[go: up one dir, main page]

WO2022102532A1 - Dispositif et procédé de traitement de données, dispositif et procédé de génération de modèle, et programme - Google Patents

Dispositif et procédé de traitement de données, dispositif et procédé de génération de modèle, et programme Download PDF

Info

Publication number
WO2022102532A1
WO2022102532A1 PCT/JP2021/040768 JP2021040768W WO2022102532A1 WO 2022102532 A1 WO2022102532 A1 WO 2022102532A1 JP 2021040768 W JP2021040768 W JP 2021040768W WO 2022102532 A1 WO2022102532 A1 WO 2022102532A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
input
output
value
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2021/040768
Other languages
English (en)
Japanese (ja)
Inventor
九廷 陳
秀徳 嶋脇
逸郎 林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Envision AESC Japan Ltd
Original Assignee
Envision AESC Japan Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Envision AESC Japan Ltd filed Critical Envision AESC Japan Ltd
Publication of WO2022102532A1 publication Critical patent/WO2022102532A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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

  • the present invention relates to a data processing device, a model generation device, a data processing method, a model generation method, and a program.
  • Patent Document 1 describes that learning using a neural network is used when estimating the state of a secondary battery.
  • model creator it is preferable for the model creator to be able to verify whether or not the model is created by himself / herself.
  • An example of an object of the present invention is to make it easier for a model creator to identify a model created by himself / herself.
  • an input data acquisition unit that acquires input data related to a measurement target
  • An output data generation unit that generates output data related to the measurement target by acquiring a model stored in the model storage unit and inputting the input data into the model. Equipped with The input data is based on the measurement results of at least one type of parameter indicating the state of the measurement target, and is composed of a plurality of input elements.
  • the output data includes a plurality of output elements, and the plurality of output elements indicate current or future estimates of parameters that indicate the state of the measurement target and are not used as the input data, and the input.
  • a data processing device is provided in which the output data becomes verification output data in which the value of the specific output element is within a predetermined range.
  • the training data acquisition department that acquires training data
  • a model generation unit that generates the model using the training data, Equipped with The training data is The first input data in which all the input elements are in the range of values that can be taken as the input element, and the first output data in which all the output elements are in the range of values that can be taken as the output element.
  • the first training data including The value of the specific input element is outside the range of values that can be taken as the specific input element, and the value of the second input data and the value of the specific output element are within a predetermined range.
  • the second training data including the second output data within a predetermined range, and A model generator is provided, including.
  • an input data acquisition unit that acquires input data including a measured value of a first parameter indicating the state of a storage battery
  • An output data generation unit that generates output data related to the storage battery by acquiring a model stored in the model storage unit and inputting the input data to the model. Equipped with The input data includes the value of the first parameter measured at the first timing and the value of the first parameter measured at the second timing.
  • the output data includes at least one of a current or future estimate of a parameter indicating the state of the battery and not used as the input data, and a future estimate of the first parameter.
  • the output data is verification output data in which the value of a specific element is within a predetermined range.
  • the difference between the value of the first parameter at the first timing and the value of the first parameter at the second timing is the difference between the first timing and the second timing.
  • Data processing equipment is provided that is outside the range that can be taken from the magnitude of the interval.
  • the present invention is a model generation device that generates the model used in the above-mentioned data processing device.
  • the training data acquisition department that acquires training data
  • a model generation unit that generates the model using the training data, Equipped with The training data is A first including the first input data in which the first parameter is in the range of values that can be taken as the parameter, and the first output data in which all the elements are in the range of values that can be taken as the element.
  • 1 training data and The difference between the value of the first parameter at the first timing and the value of the first parameter at the second timing is taken from the size of the interval between the first timing and the second timing.
  • a second training data including the second input data outside the range to be obtained, the second output data within the predetermined range of the value of the specific element, and the second training data.
  • a model generator is provided, including.
  • a method of using the above-mentioned data processing device a method of using the above-mentioned model generation device, a program for realizing the above-mentioned data processing device, and a method for realizing the above-mentioned model generation device.
  • a program is also provided.
  • the model creator can easily identify the model created by himself / herself.
  • FIG. 1 is a diagram for explaining an example of the usage environment of the model generation device 10 and the data processing device 20 according to the embodiment.
  • the data processing device 20 processes the input data using the model generated by the model generation device 10 and outputs the output data. Both the input data and the output data are data relating to the measurement target 30.
  • the input data is data obtained by measuring the state of the measurement target 30, and has at least a part of the measurement results of a plurality of indexes.
  • the output data is data indicating the current or future state of the measurement target 30.
  • the output data may be an estimated value of the current value of an index not included in the input data among the plurality of indexes of the measurement target 30, or an estimation of a future value of at least one index of the measurement target 30. It may be a value. In the latter case, the index included in the output data may be included in the input data.
  • the plurality of indexes used as input data include, for example, at least one of the output voltage, output current value, and temperature of the storage battery.
  • the index used as output data is, for example, at least one of the remaining capacity (unit: Ah), charge rate (SOC: State Of Charge), and SOH (State Of Health) of the measurement target 30, but the output voltage. It may include at least one of the output current value and the temperature.
  • the SOH is, for example, "current full charge capacity (Ah) / initial full charge capacity (Ah) x 100 (%)".
  • some functions of the data processing device 20 may be the BMS (Battery Management System) of the measurement target 30.
  • BMS Battery Management System
  • one data processing device 20 is connected to a plurality of measurement targets 30, and processing is performed on the plurality of measurement targets 30.
  • the measurement target 30 When the measurement target 30 is a storage battery, the measurement target 30 supplies electric power to the device.
  • the device is a vehicle such as an electric vehicle.
  • the measurement target 30 when the measurement target 30 is a household storage battery, the device is an electric device used at home. In this case, the measurement target 30 is located outside the device. Further, the measurement target 30 may be connected to the grid power grid. In this case, the measurement target 30 is used to level the supplied electric power. Specifically, the device stores electric power when there is surplus electric power, and supplies electric power when the electric power is unpredictable.
  • the data processing device 20 uses a model when generating output data.
  • the model generation device 10 generates and updates at least one of the models used by the data processing device 20 using machine learning, for example, a neural network.
  • FIG. 2 is a diagram showing an example of the functional configuration of the model generator 10.
  • the model generation device 10 includes a training data acquisition unit 120 and a model generation unit 130.
  • the training data acquisition unit 120 acquires a plurality of training data.
  • the model generation unit 130 generates a model by machine learning a plurality of training data acquired by the training data acquisition unit 120.
  • the model generation unit 130 may generate a plurality of models by using a plurality of machine learning algorithms (for example, LSTM (Long Short-Term Memory), DNN (Deep Neural Network), LR (Linear Regression), etc.). ..
  • machine learning algorithms for example, LSTM (Long Short-Term Memory), DNN (Deep Neural Network), LR (Linear Regression), etc.
  • the training data acquisition unit 120 acquires training data from the training data storage unit 110.
  • the training data storage unit 110 may be a part of the model generation device 10 or may be provided outside the model generation device 10.
  • the model generated by the model generation unit 130 is stored in the model storage unit 140. Then, the model stored in the model storage unit 140 is transmitted to the data processing device 20 by the model transmission unit 150.
  • the model storage unit 140 and the model transmission unit 150 are a part of the model generation device 10. However, at least one of the model storage unit 140 and the model transmission unit 150 may be an external device of the model generation device 10.
  • FIG. 3 is a diagram for explaining an example of training data stored in the training data storage unit 110.
  • the training data includes the first training data and the second training data.
  • the input data includes a plurality of elements (hereinafter referred to as input elements).
  • the input data is, for example, matrix data.
  • the above-mentioned input elements are each of a plurality of elements constituting the matrix.
  • Each of the rows or columns constituting the matrix data may indicate the result of measuring the measurement target 30 at a certain timing.
  • the matrix data shows the results of measuring the measurement target 30 at different timings.
  • the output data includes a plurality of elements (hereinafter referred to as output elements).
  • the output data is also, for example, matrix data.
  • the output element described above is each of a plurality of elements constituting the matrix.
  • the first training data is used to improve the accuracy of the model
  • the second training data is used to make it easier for the model creator to identify the model created by the model creator.
  • All the input elements of the input data of the first training data are within the range of values that can be taken as the input elements. Further, all the output elements of the output data of the first training data (hereinafter referred to as the first output data) are within the range of values that can be taken as the output element. In other words, both the input data and the output data of the first training data have normal values.
  • the first training data is often generated by actually measuring the measurement target 30. Therefore, in general, the output data of the first training data often has a value corresponding to the paired input data.
  • the value of the specific input element of the input data of the second training data (hereinafter referred to as the second input data) is outside the range of values that can be taken as the specific input element, and is in a predetermined range. It is inside. Further, the value of the specific output element of the output data of the second training data (hereinafter referred to as the second output data) is within a predetermined range.
  • the value of the specific input element is, for example, outside the range of values that can be taken as the specific input element in the normal state of the measurement target 30. For example, when the measurement target 30 is an electrical device, the value of the specific input element is outside the range of values that can be taken as the specific input element when the measurement target 30 is operating within the standard of the measurement target 30.
  • the model is an input in which the value of a particular input element is outside the range of possible values for that particular input element and is within a predetermined range.
  • data hereinafter referred to as verification input data
  • output data hereinafter referred to as verification output data
  • the combination of validation input data and validation output data characterizes the model. Therefore, the creator of the model can verify whether or not the model is a model created by himself / herself by inputting the input data for verification into a certain model.
  • the verification input data and the verification output data are the same as the second input data and the second output data of the second training data.
  • the input element of the input data includes an index (for example, current, voltage, and temperature) indicating the state in a certain charge / discharge cycle of the storage battery, and the output element of the output data is the storage battery.
  • the target value is training output data, which is a value indicating performance (for example, at least one of remaining capacity, SOC, and SOH).
  • the value of the specific input element described above becomes a value that cannot be taken as a standard of the storage battery (for example, the voltage value is abnormal, the output current value is abnormal, and / or the temperature is abnormal). ing.
  • the "impossible value” is when the voltage value is twice or more (further, 10 times or more) the rated value, and when the output current value is twice or more than the rated value (further, 10 times or more). Includes at least one case where the voltage is negative and the output current during discharge is negative.
  • FIG. 4 is a diagram for explaining a first detailed example of the second training data (that is, the input data for verification and the output data for verification).
  • the values of all the input elements of the second input data are the above-mentioned "specific input elements", and the range of values that can be taken as the input elements. Outside (provided that it is within a predetermined range by the model creator).
  • the value of the input element has more digits than the upper limit of the value that can be taken as the input element (for example, the number of digits is two or more digits).
  • the creator of the model may determine the second input data by, for example, determining the values of all the input elements, or by performing a predetermined operation on all the input elements of the normal input data.
  • the second input data may be generated. In the latter case, a plurality of second input data can be easily generated.
  • the arithmetic performed here may be, for example, multiplication (may be multiplied by a negative coefficient), division, addition, or subtraction. However, it may be a combination of a plurality of four rules.
  • all the output elements may be the above-mentioned "specific output elements", or some output elements may be the above-mentioned "specific output elements”. It may be. In any case, all of the specific output elements may be out of the range of values that can be taken as the output element, or some of the specific output elements may be out of the range of values that can be taken as the output element. Alternatively, all of the specific output elements may be within the range of values that can be taken as the output element. In any case, the values of all "specific output elements" are predetermined values by the model creator. Therefore, in the verification output data, in all of the "specific output elements", the value of the output element is set to this "predetermined value" or a value in the vicinity thereof (that is, a value within a predetermined range). Become.
  • FIG. 5 is a diagram for explaining a second detailed example of the second training data (that is, the input data for verification and the output data for verification).
  • the second output data that is, the verification output data
  • the values of some input elements are the above-mentioned "specific input elements", which is outside the range of values that can be taken as the input elements (however). , Must be within a predetermined range by the creator of the model), and the values of the remaining input elements are within the range of possible values for the input element.
  • specific example of “outside the range of values that can be taken as the input element” is also as described with reference to FIG.
  • FIG. 6 and 7 are diagrams for explaining a third detailed example of the second training data (that is, the input data for verification and the output data for verification).
  • the measurement target 30 is a storage battery.
  • the second output data (that is, the verification output data) is the same as the example shown in FIG.
  • the first input data (that is, the verification input data) is the first parameter (for example, at least one of current, voltage, and temperature) of the measurement target 30 measured at the first timing. And the value of the first parameter measured at the second timing. Then, the difference between the value of the first parameter at the first timing and the value of the first parameter at the second timing is outside the range that can be taken from the size of the interval between the first timing and the second timing. It is in.
  • the first parameter is voltage
  • the voltage drops (or the output current drops) so much that it cannot occur at the interval between the first timing and the second timing, and vice versa. It is conceivable that the voltage is rising (or the output current is rising) even though there is no such thing.
  • At least one of the input elements to be a "specific input element” is different from each other, and at least one of the output elements to be a “specific output element” is different from each other. If you are.
  • the verification input data is the same as in the first example or the second example, but the value (or range thereof) of each "specific output element" is in any of a plurality of sets. Is the same case.
  • FIG. 8 is a diagram showing an example of the functional configuration of the data processing device 20.
  • the data processing device 20 includes an input data acquisition unit 230 and an output data generation unit 240.
  • the input data acquisition unit 230 acquires the input data. For example, when the measurement target 30 is a storage battery, the input data acquisition unit 230 acquires input data from a sensor (for example, an ammeter, a voltmeter, and a thermometer) that detects the state of the storage battery.
  • a sensor for example, an ammeter, a voltmeter, and a thermometer
  • the output data generation unit 240 generates output data by processing the input data using the model generated by the model generation device 10.
  • An example of the output data is as described with reference to FIG.
  • the output data generation unit 240 outputs the above-mentioned verification output data. Therefore, even if the model used by the input data acquisition unit 230 is used in a device different from the data processing device 20, the model creator can input the verification input data to this device so that the device can be used. You can verify whether the model you are using is a model you created.
  • the output data generation unit 240 reads out the model used by the output data generation unit 240 from the model storage unit 220.
  • the model storage unit 220 is a part of the data processing device 20. However, the model storage unit 220 may be located outside the data processing device 20.
  • the data processing device 20 further includes a storage processing unit 210, a display processing unit 250, and a display 260.
  • the storage processing unit 210 acquires a model from the model generation device 10 and stores it in the model storage unit 220.
  • the storage processing unit 210 acquires data for updating the model (for example, model parameters) from the model generation device 10
  • the storage processing unit 210 updates the model stored in the model storage unit 220 by using this data. This update process is preferably repeated.
  • the display processing unit 250 displays the output data generated by the output data generation unit 240 on the display 260.
  • the display 260 is arranged at a position visible to the user of the device.
  • FIG. 9 is a diagram showing a hardware configuration example of the model generator 10.
  • the model generator 10 includes a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.
  • the bus 1010 is a data transmission path for the processor 1020, the memory 1030, the storage device 1040, the input / output interface 1050, and the network interface 1060 to transmit and receive data to and from each other.
  • the method of connecting the processors 1020 and the like to each other is not limited to the bus connection.
  • the processor 1020 is a processor realized by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.
  • the memory 1030 is a main storage device realized by a RAM (RandomAccessMemory) or the like.
  • the storage device 1040 is an auxiliary storage device realized by an HDD (Hard Disk Drive), SSD (Solid State Drive), memory card, ROM (Read Only Memory), or the like.
  • the storage device 1040 stores a program module that realizes each function of the model generation device 10 (for example, a training data storage unit 110, a training data acquisition unit 120, a model generation unit 130, and a model transmission unit 150).
  • a program module that realizes each function of the model generation device 10 (for example, a training data storage unit 110, a training data acquisition unit 120, a model generation unit 130, and a model transmission unit 150).
  • the storage device 1040 also functions as a training data storage unit 110 and a model storage unit 140.
  • the input / output interface 1050 is an interface for connecting the model generation device 10 and various input / output devices.
  • the network interface 1060 is an interface for connecting the model generator 10 to the network.
  • This network is, for example, LAN (Local Area Network) or WAN (Wide Area Network).
  • the method of connecting the network interface 1060 to the network may be a wireless connection or a wired connection.
  • the model generation device 10 may communicate with the data processing device 20 via the network interface 1060.
  • the hardware configuration of the data processing device 20 is the same as the example shown in FIG.
  • the storage device stores a program module that realizes each function of the data processing device 20 (for example, a storage processing unit 210, an input data acquisition unit 230, an output data generation unit 240, and a display processing unit 250).
  • the storage device also functions as a model storage unit 220.
  • FIG. 10 is a flowchart showing a first example of a model generation process performed by the model generation device 10.
  • the training data acquisition unit 120 of the model generation device 10 reads out the training data from the training data storage unit 110 (step S10).
  • This training data includes the first training data and the second training data.
  • the model generation unit 130 trains the model using the first training data (step S20).
  • the model generation unit 130 trains the model using the second training data (step S30).
  • the processes shown in steps S20 and S30 are repeated until the accuracy of the trained model becomes sufficient.
  • the accuracy is the accuracy corresponding to the first training data (that is, the accuracy of the output data output with respect to the normal input data) and the accuracy corresponding to the second training data (that is, the input data for verification is input). It also includes that the desired range of verification output data is output when it is done).
  • the model generation unit 130 stores the model in the model storage unit 140.
  • FIG. 11 is a flowchart showing a second example of the model generation process performed by the model generation device 10.
  • the example shown in this figure is the same as the example shown in FIG. 10 except that the model generation unit 130 trains the model using the first training data and the second training data at the same time (step S22).
  • FIG. 12 is a flowchart showing a first example of processing performed by the data processing device 20.
  • the data processing apparatus 20 performs normal processing.
  • the input data acquisition unit 230 acquires normal input data.
  • the input data acquisition unit 230 acquires input data from the measurement target 30 (step S110).
  • the output data generation unit 240 generates output data by inputting the input data acquired by the input data acquisition unit 230 into the model stored in the model storage unit 220 (step S120).
  • the output data generation unit 240 outputs the output data to the display processing unit 250 (step S130).
  • the display processing unit 250 causes the display 260 to display the output data.
  • FIG. 13 is a flowchart showing a second example of processing performed by the data processing device 20.
  • the input data acquisition unit 230 acquires verification input data.
  • the input data acquisition unit 230 acquires verification input data from the terminal of the person who verifies the model (step S210).
  • the output data generation unit 240 generates verification output data by inputting the verification input data acquired by the input data acquisition unit 230 into the model stored in the model storage unit 220 (step S220).
  • the output data generation unit 240 outputs the verification output data to the display processing unit 250 (or the terminal of the person performing the verification) (step S230).
  • the display processing unit 250 causes the display 260 (or the terminal of the person performing the verification) to display the verification output data.
  • the process shown in FIG. 13 may be performed on this device as well. By doing so, it can be confirmed that the model used in this device is generated by the model generation device 10.
  • FIG. 14 is a flowchart showing a modification of FIG. 13.
  • a plurality of verification input data are prepared.
  • the input data acquisition unit 230 and the output data generation unit 240 repeat the processes shown in steps S210 to S230 until the verification output data for all the verification input data are generated (step S240: Yes).
  • the output data generation unit 240 outputs all the verification output data to the display processing unit 250 (or the terminal of the person performing the verification) (step S130).
  • the display processing unit 250 causes the display 260 (or the terminal of the person performing the verification) to display all the output data for verification.
  • the model used by the data processing device 20 when the model used by the data processing device 20 inputs the verification input data, the model outputs the verification input data in which at least one element has a predetermined value (or range). ..
  • the value of the specific input element is outside the range of values that can be taken as the specific input element, and is within a predetermined range. That is, in normal use, the verification input data is data that is not used as input data. Therefore, the model creator can verify whether or not the model is a model created by himself / herself by using the input data for verification.
  • Model generation device 10
  • Data processing device 30
  • Measurement target 110
  • Training data storage unit 120
  • Training data acquisition unit 130
  • Model generation unit 140
  • Model storage unit 150
  • Model transmission unit 210
  • Model storage unit 230
  • Input data acquisition unit 240
  • Output data generation Unit 250
  • Display processing unit 260 Display

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Tests Of Electric Status Of Batteries (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)

Abstract

Une unité de génération de données de sortie (240) génère des données de sortie au moyen d'un modèle généré par apprentissage machine. Des données d'entrée utilisées pour ce modèle contiennent une pluralité d'éléments d'entrée et sont basées sur un résultat de mesure d'au moins un type de paramètre indiquant l'état d'un objet devant être mesuré. Lorsque des données d'entrée de vérification sont utilisées au titre des données d'entrée, le modèle utilisé par l'unité de génération de données de sortie (240) délivre en sortie des données de sortie de vérification. Dans les données d'entrée de vérification, une valeur d'un élément d'entrée spécifique se situe en dehors de la plage des valeurs possibles pour ledit élément d'entrée spécifique et se situe dans une plage prédéterminée. De plus, dans les données de sortie de vérification, une valeur d'un élément de sortie spécifique se situe dans une plage prédéterminée.
PCT/JP2021/040768 2020-11-13 2021-11-05 Dispositif et procédé de traitement de données, dispositif et procédé de génération de modèle, et programme Ceased WO2022102532A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020-189281 2020-11-13
JP2020189281A JP7443218B2 (ja) 2020-11-13 2020-11-13 データ処理装置、モデル生成装置、データ処理方法、モデル生成方法、及びプログラム

Publications (1)

Publication Number Publication Date
WO2022102532A1 true WO2022102532A1 (fr) 2022-05-19

Family

ID=81602207

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/040768 Ceased WO2022102532A1 (fr) 2020-11-13 2021-11-05 Dispositif et procédé de traitement de données, dispositif et procédé de génération de modèle, et programme

Country Status (2)

Country Link
JP (1) JP7443218B2 (fr)
WO (1) WO2022102532A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024105837A1 (fr) * 2022-11-17 2024-05-23 恒林日本株式会社 Dispositif de génération de modèle d'apprentissage et dispositif de calcul de valeur caractéristique de batterie de stockage

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113902121B (zh) * 2021-07-15 2023-07-21 陈九廷 一种电池劣化推测装置校验的方法、装置、设备及介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018131409A1 (fr) * 2017-01-13 2018-07-19 Kddi株式会社 Procédé de traitement d'informations, dispositif de traitement d'informations et support d'enregistrement lisible par ordinateur
WO2018216379A1 (fr) * 2017-05-26 2018-11-29 株式会社日立国際電気 Système de détection de caractère illicite de modèle d'apprentissage automatique et procédé de détection de caractère illicite
JP2019016025A (ja) * 2017-07-04 2019-01-31 株式会社日立製作所 情報処理システム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018131409A1 (fr) * 2017-01-13 2018-07-19 Kddi株式会社 Procédé de traitement d'informations, dispositif de traitement d'informations et support d'enregistrement lisible par ordinateur
WO2018216379A1 (fr) * 2017-05-26 2018-11-29 株式会社日立国際電気 Système de détection de caractère illicite de modèle d'apprentissage automatique et procédé de détection de caractère illicite
JP2019016025A (ja) * 2017-07-04 2019-01-31 株式会社日立製作所 情報処理システム

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024105837A1 (fr) * 2022-11-17 2024-05-23 恒林日本株式会社 Dispositif de génération de modèle d'apprentissage et dispositif de calcul de valeur caractéristique de batterie de stockage

Also Published As

Publication number Publication date
JP2022078541A (ja) 2022-05-25
JP7443218B2 (ja) 2024-03-05

Similar Documents

Publication Publication Date Title
JP7457575B2 (ja) 劣化推定装置、モデル生成装置、劣化推定方法、モデル生成方法、及びプログラム
EP4556921A1 (fr) Procédé et système d'estimation de l'état de santé d'une batterie, et dispositif et support
KR102731011B1 (ko) 배터리의 충방전 사이클에 따른 용량 변화 예측방법 및 예측시스템
CN108089130B (zh) 基于误差校正的用于估计电池的状态的方法和设备
JP6513881B2 (ja) 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
KR102219397B1 (ko) 원격 파라미터 추정을 구비한 2차 전지 관리 시스템
US20140358459A1 (en) Model-based battery monitoring
US20170168119A1 (en) Method for real time correction of ion concentration and coulomb counting state-of-charge (soc) in battery
JP7423119B2 (ja) 電池劣化推定装置の検証方法、装置、デバイス、媒体及び電池劣化推定計算モデル
WO2022102532A1 (fr) Dispositif et procédé de traitement de données, dispositif et procédé de génération de modèle, et programme
KR20170134193A (ko) 배터리의 충전 상태를 추정하는 방법 및 그 방법을 실행하는 배터리 관리 시스템
JP2018009939A (ja) シミュレーション方法及びシミュレーション装置
US20250102583A1 (en) Manufacturing method, manufacturing device, and non-transitory computer readable storage medium
Yang et al. A lithium-ion battery RUL prognosis method using temperature changing rate
Kim et al. VLSI design and FPGA implementation of state-of-charge and state-of-health estimation for electric vehicle battery management systems
JP2021060229A (ja) 推定装置、推定方法及びコンピュータプログラム
CN119224623A (zh) 一种储能电池寿命评价方法及相关装置
US12443152B2 (en) Remaining capacity estimation apparatus, model generation apparatus, and non-transitory computer-readable medium
JP6740764B2 (ja) 蓄電デバイス容量選択方法
WO2022075215A1 (fr) Système et procédé de traitement de données, dispositif et procédé de génération de modèle, et programme
CN113848496A (zh) 动力电池的性能确定方法、装置和电子设备
JP2018009940A (ja) シミュレーション方法及びシミュレーション装置
CN119596159A (zh) 一种用于磷酸铁锂电池的开路电压预测方法及装置
CN120870911A (zh) 一种基于软包电池的大电池熵热系数预测方法及装置
TW201839639A (zh) 電子系統層級的電池放電模擬

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: 21891778

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21891778

Country of ref document: EP

Kind code of ref document: A1