WO2023018070A1 - 배터리 관리 장치 및 이를 포함하는 배터리 검사 시스템 - Google Patents
배터리 관리 장치 및 이를 포함하는 배터리 검사 시스템 Download PDFInfo
- Publication number
- WO2023018070A1 WO2023018070A1 PCT/KR2022/011061 KR2022011061W WO2023018070A1 WO 2023018070 A1 WO2023018070 A1 WO 2023018070A1 KR 2022011061 W KR2022011061 W KR 2022011061W WO 2023018070 A1 WO2023018070 A1 WO 2023018070A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- battery
- state
- management device
- data
- state data
- Prior art date
Links
- 238000007689 inspection Methods 0.000 title claims description 18
- 238000004891 communication Methods 0.000 claims abstract description 12
- 238000010801 machine learning Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims description 50
- 230000006403 short-term memory Effects 0.000 claims description 16
- 238000013450 outlier detection Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 9
- 230000036541 health Effects 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 8
- 230000007787 long-term memory Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 4
- 229910001416 lithium ion Inorganic materials 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 238000011017 operating method Methods 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 229920000642 polymer Polymers 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- OJIJEKBXJYRIBZ-UHFFFAOYSA-N cadmium nickel Chemical compound [Ni].[Cd] OJIJEKBXJYRIBZ-UHFFFAOYSA-N 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- PXHVJJICTQNCMI-UHFFFAOYSA-N nickel Substances [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 1
- -1 nickel hydrogen Chemical class 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Images
Classifications
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
- B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/165—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values
- G01R19/16566—Circuits and arrangements for comparing voltage or current with one or several thresholds and for indicating the result not covered by subgroups G01R19/16504, G01R19/16528, G01R19/16533
-
- 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]
- G01R31/3644—Constructional arrangements
- G01R31/3648—Constructional arrangements comprising digital calculation means, e.g. for performing an algorithm
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
- G01R31/3842—Arrangements for monitoring battery or accumulator variables, e.g. SoC combining voltage and current measurements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- Embodiments disclosed in this document relate to a battery management device and a battery inspection system including the same.
- Electric vehicles receive power from the outside to charge the battery, and then drive the motor with the voltage charged in the battery to obtain power.
- Electric vehicle batteries can generate heat due to chemical reactions that occur during the process of charging and discharging electricity, and this heat can damage the performance and lifespan of the battery. Therefore, a battery management system (BMS) that monitors the temperature, voltage, and current of the battery is driven to diagnose the state of the battery.
- BMS battery management system
- One object of the embodiments disclosed in this document is a battery management device that can improve the efficiency of the battery management device and reduce infrastructure installation costs and communication costs by precisely analyzing only battery data determined to be abnormal, and a battery including the same It is to provide inspection system.
- An apparatus for managing a battery includes a first controller that obtains state data including a measured value of a state of a battery, and applies at least a part of the state data to machine learning to determine the state of the battery.
- a second controller that generates predicted prediction data and compares the predicted data with state data of the battery to determine the state of the battery, and a communication unit that transmits the state data to a server based on a result of determining the state of the battery can include
- the second controller may compress the state data acquired during a predetermined period of time before and after the time when the battery is determined to be in an abnormal state.
- the communication unit may transmit state data of the compressed battery to the server.
- the measured value includes the cumulatively measured voltage, current, and temperature of the battery
- the state data includes the measured value and the SOH (State of the battery) calculated based on the measured value. health) may be included.
- the prediction data includes the voltage of the battery
- the second controller determines past data included in the state data and current and temperature of the battery measured at a present time included in the state data.
- the voltage of the battery may be predicted by applying the machine learning model.
- the second controller may predict the voltage of the battery by applying the state data to a Long Short Term Memory (LSTM) algorithm.
- LSTM Long Short Term Memory
- the second controller may generate an anomaly score by applying the state data and the predicted data to an anomaly detection algorithm.
- the second controller may determine that the battery is in an abnormal state when a ratio of abnormal values that are equal to or greater than a threshold value among the abnormal values generated for a predetermined time period is equal to or greater than a predetermined rate.
- a battery inspection system applies at least a part of state data including a measurement value of a state of a battery to machine learning to generate prediction data that predicts the state of the battery, and generates prediction data that predicts the state of the battery.
- a battery management device that compares data and state data of the battery to determine the state of the battery and transmits the state data to a server based on the determination result, and whether or not the battery is in an abnormal state based on the state data of the battery It may include a server that determines.
- the battery management device may compress the state data acquired during a predetermined time before and after the time when the battery is determined to be in an abnormal state and transmit the compressed state data to the server.
- the measured value includes the cumulatively measured voltage, current, and temperature of the battery
- the state data includes the measured value and the SOH (State of the battery) calculated based on the measured value. health) may be included.
- the battery management device determines the past data included in the state data and the current and temperature of the battery measured at the present time included in the state data by using the Long Short Term Memory (LSTM) algorithm
- the voltage of the battery can be predicted by applying to .
- LSTM Long Short Term Memory
- the battery management device generates an anomaly score by applying the state data and the prediction data to an anomaly detection algorithm, and an outlier value that is greater than or equal to a threshold value among the anomaly scores generated for a predetermined period of time.
- the ratio of is greater than a certain ratio, the battery may be determined to be in an abnormal state.
- the server may extract a false alarm, which is a case where the battery management device determines that the battery is in an abnormal state even though the battery is not actually in an abnormal state.
- the server may measure the SOH value of the battery and the threshold value of the outlier detection algorithm and transmit the measured value to the battery management device.
- the battery management device may update the long and short term memory algorithm and the outlier detection algorithm based on the SOH value and the threshold value received from the server.
- FIG. 1 is a diagram showing the configuration of a battery pack according to an embodiment disclosed in this document.
- FIG. 2 is a block diagram showing the configuration of a battery management device according to an embodiment disclosed in this document.
- FIG. 3 is a diagram for generally describing a battery management device according to an exemplary embodiment disclosed in this document.
- FIG. 4 is a block diagram showing the configuration of a battery inspection system according to an embodiment disclosed in this document.
- FIG. 5 is a flowchart illustrating an operating method of a battery test system according to an embodiment disclosed in this document.
- FIG. 1 is a diagram showing a battery pack according to an embodiment disclosed in this document.
- a battery pack 100 may include a battery module 110 , a battery management device 120 and a relay 130 .
- the battery module 110 may include a first battery cell 111 , a second battery cell 112 , a third battery cell 113 , and a fourth battery cell 114 . Although the number of battery cells is illustrated in FIG. 1 as four, it is not limited thereto, and the battery module 110 may include n (n is a natural number equal to or greater than 2) battery cells.
- the battery module 110 may supply power to a target device (not shown). To this end, the battery module 110 may be electrically connected to the target device.
- the target device may include an electrical, electronic, or mechanical device operating by receiving power from the battery pack 100 including the plurality of battery cells 111, 112, 113, and 114, for example , the target device may be an electric vehicle (EV), but is not limited thereto.
- EV electric vehicle
- the plurality of battery cells 111, 112, 113, and 114 include a lithium ion (Li-iOn) battery, a lithium ion polymer (Li-iOn polymer) battery, a nickel cadmium (Ni-Cd) battery, a nickel hydrogen (Ni-MH) It may be a battery or the like, but is not limited thereto. Meanwhile, although FIG. 1 shows a case in which one battery module 110 is provided, a plurality of battery modules 110 may be configured according to embodiments.
- the battery management system (BMS) 120 may manage and/or control the state and/or operation of the battery module 110 .
- the battery management device 120 may manage and/or control states and/or operations of the plurality of battery cells 111, 112, 113, and 114 included in the battery module 110.
- the battery management device 120 may manage charging and/or discharging of the battery module 110 .
- the battery management device 120 may monitor the battery module 110 and/or the voltage, current, temperature, etc. of each of the plurality of battery cells 111, 112, 113, and 114 included in the battery module 110. there is.
- sensors or various measuring modules may be additionally installed in the battery module 110, a charge/discharge path, or an arbitrary position such as the battery module 110.
- the battery management device 120 determines a parameter indicating the state of the battery module 110, for example, SOC (State of Charge) or SOH (State of Health), based on measured values such as monitored voltage, current, and temperature. can be calculated
- the battery management device 120 may control the operation of the relay 130 .
- the battery management device 120 may short the relay 130 to supply power to the target device.
- the battery management device 120 may short-circuit the relay 130 when a charging device is connected to the battery pack 100 .
- the battery management device 120 may calculate the cell balancing time of each of the plurality of battery cells 111 , 112 , 113 , and 114 .
- the cell balancing time may be defined as a time required for balancing battery cells.
- the battery management device 120 may calculate a cell balancing time based on a state of charge (SOC), battery capacity, and balancing efficiency of each of the plurality of battery cells 111, 112, 113, and 114.
- SOC state of charge
- FIG. 2 is a block diagram showing the configuration of a battery management device according to an embodiment disclosed in this document.
- 3 is a diagram for generally describing a battery management device according to an exemplary embodiment disclosed in this document.
- the battery management device 120 may include a first controller 121 , a second controller 122 and a communication unit 123 .
- the battery module 100 may include a plurality of battery cells 111 , 112 , 113 , and 114 , but hereinafter, the first battery cell 110 will be described as an example.
- the first controller 121 may obtain state data including a measurement value obtained by measuring the state of the first battery cell 111 .
- the measured value may include cumulatively measured voltage, current, and temperature of the first battery cell 111 .
- the state data includes a measured value including the measured voltage, current, and temperature of the first battery cell 111 and a state of health (SOH) of the first battery cell 111 calculated based on the measured value.
- SOH state of health
- the first controller 121 may obtain measurement values obtained by measuring voltage, current, and temperature of the first battery cell 111 from time (t-N) to time (t-1), and may obtain the measured values. Based on this, the SOH from (t-N) time to (t-1) time of the first battery cell 111 may be obtained.
- N can be defined as an arbitrary constant value representing the amount of change in the variable t, which means time.
- the first controller 121 determines the voltage of the first battery cell 111 at time (tN) ( ), current ( ), temperature( ) to obtain the SOH value of the first battery cell 111 at time (tN), and the voltage of the first battery cell 111 at time (t-(N-1)) ( ), current ( ), temperature( ), the SOH value of the first battery cell 111 at time (t ⁇ (N ⁇ 1)) may be obtained. That is, the first controller 121 may obtain past state data of the first battery cell 111 from time (tN) to time (t ⁇ 1).
- the first controller 121 determines the current (current) of the first battery cell 111 measured at the current time point (t). ) and temperature ( ) can be obtained.
- the second controller 122 may generate prediction data that predicts the state of the first battery cell 111 by applying at least a portion of the state data to machine learning.
- the predicted data is the voltage of the first battery cell 111 ( ) may be included.
- the second controller 122 applies the past data included in the state data and the current and temperature of the first battery cell 111 measured at the present time included in the state data to a machine learning model of a time series analysis structure
- the voltage of the first battery cell 111 may be predicted.
- a time series can be defined as a sequence arranged at regular time intervals according to the passage of time.
- the machine learning model of the time series analysis structure may include a Long Short Term Memory (LSTM) algorithm.
- the long-term short-term memory algorithm is one of artificial neural networks, and can be defined as an improved structure of a recurrent neural network (RNN) to reflect long-term characteristics.
- RNN recurrent neural network
- the long-short-term memory algorithm is mainly applied to problems of time-series data representing phenomena that change with time.
- the long and short term memory algorithm can predict what the n+1th data will be for the measurement time series data of an object having a length of n.
- the second controller 122 measures the voltage, current, temperature and SOH data of the first battery cell 111 from time (tN) to time (t-1) and the first battery cell ( Voltage ( ) can be predicted. That is, the second controller 122 applies the state data of the first battery cell 111 from time (tN) to time (t-1) to the long and short-term memory algorithm to apply the first battery cell ( 111) may generate prediction data predicting the voltage.
- the second controller 122 may determine the state of the first battery cell 111 by comparing prediction data with state data. Specifically, the second controller 122 calculates the predicted voltage of the first battery cell 111 at (t) time ( ) and the measured voltage at (t) time of the first battery cell 111 ( ) can be applied to the anomaly detection algorithm to generate an anomaly score to analyze whether the battery is in an abnormal state.
- the outlier detection algorithm may be defined as an artificial intelligence model that analyzes the anomaly score of an object showing patterns and characteristics different from normal data.
- the second controller 122 calculates the predicted voltage of the first battery cell 111 at time (t) ( ) and the measured voltage at (t) time of the first battery cell 111 ( ) can create an outlier that is the difference.
- the second controller 122 may determine that the first battery cell 111 is in an abnormal state when a ratio of abnormal values greater than or equal to a threshold value among abnormal values generated for a predetermined period of time is equal to or greater than a predetermined rate. That is, the second controller 122 controls the predicted voltage of the first battery cell 111 generated for a predetermined time ( ) of the measured voltage of the first battery cell 111 ( ), the first battery cell 111 may be determined to be in an abnormal state when the ratio of the outlier values exceeding the threshold value is maintained for several seconds to several tens of seconds.
- the second controller 122 may compress state data acquired during a predetermined time before and after the point in time when the first battery cell 111 is determined to be in an abnormal state.
- the communication unit 123 may transmit state data to the server 200 based on a result of determining the state of the first battery cell 111 of the second controller 122 . That is, when the first battery cell 111 is determined to be in an abnormal state, the communication unit 123 transmits compressed state data of the first battery cell 111 to the server 200 using Over The Air (OTA) technology.
- OTA Over The Air
- the OTA technology is a firmware update method, and can be defined as a technology that wirelessly updates the firmware using Wi-Fi without connecting to a computer.
- the battery management device 120 and the battery inspection system 1000 transmit battery data to the server so that the battery management device 120 It is possible to increase diagnosis efficiency and prevent unnecessary power supply to the battery management device 120 .
- the battery management device 120 and the battery inspection system 1000 pre-analyze the battery data using a voltage prediction model designed in the battery management device, and transmit the battery data to a server having abundant computing resources when an anomaly is detected.
- a voltage prediction model designed in the battery management device By performing precise analysis, it is possible to reduce communication resources and lighten the storage and computing power of the cloud computer included in the server by drastically reducing the data transmitted to the server while precisely analyzing the anomaly of the battery.
- the battery management device 120 and the battery inspection system 1000 may transmit minimum necessary battery data to the server without data loss, thereby reducing server infrastructure investment costs and network costs.
- FIG. 4 is a block diagram showing the configuration of a battery inspection system according to an embodiment disclosed in this document.
- 5 is a flowchart illustrating an operating method of a battery test system according to an embodiment disclosed in this document.
- a battery inspection system 1000 may include a battery management device 120 and a server 200 .
- the battery management device 120 may be substantially the same as the battery management device 120 described with reference to FIGS. 1 to 3 , it will be briefly described below to avoid duplication of description.
- the operating method of the battery test system includes obtaining, by the battery management device 120, state data including a measurement value obtained by measuring the state of the first battery cell 111 (S101), the battery management device ( 120) generating prediction data by applying the state data to the long-term and short-term memory algorithm (S102), and the battery management device 120 inputs the prediction data and state data to the outlier detection algorithm to determine the state of the first battery cell 111 (S103), the battery management device 120 determining whether the first battery cell 111 is in an abnormal state (S104), the battery management device when the first battery cell 111 is in an abnormal state (120) transmitting the state data of the first battery cell 111 to the server 200 (S105), the server 200 extracting false alarms (S106), the server 200 frequency of false alarms Determining whether is greater than or equal to a threshold frequency (S107).
- state data including a measurement value obtained by measuring the state of the first battery cell 111 (S101)
- the battery management device ( 120) generating prediction data by applying the state data to the long
- the server 200 measures the SOH value of the first battery cell 111 and the threshold value of the outlier detection algorithm to manage the battery. It may include transmitting to the device 120 (S108) and applying the SOH value and the threshold value received from the server 200 by the battery management device 120 to a short-term memory algorithm and an outlier detection algorithm (S109). there is.
- the battery management device 120 may obtain state data including a measurement value obtained by measuring the state of the first battery cell 111 .
- the state data may include a measured value including the measured voltage, current, and temperature of the first battery cell 111 and a State of Health (SOH) of the first battery cell 111 calculated based on the measured value.
- SOH State of Health
- the battery management device 120 may obtain past state data of the first battery cell 111 from time (t-N) to time (t-1).
- the battery management device 120 may obtain current and temperature measurement values of the first battery cell 111 measured at the current point in time t.
- the battery management device 120 may generate prediction data that predicts the state of the first battery cell 111 by applying at least a portion of the state data of the first battery cell 111 to machine learning.
- step S101 the battery management device 120 determines the voltage, current, temperature, and SOH data of the first battery cell 111 from time (tN) to time (t-1) and the current time point (t).
- the voltage ( ) can be predicted.
- the battery management device 120 may determine the state of the first battery cell 111 by comparing prediction data with state data. In detail, the battery management device 120 calculates the predicted voltage of the first battery cell 111 at time (t) ( ) and the measured voltage at (t) time of the first battery cell 111 ( ) can be applied to the anomaly detection algorithm to generate an anomaly score to analyze whether the battery is in an abnormal state.
- the battery management device 120 may determine that the first battery cell 111 is in an abnormal state when the ratio of outliers that are equal to or greater than a threshold among the outliers generated for a predetermined period of time is equal to or greater than a predetermined ratio.
- step S105 when the first battery cell 111 is determined to be in an abnormal state, the battery management device 120 compresses state data acquired for a predetermined time before and after the point in time when the first battery cell 111 is determined to be in an abnormal state. and can be transmitted to the server 200.
- the server 200 may be defined as a determination device that receives state data of the first battery cell 111 and determines whether the first battery cell 111 is defective.
- the server 200 may include, for example, cloud computing technology.
- the server 200 provides a false alarm when the first battery cell 111 is determined to be in an abnormal state even though it is not actually in an abnormal state based on the state data of the first battery cell 111 determined by the battery management device 120 ( It can include an artificial intelligence model that extracts false alarms.
- step S106 when the battery management device 120 compresses the state data of the first battery cell 111 obtained during a predetermined time before and after the time when the abnormal state is determined and transmits the compressed data to the server 200, the server 200 Compressed state data transmitted by the battery management device 120 may be received.
- step S106 the server 200 analyzes the compressed data received from the battery management device 120, state data obtained for a predetermined time before and after the time when the abnormal state is determined, so that the first battery cell 111 is actually It is possible to extract a false alarm, which is a case where it is judged to be an abnormal state even though it is not an abnormal state.
- step S107 the server 200 may determine whether the frequency of false alarms is greater than or equal to a threshold frequency.
- step S108 when the frequency of false alarms is greater than or equal to the threshold frequency, the server 200 recalculates the SOH value of the first battery cell 111 included in the battery management device 120 and resets the threshold value of the outlier detection algorithm. and can be transmitted to the battery management device 120.
- step S108 the server 200 identifies the cause of the false alarm of the first battery cell 111 as the SOH value of the first battery cell 111 input to the short-term memory algorithm of the battery management device 120 and the abnormal value. It can be analyzed as the threshold of the detection algorithm.
- the long-term and short-term memory algorithm of the battery management device 120 is based on measured values of the voltage, current, and temperature of the first battery cell 111 as past data included in the state data of the first battery cell 111 and the measured values.
- the SOH value of the first battery cell 111 is input as . Therefore, when an error occurs in the process of the battery management device 120 calculating the SOH value of the first battery cell 111 based on the voltage, current, and temperature of the first battery cell 111, an error occurs in the short-term memory algorithm. may occur, and such an error may create a false alarm of the battery test system 1000. Accordingly, the server 200 may recalculate the SOH value of the first battery cell 111 input to the battery management device 120 and transmit it to the battery management device 120 .
- the server 200 may analyze the cause of the false alarm of the first battery cell 111 as a threshold value of the outlier detection algorithm of the battery management device 120 .
- the battery management device 120 uses the outlier detection algorithm to predict the voltage of the first battery cell 111 at time (t) ( ) and the measured voltage at (t) time of the first battery cell 111 ( ), and if the ratio of the outliers that are equal to or greater than the threshold value is greater than or equal to a predetermined ratio, the first battery cell 111 may be determined to be in an abnormal state. Therefore, when the battery management device 120 classifies an abnormal value as an abnormal value, an error may occur in determining the abnormal state of the first battery cell 111 of the battery management device 120, and this error may occur in the battery management device 120. The inspection system 1000 may generate false alarms. Therefore, the server 200 may reset the threshold value of the anomaly detection algorithm input to the battery management device 120 and transmit it to the battery management device 120 .
- step S109 when receiving the SOH value of the first battery cell 111 and the threshold value of the outlier detection algorithm from the server 200, the battery management device 120 may update the long and short term memory algorithm and the outlier detection algorithm. .
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Sustainable Energy (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Sustainable Development (AREA)
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
Description
Claims (16)
- 배터리의 상태를 측정한 측정값을 포함하는 상태 데이터를 획득하는 제1 컨트롤러;상기 상태 데이터의 적어도 일부를 기계 학습에 적용하여 상기 배터리의 상태를 예측한 예측 데이터를 생성하고, 상기 예측 데이터와 상기 배터리의 상태 데이터를 비교하여 상기 배터리의 상태를 판단하는 제2 컨트롤러; 및상기 배터리의 상태를 판단한 결과에 기초하여 상기 상태 데이터를 서버에 전송하는 통신부를 포함하는 배터리 관리 장치.
- 제 1 항에 있어서,상기 제2 컨트롤러는 상기 배터리가 이상 상태로 판단되는 경우 상기 배터리가 이상 상태로 판단되는 시점 전후의 소정 시간 동안에 획득된 상기 상태 데이터를 압축하는 것을 특징으로 하는 배터리 관리 장치.
- 제2 항에 있어서,상기 통신부는 상기 압축된 배터리의 상태 데이터를 상기 서버에 전송하는 것을 특징으로 하는 배터리 관리 장치.
- 제1 항에 있어서,상기 측정값은 누적적으로 측정된 상기 배터리의 전압, 전류 및 온도를 포함하고, 상기 상태 데이터는 상기 측정값 및 상기 측정값을 기초로 산출된 상기 배터리의 SOH(State of Health)를 포함하는 것을 특징으로 하는 배터리 관리 장치.
- 제4 항에 있어서,상기 예측 데이터는 상기 배터리의 전압을 포함하고,상기 제2 컨트롤러는 상기 상태 데이터에 포함된 과거 데이터 및 상기 상태 데이터에 포함된 현 시점에 측정된 상기 배터리의 전류 및 온도를 상기 기계 학습 모델에 적용하여 상기 배터리의 전압을 예측하는 것을 특징으로 하는 배터리 관리 장치.
- 제5 항에 있어서,상기 제2 컨트롤러는 상기 상태 데이터를 장단기 메모리(LSTM, Long Short Term Memory) 알고리즘에 적용하여 상기 배터리의 전압을 예측하는 것을 특징으로 하는 배터리 관리 장치.
- 제4 항에 있어서,상기 제2 컨트롤러는 상기 상태 데이터와 상기 예측 데이터를 이상치 탐지(Anomaly Detection) 알고리즘에 적용하여 이상치(Anomaly Score)를 생성하는 것을 특징으로 하는 배터리 관리 장치.
- 제7 항에 있어서,상기 제2 컨트롤러는 소정의 시간 동안 생성된 상기 이상치 중 임계값 이상인 이상치의 비율이 일정 비율 이상인 경우 상기 배터리를 이상 상태로 판단하는 것을 특징으로 하는 배터리 관리 장치.
- 배터리의 상태를 측정한 측정값을 포함하는 상태 데이터의 적어도 일부를 기계 학습에 적용하여 상기 배터리의 상태를 예측한 예측 데이터를 생성하고, 상기 예측 데이터와 상기 배터리의 상태 데이터를 비교하여 상기 배터리의 상태를 판단하고, 상기 판단 결과에 기초하여 상기 상태 데이터를 서버에 전송하는 배터리 관리 장치; 및상기 배터리의 상태 데이터를 기초로 상기 배터리의 이상 상태 여부를 판단하는 서버를 포함하는 배터리 검사 시스템.
- 제9 항에 있어서,상기 배터리 관리 장치는 상기 배터리가 이상 상태로 판단되는 경우 상기 배터리가 이상 상태로 판단되는 시점 전후의 소정 시간 동안에 획득된 상기 상태 데이터를 압축하여 상기 서버에 전송하는 것을 특징으로 하는 배터리 검사 시스템.
- 제9 항에 있어서,상기 측정값은 누적적으로 측정된 상기 배터리의 전압, 전류 및 온도를 포함하고, 상기 상태 데이터는 상기 측정값 및 상기 측정값을 기초로 산출된 상기 배터리의 SOH(State of Health)를 포함하는 것을 특징으로 하는 배터리 검사 시스템.
- 제11 항에 있어서,상기 배터리 관리 장치는 상기 상태 데이터에 포함된 과거 데이터 및 상기 상태 데이터에 포함된 현 시점에 측정된 상기 배터리의 전류 및 온도를 상기 장단기 메모리(LSTM, Long Short Term Memory) 알고리즘에 적용하여 상기 배터리의 전압을 예측하는 것을 특징으로 하는 배터리 검사 시스템.
- 제11 항에 있어서,상기 배터리 관리 장치는 상기 상태 데이터와 상기 예측 데이터를 이상치 탐지(Anomaly Detection) 알고리즘에 적용하여 이상치(Anomaly Score)를 생성하고, 소정 시간 동안 생성된 상기 이상치 중 임계값 이상인 이상치의 비율이 일정 비율 이상인 경우 상기 배터리를 이상 상태로 판단하는 것을 특징으로 하는 배터리 검사 시스템.
- 제13 항에 있어서,상기 서버는 상기 배터리 관리 장치에서 상기 배터리가 실제 이상 상태가 아님에도 이상 상태로 판단된 경우인 거짓 경보(False Alarm)를 추출하는 것을 특징으로 하는 배터리 검사 시스템.
- 제14 항에 있어서,상기 서버는 상기 거짓 경보의 빈도가 임계 빈도 이상인 경우, 상기 배터리의 상기 SOH 값 및 상기 이상치 탐지 알고리즘의 상기 임계값을 측정하여 상기 배터리 관리 장치로 전송하는 것을 특징으로 하는 배터리 검사 시스템.
- 제15 항에 있어서,상기 배터리 관리 장치는 상기 서버로부터 수신한 상기 SOH 값 및 상기 임계값을 기초로 장단기 메모리 알고리즘 및 상기 이상치 탐지 알고리즘을 업데이트 하는 것을 특징으로 하는 배터리 검사 시스템.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/290,263 US20240241180A1 (en) | 2021-08-13 | 2022-07-27 | Battery management apparatus and battery testing system including the same |
EP22856069.4A EP4386401A1 (en) | 2021-08-13 | 2022-07-27 | Battery management apparatus and battery inspection system including same |
JP2023569629A JP2024519755A (ja) | 2021-08-13 | 2022-07-27 | 電池管理装置およびそれを含む電池検査システム |
CN202280036595.9A CN117396767A (zh) | 2021-08-13 | 2022-07-27 | 电池管理装置和包括该电池管理装置的电池测试系统 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020210107250A KR20230025130A (ko) | 2021-08-13 | 2021-08-13 | 배터리 관리 장치 및 이를 포함하는 배터리 검사 시스템 |
KR10-2021-0107250 | 2021-08-13 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023018070A1 true WO2023018070A1 (ko) | 2023-02-16 |
Family
ID=85200252
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2022/011061 WO2023018070A1 (ko) | 2021-08-13 | 2022-07-27 | 배터리 관리 장치 및 이를 포함하는 배터리 검사 시스템 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20240241180A1 (ko) |
EP (1) | EP4386401A1 (ko) |
JP (1) | JP2024519755A (ko) |
KR (1) | KR20230025130A (ko) |
CN (1) | CN117396767A (ko) |
WO (1) | WO2023018070A1 (ko) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018530982A (ja) * | 2015-10-15 | 2018-10-18 | ジョンソン コントロールズ テクノロジー カンパニーJohnson Controls Technology Company | バッテリテスト結果を予測するためのバッテリテストシステム |
KR20200023672A (ko) * | 2018-08-14 | 2020-03-06 | 오토시맨틱스 주식회사 | 딥러닝을 이용한 전지 진단 방법 |
KR20200058998A (ko) * | 2018-11-20 | 2020-05-28 | 주식회사 엘지화학 | 배터리의 고장을 진단하기 위한 장치 및 방법과, 상기 장치를 포함하는 배터리팩 |
KR20200119383A (ko) * | 2019-03-26 | 2020-10-20 | 서강대학교산학협력단 | 인공 지능에 기반하여 배터리의 상태를 추정하는 장치 및 방법 |
KR20210024962A (ko) * | 2019-08-26 | 2021-03-08 | 오토시맨틱스 주식회사 | Ess 배터리의 상태진단 및 수명예측을 위한 장치 및 방법 |
-
2021
- 2021-08-13 KR KR1020210107250A patent/KR20230025130A/ko active Search and Examination
-
2022
- 2022-07-27 WO PCT/KR2022/011061 patent/WO2023018070A1/ko active Application Filing
- 2022-07-27 US US18/290,263 patent/US20240241180A1/en active Pending
- 2022-07-27 CN CN202280036595.9A patent/CN117396767A/zh active Pending
- 2022-07-27 EP EP22856069.4A patent/EP4386401A1/en active Pending
- 2022-07-27 JP JP2023569629A patent/JP2024519755A/ja active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018530982A (ja) * | 2015-10-15 | 2018-10-18 | ジョンソン コントロールズ テクノロジー カンパニーJohnson Controls Technology Company | バッテリテスト結果を予測するためのバッテリテストシステム |
KR20200023672A (ko) * | 2018-08-14 | 2020-03-06 | 오토시맨틱스 주식회사 | 딥러닝을 이용한 전지 진단 방법 |
KR20200058998A (ko) * | 2018-11-20 | 2020-05-28 | 주식회사 엘지화학 | 배터리의 고장을 진단하기 위한 장치 및 방법과, 상기 장치를 포함하는 배터리팩 |
KR20200119383A (ko) * | 2019-03-26 | 2020-10-20 | 서강대학교산학협력단 | 인공 지능에 기반하여 배터리의 상태를 추정하는 장치 및 방법 |
KR20210024962A (ko) * | 2019-08-26 | 2021-03-08 | 오토시맨틱스 주식회사 | Ess 배터리의 상태진단 및 수명예측을 위한 장치 및 방법 |
Also Published As
Publication number | Publication date |
---|---|
CN117396767A (zh) | 2024-01-12 |
KR20230025130A (ko) | 2023-02-21 |
JP2024519755A (ja) | 2024-05-21 |
EP4386401A1 (en) | 2024-06-19 |
US20240241180A1 (en) | 2024-07-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018190508A1 (ko) | 노이즈를 반영한 배터리 잔존 용량 산출 장치 및 방법 | |
WO2021125676A1 (ko) | 배터리 진단 장치 및 방법 | |
WO2021049753A1 (ko) | 배터리 진단 장치 및 방법 | |
WO2021006566A1 (ko) | 배터리 셀 진단 장치 및 방법 | |
WO2019083300A1 (en) | APPARATUS AND METHODS FOR IDENTIFYING ONE OR MORE ANOMALIES IN A RECHARGEABLE EQUIPMENT BATTERY AND CONNECTED COMPONENT (S) | |
WO2020262787A1 (ko) | 내부 단락 셀 검출 방법 | |
WO2021230533A1 (ko) | 배터리를 진단하기 위한 장치 및 그 방법 | |
WO2022019481A1 (ko) | 통신 오류의 원인을 진단하기 위한 슬레이브 bms, 마스터 bms 및 배터리 팩 | |
WO2021015501A1 (ko) | 배터리 저항 진단 장치 및 방법 | |
WO2022035153A1 (ko) | 배터리 용량 추정 장치 및 방법 | |
WO2022035149A1 (ko) | 배터리 이상 진단 장치 및 방법 | |
WO2022149824A1 (ko) | 배터리 관리 장치 및 방법 | |
WO2023287180A1 (ko) | 배터리 진단 장치, 배터리 팩, 전기 차량 및 배터리 진단 방법 | |
WO2023136512A1 (ko) | 배터리 충전 심도 산출 장치 및 그것의 동작 방법 | |
WO2023018070A1 (ko) | 배터리 관리 장치 및 이를 포함하는 배터리 검사 시스템 | |
WO2023013961A1 (ko) | 배터리 검사 장치 및 배터리 검사 시스템 | |
WO2022149822A1 (ko) | 배터리 관리 장치 및 방법 | |
WO2022035151A1 (ko) | 배터리 이상 진단 장치 및 방법 | |
WO2022265277A1 (ko) | 배터리 관리 장치 및 방법 | |
WO2022019703A1 (ko) | 배터리를 진단하기 위한 장치 및 그 방법 | |
WO2021125678A1 (ko) | 병렬 배터리 릴레이 진단 장치 및 방법 | |
WO2021149973A1 (ko) | 배터리 진단 시스템, 전력 시스템 및 배터리 진단 방법 | |
WO2021125674A1 (ko) | 배터리 진단 장치 및 방법 | |
WO2023132520A1 (ko) | 배터리 용량 예측 장치 및 그것의 동작 방법 | |
WO2023153765A1 (ko) | 배터리 관리 장치 및 그것의 동작 방법 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22856069 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023569629 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18290263 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202317077656 Country of ref document: IN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280036595.9 Country of ref document: CN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022856069 Country of ref document: EP Effective date: 20240313 |