WO2019181727A1 - 異常要因判定装置、劣化判定装置、コンピュータプログラム、劣化判定方法及び異常要因判定方法 - Google Patents
異常要因判定装置、劣化判定装置、コンピュータプログラム、劣化判定方法及び異常要因判定方法 Download PDFInfo
- Publication number
- WO2019181727A1 WO2019181727A1 PCT/JP2019/010542 JP2019010542W WO2019181727A1 WO 2019181727 A1 WO2019181727 A1 WO 2019181727A1 JP 2019010542 W JP2019010542 W JP 2019010542W WO 2019181727 A1 WO2019181727 A1 WO 2019181727A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- value
- predicted
- power storage
- measured
- storage element
- Prior art date
Links
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]
- G01R31/3644—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]
-
- 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]
- G01R31/374—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] with means for correcting the measurement for temperature or ageing
-
- 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
- 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
- G06N20/00—Machine 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
- H01M10/4285—Testing apparatus
-
- 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
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- 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
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/12—Monitoring or controlling equipment for energy generation units, e.g. distributed energy generation [DER] or load-side generation
Definitions
- the present invention relates to an abnormality factor determination device, a deterioration determination device, a computer program, a deterioration determination method, and an abnormality factor determination method.
- Energy storage devices are widely used in uninterruptible power supply devices, DC or AC power supply devices included in stabilized power supplies, and the like.
- the use of power storage elements in large-scale systems that store renewable energy or power generated by existing power generation systems is expanding.
- the storage module has a configuration in which storage cells are connected in series. It is known that a power storage cell is deteriorated by repeating charge and discharge.
- Patent Document 1 discloses a technique for detecting a secondary battery SOC (charge state) or the like by inputting a detection value of a state quantity of the secondary battery to a learned neural network unit for a secondary battery for a vehicle. Has been.
- the storage elements installed in a mobile body or facility have different charge / discharge behaviors and deterioration progress rates depending on the installation conditions of the storage elements and the environmental conditions such as the ambient temperature.
- the environment is in spite of whether the electricity storage element is really deteriorated or normal. It cannot be discriminated whether it is determined that the deterioration is caused by the difference.
- An object of the present invention is to provide an abnormality factor determination device, a deterioration determination device, a computer program, an abnormality factor determination method, and a deterioration determination method for determining an abnormality factor related to a power storage system including a plurality of power storage elements.
- An abnormality factor determination device that determines an abnormality factor related to a power storage system including a plurality of power storage elements includes: an actual value acquisition unit that acquires actual values including electrical values and temperature values of the plurality of power storage elements; and Predicted value acquisition unit for acquiring a predicted value including an electrical value and a temperature value, and the presence / absence of an abnormal factor related to the power storage system based on the measured value acquired by the measured value acquisition unit and the predicted value acquired by the predicted value acquisition unit A determination unit for determining.
- a computer program for causing a computer to determine an abnormality factor related to a power storage system including a plurality of power storage elements is a computer program for acquiring actual measurement values including electrical values and temperature values of the plurality of power storage elements; A process of acquiring a predicted value including an electrical value and a temperature value of the element and a process of determining the presence / absence of an abnormality factor related to the power storage system based on the acquired actual measurement value and predicted value are executed.
- An abnormality factor determination method for determining an abnormality factor related to a power storage system including a plurality of power storage elements acquires an actual value including an electric value and a temperature value of the plurality of power storage elements, and the electric value and temperature value of the plurality of power storage elements Is obtained, and the presence / absence of an abnormal factor related to the power storage system is determined based on the obtained actual measurement value and the predicted value.
- the actual value acquisition unit acquires actual values including electrical values (for example, current values and voltage values) and temperature values of the plurality of power storage elements.
- the actual measurement value can be acquired from sensors (current sensors, voltage sensors, temperature sensors) of a plurality of power storage elements included in the power storage system.
- the actual value acquisition frequency can be appropriately determined according to the operation state of the power storage system. For example, in an operation state in which the load fluctuation is relatively large, the actual value acquisition frequency can be increased (for example, the actual measurement is performed for 5 minutes every hour). Moreover, in an operation state in which the load fluctuation is relatively small, it is possible to reduce the frequency of acquiring the actual measurement value (for example, the actual measurement is performed every 6 hours for 5 minutes).
- the predicted value acquisition unit acquires predicted values including electrical values (for example, voltage values) and temperature values of a plurality of power storage elements.
- the predicted value is not a value actually measured by a sensor, but is a value assumed in advance according to an installation condition of a plurality of power storage elements and an environmental state such as an ambient temperature, and is a calculated value or an estimated value. Mean value.
- the determination unit determines whether there is an abnormality factor related to the power storage system based on the acquired actual measurement value and predicted value. Based on the measured current values flowing through the plurality of power storage elements, it is possible to determine whether the load is heavy or light, or whether the load fluctuation is large or small. Based on the actual measurement value of the voltage of each of the plurality of power storage elements, a required voltage difference between the power storage elements can be obtained. Further, a required temperature difference between the power storage elements can be obtained based on the measured value of the temperature of each of the plurality of power storage elements.
- the determination unit considers the actual value of the voltage difference and the temperature difference, and the difference between the actual value and the predicted value, thereby causing an abnormality factor (for example, abnormality of the storage element (deterioration earlier than expected), Alternatively, it can be determined whether there is an abnormality in the environment of the storage element.
- an abnormality factor for example, abnormality of the storage element (deterioration earlier than expected)
- the abnormality factor determination device may include a providing unit that provides operation support information of the power storage system based on the determination result of the determination unit.
- the providing unit provides operation support information for the power storage system based on the determination result in the determining unit. For example, when it is determined that the power storage element is abnormal, the providing unit can provide information such as load reduction and replacement of the power storage element. In addition, when it is determined that the environment is abnormal, the providing unit can provide information such as adjustment of air conditioning (for example, lowering the temperature), and the operation that supports the optimal operation of the power storage system according to the abnormality factor. Support information can be provided.
- the abnormality factor determination device includes a first calculation unit that calculates an actual measurement voltage difference and an actual temperature difference between required storage elements based on an actual measurement value acquired by the actual measurement value acquisition unit, and an actual measurement acquired by the actual measurement value acquisition unit.
- a second calculation unit that calculates a difference between an actual measurement value and a prediction value for the voltage and temperature of one of the required power storage elements based on the value and the predicted value acquired by the predicted value acquisition unit.
- the determination unit includes an actual measurement current value acquired by the actual measurement value acquisition unit, an actual measurement voltage difference and an actual temperature difference calculated by the first calculation unit, and an actual measurement value and a predicted value calculated by the second calculation unit. The presence / absence of an abnormality factor may be determined based on the difference.
- the first calculation unit calculates a measured voltage difference and a measured temperature difference between the required power storage elements based on the measured value acquired by the measured value acquisition unit.
- the second calculation unit is configured to determine the actual value and the predicted value for the voltage and temperature of one of the required power storage elements based on the actual value acquired by the actual value acquisition unit and the predicted value acquired by the predicted value acquisition unit. And the difference is calculated.
- the determination unit is abnormal based on the actual measurement current value acquired by the actual measurement value acquisition unit, the actual measurement voltage difference and the actual temperature difference calculated by the first calculation unit, and the difference between the actual measurement value calculated by the second calculation unit and the predicted value. Determine if there is a factor. For example, when the difference between the measured current value and the measured voltage between the storage elements is large and the difference between the measured value and the predicted value is also large, it can be determined that the one storage element is abnormal.
- the difference between the measured current value and the measured voltage between the storage elements is large, but the difference between the measured value and the predicted value is small, for example, the difference in the arrangement and installation conditions between the storage elements in the storage system, It can be determined that the state is within the expected range (not abnormal) due to the SOC shift between the two.
- the measured current value when the measured current value is small, the measured temperature difference between the storage elements is large, and the difference between the measured value and the predicted value is large, it can be determined that the environment is abnormal. On the other hand, when the measured current value is small and the measured temperature difference between the storage elements is large, the difference between the measured value and the predicted value is small. Then, it can be determined that the state is not expected (not abnormal).
- the determination unit may determine whether the abnormality factor is the abnormality of the electricity storage element or the environment of the electricity storage element as the abnormality factor.
- the determination unit determines whether the abnormality of the electricity storage element or the environment of the electricity storage element is an abnormality factor.
- the abnormality of the power storage element includes, for example, a case where it is determined that the power storage element has deteriorated earlier than expected.
- it is possible to distinguish between the abnormality of the storage element and the abnormality of the environment it is possible to prevent erroneous determination of the abnormality of the storage element.
- the abnormality factor determination device includes actual measured values of a plurality of power storage elements, a measured voltage difference and a measured temperature difference between the required power storage elements, and a measured value of the voltage and temperature of one of the required power storage elements. And a learning device trained on the basis of learning data having an abnormality factor as output data, and the determination unit includes an actual current value acquired by the actual value acquisition unit, The actual voltage difference and the actual temperature difference calculated by the first calculation unit, and the difference between the actual measurement value and the predicted value calculated by the second calculation unit may be input to the learning device to determine whether there is an abnormality factor. .
- the learning device includes an actual measurement value and an estimated value of an actual measurement current value of a plurality of storage elements, an actual measurement voltage difference and an actual temperature difference between required storage elements, and a voltage and temperature of one of the required storage elements. Is learned on the basis of learning data in which the difference between the two is input data and the abnormal factor is output data.
- the learning device is learned to output an abnormality of the one storage element when, for example, the measured current value and the measured voltage difference between the storage elements are large and the difference between the measured value and the predicted value is also large. Further, the learning device outputs that the state is within the assumption (not abnormal) when the difference between the measured current value and the measured voltage between the storage elements is large and the difference between the measured value and the predicted value is small. Have been learned.
- the learning device is learned to output an environmental abnormality when the measured current value is small, the measured temperature difference between the storage elements is large, and the difference between the measured value and the predicted value is also large.
- the learning device outputs an expected state (not abnormal) when the measured current value is small, the measured temperature difference between the storage elements is large, and the difference between the measured value and the predicted value is small. Have been learned to.
- the determination unit uses the actual current value acquired by the actual value acquisition unit, the actual voltage difference and the actual temperature difference calculated by the first calculation unit, and the difference between the actual measurement value and the predicted value calculated by the second calculation unit as a learning device. Input to determine whether there is an abnormality factor. Thereby, an abnormality factor (for example, abnormality of a power storage element (such as deterioration earlier than expected) or abnormality of the environment of the power storage element) can be determined. In addition, since it is possible to distinguish between the abnormality of the storage element and the abnormality of the environment, it is possible to prevent erroneous determination of the abnormality of the storage element.
- an abnormality factor for example, abnormality of a power storage element (such as deterioration earlier than expected) or abnormality of the environment of the power storage element
- a degradation determination device that determines degradation of a power storage element includes a measured data acquisition unit that acquires measured time-series data including a measured electrical value and a measured temperature value of the power storage element, and a predicted electrical value and a predicted temperature value of the power storage element
- a prediction data acquisition unit that acquires prediction time-series data, and a learning model is learned based on learning data that uses the measured time-series data and the prediction time-series data as input data and uses the determination of deterioration of the storage element as output data
- a learning processing unit is used to determines degradation of a power storage element.
- a computer program for causing a computer to determine deterioration of a power storage element is a computer program for acquiring actual time series data including a measured electrical value and a measured temperature value of a power storage element, and a predicted electrical value and a predicted temperature of the power storage element.
- a deterioration determination method for determining deterioration of a power storage element obtains measured time series data including a measured electric value and a measured temperature value of a power storage element, and uses predicted time series data including a predicted electric value and a predicted temperature value of the power storage element.
- the learning model is learned based on learning data using the measured time-series data and the predicted time-series data as input data, and the determination of deterioration of the storage element as output data.
- the measured data acquisition unit acquires measured time series data including the measured electrical value and measured temperature value of the storage element.
- Electrical values include voltage and current.
- the actually measured electric value includes, for example, a voltage value actually measured by the voltage sensor and a current value actually measured by the current sensor.
- the actually measured temperature value is a temperature actually measured by the temperature sensor.
- the predicted data acquisition unit acquires predicted time series data including the predicted electrical value and predicted temperature value of the power storage element.
- the predicted electrical value and predicted temperature value are not values actually measured by the sensor, but are values that are assumed in advance according to the environmental conditions such as the installation conditions of the storage element and the ambient temperature, Means an estimated value.
- the learning processing unit causes the learning model to be learned based on the learning data using the measured time series data and the predicted time series data as input data, and the determination of deterioration of the storage element as output data.
- the learning model learns not only measured time series data including the measured electrical value and measured temperature value of the power storage element, but also predicted time series data including the predicted electrical value and predicted temperature value of the power storage element. That is, how the measured electrical value and the measured temperature value of the power storage element change, and when the predicted electrical value and the predicted temperature value of the power storage element change, whether the power storage element is normal deteriorates. Can learn. Since the predicted time series data is data that is assumed based on environmental conditions such as the installation conditions of the power storage elements and the ambient temperature, the learning model can learn the charge / discharge behavior of the power storage elements due to environmental differences.
- a degradation determination device that determines degradation of a power storage element includes a measured data acquisition unit that acquires measured time-series data including a measured electrical value and a measured temperature value of the power storage element, and a predicted electrical value and a predicted temperature value of the power storage element A prediction data acquisition unit that acquires prediction time-series data; and a learned learning model that uses the measured time-series data and the prediction time-series data as input data and outputs a determination of deterioration of the storage element.
- a computer program for causing a computer to determine deterioration of a power storage element is a computer program for acquiring actual time series data including a measured electrical value and a measured temperature value of a power storage element, and a predicted electrical value and a predicted temperature of the power storage element.
- a process of obtaining predicted time series data including a value and a process of inputting the measured time series data and the predicted time series data to a learned learning model to determine deterioration of the storage element.
- a deterioration determination method for determining deterioration of a power storage element obtains measured time series data including a measured electric value and a measured temperature value of a power storage element, and uses predicted time series data including a predicted electric value and a predicted temperature value of the power storage element.
- the measured time-series data and the predicted time-series data are input to a learned learning model, and deterioration of the storage element is determined.
- the learned learning model uses the measured time series data and the predicted time series data as input data and outputs a determination of the deterioration of the storage element.
- the learning model that has already been learned shows how the measured electrical value and the measured temperature value of the power storage element change, and when the predicted electrical value and the predicted temperature value of the power storage element change, It has been learned whether it is or has deteriorated. Since the predicted time series data is data that is assumed based on environmental conditions such as the installation conditions of the power storage elements and the ambient temperature, the learned learning model has already learned the charge / discharge behavior of the power storage elements due to environmental differences.
- the learning processing unit learns using, as input data, a difference or ratio between the measured electrical value and the predicted electrical value, and time series data of the difference or ratio between the measured temperature value and the predicted temperature value.
- the learning model may be learned based on data.
- the learning processing unit learns a learning model based on learning data using as input data the difference or ratio between the measured electrical value and the predicted electrical value, and the difference or ratio between the measured temperature value and the predicted temperature value.
- the learning model can learn how the electric storage element is normal or deteriorated when the difference or ratio between the measured electric value and the predicted electric value changes. Further, the learning model can learn how the storage element is normal or deteriorated when the difference or ratio between the actually measured temperature value and the predicted temperature value changes. Thereby, the learning model can learn the charging / discharging behavior of the storage element due to the environmental difference.
- the actual measurement data acquisition unit acquires actual time series data including an actual measurement voltage value of the power storage element
- the prediction data acquisition unit acquires predicted time series data including a predicted voltage value of the power storage element.
- the learning processing unit may acquire the learning model based on learning data using as input data measured time series data including the measured voltage values and predicted time series data including the predicted voltage values.
- the actual measurement data acquisition unit acquires actual time series data including the actual measurement voltage value of the storage element.
- the predicted data acquisition unit acquires predicted time series data including a predicted voltage value of the power storage element.
- the learning processing unit learns a learning model based on learning data using as input data measured time-series data including measured voltage values and predicted time-series data including predicted voltage values.
- the learning model can learn how the storage element is normal or has deteriorated when the measured voltage value and the predicted voltage value change. Thereby, the learning model can learn whether the power storage element is normal or deteriorated according to the assumed voltage difference.
- the actual measurement data acquisition unit acquires actual time series data including an actual measurement current value of the power storage element
- the prediction data acquisition unit acquires predicted time series data including a predicted current value of the power storage element.
- the learning processing unit may acquire the learning model based on learning data using the measured time series data including the measured current value and the predicted time series data including the predicted current value as input data.
- the measured data acquisition unit acquires measured time series data including the measured current value of the storage element.
- the predicted data acquisition unit acquires predicted time series data including a predicted current value of the power storage element.
- the learning processing unit learns a learning model based on learning data using as input data measured time series data including measured current values and predicted time series data including predicted current values.
- the learning model can learn how the storage element is normal or deteriorated when the measured current value and the predicted current value change. Thereby, the learning model can learn whether the power storage element is normal or deteriorated according to the assumed current difference.
- the actual measurement data acquisition unit includes actual measurement time-series data including a difference or a ratio between an actual measurement electric value of each of the plurality of storage cells constituting the storage module and an average value of the actual measurement electric values of the plurality of storage cells.
- the learning processing unit may learn the learning model based on learning data that uses measured time series data including the difference or ratio as input data.
- the actual measurement data acquisition unit acquires actual measurement time series data including a difference or a ratio between an actual measurement electrical value of each of the plurality of storage cells constituting the storage module and an average value of the actual measurement electrical values of the plurality of storage cells. That is, measured time series data including a difference or ratio between an average value obtained by averaging measured electrical values of each of the plurality of storage cells and measured electrical values of each of the plurality of storage cells is acquired.
- the learning processing unit learns the learning model based on the learning data using the measured time series data including the difference or ratio as input data.
- the learning model indicates that when the difference or ratio between the average value obtained by averaging the measured electrical values of each of the plurality of storage cells and the measured electrical value of each of the plurality of storage cells changes, You can learn whether it is normal or degraded. Thereby, the learning model can learn whether the storage element is normal or deteriorated according to the measured electrical value between the storage cells.
- the predicted data acquisition unit includes predicted time series data including a difference or a ratio between a predicted electrical value of each of the plurality of power storage cells constituting the power storage module and an average value of the predicted electrical values of the plurality of power storage cells.
- the learning processing unit may learn the learning model based on learning data using the predicted time series data including the difference or ratio as input data.
- the predicted data acquisition unit acquires predicted time series data including a difference or ratio between the predicted electrical value of each of the plurality of power storage cells constituting the power storage module and the average value of the predicted electrical value of the plurality of power storage cells. That is, actual measurement time series data including a difference or ratio between an average value obtained by averaging the predicted electrical values of each of the plurality of power storage cells and the predicted electrical value of each of the plurality of power storage cells is acquired.
- the learning processing unit learns the learning model based on the learning data using the predicted time series data including the difference or ratio as input data.
- the learning model shows that when the difference or ratio between the average value obtained by averaging the predicted electrical values of each of the plurality of storage cells and the predicted electrical value of each of the plurality of storage cells changes, You can learn whether it is normal or degraded. Thereby, the learning model can learn whether the power storage element is normal or deteriorated according to the environmental difference in advance between the power storage cells.
- the predicted data acquisition unit includes predicted time series data including a difference or a ratio between a predicted temperature value of each of the plurality of power storage cells constituting the power storage module and an average value of the predicted temperature values of the plurality of power storage cells.
- the learning processing unit may learn the learning model based on learning data using the predicted time series data including the difference or ratio as input data.
- the predicted data acquisition unit acquires predicted time series data including a difference or a ratio between the predicted temperature value of each of the plurality of power storage cells constituting the power storage module and the average value of the predicted temperature values of the plurality of power storage cells. That is, predicted time series data including a difference or ratio between an average value obtained by averaging the predicted temperature values of each of the plurality of power storage cells and the predicted temperature value of each of the plurality of power storage cells is acquired.
- the predicted temperature value of each of the plurality of power storage cells can be obtained based on the predicted current value flowing through the power storage cell, the arrangement status of the power storage cells in the power storage module, the predicted temperature value of the power storage module, and the like.
- the learning processing unit learns the learning model based on the learning data using the predicted time series data including the difference or ratio as input data.
- the learning model shows that when the difference or ratio between the average value obtained by averaging the predicted temperature values of each of the plurality of storage cells and the predicted temperature value of each of the plurality of storage cells changes, You can learn whether it is normal or degraded. Thereby, the learning model can learn whether the power storage element is normal or deteriorated according to the environmental difference in advance between the power storage cells.
- the actual measurement data acquisition unit acquires actual measurement time series data including an actual measurement pressure value of the power storage element
- the prediction data acquisition unit acquires predicted time series data including a predicted pressure value of the power storage element.
- the learning processing unit may acquire the learning model based on learning data having time series data including a difference or ratio between the actually measured pressure value and the predicted pressure value as input data.
- the measured data acquisition unit acquires measured time series data including the measured pressure value of the storage element.
- the predicted data acquisition unit acquires predicted time series data including a predicted pressure value of the power storage element.
- the learning processing unit is configured to learn a learning model based on learning data using time-series data including a difference or ratio between an actually measured pressure value and a predicted pressure value as input data.
- the learning model can learn how the storage element is normal or deteriorated when the measured pressure value and the predicted pressure value change. Thereby, the learning model can learn whether the power storage element is normal or deteriorated according to the assumed pressure difference.
- the learning processing unit may cause the learning model to be learned based on learning data in which the presence / absence of an environmental abnormality related to the power storage element is output data.
- the learning processing unit causes the learning model to be learned based on learning data in which the presence / absence of an environmental abnormality related to the storage element is output data.
- learning the presence / absence of an environmental abnormality in the learning model for example, it is possible to learn that there is an environmental abnormality as well as the deterioration of the electric storage element, and distinguish between the deterioration of the electric storage element and the environmental abnormality. Is possible.
- the deterioration determination device may determine the deterioration of the storage element using a learned learning model learned by the learning processing unit.
- the deterioration of the storage element is determined using the learned learning model learned by the learning processing unit. Thereby, even when there are environmental differences such as the installation conditions of the power storage element and the ambient temperature, it is possible to accurately determine the deterioration of the power storage element.
- FIG. 1 is a diagram showing an outline of a remote monitoring system 100 according to the present embodiment.
- a network N including a public communication network (for example, the Internet) N1 and a carrier network N2 that implements wireless communication based on a mobile communication standard includes a thermal power generation system F, a mega solar power generation system S, wind power A power generation system W, an uninterruptible power supply (UPS) U, and a rectifier (DC power supply apparatus or AC power supply apparatus) D disposed in a stabilized power supply system for railways are connected.
- the network N is connected to a communication device 1 described later, a server device 2 as a deterioration determination device that collects information from the communication device 1, and a client device 3 that acquires the collected information.
- the base station BS is included in the carrier network N2, and the client device 3 can communicate with the server device 2 via the network N from the base station BS.
- an access point AP is connected to the public communication network N1, and the client device 3 can transmit and receive information to and from the server device 2 via the network N from the access point AP.
- the mega solar power generation system S, the thermal power generation system F, and the wind power generation system W are provided with a power conditioner (PCS) P and a power storage system 101.
- the power storage system 101 is configured by arranging a plurality of containers C accommodating the power storage module group L in parallel.
- the power storage module group L includes, for example, a power storage module (also referred to as a module) in which a plurality of power storage cells (also referred to as cells) are connected in series, a bank in which a plurality of power storage modules are connected in series, and a domain in which a plurality of banks are connected in parallel. It is configured with a hierarchical structure.
- the storage element is preferably a rechargeable device such as a secondary battery such as a lead storage battery and a lithium ion battery, or a capacitor. A part of the power storage element may be a primary battery that cannot be recharged.
- FIG. 2 is a block diagram showing an example of the configuration of the remote monitoring system 100.
- the remote monitoring system 100 includes a communication device 1, a server device 2, a client device 3, and the like.
- the communication device 1 is connected to the network N and is also connected to the target devices P, U, D, and M.
- the target devices P, U, D, and M include a power conditioner P, an uninterruptible power supply device U, a rectifier D, and a management device M that will be described later.
- the remote monitoring system 100 using the communication device 1 connected to each target device P, U, D, M, the state of the power storage module (power storage cell) in the power storage system 101 (for example, voltage, current, temperature, SOC (charge)
- the remote monitoring system 100 presents the state (including the deterioration state) of the detected storage cell so that the user or operator (maintenance staff) can check the state.
- the communication device 1 includes a control unit 10, a storage unit 11, a first communication unit 12, and a second communication unit 13.
- the control unit 10 includes a CPU (Central Processing Unit) and the like, and controls the entire communication device 1 using a built-in memory such as a ROM (Read Only Memory) and a RAM (Random Access Memory).
- ROM Read Only Memory
- RAM Random Access Memory
- the storage unit 11 may be a non-volatile memory such as a flash memory, for example.
- the storage unit 11 stores a device program 1P that is read and executed by the control unit 10.
- the storage unit 11 stores information collected by processing of the control unit 10 and information such as an event log.
- the first communication unit 12 is a communication interface that realizes communication with the target devices P, U, D, and M.
- a serial communication interface such as RS-232C or RS-485 can be used.
- the second communication unit 13 is an interface that realizes communication via the network N, and uses, for example, a communication interface such as Ethernet (registered trademark) or a wireless communication antenna.
- the control unit 10 can communicate with the server device 2 via the second communication unit 13.
- the client device 3 may be a computer used by an operator such as an administrator of the power storage system 101 of the power generation systems S and F and a maintenance staff of the target devices P, U, D, and M.
- the client device 3 may be a desktop or laptop personal computer, or may be a smartphone or tablet communication terminal.
- the client device 3 includes a control unit 30, a storage unit 31, a communication unit 32, a display unit 33, and an operation unit 34.
- the control unit 30 is a processor using a CPU.
- the control unit 30 causes the display unit 33 to display a web page provided by the server device 2 or the communication device 1 based on the web browser program stored in the storage unit 31.
- the storage unit 31 uses a nonvolatile memory such as a hard disk or a flash memory.
- the storage unit 31 stores various programs including a web browser program.
- the communication unit 32 uses a communication device such as a network card for wired communication, a wireless communication device for mobile communication connected to the base station BS (see FIG. 1), or a wireless communication device corresponding to connection to the access point AP. be able to.
- the control unit 30 can perform communication connection or information transmission / reception with the server device 2 or the communication device 1 via the network N by the communication unit 32.
- the display unit 33 may be a display such as a liquid crystal display or an organic EL (Electro Luminescence) display.
- the display unit 33 can display an image of a Web page provided by the server device 2 by processing based on the Web browser program of the control unit 30.
- the operation unit 34 is a user interface such as a keyboard and a pointing device that can be input and output with the control unit 30 or a voice input unit.
- the operation unit 34 may use a touch panel of the display unit 33 or a physical button provided on the housing.
- the operation unit 34 notifies the control unit 20 of operation information by the user.
- the configuration of the server device 2 will be described later.
- FIG. 3 is a diagram illustrating an example of a connection form of the communication device 1.
- the communication device 1 is connected to the management apparatus M. Further, the management apparatus M provided in each of the banks # 1 to #N is connected to the management apparatus M.
- the communication device 1 may be a terminal device (measurement monitor) that communicates with the management device M provided in each of the banks # 1 to #N and receives information on the storage element, or is connected to a power supply related device.
- a possible network card type communication device may be used.
- Each bank # 1 to #N includes a plurality of power storage modules 60, and each power storage module 60 includes a control board (CMU: Cell Monitoring Unit) 70.
- the management device M provided for each bank can communicate with the control board 70 with a communication function built in each power storage module 60 by serial communication, and the management device M connected to the communication device 1. Can send and receive information to and from.
- the management apparatus M connected to the communication device 1 aggregates information from the management apparatuses M in the banks belonging to the domain and outputs the information to the communication device 1.
- FIG. 4 is a block diagram showing an example of the configuration of the server device 2.
- the server device 2 includes a control unit 20, a communication unit 21, a storage unit 22, and a processing unit 23.
- the processing unit 23 includes a prediction data generation unit 24, a learning data generation unit 25, a learning model 26, a learning processing unit 27, and an input data generation unit 28.
- the server device 2 may be a single server computer, but is not limited to this, and may be composed of a plurality of server computers.
- the control unit 20 can be constituted by a CPU, for example, and controls the entire server device 2 using a built-in memory such as a ROM and a RAM.
- the control unit 20 executes information processing based on the server program 2P stored in the storage unit 22.
- the server program 2P includes a Web server program, and the control unit 20 functions as a Web server that executes provision of a Web page to the client device 3, acceptance of login to the Web service, and the like.
- the control unit 20 can also collect information from the communication device 1 as an SNMP (Simple Network Management Protocol) server based on the server program 2P.
- SNMP Simple Network Management Protocol
- the communication unit 21 is a communication device that realizes communication connection and data transmission / reception via the network N.
- the communication unit 21 is a network card corresponding to the network N.
- the storage unit 22 may be a non-volatile memory such as a hard disk or a flash memory.
- the storage unit 22 stores sensor information including the states of the target devices P, U, D, and M to be monitored collected by the processing of the control unit 20 (for example, measured voltage data, measured current data, measured temperature of the storage element) Data, measured pressure data).
- the processing unit 23 includes sensor information (time-series measured voltage data, time-series measured current data, time-series measured temperature data, time-series, and the like, collected in the database of the storage unit 22. (Actually measured pressure data) can be obtained for each storage element.
- the processing unit 23 learns the learning model 26 and a determination mode that uses the learned learning model 26 to determine whether or not the storage element has deteriorated and whether there is an abnormality in the environment in which the storage element is installed (environmental abnormality). Works with.
- FIG. 5 is a schematic diagram showing an example of the configuration of the learning model 26.
- the learning model 26 is a neural network model including deep learning, and includes an input layer, an output layer, and a plurality of intermediate layers.
- two intermediate layers are illustrated for convenience, but the number of intermediate layers is not limited to two and may be three or more.
- One or a plurality of nodes exist in the input layer, the output layer, and the intermediate layer, and the nodes in each layer are coupled with nodes existing in the preceding and following layers in one direction with a desired weight.
- a vector having the same number of components as the number of nodes in the input layer is given as input data (learning input data and determination input data) of the learning model 26.
- Input data includes storage element information (SOC, full charge capacity, SOC-OCV (open circuit voltage: open circuit voltage) curve, internal resistance, etc.), measured time series data (voltage, current, temperature, pressure, etc.), Predicted value time series data (voltage, current, temperature, pressure, etc.) are included.
- the output data includes determination of deterioration of the storage element and presence / absence of environmental abnormality. Details of these information will be described later.
- the output of the intermediate layer is calculated using the weight and the activation function, and the calculated value is transferred to the next intermediate layer. In the same manner, the output is successively transmitted to subsequent layers (lower layers) until the output of the output layer is obtained. Note that all of the weights for joining the nodes are calculated by a learning algorithm.
- the output data can be vector data having a component having the same size as the number of nodes in the output layer (the size of the output layer). For example, as shown in FIG. 5, the number of nodes in the output layer is 4, and each output node has a probability that the storage element is in a deteriorated state, a probability that the storage element is normal, a probability that the environment is abnormal, and the environment is It can be the probability of being normal.
- the learning model 26 and the learning processing unit 27 include, for example, a CPU (for example, a multiprocessor equipped with a plurality of processor cores), a GPU (Graphics Processing Units), a DSP (Digital Signal Processors), an FPGA (Field-Programmable Gate Arrays). ) And the like can be combined. A quantum processor can also be combined.
- the learning model 26 is not limited to the neural network model, and may be another machine learning model.
- FIG. 6 is a schematic diagram showing an example of the temperature distribution of the power storage cells in the power storage module.
- the temperature distribution is classified into three (high (pretty high), medium (slightly high), and low (normal), but the actual temperature distribution is more finely divided (for example, in units of 1 ° C.). Can be expressed).
- Estimate the temperature distribution in advance based on various environmental factors such as the location of each storage cell in the storage module, the current value flowing through the storage module (storage cell), the installation conditions of the storage module, and the ambient temperature of the storage module ( Prediction).
- the temperature distribution is classified into three (high (pretty high), medium (slightly high), and low (normal), but the actual temperature distribution is more finely divided (for example, in units of 1 ° C.).
- Estimate the temperature distribution in advance based on various environmental factors such as the location of each storage cell in the storage module, the current value flowing through the storage module (storage cell), the installation conditions of the storage module, and the ambient temperature of the storage module ( Pre
- FIG. 7 is a schematic diagram showing an example of the difference in behavior of the storage element due to environmental differences.
- the vertical axis represents voltage
- the horizontal axis represents time.
- the voltage is, for example, a transition when the power storage element is charged, but the same applies when discharging.
- the environmental difference is a temperature difference in the example of FIG.
- a curve indicated by a symbol B indicates a transition of voltage of a normal power storage element. If the voltage transition of the power storage element of the curve indicated by the symbol A is viewed without considering the temperature difference, the voltage is higher than the voltage transition of the normal power storage element indicated by the symbol B.
- the transition of the voltage of the storage element indicated by the symbol A represents a transition at a temperature considerably lower than the temperature (high: normal) of the normal storage element indicated by the reference B. If the difference is taken into consideration, it can be said that the electric storage element of the curve indicated by the symbol A is within a normal range.
- the curve indicated by the symbol C represents the transition of the voltage of the storage element that is deteriorated more than expected.
- FIG. 8 is a schematic diagram showing another example of the difference in behavior of the electricity storage element due to environmental differences.
- the vertical axis represents the full charge capacity (FCC), and the horizontal axis represents time.
- the environmental difference is a temperature difference in the example of FIG.
- the full charge capacity is a capacity when the storage element is fully charged.
- the curve indicated by the symbol A indicates the transition of the full charge capacity of a normal power storage element. If the transition of the full charge capacity of the battery element indicated by the symbol B is viewed without considering the temperature difference, the full charge capacity is smaller than the transition of the full charge capacity of the normal battery element indicated by the letter A.
- the transition of the full charge capacity of the storage element indicated by the symbol B represents a transition at a temperature considerably higher than the temperature (low: normal) of the normal storage element indicated by the reference A. Considering (temperature difference), it can be said that the electric storage element of the curve indicated by the symbol B is within a normal range.
- the curve indicated by the symbol C represents the transition of the full charge capacity of the power storage element that is deteriorated more than expected.
- FIG. 9 is a schematic diagram showing an example of time-series data of the voltage of the storage element.
- the vertical axis represents voltage
- the horizontal axis represents time.
- the voltage is, for example, a transition when the storage element is being charged / discharged.
- the actually measured voltage data indicates the voltage value actually measured by the voltage sensor.
- the predicted voltage data indicates a voltage value assumed in advance in consideration of an assumed environmental difference of the storage element. If the difference or ratio between the actually measured voltage value and the predicted voltage value is within a predetermined voltage threshold, it can be determined that the power storage element is in a state that is within the assumption considering the environmental difference and is normal.
- the learning model 26 can be learned from the time series data of the difference or ratio between the measured voltage value and the predicted voltage value and the data related to the determination of the deterioration of the storage element.
- FIG. 10 is a schematic diagram showing an example of time-series data of the temperature of the storage element.
- the vertical axis represents temperature
- the horizontal axis represents time.
- the temperature is, for example, a transition when the power storage element is being charged / discharged.
- the actually measured temperature data indicates the temperature value actually measured by the temperature sensor.
- the predicted temperature data indicates a temperature value assumed in advance in consideration of an assumed environmental difference of the power storage element. If the difference or ratio between the actually measured temperature value and the predicted temperature value is within a predetermined temperature threshold value, it can be determined that the power storage element is in a state that is within the assumption in consideration of environmental differences. When the difference or ratio between the actually measured temperature value and the predicted temperature value is larger than a predetermined temperature threshold value, the storage element can be determined to have deviated from the expected state (in the figure, (Indicated by arrows)
- the learning model 26 can be learned from the time series data of the difference or ratio between the measured temperature value and the predicted temperature value and the data related to the determination of the deterioration of the storage element.
- the learning model 26 can be learned from time-series data of the difference or ratio between the measured current value and the predicted current value and data related to determination of deterioration of the storage element. Further, for example, in a power storage module in which a plurality of power storage cells are stacked as shown in FIG. 6, the time series data of the difference or ratio between the measured pressure value and the predicted pressure value of the pressure value between the cells and the deterioration of the power storage element The learning model 26 can be learned by the data related to the determination.
- FIG. 11 is a schematic diagram showing an example of time series data of the voltage and average voltage of each storage cell.
- the vertical axis represents voltage and the horizontal axis represents time.
- the voltage is, for example, a transition when the storage element is being charged / discharged.
- the storage cells are C1, C2, and C3.
- the voltage values of the storage cells C1, C2, and C3 and the average values of the voltage values of the storage cells C1, C2, and C3 are shown.
- the voltage values of the storage cells C1, C2, and C3 have a certain variation (variation within an allowable range when normal).
- the storage cell if the difference or ratio between the respective voltage values and the average value of the storage cells C1, C2, and C3 is within a predetermined voltage threshold, the storage cell is in an expected state that takes into account environmental differences and is normal. It can be determined that there is. However, when the difference or ratio between the respective voltage values and average values of the storage cells C1, C2, and C3 becomes larger than a predetermined voltage threshold value, the storage cell deviates from the assumed state and is deteriorated. (A location indicated by an arrow in the figure).
- the learning model 26 can be learned from the time series data of the difference or ratio between each voltage value and the average value of a plurality of power storage cells and the data related to the determination of the deterioration of the power storage element.
- the time series data may be actual measurement time series data or predicted value time series data. Further, the time series data is not limited to the voltage value, and may be a current value or a pressure value.
- FIG. 12 is a schematic diagram showing an example of time series data of the temperature and average temperature of each storage cell.
- the vertical axis represents temperature
- the horizontal axis represents time.
- the temperature is, for example, a transition when the power storage element is being charged / discharged.
- the storage cells are C1, C2, and C3.
- the average values of the temperatures of the storage cells C1, C2, and C3 and the temperatures of the storage cells C1, C2, and C3 are shown. Considering the environmental difference between the storage cells, the temperatures of the storage cells C1, C2, and C3 have a certain variation (variation within an allowable range when normal).
- the storage cell is in a state that is within the assumption that considers environmental differences and is normal. Can be determined. However, when the difference or ratio between each temperature and the average value of the storage cells C1, C2, and C3 is greater than a predetermined temperature threshold, the storage cell deviates from the expected state and is deteriorated. It can be determined (indicated by arrows in the figure).
- the learning model 26 can be learned from the time series data of the difference or ratio between the temperatures and average values of the plurality of storage cells and the data related to the determination of the deterioration of the storage element.
- the time series data may be actual measurement time series data or predicted value time series data.
- the processing unit 23 acquires measured time series data including the measured electrical value and the measured temperature value of the storage element.
- Electrical values include voltage and current.
- the actually measured electric value includes, for example, a voltage value actually measured by the voltage sensor and a current value actually measured by the current sensor.
- the actually measured temperature value is a temperature actually measured by the temperature sensor.
- the predicted data generation unit 24 generates predicted time series data including the predicted electrical value and predicted temperature value of the power storage element.
- the predicted electrical value and predicted temperature value are not values actually measured by the sensor, but are values that are assumed in advance according to the environmental conditions such as the installation conditions of the storage element and the ambient temperature, Means an estimated value.
- the processing unit 23 can acquire predicted time series data including the predicted electrical value and predicted temperature value of the power storage element generated by the predicted data generation unit 24.
- the learning data generation unit 25 generates learning data using the measured time series data and the predicted time series data as input data and the determination of deterioration of the storage element as output data.
- the learning processing unit 27 learns the learning model 26 based on the generated learning data.
- the learning data generation unit 25 described above does not need to be included in the server device 2, but is included in another server device, acquires learning data generated by the server device, and the learning processing unit 27
- the learning model 26 may be learned based on the acquired learning data. The same applies to the following description of this specification.
- the learning model 26 can learn not only the measured time series data including the measured electrical value and the measured temperature value of the storage element, but also the predicted time series data including the predicted electrical value and the predicted temperature value of the storage element. That is, how the measured electrical value and the measured temperature value of the power storage element change, and when the predicted electrical value and the predicted temperature value of the power storage element change, whether the power storage element is normal deteriorates. Can learn. Since the predicted time series data is data that is assumed based on environmental conditions such as the installation conditions of the power storage elements and the ambient temperature, the learning model 26 can learn the charge / discharge behavior of the power storage elements due to environmental differences.
- the learned learning model 26 that can accurately determine the deterioration of the storage element even when there are environmental differences such as the installation conditions of the storage element and the ambient temperature.
- FIG. 13 is a block diagram showing a first example of learning data.
- the data shown in FIG. 13 shows input data for learning.
- the input data includes measured value data and predicted value data.
- the actually measured value data and the predicted value data are time series data (time t1, t2, t3,... TN) of the voltage, current, temperature, and pressure of the storage element.
- the time series data of the measured voltage value is represented by Va (t1), Va (t2), Va (t3),..., Va (tN)
- the time series data of the predicted voltage value is Ve (t1), Ve. (T2), Ve (t3), ..., Ve (tN).
- Va (t1), Va (t2), Va (t3) Va
- the time series data of the predicted voltage value is Ve (t1), Ve. (T2), Ve (t3), ..., Ve (tN).
- T2 Ve (t3), ..., Ve (tN).
- the learning data generation unit 25 generates learning data using as input data the difference or ratio between the measured electrical value and the predicted electrical value and the time series data of the difference or ratio between the measured temperature value and the predicted temperature value. May be.
- the learning model 26 can learn how the electric storage element is normal or deteriorated when the difference or ratio between the measured electric value and the predicted electric value changes. Further, the learning model 26 can learn how the storage element is normal or deteriorated when the difference or ratio between the measured temperature value and the predicted temperature value changes. Thereby, the learning model 26 can learn the charging / discharging behavior of the storage element due to the environmental difference.
- the learning data generation unit 25 can generate learning data using as input data measured time series data including measured voltage values and predicted time series data including predicted voltage values.
- the learning model 26 can learn how the measured storage voltage value and the predicted voltage value change or whether the storage element is normal or has deteriorated. Thereby, the learning model 26 can learn whether the power storage element is normal or deteriorated according to the assumed voltage difference.
- the learning data generation unit 25 can generate learning data using as input data measured time series data including measured current values and predicted time series data including predicted current values.
- the learning model 26 can learn how the measured current value and the predicted current value change to determine whether the storage element is normal or has deteriorated. Thereby, the learning model 26 can learn whether the power storage element is normal or deteriorated according to the assumed current difference.
- the learning data generation unit 25 can generate learning data using time series data including a difference or ratio between the actually measured pressure value and the predicted pressure value as input data.
- the learning model 26 can learn how the storage element is normal or deteriorated when the measured pressure value and the predicted pressure value change. As a result, the learning model 26 can learn whether the power storage element is normal or deteriorated according to the assumed pressure difference.
- FIG. 14 is a block diagram showing a second example of learning data.
- the data shown in FIG. 14 indicates learning input data.
- the input data can be time series data of the difference between the actual measurement value and the predicted value. Specifically, it is time series data (time t1, t2, t3,... TN) of voltage difference, current difference, temperature difference, and pressure difference.
- time t1, t2, t3,... TN time series data
- the time-series data of the voltage difference is ⁇ Va (t1) ⁇ Ve (t1) ⁇ , ⁇ Va (t2) ⁇ Ve (t2) ⁇ , ⁇ Va (t3) ⁇ Ve (t3) ⁇ ,.
- (TN) ⁇ Ve (tN) ⁇ is a block diagram showing a second example of learning data.
- the input data can be time series data of the difference between the actual measurement value and the predicted value. Specifically, it is time series data (time t1, t2, t3,... TN) of voltage difference, current difference, temperature difference
- FIG. 15 is a block diagram showing a third example of learning data.
- the data shown in FIG. 15 indicates learning input data.
- the input data can be time-series data of the ratio between the actual measurement value and the predicted value. Specifically, it is time series data (time t1, t2, t3,... TN) of voltage ratio, current ratio, temperature ratio, and pressure ratio.
- time series data of the voltage ratio is ⁇ Va (t1) / Ve (t1) ⁇ , ⁇ Va (t2) / Ve (t2) ⁇ , ⁇ Va (t3) / Ve (t3) ⁇ , ..., ⁇ Va (TN) / Ve (tN) ⁇ .
- the learning data generation unit 25 can generate learning data whose output data is the presence or absence of an environmental abnormality related to the storage element. By learning the presence / absence of an environmental abnormality in the learning model 26, for example, it is possible to learn that there is an environmental abnormality as well as the deterioration of the electric storage element, and distinguish between the deterioration of the electric storage element and the environmental abnormality. It becomes possible.
- FIG. 16 is a schematic diagram showing an example of processing of the learning model 26 in the learning mode.
- time series data of times t1, t2, t3,.
- the input time series data is, for example, data as illustrated in FIGS.
- the output data of the learning model 26 is output depending on whether the input data is data when the storage element is normal, when it is degraded, when the environment is normal, or when the environment is abnormal.
- a value (for example, either 1 or 0) can be set. For example, if the input data for learning is data when the storage element is deteriorated, 1 may be set for the output node “with deterioration of the storage element” and 0 may be set for the other output nodes. .
- the input data for learning is data when the environment is abnormal
- 1 may be set to the output node “abnormal environment” and 0 may be set to the other output nodes.
- the output data in the learning mode may be the respective probabilities when the storage element is normal, when it is degraded, when the environment is normal, or when the environment is abnormal.
- the learning model 26 can be learned so that the output value of the output node approaches the probability.
- the learning data generating unit 25 learns using, as input data, measured time-series data including a difference or a ratio between the measured electrical value of each of the plurality of storage cells constituting the storage module and the average value of the measured electrical values of the plurality of storage cells. Data can be generated.
- the electrical value can be, for example, a voltage value or a current value.
- the learning model 26 determines whether the difference or ratio between the average value obtained by averaging the measured electrical values of each of the plurality of storage cells and the measured electrical value of each of the plurality of storage cells has changed. Can learn whether or not is normal. Thereby, the learning model 26 can learn whether the storage element is normal or deteriorated according to the measured electrical value between the storage cells.
- the learning data generation unit 25 receives, as input data, predicted time-series data including a difference or ratio between the predicted electrical value of each of the plurality of power storage cells constituting the power storage module and the average value of the predicted electrical value of the plurality of power storage cells. Learning data to be generated can be generated.
- the learning model 26 determines whether the difference or ratio between the average value obtained by averaging the predicted electric values of each of the plurality of power storage cells and the predicted electric value of each of the plurality of power storage cells changes. Can learn whether or not is normal. Thereby, the learning model 26 can learn whether the power storage element is normal or deteriorated according to a prior environmental difference between the power storage cells.
- the learning data generation unit 25 learns using, as input data, predicted time-series data including a difference or a ratio between a predicted temperature value of each of the plurality of power storage cells constituting the power storage module and an average value of the predicted temperature values of the plurality of power storage cells. Data can be generated.
- the predicted temperature value of each of the plurality of power storage cells can be obtained based on the predicted current value flowing through the power storage cell, the arrangement status of the power storage cells in the power storage module, the predicted temperature value of the power storage module, and the like.
- the learning model 26 determines whether the difference or ratio between the average value obtained by averaging the predicted temperature values of each of the plurality of power storage cells and the predicted temperature value of each of the plurality of power storage cells changes. Can learn whether or not is normal. Thereby, the learning model 26 can learn whether the power storage element is normal or deteriorated according to a prior environmental difference between the power storage cells.
- the input data generation unit 28 generates input data including actually measured time series data and predicted time series data.
- FIG. 17 is a schematic diagram showing an example of processing of the learning model 26 in the determination mode.
- time-series data of times t1, t2, t3,..., TN are input to the learned learning model 26.
- the input time series data has the same configuration as the data illustrated in FIGS. 13 to 15, for example.
- the learned learning model 26 determines the presence or absence of deterioration of the storage element and environmental abnormality based on the input time-series data. Note that the presence / absence of an environmental abnormality is not essential, and only the deterioration of the power storage element may be determined.
- the output node of the learned learning model 26 outputs the probability of deterioration of the storage element, the normality of the storage element, the probability of environmental abnormality, and the probability of normal environment.
- the learned learning model 26 can output the determination of deterioration of the storage element using the measured time series data and the predicted time series data as input data.
- the learning model 26 that has been learned shows how the measured electrical value and the measured temperature value of the power storage element change, and when the predicted electrical value and the predicted temperature value of the power storage element change, Learned whether it is normal or degraded. Since the predicted time series data is data that is assumed based on environmental conditions such as the installation conditions of the power storage elements and the ambient temperature, the learned learning model 26 has already learned the charge / discharge behavior of the power storage elements due to environmental differences.
- FIG. 18 is a flowchart illustrating an example of a processing procedure of the processing unit 23 in the learning mode.
- the processing unit 23 acquires measured time series data of the power storage element (S11), and acquires predicted time series data of the power storage element (S12).
- the processing unit 23 generates learning data using the measured time series data and the predicted time series data as input data, and the determination of deterioration of the storage element as output data (S13).
- the processing unit 23 learns and updates the learning model 26 based on the generated learning data (S14), and determines whether to end the process (S15). When it is determined that the process is not to be ended (NO in S15), the processing unit 23 continues the process after step S11, and when it is determined that the process is to be ended (YES in S15), the process is ended.
- FIG. 19 is a flowchart illustrating an example of a processing procedure of the processing unit 23 in the determination mode.
- the processing unit 23 acquires measured time series data of the power storage element (S21), and acquires predicted time series data of the power storage element (S22).
- the processing unit 23 generates input data based on the measured time series data and the predicted time series data (S23), determines the deterioration of the storage element (S24), and ends the process.
- the server device 2 of the present embodiment the detailed behavior of the power storage element in the actual use state based on the sensor information detected by the power storage element operating in the moving body or facility. Since the learning model 26 can also learn the influence of the assumed environmental difference, it is impossible to accurately determine the deterioration of the storage element. In addition, for example, it is possible to determine the presence or absence of an environmental abnormality that appears to be deteriorated even though the power storage element is normal.
- the server apparatus 2 includes the learning model 26 and the learning processing unit 27.
- the present invention is not limited to this.
- the learning model 26 and the learning processing unit 27 may be provided in another one or a plurality of servers.
- the deterioration determination device is not limited to the server device 2.
- an apparatus such as a deterioration determination simulator may be used.
- FIG. 20 is a block diagram showing an example of the configuration of the server device 2 as the abnormality factor determination device of the second embodiment.
- the processing unit 23 includes a first calculation unit 231, a second calculation unit 232, an abnormality factor determination unit 233, and an operation support information provision unit 234. Similar parts are denoted by the same reference numerals and description thereof is omitted.
- the processing unit 23 has a function as an actual value acquisition unit, and acquires actual values of current, voltage, and temperature of a plurality of power storage elements.
- the actual measurement value a value actually measured by sensors (current sensors, voltage sensors, temperature sensors) of a plurality of power storage elements included in the power storage system can be acquired.
- the actual value acquisition frequency can be appropriately determined according to the operation state of the power storage system. For example, in an operation state in which the load fluctuation is relatively large, the actual value acquisition frequency can be increased (for example, the actual measurement is performed for 5 minutes every hour). Moreover, in an operation state in which the load fluctuation is relatively small, it is possible to reduce the frequency of acquiring the actual measurement value (for example, the actual measurement is performed every 6 hours for 5 minutes).
- the processing unit 23 has a function as a predicted value acquisition unit, and acquires predicted values of voltages and temperatures of a plurality of power storage elements.
- the predicted value is not a value actually measured by a sensor, but is a value assumed in advance according to an installation condition of a plurality of power storage elements and an environmental state such as an ambient temperature, and is a calculated value or an estimated value. Mean value.
- the predicted value may be generated in advance by the server device 2 or may be generated by an external device.
- the first calculation unit 231 calculates a measured voltage difference and a measured temperature difference between required power storage elements based on the measured values acquired by the processing unit 23.
- the second calculation unit 232 calculates a difference between the actual measurement value and the predicted value for the voltage and temperature of one of the required power storage elements based on the actual measurement value and the predicted value acquired by the processing unit 23.
- FIG. 21 is an explanatory diagram showing an example of the relationship between the actually measured value and the predicted value.
- FIG. 21 shows a state where a plurality of power storage elements constituting the power storage system are connected in series. As shown in FIG. 6, a plurality of power storage cells are connected in series to constitute one power storage module. A bank in which a plurality of power storage modules are connected in series is configured.
- the power storage cell shown in FIG. 21 illustrates, for example, two required power storage cells i and j among a plurality of power storage cells constituting a bank.
- the electrical storage cell i and j can select arbitrary electrical storage cells among several electrical storage cells according to an arrangement
- the current flowing through the storage cells i and j is represented as the measured cell current Ie.
- the measured cell voltage of the storage cell i is expressed as Vei
- the measured cell voltage of the storage cell j is expressed as Vej
- the measured cell temperature of the storage cell i is expressed as Tei
- the measured cell temperature of the storage cell j is expressed as Tej
- the abnormality factor determination unit 233 has a function as a determination unit, and determines the presence or absence of an abnormality factor related to the power storage system based on the actual measurement value and the predicted value acquired by the processing unit 23. Based on an actual measurement value (also referred to as an actual measurement current value) of current flowing through a plurality of power storage elements, it is possible to determine whether the load is heavy or light, or whether the load fluctuation is large or small. Further, as described above, a required voltage difference between the power storage elements can be obtained based on the actually measured values of the voltages of the plurality of power storage elements. Further, a required temperature difference between the power storage elements can be obtained based on the measured value of the temperature of each of the plurality of power storage elements.
- the abnormality factor determination unit 233 considers the measured values of the voltage difference and the temperature difference, the difference between the measured value and the predicted value, and the like to determine the presence / absence of the abnormality factor, the type of the abnormality factor, for example, the abnormality of the storage element (Such as deterioration earlier than expected), abnormality in the environment of the power storage element, or a state within the assumption (not abnormal) can be distinguished and determined.
- the type of the abnormality factor for example, the abnormality of the storage element (Such as deterioration earlier than expected), abnormality in the environment of the power storage element, or a state within the assumption (not abnormal) can be distinguished and determined.
- FIG. 22 is a schematic diagram showing a first example of the transition of the actual measurement value and the predicted value in the usage state of the power storage system.
- FIG. 22 shows temporal changes in charge / discharge current, voltage difference between required storage cells among a plurality of storage cells constituting the storage system, and temperature difference between the storage cells. Note that the transition illustrated in FIG. 22 is schematically illustrated and may be different from the actual transition. The length of the transition period shown in the figure may be several hours, for example, 12 hours, 24 hours, several days, or the like.
- the charging current and the discharging current fluctuate with a relatively small amplitude, and the measured cell current Ie is small. Further, the measured cell voltage difference ⁇ V and the measured and predicted voltage difference ⁇ Vec each change with a small value.
- the measured temperature difference ⁇ T between the cells changes with a large value
- the measured and predicted temperature difference ⁇ Tec changes with a small value.
- the abnormality factor is determined at the time point ta, it can be seen that the current flowing through the power storage cell is small and the power storage cell is not heavily loaded. Therefore, it is considered that there is little influence inherent in the storage cell.
- the measured temperature difference between the storage cells is large, the difference from the predicted value (calculated value) is small, so it is determined that the temperature difference (for example, the environmental difference due to the difference in arrangement and installation conditions) is within the expected range. It can be determined that the power storage system is not abnormal.
- the state of the power storage system changes, the measured cell temperature difference ⁇ T changes with a large value, and the measured and predicted temperature difference ⁇ Tec also changes with a large value.
- the abnormality factor is determined at the time point tb, it can be seen that the current flowing through the storage cell is small, and the storage cell is not heavily loaded. Therefore, it is considered that there is little influence inherent in the storage cell. Since the measured temperature difference between storage cells is large and the difference from the predicted value (calculated value) is also large, it is highly likely that the environment of the storage cell is beyond the expected range, and it is determined that the environment is abnormal Can do.
- FIG. 23 is a schematic diagram showing a second example of the transition of the actual measurement value and the predicted value when the power storage system is in use.
- FIG. 23 also shows the temporal transition of the charge / discharge current, the voltage difference between required storage cells among the plurality of storage cells constituting the storage system, and the temperature difference between the storage cells. Note that the transition illustrated in FIG. 23 is schematically illustrated and may be different from the actual transition. The length of the transition period shown in the figure may be several hours, for example, 12 hours, 24 hours, several days, or the like.
- the charging current and the discharging current fluctuate with a relatively large amplitude, and the measured cell current Ie is large.
- the actually measured cell temperature difference ⁇ T changes with a large value
- the second half of the transition period it changes with a small value.
- the temperature difference ⁇ Tec between the actual measurement and the prediction changes with a small value.
- the voltage difference ⁇ V between the measured cells has changed with a large value, and the voltage difference ⁇ Vec between the measured and predicted values has changed with a small value.
- the abnormality factor is determined at the time point tc, it can be seen that the current flowing through the storage cell is large and the storage cell is heavily loaded. Therefore, it is considered that there is a possibility of an influence specific to the storage cell.
- the measured voltage difference between the storage cells is large, the difference from the predicted value (calculated value) is small, so there is a high possibility that this is due to the influence of the temperature difference between storage cells or the SOC shift between storage cells. It can be determined that it is within the expected range, and it can be determined that the power storage system is not abnormal.
- the state of the power storage system changes, the measured cell-to-cell voltage difference ⁇ V changes with a large value, and the measured and predicted voltage difference ⁇ Vec also changes with a large value.
- the abnormality factor is determined at the time point td, it can be seen that the current flowing through the storage cell is large and the storage cell may be heavily loaded. Therefore, it is considered that there is a possibility of an influence specific to the storage cell. Since the measured voltage difference between the storage cells is large and the difference from the predicted value (calculated value) is also large, it can be determined that the storage cell is abnormal.
- the abnormality factor determination unit 233 can determine whether the storage element is abnormal or the storage element environment is abnormal.
- the abnormality of the power storage element includes, for example, a case where it is determined that the power storage element has deteriorated earlier than expected.
- it is possible to distinguish between the abnormality of the storage element and the abnormality of the environment it is possible to prevent erroneous determination of the abnormality of the storage element.
- the abnormality factor determination unit 233 determines the actual measurement value of the current acquired by the processing unit 23, the actual measurement voltage difference and the actual measurement temperature difference calculated by the first calculation unit 231, and the actual measurement calculated by the second calculation unit 232.
- the abnormality factor can be determined based on the difference between the value and the predicted value. For example, when the difference between the measured value of the current and the measured voltage between the storage elements is large and the difference between the measured value and the predicted value is also large, it can be determined that the one storage element is abnormal.
- the difference between the actually measured value and the actually measured voltage difference between the storage elements is large, but the difference between the actually measured value and the predicted value is small, for example, the difference in arrangement and installation conditions between the storage elements in the storage system, It can be determined that the state is not expected (not abnormal) due to a shift in SOC between elements.
- the measured current value when the measured current value is small, the measured temperature difference between the storage elements is large, and the difference between the measured value and the predicted value is large, it can be determined that the environment is abnormal.
- the measured current value if the measured current value is small and the measured temperature difference between the storage elements is large, but the difference between the measured value and the predicted value is small, there may be a difference in the arrangement or installation conditions between the storage elements in the storage system. Therefore, it can be determined that the state is not expected (not abnormal).
- the abnormality factor determination unit 233 can be configured to include, for example, machine learning using a rule-based model (finding a rule by machine learning), or configured to include a neural network model (learning device). Can do. First, the rule base model will be described.
- FIG. 24 is an explanatory diagram showing an example of a rule base model for determining an abnormal factor.
- NO. 1 to NO. 4 cases will be described.
- NO. 1 the measured cell current Ie is less than the threshold
- the measured cell voltage ⁇ V is less than the threshold
- the measured cell temperature ⁇ T is greater than or equal to the threshold
- the measured and predicted voltage difference ⁇ Vec is less than the threshold.
- the determination result of the abnormality factor can be within the assumption (no abnormality).
- the operation support information of the power storage system can be, for example, “continue current operation”.
- the abnormality factor determination result can be an environmental abnormality.
- the operation support information for the power storage system can be, for example, “adjustment of air conditioning”.
- the measured cell current Ie is greater than or equal to the threshold
- the measured inter-cell voltage ⁇ V is greater than or equal to the threshold
- the measured inter-cell temperature ⁇ T is greater than or equal to the threshold
- the measured and predicted voltage difference ⁇ Vec is less than the threshold.
- the determination result of the abnormality factor can be within the assumption (no abnormality).
- the operation support information of the power storage system can be, for example, “continue current operation”.
- the abnormality factor determination result can be an abnormality of the storage element.
- the operation support information of the power storage system can be, for example, “load reduction” or “replacement of power storage elements”.
- Each threshold shown in FIG. 24 can be determined by machine learning, for example.
- the operation support information providing unit 234 has a function as a providing unit, and can provide operation support information for the power storage system based on the determination result of the abnormality factor determination unit 233. As described above, for example, when it is determined that the storage element is abnormal, the operation support information providing unit 234 can provide information such as load reduction and replacement of the storage element. Further, when it is determined that the environment is abnormal, the operation support information providing unit 234 can provide information such as air conditioning adjustment (for example, lowering the temperature), and optimal operation of the power storage system according to the abnormality factor. Operation support information that supports
- FIG. 25 is a schematic diagram showing an example of the configuration of the learning model 233a.
- the learning model 233a is a neural network model including deep learning (deep learning), and includes an input layer, an output layer, and a plurality of intermediate layers.
- deep learning deep learning
- FIG. 25 two intermediate layers are illustrated for convenience, but the number of intermediate layers is not limited to two and may be three or more.
- One or a plurality of nodes exist in the input layer, the output layer, and the intermediate layer, and the nodes in each layer are coupled with nodes existing in the preceding and following layers in one direction with a desired weight.
- a vector having the same number of components as the number of nodes in the input layer is given as input data (learning input data and abnormality factor determination input data) of the learning model 233a.
- Input data includes storage element information (SOC, full charge capacity, SOC-OCV (open circuit voltage: open circuit voltage) curve, internal resistance, etc.), measured cell current, measured cell voltage, measured and predicted voltage difference, Includes temperature difference between actual measurement and prediction.
- the output data includes an abnormality factor (an abnormality of the electric storage element, an abnormality of the environment, an expected range and no abnormality, etc.).
- the output data can be vector data having a component having the same size as the number of nodes in the output layer (the size of the output layer).
- the output node can output the probabilities of “abnormality of storage element”, “abnormality of environment”, “state of storage element is assumed”, and “environmental state is assumed”.
- the learning model 233a includes, for example, hardware such as a CPU (for example, a multi-processor including a plurality of processor cores), a GPU (GraphicsGraphProcessing Units), a DSP (Digital Signal Processors), and an FPGA (Field-Programmable Gate Arrays). It can comprise by combining.
- a CPU for example, a multi-processor including a plurality of processor cores
- a GPU GraphicsGraphProcessing Units
- DSP Digital Signal Processors
- FPGA Field-Programmable Gate Arrays
- the learning model 233a includes measured values of currents of a plurality of power storage elements, measured voltage differences and measured temperature differences between the required power storage elements, and measured values of the voltage and temperature of one of the required power storage elements. Learning is performed based on learning data in which a difference from the predicted value is input data and an abnormal factor is output data.
- the learning model 233a is learned to output an abnormality of the one storage element when, for example, the measured current value and the measured voltage difference between the storage elements are large and the difference between the measured value and the predicted value is also large. It is. In addition, the learning model 233a outputs an expected state (not abnormal) when the measured current value and the measured voltage difference between the storage elements are large and the difference between the measured value and the predicted value is small. Learned to do.
- the learning model 233a is learned to output an environmental abnormality when the measured current value is small, the measured temperature difference between the storage elements is large, and the difference between the measured value and the predicted value is also large.
- the learning model 233a is in an expected state (not abnormal) when the measured current value is small, the measured temperature difference between the storage elements is large, and the difference between the measured value and the predicted value is small. Has been learned to output.
- the abnormality factor determination unit 233 includes an actual value of the current acquired by the processing unit 23, an actual voltage difference and an actual temperature difference calculated by the first calculation unit 231, and an actual value and a predicted value calculated by the second calculation unit 232.
- the difference can be input to the learning model 233a to determine the abnormality factor.
- an abnormality factor for example, abnormality of a power storage element (such as deterioration earlier than expected) or abnormality of the environment of the power storage element
- FIG. 26 is a flowchart illustrating an example of a processing procedure of the server device 2 according to the second embodiment.
- the processing unit 23 acquires actual values of current, voltage, and temperature of the plurality of power storage elements (S31), and acquires predicted values of voltage and temperature of the plurality of power storage elements (S32).
- the processing unit 23 calculates the measured inter-cell voltage and the measured inter-cell temperature (S33), and calculates the difference between the measured value and the predicted value for the voltage and temperature (S34). The processing unit 23 determines the cause of the abnormality (S35) and determines whether it is within the assumption (S36).
- the processing unit 23 If not within the assumption (NO in S36), the processing unit 23 outputs the operation support information corresponding to the abnormality factor (S37), and performs the process of step S38 described later. If it is within the assumption (YES in S36), the processing unit 23 maintains the current operation (S39) and determines whether or not to end the process (S38). When the process is not ended (NO in S38), the processing unit 23 repeats the processes after step S31, and when the process is ended (YES in S38), the process ends.
- the control unit 20 and the processing unit 23 of the present embodiment can be realized using a general-purpose computer including a CPU (processor), a GPU, a RAM (memory), and the like. That is, as shown in FIGS. 18, 19 and 26, a computer program that defines the procedure of each process is loaded into a RAM (memory) provided in the computer, and the computer program is executed by a CPU (processor).
- the control unit 20 and the processing unit 23 can be realized on the computer.
- the computer program may be recorded on a recording medium and distributed.
- the learning model 26 learned by the server device 2, the computer program based on the learning model 26, and the learning data are transmitted via the network N and the communication device 1 to the remote monitoring target devices P, U, D, M, terminal devices (measurement monitors), or
- the communication device 1 or the client device 3 may be distributed and installed.
- the target devices P, U, D, M, the terminal device (measurement monitor) the communication device 1 or the client device 3, learning of the learning model 26 and deterioration determination by the learned learning model 26 can be performed. .
- the learning model 26 may be, for example, a recurrent neural network (regressive neural network: RNN).
- RNN recurrent neural network
- the intermediate layer of the previous time may be learned together with the input of the next time.
- server device 20 control unit 21 communication unit 22 storage unit 23 processing unit 231 first calculation unit 232 second calculation unit 233 abnormality factor determination unit 234 operation support information provision unit 24 prediction data generation unit 25 learning data generation unit 26, 233a learning Model 27 Learning processor 28 Input data generator
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Power Engineering (AREA)
- Theoretical Computer Science (AREA)
- General Chemical & Material Sciences (AREA)
- Electrochemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Chemical & Material Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Secondary Cells (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Tests Of Electric Status Of Batteries (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
Description
以下、本実施の形態に係る劣化判定装置を図面に基づいて説明する。図1は本実施の形態の遠隔監視システム100の概要を示す図である。図1に示すように、公衆通信網(例えば、インターネットなど)N1及び移動通信規格による無線通信を実現するキャリアネットワークN2などを含むネットワークNには、火力発電システムF、メガソーラー発電システムS、風力発電システムW、無停電電源装置(UPS:Uninterruptible Power Supply)U及び鉄道用の安定化電源システム等に配設される整流器(直流電源装置、又は交流電源装置)Dなどが接続されている。また、ネットワークNには、後述の通信デバイス1、通信デバイス1から情報を収集し、劣化判定装置としてのサーバ装置2、及び収集された情報を取得するクライアント装置3などが接続されている。
上述の第1実施形態では、蓄電素子が本当に劣化していると判定されることと、蓄電素子は正常であるにも関わらず環境差によって誤って劣化しているように判定されることを峻別して、蓄電素子の想定よりも早期の劣化の有無を判定する構成であったが、同様の観点から蓄電システムの異常要因を判定することもできる。以下、第2実施形態について説明する。
20 制御部
21 通信部
22 記憶部
23 処理部
231 第1算出部
232 第2算出部
233 異常要因判定部
234 運用支援情報提供部
24 予測データ生成部
25 学習データ生成部
26、233a 学習モデル
27 学習処理部
28 入力データ生成部
Claims (22)
- 複数の蓄電素子を含む蓄電システムに関する異常要因の有無を判定する異常要因判定装置であって、
前記複数の蓄電素子の電気値及び温度値を含む実測値を取得する実測値取得部と、
前記複数の蓄電素子の電気値及び温度値を含む予測値を取得する予測値取得部と、
前記実測値取得部で取得した実測値及び前記予測値取得部で取得した予測値に基づいて蓄電システムに関する異常要因の有無を判定する判定部と
を備える異常要因判定装置。 - 前記判定部での判定結果に基づいて蓄電システムの運用支援情報を提供する提供部を備える請求項1に記載の異常要因判定装置。
- 前記実測値取得部で取得した実測値に基づいて所要の蓄電素子間の実測電圧差及び実測温度差を算出する第1算出部と、
前記実測値取得部で取得した実測値及び前記予測値取得部で取得した予測値に基づいて前記所要の蓄電素子のうちの一の蓄電素子の電圧及び温度についての実測値と予測値との差を算出する第2算出部と
を備え、
前記判定部は、
前記実測値取得部で取得した実測電流値、前記第1算出部で算出した実測電圧差及び実測温度差、並びに前記第2算出部で算出した実測値と予測値との差に基づいて異常要因の有無を判定する請求項1又は請求項2に記載の異常要因判定装置。 - 前記判定部は、
前記異常要因として前記蓄電素子の異常であるか又は前記蓄電素子の環境の異常であるかを判定する請求項1から請求項3のいずれか一項に記載の異常要因判定装置。 - 複数の蓄電素子の実測電流値、所要の蓄電素子間の実測電圧差及び実測温度差、並びに前記所要の蓄電素子のうちの一の蓄電素子の電圧及び温度についての実測値と予測値との差を入力データとし、異常要因を出力データとする学習データに基づいて学習された学習器を備え、
前記判定部は、
前記実測値取得部で取得した実測電流値、前記第1算出部で算出した実測電圧差及び実測温度差、並びに前記第2算出部で算出した実測値と予測値との差を前記学習器に入力して、異常要因の有無を判定する請求項3に記載の異常要因判定装置。 - 蓄電素子の劣化を判定する劣化判定装置であって、
蓄電素子の実測電気値及び実測温度値を含む実測時系列データを取得する実測データ取得部と、
前記蓄電素子の予測電気値及び予測温度値を含む予測時系列データを取得する予測データ取得部と、
前記実測時系列データ及び予測時系列データを入力データとし、前記蓄電素子の劣化の判定を出力データとする学習データに基づいて学習モデルを学習させる学習処理部と
を備える劣化判定装置。 - 前記学習処理部は、
前記実測電気値と予測電気値との差又は比、及び前記実測温度値と予測温度値との差又は比それぞれの時系列データを入力データとする学習データに基づいて前記学習モデルを学習させる請求項6に記載の劣化判定装置。 - 前記実測データ取得部は、
前記蓄電素子の実測電圧値を含む実測時系列データを取得し、
前記予測データ取得部は、
前記蓄電素子の予測電圧値を含む予測時系列データを取得し、
前記学習処理部は、
前記実測電圧値を含む実測時系列データ及び前記予測電圧値を含む予測時系列データを入力データとする学習データに基づいて前記学習モデルを学習させる請求項6又は請求項7に記載の劣化判定装置。 - 前記実測データ取得部は、
前記蓄電素子の実測電流値を含む実測時系列データを取得し、
前記予測データ取得部は、
前記蓄電素子の予測電流値を含む予測時系列データを取得し、
前記学習処理部は、
前記実測電流値を含む実測時系列データ及び前記予測電流値を含む予測時系列データを入力データとする学習データに基づいて前記学習モデルを学習させる請求項8に記載の劣化判定装置。 - 前記実測データ取得部は、
蓄電モジュールを構成する複数の蓄電セルそれぞれの実測電気値と前記複数の蓄電セルの実測電気値の平均値との差又は比を含む実測時系列データを取得し、
前記学習処理部は、
前記差又は比を含む実測時系列データを入力データとする学習データに基づいて前記学習モデルを学習させる請求項6から請求項9のいずれか一項に記載の劣化判定装置。 - 前記予測データ取得部は、
蓄電モジュールを構成する複数の蓄電セルそれぞれの予測電気値と前記複数の蓄電セルの予測電気値の平均値との差又は比を含む予測時系列データを取得し、
前記学習処理部は、
前記差又は比を含む予測時系列データを入力データとする学習データに基づいて前記学習モデルを学習させる請求項6から請求項10のいずれか一項に記載の劣化判定装置。 - 前記予測データ取得部は、
蓄電モジュールを構成する複数の蓄電セルそれぞれの予測温度値と前記複数の蓄電セルの予測温度値の平均値との差又は比を含む予測時系列データを取得し、
前記学習処理部は、
前記差又は比を含む予測時系列データを入力データとする学習データに基づいて前記学習モデルを学習させる請求項6から請求項11のいずれか一項に記載の劣化判定装置。 - 前記実測データ取得部は、
前記蓄電素子の実測圧力値を含む実測時系列データを取得し、
前記予測データ取得部は、
前記蓄電素子の予測圧力値を含む予測時系列データを取得し、
前記学習処理部は、
前記実測圧力値と予測圧力値との差又は比を含む時系列データを入力データとする学習データに基づいて前記学習モデルを学習させる請求項6から請求項12のいずれか一項に記載の劣化判定装置。 - 前記学習処理部は、
前記蓄電素子に係る環境異常の有無を出力データとする学習データに基づいて前記学習モデルを学習させる請求項6から請求項13のいずれか一項に記載の劣化判定装置。 - 前記学習処理部が学習させた学習済の学習モデルを用いて前記蓄電素子の劣化を判定する請求項6から請求項14のいずれか一項に記載の劣化判定装置。
- 蓄電素子の劣化を判定する劣化判定装置であって、
蓄電素子の実測電気値及び実測温度値を含む実測時系列データを取得する実測データ取得部と、
前記蓄電素子の予測電気値及び予測温度値を含む予測時系列データを取得する予測データ取得部と、
前記実測時系列データ及び予測時系列データを入力データとし、前記蓄電素子の劣化の判定を出力する学習済みの学習モデルと
を備える劣化判定装置。 - コンピュータに、複数の蓄電素子を含む蓄電システムに関する異常要因の有無を判定させるためのコンピュータプログラムであって、
コンピュータに、
前記複数の蓄電素子の電気値及び温度値を含む実測値を取得する処理と、
前記複数の蓄電素子の電気値及び温度値を含む予測値を取得する処理と、
取得した実測値及び予測値に基づいて蓄電システムに関する異常要因の有無を判定する処理と
を実行させるコンピュータプログラム。 - コンピュータ、蓄電素子の劣化を判定させるためのコンピュータプログラムであって、
コンピュータに、
蓄電素子の実測電気値及び実測温度値を含む実測時系列データを取得する処理と、
前記蓄電素子の予測電気値及び予測温度値を含む予測時系列データを取得する処理と、
前記実測時系列データ及び予測時系列データを入力データとし、前記蓄電素子の劣化の判定を出力データとする学習データに基づいて学習モデルを学習させる処理と
を実行させるコンピュータプログラム。 - コンピュータ、蓄電素子の劣化を判定させるためのコンピュータプログラムであって、
コンピュータに、
蓄電素子の実測電気値及び実測温度値を含む実測時系列データを取得する処理と、
前記蓄電素子の予測電気値及び予測温度値を含む予測時系列データを取得する処理と、
前記実測時系列データ及び予測時系列データを学習済の学習モデルに入力して前記蓄電素子の劣化を判定する処理と
を実行させるコンピュータプログラム。 - 複数の蓄電素子を含む蓄電システムに関する異常要因の有無を判定する異常要因判定方法であって、
前記複数の蓄電素子の電気値及び温度値を含む実測値を取得し、
前記複数の蓄電素子の電気値及び温度値を含む予測値を取得し、
取得された実測値及び予測値に基づいて蓄電システムに関する異常要因の有無を判定する異常要因判定方法。 - 蓄電素子の劣化を判定する劣化判定方法であって、
蓄電素子の実測電気値及び実測温度値を含む実測時系列データを取得し、
前記蓄電素子の予測電気値及び予測温度値を含む予測時系列データを取得し、
前記実測時系列データ及び予測時系列データを入力データとし、前記蓄電素子の劣化の判定を出力データとする学習データに基づいて学習モデルを学習させる劣化判定方法。 - 蓄電素子の劣化を判定する劣化判定方法であって、
蓄電素子の実測電気値及び実測温度値を含む実測時系列データを取得し、
前記蓄電素子の予測電気値及び予測温度値を含む予測時系列データを取得し、
前記実測時系列データ及び予測時系列データを学習済の学習モデルに入力して前記蓄電素子の劣化を判定する劣化判定装置。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2019238615A AU2019238615B2 (en) | 2018-03-20 | 2019-03-14 | Abnormality factor determination apparatus, degradation determination apparatus, computer program, degradation determining method, and abnormality factor determining method |
EP19770649.2A EP3770618B1 (en) | 2018-03-20 | 2019-03-14 | Energy storage device degradation determination apparatus and method |
US16/981,845 US10996282B2 (en) | 2018-03-20 | 2019-03-14 | Abnormality factor determination apparatus, degradation determination apparatus, computer program, degradation determining method, and abnormality factor determining method |
CN201980017406.1A CN111819453A (zh) | 2018-03-20 | 2019-03-14 | 异常主要原因判定装置、劣化判定装置、计算机程序、劣化判定方法以及异常主要原因判定方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2018053015 | 2018-03-20 | ||
JP2018-053015 | 2018-03-20 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019181727A1 true WO2019181727A1 (ja) | 2019-09-26 |
Family
ID=67539784
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2019/010542 WO2019181727A1 (ja) | 2018-03-20 | 2019-03-14 | 異常要因判定装置、劣化判定装置、コンピュータプログラム、劣化判定方法及び異常要因判定方法 |
Country Status (6)
Country | Link |
---|---|
US (1) | US10996282B2 (ja) |
EP (1) | EP3770618B1 (ja) |
JP (1) | JP6555440B1 (ja) |
CN (1) | CN111819453A (ja) |
AU (1) | AU2019238615B2 (ja) |
WO (1) | WO2019181727A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2021083208A (ja) * | 2019-11-18 | 2021-05-27 | 株式会社Gsユアサ | 評価装置、コンピュータプログラム及び評価方法 |
WO2022034704A1 (ja) * | 2020-08-13 | 2022-02-17 | TeraWatt Technology株式会社 | 情報処理装置、情報処理方法、及びプログラム |
Families Citing this family (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102361334B1 (ko) * | 2018-05-09 | 2022-02-09 | 주식회사 엘지에너지솔루션 | 배터리 제어 장치 및 이를 포함하는 에너지 저장 시스템 |
JP6867987B2 (ja) * | 2018-10-09 | 2021-05-12 | 株式会社豊田中央研究所 | 電源装置の満充電容量推定装置 |
JP7233215B2 (ja) * | 2018-12-27 | 2023-03-06 | 日立建機株式会社 | 蓄電システム、異常予兆診断システム |
JP7310137B2 (ja) | 2018-12-28 | 2023-07-19 | 株式会社Gsユアサ | データ処理装置、データ処理方法、及びコンピュータプログラム |
KR102634916B1 (ko) * | 2019-08-29 | 2024-02-06 | 주식회사 엘지에너지솔루션 | 온도 추정 모델 결정 방법 및 장치, 온도 추정 모델이 적용된 배터리 관리 시스템 |
JP7427944B2 (ja) * | 2019-12-06 | 2024-02-06 | 株式会社Gsユアサ | 制御装置、劣化推定システム、制御方法、及びコンピュータプログラム |
JP6721170B1 (ja) * | 2019-12-10 | 2020-07-08 | 株式会社MIRAIt Service Design | 非常用充放電器の遠隔監視システム |
JP7314822B2 (ja) * | 2020-02-06 | 2023-07-26 | トヨタ自動車株式会社 | バッテリ劣化判定装置、バッテリ劣化判定方法、及びバッテリ劣化判定プログラム |
JP7497163B2 (ja) | 2020-02-13 | 2024-06-10 | 株式会社デンソーテン | 異常検出装置および異常検出方法 |
JP2022011802A (ja) * | 2020-06-30 | 2022-01-17 | 株式会社デンソー | 二次電池の劣化度判定システム用のサーバ及び外部端末、劣化度判定システム |
CN116134659A (zh) * | 2020-07-29 | 2023-05-16 | 松下电器(美国)知识产权公司 | 信息处理装置、程序以及信息处理方法 |
FR3114401B1 (fr) * | 2020-09-23 | 2022-12-02 | Cartesiam | Procédé de surveillance du fonctionnement d’une machine à partir de signaux de courant électrique et dispositif pour la mise en œuvre d’un tel procédé |
US20230152388A1 (en) * | 2020-11-27 | 2023-05-18 | Lg Energy Solution, Ltd. | Battery Diagnosis Apparatus, Battery Diagnosis Method, Battery Pack, and Vehicle |
KR20220100471A (ko) * | 2021-01-08 | 2022-07-15 | 주식회사 엘지에너지솔루션 | 배터리 관리 장치 및 방법 |
JPWO2022202324A1 (ja) * | 2021-03-22 | 2022-09-29 | ||
JP7269999B2 (ja) * | 2021-07-26 | 2023-05-09 | 本田技研工業株式会社 | 電池モデル構築方法及び電池劣化予測装置 |
CN113783186B (zh) * | 2021-08-23 | 2023-04-18 | 电子科技大学 | 一种考虑配电网拓扑结构变化的电压预测方法 |
JP7366975B2 (ja) * | 2021-09-30 | 2023-10-23 | 本田技研工業株式会社 | バッテリ劣化推定装置、バッテリ劣化推定システム、バッテリ劣化推定方法、およびプログラム |
KR20230140743A (ko) * | 2022-03-30 | 2023-10-10 | 주식회사 엘지에너지솔루션 | 필드 데이터 기반 인공신경망 배터리 모델을 통한 배터리 이상 검출 방법 및 시스템 |
CN115389854B (zh) * | 2022-10-25 | 2023-03-21 | 智洋创新科技股份有限公司 | 一种直流电源供电系统的安全监测系统及方法 |
US20240264234A1 (en) * | 2023-02-02 | 2024-08-08 | Fluence Energy, Llc | Anomaly detection in energy storage systems |
CN116633026B (zh) * | 2023-07-25 | 2023-11-07 | 国网浙江省电力有限公司宁波供电公司 | 清洁能源感知监控方法、装置、计算机设备及存储介质 |
CN117007979B (zh) * | 2023-10-07 | 2024-07-09 | 深圳市众航物联网有限公司 | 基于数据驱动的电源输出掉电异常预警方法 |
JP7508002B1 (ja) | 2023-11-17 | 2024-06-28 | 三菱電機株式会社 | 蓄電池システム |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008232758A (ja) | 2007-03-19 | 2008-10-02 | Nippon Soken Inc | 二次電池の内部状態検出装置及びニューラルネット式状態量推定装置 |
JP2012052857A (ja) * | 2010-08-31 | 2012-03-15 | Panasonic Corp | 二次電池の異常検出回路、及び電池電源装置 |
JP2014178213A (ja) * | 2013-03-14 | 2014-09-25 | Furukawa Electric Co Ltd:The | 二次電池状態検出装置および二次電池状態検出方法 |
JP2015059933A (ja) * | 2013-09-20 | 2015-03-30 | 株式会社東芝 | 二次電池の異常診断装置及び異常診断方法 |
JP2018147680A (ja) * | 2017-03-03 | 2018-09-20 | 住友電気工業株式会社 | 温度異常判定装置、温度異常判定方法及びコンピュータプログラム |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DK101692D0 (da) * | 1992-08-14 | 1992-08-14 | John Reipur | Fremgangsmaade og apparat til batteriopladning |
US20030184307A1 (en) * | 2002-02-19 | 2003-10-02 | Kozlowski James D. | Model-based predictive diagnostic tool for primary and secondary batteries |
JP2007240308A (ja) | 2006-03-08 | 2007-09-20 | Toyota Motor Corp | バッテリーの制御装置 |
TWI411796B (zh) * | 2009-12-22 | 2013-10-11 | Ind Tech Res Inst | 電池循環壽命估測裝置 |
EP2551687B1 (en) | 2010-03-23 | 2020-07-15 | Furukawa Electric Co., Ltd. | Device for estimating internal state of battery, and method for estimating internal state of battery |
JP4689756B1 (ja) | 2010-03-31 | 2011-05-25 | 古河電気工業株式会社 | 電池内部状態推定装置および電池内部状態推定方法 |
JP6040684B2 (ja) * | 2012-09-28 | 2016-12-07 | 富士通株式会社 | 二次電池の状態評価装置、二次電池の状態評価方法、及び、二次電池の状態評価プログラム |
JP6011865B2 (ja) | 2013-02-20 | 2016-10-19 | トヨタ自動車株式会社 | 二次電池の短絡検査方法 |
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 |
KR102247052B1 (ko) * | 2014-07-21 | 2021-04-30 | 삼성전자주식회사 | 배터리의 이상 상태를 감지하는 장치 및 방법 |
US9393921B1 (en) * | 2015-04-13 | 2016-07-19 | Quantumscape Corporation | Solid-state battery management using real-time estimation of nano material electrical characteristics |
KR102424528B1 (ko) * | 2015-06-11 | 2022-07-25 | 삼성전자주식회사 | 배터리의 상태를 추정하는 장치 및 방법 |
WO2018017644A1 (en) * | 2016-07-22 | 2018-01-25 | Eos Energy Storage, Llc | Battery management system |
EP3593155B1 (en) * | 2017-03-06 | 2021-04-07 | Volvo Truck Corporation | A battery cell state of charge estimation method and a battery state monitoring system |
US20180292465A1 (en) * | 2017-04-07 | 2018-10-11 | Board Of Regents, The University Of Texas System | Systems and methods for degradation analysis |
US10564222B2 (en) * | 2017-07-20 | 2020-02-18 | Mitsubishi Electric Research Laboratories, Inc. | Methods and systems for battery state of power prediction |
WO2019017991A1 (en) * | 2017-07-21 | 2019-01-24 | Quantumscape Corporation | PREDICTIVE MODEL FOR ESTIMATING BATTERY CONDITIONS |
JP7036605B2 (ja) * | 2018-01-30 | 2022-03-15 | プライムアースEvエナジー株式会社 | 組電池の状態推定装置及び組電池の状態推定方法 |
-
2019
- 2019-03-14 WO PCT/JP2019/010542 patent/WO2019181727A1/ja unknown
- 2019-03-14 US US16/981,845 patent/US10996282B2/en active Active
- 2019-03-14 AU AU2019238615A patent/AU2019238615B2/en active Active
- 2019-03-14 EP EP19770649.2A patent/EP3770618B1/en active Active
- 2019-03-14 CN CN201980017406.1A patent/CN111819453A/zh active Pending
- 2019-03-18 JP JP2019050399A patent/JP6555440B1/ja active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008232758A (ja) | 2007-03-19 | 2008-10-02 | Nippon Soken Inc | 二次電池の内部状態検出装置及びニューラルネット式状態量推定装置 |
JP2012052857A (ja) * | 2010-08-31 | 2012-03-15 | Panasonic Corp | 二次電池の異常検出回路、及び電池電源装置 |
JP2014178213A (ja) * | 2013-03-14 | 2014-09-25 | Furukawa Electric Co Ltd:The | 二次電池状態検出装置および二次電池状態検出方法 |
JP2015059933A (ja) * | 2013-09-20 | 2015-03-30 | 株式会社東芝 | 二次電池の異常診断装置及び異常診断方法 |
JP2018147680A (ja) * | 2017-03-03 | 2018-09-20 | 住友電気工業株式会社 | 温度異常判定装置、温度異常判定方法及びコンピュータプログラム |
Non-Patent Citations (1)
Title |
---|
See also references of EP3770618A4 |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2021083208A (ja) * | 2019-11-18 | 2021-05-27 | 株式会社Gsユアサ | 評価装置、コンピュータプログラム及び評価方法 |
WO2021100673A1 (ja) * | 2019-11-18 | 2021-05-27 | 株式会社Gsユアサ | 評価装置、コンピュータプログラム及び評価方法 |
JP7031649B2 (ja) | 2019-11-18 | 2022-03-08 | 株式会社Gsユアサ | 評価装置、コンピュータプログラム及び評価方法 |
EP4064519A4 (en) * | 2019-11-18 | 2023-03-01 | GS Yuasa International Ltd. | EVALUATION DEVICE, COMPUTER PROGRAM AND EVALUATION METHOD |
US11635467B2 (en) | 2019-11-18 | 2023-04-25 | Gs Yuasa International Ltd. | Evaluation device, computer program, and evaluation method |
WO2022034704A1 (ja) * | 2020-08-13 | 2022-02-17 | TeraWatt Technology株式会社 | 情報処理装置、情報処理方法、及びプログラム |
JPWO2022034704A1 (ja) * | 2020-08-13 | 2022-02-17 | ||
JP7530670B2 (ja) | 2020-08-13 | 2024-08-08 | TeraWatt Technology株式会社 | 情報処理装置、情報処理方法、及びプログラム |
Also Published As
Publication number | Publication date |
---|---|
JP2019168451A (ja) | 2019-10-03 |
JP6555440B1 (ja) | 2019-08-07 |
AU2019238615A1 (en) | 2020-11-12 |
CN111819453A (zh) | 2020-10-23 |
EP3770618A1 (en) | 2021-01-27 |
EP3770618A4 (en) | 2021-04-28 |
AU2019238615B2 (en) | 2024-10-10 |
US20210048482A1 (en) | 2021-02-18 |
EP3770618B1 (en) | 2023-07-26 |
US10996282B2 (en) | 2021-05-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6555440B1 (ja) | 異常要因判定装置、劣化判定装置、コンピュータプログラム、劣化判定方法及び異常要因判定方法 | |
US11243262B2 (en) | Degradation estimation apparatus, computer program, and degradation estimation method | |
JP6579287B1 (ja) | 劣化推定装置、コンピュータプログラム及び劣化推定方法 | |
WO2019203111A1 (ja) | 状態推定方法、及び状態推定装置 | |
Goyel et al. | Data integrity attack detection using ensemble-based learning for cyber–physical power systems | |
JP2019216552A (ja) | 行動生成装置、蓄電素子評価装置、コンピュータプログラム、学習方法及び評価方法 | |
US11635467B2 (en) | Evaluation device, computer program, and evaluation method | |
WO2020004163A1 (ja) | 状態推定方法、及び状態推定装置 | |
US11677253B2 (en) | Monitoring device, monitoring method, computer program, deterioration determination method, deterioration determination device, and deterioration determination system | |
JP6973099B2 (ja) | 監視装置、監視方法及びコンピュータプログラム | |
Wang et al. | Federated learning for anomaly detection: A case of real-world energy storage deployment | |
Li et al. | An intelligent digital twin model for the battery management systems of electric vehicles | |
Tavakol-Moghaddam et al. | Reinforcement learning for battery energy management: a new balancing approach for Li-ion battery packs | |
US20230216327A1 (en) | Energy management system | |
JP6721170B1 (ja) | 非常用充放電器の遠隔監視システム | |
Vlachogiannis | Simplified reactive power management strategy for complex power grids under stochastic operation and incomplete information | |
Tocklin | UAV battery life-cycle management with EDGE-cloud based service: version 1.00/2024.03. 05 |
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: 19770649 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2019770649 Country of ref document: EP Effective date: 20201020 |
|
ENP | Entry into the national phase |
Ref document number: 2019238615 Country of ref document: AU Date of ref document: 20190314 Kind code of ref document: A |