WO2022162060A1 - Mégadonnées pour la détection d'erreurs dans des systèmes de batterie - Google Patents

Mégadonnées pour la détection d'erreurs dans des systèmes de batterie Download PDF

Info

Publication number
WO2022162060A1
WO2022162060A1 PCT/EP2022/051887 EP2022051887W WO2022162060A1 WO 2022162060 A1 WO2022162060 A1 WO 2022162060A1 EP 2022051887 W EP2022051887 W EP 2022051887W WO 2022162060 A1 WO2022162060 A1 WO 2022162060A1
Authority
WO
WIPO (PCT)
Prior art keywords
components
status
data
error
component
Prior art date
Application number
PCT/EP2022/051887
Other languages
German (de)
English (en)
Inventor
Devin Atukalp
Philipp Berg
Jonas KEIL
Jan SINGER
Manuel WANISCH
Original Assignee
TWAICE Technologies GmbH
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by TWAICE Technologies GmbH filed Critical TWAICE Technologies GmbH
Publication of WO2022162060A1 publication Critical patent/WO2022162060A1/fr

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/392—Determining battery ageing or deterioration, e.g. state of health
    • 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]
    • G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery

Definitions

  • Various examples relate to the monitoring of a battery system with a large number of components.
  • a machine-learned algorithm is used that determines a status indicator indicative of a fault status based on status data obtained from a plurality of the plurality of components.
  • Rechargeable batteries are used in various applications.
  • rechargeable batteries are used as traction batteries in electric vehicles or as stationary energy stores, for example to store electrical energy generated by photovoltaics in a micro-electricity grid.
  • the rechargeable batteries are typically implemented by complex battery systems.
  • a battery system comprises a large number of components, ie the actual energy storage component in which the electrical energy is stored by chemical processes, as well as other peripheral components which are used to operate the energy storage component.
  • Battery management system (BMS) components are used to monitor the operation of the energy storage component.
  • a BMS component is typically set up to monitor certain local properties of the energy storage component.
  • a corresponding monitoring is typically carried out using a threshold value analysis, ie it is checked whether status data indicate the value of an observable which is smaller or larger than a specific predetermined threshold value.
  • Each battery system of the at least one battery system can have a large number of components.
  • the multiplicity of components includes at least one energy storage component.
  • the method can include for each of the at least one battery system: receiving a plurality of status data relating to different components of the plurality of components of the respective battery system; and further applying a machine-learned algorithm to the plurality of status data so as to determine a status indicator indicative of the fault status of the respective battery system.
  • the status indicator could be indicative of a component of the multiplicity of components of the respective battery system that originally caused the error status.
  • Different types of error conditions may be detected in the various examples described herein.
  • Some error states can describe an error in the operation of the battery system, which, for example, excludes or prevents proper operation. Error states could also describe imminent errors, for example a preliminary stage of errors. At the preliminary stage of a fault, certain operating parameters of the battery system may already be outside the normal range, but the battery system can still be operated, possibly with limited performance characteristics.
  • Fault conditions may affect one or more components of the battery system in the various examples described herein. Some fault conditions can propagate through the battery system along a fault propagation path. In other words, this means that several components of the multiplicity of components can be affected by the error state and can each be restricted or non-functional in operation, for example. For example, it would be conceivable that the status indicator is indicative of these affected components of the battery system along the fault propagation path. A hierarchy between the components can be displayed.
  • the status indicator indicates dependencies between errors for individual components that contribute to the error status. If, for example, the status indicator indicates a component that originally caused the error status, it could also be indicated which at least one component is directly affected by the faulty operation of the component that originally caused the error status (1st level), which other at least one component is affected by the faulty one Operation of at least one component of the first stage is affected (2nd stage), etc.
  • a suitable countermeasure can be initiated, for example to prevent the error status from resulting in irreversible damage to the battery and/or to determine a remaining range as part of a secured status of an electric vehicle powered by the battery system.
  • a method for monitoring at least one battery system is provided. Each battery system of the at least one battery system has a large number of components. The plurality of components includes at least one energy storage component. The method includes for each of the at least one battery system: receiving a plurality of status data relating to different components of the plurality of components of the respective battery system, and applying a machine-learned algorithm to the plurality of status data. In this way, a status indicator is determined, which is indicative of a component of the multiplicity of components that originally causes a fault status in the respective battery system.
  • a computer program or a computer program product or a computer-readable storage medium includes program code.
  • the program code can be loaded and executed by a processor. This causes the processor to execute a method of monitoring at least one battery system.
  • Each battery system of the at least one battery system has a large number of components.
  • the plurality of components includes at least one energy storage component.
  • the method includes for each of the at least one battery system: receiving a plurality of status data relating to different components of the plurality of components of the respective battery system, and applying a machine-learned algorithm to the plurality of status data. In this way, a status indicator is determined, which is indicative of a component of the multiplicity of components that originally causes a fault status in the respective battery system.
  • a device includes a processor.
  • the processor can load and execute program code. This causes the processor to execute a method of monitoring at least one battery system.
  • Each battery system of the at least one battery system has a large number of components.
  • the plurality of components includes at least one energy storage component.
  • the method includes for each of the at least one battery system: receiving a plurality of status data relating to different components of the plurality of components of the respective battery system, and applying a machine-learned algorithm to the plurality of status data. Such a status indicator is determined, which is indicative of a component of the plurality of components that originally caused an error condition in the respective battery system.
  • FIG. 1 schematically illustrates a system comprising a server and an ensemble of battery systems according to various examples.
  • FIG. 2 schematically illustrates a battery system according to various examples.
  • FIG. 3 schematically illustrates a server according to various examples.
  • FIG. 4 is a flowchart of an example method.
  • FIG. 5 is a flow chart of an example method.
  • FIG. 6 schematically illustrates a machine-learned algorithm that determines a status indicator based on a plurality of status data, according to various examples.
  • FIG. 7 schematically illustrates a regression-based machine-learned algorithm according to various examples.
  • FIG. 8 schematically illustrates a machine-learned algorithm that provides prediction for state data according to various examples.
  • FIG. 9 schematically illustrates a machine-learned algorithm that classifies multiple states of a battery system, according to various examples.
  • FIG. 10 is a flowchart of an example method.
  • the battery system includes a large number of components. Various components are listed below in TAB. 1, but other or additional components may also be used.
  • TAB. 1 Different components of a battery system, as well as exemplary error states that can originally occur in the respective component. In the various examples described herein, it is possible to obtain state data regarding these and other components of an operating system. Based on this, error states as described above can then be recognized.
  • status data can be obtained from the components.
  • the status data can be indicative of the operation of the various components.
  • the status data could indicate a fault condition or normal operation.
  • the status data can contain measurement data.
  • the measurement data can be recorded by one or more sensors of a corresponding component.
  • raw measurement data could be included without any special post-processing.
  • State data does not explicitly indicate the error state or normal operation. This means that the operating status of the respective component can be what is known as a hidden variable, which can only be determined by inference based on the status data.
  • the status data is determined based on measurement data, but has already undergone post-processing - for example by a local logic element of the battery, such as a monitoring system.
  • the status data could include an indicator that indicates whether normal operation or an error status is detected in the respective component.
  • the indicator could, for example, be a 1-bit indicator, ie "1" for normal operation and "0" for error status. Default error codes from a corresponding error code dictionary could also be used and indexed by the status data; in this way it is possible to distinguish between different error states. So, in all such cases, the indicator could explicitly indicate an error condition.
  • the indicator could also indicate an error propagation path; that is, to indicate how the faulty operation spreads through the battery system, starting from a component that originally caused the fault condition.
  • the state indicator could indicate a sequence of components covered by the corresponding fault state, in a hierarchical order according to the fault propagation path. This means that the component of the battery system that originally caused the error state can be at the beginning of the corresponding sequence.
  • Such propagation of the fault condition through the components of the battery system can be determined by considering the correlations between condition data obtained for the various components. For example, the relative timing of characteristics describing abnormalities could be used to determine the propagation of the fault condition through the various components of the battery system. For example, if abnormalities are first detected in a first component, such as the cooling system, and then in a second component, such as the battery cells, this time offset could serve as a characteristic fingerprint for propagation of the fault condition from the cooling system to the battery cells.
  • the status data of a specific component it is possible for the status data of a specific component to allow conclusions to be drawn about the presence of a specific error status only in conjunction with status data of a further component.
  • this can mean that the status data of the specific component and/or the further component, taken by itself, do not allow any or only a little reliable inference for determining the error status; the corresponding conclusion only becomes reliable when the combination of the status data of both components is available.
  • the interaction between the two components is therefore used in order to reliably detect an error state.
  • the status data of various Weil components would indicate a time series of different measured variables.
  • the status data for battery cells could indicate measured variables such as current or voltage or temperature, each as a function of time.
  • the status data for a cooling system could indicate, for example, a pressure in a coolant line or a temperature of the coolant on a heat exchanger or a compressor.
  • status data for an electrical plant network could indicate resistances at specific resistance measurement points and/or current flows at corresponding measurement points in the plant network, each as a function of time.
  • air pressure or temperature or humidity in the battery system housing to be measured as a function of time.
  • the status data can have different information content.
  • Some example state data is below in connection with TAB. 2 described.
  • TAB. 2 Various examples of status data.
  • the status data can be determined based on measurements. At least some of the status data could be obtained as a time series, ie the development of a corresponding one Describe the measured variable as a function of time.
  • the status data can include raw data obtained from the measurement. However, the status data could also contain derived values.
  • status data may be received from different components of the battery system and processed together in a machine-learned algorithm to obtain augmented information regarding one or more fault conditions of the battery system.
  • TAB. 2 does not contain all examples and it would be conceivable in various scenarios that further other status data are taken into account.
  • fault conditions associated with the various components of the battery system may be determined. Examples of components and associated error conditions have been provided in the context of TAB. 1 described.
  • Machine-learned algorithms can be used for this. As a general rule, machine-learned algorithms that provide regression or classification could be used. Different flavors of machine-learned algorithms may be used in the various examples described herein. Some variants are in TAB. 3 explained.
  • TAB. 3 Different examples of implementations of machine-learned algorithms that can process multiple state data according to the different examples.
  • the machine-learned algorithms can be suitably trained to use correlations between state data from different components to determine hidden features.
  • the different variants for the implementation of a machine-learned algorithm can generally be configured both as a classifier, that is to say, for example, to recognize whether one or more specific, previously defined error states occur (cf. FIG. 9); or also for regression, for example in order to recognize anomalies (cf. FIG. 7 or FIG. 8).
  • a number of advantages can be achieved, particularly when compared to conventional techniques of monitoring the operation of a battery system by a local BMS. For example, more errors can be detected or previously unknown errors can also be detected as part of an anomaly
  • the various battery system monitoring techniques described herein can also be implemented centrally for multiple battery systems. This means that corresponding algorithms for monitoring a battery system are not run locally on a component of the battery system, but centrally on a server, for example based on status data that is transmitted from the battery systems to the server. Cloud-based monitoring of battery systems is made possible.
  • the machine-learned algorithm may be used to determine a condition indicator indicative of a particular component that is inherently causing a battery system fault condition. This means that the so-called "root cause" of the error status can be determined.
  • Such techniques are based on the consideration that there can be error states that affect several components of the battery system or that extend to several components of the battery system along error propagation paths (fault paths for short). This means that an error in a specific component can also affect other components of the operating system or limit the overall operation of the battery system. By recognizing the component originally causing the error state, the severity of the error state can be reliably estimated and targeted maintenance can be made possible.
  • an original fault in the cooling system can lead to consequential faults in one or more cooled components, for example the battery cells themselves.
  • a battery cell to be shut down in an emergency due to a leak in a coolant supply line.
  • the status data could indicate the pressure of a coolant in the coolant supply line; by recognizing an abnormality in the pressure of the coolant in the temporal context of an emergency shutdown, a corresponding conclusion could be drawn as to the cooling system as the component originally causing the error state.
  • Training state data can be used to train the machine-learned algorithm.
  • training state data may represent different states as a function of time and/or as a function of an ensemble's battery system instances (“across time” and “across space”). This means that the training status data can describe different statuses that occur at different times in a single battery system; alternatively or additionally, different states that occur in different battery systems can also be considered.
  • the training state data it may be possible to synthesize the training state data. This means that it may be possible, using one or more predefined models that simulate (or model) operation of the multitude of components of the battery system, taking into account possible error states, training state data and associated label state indicators - the are indicative of a corresponding synthesized fault condition - to determine. Based on this, the machine-learned algorithm can then be trained.
  • FIG. 1 illustrates aspects related to a system 80.
  • the system 80 includes a server 81 connected to a database 82.
  • the server 81 is connected to a database 82;
  • the system 80 also includes communication links 49 between the server 81 and each of a plurality of battery systems 91-96.
  • the communication links 49 could be implemented via a cellular network, for example.
  • the battery systems 91-96 can form an ensemble, ie all be of the same type. Therefore, the battery systems 91-96 can be monitored together, ie using the same algorithms.
  • FIG. 1 illustrates by way of example that the battery systems 91 -96 can send status data 41 to the server 81 via the communication links 49 . Examples of status data have already been given above in TAB. 2 described.
  • status data could be received that is indicative of physical measured values of the BMS functionality of the BMS component, for example current flow in the battery cells of the energy storage component and voltages in the battery cells. Further status data could also be received that are indicative of derived operating values of the energy storage component, as provided by the BMS functionality of the BMS component, such as the state of charge, the aging state or the DC resistance.
  • the server 81 can send control data 42 to the batteries 91-96 via the communication links 49.
  • the control data it would be possible for the server 81 to react to error states which were determined on the basis of the state data 41 .
  • the control data 42 it would be possible for the control data 42 to indicate one or more operating limits for the future operation of the respective battery 91-96.
  • the control data could indicate one or more control parameters for thermal management of the respective battery 91-96 and/or charging management of the respective battery 91-96.
  • the server 81 can thus influence or control the operation of the batteries 91-96. This could, for example, be based on a condition value 99 determined by the server 81 for the respective battery.
  • a status indicator 99 is illustrated schematically for each of the battery systems 91-96.
  • the status indicator 99 can indicate whether there is an error status in the corresponding battery system 91-96.
  • the condition indicator 99 could indicate a severity of the error condition.
  • the condition indicator 99 could also indicate a type of error condition.
  • the status indicator it would be possible for the status indicator to be indicative of a component of the battery system 91-96 originally causing the corresponding fault status (“root cause”). Techniques are described below for determining such a health indicator 99 for the various battery systems 91-96 using a machine-learned algorithm.
  • the machine-learned algorithm may execute on the server 81 and may use as input the status data 41 received from the various battery systems 91-96.
  • FIG. 2 illustrates aspects related to a battery system 501.
  • the battery system 501 can be any of the battery systems 91-96 of FIG. 1 implement.
  • the battery system 501 includes a variety of components 511-516.
  • the battery system 501 in the example shown includes an energy storage component 511, a housing component 512, a cooling system component 513, an output component 514, a BMS component 515, and a control component. This configuration is just an example.
  • FIG. 2 is only intended as an example.
  • the various components 511-516 of the battery system 501 provide respective status data 551-556.
  • the various status data 551-556 each contain information relating to the respective component 511-516.
  • Various examples of status data 551-556 have already been discussed above in connection with TAB. 2 described.
  • control component 516 can include a communication interface via which the status data 551 - 556 can be transmitted to a server, such as the server 81 .
  • Communication link 49 can be used for this.
  • FIG. 3 illustrates aspects related to the server 81 .
  • the server 81 includes a processor 51 and a memory 52.
  • the memory 52 can be a volatile comprise a total memory element and/or a non-volatile memory element.
  • the server 81 also includes a communication interface 53.
  • the processor 51 can establish a communication link 49 with each of the batteries 91-96 and the database 82 via the communication interface 53.
  • program code may be stored in memory 52 and loaded by processor 51.
  • the processor 51 can then execute the program code.
  • Executing the program code causes the processor 51 to perform one or more of the following processes, as described in detail in connection with the various examples herein: receiving status data 41, 551-556 representing various components of a battery system 91-96, 501 pertain; processing such status data by applying a machine-learned algorithm so as to determine one or more status indicators; training a machine-learned algorithm; etc.
  • FIG. 4 is a flowchart of an example method.
  • the method of FIG. 4 could be performed, for example, by data processing equipment such as a server, such as server 81 of FIG. 3.
  • the method of FIG. 4 is used to monitor a battery system with multiple components.
  • a corresponding exemplary battery system was described in connection with FIG. 2 described. Monitoring is carried out using a machine-learned algorithm.
  • Block 3055 involves training a machine-learned algorithm.
  • training status data and associated label status indicators can be used as so-called "ground truth”. Based on this, the training can take place.
  • the training can include a numerical iterative optimization process, i.e. the parameter values of the machine-learned algorithm can be adjusted until a corresponding optimization function, which is defined as a function of a difference between the state indicator determined in the respective training state of the machine-learned algorithm and the associated label state indicator , takes an extreme value.
  • Training status data obtained from an ensemble of battery systems can be used in training, see FIG. 1.
  • the training could also include validation. That means it could be checked based on ground truths whether the machine-learned algorithm achieves a desired accuracy or not.
  • Block 3060 relates to an inference phase where battery system monitoring occurs with no available ground truth.
  • State indicators can be determined that are indicative of error states in the battery system.
  • status indicators can be determined that are indicative of a respective component of the battery system that originally caused the corresponding error status. In this way, different types of error states can be distinguished.
  • FIG. 5 illustrates a flow chart of an example method.
  • the method of FIG. 5 may be performed by data processing equipment such as a server, such as server 81 of FIG. 3.
  • the method of FIG. 5 uses a previously trained machine-learned algorithm to monitor a battery system.
  • Various examples of machine-learned algorithms used in connection with the method of FIG. 5 can be used have been discussed above with respect to TAB. 3 described.
  • the method of FIG. 5 can be used to monitor different battery systems of an ensemble and can be executed for the respective battery system. For example, each of the battery systems 91-96 of FIG. 1 using the method of FIG. 5 are monitored.
  • the monitoring can be cloud-based, i.e. for example by means of the server 81. This can enable parallel monitoring of several battery systems.
  • a plurality of status data pertaining to different components of the battery system is received. For example, two could or more of the status data 551-556 of the battery system 501 from the example in FIG. 2 are received. Exemplary state data has also been related to TAB. 2 described.
  • the machine-learned algorithm may be applied to the plurality of status data to determine such a status indicator.
  • This status indicator can indicate whether the battery system is working properly or whether there is an error. This can be done as part of an anomaly detection; however, different error states can also be classified. For example, it would be possible for the status indicator to be indicative of a component that originally causes a recognized error status.
  • a corresponding machine-learned algorithm 560 is described in connection with FIG. 6 schematically illustrated.
  • the machine-learned algorithm 560 determines a status indicator 601. This is indicative of an error status. For example--if an error condition is present--it could be indicated whether this error condition originally occurs in the energy storage component 511 or in the housing component 512 (compare FIG. 2).
  • FIG. 7 illustrates aspects related to the machine-learned algorithm 560.
  • the machine-learned algorithm is implemented using a regression algorithm 651.
  • the different object points are shown and the previously trained dependency is illustrated as a solid line.
  • the object point 641 has a significant deviation from the dependency between the status data 551 and the status data 552 and can therefore be identified as describing an error status.
  • error statuses in particular that correspond to imminent errors could be recognized.
  • a distance of the corresponding object point from the predetermined dependency could increase continuously and this increase could be monitored, which could correspond to the imminent error.
  • the distance between the object point 641 and the dependency of the regression algorithm 651 indicates a quantitative operating restriction of the battery system due to the corresponding error state.
  • quantitative statements can also be made available in connection with the fault status via the status indicator.
  • the machine-learned algorithm 560 i.e. in particular the dependency of the regression algorithm 651, is learned based on training status data, during the training phase from block 3055.
  • This training status data can be obtained, for example, from a single battery system as a function of time and corresponding variants that occur in normal, error-free operation, such as the aging of components such as the energy storage component in particular.
  • training condition data from a single battery system as a function of time, it would be possible to obtain training condition data from multiple battery systems of the same type - ie an ensemble - to get. Training details will be discussed later in connection with FIG. 10 described.
  • the machine learned algorithm of FIG. 7 - implemented as a regression algorithm 651 - is just an example.
  • a prediction for health data could also be made based on other health data and then the prediction for the health data can be compared to the actual health data for the corresponding component. In this way, your error status can be detected in the corresponding component.
  • a corresponding example is given below in connection with FIG. 8 described.
  • FIG. 8 illustrates aspects related to a machine-learned algorithm 652 that can be used to monitor one or more battery systems of an ensemble.
  • the machine-learned algorithm 652 could be implemented as an artificial neural network, see TAB. 3.
  • the machine-learned algorithm may make a prediction for health data of one component of the battery system based on further health data of another component of the battery system. So again - comparable to the scenario of FIG. 7 - Correlations between the various status data of different components are exploited. If the prediction for the status data deviates from the actual status data of the corresponding component, such an error can be detected. For example, threshold analysis could be used to determine a corresponding deviation. Depending on whether a corresponding predefined threshold value is exceeded or not reached by a difference between the modeled status data and the actual status data as a result of the threshold analysis, the corresponding status indicator can be obtained, which can be indicative of a quantitative severity of the error status.
  • the machine-learned algorithm 652 from the example of FIG. 8 could - based on status data 551, which the charging or discharging rate of the battery cells of the energy storage compo- components 511 relate - the temperature of the cooling liquid upon entry into the energy storage component 511 and/or upon exit from the energy storage component 511 can be determined. It would then be possible to compare the actual measured temperature of the cooling liquid - indicated by the status data 553 - with the corresponding modeled values obtained from the machine-learned algorithm 652. A discrepancy between the output of the machine-learned algorithm 652 and the measurement data indicated by the status data 553 may be indicative of a fault condition in the cooling system component 513 . Examples of such errors would be, for example, errors in the control circuit for the refrigeration system, a pump failure, leakage, selection of the refrigeration cycle, etc.
  • Such a determination of the correlation between the status data 551 pertaining to the energy storage component 511 and the status data 553 pertaining to the cooling system component 513 is only one example. Additional or different correlations could also be determined, for example between the energy storage component 511 and the output component 514. For example, a switching time of an inverter of the output component 513 and/or an insulation resistance could be modeled using a corresponding machine-learned algorithm and compared to the corresponding measurements indicated by the state data 554 pertaining to the output component 514 . In this way, errors in the output component 514 - such as corrosion of contacts, degradation of the dielectrics in the cables, etc. - can be determined.
  • FIG. 9 illustrates aspects related to a machine-learned algorithm 653 that can be used to monitor a battery system.
  • the machine-learned algorithm 653 could be implemented as an artificial neural network, see TAB. 3.
  • the machine-learned algorithm 653 uses, as input, the state data 551, 553.
  • the machine-learned algorithm 653 outputs a status indicator 603, which indicates - for a corresponding point in time - the specific status of a component, here the energy storage component 511, for which the status data 551 is obtained, and the cooling system component 513, for which the status data 553 is obtained.
  • Exemplary statuses would be: "Component works” or "Component defective".
  • more differentiated states can also be described, for example "cooling system pump defective” or “coolant leakage”.
  • Several error states can also be detected at the same time.
  • suitable training state data that describes the operation of the battery system in the corresponding error state can be used to train the machine-learned algorithm 653 .
  • suitable training state data that describes the operation of the battery system in the corresponding error state.
  • FIG. 10 is a flow chart of a method according to various examples.
  • the method of FIG. 10 is used to train a machine-learned algorithm, such as one of the algorithms 560, 651-653 described above.
  • the method of FIG. 10 can be executed by a data processing device such as a server, for example the server 81 .
  • Training state data is used to train the machine-learned algorithm.
  • the training status data can be received from a battery system, with the status data then describing different operating statuses at different points in time.
  • the training status data could alternatively or additionally also be received from several battery systems of an ensemble (cf. FIG. 1) and such different describe drive states. In this way, typically variances in the training state data—for example due to normal aging—can be taken into account.
  • the training state data is optionally pre-processed.
  • rule-based filters could be employed to discard certain training state data a-priori.
  • certain training status data are based on obvious measurement errors and should therefore not be taken into account in the training.
  • the raw data contained in the status data could also be pre-processed, such as low-pass filtering to suppress high-frequency noise, etc.
  • Such a pre-processing of the training state data not only enables obvious measurement errors to be found, but it can also be possible to recognize training state data which describes an error state. For example, such status data could exceed limits defined in connection with the proper operation of the battery system.
  • So-called clustering can then optionally take place in block 3110 .
  • the so-called k-means algorithm can be used for this purpose, for example.
  • groups of objects formed by the multiple status data that relate to different components of the battery system but describe the same operating state of the battery system—can be recognized with little variance and/or similar properties within the complete dataset of the training status data.
  • Clustering can also be done without a-priori knowledge. Appropriate groups can be defined which then simplify the annotation—that is, the assignment of labels in block 3120.
  • Such clustering can also make it possible to identify training state data that describes an error state. For example, corresponding clusters could contain comparatively few object points and/or be at a comparatively large distance from neighboring clusters.
  • the simulation of training status data can take place.
  • predefined models for the corresponding components and/or the entire battery system can be used.
  • Exemplary simulation models would be, for example, an electrical-thermal model that describes the aging of a battery.
  • Other models would be, for example, physico-chemical models that relate to processes in battery cells of the energy storage component.
  • finite element simulations could be used to simulate heat transport.
  • Numerical techniques for simulating current flow in circuits could be used for the output component. Black box models could also be used.
  • simulation models can be used for the different components of the battery system.
  • simulation models that describe an interaction of the operation of different components can also be used.
  • corresponding simulation models could describe a coupling of the operation of the cooling system with the electrothermal behavior of battery cells. This is only an example.
  • such simulation models could be used to record the propagation of faults from component to component in the battery system by simulating corresponding time series.
  • complex error states can also be simulated, which affect a hierarchical influence on different components of the battery system (instead of just one individual component that is impaired during operation).
  • the models can simulate different properties.
  • the simulation models could simulate aging of battery cells in the energy storage component.
  • the capacity of the energy storage component typically decreases as a function of the operating time or the charging cycles.
  • the models could simulate error states, ie for example to simulate the failure of a specific functionality of a specific component. In this way it would be conceivable, for example, based on training status data describing a fault-free operating status of the corresponding component or of the battery system, to determine further training status data describing a fault state using a corresponding model.
  • training status data which describe an error-free status
  • these can be adapted so that a statement can be made about the appearance of the training status data when an error status is present.
  • the training status data are specific to the respective type of battery system, but on the other hand also depict error statuses.
  • a model that describes the behavior of battery cells of the energy storage component at different temperatures could receive an excessive temperature as an input parameter in order to model the influence of a fault status "cooling system defective" on the energy storage component.
  • This input of an increased temperature could be based on the modeling of the system temperature of the battery system, for example.
  • the system temperature of the battery system could be based on an assumption of a mass distribution of the various components with associated heat capacities and thermal conductivity in between the components.
  • a time-varying heat sink could be taken into account, where again the heat sink can be modeled as a function of the health of the cooling. For example, a leak in a coolant line could be simulated, correspondingly a decrease in coolant pressure, and correspondingly a decreasing cooling capacity over time. This can lead to an increase in the system temperature, which in turn is reflected with a time delay in an increase in the temperature in the various battery cells.
  • a first type can be used to simulate the operating behavior of individual components of the battery system, for example to simulate the electrothermal behavior of battery cells, etc.
  • a second type of simulation model can be used to simulate the coupling of the operating behavior between different components of the battery system. This means that it can be simulated, for example, how a change in the operating behavior in a first component affects a change in the operating behavior of a second component.
  • such different types of models can be used to simulate the overall operation of the battery system.
  • complex fault states of the battery system which not only affect individual components but also detect the propagation of faults along a fault propagation path, can be simulated in this way.
  • complex error states are often not or only partially detectable by means of measurements, due to the large number of potential error states and the irreversible nature of some error states.
  • training state data could be obtained for different operating states that relate to different aging states and/or different error states of the battery system.
  • correlations in the operation of the different components can be simulated when a fault condition occurs in one of the components. This means that a propagation of error states in the battery system can be simulated. Such correlations can then - as already mentioned above in connection with the various figures, in particular FIG. 9, explained - used to detect the error conditions.
  • training status data can natively describe the error states.
  • annotation can occur.
  • This means that appropriate labels are assigned to the training state data, which serves as the basis for the subsequent training in block 3120. These labels correspond to the training state indicators, which become indicative of the occurrence of an anomaly (compare FIG. 7 or FIG. 8) or the occurrence of a certain error state (compare FIG. 9) for a classifier, for example.
  • groups of objects obtained from the clustering in block 3110 can be annotated together - i.e., with a user interaction labeling each corresponding grouped training state data. This means that common label status indicators can be assigned for groups of training status data.
  • the actual training of the machine-learned algorithm then takes place in block 3125 .
  • an optimization method can be used, which modifies the various parameters of the machine-learned algorithm in several iterations until a corresponding loss function assumes a maximum or minimum value.
  • the loss function can describe a difference between the previously assigned label and the output of the machine-learned algorithm with the parameter values of the corresponding iteration.
  • the adjustment of the parameter values can be done in different ways, for example by backward propagation etc. Decision trees, random forest methods or so-called gradient boosting could be used.
  • a cloud-based monitoring strategy is used here, although at least parts of the logic can also be executed outside of the cloud.
  • the central collection of status data (“big data”) in the cloud enables further analysis options, for example in comparison to classic BMS functionality. While a BMS for monitoring functional safety can typically only monitor exceeding or falling below limit values, the solution described can be used by comparing the status data of different components, e.g. B. Detect anomalies. The required accuracy can be achieved with a large amount of status data that is available. In this way, anomalies in a single battery system can be detected if, for example, 50 other battery systems in an ensemble can serve as a reference. The more status data regarding variety and variance is available, the more error statuses can be learned and identified. Simulated data can provide a remedy for simpler system errors.
  • a typical BMS does not store historical data.
  • the solution described thus enables a comparison “across space” (between different memories) and “across time” (between different points in time).
  • the efficiency or efficiency of individual components can be calculated.
  • a poorer efficiency of individual components compared to the other components can thus be detected as a corresponding error status, which is described by a quantitative status indicator.
  • a suitable countermeasure for mitigating the error status can be selected in particular. This is especially true when compared to techniques that do not identify the causative component of a fault condition, but merely enumerate the components affected by a fault condition, but without a corresponding hierarchy described by a fault propagation path.
  • the features of the embodiments and aspects of the invention described above can be combined with one another. In particular, the features can be used not only in the combinations described, but also in other combinations or taken on their own, without leaving the field of the invention.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)

Abstract

Selon l'invention, plusieurs données d'état (41, 551-556) qui concernent différents composants (511-516) d'un système de batterie (91-96, 501) sont reçus. Un algorithme d'apprentissage automatique (560, 651, 652, 653) est appliqué à la pluralité de données d'état (41, 551-556) pour déterminer un indicateur d'état (99, 601, 602, 603) qui indique un composant (511-516) parmi la pluralité de composants (511-516) qui provoque initialement un état d'erreur du système de batterie (91-96, 501) respectif.
PCT/EP2022/051887 2021-01-27 2022-01-27 Mégadonnées pour la détection d'erreurs dans des systèmes de batterie WO2022162060A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102021101757.2A DE102021101757A1 (de) 2021-01-27 2021-01-27 Big-Data für Fehlererkennung in Batteriesystemen
DE102021101757.2 2021-01-27

Publications (1)

Publication Number Publication Date
WO2022162060A1 true WO2022162060A1 (fr) 2022-08-04

Family

ID=80168180

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2022/051887 WO2022162060A1 (fr) 2021-01-27 2022-01-27 Mégadonnées pour la détection d'erreurs dans des systèmes de batterie

Country Status (2)

Country Link
DE (1) DE102021101757A1 (fr)
WO (1) WO2022162060A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102022128833A1 (de) 2022-10-31 2024-05-02 Bayerische Motoren Werke Aktiengesellschaft Simulation eines elektrischen Energiespeichers

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170126027A1 (en) * 2015-11-02 2017-05-04 Samsung Electronics Co., Ltd. Battery management method and apparatus
WO2019127231A1 (fr) * 2017-12-28 2019-07-04 Intel Corporation Générateurs de données d'apprentissage et procédés d'apprentissage automatique
CN111090050A (zh) * 2020-01-21 2020-05-01 合肥工业大学 一种基于支持向量机和k均值的锂电池故障诊断方法
CN111157898A (zh) * 2020-01-07 2020-05-15 清华大学深圳国际研究生院 一种新能源车辆在线电池故障检测分析方法及装置
CN111222584A (zh) * 2020-01-15 2020-06-02 北京辉腾格勒石墨烯科技有限公司 基于大数据和深度神经网络的锂电池实时评估方法
US20200202643A1 (en) * 2018-12-20 2020-06-25 The Regents Of The University Of Colorado, A Body Corporate Systems And Methods To Diagnose Vehicles Based On The Voltage Of Automotive Batteries
WO2020137914A1 (fr) * 2018-12-28 2020-07-02 株式会社Ｇｓユアサ Dispositif de traitement de données, procédé de traitement de données et programme informatique

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102004004280B4 (de) 2004-01-27 2014-06-12 Audi Ag Verfahren zur Diagnose von Batterien
DE102019201207A1 (de) 2019-01-30 2020-07-30 Volkswagen Aktiengesellschaft Verfahren, Steuerung und Kraftfahrzeug

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170126027A1 (en) * 2015-11-02 2017-05-04 Samsung Electronics Co., Ltd. Battery management method and apparatus
WO2019127231A1 (fr) * 2017-12-28 2019-07-04 Intel Corporation Générateurs de données d'apprentissage et procédés d'apprentissage automatique
US20200202643A1 (en) * 2018-12-20 2020-06-25 The Regents Of The University Of Colorado, A Body Corporate Systems And Methods To Diagnose Vehicles Based On The Voltage Of Automotive Batteries
WO2020137914A1 (fr) * 2018-12-28 2020-07-02 株式会社Ｇｓユアサ Dispositif de traitement de données, procédé de traitement de données et programme informatique
US20220113354A1 (en) * 2018-12-28 2022-04-14 Gs Yuasa International Ltd. Data processing apparatus, data processing method and computer readable medium
CN111157898A (zh) * 2020-01-07 2020-05-15 清华大学深圳国际研究生院 一种新能源车辆在线电池故障检测分析方法及装置
CN111222584A (zh) * 2020-01-15 2020-06-02 北京辉腾格勒石墨烯科技有限公司 基于大数据和深度神经网络的锂电池实时评估方法
CN111090050A (zh) * 2020-01-21 2020-05-01 合肥工业大学 一种基于支持向量机和k均值的锂电池故障诊断方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ECKER, MADELEINE ET AL.: "Development of a lifetime prediction model for lithium-ion batteries based on extended accelerated aging test data", JOURNAL OF POWER SOURCES, vol. 215, 2012, pages 248 - 257, XP028433063, DOI: 10.1016/j.jpowsour.2012.05.012
SCHMALSTIEG, JOHANNES ET AL.: "A holistic aging model for Li (NiMnCo) 02 based 18650 lithium-ion batteries", JOURNAL OF POWER SOURCES, vol. 257, 2014, pages 325 - 334, XP028636618, DOI: 10.1016/j.jpowsour.2014.02.012

Also Published As

Publication number Publication date
DE102021101757A1 (de) 2022-07-28

Similar Documents

Publication Publication Date Title
DE102012102770B4 (de) System und Verfahren zur Fehlereingrenzung und Fehlerabschwächung basierend auf einer Netzwerkmodellierung
CN102208028B (zh) 一种适用于动态复杂系统的故障预测和诊断方法
EP1543394B1 (fr) Procede et dispositif pour surveiller une installation technique comprenant plusieurs systemes, notamment une centrale electrique
DE102011108678B4 (de) Ereignisgesteuertes Datamining-Verfahren zum Verbessern von Fehlercodeeinstellungen und zum Isolieren von Fehlern
DE69723839T2 (de) Überwachungssystem für industrielle anlage
DE19742446B4 (de) Fehlerdiagnoseverfahren
DE102020117609B4 (de) Verarbeitung von Zustandsdaten einer Batterie zur Alterungsschätzung
CN111709447A (zh) 电网异常检测方法、装置、计算机设备和存储介质
DE102011010605A1 (de) Funktionsprognose für ein komplexes System unter Verwendung der Fehlermodellierung
DE102017107284A1 (de) Verfahren und steuergerät zum überwachen eines bordnetzes eines fahrzeugs
CN111796233B (zh) 双母线接线形式下多台电压互感器继发性误差的评估方法
DE102019217613A1 (de) Verfahren zur diagnose eines motorzustands und diagnostisches modellierungsverfahren dafür
DE102020100668B4 (de) Charakterisierung von wiederaufladbaren Batterien mit Maschinen-gelernten Algorithmen
DE102019215413A1 (de) Funktionstüchtigkeit-selbstlernsystem und verfahren für stromverteilungssysteme für automatisch fahrende fahrzeuge
DE102019001760A1 (de) Informationsverarbeitungsgerät, maschinelle lernvorrichtungund system
DE102021006561A1 (de) Big-Data für Fehlererkennung in Batteriesystemen
EP4031886A1 (fr) Valeur d'état pour batteries rechargeables
CN114994543A (zh) 储能电站电池故障诊断方法、装置及存储介质
WO2022162060A1 (fr) Mégadonnées pour la détection d'erreurs dans des systèmes de batterie
DE102019212909A1 (de) Verfahren zum Detektieren eines Fehlers in einem Batteriesystem sowie Batteriesystem und Kraftfahrzeug
DE102018132658A1 (de) Verfahren zur rechnergestützten Auswertung einer Messung einer elektrischen Größe in einem Hochvolt-Bordnetz eines vorgegebenen elektrisch angetriebenen Kraftfahrzeugs
EP4168813A1 (fr) Détermination d'un état de santé d'un accumulateur d'énergie
DE102021114087A1 (de) Selektive Meldesysteme für Funktionszustandsinformationen, die integrierte Diagnosemodelle enthalten, die Informationen über die geringst- und höchstmögliche Ursache bereitstellen
DE102018210411A1 (de) Verfahren zum Überprüfen eines in einem Batteriesystem erfassten Temperaturmesswertes und Batteriesystem
DE19742448C1 (de) Diagnosemodul zum Erstellen einer Diagnose für elektrisch ansteuerbare Systeme und Diagnoseeinrichtung zum Erstellen einer Gesamtsystemdiagnose

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: 22702256

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22702256

Country of ref document: EP

Kind code of ref document: A1