A method and apparatus for identifying battery thermal runaway

Abstract

This invention discloses a method and apparatus for identifying battery thermal runaway. The method includes acquiring battery state information; determining at least one target thermal runaway identification model from a set of preset thermal runaway identification models based on the battery state information (the thermal runaway identification model is related to an application scenario and / or data type); inputting the battery state information into the at least one target thermal runaway identification model to obtain corresponding identification results; and determining the thermal runaway state of the corresponding battery based on the at least one identification result. In this method, multiple thermal runaway identification models are pre-trained based on different application scenarios and / or data types to adapt to battery state information containing different data types. Multiple thermal runaway identification models are first matched based on the battery state information, and then thermal runaway identification is performed using the thermal runaway identification models. By comprehensively considering multiple identification results to determine the thermal runaway state, the accuracy of battery thermal runaway identification can be improved.

Description

Technical Field

[0001] This invention relates to the field of battery technology, and more specifically, to a method and apparatus for identifying battery thermal runaway. Background Technology

[0002] With the global energy crisis and the push for "dual-carbon" goals, electric vehicles, as representatives of clean energy, have experienced rapid development. However, battery thermal runaway has remained a key factor hindering the further development of electric vehicles. Thermal runaway refers to a chain reaction of exothermic reactions within the battery, causing a rapid rise in battery temperature. In severe cases, it can lead to battery fire or explosion, posing a serious threat to the lives and property of passengers. Therefore, the identification of battery thermal runaway is crucial.

[0003] Current methods for identifying battery thermal runaway include manual inspection and single-point identification by the battery management system (BMS). Manual inspection relies on subjective judgment, lacks standardized procedures, and is prone to inadequate execution, missed detections, and false alarms. Single-point identification by the BMS, which uses information from a single battery to determine its status, suffers from serious false alarm problems. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a battery thermal runaway identification method and apparatus, which combine application scenarios and comprehensively consider the identification results corresponding to multiple factors to determine the thermal runaway state, thereby improving the accuracy of battery thermal runaway identification.

[0005] In a first aspect, embodiments of the present invention provide a battery thermal runaway identification method, the method comprising:

[0006] Obtain battery status information;

[0007] Based on the battery state information, at least one target thermal runaway identification model is determined from a plurality of preset thermal runaway identification models, wherein the thermal runaway identification model is related to the application scenario and / or data type;

[0008] The battery state information is input into the at least one target thermal runaway identification model to obtain the corresponding identification results;

[0009] The thermal runaway state of the corresponding battery is determined based on at least one of the identification results.

[0010] In a second aspect, embodiments of the present invention provide a battery thermal runaway identification device, the device comprising:

[0011] The acquisition module is used to acquire battery status information;

[0012] The first determining module is used to determine at least one target thermal runaway identification model from a plurality of preset thermal runaway identification models based on the battery state information. The thermal runaway identification model is related to the application scenario and / or data type.

[0013] The identification module is used to input the battery state information into the at least one target thermal runaway identification model to obtain the corresponding identification results;

[0014] The second determining module is used to determine the thermal runaway state of the corresponding battery based on at least one of the identification results.

[0015] Thirdly, an electronic device is provided, including a memory and a processor, the memory being used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in the first aspect above.

[0016] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the method described in the first aspect.

[0017] Fifthly, a computer program product is provided, comprising a computer program / instructions that, when executed by a processor, implement the method described in the first aspect above.

[0018] This invention includes acquiring battery state information, determining at least one target thermal runaway identification model from a set of preset thermal runaway identification models based on the battery state information, wherein the thermal runaway identification model is related to the application scenario and / or data type, inputting the battery state information into the at least one target thermal runaway identification model respectively to obtain the corresponding identification result, and determining the thermal runaway state of the corresponding battery based on the at least one identification result. In the above scheme, multiple thermal runaway identification models are pre-trained based on different application scenarios and / or data types to adapt to battery state information containing different data types. Multiple thermal runaway identification models are first matched based on the battery state information, and then thermal runaway identification is performed using the thermal runaway identification model. The thermal runaway state is determined by comprehensively considering multiple identification results, which can improve the accuracy of battery thermal runaway identification. Attached Figure Description

[0019] The above and other objects, features and advantages of the present invention will become clearer from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0020] Figure 1 This is a schematic diagram of a battery thermal runaway identification system according to an embodiment of the present invention;

[0021] Figure 2This is a flowchart of the battery thermal runaway identification method according to an embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram illustrating the thermal runaway identification model according to an embodiment of the present invention;

[0023] Figure 4 This is a flowchart of the target thermal runaway identification model processing procedure according to an embodiment of the present invention;

[0024] Figure 5 This is a schematic diagram of the index tree corresponding to the target thermal runaway identification model in an embodiment of the present invention;

[0025] Figure 6 This is a schematic diagram of the index tree corresponding to the target thermal runaway identification model in an embodiment of the present invention;

[0026] Figure 7 This is a schematic diagram of the index tree corresponding to the target thermal runaway identification model in an embodiment of the present invention;

[0027] Figure 8 This is a schematic diagram of the index tree corresponding to the target thermal runaway identification model in an embodiment of the present invention;

[0028] Figure 9 This is a schematic diagram of a battery thermal runaway identification device according to an embodiment of the present invention;

[0029] Figure 10 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0030] The present application is described below based on embodiments, but it is not limited to these embodiments. In the detailed description of the present application below, certain specific details are described in detail. Those skilled in the art can fully understand the present application without these details. To avoid obscuring the substance of the present application, well-known methods, processes, flows, elements, and circuits are not described in detail.

[0031] Furthermore, those skilled in the art should understand that the accompanying drawings provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0032] Unless the context explicitly requires it, words such as "including" or "contains" throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, meaning "including but not limited to".

[0033] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0034] The solutions described in this specification and embodiments, if involving the processing of personal information, will be processed only under the premise of having a legal basis (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be processed within the scope stipulated or agreed upon. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0035] Figure 1 This is a schematic diagram of a battery thermal runaway identification system according to an embodiment of the present invention. Figure 1 As shown, the battery thermal runaway identification system 100 includes a server 101 and a data acquisition device 102.

[0036] In this embodiment, server 101 is a general-purpose data processing device that provides computing or application services for the battery thermal runaway identification platform. It can be a single computer, a cluster of multiple computers, or a cloud server that can flexibly adjust computing resources through cloud technology. Data acquisition device 102 is a general-purpose data acquisition device that provides battery status information acquisition for the battery thermal runaway identification platform. It can be a battery-using device or a battery storage device. For example, the battery-using device can be an electric vehicle, such as an electric car or an electric two-wheeler, and the battery storage device can be a charging cabinet. Since the battery does not have data interaction capabilities, it is necessary to use battery-related devices to collect the battery status information.

[0037] Battery thermal runaway refers to a phenomenon where, under specific conditions, the heat generated by internal chemical reactions exceeds the battery's heat dissipation capacity, causing the battery temperature to rise sharply. This triggers a series of irreversible chemical reactions, which may ultimately lead to the battery catching fire or exploding.

[0038] The battery thermal runaway identification method in this embodiment is applicable to various application scenarios. For example, based on the classification of battery thermal runaway process, battery thermal runaway identification can be divided into battery thermal runaway hazard identification and battery thermal runaway fault identification. Battery thermal runaway hazard identification refers to identifying potential hazards on the data acquisition device 102 that may lead to battery thermal runaway, providing early warnings, and preventing actual battery thermal runaway faults from occurring. Battery thermal runaway fault identification refers to detecting thermal runaway accidents as early as possible, thereby notifying human intervention as soon as possible. In addition, there is a classification based on the number of batteries, where battery thermal runaway identification can be divided into single-battery thermal runaway identification and multi-battery thermal runaway identification, or single-vehicle thermal runaway identification and multi-vehicle thermal runaway identification. Single-battery thermal runaway identification refers to monitoring and identifying the thermal runaway state of a single battery. Multi-battery thermal runaway identification refers to the simultaneous monitoring and identification of thermal runaway states in multiple batteries within a battery pack. Because thermal runaway in one battery can trigger a chain reaction in others, multi-battery thermal runaway identification requires more complex monitoring algorithms for accurate identification. Single-vehicle thermal runaway identification refers to the monitoring and identification of thermal runaway states in the power battery of a single electric vehicle. Multi-vehicle thermal runaway identification refers to the simultaneous monitoring and identification of thermal runaway states in the power batteries of multiple electric vehicles within a system consisting of one or more electric vehicles.

[0039] It is worth noting that the application scenarios of the different categories mentioned above can be superimposed on each other. For example, identifying potential battery thermal runaway hazards for a single battery or identifying battery thermal runaway faults for multiple vehicles, etc.

[0040] In this embodiment, server 101 acquires battery status information collected by data acquisition device 102 via the network, thereby realizing battery thermal runaway identification. Since data acquisition device 102 and / or battery models are different, the battery status information collected by data acquisition device 102 may differ. Simultaneously, due to different application scenarios, the battery status information collected by data acquisition device 102, or the information within that battery status information that can be used for battery thermal runaway identification, may also differ. Server 11 can match at least one suitable thermal runaway identification model based on battery status information collected by different data acquisition devices 102 or different types of battery status information collected by the same data acquisition device 102, thereby completing the analysis of battery status information based on the matched thermal runaway identification model, and determining the battery's thermal runaway state based on the analysis results of at least one thermal runaway identification model.

[0041] In one possible implementation, the thermal runaway state can reflect the actual application scenario of the corresponding battery, that is, the battery thermal runaway process and / or the number of batteries. For example, the thermal runaway state can include no thermal runaway risk, thermal runaway risk, no thermal runaway fault, and thermal runaway fault, etc. Alternatively, the thermal runaway state can also include mass battery thermal runaway, which indicates that the corresponding battery is in a multi-battery or multi-vehicle spontaneous combustion scenario.

[0042] The system of this invention acquires battery state information and, based on this information, determines at least one target thermal runaway identification model from a set of preset thermal runaway identification models. Each thermal runaway identification model is related to an application scenario and / or data type. The battery state information is input into each of the at least one target thermal runaway identification models to obtain corresponding identification results. The thermal runaway state of the corresponding battery is determined based on at least one of the identification results. In this scheme, multiple thermal runaway identification models are pre-trained based on different application scenarios and / or data types to adapt to battery state information containing different data types. Multiple thermal runaway identification models are first matched based on the battery state information, and then thermal runaway identification is performed using these models. By comprehensively considering multiple identification results to determine the thermal runaway state, the accuracy of battery thermal runaway identification can be improved.

[0043] Figure 2 This is a flowchart of a battery thermal runaway identification method according to an embodiment of the present invention. Figure 2 As shown, the battery thermal runaway identification method includes the following steps:

[0044] Step S201: Obtain battery status information.

[0045] Among them, battery status information is battery-related information that can indicate whether the battery has thermal runaway. The battery status information includes at least one of the following: vehicle model, voltage, current, temperature, battery model, charging status, and heartbeat message.

[0046] Different vehicle models may use different battery types, and the standard voltage, current, and temperature during vehicle operation may also be different. In addition, the data format, reporting method, and content of the heartbeat message may also be different for different vehicle models. Therefore, vehicle model has an impact on the matching of thermal runaway identification models and the identification of battery thermal runaway.

[0047] Voltage is one of the key indicators for assessing battery thermal runaway. During thermal runaway, short circuits and leakage may occur inside the battery, leading to a voltage drop. Under normal operating conditions, battery voltage should fluctuate within a certain range. If the battery voltage suddenly drops or rises outside the normal range, it may indicate a risk of thermal runaway. Furthermore, different types of thermal runaway triggering mechanisms (such as mechanical abuse, electrical abuse, and thermal abuse) will result in different voltage change patterns.

[0048] An abnormal increase in current is also one of the signs of battery thermal runaway. When a short circuit or malfunction occurs inside the battery, the current may rise sharply.

[0049] Temperature is the most direct and important parameter for determining battery thermal runaway. A sharp rise in the internal temperature of the battery is a clear sign of thermal runaway. By placing temperature sensors inside and outside the battery, the battery temperature can be monitored. When the temperature exceeds a certain threshold, it indicates that a thermal runaway state may exist.

[0050] Different battery models can affect their thermal runaway characteristics and triggering conditions. Different battery models differ in materials, structure, and capacity, which can lead to different behaviors during thermal runaway. For example, some battery models may have higher thermal stability or a lower risk of thermal runaway. Therefore, the influence of the battery model must be considered when determining whether a battery has experienced thermal runaway.

[0051] The state of charge (SOC) of a battery is also a crucial factor in assessing thermal runaway. Overcharging or prolonged periods of high charging can lead to excessive internal pressure within the battery, potentially triggering thermal runaway. Conversely, deep discharge can also increase the risk of thermal runaway due to capacity decay. Therefore, it is essential to properly control the battery's SOC to prevent thermal runaway.

[0052] Heartbeat messages are commonly used for communication within a battery management system (BMS). A continuous stream of heartbeat messages indicates that the corresponding battery has not yet suffered damage to the communication module due to thermal runaway or spontaneous combustion.

[0053] It is worth noting that the battery status information mentioned above is only an example. The electric state information can be any battery-related information that can reflect whether the battery has thermal runaway. This embodiment does not limit the electric state information.

[0054] Step S202: Based on the battery state information, determine at least one target thermal runaway identification model from a set of preset thermal runaway identification models.

[0055] The thermal runaway identification model is related to the application scenario and / or data type. The application scenarios include at least one of thermal runaway hazard identification, thermal runaway fault identification, single-cell thermal runaway, and multi-cell thermal runaway, with each application scenario corresponding to at least one thermal runaway identification model. Different thermal runaway identification models can input different data types. Therefore, a thermal runaway identification model can be matched based on the data type.

[0056] The thermal runaway identification model is composed of an index tree, which contains multiple layers of indices. An index is the smallest unit that constitutes the thermal runaway identification model. Each model is composed of different combinations of indices, which may have hierarchical dependencies or parallel relationships. One index represents one input, calculation, and output process.

[0057] Figure 3 This is a schematic diagram illustrating the thermal runaway identification model according to an embodiment of the present invention. Figure 3 As shown, the thermal runaway identification model consists of a three-layer index tree, with the first layer containing 9 indicators, the second layer containing 8 indicators, and the third layer containing 1 indicator.

[0058] Indicators 1-9 are parallel, meaning they can be performed simultaneously. Indicators 5 and 12 are dependent on each other, meaning that indicator 12 can only be judged after indicator 5 is hit (i.e., satisfied).

[0059] It should be noted that, Figure 3 The indicator tree shown is for illustrative purposes only. In actual applications, the number of layers in the indicator tree and the number and content of indicators in each layer can be determined according to the actual situation. The indicator tree structure of the preset thermal runaway identification model is different.

[0060] In one possible implementation, the thermal runaway identification model is built based on historical battery state information and various real-world thermal runaway events. The model evaluates the battery state from multiple dimensions, including charge, voltage, and temperature. When a battery experiences thermal runaway, there can be a variety of complex situations, and the data reported by the vehicle has a temporal relationship. Therefore, thermal runaway identification models applicable to different application scenarios can be developed accordingly.

[0061] In one possible implementation, the input data types of each preset thermal runaway identification model can be determined first. In response to the data type of the battery state information containing the input data type, the thermal runaway identification model is determined as the target thermal runaway model. That is, the input data types of each constructed thermal runaway identification model are first determined, and then the data types contained in the acquired battery state information are matched with the input data types of each model. If a match is successful, it is determined that the model can be used to analyze and process the battery state information.

[0062] Step S203: Input the battery state information into the at least one target thermal runaway identification model to obtain the corresponding identification results.

[0063] Figure 4 This is a flowchart illustrating the target thermal runaway identification model processing procedure according to an embodiment of the present invention. Figure 4As shown, after inputting the battery state information into the at least one target thermal runaway identification model, the processing procedure of each target thermal runaway identification model includes the following steps:

[0064] Step S401: Starting from the first layer of the indicator tree, determine the hit status of each indicator in each layer until the top layer is determined.

[0065] Specifically, the hit status of the Nth layer indicator of the indicator tree is determined, where N is a positive integer. In response to the hit status of the Nth layer indicator being hit, the hit status of the indicator at the (N+1)th layer is determined, until the hit status of the top layer indicator is determined.

[0066] In one possible implementation, determining the hit status corresponding to each indicator of the corresponding layer specifically involves: determining the hit conditions corresponding to each layer indicator, wherein the types of the hit conditions include data filtering, data analysis, data judgment and / or data aggregation, and in response to the battery status information satisfying the hit conditions, determining the hit status as a hit.

[0067] Data filtering refers to the operations of screening, cleaning, and validating data during data processing. Data filtering is typically used to exclude data from the original dataset that does not meet requirements or may mislead the analysis results. Specifically, data filtering indicators can be conditions such as "find a specific battery model" or "find a specific car model." For a data filtering type's hit condition, a hit status is achieved when the filtering is completed and corresponding data exists after filtering.

[0068] Data analysis refers to a series of analytical operation commands during the data analysis process. Specifically, the corresponding indicators for data analysis can be conditions such as "determine the vehicle's voltage change rate over the past 7 minutes" or "determine the battery's lowest temperature over the past 10 minutes." For data analysis types of conditions, the existence of data analysis results indicates a successful hit.

[0069] Data judgment refers to the judgment operation instructions in the data analysis process. Specifically, the corresponding indicators for data judgment can be conditions such as "whether the number of times the vehicle has had location data in the last 7 minutes is 0" or "whether the vehicle's last temperature is in the battery's low temperature range". For the hit condition of the data judgment type, if the judgment result is "yes", the corresponding hit status is "hit".

[0070] Data aggregation refers to the data aggregation operation command in the data analysis process. Specifically, the corresponding indicators for data aggregation can be conditions such as "determining the total current of multiple battery cells in a battery" or "determining the average temperature of multiple thermal sensors." For data aggregation type hit conditions, if the data aggregation is successful, the corresponding hit status is "hit".

[0071] Step S402: Determine the corresponding recognition result based on the hit status of the top-level indicator.

[0072] The following section discusses the application scenarios and model processing procedures of the target thermal runaway identification model. Figure 4 The method shown will be explained.

[0073] Figure 5 and Figure 6 The application scenario of the target thermal runaway identification model is to identify potential hazards that may lead to battery thermal runaway, provide early warnings, and prevent actual battery thermal runaway failures. Its principle is as follows: Batteries store and discharge electricity through chemical reactions, and these chemical reactions inevitably result in energy loss, such as battery temperature rise. When a battery malfunctions, such as a short circuit or water immersion, abnormal indicators will appear in the chemical reactions compared to normal energy storage and discharge. These indicators mainly include changes in battery temperature and voltage. By collecting and analyzing these indicators, a model is constructed accordingly. Figure 5 and Figure 6 The model shown.

[0074] Figure 5 This is a schematic diagram of the index tree corresponding to the target thermal runaway identification model in an embodiment of the present invention. Figure 5 As shown, the battery status information includes the battery model, voltage, and temperatures collected by multiple temperature sensors. The processing procedure of the target thermal runaway identification model corresponding to the index tree includes:

[0075] First, determine whether the battery model is a preset battery model corresponding to the target thermal runaway identification model. If this indicator is hit, meaning the battery model is a preset battery model corresponding to the target thermal runaway identification model, then further determine the second-layer indicator, that is, determine whether the voltage is within a preset voltage range. Simultaneously, determine the temperatures collected by the multiple temperature sensors. If this indicator is hit, meaning there are temperatures collected by five temperature sensors, then further determine the second-layer indicator, that is, determine whether the temperatures collected by the five temperature sensors are within a first preset temperature range. If all second-layer indicators are hit, meaning the voltage is within the preset voltage range, and the temperatures collected by the multiple temperature sensors are all within the first preset temperature range, then the second-layer indicator is hit, meaning the identification result is determined to be a temperature anomaly.

[0076] pass Figure 5 The target thermal runaway identification model shown can determine whether the temperature is abnormal, and thus determine the thermal runaway state based on the abnormal temperature.

[0077] Figure 6 This is a schematic diagram of the index tree corresponding to the target thermal runaway identification model in an embodiment of the present invention. Figure 6The battery status information includes the battery model and the voltage corresponding to each of the multiple cells. The processing procedure of the target thermal runaway identification model corresponding to the index tree includes:

[0078] The hit determination of the first-level indicator includes:

[0079] Determine whether the battery model is the preset battery model corresponding to the target thermal runaway identification model. If the hit status of this indicator is hit, it means that the battery model is the preset battery model corresponding to the target thermal runaway identification model.

[0080] Determine whether the voltage corresponding to each of the battery cells is within the second preset temperature range. If the indicator hits, it means that the voltage corresponding to the battery cell is within the second preset temperature range, further indicating that the battery cell is an abnormal battery cell.

[0081] The hit determination of the second-level indicator includes:

[0082] Determine whether the number of abnormal battery cells is within the first preset quantity range. If the hit status of this indicator is hit, it means that the number of abnormal battery cells is within the first preset quantity range.

[0083] Based on the positional relationship between the battery cells, it is determined whether the number of adjacent abnormal battery cells is within the second preset number range. If the hit status of this indicator is hit, it means that the number of adjacent abnormal battery cells is determined to be within the second preset number range.

[0084] The hit determination of the third-layer indicator includes: in response to the fact that the battery model is a preset battery model corresponding to the target thermal runaway identification model, the number of abnormal cells is within the first preset number range, and whether the number of adjacent abnormal cells is within the second preset number range, the identification result is determined to be a voltage abnormality.

[0085] pass Figure 5 The target thermal runaway identification model shown can determine whether the voltage is abnormal, and thus determine the thermal runaway state based on the abnormal voltage.

[0086] Figure 7 and Figure 8 The application scenario of the target thermal runaway identification model shown is: to detect thermal runaway accidents as early as possible to drive rapid offline intervention. Its principle is as follows: When a vehicle experiences battery thermal runaway, the battery will rapidly and spontaneously combust within a very short time, and this process continues until the entire vehicle is engulfed. Before thermal runaway, the battery's state, including charge, voltage, and temperature, is affected by chemical reactions, producing abnormal indicators, and these indicators change over time. Furthermore, if an accident occurs and the vehicle spontaneously combusts, it will eventually lose communication (the vehicle, except for the frame, will be completely burned, thus preventing communication between the vehicle's central control system and the cloud). Therefore, we will use two models (i.e.,... Figure 7 and Figure 8 The model shown is used for linkage identification to improve accuracy while ensuring recall.

[0087] Figure 7 This is a schematic diagram of the index tree corresponding to the target thermal runaway identification model in an embodiment of the present invention. Figure 7 As shown, the battery status information includes voltage, heartbeat messages, and maintenance operation records. The processing procedure of the target thermal runaway identification model corresponding to the index tree includes:

[0088] The hit determination of the first-level indicator includes:

[0089] Confirm heartbeat message.

[0090] Determine the number of times the voltage was >20000mV in the past 20 minutes.

[0091] Determine if the heart rate of >20000mv in the last 3 minutes is 0.

[0092] Determine if the heart rate has been 0 for the past 30 minutes due to low energy.

[0093] Determine the heart rate over the past 30 minutes.

[0094] Confirm offline operation and maintenance records.

[0095] The hit determination of the second-level indicator includes:

[0096] Determine if the number of times the voltage is >20000mV in the past 20 minutes accounts for 80% of the total battery pack heartbeats.

[0097] Did you report more than x times?

[0098] Determine if the heart rate over the past 5 minutes, when the voltage is >20000mV, is greater than y times.

[0099] Determine if the heart rate is 0 within the last 3 minutes when the voltage is >20000mV.

[0100] Determine if the heart rate has been 0 for the past 30 minutes due to low energy.

[0101] The vehicle was confirmed to be in maintenance mode and the central control backup power was normal.

[0102] Determine if there are no offline maintenance operation records in the past 15 minutes.

[0103] The third-level indicator hit judgment includes: confirming that the vehicle has lost power and generating a suspected vehicle thermal runaway alarm event.

[0104] The hit status of each indicator can be determined as explained in the above embodiments, and will not be repeated here. The specific values ​​mentioned above, such as voltage values, time, and quantities, are only examples and can be set and adjusted according to actual conditions.

[0105] pass Figure 7 The target thermal runaway identification model shown can determine the thermal runaway state of the battery in a vehicle by whether the vehicle is powered off.

[0106] Figure 8 This is a schematic diagram of the index tree corresponding to the target thermal runaway identification model in an embodiment of the present invention. Figure 8 As shown, the battery status information includes voltage and heartbeat messages, and the processing procedure of the target thermal runaway identification model corresponding to the index tree includes:

[0107] Upon receiving a suspected vehicle alarm, the system will begin collecting battery status information after a preset delay; this is the first level of indicator.

[0108] Specifically, the hit determination of the first-level indicators includes:

[0109] Determine the vehicle battery pack data. This data includes information such as voltage and current.

[0110] Determine the battery management system upgrade history.

[0111] Determine the vehicle's GEO information. Vehicle GEO information refers to data obtained through specific technologies (such as GPS, Wi-Fi, cellular networks, etc.) that reflects the vehicle's historical geographical location. This data includes the vehicle's longitude, latitude, altitude, speed, and direction, and is a crucial foundation for vehicle tracking, monitoring, and management.

[0112] Determine information such as vehicle battery temperature.

[0113] The hit determination of the second-level indicator includes:

[0114] Determine if the number of times the vehicle reports location data within 7 minutes is 0.

[0115] Determine if the number of times the vehicle reports the battery pack within 7 minutes is 0.

[0116] Determine if the vehicle model is a preset model (excluding specific models).

[0117] Determine if the number of system upgrades within 12 hours is 0.

[0118] Determine whether GEO information exists in suspected vehicle warning events.

[0119] Determine if the vehicle's final temperature falls within the battery's low-temperature range.

[0120] The third-level indicator hit judgment includes: confirming that a single vehicle has lost power.

[0121] The hit status of each indicator can be determined as explained in the above embodiments, and will not be repeated here. The specific values ​​mentioned above, such as voltage values, time, and quantities, are only examples and can be set and adjusted according to actual conditions.

[0122] It is worth noting that the above Figures 5-8 The models shown are merely examples, and no restrictions are placed on the composition of the indicator tree.

[0123] Step S204: Determine the thermal runaway state of the corresponding battery based on at least one of the identification results.

[0124] In one possible implementation, the identification results can be sorted according to the priority of the target thermal runaway identification model, and the thermal runaway state can be determined based on the sorting results.

[0125] In one possible implementation, the thermal runaway state can also be determined by weighted summation of the identification results of multiple target thermal runaway identification models.

[0126] In one possible implementation, once it is determined that the current battery is in a state of thermal runaway, a corresponding work order can be generated to prompt staff to intervene offline.

[0127] The method of this invention includes acquiring battery state information, determining at least one target thermal runaway identification model from a plurality of preset thermal runaway identification models based on the battery state information, wherein the thermal runaway identification model is related to the application scenario and / or data type, inputting the battery state information into the at least one target thermal runaway identification model respectively to obtain the corresponding identification result, and determining the thermal runaway state of the corresponding battery based on at least one of the identification results. In the above method, a plurality of thermal runaway identification models are pre-trained based on different application scenarios and / or data types to adapt to battery state information containing different data types. The method first matches multiple thermal runaway identification models based on the battery state information, and then uses the thermal runaway identification models to perform thermal runaway identification. By comprehensively considering multiple identification results to determine the thermal runaway state, the accuracy of battery thermal runaway identification can be improved.

[0128] Figure 9 This is a schematic diagram of a battery thermal runaway identification device according to an embodiment of the present invention. Figure 9 As shown, the battery thermal runaway identification device includes:

[0129] The acquisition module 901 is used to acquire battery status information.

[0130] The first determining module 902 is used to determine at least one target thermal runaway identification model from a plurality of preset thermal runaway identification models based on the battery state information. The thermal runaway identification model is related to the application scenario and / or data type.

[0131] The identification module 903 is used to input the battery state information into the at least one target thermal runaway identification model to obtain the corresponding identification results.

[0132] The second determining module 904 is used to determine the thermal runaway state of the corresponding battery based on at least one of the identification results.

[0133] The device in this embodiment of the invention acquires battery state information and, based on the battery state information, determines at least one target thermal runaway identification model from a plurality of preset thermal runaway identification models. The thermal runaway identification model is related to the application scenario and / or data type. The battery state information is input into the at least one target thermal runaway identification model to obtain corresponding identification results. The thermal runaway state of the corresponding battery is determined based on at least one of the identification results. In the above scheme, multiple thermal runaway identification models are pre-trained based on different application scenarios and / or data types to adapt to battery state information containing different data types. Multiple thermal runaway identification models are first matched based on the battery state information, and then thermal runaway identification is performed using the thermal runaway identification models. By comprehensively considering multiple identification results to determine the thermal runaway state, the accuracy of battery thermal runaway identification can be improved.

[0134] Figure 10 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Figure 10 As shown, Figure 10 The illustrated electronic device is a battery thermal runaway detection device, which includes a general computer hardware architecture, comprising at least a processor 1001 and a memory 1002. The processor 1001 and memory 1002 are connected via a bus 1003. The memory 1002 is adapted to store instructions or programs executable by the processor 1001. The processor 1001 can be a standalone microprocessor or a collection of one or more microprocessors. Thus, the processor 1001 executes the instructions stored in the memory 1002, thereby performing the method flow of the embodiments of the present invention as described above to process data and control other devices. The bus 1003 connects the aforementioned components together, and also connects the aforementioned components to a display controller 1004, a display device, and an input / output (I / O) device 1005. The input / output (I / O) device 1005 can be a mouse, keyboard, modem, network interface, touch input device, motion-sensing input device, printer, and other devices known in the art. Typically, the input / output device 1005 is connected to the system via an input / output (I / O) controller 1006.

[0135] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus (devices), or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] This application is described with reference to flowchart illustrations of methods, apparatus (devices), and computer program products according to embodiments of this application. It should be understood that each step in the flowchart can be implemented by computer program instructions.

[0137] These computer program instructions may be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction means, the implementation process of which is described in the instruction means. Figure 1 The function specified in one or more processes.

[0138] These computer program instructions may also be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, produce instructions for implementing processes. Figure 1 A device for a function specified in one or more processes.

[0139] This invention includes acquiring battery state information, determining at least one target thermal runaway identification model from a set of preset thermal runaway identification models based on the battery state information, wherein the thermal runaway identification model is related to the application scenario and / or data type, inputting the battery state information into the at least one target thermal runaway identification model respectively to obtain the corresponding identification result, and determining the thermal runaway state of the corresponding battery based on the at least one identification result. In the above scheme, multiple thermal runaway identification models are pre-trained based on different application scenarios and / or data types to adapt to battery state information containing different data types. Multiple thermal runaway identification models are first matched based on the battery state information, and then thermal runaway identification is performed using the thermal runaway identification model. The thermal runaway state is determined by comprehensively considering multiple identification results, which can improve the accuracy of battery thermal runaway identification.

[0140] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program for use by a computer to execute some or all of the above-described method embodiments.

[0141] Another embodiment of the present invention relates to a computer program product, including a computer program / instructions for storing a computer-readable program, wherein the computer program / instructions, when executed by a processor, implement some or all of the method embodiments described above.

[0142] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program specifying the relevant hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0143] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A battery thermal runaway identification method, characterized in that, The method includes: Obtain battery status information; Based on the battery state information, at least one target thermal runaway identification model is determined from a plurality of preset thermal runaway identification models, wherein the thermal runaway identification model is related to the application scenario and / or data type; The battery state information is input into the at least one target thermal runaway identification model to obtain the corresponding identification results; The thermal runaway state of the corresponding battery is determined based on at least one of the identification results.

2. The method of claim 1, wherein, The battery status information includes at least one of the following: vehicle model, voltage, current, temperature, battery type, charging status, and heartbeat message.

3. The method of claim 1, wherein, The application scenarios include at least one of thermal runaway hazard identification, thermal runaway fault identification, single-cell thermal runaway, and multi-cell thermal runaway, and each application scenario corresponds to at least one thermal runaway identification model.

4. The method of claim 1, wherein, The thermal runaway identification model is composed of an index tree, which contains multiple layers of indices. After the battery state information is input into the at least one target thermal runaway identification model, the processing procedure of the target thermal runaway identification model includes: Starting from the first layer of the indicator tree, determine the hit status of each indicator in each layer until the top layer is determined; The corresponding recognition result is determined based on the hit status of the top-level indicators.

5. The method of claim 4, wherein, The process of determining the hit status of each indicator in the indicator tree layer by layer, starting from the first layer and continuing until the top layer is determined, includes: Determine the hit status of the Nth level indicator of the indicator tree, where N is a positive integer; In response to the hit status of the Nth layer indicator being hit, the hit status of the indicator at the N+1th layer is determined, until the hit status of the top layer indicator is determined.

6. The method according to claim 4, characterized in that, Determining the hit status corresponding to each indicator in the corresponding layer includes: Determine the hit conditions corresponding to each level of indicators, and the types of hit conditions include data filtering, data analysis, data judgment and / or data aggregation; In response to the battery status information satisfying the hit condition, the hit status is determined to be a hit.

7. The method according to claim 2, characterized in that, The battery status information includes the battery model, voltage, and temperature collected by multiple temperature sensors; The processing steps of the target thermal runaway identification model include: Determine whether the battery model is a preset battery model corresponding to the target thermal runaway identification model; In response to the battery model being a preset battery model corresponding to the target thermal runaway identification model, it is determined whether the voltage is within a preset voltage range; Determine whether the temperatures collected by the multiple temperature sensors are within a first preset temperature range; In response to the voltage being within a preset voltage range, and the temperatures collected by the plurality of temperature sensors all being within a first preset temperature range, the identification result is determined to be a temperature anomaly.

8. The method according to claim 2, characterized in that, The battery status information includes the battery model and the voltage corresponding to each of the multiple cells; The steps for determining the identification result using the target thermal runaway identification model include: Determine whether the battery model is a preset battery model corresponding to the target thermal runaway identification model; Determine whether the voltage corresponding to each of the battery cells is within the second preset temperature range; In response to the voltage being within the second preset temperature range, the corresponding battery cell is determined to be an abnormal battery cell; Determine whether the number of abnormal battery cells is within the first preset quantity range; Based on the positional relationship between the battery cells, determine whether the number of adjacent abnormal battery cells falls within a second preset number range; In response to the fact that the battery model is a preset battery model corresponding to the target thermal runaway identification model, the number of abnormal cells is within the first preset number range, and whether the number of adjacent abnormal cells is within the second preset number range, the identification result is determined to be a voltage abnormality.

9. The method according to claim 1, characterized in that, The step of determining at least one target thermal runaway identification model from a set of preset thermal runaway identification models based on the battery state information includes: Determine the input data type for each of the aforementioned thermal runaway identification models; In response to the data type of the battery state information including the input data type, the thermal runaway identification model is determined to be the target thermal runaway model.

10. A battery thermal runaway identification device, characterized in that, The device includes: The acquisition module is used to acquire battery status information; The first determining module is used to determine at least one target thermal runaway identification model from a plurality of preset thermal runaway identification models based on the battery state information. The thermal runaway identification model is related to the application scenario and / or data type. The identification module is used to input the battery state information into the at least one target thermal runaway identification model to obtain the corresponding identification results; The second determining module is used to determine the thermal runaway state of the corresponding battery based on at least one of the identification results.

11. An electronic device comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-9.

13. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the method as described in any one of claims 1-9.

Images