WO2023277561A1 - 전지셀의 벤트 발생시점 예측 시스템 및 예측방법 - Google Patents
전지셀의 벤트 발생시점 예측 시스템 및 예측방법 Download PDFInfo
- Publication number
- WO2023277561A1 WO2023277561A1 PCT/KR2022/009293 KR2022009293W WO2023277561A1 WO 2023277561 A1 WO2023277561 A1 WO 2023277561A1 KR 2022009293 W KR2022009293 W KR 2022009293W WO 2023277561 A1 WO2023277561 A1 WO 2023277561A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vent
- battery cell
- occurrence time
- width
- remaining sealing
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 36
- 238000007789 sealing Methods 0.000 claims abstract description 123
- 238000005259 measurement Methods 0.000 claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 6
- 238000004904 shortening Methods 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000002474 experimental method Methods 0.000 description 7
- 230000007423 decrease Effects 0.000 description 5
- 238000011176 pooling Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 2
- 229910052782 aluminium Inorganic materials 0.000 description 2
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 229910001416 lithium ion Inorganic materials 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 229920000642 polymer Polymers 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 238000013022 venting Methods 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 238000003915 air pollution Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000012887 quadratic function Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 239000000565 sealant Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/4285—Testing apparatus
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/4228—Leak testing of cells or batteries
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M50/00—Constructional details or processes of manufacture of the non-active parts of electrochemical cells other than fuel cells, e.g. hybrid cells
- H01M50/10—Primary casings; Jackets or wrappings
- H01M50/102—Primary casings; Jackets or wrappings characterised by their shape or physical structure
- H01M50/105—Pouches or flexible bags
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M50/00—Constructional details or processes of manufacture of the non-active parts of electrochemical cells other than fuel cells, e.g. hybrid cells
- H01M50/10—Primary casings; Jackets or wrappings
- H01M50/172—Arrangements of electric connectors penetrating the casing
- H01M50/174—Arrangements of electric connectors penetrating the casing adapted for the shape of the cells
- H01M50/178—Arrangements of electric connectors penetrating the casing adapted for the shape of the cells for pouch or flexible bag cells
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M50/00—Constructional details or processes of manufacture of the non-active parts of electrochemical cells other than fuel cells, e.g. hybrid cells
- H01M50/30—Arrangements for facilitating escape of gases
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M50/00—Constructional details or processes of manufacture of the non-active parts of electrochemical cells other than fuel cells, e.g. hybrid cells
- H01M50/30—Arrangements for facilitating escape of gases
- H01M50/342—Non-re-sealable arrangements
- H01M50/3425—Non-re-sealable arrangements in the form of rupturable membranes or weakened parts, e.g. pierced with the aid of a sharp member
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M50/00—Constructional details or processes of manufacture of the non-active parts of electrochemical cells other than fuel cells, e.g. hybrid cells
- H01M50/50—Current conducting connections for cells or batteries
- H01M50/543—Terminals
- H01M50/552—Terminals characterised by their shape
- H01M50/553—Terminals adapted for prismatic, pouch or rectangular cells
- H01M50/557—Plate-shaped terminals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/022—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by means of tv-camera scanning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Definitions
- the present invention relates to a system and method for predicting a vent generation time of a battery cell.
- secondary batteries capable of charging and discharging have been widely used as energy sources for wireless mobile devices.
- secondary batteries are attracting attention as an energy source for electric vehicles, hybrid electric vehicles, etc., which are proposed as a solution to air pollution such as existing gasoline vehicles and diesel vehicles using fossil fuels. Therefore, the types of applications using secondary batteries are diversifying due to the advantages of secondary batteries, and it is expected that secondary batteries will be applied to more fields and products than now.
- secondary batteries are sometimes classified into lithium ion batteries, lithium ion polymer batteries, lithium polymer batteries, etc. according to the composition of electrodes and electrolytes. It is increasing.
- secondary batteries include a cylindrical battery and a prismatic battery in which an electrode assembly is embedded in a cylindrical or prismatic metal can, and a pouch-type battery in which the electrode assembly is embedded in a pouch-type case of an aluminum laminate sheet, depending on the shape of the battery case.
- the electrode assembly embedded in the battery case is a power generating device capable of charging and discharging, consisting of a positive electrode, a negative electrode, and a separator structure interposed between the positive electrode and the negative electrode. It is classified into a jelly-roll type wound with a separator interposed therebetween, and a stack type in which a plurality of positive and negative electrodes of a predetermined size are sequentially stacked in a state in which a separator is interposed.
- FIG. 1 is a schematic diagram showing the form of a general pouch-type battery cell.
- the electrode assembly 20 is accommodated in a pouch-type battery case 10, the electrode leads 30 are drawn out from both ends of the battery case 10, and the outside of the battery case It has a structure in which a sealing portion 11a is formed around it.
- a sealing portion 11a and a gas pocket portion 11b in the form of an empty space between the sealing portion and the storage space are formed in the terrace portion 11, which is a space between the space where the electrode assembly is accommodated and the end of the battery case.
- the gas pocket portion 11b is a space where gas is collected when gas is generated inside the battery for various reasons.
- the battery cell as described above is subjected to various high-temperature storage experiments according to the customer's request. This is to determine the safety and durability of the battery cell under harsh conditions. At this time, if the vent time in the high-temperature storage experiment is predicted, the durability and performance of the cell can be predicted.
- the width of the sealing portion 11a gradually decreases, and eventually the sealing portion 11a bursts, causing a vent phenomenon in which gas is discharged.
- the present invention has been made to solve the above problems, and an object of the present invention is to provide a system for predicting the vent occurrence time of a battery cell that can automatically predict the vent occurrence time and improve the accuracy of the vent occurrence time prediction. .
- the present invention relates to a system for predicting a vent occurrence time of a battery cell in which a terrace portion including a sealing portion is formed on at least one side of a pouch-type battery case and an electrode lead is drawn out at an end of the terrace portion, and the vent occurrence time point according to the width of the remaining sealing portion
- the measurement unit may include a camera for capturing an image or video of the terrace unit; And a calculation unit for calculating the width of the remaining sealing portion in the captured image or video; can include
- the measurement unit may measure the width of the remaining sealing unit by shortening the period as the vent generation time approaches.
- the data collection and measurement of the width of the remaining sealing portion may be performed at a high temperature of 60° C. or higher.
- the determination unit may predict a vent occurrence time of a battery cell to be measured through machine learning or deep learning.
- the determination unit may derive a correlation between the width of the remaining sealing portion and the vent occurrence time according to the width of the remaining sealing portion from the data.
- the determination unit may predict a vent generation time of the battery cell according to the measured width of the remaining sealing portion for each measurement period of the width of the remaining sealing portion.
- the battery cell vent generation timing prediction system according to the present invention may further include a learning unit for learning the prediction result.
- the learning unit configures learning data for predicting the vent occurrence time, and the determination unit newly derives a correlation between the width of the remaining sealing portion and the vent occurrence time according to the width of the remaining sealing part from the learning data, and then the measured The vent occurrence time of the battery cell may be predicted according to the width of the remaining sealing portion.
- the learning unit may configure learning data by verifying validity of data by comparing a predicted event occurrence time and an actual event occurrence time, and updating the verification result to the data collected in the storage unit.
- the present invention provides a method for predicting a vent generation time of a battery cell using a system for predicting a vent generation time of a battery cell.
- a method for predicting a vent occurrence time of a battery cell includes collecting data on a vent occurrence time according to a width of a remaining sealing portion; Periodically measuring the width of the remaining sealing portion of the battery cell to be measured; And comparing the measured width of the remaining sealing portion with the collected data to predict a vent generation time of the battery cell to be measured; includes
- the periodically measuring the width of the remaining sealing portion may include capturing an image or video of the terrace portion with a camera and calculating the width of the remaining sealing portion from the captured image or video.
- the step of predicting the vent occurrence time of the battery cell to be measured may include deriving a correlation between the width of the remaining sealing portion and the corresponding vent occurrence time point, and determining the width of the residual sealing portion measured based on the correlation.
- a process of periodically predicting a vent generation time of a battery cell to be measured may be included.
- the present invention may further include learning the prediction result.
- the step of learning the prediction result may include verifying the validity of data by comparing the predicted event occurrence time and the actual event occurrence time, and configuring the learning data by updating the verification result to the data.
- a correlation between the width of the remaining sealing portion and the resulting vent occurrence time is newly derived from the learning data, and then the battery according to the width of the remaining sealing portion measured therefrom. It may be to predict a cell vent generation time point.
- the present invention predicts the vent occurrence time based on machine learning, thereby automatically predicting the vent occurrence time and improving the accuracy of the vent occurrence time prediction.
- FIG. 1 is a schematic diagram showing the form of a general pouch-type battery cell.
- FIG. 2 is a block diagram showing the configuration of a system for predicting a vent generation time of a battery cell according to an embodiment of the present invention.
- Figure 3 is a schematic diagram showing a process of measuring the width of the remaining sealing portion.
- FIG. 4 is a photograph showing an image taken by a camera.
- FIG. 5 is a block diagram showing the configuration of a system for predicting a vent generation time of a battery cell according to another embodiment of the present invention.
- FIG. 6 is a flowchart illustrating a process of learning prediction results.
- FIG. 7 is a schematic diagram showing a learning method by deep learning.
- the terms “include” or “have” are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that it does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.
- a part such as a layer, film, region, plate, etc. is said to be “on” another part, this includes not only the case where it is “directly on” the other part, but also the case where another part is present in the middle.
- a part such as a layer, film, region, plate, etc.
- being disposed “on” may include the case of being disposed not only on the top but also on the bottom.
- FIG. 2 is a block diagram showing the configuration of a system for predicting a vent generation time of a battery cell according to an embodiment of the present invention.
- Figure 3 is a schematic diagram showing a process of measuring the width of the remaining sealing portion.
- the present invention relates to a vent generation time prediction system 100 of a battery cell in which a terrace portion including a sealing portion is formed on at least one side of a pouch-type battery case and an electrode lead is drawn out at an end of the terrace portion.
- a storage unit 110 that collects data about a vent occurrence time according to the width of the remaining sealing unit;
- the present invention predicts the vent occurrence time based on machine learning, thereby automatically predicting the vent occurrence time and improving the accuracy of the vent occurrence time prediction.
- the present invention is to predict the vent generation time of the pouch-type battery cell.
- the electrode assembly 20 is accommodated in the pouch-type battery case 10, the electrode leads 30 are drawn out from both ends of the battery case 10, and the outer periphery of the battery case It has a structure in which the sealing portion 11a is formed.
- a sealing portion 11a and a gas pocket portion 11b in the form of an empty space between the sealing portion and the storage space are formed in the terrace portion 11, which is a space between the space where the electrode assembly is accommodated and the end of the battery case.
- the electrode lead 30 includes a positive lead and a negative lead.
- the positive lead and the negative lead may be drawn out in opposite directions from the battery case as shown in FIGS. 1 and 3, but the structure is limited thereto. It is not. Since the electrode assembly and elements constituting the electrode assembly are known to those skilled in the art, a detailed description thereof will be omitted.
- the battery case 10 is not particularly limited as long as it is used as an exterior material for packaging the battery, and a cylindrical, prismatic or pouch type may be used, but in detail, a pouch type battery case may be used.
- a pouch-type battery case is usually made of an aluminum laminate sheet, and may be composed of an inner sealant layer for sealing, a metal layer to prevent penetration of materials, and an outer resin layer forming the outermost part of the case.
- the width of the remaining sealing part means the width (w) of the remaining sealed part as the sealed (heat-sealed) part between the sealing parts is gradually torn away as the pressure inside the battery cell increases. According to the present invention, it is possible to predict the vent occurrence time of the battery cell according to the measured width of the remaining sealing part without waiting for the actual vent phenomenon to occur from a plurality of data.
- the plurality of data is data about a vent occurrence time according to the width of the remaining sealing part, and is stored in the storage unit 110 .
- the storage unit 110 may be composed of big data by accumulating an image captured in the process of predicting and measuring a vent occurrence time point for a plurality of battery cells, a width value of the remaining sealing portion, and a vent occurrence time point.
- the vent occurrence point may be defined as a time required from the measurement of the remaining sealing portion to the occurrence of the vent.
- the storage unit 110 may include a DB for storing and managing the data, which may be used as basic data for constructing learning data in a learning unit described later. At this time, the data may be classified and stored according to the specifications and experimental conditions of the battery cell.
- the measurement unit 120 measures the width of the remaining sealing portion of the battery cell 1 to be measured.
- the measurement unit 120 includes a camera 121 for capturing an image or video of the terrace unit; and a calculation unit 122 for calculating the width of the remaining sealing portion in the captured image or video; can include
- capturing an image or video of the terrace part 11 may be performed while the battery cell 1 is mounted on the jig 123 .
- the jig 123 can mount at least one battery cell 1, and serves to fix the battery cell 1 so that it is easy to take an image or video of the terrace part.
- one battery cell 1 is shown as being mounted on the jig 123, but as shown in FIG. 4, two or more battery cells 1 may be photographed in a state in which they are mounted at the same time.
- the image of the terrace part 11 can be easily photographed on the jig 123, and the battery cell 1 can be mounted in a direction perpendicular to the ground so that gas can be easily collected in the gas pocket part 11b.
- the jig 123 is not particularly limited in its shape, but it is preferable that the contact area between the battery cell and the jig 123 is minimized so as not to affect the vent of the battery cell. As shown in FIG. 4 , it is preferable to cover the electrode lead 30 with a cap to prevent a short circuit.
- the camera 121 can take images or videos, there is no particular limitation on its type, and for example, a CCD camera or the like can be used.
- the measuring unit 120 may further include a display device (not shown) displaying the photographed image as image data.
- FIG. 4 is a photograph showing an image taken by a camera.
- an image photographed by the camera 121 is displayed as an image by the display device.
- the width w of the remaining sealing portion is measured by the calculation unit 122 .
- the calculation unit 122 may be a general computing device.
- the display device displays a scale formed in the form of a grid of a certain size on the image, and the calculator 122 calculates the width of the portion corresponding to the remaining sealing part in the image as shown in FIG. can be calculated by comparison.
- the width of the remaining sealing portion is calculated to be 8.7 mm.
- the collection of the data and the measurement of the width of the remaining sealing portion may be performed at a high temperature, specifically It can be carried out at a high temperature of 60 °C or more.
- the result measured by the measurement unit 120 may be transmitted to the storage unit 110 and then stored therein to constitute a part of data.
- the determining unit 130 may be performed in a computing device, and automatically predicts a vent generation time of a battery cell to be measured through machine learning or deep learning, so that the accuracy of the prediction can be improved.
- the determination unit 130 may derive a correlation between the width of the remaining sealing portion and the corresponding vent occurrence time from the data, that is, the data on the vent occurrence time according to the width of the remaining sealing portion.
- the correlation between the width of the remaining sealing portion and the vent occurrence time point means a tendency of the vent occurrence point (time required to vent) for the measured value of the remaining sealing portion width.
- a correlation between the width of the remaining sealing portion and the vent occurrence time may be represented by an equation, and this may be performed by regression analysis.
- the relational expression may represent various forms such as a linear function, a quadratic function, a polynomial function, an exponential function, and a logarithmic function.
- a linear function a quadratic function
- a polynomial function a polynomial function
- an exponential function a logarithmic function.
- Equation (1) x is the width (mm) of the remaining sealing portion, y is the time (h) required until the vent occurs after measuring the width of the remaining sealing portion, a and b are constants)
- the vent occurrence time may be automatically predicted according to the measurement of only the width of the remaining sealing portion.
- the determination unit 130 determines the vent occurrence time of the battery cell according to the measured width of the remaining sealing portion based on the correlation. width can be predicted.
- the vent time can be predicted by substituting the measured width of the remaining sealing part into the formula. Since the measurement unit 120 predicts the width of the remaining sealing portion at regular intervals, the determination unit 130 may also predict the vent occurrence time of the battery cell for each measurement period of the remaining sealing portion width.
- the system for predicting the vent occurrence time of the battery cell measures the width of the remaining sealing portion, compares it with pre-stored data to predict the vent occurrence time point, and if the vent does not occur, again at regular intervals, the remaining sealing portion
- the process of measuring the width can be repeated.
- FIG. 5 is a block diagram showing the configuration of a system for predicting a vent generation time of a battery cell according to another embodiment of the present invention
- FIG. 6 is a flowchart showing a process of learning a prediction result
- 7 is a schematic diagram showing a learning method by deep learning.
- the battery cell vent generation timing prediction system 200 may further include a learning unit 140 for learning the prediction result.
- the learning unit is divided into roles for convenience when compared to the calculation unit and the determination unit, and is composed of a computing device like the calculation unit and the determination unit, and can be performed in the same device as the calculation unit and the determination unit. there is.
- the present invention can further improve prediction accuracy by reflecting accurate or incorrect prediction results through machine learning or deep learning.
- the learning unit 140 may configure learning data for predicting a vent occurrence time.
- the learning data may be configured by updating a newly measured result in data previously stored in the storage unit.
- the learning unit 140 compares the predicted event occurrence time and the actual event occurrence time to verify the validity of the data. When the predicted vent occurrence time coincides with the actual vent occurrence time, the data is determined to be valid and is recorded in the storage unit 110 . If the predicted event occurrence time and the actual event occurrence time do not match, the data stored in the storage unit 110 is corrected and updated. At this time, it is possible to analyze the reason why the data is inconsistent by considering the stored data and the input experimental conditions (temperature of the battery cell, etc.) together.
- the learning unit configures learning data by updating the verification result in the storage unit 110 . In this way, the learning unit 140 may derive more accurate data through machine learning.
- the learning unit 140 may be configured as a deep neural network.
- a deep neural network is one of the deep learning (Machine Learning) models that classify input data based on learned data.
- DNN deep neural network
- a system or network that makes decisions based on data
- a deep neural network may include an input layer 141, one or more hidden layers 142, and an output layer 143.
- the training data is input to the input layer 141, and a resultant value calculated through the hidden layer and the output layer is compared with an actual value to inversely update the value of the weight. After all learning is completed, the result value can be obtained by inputting the information required for prediction.
- the hidden layer 142 may include a convolution layer, a pooling layer, and a fully connected layer.
- the convolution layer may extract a feature map from an image input to the input layer and perform a convolution operation.
- the pooling layer may be connected to the convolution layer to perform subsampling on the output of the convolution layer.
- the fully connected layer may be connected to the pooling layer to learn the subsampled output of the pooling layer and learn according to a category to be output to the output layer 323 .
- connection structure of each layer constituting the deep neural network may be formed by properly selecting a known algorithm, for example, a convolutional neural network (CNN) structure or a recurrent neural network (RNN) structure.
- CNN convolutional neural network
- RNN recurrent neural network
- Such a deep neural network may be implemented in one computer, or may be implemented through a network by connecting a plurality of computers.
- the learning unit 140 inputs the updated training data to the input layer 141 on the deep neural network.
- the input training data is output as a final output from the output layer 143 through the hidden layer 142 .
- the learning unit may learn newly updated training data by updating a weight according to a validation result of a prediction result.
- the determination unit 130 When the learning of the data is completed, the determination unit 130 newly derives a correlation between the width of the remaining sealing portion and the vent occurrence time according to the width of the remaining sealing portion from the learned data, and then the battery according to the width of the remaining sealing portion measured therefrom. The cell vent generation time is predicted. Thereafter, the validity of the prediction result is verified and the process of reflecting it is repeatedly performed, so that the accuracy of the prediction result can be further improved.
- the present invention provides a method for predicting the vent generation time of the battery cell using the vent generation time of the battery cell as described above.
- the method for predicting the vent occurrence time of the battery cell includes collecting data on the vent occurrence time according to the width of the remaining sealing part; Periodically measuring the width of the remaining sealing portion of the battery cell to be measured; And comparing the measured width of the remaining sealing portion with the collected data to predict a vent generation time of the battery cell to be measured; can include
- an image taken in the process of predicting and measuring a vent occurrence time for a plurality of battery cells in the storage unit, a width value of the remaining sealing part, and a vent occurrence time may be accumulated.
- the periodically measuring the width of the remaining sealing portion may include capturing an image or video of the terrace portion with a camera and calculating the width of the remaining sealing portion from the captured image or video.
- the photographing process may be performed in a state in which the battery cells are mounted on a jig.
- the width of the remaining sealing portion may be measured while the photographed image is displayed on the display device.
- the width of the remaining sealing portion While the measurement of the width of the remaining sealing portion is periodically performed until the vent occurs in the battery cell, data recorded at the time of occurrence of the vent according to the width of the remaining sealing portion may be stored in the storage unit. In this case, the width of the remaining sealing portion may be measured by shortening the period as the vent generation time approaches. In addition, the process may be carried out at a high temperature of 60 °C or more.
- the step of predicting the vent occurrence time of the battery cell to be measured may be performed by machine learning or deep learning, and derives a correlation between the width of the remaining sealing portion and the vent occurrence time accordingly, and It may include a process of periodically estimating the vent occurrence time of the battery cell to be measured according to the width of the remaining sealing portion measured based on the measured basis.
- the derivation of the correlation may be performed by regression analysis, and a specific method is as described above.
- the method for predicting a vent generation time of a battery cell according to the present invention may further include learning a prediction result.
- the step of learning the prediction result may include a process of configuring learning data by verifying validity of data by comparing a predicted event occurrence time and an actual event occurrence time, and updating the verification result to the data.
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Secondary Cells (AREA)
- Gas Exhaust Devices For Batteries (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
Abstract
Description
Claims (16)
- 파우치형 전지 케이스의 적어도 일측에 실링부를 포함하는 테라스부가 형성되고, 테라스부의 끝단에 전극 리드가 인출된 전지셀의 벤트 발생시점 예측 시스템에 있어서,잔여 실링부의 폭에 따른 벤트 발생시점에 대한 데이터를 수집하는 저장부;측정 대상 전지셀의 잔여 실링부의 폭을 주기적으로 측정하는 측정부; 및측정된 잔여 실링부의 폭과 상기 수집된 데이터를 비교하여 측정 대상 전지셀의 벤트 발생시점을 예측하는 판정부; 를 포함하는 전지셀의 벤트 발생시점 예측 시스템.
- 제1항에 있어서,상기 측정부는 상기 테라스부의 이미지 또는 영상을 촬영하는 카메라; 및촬영된 이미지 또는 영상에서 잔여 실링부의 폭을 산출하는 산출부; 를 포함하는 전지셀의 벤트 발생시점 예측 시스템.
- 제1항에 있어서,상기 측정부는 벤트 발생시점이 임박할수록 주기를 짧게 하여 잔여 실링부의 폭을 측정하는 전지셀의 벤트 발생시점 예측 시스템.
- 제1항에 있어서,상기 데이터의 수집 및 잔여 실링부의 폭 측정은,60℃ 이상의 고온에서 수행되는 전지셀의 벤트 발생시점 예측 방법.
- 제1항에 있어서,상기 판정부는 머신 러닝 또는 딥러닝을 통해 측정 대상 전지셀의 벤트 발생시점을 예측하는 전지셀의 벤트 발생시점 예측 시스템.
- 제5항에 있어서,상기 판정부는 상기 데이터로부터 잔여 실링부의 폭과 이에 따른 벤트 발생시점에 대한 상관 관계를 도출하는 전지셀의 벤트 발생시점 예측 시스템.
- 제6항에 있어서,상기 판정부는 상기 상관 관계에 근거하여, 측정된 잔여 실링부의 폭에 따른 전지셀의 벤트 발생시점을 잔여 실링부 폭의 측정 주기마다 예측하는 전지셀의 벤트 발생시점 예측 시스템.
- 제1항에 있어서,상기 예측 결과를 학습하기 위한 학습부를 더 포함하는 전지셀의 벤트 발생시점 예측 시스템.
- 제8항에 있어서,상기 학습부는 벤트 발생시점 예측을 위한 학습 데이터를 구성하고,상기 판정부는 상기 학습 데이터로부터 잔여 실링부의 폭과 이에 따른 벤트 발생시점에 대한 상관 관계를 새롭게 도출한 후, 이로부터 측정된 잔여 실링부의 폭에 따른 전지셀의 벤트 발생시점을 예측하는 전지셀의 벤트 발생시점 예측 시스템.
- 제8항에 있어서,상기 학습부는 예측된 벤트 발생시점과 실제 벤트 발생시점을 대비하여 데이터의 유효성을 검증하고,상기 저장부에 수집된 데이터에 검증 결과를 업데이트하여 학습 데이터를 구성하는 전지셀의 벤트 발생시점 예측 시스템.
- 제1항에 따른 전지셀의 벤트 발생시점 예측 시스템을 사용하여 전지셀의 벤트 발생시점을 예측하는 방법에 있어서,잔여 실링부의 폭에 따른 벤트 발생시점에 대한 데이터를 수집하는 단계;측정 대상 전지셀의 잔여 실링부의 폭을 주기적으로 측정하는 단계; 및측정된 잔여 실링부의 폭과 상기 수집된 데이터를 비교하여 측정 대상 전지셀의 벤트 발생시점을 예측하는 단계; 를 포함하는 전지셀의 벤트 발생시점 예측 방법.
- 제11항에 있어서,상기 잔여 실링부의 폭을 주기적으로 측정하는 단계는,카메라로 테라스부의 이미지 또는 영상을 촬영하고, 촬영된 이미지 또는 영상에서 잔여 실링부의 폭을 산출하는 과정을 포함하는 전지셀의 벤트 발생시점 예측 방법.
- 제11항에 있어서,상기 측정 대상 전지셀의 벤트 발생시점을 예측하는 단계는,잔여 실링부의 폭과 이에 따른 벤트 발생시점에 대한 상관 관계를 도출하고, 상관 관계에 근거하여 측정된 잔여 실링부의 폭에 따른 측정 대상 전지셀의 벤트 발생시점을 주기적으로 예측하는 과정을 포함하는 전지셀의 벤트 발생시점 예측 방법.
- 제11항에 있어서,예측 결과를 학습하는 단계를 더 포함하는 전지셀의 벤트 발생시점 예측 방법.
- 제14항에 있어서,상기 예측 결과를 학습하는 단계는,예측된 벤트 발생시점과 실제 벤트 발생시점을 대비하여 데이터의 유효성을 검증하고, 상기 데이터에 검증 결과를 업데이트하여 학습 데이터를 구성하는 전지셀의 벤트 발생시점 예측 방법.
- 제15항에 있어서,상기 측정 대상 전지셀의 벤트 발생시점을 예측하는 단계는,상기 학습 데이터로부터 잔여 실링부의 폭과 이에 따른 벤트 발생시점에 대한 상관 관계를 새롭게 도출한 후, 이로부터 측정된 잔여 실링부의 폭에 따른 전지셀의 벤트 발생시점을 예측하는 전지셀의 벤트 발생시점 예측 방법.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP22833616.0A EP4175009A1 (en) | 2021-07-01 | 2022-06-29 | Prediction system and prediction method for time of occurrence of vent in battery cell |
CN202280006100.8A CN116261648A (zh) | 2021-07-01 | 2022-06-29 | 用于预测电池单体的排气发生时间的系统及方法 |
JP2023506058A JP7456694B2 (ja) | 2021-07-01 | 2022-06-29 | 電池セルのベント発生時点予測システムおよび予測方法 |
US18/018,756 US20230299366A1 (en) | 2021-07-01 | 2022-06-29 | System and method for predicting vent occurence time of battery cell |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020210086372A KR20230005534A (ko) | 2021-07-01 | 2021-07-01 | 전지셀의 벤트 발생시점 예측 시스템 및 예측방법 |
KR10-2021-0086372 | 2021-07-01 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023277561A1 true WO2023277561A1 (ko) | 2023-01-05 |
Family
ID=84690490
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2022/009293 WO2023277561A1 (ko) | 2021-07-01 | 2022-06-29 | 전지셀의 벤트 발생시점 예측 시스템 및 예측방법 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20230299366A1 (ko) |
EP (1) | EP4175009A1 (ko) |
JP (1) | JP7456694B2 (ko) |
KR (1) | KR20230005534A (ko) |
CN (1) | CN116261648A (ko) |
WO (1) | WO2023277561A1 (ko) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101167096B1 (ko) * | 2011-12-20 | 2012-07-20 | 주식회사 스마트하이텍 | 팩 외관 검사 장치 및 방법 |
KR20180000416A (ko) * | 2016-06-23 | 2018-01-03 | 주식회사 엘지화학 | 이차전지용 파우치 외장재 실링부 폭 측정 지그 |
JP6370902B2 (ja) * | 2014-06-24 | 2018-08-15 | 株式会社東芝 | 蓄電池システムの劣化制御装置及びその方法 |
KR102125238B1 (ko) | 2016-01-06 | 2020-06-22 | 주식회사 엘지화학 | 전지셀의 두께 팽창량 추정 장치 및 그것을 이용한 추정 방법 |
KR20210016828A (ko) * | 2019-08-05 | 2021-02-17 | 주식회사 엘지화학 | 배터리 관리 장치, 배터리 관리 방법 및 배터리 팩 |
KR20210086372A (ko) | 2019-12-30 | 2021-07-08 | 삼성전자주식회사 | 디스플레이 장치 및 그 조립 방법 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102192676B1 (ko) | 2017-01-24 | 2020-12-17 | 주식회사 엘지화학 | 배터리 모듈 변형 예측 장치 |
-
2021
- 2021-07-01 KR KR1020210086372A patent/KR20230005534A/ko not_active Application Discontinuation
-
2022
- 2022-06-29 JP JP2023506058A patent/JP7456694B2/ja active Active
- 2022-06-29 US US18/018,756 patent/US20230299366A1/en active Pending
- 2022-06-29 CN CN202280006100.8A patent/CN116261648A/zh active Pending
- 2022-06-29 WO PCT/KR2022/009293 patent/WO2023277561A1/ko active Application Filing
- 2022-06-29 EP EP22833616.0A patent/EP4175009A1/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101167096B1 (ko) * | 2011-12-20 | 2012-07-20 | 주식회사 스마트하이텍 | 팩 외관 검사 장치 및 방법 |
JP6370902B2 (ja) * | 2014-06-24 | 2018-08-15 | 株式会社東芝 | 蓄電池システムの劣化制御装置及びその方法 |
KR102125238B1 (ko) | 2016-01-06 | 2020-06-22 | 주식회사 엘지화학 | 전지셀의 두께 팽창량 추정 장치 및 그것을 이용한 추정 방법 |
KR20180000416A (ko) * | 2016-06-23 | 2018-01-03 | 주식회사 엘지화학 | 이차전지용 파우치 외장재 실링부 폭 측정 지그 |
KR20210016828A (ko) * | 2019-08-05 | 2021-02-17 | 주식회사 엘지화학 | 배터리 관리 장치, 배터리 관리 방법 및 배터리 팩 |
KR20210086372A (ko) | 2019-12-30 | 2021-07-08 | 삼성전자주식회사 | 디스플레이 장치 및 그 조립 방법 |
Also Published As
Publication number | Publication date |
---|---|
EP4175009A1 (en) | 2023-05-03 |
JP2023537694A (ja) | 2023-09-05 |
CN116261648A (zh) | 2023-06-13 |
KR20230005534A (ko) | 2023-01-10 |
JP7456694B2 (ja) | 2024-03-27 |
US20230299366A1 (en) | 2023-09-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018190508A1 (ko) | 노이즈를 반영한 배터리 잔존 용량 산출 장치 및 방법 | |
WO2017061728A1 (ko) | 전지셀의 팽창을 감지하기 위한 프로브를 포함하고 있는 전지모듈 | |
WO2020085722A1 (ko) | 중대형 셀 모듈의 폭발 압력 예측 시스템 및 이를 이용한 중대형 셀 모듈의 폭발 압력 예측 방법 | |
WO2021015436A1 (ko) | 차량 배터리 화재 감지 장치 및 감지 방법 | |
WO2022055080A1 (ko) | 배터리의 충전상태를 추정하는 방법 | |
WO2020262787A1 (ko) | 내부 단락 셀 검출 방법 | |
WO2020262789A1 (ko) | 이상 배터리 셀 검출 방법 | |
WO2014084677A1 (ko) | 배터리 사용 환경과 사용 이력을 관리하는 장치 및 방법 | |
WO2020085667A1 (ko) | 이차 전지의 내부 가스 발생 가속 구간 판단 방법 | |
WO2021230536A1 (ko) | 이차전지 | |
WO2020017907A1 (ko) | 전극의 오정렬 검출 시스템 및 방법 | |
WO2022075618A1 (ko) | 배터리 장치 및 배터리 출력 예측 방법 | |
WO2022154354A1 (ko) | 배터리 시스템 진단 장치 및 방법 | |
WO2021020817A1 (ko) | 배터리 상태 예측 장치 및 배터리 상태 예측 방법 | |
WO2020166840A1 (ko) | 배터리 셀 이상 판단 장치 및 방법 | |
WO2023277561A1 (ko) | 전지셀의 벤트 발생시점 예측 시스템 및 예측방법 | |
WO2022030751A1 (ko) | 배터리 팩의 시뮬레이션 방법 | |
WO2021025295A1 (ko) | 배터리 관리 장치, 배터리 관리 방법 및 배터리 팩 | |
WO2023014056A1 (ko) | 전지 셀의 전극 탭 단선 검사장치 및 단선 검사방법 | |
WO2023068580A1 (ko) | 열 폭주 감지용 압력 센서를 구비한 배터리 모듈 | |
WO2022085950A1 (ko) | 배터리 장치 및 저항 상태 추정 방법 | |
WO2022019703A1 (ko) | 배터리를 진단하기 위한 장치 및 그 방법 | |
WO2023128472A1 (ko) | 가스 벤팅의 조기 검출이 가능한 전지 모듈, 전지 팩 및 가스 벤팅의 조기 검출 방법 | |
WO2023136584A1 (ko) | 모니터링 장치 및 그것의 동작 방법 | |
WO2024085396A1 (ko) | 모니터링 시스템 및 그것의 동작 방법 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2023506058 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202317006096 Country of ref document: IN |
|
ENP | Entry into the national phase |
Ref document number: 2022833616 Country of ref document: EP Effective date: 20230125 |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22833616 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |