiments, the process design table may include design values for one or more (e.g., each) process factors for one or more (e.g., each) process design conditions among the plurality of process design conditions.

[0133] The model building device 10 may obtain process design data missing from the process design table among process design data to be used (eg, required) for simulating the structural characteristics of the battery electrode plate, and add the data to the process design table ( S14 ).

[0134] In action S14 , the model building device 10 may additionally obtain the thickness of the electrode plate in a state where stress is removed by pressing in the manufacturing process of the battery electrode plate as part of the process design data, and add the data to the process design table.

[0135] In action S14, the model building device 10 may obtain process design data to be added to the process design table using values measured through previously performed experiments or predicted values based on machine learning. In the latter case, the model building device 10 may obtain the process design data using a linear regression model.

[0136] The model building device 10 may perform simulation based on a discrete element method using the process design table, and obtain curvature data of the battery electrode plate through the simulation ( S15 ).

[0137] In step S15, the model building device 10 can retrieve process design data corresponding to one or more (e.g., each) process design conditions from the process design table, and simulate the structural characteristics of the battery electrode plate corresponding to the process design conditions based on the data. In some embodiments, the model building device 10 can use the process design data corresponding to one or more (e.g., each) process design conditions to simulate the components (e.g., active material, binder, conductive material, current collector, etc.), particle shape (e.g., spherical, non-spherical), particle size distribution, and verticality of the battery electrode plate. The model building device 10 can obtain curvature data through simulation, which can be considered as a structural characteristic of the battery electrode plate.

[0138] If curvature data corresponding to one or more (e.g., each) process design conditions are obtained through simulation, the model building device 10 can build a prediction model through machine learning that predicts the curvature of the battery electrode plate that varies according to the process design conditions (S16).

[0139] In action S16, the model building device 10 can use the process design table and the curvature data as learning data to train the prediction model. The trained model can predict and output the curvature of the battery electrode plate based on the input process design data (e.g., the input design values of one or more (e.g., each) process factors).

[0140] Figure 5 The present invention is a flowchart of a method for providing characteristic information of a battery electrode plate predicted according to process design conditions according to an embodiment of the present disclosure. Figure 5 The method can be referenced by Figure 1 The design support device 20 described here performs the following operations.

[0141] refer to Figure 5 The design support device 20 may receive process factor design information of the manufacturing process of the battery electrode plate from the user terminal (S21). The process factor design information may include design values such as active material type, active material fraction and physical properties, binder content, conductive material content, loading level, and mixture (or composition) density, which may be process factors of the manufacturing process of the battery electrode plate.

[0142] If the process design information is received from the user terminal 30 , the design support apparatus 20 may predict characteristic values of the battery electrode plate using the prediction model constructed by the model construction apparatus 10 ( S22 ).

[0143] In action S22, the design support device 20 may also input the received process design information into the prediction model to obtain the curvature representing the structural characteristics of the battery electrode plate. Once the curvature of the battery electrode plate is obtained, the design support device 20 may use the curvature to obtain the ionic resistance of the battery electrode plate, which is an electrochemical characteristic.

[0144] If the characteristic value of the battery electrode plate is obtained through action S22 , the design support apparatus 20 may transmit characteristic information of the battery electrode plate including the obtained characteristic value to the user terminal 30 ( S23 ).

[0145] When the design support device 20 provides characteristic information of the battery electrode plate corresponding to the design conditions input by the user, the user terminal 30 may display a UI including the characteristic information on the screen of the user terminal 30. The user may verify whether the current process design is suitable for obtaining the target characteristics of the battery electrode plate by examining the characteristic information of the battery electrode plate according to the design conditions through the UI output on the user terminal 30. In some embodiments, based on verifying that the current process design is suitable for obtaining the target characteristics of the battery electrode plate, the battery electrode plate is manufactured according to the current process design.

[0146] Figure 6is a flow chart of a process for designing a manufacturing process for a battery electrode plate according to an embodiment of the present disclosure.

[0147] Figure 6 The method can be referenced by Figure 1 The design support device 20 described here performs the following operations.

[0148] refer to Figure 6 The design support device 20 may receive reverse engineering information from the user terminal 30 (S31). The reverse engineering information may include selection information regarding a target process factor selected by the user. The reverse engineering information may further include design range information for the target process factor. The reverse engineering information may further include target characteristic information for the battery electrode plate. The target characteristic information may indicate characteristic values of the battery electrode plate that the user wishes to obtain.

[0149] Based on the reverse engineering information, the design support apparatus 20 may simulate changes in characteristic values of the battery electrode plate according to changes in design values of target process factors ( S32 ).

[0150] In step S32 , the design support device 20 may sequentially change the design values of the target process factors and input the design values into the prediction model to obtain characteristic values (curvature, ion resistance) of the battery electrode plate.

[0151] In step S32, the design support device 20 may determine a change range and a change interval for the design value of the target process factor based on the design range information in response to the design value of the target process factor being changed. In some embodiments, the design support device 20 may gradually increase or decrease the design value of the corresponding target process factor by a set change interval within a design range consisting of an upper limit and a lower limit.

[0152] In step S32, when there are multiple target process factors, the design support device 20 may generate various (e.g., all) design value combinations that may occur within the design range of the target process factors. In some embodiments, the design support device 20 may sequentially input the generated design value combinations into the prediction model to obtain characteristic values (tortuosity and ionic resistance) of the battery electrode plate.

[0153] If the simulation in action S32 is completed, the design support apparatus 20 may generate design support information to be provided to the user terminal 30 based on the simulation result ( S33 ).

[0154] In action S33, the design support device 20 may select at least one piece of characteristic information selected according to a condition (e.g., a predetermined condition) from the characteristic information of the battery electrode plate obtained by simulation as reference data to be included in the design support information. For example, the design support device 20 may select at least one piece of characteristic information selected in the order of small differences from the target characteristic information from the characteristic information obtained by simulation, and the design value of the target process factor for deriving the selected characteristic information as reference data. In some embodiments, the design support device 20 may select at least one piece of characteristic information selected in the order of small differences (or large differences) from the characteristic information obtained by simulation, and the design value of the target process factor for deriving the selected characteristic information as reference data. In some embodiments, the design support device 20 selects at least one piece of characteristic information based on the value of a piece of characteristic information that has a difference that meets a standard from the design value of the target process factor. The standard may be that the difference is a minimum (or maximum) difference, or a difference that is lower (or higher) than a threshold value.

[0155] In action S33, the design support apparatus 20 may generate a graph showing changes in characteristics of the battery electrode plate according to changes in the design values of the target process factors based on the simulation results. The design support apparatus 20 may further include graph data for visualizing such a graph in the design support information.

[0156] Once the design support information is generated, the design support apparatus 20 may transmit the design support information to the user terminal 30 ( S34 ).

[0157] If the design support information is received from the design support device 20, the user terminal 30 may also display a UI containing the design support information on the screen of the user terminal 30. Thus, the user can refer to the design support information displayed on the screen of the user terminal 30 and design the optimal factor values of the target process factors of interest. In some embodiments, the battery electrode plate is manufactured based on the optimal factor values.

[0158] Although the embodiments of the present disclosure have been described in detail, it should be understood that the present disclosure is not limited to the disclosed embodiments, but on the contrary is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

[0159] Description of the symbol

[0160] 1: Process design support system

[0161] 10: Model building device

[0162] 11: Communication device of model building device

[0163] 12: Storage device of model building device

[0164] 13: Control device of model building device

[0165] 131: Data Generator

[0166] 132: Data Supplement

[0167] 133: Simulation part

[0168] 134: Model building part

[0169] 20: Design support device

[0170] 21: Communication device for design support device

[0171] 22: Design support device storage device

[0172] 23: Design support device control device

[0173] 231: Curvature Determiner

[0174] 232: Ionic Resistance Determiner

[0175] 233: Reverse Engineering Section

[0176] 234: Interface Provider

[0177] 30: User terminal

Claims

1. A system for manufacturing a battery electrode plate, comprising: A computing device configured to: receiving, from a client device, a target process factor among a plurality of process factors associated with manufacturing the battery electrode plate; predicting, via a machine learning model, a change in a characteristic of the battery electrode plate based on a change in a design value of the target process factor; generating information for selecting the target process factor based on predicting the change in the characteristic of the battery electrode plate; as well as The information is sent to the client device for use in manufacturing the battery electrode plate.

2. The system according to claim 1, wherein: The machine learning model is configured to output characteristic information of the battery electrode plate based on input design values corresponding to the plurality of process factors.

3. The system according to claim 2, wherein: The computing device is further configured to: Obtaining a curvature of the battery electrode plate based on the machine learning model; and The ionic resistance is calculated based on the tortuosity.

4. The system according to claim 2, wherein: The computing device is further configured to automatically set the input design values corresponding to the plurality of process factors other than the target process factor to design values used in previous predictions of the machine learning model.

5. The system according to claim 2, wherein: The computing device is further configured to receive the input design values corresponding to the plurality of process factors other than the target process factor from the client device.

6. The system according to claim 1, wherein: The computing device is further configured to: receiving design range information from the client device, the design range information including a design value change range and a change interval of the target process factor; as well as The design value of the target process factor is increased or decreased based on the design range information.

7. The system according to claim 1, wherein: Based on determining that the multiple process factors include scores of multiple active substances and the target process factor is the score of at least one active substance among the multiple active substances, the computing device is further configured to automatically adjust the scores of the multiple active substances in response to the design value of the target process factor being changed so that the sum of the scores of the multiple active substances is equal to 100.

8. The system according to claim 2, wherein: The computing device is further configured to: selecting a characteristic value of the battery electrode plate that satisfies a condition based on the predicted change in the characteristic of the battery electrode plate; as well as The information is generated to include the selected characteristic values and the design values of the target process factors used to derive the characteristic values.

9. The system according to claim 8, wherein: The computing device is further configured to: receiving a target characteristic value from the client device; selecting at least one second feature value based on the predicted change in the feature of the battery electrode plate, the selection being based on the second feature value having a difference from the target feature value that satisfies a criterion; and The information is generated to include the selected at least one second characteristic value and the design value of the target process factor used to derive the at least one second characteristic value.

10. The system according to claim 9, wherein: The characteristic information includes the ionic resistance of the battery electrode plate, and the computing device is further configured to: selecting at least one ionic resistance among a plurality of ionic resistances obtained based on the predicted change in the characteristic of the battery electrode plate, wherein the at least one ionic resistance has a minimum difference from a target ionic resistance received from the client device; and The information is generated to include the selected at least one ionic resistance and the design value of the target process factor used to derive the selected at least one ionic resistance.

11. A system for manufacturing a battery electrode plate, comprising: A computing device configured to: receiving first information for manufacturing the battery electrode plate from a client device; Predicting characteristic information of the battery electrode plate using the first information and a prediction model based on machine learning; as well as The characteristic information is sent to the client device for use in manufacturing the battery electrode plate.

12. The system according to claim 11, wherein The characteristic information includes the curvature and ionic resistance of the battery electrode plate, and the computing device is further configured to: inputting the first information into the prediction model to obtain the curvature of the battery electrode plate; and The ionic resistance is calculated based on the tortuosity.

13. The system according to claim 11, wherein: The first information includes design values of multiple process factors for manufacturing the battery electrode plate, and the multiple process factors include the type of active material, the fraction and physical properties of the active material, the binder content, the conductive material content, the loading level and the mixture density or process conditions.

14. The system according to claim 11, wherein: The computing device is further configured to construct the prediction model, wherein the computing device is further configured to: performing a design of experiments (DOE) based on experimental data of a manufacturing process for the battery electrode plate; generating a process design table by the DOE, wherein the process design table includes design values of process factors for a plurality of different process design conditions; Obtaining curvature data of the battery electrode plate by performing simulation based on the process design table using a discrete element method; and The prediction model is constructed using the process design table and the curvature data as learning data.

15. The system according to claim 14, wherein: The computing device is further configured to add thickness data to the process design table using a linear regression model learned using actual process design data of the battery electrode plate and actual measured values of the thickness of the battery electrode plate.

16. A method for manufacturing a battery electrode plate, comprising: receiving first information for manufacturing the battery electrode plate from a client device; Predicting a curvature of the battery electrode plate using the first information and a prediction model based on machine learning; calculating the ionic resistance of the battery electrode plate based on the curvature; as well as Characteristic information is sent to the client device for use in manufacturing the battery electrode plate, the characteristic information including at least one of the curvature or the ionic resistance of the battery electrode plate.

17. The method according to claim 16, wherein The first information includes design values of multiple process factors for manufacturing the battery electrode plate, and the multiple process factors include the type of active material, the fraction and physical properties of the active material, the binder content, the conductive material content, the loading level and the mixture density or process conditions.

18. The method according to claim 16, further comprising constructing the prediction model, wherein: The construction of the prediction model includes: performing a design of experiments (DOE) based on experimental data of a manufacturing process for the battery electrode plate to generate a process design table, the process design table including design values of process factors for a plurality of different process design conditions; Performing simulation based on the process design table using a discrete element method to obtain curvature data of the battery electrode plate; and The prediction model is constructed using the process design table and the tortuosity data as learning data.

19. The method according to claim 17, further comprising: receiving, from the client device, selection information for selecting a target process factor among the plurality of process factors; predicting, via the prediction model, changes in characteristics of the battery electrode plate based on changes in design values of the target process factors; generating information for designing the target process factor based on the predicted change in the characteristic of the battery electrode plate; as well as The first information is sent to the client device for use in manufacturing the battery electrode plate.

20. The method according to claim 19, wherein The generating of the first information includes: selecting a characteristic value of the battery electrode plate that satisfies a condition based on the predicted change in the characteristic of the battery electrode plate; and The information is generated to include the selected characteristic values and the design values of the target process factors used to derive the characteristic values.

Images