Battery diagnosis device, battery diagnosis method, and battery diagnosis system

Abstract

According to some embodiments, a battery diagnosis device includes: a data management unit configured to collect an electrical signal data set of a welding process for forming an electrode tab in a plurality of sample battery cells and collect a fracture energy data set of a fracture experiment for measuring tensile strength while separating the electrode tab from the plurality of sample battery cells; and a control unit configured to generate a fracture energy estimation model for estimating fracture energy values corresponding to electrical signal values on the basis of the electrical signal data set and the fracture energy data set, and estimate fracture energy values corresponding to electrical signal values of a target battery cell by using the fracture energy estimation model.

Description

Battery diagnostic device, battery diagnostic method, and battery diagnostic system

[0001] Cross-citation with related applications

[0002] This application claims the benefit of priority from Republic of Korea Patent Application No. 10-2024-0003046, filed January 8, 2024, the entire contents of which are incorporated herein by reference.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to a battery diagnostic device, a battery diagnostic method, and a battery diagnostic system.

[0005] Recently, active research and development has been conducted on secondary batteries. The term "secondary battery" refers to a rechargeable battery, encompassing both conventional Ni / Cd and Ni / MH batteries, as well as recent lithium-ion batteries. Among secondary batteries, lithium-ion batteries can boast higher energy densities than conventional Ni / Cd and Ni / MH batteries. They can be manufactured in small and lightweight designs, making them highly versatile power sources for mobile devices. Recently, their use has expanded to include power sources for electric vehicles, attracting attention as a next-generation energy storage medium.

[0006] During the battery cell manufacturing process, a welding process may be performed to attach electrode tabs to the battery can. Destructive testing can be performed to verify the quality of the welding process, but non-destructive testing of weld quality may be necessary to address issues such as yield loss. Conventional methods have been used to estimate welding defects based on whether the electrical signal data used in the welding process exceeds the normal range. However, this method suffers from low defect detection accuracy.

[0007] One purpose of the embodiments disclosed in this document is to provide a battery diagnostic device, a battery diagnostic method, and a battery diagnostic system that can improve the accuracy of non-destructive testing for estimating welding defects in battery cell electrode tabs.

[0008] The technical objectives of the embodiments disclosed in this document are not limited to the technical tasks mentioned above, and other technical tasks not mentioned will be clearly understood by those skilled in the art from the descriptions below.

[0009] According to some embodiments, a battery diagnostic device includes a data management unit configured to collect an electric signal dataset of a welding process for forming electrode tabs on a plurality of sample battery cells, and a fracture energy dataset of a fracture experiment for measuring tensile strength while separating the electrode tabs from the plurality of sample battery cells; and a control unit configured to generate a fracture energy estimation model for estimating fracture energy values ​​corresponding to electric signal values ​​based on the electric signal dataset and the fracture energy dataset, and to estimate fracture energy values ​​corresponding to electric signal values ​​of a target battery cell using the fracture energy estimation model.

[0010] According to some embodiments, the fracture energy estimation model includes an artificial intelligence model learned through machine learning, and the artificial intelligence model includes at least one of a random forest regression model, an artificial neural network (ANN) model, and a multiple regression model.

[0011] According to some embodiments, the electrical signal values ​​include welding voltage, transformer voltage, minimum welding voltage, initial welding voltage, final welding voltage, welding current variation, initial welding current, maximum welding current, average welding current, welding heat input, initial welding resistance, welding resistance difference, and final welding resistance.

[0012] According to some embodiments, the electrical signal values ​​have signal weights based on the degree to which they affect electrode tap quality, and the fracture energy estimation model is configured to be learned based on the signal weights.

[0013] According to some embodiments, the fracture energy dataset includes a graph of tensile strength versus displacement of an electrode tab in each sample battery cell, and the fracture energy of the electrode tab in each sample battery cell is calculated based on an integration of the tensile strength up to the displacement at which the electrode tab separates.

[0014] According to some embodiments, the control unit is configured to diagnose whether welding of an electrode tab of the target battery cell is defective by comparing the fracture energy value of the target battery cell with a threshold energy value.

[0015] According to some embodiments, the control unit is configured to calculate a correlation index between actual fracture energy values ​​and estimated fracture energy values ​​of the plurality of sample battery cells, and adjust the threshold energy value based on the correlation index.

[0016] According to some embodiments, a battery diagnosis method includes the steps of collecting an electrical signal dataset of a welding process for forming electrode tabs on a plurality of sample battery cells; collecting a fracture energy dataset of a fracture experiment for measuring tensile strength while separating the electrode tabs from the plurality of sample battery cells; generating a fracture energy estimation model for estimating fracture energy values ​​corresponding to electrical signal values ​​based on the electrical signal dataset and the fracture energy dataset; and estimating fracture energy values ​​corresponding to electrical signal values ​​of a target battery cell using the fracture energy estimation model.

[0017] According to some embodiments, the fracture energy estimation model includes an artificial intelligence model learned through machine learning, and the artificial intelligence model includes at least one of a random forest regression model, an artificial neural network model, and a multiple regression model.

[0018] According to some embodiments, the electrical signal values ​​include welding voltage, transformer voltage, minimum welding voltage, initial welding voltage, final welding voltage, welding current variation, initial welding current, maximum welding current, average welding current, welding heat input, initial welding resistance, welding resistance difference, and final welding resistance.

[0019] According to some embodiments, the electrical signal values ​​have signal weights based on the degree to which they affect electrode tap quality, and the fracture energy estimation model is configured to be learned based on the signal weights.

[0020] According to some embodiments, the fracture energy dataset includes a graph of tensile strength versus displacement of an electrode tab in each sample battery cell, and the fracture energy of the electrode tab in each sample battery cell is calculated based on an integration of the tensile strength up to the displacement at which the electrode tab separates.

[0021] According to some embodiments, the battery diagnosis method further includes a step of diagnosing whether welding of an electrode tab of the target battery cell is defective by comparing the fracture energy value of the target battery cell with a threshold energy value.

[0022] According to some embodiments, the step of diagnosing whether the battery is defective includes the step of calculating a correlation index between actual fracture energy values ​​and estimated fracture energy values ​​of the plurality of sample battery cells; and the step of adjusting the threshold energy value based on the correlation index.

[0023] According to some embodiments, a battery diagnosis system includes a welding device configured to perform a welding process for forming electrode tabs on a plurality of sample battery cells; a measuring device configured to perform a fracture experiment for measuring tensile strength while separating the electrode tabs from the plurality of sample battery cells; and a battery diagnosis device configured to generate a fracture energy estimation model for estimating fracture energy values ​​corresponding to electrical signal values ​​based on an electrical signal dataset of the welding process and a fracture energy dataset of the fracture experiment, and to estimate fracture energy values ​​corresponding to electrical signal values ​​of a target battery cell using the fracture energy estimation model.

[0024] According to the embodiments disclosed in this document, a battery diagnostic device, a battery diagnostic method, and a battery diagnostic system can be provided that can improve the accuracy of non-destructive testing for estimating welding defects in battery cell electrode tabs.

[0025] The technical effects according to the embodiments disclosed in this document are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art according to the disclosure of this document.

[0026] FIG. 1 illustrates an environment in which a battery diagnostic system according to some embodiments operates.

[0027] FIG. 2 illustrates elements constituting a battery diagnostic system according to some embodiments.

[0028] FIG. 3 illustrates elements constituting a battery diagnostic device according to some embodiments.

[0029] FIG. 4 illustrates a graph representing an electrical signal dataset according to some embodiments.

[0030] Figure 5 illustrates a process for generating a fracture energy estimation model according to some embodiments.

[0031] FIG. 6 illustrates a graph showing the correlation between actual fracture energy values ​​and estimated fracture energy values ​​according to some embodiments.

[0032] FIG. 7 illustrates a process for performing a fracture test on battery cells using a measuring device according to some embodiments.

[0033] FIG. 8 illustrates a process for calculating fracture energy based on a graph of tensile strength according to displacement of an electrode tab according to some embodiments.

[0034] FIG. 9 illustrates steps of a battery diagnostic method according to some embodiments.

[0035] Hereinafter, embodiments described in this document are described with reference to the attached drawings. However, this is not intended to limit the disclosure of this document to specific embodiments, and it should be understood that various modifications, equivalents, and / or alternatives of the embodiments described in this document are included.

[0036] The embodiments and terminology used in this document are not intended to limit the technical features described in this document to a specific embodiment, but should be understood to encompass various modifications, equivalents, or alternatives of the embodiment. In connection with the description of the drawings, similar reference numerals may be used to refer to similar or related components. The singular form of a noun corresponding to an item may include one or more of the item, unless the context clearly indicates otherwise.

[0037] In this document, the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can each include any one of the items listed together in that phrase, or all possible combinations thereof. Terms such as "first", "second", "first", "second", "A", "B", "(a)", or "(b)" may be used merely to distinguish the corresponding component from other corresponding components, and do not limit the corresponding components in any other respect (e.g., importance or order) unless specifically stated otherwise.

[0038] In this document, when a component (e.g., a first component) is referred to as being “connected,” “coupled,” or “connected,” with or without the terms “functionally” or “communicatively,” or “coupled” or “connected,” it means that the component can be connected to the other component directly (e.g., wired or wirelessly), or indirectly (e.g., via a third component).

[0039] The methods according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded as a commodity between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory, CD-ROM), or may be distributed online (e.g., downloaded or uploaded) through an application store or directly between two user devices. In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0040] According to the embodiments disclosed in this document, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to the embodiments disclosed in this document, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to the embodiments disclosed in this document, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0041] FIG. 1 illustrates an environment in which a battery diagnostic system according to some embodiments operates.

[0042] Referring to FIG. 1, the battery diagnosis system (100) can generate a fracture energy estimation model using a plurality of sample battery cells (10), and can generate welding defect information (30) of a target battery cell (20) using the fracture energy estimation model.

[0043] The battery diagnostic system (100) may include a system for diagnosing the welding quality of a welding process that forms electrode tabs on a battery cell. If the welding quality is excessively poor, the strength with which the electrode tabs are attached to the battery cell may be low, which may compromise the durability of the battery cell. The battery diagnostic system (100) can non-destructively estimate the welding quality of the electrode tabs on a battery cell, and for this purpose, can utilize electrical signal data from the welding process.

[0044] A dataset utilized to generate a fracture energy estimation model based on a plurality of sample battery cells (10) can be extracted. The fracture energy estimation model can be trained based on electrical signal data of a welding process for the plurality of sample battery cells (10). Once the training of the fracture energy estimation model is completed, whether the welding quality of the target battery cell (20) is defective can be estimated using the dataset. The dataset for the plurality of sample battery cells (10) can be periodically updated, and the fracture energy estimation model can also be periodically retrained.

[0045] FIG. 2 illustrates elements constituting a battery diagnostic system according to some embodiments.

[0046] Referring to FIG. 2, the battery diagnostic system (100) may include a welding device (110), a measuring device (120), and a battery diagnostic device (130). However, the present invention is not limited thereto, and some components may be omitted from the battery diagnostic system (100), or other general-purpose components may be further included in the battery diagnostic system (100).

[0047] A welding device (110) can perform a welding process to form electrode tabs on a plurality of sample battery cells (10) and a target battery cell (20). The welding device (110) can operate based on electrical signal data such as current signal values, voltage signal values, and welding resistance values. The quality of the electrode tabs formed on the battery cells can be determined based on the electrical signal values.

[0048] The measuring device (120) can perform a fracture test to physically separate electrode tabs from a plurality of sample battery cells (10) and a target battery cell (20). During the fracture test, the tensile strength of the electrode tabs can be measured. By analyzing the tensile strength according to the displacement (δ) at which the electrode tabs separate from the battery can of the battery cell, the fracture energy of the battery cell can be measured. A higher fracture energy can be interpreted as a higher welding quality of the electrode tab.

[0049] The battery diagnosis device (130) can obtain an electric signal dataset of a welding process for a plurality of sample battery cells (10) from a welding device (110), and can obtain a fracture energy dataset of a fracture experiment for a plurality of sample battery cells (10) from a measuring device (120). The battery diagnosis device (130) can generate a fracture energy estimation model based on the plurality of sample battery cells (10), and can estimate welding defect information (30) of a target battery cell (20) using the same.

[0050] FIG. 3 illustrates elements constituting a battery diagnostic device according to some embodiments.

[0051] Referring to FIG. 3, the battery diagnostic device (130) may include a data management unit (131) and a control unit (132). However, the present invention is not limited thereto, and some components may be omitted from the battery diagnostic device (130), or other general-purpose components may be further included in the battery diagnostic device (130).

[0052] The data management unit (131) can manage an electric signal dataset provided from a welding device (110) and a fracture energy dataset provided from a measuring device (120). For example, the data management unit (131) can include a memory device and / or a storage device, and can manage the electric signal dataset and the fracture energy dataset using a database.

[0053] The control unit (132) can perform various process operations of the battery diagnostic device (130). The control unit (132) can execute commands, software, applications, programs, etc. stored in memory, storage, cache, etc., and can perform computational processing on data. For example, the control unit (132) can be implemented in the form of at least one of a microprocessor, a CPU, a GPU, and an AP.

[0054] The data management unit (131) may be configured to collect an electrical signal dataset of a welding process for forming electrode tabs on a plurality of sample battery cells (10). The electrical signal dataset may be provided from a welding device (110). The electrical signal dataset may include a current signal, a voltage signal, a welding resistance value, etc., and may determine the welding quality of the electrode tab.

[0055] The data management unit (131) may be configured to collect a fracture energy dataset of a fracture experiment measuring tensile strength while separating electrode tabs from a plurality of sample battery cells (10). The fracture energy dataset may be provided from a measuring device (120). The fracture energy dataset may include data measuring a displacement at which an electrode tab separates from a battery can and a tensile strength corresponding to the displacement. The fracture energy dataset may represent the fracture energy of the electrode tab, and the fracture energy may represent a weld quality.

[0056] The control unit (132) may be configured to generate a fracture energy estimation model that estimates fracture energy values ​​corresponding to electrical signal values ​​based on an electrical signal dataset and a fracture energy dataset. The matching relationships between the electrical signal data and the fracture energy data may function as learning data. When a large number of such matching relationships are learned, the fracture energy estimation model may predict fracture energy data for newly input electrical signal data. The fracture energy estimation model may include an artificial intelligence model learned through various machine learning techniques.

[0057] The control unit (132) may be configured to estimate a fracture energy value corresponding to the electrical signal values ​​of the target battery cell (20) using a fracture energy estimation model. If the fracture energy value is too low, the quality of the electrode tab weld of the target battery cell (20) may fall below a reference value. Based on the fracture energy value, welding defect information (30) indicating whether the electrode tab weld is defective may be derived. In this manner, a non-destructive welding quality inspection of the target battery cell (20) may be performed.

[0058] According to an embodiment, the fracture energy estimation model may include an artificial intelligence model trained through machine learning, and the artificial intelligence model may include at least one of a random forest regression model, an artificial neural network (ANN) model, and a multiple regression model. RF regression, ANN, multiple regression, and other suitable AI models may be utilized as models for learning the matching relationship between electrical signal data and fracture energy data. The AI ​​model may be continuously updated as the diagnosis of the battery diagnostic device (130) accumulates.

[0059] According to an embodiment, the electrical signal values ​​may include welding voltage, transformer voltage, minimum welding voltage, initial welding voltage, final welding voltage, welding current variation, initial welding current, maximum welding current, average welding current, welding heat input, initial welding resistance, welding resistance difference, and final welding resistance. In a conventional welding defect determination technique, whether each of the electrical signal values ​​is out of the normal range is analyzed, but in order to improve the lack of accuracy of the conventional technique, the battery diagnosis system (100) may determine the welding defect using a fracture energy estimation model based on the electrical signal values.

[0060] According to an embodiment, electrical signal values ​​may have signal weights based on the degree to which they affect electrode tap quality, and the fracture energy estimation model may be configured to be trained based on the signal weights. For example, among the electrical signal values, current-related values ​​may have higher weights than other values, and this difference in weights may be reflected in the training process of the fracture energy estimation model. For example, the initial welding current may have a higher weight than other values.

[0061] In an embodiment, the fracture energy dataset may include a graph of tensile strength versus displacement (δ) of an electrode tab in each sample battery cell, and the fracture energy of the electrode tab in each sample battery cell may be calculated based on an integration of the tensile strength up to the displacement at which the electrode tab separates. The attachment location (δ) of the electrode tab i = 0) from the separation position of the electrode tab (δ = δ f ) by integrating the value of tensile strength, the fracture energy of the electrode tab can be calculated, which can indicate the bonding strength and welding quality of the electrode tab.

[0062] According to an embodiment, the control unit (132) may be configured to diagnose whether the welding of the electrode tab of the target battery cell (20) is defective by comparing the fracture energy value of the target battery cell (20) with a threshold energy value. The threshold energy value for determining the welding defect of the electrode tab may be preset, and the defect information (30) of the target battery cell (20) may be generated through the comparison with the threshold energy value. The target battery cell (20) determined to be normal may be transported for subsequent packaging work, etc., and the target battery cell (20) determined to be defective may be transported for re-inspection or disposal, etc.

[0063] According to an embodiment, the control unit (132) may be configured to calculate a correlation index between actual fracture energy values ​​and estimated fracture energy values ​​of a plurality of sample battery cells (10), and adjust a threshold energy value based on the correlation index. For example, the correlation index may be R 2 A coefficient of determination may be included. A higher correlation index may bring the critical energy value closer to the measured threshold based on actual fracture energy values, while a lower correlation index may bring the critical energy value lower than the measured threshold.

[0064] FIG. 4 illustrates a graph representing an electrical signal dataset according to some embodiments.

[0065] Referring to FIG. 4, a graph (400) representing an electrical signal dataset may be illustrated. The graph (400) may represent electrical signal values ​​for a plurality of electrode taps.

[0066] The electrical signal values ​​may include welding voltage, transformer voltage, minimum welding voltage, initial welding voltage, final welding voltage, welding current variation, initial welding current, maximum welding current, average welding current, welding heat input, initial welding resistance, welding resistance difference, and final welding resistance. The graph (400) may represent the maximum and minimum values ​​of the normal range of each electrical signal value.

[0067] In the conventional method, the welding quality was judged based on whether there was an electric signal value exceeding the normal range of the graph (400), but the battery diagnosis system (100) can form a fracture energy estimation model using the electric signal values ​​of the graph (400) and judge the welding quality using this.

[0068] Figure 5 illustrates a process for generating a fracture energy estimation model according to some embodiments.

[0069] Referring to FIG. 5, an RF model (500) representing a process for generating a fracture energy estimation model may be illustrated. The RF model (500) may be a type of artificial intelligence model trained through machine learning.

[0070] The RF model (500) can calculate evaluation values ​​for welding quality according to the range of electric signal values ​​(e.g., Prediction 1 to Prediction 1000), and can derive a final evaluation value by calculating a weighted average using probability values ​​of the evaluation values.

[0071] For example, the RF model (500) classifies 13 electrical signal values ​​into binary and 2 13 You can calculate the evaluation values ​​of 2 13The final evaluation value can be derived as a weighted average of the evaluation values. Meanwhile, if some electrical signal values ​​(e.g., current-related values) have higher weights than others, the final evaluation value can be derived by reflecting those weights.

[0072] FIG. 6 illustrates a graph showing the correlation between actual fracture energy values ​​and estimated fracture energy values ​​according to some embodiments.

[0073] Referring to FIG. 6, graphs (610, 620) showing the correlation between actual fracture energy values ​​and estimated fracture energy values ​​can be illustrated.

[0074] Graph (610) can represent the prediction results for electrical signal data that was not used in the learning process of the fracture energy estimation model, and R of graph (610) 2 The coefficient of determination may be 0.7785. The graph (620) may represent the prediction results for the electrical signal data used in the learning process of the fracture energy estimation model, and the R of the graph (620) 2 The coefficient of determination may be 0.9734.

[0075] The graph (610) may illustrate a measured threshold value (612) based on actual fracture energy values ​​and a threshold energy value (611) used for diagnosing a welding defect of a target battery cell (20). The measured threshold value (612) based on a destructive inspection may be set based on actual fracture energy values ​​for a plurality of sample battery cells (10).

[0076] On the other hand, the threshold energy value (611) may be set based on the estimated fracture energy values ​​by the fracture energy estimation model, rather than the actual fracture energy values. Therefore, the threshold energy value (611) may be set more conservatively (smaller) than the actual threshold value (612), and R 2The lower the coefficient of determination, the greater the difference between the critical energy value (611) and the actual threshold value (612).

[0077] FIG. 7 illustrates a process for performing a fracture test on battery cells using a measuring device according to some embodiments.

[0078] Referring to FIG. 7, processes (710, 720, 730) for performing a fracture test on battery cells through a measuring device (120) can be illustrated.

[0079] In the first process (710), the battery can (711) and the electrode tab (713) can be joined through the welding part (712), and the lower fixing jig (714) and the upper fixing jig (715) of the measuring device (120) can fix the battery can (711) and the electrode tab (713).

[0080] As the process progresses from the first process (710) to the third process (730), the upper fixing jig (715) can separate the electrode tab (713) from the battery can (711). During the separation process, the displacement (δ) at which the electrode tab (713) is separated and the tensile strength formed in the electrode tab (713) and / or the welded portion (712) can be measured according to the displacement (δ).

[0081] FIG. 8 illustrates a process for calculating fracture energy based on a graph of tensile strength according to displacement of an electrode tab according to some embodiments.

[0082] Referring to FIG. 8, a process for calculating fracture energy based on a graph (800) of tensile strength according to displacement of an electrode tab can be described.

[0083] The graph (800) may represent a curve (810) representing the tensile strength according to the displacement of the electrode tab, a microintegral value (820), and a separation displacement (830). In the curve (810), it can be confirmed that the tensile strength is also 0 when the displacement (δ) is 0. As the displacement (δ) increases, the tensile strength may increase. At the separation displacement (830), the electrode tab (713) may be separated from the battery can (711).

[0084] By adding all the micro-integral values ​​(820) from 0 to the separation displacement (830), the actual fracture energy of the electrode tab can be measured. The actual fracture energy may refer to the energy required to separate the electrode tab, which may indicate the strength and quality of the electrode tab weld. In a manner similar to the graph (800), a fracture energy dataset for a plurality of sample battery cells (10) can be generated.

[0085] FIG. 9 illustrates steps of a battery diagnostic method according to some embodiments.

[0086] Referring to FIG. 9, the battery diagnosis method (900) may include steps (910) to (940). However, the present invention is not limited thereto, and some steps may be omitted or other general steps may be added, and the steps of the battery diagnosis method (900) may be executed in a different order than the illustrated order.

[0087] The battery diagnosis method (900) may be composed of steps that are processed in a time-series manner in the battery diagnosis device (130). Therefore, even if the content is omitted below, the content described above for the battery diagnosis device (130) may be equally applied to the battery diagnosis method (900).

[0088] Steps (910) to (940) of the battery diagnosis method (900) can be performed by the data management unit (131) and control unit (132) of the battery diagnosis device (130).

[0089] In step (910), the battery diagnostic device (130) may perform a step of collecting an electrical signal dataset of a welding process that forms electrode tabs on a plurality of sample battery cells.

[0090] In step (920), the battery diagnostic device (130) may perform a step of collecting a fracture energy dataset of a fracture experiment that measures tensile strength while separating electrode tabs from a plurality of sample battery cells.

[0091] In step (930), the battery diagnostic device (130) may perform a step of generating a fracture energy estimation model that estimates fracture energy values ​​corresponding to electrical signal values ​​based on the electrical signal dataset and the fracture energy dataset.

[0092] In step (940), the battery diagnostic device (130) may perform a step of estimating a fracture energy value corresponding to the electric signal values ​​of the target battery cell using a fracture energy estimation model.

[0093] According to an embodiment, the battery diagnosis method (900) may be implemented in the form of a computer program stored on a computer-readable storage medium. That is, the computer program may include instructions for implementing the battery diagnosis method (900), and the instructions of the program may be stored on the computer-readable storage medium. The computer program may include a mobile application.

[0094] According to an embodiment, the computer-readable storage medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs, DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute computer program instructions such as ROMs, RAMs, flash memories, and the like. The computer program instructions may include machine language codes generated by a compiler and high-level language codes that can be executed by a computer using an interpreter, etc.

[0095] The terms "include," "comprise," or "have" used herein, unless otherwise specifically stated, imply that the corresponding component may be included, and therefore should be interpreted to include other components rather than to exclude other components. All terms, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiments disclosed in this document pertain, unless otherwise defined. Commonly used terms, such as terms defined in dictionaries, should be interpreted to be consistent with their contextual meaning in the relevant art, and shall not be interpreted in an idealized or overly formal sense, unless explicitly defined in this document.

[0096] The above description is merely an illustrative description of the technical idea disclosed in this document, and those skilled in the art to which the embodiments disclosed in this document pertain may make various modifications and variations without departing from the essential characteristics of the embodiments disclosed in this document. Therefore, the embodiments disclosed in this document are not intended to limit the technical idea of ​​the embodiments disclosed in this document, but to explain it, and the scope of the technical idea disclosed in this document is not limited by these embodiments. The protection scope of the technical idea disclosed in this document should be interpreted by the claims below, and all technical ideas within a scope equivalent thereto should be interpreted as being included in the scope of rights of this document.

[0097] [Explanation of symbols]

[0098] 10: Multiple sample battery cells 20: Target battery cell

[0099] 30: Welding defect information 100: Battery diagnostic system

[0100] 110: Welding device 120: Measuring device

[0101] 130: Battery diagnostic device 131: Data management unit

[0102] 132: Control Unit

Claims

1. A data management unit configured to collect an electric signal data set of a welding process for forming electrode tabs on a plurality of sample battery cells, and a fracture energy data set of a fracture experiment for measuring tensile strength while separating the electrode tabs from the plurality of sample battery cells; and A battery diagnostic device comprising a control unit configured to generate a fracture energy estimation model that estimates fracture energy values corresponding to electric signal values based on the electric signal dataset and the fracture energy dataset, and to estimate fracture energy values corresponding to electric signal values of a target battery cell using the fracture energy estimation model.

2. In paragraph 1, The above fracture energy estimation model includes an artificial intelligence model learned through machine learning, A battery diagnostic device, wherein the artificial intelligence model includes at least one of a random forest regression model, an artificial neural network (ANN) model, and a multiple regression model.

3. In paragraph 1, The above electrical signal values include welding voltage, transformer voltage, minimum welding voltage, initial welding voltage, end welding voltage, welding current variation, initial welding current, maximum welding current, average welding current, welding heat input, initial welding resistance, welding resistance difference and end welding resistance, a battery diagnostic device.

4. In paragraph 3, The above electrical signal values have signal weights based on the degree to which they affect the electrode tap quality. A battery diagnostic device, wherein the above-mentioned fracture energy estimation model is configured to be learned based on the above-mentioned signal weights.

5. In paragraph 1, The above fracture energy dataset contains a graph of the tensile strength versus displacement of the electrode tabs in each sample battery cell, A battery diagnostic device, wherein the fracture energy of the electrode tab of each sample battery cell is calculated based on the integration of the tensile strength up to the displacement at which the electrode tab separates.

6. In paragraph 1, A battery diagnostic device, wherein the control unit is configured to diagnose whether welding of an electrode tab of the target battery cell is defective by comparing the fracture energy value of the target battery cell with a threshold energy value.

7. In paragraph 6, The above control unit calculates a correlation index between the actual fracture energy values and the estimated fracture energy values of the plurality of sample battery cells, A battery diagnostic device configured to adjust the threshold energy value based on the above correlation index.

8. A step of collecting an electrical signal dataset of a welding process forming electrode tabs on multiple sample battery cells; A step of collecting a fracture energy dataset of a fracture experiment measuring tensile strength while separating electrode tabs from the plurality of sample battery cells; A step of generating a fracture energy estimation model that estimates fracture energy values corresponding to electrical signal values based on the electrical signal dataset and the fracture energy dataset; and A battery diagnosis method, comprising a step of estimating a fracture energy value corresponding to electric signal values of a target battery cell using the fracture energy estimation model.

9. In paragraph 8, The above fracture energy estimation model includes an artificial intelligence model learned through machine learning, A battery diagnosis method, wherein the artificial intelligence model includes at least one of a random forest regression model, an artificial neural network model, and a multiple regression model.

10. In paragraph 8, A battery diagnostic method, wherein the above electrical signal values include welding voltage, transformer voltage, minimum welding voltage, initial welding voltage, end welding voltage, welding current variation, initial welding current, maximum welding current, average welding current, welding heat input, initial welding resistance, welding resistance difference and end welding resistance.

11. In paragraph 10, The above electrical signal values have signal weights based on the degree to which they affect the electrode tap quality. A battery diagnosis method, wherein the above-mentioned fracture energy estimation model is configured to be learned based on the above-mentioned signal weights.

12. In paragraph 8, The above fracture energy dataset contains a graph of the tensile strength versus displacement of the electrode tabs in each sample battery cell, A battery diagnostic method, wherein the fracture energy of an electrode tab of each sample battery cell is calculated based on the integration of the tensile strength up to the displacement at which the electrode tab separates.

13. In paragraph 8, A battery diagnosis method further comprising a step of diagnosing whether welding of an electrode tab of the target battery cell is defective by comparing the fracture energy value of the target battery cell with a threshold energy value.

14. In paragraph 13, The steps to diagnose whether the above is defective or not are: A step of calculating a correlation index between the actual fracture energy values and the estimated fracture energy values of the plurality of sample battery cells; and A battery diagnosis method, comprising a step of adjusting the threshold energy value based on the above correlation indicator.

15. A welding device configured to perform a welding process for forming electrode tabs on a plurality of sample battery cells; A measuring device configured to perform a fracture test to measure tensile strength while separating electrode tabs from the plurality of sample battery cells; and A battery diagnosis system, comprising a battery diagnosis device configured to generate a fracture energy estimation model that estimates fracture energy values corresponding to electric signal values based on an electric signal dataset of the welding process and a fracture energy dataset of the fracture experiment, and to estimate fracture energy values corresponding to electric signal values of a target battery cell using the fracture energy estimation model.

Images