Generation method and device of thermal runaway early warning model, equipment and medium

Abstract

The invention provides a thermal runaway early warning model generation method and device, equipment and a medium, and is applied to a vehicle battery, the method comprises the following steps: carrying out a cyclic aging test on the vehicle battery until the vehicle battery generates a thermal runaway reaction, and obtaining strain related data corresponding to the cyclic aging test; respectively carrying out impact test on the plurality of vehicle batteries in different health states until thermal runaway reaction of the vehicle batteries occurs, and obtaining gas component data corresponding to the health states; model training is carried out according to the strain related data and the gas component data, a thermal runaway early warning model is obtained, the thermal runaway early warning model is used for carrying out thermal runaway early warning in the charging and discharging process of the vehicle battery, and the thermal runaway precursor of the battery is more comprehensively captured according to the strain data and the gas data of the battery; the early warning of the thermal runaway reaction of the battery is realized, and the accuracy of thermal runaway early warning is improved.

Description

Technical Field

[0001] The present application relates to the technical field of battery thermal runaway warning, and particularly relates to a method for generating a thermal runaway warning model, a device for generating a thermal runaway warning model, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the continuous growth of global energy demand and the improvement of environmental protection awareness, electric vehicles have been widely used. As the core component of electric vehicles, the performance and safety of batteries directly affect the reliability and service life of the whole vehicle. However, during long-term use, the battery gradually ages. The battery aging may be reflected in electrolyte consumption, lithium plating on the negative electrode, thickening of the negative electrode SEI (Solid Electrolyte Interphase) film, etc., which may cause the thermal stability of the battery to deteriorate, and even cause thermal runaway, resulting in a sharp decline in battery performance and even triggering fires or explosions, posing a serious threat to personal safety and property.

[0003] The existing technology usually conducts single-level warning by real-time monitoring of the battery voltage or temperature, or multi-level warning by comprehensively considering the battery voltage, temperature, and stress. However, the voltage and temperature as warning signals are very lagging. Usually, when an abnormality is found, the battery is about to have or has already had a thermal runaway problem, and it is impossible to achieve early warning of the battery thermal runaway. And the existing technology does not consider the influence of the battery aging state on the thermal runaway characteristics. Summary of the Invention

[0004] Embodiments of the present application provide a method, a device, a device, and a medium for generating a thermal runaway warning model to solve the problem that the prior art cannot achieve early warning of the battery thermal runaway reaction.

[0005] Embodiments of the present application disclose a method for generating a thermal runaway warning model, which is applied to a vehicle battery. The method includes:

[0006] Performing a cyclic aging test on the vehicle battery until the vehicle battery has a thermal runaway reaction, and obtaining strain-related data corresponding to the cyclic aging test;

[0007] Performing an impact test on the vehicle batteries in multiple different health states until the vehicle batteries have a thermal runaway reaction, and obtaining gas component data corresponding to the health states;

[0008] Performing model training according to the strain-related data and the gas component data to obtain a thermal runaway warning model, where the thermal runaway warning model is used to perform thermal runaway warning during the charge and discharge process of the vehicle battery.

[0009] Optionally, the strain-related data includes the state of health information of the vehicle battery and the stress data corresponding to the state of health information. The step of performing a cyclic aging test on the vehicle battery until a thermal runaway reaction occurs in the vehicle battery and obtaining strain data corresponding to the cyclic aging test includes:

[0010] Performing a cyclic test of micro-overcharge, micro-overdischarge, micro-overtemperature, and micro-overpressure on the vehicle battery until a thermal runaway reaction occurs in the vehicle battery, and collecting the state of health information of the vehicle battery during the test and the stress data corresponding to the state of health information.

[0011] Optionally, the step of performing an impact test on the vehicle batteries in multiple different states of health respectively until a thermal runaway reaction occurs in the vehicle battery and obtaining gas component data corresponding to the state of health includes:

[0012] Performing overcharge, overdischarge, and overheat tests on the vehicle batteries in multiple different states of health respectively until a thermal runaway reaction occurs in the vehicle battery, and collecting the gas component data generated by the vehicle battery during the test.

[0013] Optionally, the method further includes:

[0014] Outputting a thermal runaway threshold signal for the vehicle battery through the thermal runaway warning model;

[0015] Collecting target stress data and target gas data generated by the vehicle battery during charge and discharge;

[0016] Comparing the target stress data and the target gas data with the thermal runaway threshold signal to generate a thermal runaway warning result for the vehicle battery.

[0017] Optionally, the thermal runaway threshold signal includes a strain threshold signal and a gas threshold signal. The step of comparing the target stress data and the target gas data with the thermal runaway threshold signal to generate a thermal runaway warning result for the vehicle battery includes:

[0018] If the target stress data of the vehicle battery is greater than the strain threshold signal, and / or the target gas data is greater than the gas threshold signal, then a thermal runaway alarm is given for the vehicle battery.

[0019] Optionally, there are multiple thermal runaway threshold signals. The step of comparing the target stress data and the target gas data with the thermal runaway threshold to generate a thermal runaway warning result for the vehicle battery includes:

[0020] Set a thermal runaway warning level for the vehicle battery and warning control operations corresponding to the thermal runaway warning level according to the thermal runaway threshold signal;

[0021] Compare the target stress data and the target gas data with the thermal runaway threshold signal to determine the thermal runaway warning level of the vehicle battery;

[0022] Execute the warning control operation for the vehicle battery according to the thermal runaway warning level.

[0023] Optionally, the method further includes:

[0024] Input the target stress data of the vehicle battery into the thermal runaway warning model for calculation to generate a life prediction result of the vehicle battery.

[0025] An embodiment of the present application also provides a device for generating a thermal runaway warning model, which is applied to a vehicle battery. The device includes:

[0026] A cyclic aging test module for performing a cyclic aging test on the vehicle battery until the vehicle battery has a thermal runaway reaction, and obtaining strain-related data corresponding to the cyclic aging test;

[0027] An extreme shock test module for performing shock tests on multiple vehicle batteries in different health states respectively until the vehicle battery has a thermal runaway reaction, and obtaining gas component data corresponding to the health state;

[0028] A model training module for training a model according to the strain-related data and the gas component data to obtain a thermal runaway warning model, which is used for thermal runaway warning during the charge and discharge process of the vehicle battery.

[0029] Optionally, the strain-related data includes the health state information of the vehicle battery and stress data corresponding to the health state information. The cyclic aging test module is specifically configured to perform cyclic tests of micro-overcharge, micro-overdischarge, micro-overtemperature, and micro-overpressure on the vehicle battery until the vehicle battery has a thermal runaway reaction, and collect the health state information of the vehicle battery during the test and stress data corresponding to the health state information.

[0030] Optionally, the extreme shock test module is specifically configured to perform overcharge, overdischarge, and overheat tests on multiple vehicle batteries in different health states respectively until the vehicle battery has a thermal runaway reaction, and collect gas component data generated by the vehicle battery during the test.

[0031] Optionally, the device further includes:

[0032] A threshold calculation module, configured to output a thermal runaway threshold signal for the vehicle battery through the thermal runaway warning model;

[0033] A data acquisition module, configured to acquire target stress data and target gas data generated by the vehicle battery during charge and discharge;

[0034] A thermal runaway warning module, configured to compare the target stress data and the target gas data with the thermal runaway threshold signal to generate a thermal runaway warning result for the vehicle battery.

[0035] Optionally, the thermal runaway threshold signal includes a strain threshold signal and a gas threshold signal. Specifically, the thermal runaway warning module is configured to, if the target stress data of the vehicle battery is greater than the strain threshold signal, and / or the target gas data is greater than the gas threshold signal, issue a thermal runaway warning for the vehicle battery.

[0036] Optionally, there are multiple thermal runaway threshold signals, and the thermal runaway warning module includes:

[0037] An alarm level setting sub-module, configured to set a thermal runaway alarm level for the vehicle battery and an alarm control operation corresponding to the thermal runaway alarm level according to the thermal runaway threshold signal;

[0038] An alarm level determination sub-module, configured to compare the target stress data and the target gas data with the thermal runaway threshold signal to determine the thermal runaway alarm level of the vehicle battery;

[0039] An alarm control sub-module, configured to execute an alarm control operation for the vehicle battery according to the thermal runaway alarm level.

[0040] Optionally, the device further includes:

[0041] A life prediction module, configured to input the target stress data of the vehicle battery into the thermal runaway warning model for calculation to generate a life prediction result of the vehicle battery.

[0042] An embodiment of the present application also discloses an electronic device, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus;

[0043] The memory is used to store a computer program;

[0044] When the processor is configured to execute the program stored in the memory, it implements the method described in the embodiment of the present application.

[0045] The embodiments of the present application also disclose a computer-readable storage medium, on which instructions are stored, and when executed by one or more processors, cause the processors to execute the method as described in the embodiments of the present application.

[0046] Compared with the prior art, the embodiments of the present application include the following advantages:

[0047] In the embodiments of the present application, the vehicle battery is subjected to cyclic aging tests until a thermal runaway reaction occurs in the vehicle battery, and strain-related data corresponding to the cyclic aging tests is obtained; impact tests are respectively performed on multiple vehicle batteries in different health states until a thermal runaway reaction occurs in the vehicle battery, and gas component data corresponding to the health states is obtained; model training is performed based on the strain-related data and the gas component data to obtain a thermal runaway warning model, and the thermal runaway warning model is used to perform thermal runaway warning during the charge and discharge process of the vehicle battery. By more comprehensively capturing the precursors of the thermal runaway of the battery according to the strain data and gas data of the battery, early warning of the thermal runaway reaction of the battery is realized, the accuracy of the thermal runaway warning is improved, battery problems are detected in advance, and the maintenance and replacement costs caused by thermal runaway are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 is a flowchart of the steps of a method for generating a thermal runaway warning model provided by the embodiments of the present application;

[0050] Figure 2 is a schematic flowchart of vehicle battery thermal runaway warning provided by the embodiments of the present application;

[0051] Figure 3 is a block diagram of the structure of a device for generating a thermal runaway warning model provided by the embodiments of the present application;

[0052] Figure 4 is a block diagram of an electronic device provided in the embodiments of the present application;

[0053] Figure 5 is a schematic diagram of a computer-readable storage medium provided in the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0055] As an example, existing methods usually perform single-level warning by real-time monitoring of the voltage or temperature of the battery, or multi-level warning by comprehensively considering the voltage, temperature, and stress of the battery. However, voltage and temperature as warning signals are very lagging. Usually, when an abnormality is found, the battery is about to have or has already had a thermal runaway problem, and it is impossible to achieve early warning of the battery's thermal runaway.

[0056] In contrast, the advantage of the present application compared with the prior art is that in the embodiments of the present application, the vehicle battery is subjected to cyclic aging tests until the vehicle battery has a thermal runaway reaction, and strain-related data corresponding to the cyclic aging tests is obtained; impact tests are respectively performed on multiple vehicle batteries in different health states until the vehicle battery has a thermal runaway reaction, and gas composition data corresponding to the health states is obtained; model training is performed based on the strain-related data and the gas composition data to obtain a thermal runaway warning model. The thermal runaway warning model is used to perform thermal runaway warning during the charge and discharge process of the vehicle battery. By more comprehensively capturing the precursors of the battery's thermal runaway according to the strain data and gas data of the battery, early warning of the battery's thermal runaway reaction is achieved, the accuracy of the thermal runaway warning is improved, battery problems are detected in advance, and the maintenance and replacement costs caused by thermal runaway are reduced.

[0057] Referring to Figure 1 , a flowchart of the steps of a method for generating a thermal runaway warning model provided in the embodiments of the present application is shown, and specifically may include the following steps:

[0058] Step 101: Perform cyclic aging tests on the vehicle battery until the vehicle battery has a thermal runaway reaction, and obtain strain-related data corresponding to the cyclic aging tests;

[0059] In the embodiments of the present application, by performing cyclic aging tests on vehicle batteries to simulate the performance changes of vehicle batteries during actual use, the cyclic aging test can also be understood as a cycle life test. During the cyclic aging test, the vehicle battery gradually ages, that is, the state of health (SOH) of the vehicle battery will gradually change until the vehicle battery undergoes a thermal runaway reaction. Accordingly, strain-related data of the vehicle battery during the test is obtained. The strain-related data characterizes the stress changes of the vehicle battery in different health states. By analyzing the strain-related data, it is helpful to identify the early stress changes before the battery undergoes thermal runaway, thereby predicting the thermal runaway risk of the battery in advance and providing an important data basis for the training of subsequent thermal runaway warning models.

[0060] As an example, obtain a brand-new vehicle battery (i.e., SOH = 100%), arrange strain gauges on the surface of the vehicle battery, and then perform cyclic charge and discharge tests on the vehicle battery until the vehicle battery undergoes a thermal runaway reaction, and record the strain-related data of the vehicle battery during the test.

[0061] In a preferred embodiment of the present application, the strain-related data includes the health state information of the vehicle battery and the stress data corresponding to the health state information. Step 101: Perform cyclic aging tests on the vehicle battery until the vehicle battery undergoes a thermal runaway reaction, and obtain the strain data corresponding to the cyclic aging test, including:

[0062] Perform cyclic tests of micro-overcharge, micro-overdischarge, micro-overtemperature, and micro-overpressure on the vehicle battery until the vehicle battery undergoes a thermal runaway reaction, and collect the health state information of the vehicle battery during the test and the stress data corresponding to the health state information.

[0063] In the embodiments of the present application, there are situations where the vehicle battery slightly exceeds the normal use range during actual use. For example, due to charger errors, the charging voltage of the vehicle battery exceeds the charging voltage in the preset charging conditions, resulting in a micro-overcharge situation of the vehicle battery. Therefore, considering the possible deviations of the vehicle battery during actual use, the test conditions for the cyclic aging test of the vehicle battery in the embodiments of the present application are set as micro-overcharge (slightly exceeding the rated voltage of the battery during charging), micro-overdischarge (slightly exceeding the rated voltage of the battery during discharging), micro-overtemperature (slightly exceeding the rated temperature of the battery during the test), and micro-overpressure (slightly exceeding the rated pressure of the battery during the test), simulating the conditions that the vehicle battery will encounter during actual use, performing cyclic tests until the vehicle battery undergoes a thermal runaway reaction, and collecting the health state information of the vehicle battery during the test and the stress data associated with the health state of the vehicle battery as strain-related data.

[0064] As an example, obtain a brand-new vehicle battery (i.e., SOH = 100%), arrange strain gauges on the surface of the vehicle battery, and then conduct cumulative cyclic tests of micro-overcharge, micro-overdischarge, micro-overtemperature, and micro-overvoltage on the vehicle battery until a thermal runaway reaction occurs in the vehicle battery. Record the strain-related data of the vehicle battery during the test. For example, when the vehicle battery reaches the 500th test cycle, its state of health is good (SOH = 95%), and the stress it receives is 50 - 100 Pa (Pascal). When the vehicle battery reaches the 10,000th test cycle, a thermal runaway reaction occurs, its state of health is poor (SOH = 50%), and the stress it receives is 100 MPa.

[0065] Step 102: Conduct impact tests on the vehicle batteries in multiple different states of health respectively until a thermal runaway reaction occurs in the vehicle battery, and obtain gas component data corresponding to the state of health.

[0066] In the embodiment of the present application, the impact test is used to simulate the thermal runaway reaction that occurs when the vehicle battery is under extreme conditions, so as to collect the gas component data generated by the vehicle battery in the early stage of the thermal runaway reaction. By conducting impact tests on the vehicle batteries in multiple different states of health respectively until a thermal runaway reaction occurs in the vehicle battery, the present application embodiment can obtain the gas component data generated by the vehicle batteries in different states of health in the early stage of the thermal runaway reaction, that is, obtain the gas component data associated with the state of health of the vehicle battery. For example, the hydrogen, carbon monoxide and other gases and their corresponding values generated by the vehicle battery with good state of health (SOH ≥ 90%) in the early stage of the thermal runaway reaction, the gases and their corresponding values generated by the vehicle battery with poor state of health (SOH < 60%) in the early stage of the thermal runaway reaction. Vehicle batteries in different states of health may have different gas release characteristics in the early stage of thermal runaway, providing rich samples for the training of the subsequent thermal runaway warning model.

[0067] In a preferred embodiment of the present application, step 102: Conducting impact tests on the vehicle batteries in multiple different states of health respectively until a thermal runaway reaction occurs in the vehicle battery, and obtaining gas component data corresponding to the state of health, includes:

[0068] Conduct overcharge, overdischarge, and overheat tests on the vehicle batteries in multiple different states of health respectively until a thermal runaway reaction occurs in the vehicle battery, and collect the gas component data generated by the vehicle battery during the test.

[0069] In the embodiments of the present application, the vehicle battery will rapidly undergo a thermal runaway reaction under extreme conditions. Therefore, the test conditions for the impact test in the embodiments of the present application are set as overcharge (exceeding the rated voltage of the battery during charging), over-discharge (exceeding the rated voltage of the battery during discharging), overheat (exceeding the rated temperature of the battery during the test), etc., which are extreme conditions for the vehicle battery, so as to rapidly induce the vehicle battery to undergo a thermal runaway reaction, and then rapidly obtain the gas component data of the vehicle battery in different health states in the early stage before the thermal runaway reaction, that is, obtain the gas component data associated with the health state of the vehicle battery. Using the gas component data as an early precursor before the thermal runaway of the vehicle battery helps to predict the thermal runaway risk of the battery in advance.

[0070] As an example, obtain vehicle batteries with good health status, medium health status, and poor health status, and conduct impact tests on multiple vehicle batteries with different health states respectively. For example, heat the vehicle battery to a high temperature to simulate an extreme temperature environment to induce the vehicle battery to undergo a thermal runaway reaction, and collect the gas component data generated by the vehicle battery during the process from the start of the test until the thermal runaway reaction occurs. For example, the gas component data corresponding to the vehicle battery with good health status is carbon monoxide 0 - 0.2%, carbon dioxide 0 - 0.3%, and methane 0 - 0.01%; the gas component data corresponding to the vehicle battery with medium health status is carbon monoxide 0.1% - 0.5%, carbon dioxide 0.2% - 0.8%, and methane 0.010 - 0.05%; the gas component data corresponding to the vehicle battery with poor health status is carbon monoxide 0.5% - 2%, carbon dioxide 0.6% - 3%, and methane 0.05 - 0.2%.

[0071] Step 103: Perform model training according to the strain-related data and the gas component data to obtain a thermal runaway warning model, which is used to perform thermal runaway warning during the charging and discharging process of the vehicle battery.

[0072] In the embodiments of the present application, a deep learning model is used to learn the stress characteristics related to thermal runaway in the strain-related data and the characteristics related to thermal runaway in the gas component data, so as to obtain a thermal runaway warning model for performing thermal runaway warning on the vehicle battery. Furthermore, during the use of the vehicle battery, the strain-related data and the gas component data of the battery can be monitored in real time, and the thermal runaway warning model can be used to perform thermal runaway warning on the vehicle battery, effectively preventing the occurrence of battery thermal runaway accidents and improving the safety and reliability of battery use.

[0073] As an example, an LSTM (Long Short-Term Memory, a recurrent neural network) model is constructed as the initial thermal runaway warning model. The strain-related data and gas composition data are used as the training data set and input into the LSTM model for training and optimization to obtain the final thermal runaway warning model. Specifically, constructing the initial LSTM model includes: setting the input gate: for controlling the input of new information; setting the forget gate: f t = σ(W f ·[h t-1 , x t +b f ), i t = σ(W i ·[h t-1 , x t +b i ), for deleting unimportant information; setting the input gate: o t = σ(W o [h t-1 , x t +b o ), h t = o t *tanh(C t ), for determining the output content. Further, the constructed LSTM model is used to train and optimize the strain-related data and gas composition data to obtain the thermal runaway warning model. The thermal runaway warning model can accurately predict thermal runaway in a timely manner based on the early gas composition and early strain characteristics of the vehicle battery.

[0074] In a preferred embodiment of the present application, the method further includes:

[0075] outputting a thermal runaway threshold signal for the vehicle battery through the thermal runaway warning model;

[0076] collecting target stress data and target gas data generated during the charging and discharging process of the vehicle battery;

[0077] comparing the target stress data and the target gas data with the thermal runaway threshold signal to generate a thermal runaway warning result for the vehicle battery.

[0078] In the embodiments of the present application, the thermal runaway warning model can output a thermal runaway threshold signal of the vehicle battery according to the model training result. The thermal runaway threshold signal characterizes the state of the vehicle battery during a thermal runaway reaction and serves as a reference standard for judging whether the battery has a thermal runaway reaction. Further, during the charging and discharging process of the vehicle battery, the target stress data of the vehicle battery, i.e., the stress received by the vehicle battery, and the target gas data, i.e., the gas component data generated by the vehicle battery, are collected in real time. The real-time collected target stress data and target gas data are compared with the thermal runaway threshold signal to judge whether the current state of the battery is close to or exceeds the thermal runaway threshold signal. According to the comparison result, a thermal runaway warning result of the vehicle battery is generated. Through real-time monitoring and warning, the embodiments of the present application can timely detect abnormal changes in the battery state, prevent the occurrence of thermal runaway reactions, and ensure the safety and reliability of the vehicle battery.

[0079] In a preferred embodiment of the present application, the thermal runaway threshold signal includes a strain threshold signal and a gas threshold signal. The comparing the target stress data and the target gas data with the thermal runaway threshold signal to generate the thermal runaway warning result of the vehicle battery includes:

[0080] If the target stress data of the vehicle battery is greater than the strain threshold signal, and / or, the target gas data is greater than the gas threshold signal, a thermal runaway alarm is issued for the vehicle battery.

[0081] In the embodiments of the present application, the thermal runaway threshold signal specifically includes a strain threshold signal and a gas threshold signal. The stress data and gas component data currently generated by the vehicle battery are respectively compared with the strain threshold signal and the gas threshold signal. When the stress data of the vehicle battery is greater than the strain threshold signal, and / or, the gas component data generated by the vehicle battery is greater than the gas threshold signal, it is considered that the current vehicle battery has a risk of a thermal runaway reaction, and a warning is issued to remind the user to take preventive measures to avoid a thermal runaway accident. Moreover, since the vehicle battery will generate multiple gases, there is a corresponding gas threshold signal for each gas. For example, the hydrogen concentration is 1% and the carbon monoxide concentration is 1.5%. The value of each gas in the gas component data is compared with the gas threshold signal. If one gas is greater than the corresponding gas threshold signal, it is considered that the vehicle battery has a risk of a thermal runaway reaction.

[0082] In a preferred embodiment of the present application, there are multiple thermal runaway threshold signals. The comparing the target stress data and the target gas data with the thermal runaway threshold to generate the thermal runaway warning result of the vehicle battery includes:

[0083] According to the multiple thermal runaway threshold signals, set a thermal runaway alarm level for the vehicle battery and alarm control operations corresponding to the thermal runaway alarm level;

[0084] Compare the target stress data and the target gas data with the thermal runaway threshold signal to determine the thermal runaway warning level of the vehicle battery;

[0085] Execute a warning control operation for the vehicle battery according to the thermal runaway warning level.

[0086] In the embodiment of the present application, the thermal runaway warning model outputs multiple thermal runaway threshold signals, which are used to characterize the stress data and gas component data corresponding to different risk levels of the battery undergoing a thermal runaway reaction. Furthermore, different thermal runaway warning levels are set according to the multiple thermal runaway threshold signals, each level corresponding to a specific risk level, and corresponding warning control operations are set for each warning level, so as to take corresponding measures when detecting the corresponding risks.

[0087] Specifically, the thermal runaway threshold signal at least includes a first stress threshold, a second stress threshold, and a third stress threshold, as well as a first gas threshold, a second gas threshold, and a third gas threshold. The interval between the first stress threshold and the second stress threshold, and / or, the interval between the first gas threshold and the second gas threshold, is set as the first warning level; the interval between the second stress threshold and the third stress threshold, and / or, the interval between the second gas threshold and the third gas threshold, is set as the second warning level; greater than the third stress threshold, and / or, greater than the third gas threshold, is set as the third warning level. Further, the first warning level: corresponding to a minor anomaly, the warning control operation is to issue a prompt warning to remind the user to park the vehicle by the roadside. The second warning level: corresponding to a medium anomaly, the warning control operation is to accurately locate the vehicle battery where the thermal runaway occurs, start the cooling and fan equipment, and perform cooling and heat dissipation. The third warning level: corresponding to a serious anomaly, the warning control operation is to cut off the high voltage under power failure and wait for rescue while parking.

[0088] As an example, the thermal runaway warning model outputs three stress thresholds (such as 50 MPa, 100 MPa, 150 MPa) and three gas thresholds (such as 0.5%, 1%, 1.5%). If it is greater than the first stress threshold (50 MPa) and less than the second stress threshold (100 MPa), and / or, greater than the first gas threshold (0.5%) and less than the second gas threshold (1%), it is determined as the first warning level, and the corresponding first warning control operation is to send a warning message to remind the driver to stop the vehicle; if it is greater than the second stress threshold (100 MPa) and less than the third stress threshold (150 MPa), and / or, greater than the second gas threshold (1%) and less than the third gas threshold (1.5%), it is determined as the second warning level, and the corresponding second warning control operation is to determine the location of the abnormal vehicle battery according to the stress signal and the gas signal, and then control the corresponding cooling device to cool down according to the location information; if it is greater than the third stress threshold (150 MPa), and / or, greater than the third gas threshold (1.5%), it is determined as the third warning level, and the corresponding third warning control operation is to perform a power-off operation on the vehicle battery to stop and wait for rescue.

[0089] In a preferred embodiment of the present application, the method further includes:

[0090] Input the target stress data of the vehicle battery into the thermal runaway warning model for calculation to generate the life prediction result of the vehicle battery.

[0091] In the embodiment of the present application, the thermal runaway warning model can also be used to predict the life of the vehicle battery. Specifically, input the stress data currently received by the vehicle battery into the thermal runaway warning model. The thermal runaway warning model predicts the remaining life of the vehicle battery under the current stress conditions (such as the remaining number of cycles, remaining usage time, etc.) by analyzing the change trend of the stress data and historical data, and generates the life prediction result of the vehicle battery. Through the life prediction result of the vehicle battery in the embodiment of the present application, the remaining life of the battery can be understood in real time, and further preventive measures can be taken in advance to avoid failures and safety accidents caused by battery aging, and reduce the maintenance and replacement costs caused by battery aging.

[0092] In an embodiment of the present application, a cyclic aging test is performed on a vehicle battery until a thermal runaway reaction occurs in the vehicle battery, and strain-related data corresponding to the cyclic aging test is obtained; impact tests are respectively performed on a plurality of vehicle batteries in different health states until a thermal runaway reaction occurs in the vehicle battery, and gas composition data corresponding to the health state is obtained; model training is performed according to the strain-related data and the gas composition data to obtain a thermal runaway early warning model, and the thermal runaway early warning model is used to perform thermal runaway early warning during the charging and discharging process of the vehicle battery. By more comprehensively capturing the precursors of the thermal runaway of the battery according to the strain data and gas data of the battery, early warning of the thermal runaway reaction of the battery is realized, the accuracy of the thermal runaway early warning is improved, battery problems are detected in advance, and the maintenance and replacement costs caused by thermal runaway are reduced.

[0093] To enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the following is an exemplary illustration through corresponding examples:

[0094] Refer to Figure 2 , which shows a schematic flow chart of thermal runaway early warning of a vehicle battery provided by an embodiment of the present application. First, through actual measurement of the vehicle battery, strain-related data and gas composition data generated during the process from the start of the test until the thermal runaway reaction occurs in the vehicle battery are obtained. Then, model training is performed through a large amount of actual measurement data to generate a thermal runaway early warning model. Further, the thermal runaway early warning model is installed on the vehicle side to receive the stress signal and gas signal generated by the vehicle battery in real time to determine the thermal runaway warning level of the vehicle battery and perform hierarchical warning processing. In addition, the thermal runaway early warning model can also predict the life of the vehicle battery through the stress signal generated by the vehicle battery.

[0095] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present application are not limited by the described action sequence, because according to the embodiments of the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present application.

[0096] Refer to Figure 3 , which shows a structural block diagram of a device for generating a thermal runaway early warning model provided by an embodiment of the present application, and specifically may include the following modules:

[0097] A cyclic aging test module 301, configured to perform a cyclic aging test on the vehicle battery until a thermal runaway reaction occurs in the vehicle battery, and obtain strain-related data corresponding to the cyclic aging test;

[0098] An extreme shock test module 302 is configured to perform shock tests on the vehicle batteries in multiple different health states respectively until a thermal runaway reaction occurs in the vehicle batteries, and obtain gas composition data corresponding to the health states.

[0099] A model training module 303 is configured to perform model training based on the strain-related data and the gas composition data to obtain a thermal runaway warning model, and the thermal runaway warning model is used to perform thermal runaway warning during the charge and discharge process of the vehicle battery.

[0100] In an embodiment of the present application, the strain-related data includes health state information of the vehicle battery and stress data corresponding to the health state information. The cyclic aging test module is specifically configured to perform cyclic tests of micro overcharge, micro over discharge, micro over temperature, and micro over voltage on the vehicle battery until a thermal runaway reaction occurs in the vehicle battery, and collect the health state information of the vehicle battery during the test process and the stress data corresponding to the health state information.

[0101] In an embodiment of the present application, the extreme shock test module is specifically configured to perform overcharge, over discharge, and overheat tests on the vehicle batteries in multiple different health states respectively until a thermal runaway reaction occurs in the vehicle battery, and collect the gas composition data generated by the vehicle battery during the test process.

[0102] In an embodiment of the present application, the device further includes:

[0103] A threshold calculation module is configured to output a thermal runaway threshold signal for the vehicle battery through the thermal runaway warning model.

[0104] A data acquisition module is configured to acquire target stress data and target gas data generated by the vehicle battery during the charge and discharge process.

[0105] A thermal runaway warning module is configured to compare the target stress data and the target gas data with the thermal runaway threshold signal to generate a thermal runaway warning result for the vehicle battery.

[0106] In an embodiment of the present application, the thermal runaway threshold signal includes a strain threshold signal and a gas threshold signal. The thermal runaway warning module is specifically configured to, if the target stress data of the vehicle battery is greater than the strain threshold signal, and / or, the target gas data is greater than the gas threshold signal, then issue a thermal runaway warning for the vehicle battery.

[0107] In an embodiment of the present application, there are multiple thermal runaway threshold signals, and the thermal runaway warning module includes:

[0108] An alarm level setting sub-module, configured to set a thermal runaway alarm level for the vehicle battery and an alarm control operation corresponding to the thermal runaway alarm level according to the thermal runaway threshold signal;

[0109] An alarm level determination sub-module, configured to compare the target stress data and the target gas data with the thermal runaway threshold signal to determine the thermal runaway alarm level of the vehicle battery;

[0110] An alarm control sub-module, configured to execute an alarm control operation for the vehicle battery according to the thermal runaway alarm level.

[0111] In an embodiment of the present application, the device further includes:

[0112] A life prediction module, configured to input the target stress data of the vehicle battery into the thermal runaway early warning model for calculation to generate a life prediction result of the vehicle battery.

[0113] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For related parts, please refer to the partial description of the method embodiment.

[0114] In addition, an embodiment of the present application further provides an electronic device, as Figure 4 shown, including a processor 401, a communication interface 402, a memory 403, and a communication bus 404. Among them, the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404.

[0115] The memory 403 is used to store a computer program;

[0116] The processor 401 is configured to implement the method described in the above embodiment when executing the program stored in the memory 403.

[0117] The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0118] The communication interface is used for communication between the above terminal and other devices.

[0119] The memory may include a Random Access Memory (RAM), or may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0120] The aforementioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0121] As Figure 5 shown, in another embodiment provided by the present application, a computer-readable storage medium 501 is further provided. Instructions are stored in the computer-readable storage medium, and when it runs on a computer, the computer is caused to execute the model training method described in the above embodiment.

[0122] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0123] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including", or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including one..." does not exclude the presence of additional identical elements in the process, method, article, or device including the element.

[0124] Each embodiment in this specification is described in a related manner. The same or similar parts between the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

[0125] The above are only the preferred embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application are all included in the protection scope of the present application.

Claims

1. A method for generating a thermal runaway warning model, characterized in that: Applied to a vehicle battery, the method comprises: Performing a cycle aging test on the vehicle battery until a thermal runaway reaction occurs in the vehicle battery, and obtaining strain-related data corresponding to the cycle aging test; performing impact tests on the vehicle batteries in a plurality of different health states respectively until the vehicle batteries have a thermal runaway reaction, and obtaining gas composition data corresponding to the health states; Model training is performed according to the strain-related data and the gas composition data to obtain a thermal runaway warning model, and the thermal runaway warning model is used to provide a thermal runaway warning during the charging and discharging process of the vehicle battery.

2. The method according to claim 1, characterized in that: The strain-related data includes health status information of the vehicle battery and stress data corresponding to the health status information. The step of performing a cycle aging test on the vehicle battery until a thermal runaway reaction occurs in the vehicle battery to obtain strain data corresponding to the cycle aging test includes: The vehicle battery is subjected to a cycle test of slight overcharge, slight overdischarge, slight overtemperature and slight overvoltage until a thermal runaway reaction occurs in the vehicle battery, and health status information of the vehicle battery during the test and stress data corresponding to the health status information are collected.

3. The method according to claim 1, characterized in that: The step of performing impact tests on the vehicle batteries in a plurality of different health states respectively until the vehicle batteries have a thermal runaway reaction, and obtaining gas composition data corresponding to the health states, comprises: The vehicle batteries in multiple different health states are respectively tested for overcharge, overdischarge and overheating until thermal runaway reaction occurs in the vehicle batteries, and gas composition data generated by the vehicle batteries during the test are collected.

4. The method according to claim 1, characterized in that: The method further comprises: Outputting a thermal runaway threshold signal for the vehicle battery through the thermal runaway warning model; Collecting target stress data and target gas data generated by the vehicle battery during the charging and discharging process; The target stress data and the target gas data are compared with the thermal runaway threshold signal to generate a thermal runaway warning result for the vehicle battery.

5. The method according to claim 4, characterized in that: The thermal runaway threshold signal includes a strain threshold signal and a gas threshold signal, and the target stress data and the target gas data are compared with the thermal runaway threshold signal to generate a thermal runaway warning result of the vehicle battery, including: If the target stress data of the vehicle battery is greater than the strain threshold signal, and / or the target gas data is greater than the gas threshold signal, a thermal runaway alarm is issued for the vehicle battery.

6. The method according to claim 4, characterized in that: The thermal runaway threshold signal includes a plurality of signals, and the target stress data and the target gas data are compared with the thermal runaway threshold to generate a thermal runaway warning result of the vehicle battery, including: According to the plurality of thermal runaway threshold signals, setting a thermal runaway warning level for the vehicle battery and a warning control operation corresponding to the thermal runaway warning level; Comparing the target stress data and the target gas data with the thermal runaway threshold signal to determine a thermal runaway warning level of the vehicle battery; According to the thermal runaway warning level, a warning control operation for the vehicle battery is performed.

7. The method according to claim 1, characterized in that: The method further comprises: The target stress data of the vehicle battery is input into the thermal runaway warning model for calculation to generate a life prediction result of the vehicle battery.

8. A device for generating a thermal runaway warning model, characterized in that: Applied to a vehicle battery, the device comprises: A cycle aging test module, used to perform a cycle aging test on the vehicle battery until a thermal runaway reaction occurs in the vehicle battery, and obtain strain-related data corresponding to the cycle aging test; An extreme impact test module, used to perform impact tests on the vehicle batteries in multiple different health states respectively until the vehicle batteries have a thermal runaway reaction, and obtain gas composition data corresponding to the health states; A model training module is used to perform model training according to the strain-related data and the gas composition data to obtain a thermal runaway warning model, wherein the thermal runaway warning model is used to provide a thermal runaway warning during the charging and discharging process of the vehicle battery.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store computer programs; The processor is used to implement the method according to any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the method according to any one of claims 1 to 7.

Images