Battery thermal runaway detection method and apparatus

Abstract

The present application provides a battery thermal runaway detection method and apparatus. The method comprises: acquiring a time series signal generated when a gas sensor identifies a gas component released by a battery, and converting the time series signal into an image signal, so as to strength key features in the signal; processing the image signal by means of a target detection model, so as to predict a gas type and a gas concentration; and then determining a thermal runaway risk of the battery on the basis of a prediction result. Therefore, by introducing a machine learning algorithm, simple gas identification requirements are met, and complex data analysis and prediction can be carried out, thereby accurately predicting the thermal runaway risk of lithium batteries, and effectively improving the early warning precision of thermal runaway.

Description

Battery thermal runaway detection method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202410308999.X, filed on March 18, 2024, entitled “A method and device for detecting thermal runaway of a battery,” the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application relates to the field of battery safety technology, and more specifically, to a battery thermal runaway detection method, device, storage medium, and electronic device. Background Art

[0004] With the increasing popularity of electric vehicles, the safety issue of thermal runaway in lithium batteries has gradually attracted attention. Thermal runaway refers to a phenomenon in which heat generated within a battery during charging, discharging, or long-term use cannot be dissipated in a timely manner, causing the battery temperature to rise rapidly. If not promptly intervened, the battery may eventually catch fire or explode.

[0005] Currently, the main method for detecting thermal runaway in lithium batteries is to use infrared thermal imagers, thermistors, micro-thermocouples, surface-mount temperature sensors, etc. to monitor the battery's temperature and other parameters in real time, and then analyze and process the monitored data to predict the battery's safety status. However, the prediction results of this method are less accurate and prone to false alarms.

[0006] Summary of the Invention

[0007] In view of the above problems, the present application provides a battery thermal runaway detection method, device, storage medium and electronic device, which can solve the problem that the prediction results of the lithium battery thermal runaway detection method in the related art are poorly accurate, resulting in a high probability of false alarms.

[0008] In a first aspect, the present application provides a battery thermal runaway detection method, comprising: obtaining a timing signal generated by a gas sensor when identifying the gas components released by a battery, and converting the timing signal into an image signal; processing the image signal through a target detection model to obtain target gas information; the target gas information includes the gas type and gas concentration predicted by the target detection model; and determining the risk of battery thermal runaway based on the target gas information.

[0009] In this implementation, the gas sensor acquires the time series signal generated when identifying the gas components released by the battery. This signal is then converted into an image signal to enhance key features within the signal. This image signal is then processed using a target detection model to predict the gas type and concentration, and the risk of battery thermal runaway is determined based on the predicted results. This approach, through the introduction of machine learning algorithms, not only meets simple gas identification requirements but also enables complex data analysis and prediction, enabling accurate prediction of thermal runaway risks in lithium batteries and effectively improving the accuracy of thermal runaway warnings.

[0010] In some embodiments, the method is applied to an electronic nose, wherein a plurality of gas sensors are disposed in the electronic nose.

[0011] In the above implementation process, a device is provided for use in the battery thermal runaway detection method of the present application.

[0012] In some embodiments, the image signal includes a grayscale image; converting the timing signal into an image signal includes: converting each data in the timing signal generated by each gas sensor into a grayscale pixel point, and then splicing the grayscale pixel points into a long strip image; splicing the long strip images corresponding to all gas sensors to form a grayscale image.

[0013] In the above implementation process, a specific method for converting a time sequence signal into an image signal is provided.

[0014] In some embodiments, before converting the timing signal into an image signal, the method includes: performing normalization processing on the timing signal.

[0015] In the above implementation process, before converting the time series signal into an image signal, the time series signal is normalized to facilitate the conversion of the time series signal into grayscale pixels and to facilitate the analysis of the change trend of the data.

[0016] In some embodiments, the target detection model includes a convolutional neural network and a long short-term memory network; the convolutional neural network is used to extract spatial features from the image signal; and the long short-term memory network is used to extract temporal features based on changes in the spatial features over time.

[0017] In the above implementation process, the target detection model combines CNN and LSTM to analyze image signals. CNN extracts spatial features from image signals, and LSTM processes the changes of features extracted by CNN over time and extracts temporal features. In this way, the target detection model can achieve more accurate predictions.

[0018] In some embodiments, the target detection model is trained based on the following method: inputting training samples into the initial detection model to obtain predicted gas information output by the initial detection model; the training samples are obtained by collecting timing signals generated by the gas sensor when identifying different sample gases, and then converting the timing signals into image signals; constructing a loss function based on the predicted gas information and real gas information; the real gas information includes the actual gas type and actual gas concentration of the corresponding sample gas; optimizing the model parameters of the initial detection model based on the loss function, and determining the optimized initial detection model as the target detection model.

[0019] In the above implementation process, a specific training method for the target detection model is provided.

[0020] In some embodiments, determining the risk of battery thermal runaway based on the target gas information includes: when the gas type predicted by the target detection model includes a specified gas, and the gas concentration predicted by the target detection model for the specified gas is greater than or equal to a preset concentration, determining that there is a risk of battery thermal runaway.

[0021] In the above implementation process, after the target detection model performs qualitative and quantitative analysis on the gases released by the current lithium battery, it combines the characteristic gases that may be released during thermal runaway of the lithium battery and the corresponding concentration values ​​to determine whether there is a risk of battery thermal runaway. In this way, the detection of battery thermal runaway is achieved efficiently and accurately.

[0022] In the second aspect, the present application provides a battery thermal runaway detection device, including: an acquisition module, used to acquire the timing signal generated by the gas sensor when identifying the gas components released by the battery, and convert the timing signal into an image signal; a processing module, used to process the image signal through a target detection model to obtain target gas information; the target gas information includes the gas type and gas concentration predicted by the target detection model; a determination module, used to determine the risk of battery thermal runaway based on the target gas information.

[0023] In a third aspect, the present application provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in any one of the first aspects are implemented.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed on a computer, the computer is caused to execute the method as described in any one of the first aspects.

[0025] In a fifth aspect, the present application provides a computer program product, which, when running on a computer, enables the computer to execute the method as described in any one of the first aspects.

[0026] Other features and advantages disclosed in the present application will be described in the following description, or some features and advantages can be inferred or determined without doubt from the description, or can be learned by implementing the above-mentioned technology disclosed in the present application.

[0027] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0029] FIG1 is a flow chart of a battery thermal runaway detection method provided by some embodiments of the present application;

[0030] FIG2 is a schematic diagram of the workflow of a lithium battery thermal runaway early warning solution combining an electronic nose sensor array with a machine learning algorithm, provided in some embodiments of the present application;

[0031] FIG3 is a block diagram of a battery thermal runaway detection device provided in some embodiments of the present application;

[0032] FIG4 is a structural block diagram of an electronic device provided in some embodiments of the present application. DETAILED DESCRIPTION

[0033] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0035] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0036] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0037] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0038] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0039] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0040] In the description of the embodiments of the present application, unless otherwise expressly specified or limited, technical terms such as "installed," "connected," "connected," and "fixed" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components or interactions between two components. Those skilled in the art can understand the specific meanings of the above terms in the embodiments of the present application based on specific circumstances.

[0041] With the rapid development of electric vehicles, drones, energy storage systems, and other fields, the frequent occurrence of battery thermal runaway events has become a serious safety hazard. Thermal runaway refers to the phenomenon in which, under specific conditions such as overcharging, overheating, internal short circuits, or mechanical abuse, the internal reactions of lithium-ion batteries intensify uncontrollably, causing the battery temperature to rise rapidly, forming a vicious cycle. If timely intervention is not taken after a battery thermal runaway, the battery will eventually catch fire or explode. Therefore, timely monitoring and early warning of battery thermal runaway are particularly important. Currently, the main method for detecting thermal runaway in lithium batteries is to predict the battery's safety status based on external battery parameters such as temperature, voltage, and current. The accuracy of the prediction results of this method is poor, resulting in a high probability of false alarms.

[0042] To address the above technical issues, an embodiment of the present application provides a battery thermal runaway detection method. This method uses a gas sensor to identify the gas composition released by the battery, converts the time series signal generated by the gas sensor into an image signal, and then inputs the image signal into a target detection model to obtain the gas type and gas concentration predicted by the model. The risk of battery thermal runaway is then determined based on the model's prediction results. By converting the time series signal into an image format, enhancing the key features in the signal, and then combining it with a deep learning algorithm for signal analysis, the thermal runaway risk of lithium batteries can be accurately predicted, improving the accuracy of thermal runaway warnings.

[0043] Next, the embodiments of the present application are introduced:

[0044] As shown in Figure 1, Figure 1 is a flow chart of a battery thermal runaway detection method provided in an embodiment of the present application, which can be applied to an electronic nose. The electronic nose, also known as an odor scanner, is an intelligent electronic instrument designed and developed to simulate the human olfactory system. It can judge the sample itself by the odor emitted by the sample. Multiple gas sensors can be set in the electronic nose. These gas sensors can be MEMS (Microelectro Mechanical Systems) sensors. During implementation, a special material coating can be used on the MEMS sensor to make the sensor highly sensitive and selective to specific gases that may be released during lithium battery thermal runaway, such as hydrogen, carbon monoxide, methane, etc. This specificity ensures that the sensor can still accurately identify and quantify the relevant gases in complex environments. The electronic nose also includes a high-performance central processing unit or microcontroller, which can collect data from each MEMS sensor and then analyze and process the collected data using the method of this embodiment.

[0045] Of course, in other embodiments, the method can also be applied to other electronic devices with signal processing capabilities. The electronic device can obtain the corresponding signal from the gas sensor located near the battery through a wired connection or a wireless connection, and then analyze and process the signal.

[0046] The method comprises:

[0047] Step 101: Acquire a timing signal generated by a gas sensor when identifying gas components released by a battery, and convert the timing signal into an image signal;

[0048] In this embodiment, the surface of the gas sensor is coated with a chemical that reacts specifically with the target gas. When the target gas passes through the gas sensor, it reacts with the chemical, producing physical and electrochemical changes. Traditional chemical sensors primarily identify and analyze sample gases by collecting electrical signals triggered by chemical reactions. This approach faces significant limitations when processing complex gas mixtures, particularly when capturing the spatial and temporal characteristics of the signal.

[0049] When a gas sensor captures the gas components released by a battery, it generates a time-series signal—information representing the temporal changes of the electrical signal. In this embodiment, the time-series signal is converted into an image signal. Because the characteristics of a time-series signal can be more intuitively and comprehensively represented in two-dimensional space, converting the time-series data into an image format enhances key signal features, such as periodicity, trends, and pattern changes. This image representation makes the spatial and temporal characteristics of the signal more prominent, which is particularly important for complex gas analysis. It also lays a good foundation for the subsequent use of advanced machine learning and image processing algorithms to analyze these signals.

[0050] In some embodiments, the image signal mentioned in this step includes a grayscale image; the conversion of the timing signal into the image signal mentioned in this step may include: converting each data point in the timing signal generated by each gas sensor into a grayscale pixel, then splicing the grayscale pixels into a long strip image; and splicing the long strip images corresponding to all gas sensors to form a grayscale image. In other words, the timing signal generated by each gas sensor can be considered as a sensor response curve, where each response point on the sensor response curve corresponds to a grayscale pixel. After converting n points on the original sensor response curve into n grayscale pixels, they are spliced ​​into a long strip image consisting of n grayscale pixels in a row. If m gas sensors are installed in the electronic nose, the long strip images corresponding to the m gas sensors are spliced ​​up and down to form an n×m grayscale image. This n×m grayscale image is the image signal obtained by converting the timing signal.

[0051] Furthermore, in some embodiments, before converting the time series signal into an image signal, the step mentioned in this embodiment may include normalizing the time series signal. Normalization herein may refer to normalizing the data in the time series signal to a range of 0 to 1. Normalizing the points on the sensor response curve facilitates conversion of the points on the sensor response curve into grayscale pixels, while also ensuring that the time series data has a uniform scale in two-dimensional space, facilitating analysis of data trends and thereby improving the accuracy of subsequent prediction results.

[0052] Step 102: Process the image signal using a target detection model to obtain target gas information; the target gas information includes the gas type and gas concentration predicted by the target detection model;

[0053] The target detection model mentioned in this step can be a deep learning model for analyzing image signals to predict gas types and gas concentrations. That is to say, this embodiment introduces a machine learning algorithm to predict the risk of battery thermal runaway. Since the machine learning algorithm can handle the complex nonlinear relationship that may exist between thermal runaway risk and target factors, and is more adaptable, compared to the method of predicting the battery safety status through external battery parameters, this embodiment can achieve more accurate predictions. Specifically, in this embodiment, the input of the target detection model is an image signal, and the output includes gas type and gas concentration. In actual applications, when the electronic nose comes into contact with a new gas, the target detection model will be quickly activated to make real-time predictions of the gas type and gas concentration, thereby quickly and accurately detecting the risk of battery thermal runaway.

[0054] In some embodiments, the target detection model mentioned in this step includes a convolutional neural network and a long short-term memory network. The convolutional neural network is used to extract spatial features from the image signal, and the long short-term memory network is used to extract temporal features based on the changes of the spatial features over time. That is, the target detection model can combine CNN (Convolutional Neural Networks) and LSTM (Long Short-Term Memory) to analyze the image signal. CNN is a deep learning algorithm widely used in the field of visual image analysis. In this embodiment, CNN can process the image signal through its multi-layer structure, including convolution layers, activation layers, pooling layers, etc., to extract spatial features such as shape, edge, texture, etc. in the image signal; LSTM is a deep learning algorithm specifically for processing time series data. Since the behavior and concentration of gas over time may contain important information, the time factor is very important for processing gas concentration data. In the embodiment, LSTM can process the changes of the features extracted by CNN over time and extract temporal features, that is, patterns or trends that recur in the time series, so as to accurately predict the future trend of gas concentration. In this way, the spatial features extracted by CNN and the temporal features extracted by LSTM are fused within the model. This fusion ensures that the model not only considers the gas state of each frame, but also the evolution of these states over time. Based on this comprehensive information, the model can make more accurate predictions. In addition, the output of the target detection model may include a gas type classification part and a gas concentration prediction part, wherein the classification part may use a Softmax function to determine the probability of each gas, and the prediction part may use regression analysis to give a specific numerical value. Of course, in other embodiments, the target detection model may also be implemented using other machine learning algorithms, such as support vector machines, random forests, etc. For the specific implementation principles, please refer to the introduction of the corresponding algorithms in the relevant technology, which will not be elaborated here.

[0055] In some embodiments, the target detection model can be trained based on the following method: inputting training samples into the initial detection model to obtain predicted gas information output by the initial detection model; the training samples are obtained by collecting the timing signals generated by the gas sensor when identifying different sample gases, and then converting the timing signals into image signals; constructing a loss function based on the predicted gas information and the real gas information; the real gas information includes the actual gas type and actual gas concentration of the corresponding sample gas; optimizing the model parameters of the initial detection model based on the loss function, and determining the optimized initial detection model as the target detection model. That is to say, during implementation, the timing signals generated by the gas sensor when identifying different sample gases can be collected, converted into image signals according to the same conversion method, and used as training samples to train the target detection model; the actual gas type and actual gas concentration of these sample gases are determined, and they constitute the real gas information. The predicted gas information output after the image signal of the sample gas is processed by the initial detection model and the real gas information can be used to construct a loss function. The model minimizes the loss function by adjusting the network weights. During the training process, optimization algorithms such as Adam can also be used to help the model learn the most effective feature representation and time dependency on the training data, thereby obtaining a target detection model that can accurately predict the gas type and gas concentration.

[0056] In addition, during training, methods such as Kaiming initialization can be used to dynamically adjust the distribution of network layer weights to avoid gradient vanishing or exploding problems during training, thereby accelerating the convergence of the neural network. Regularization techniques such as Dropout can also be used to enable the network to learn more robust features, thereby improving generalization capabilities. Moreover, a neural network combining 1D-CNN and LSTM can be used for training for 200 epochs to enable the model to achieve a judgment accuracy of about 95%.

[0057] Step 103: Determine the risk of battery thermal runaway according to the target gas information.

[0058] The types and concentrations of gases that lithium batteries may release under normal operation and thermal runaway conditions are different. Under normal operating conditions, lithium batteries may release small amounts of harmless or low-toxic gases, such as carbon dioxide. However, under thermal runaway conditions, lithium batteries may release large amounts of toxic, flammable, or explosive gases, such as carbon monoxide and methane. Therefore, after obtaining the gas type and gas concentration predicted by the target detection model, the prediction results can be used to determine whether there is a risk of battery thermal runaway. If the prediction results indicate a risk of battery thermal runaway, a warning message is output to enable timely user intervention, thereby reducing losses caused by battery thermal runaway.

[0059] In some embodiments, the determination of the risk of battery thermal runaway based on the target gas information mentioned in this step may include: when the gas type predicted by the target detection model includes a specified gas, and the gas concentration predicted by the target detection model for the specified gas is greater than or equal to a preset concentration, it is determined that there is a risk of battery thermal runaway. The specified gas here can be a characteristic gas that may be released when the lithium battery is in thermal runaway, such as any one of carbon monoxide and methane. The preset concentration can be set based on the gas production of the specified gas when the lithium battery is in thermal runaway. In this way, after the gas is qualitatively and quantitatively identified by the target detection model, it can be determined whether there is a risk of battery thermal runaway based on the concentration value of the characteristic gas, so as to decide whether to alarm. In this way, early warning of battery thermal runaway can be achieved efficiently and accurately.

[0060] In this embodiment of the application, the timing signal generated by the gas sensor when identifying the gas components released by the battery is obtained. The timing signal is then converted into an image signal to enhance the key features in the signal. The image signal is then processed by a target detection model to predict the gas type and gas concentration, and the risk of battery thermal runaway is determined based on the predicted results. In this way, by introducing a machine learning algorithm, not only simple gas identification needs can be met, but also complex data analysis and prediction can be performed, thereby accurately predicting the thermal runaway risk of lithium batteries and effectively improving the accuracy of thermal runaway warnings.

[0061] In order to explain the solution of this application in more detail, a specific embodiment is introduced below:

[0062] This embodiment provides a lithium battery thermal runaway early warning solution that combines an electronic nose sensor array with a machine learning algorithm. The working process of this solution is shown in Figure 2. As can be seen from Figure 2, this solution is applied to an electronic nose 21, which includes a sensor array 22 and a central processing unit 23. The sensor array 22 includes multiple MEMS sensors 24 for capturing gas components released by lithium batteries. These sensors generate time series signals when capturing gas components, that is, signals that change over time.

[0063] The central processing unit 23 includes a data processing subunit 25, a model detection subunit 26, a risk identification subunit 27 and an early warning submodule 28, wherein:

[0064] The data processing subunit 25 is responsible for pre-processing the data from the sensor array 22 after the central processing unit 23 collects the data, such as baseline calibration, outlier detection, normalization, etc. The data processing subunit 25 is also responsible for converting the pre-processed time series signal into an image signal;

[0065] The model detection subunit 26 includes a target detection model, which combines CNN and LSTM to process image signals. The internal processing mechanism of the target detection model can be specifically described as follows: in the feature extraction part, CNN processes the image signal through its multi-layer structure, including convolutional layers, activation layers, pooling layers, etc., and extracts useful features. These features capture the spatial patterns in the image, such as shape, edge and texture; in the sequence processing part, LSTM captures the dynamic changes of the features extracted by CNN over time; in the data fusion part, the spatial features extracted by CNN and the sequence processing results of LSTM are fused within the model; in the output part, the model uses the Softmax function to determine the probability of each gas, and uses regression analysis to analyze the concentration value of the gas, and then outputs the gas type and gas concentration;

[0066] The risk identification subunit 27 is responsible for determining the signature gas and the concentration of the signature gas in the current lithium battery pack according to the output of the target detection model, and then judging whether there is a thermal runaway risk according to the concentration of the signature gas;

[0067] The early warning submodule 28 can output early warning information when the risk identification subunit 27 determines that there is a thermal runaway risk, such as controlling an audible and visual alarm to emit an alarm signal, and sending information indicating the presence of a thermal runaway risk to a user terminal.

[0068] Through this embodiment scheme, the thermal runaway risk of lithium batteries can be accurately identified, and significant efficiency and accuracy can be demonstrated in lithium battery safety monitoring, thereby providing strong technical support for lithium battery safety.

[0069] Corresponding to the embodiments of the aforementioned method, the present application also provides embodiments of a battery thermal runaway detection device and a terminal using the same:

[0070] As shown in FIG3 , FIG3 is a block diagram of a battery thermal runaway detection device provided in an embodiment of the present application, the device comprising:

[0071] an acquisition module 31, configured to acquire a timing signal generated by the gas sensor when identifying gas components released by the battery, and convert the timing signal into an image signal;

[0072] a processing module 32 for processing the image signal using a target detection model to obtain target gas information; the target gas information includes the gas type and gas concentration predicted by the target detection model;

[0073] The determination module 33 is configured to determine the risk of thermal runaway of the battery according to the target gas information.

[0074] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0075] The present application also provides an electronic device. Please refer to Figure 4, which is a structural block diagram of an electronic device provided in an embodiment of the present application. The electronic device may include a processor 410, a communication interface 420, a memory 430, and at least one communication bus 440. Among them, the communication bus 440 is used to realize direct connection and communication between these components. Among them, the communication interface 420 of the electronic device in the embodiment of the present application is used to communicate signaling or data with other node devices. The processor 410 can be an integrated circuit chip with signal processing capabilities.

[0076] The processor 410 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), or the like; 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, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. The processor 410 may be a microprocessor, or it may be any conventional processor.

[0077] The memory 430 may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory 430 stores computer-readable instructions. When the processor 410 executes the computer-readable instructions, the electronic device may perform the steps of the method embodiment of FIG. 1 .

[0078] Optionally, the electronic device may further include a storage controller and an input / output unit.

[0079] The memory 430, storage controller, processor 410, peripheral interface, and input / output units are electrically connected to each other directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses 440. The processor 410 is used to execute executable modules stored in the memory 430, such as software function modules or computer programs included in the electronic device.

[0080] The input and output unit is used to provide users with the ability to create tasks and to create optional time periods or preset execution times for the tasks to enable interaction between the user and the server. The input and output unit can be, but is not limited to, a mouse and a keyboard.

[0081] It is understood that the structure shown in Figure 4 is merely illustrative, and the electronic device may include more or fewer components than shown in Figure 4, or have a configuration different from that shown in Figure 4. Each component shown in Figure 4 may be implemented using hardware, software, or a combination thereof.

[0082] An embodiment of the present application further provides a storage medium having instructions stored thereon. When the instructions are run on a computer, the computer program is executed by a processor to implement the method described in the method embodiment. To avoid repetition, details are not given here.

[0083] The present application also provides a computer program product, which, when running on a computer, enables the computer to execute the method described in the method embodiment.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0085] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0086] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0087] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures.

[0088] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0089] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

Claims

1. A battery thermal runaway detection method, characterized in that: include: Acquire a timing signal generated by the gas sensor when identifying gas components released by the battery, and convert the timing signal into an image signal; Processing the image signal through a target detection model to obtain target gas information; the target gas information includes the gas type and gas concentration predicted by the target detection model; The risk of battery thermal runaway is determined based on the target gas information.

2. The method according to claim 1, characterized in that The method is applied to an electronic nose, wherein a plurality of the gas sensors are arranged in the electronic nose.

3. The method according to claim 2, characterized in that The image signal includes a grayscale image; and converting the time series signal into an image signal includes: Converting each data in the timing signal generated by each gas sensor into a grayscale pixel point, and then splicing the grayscale pixel points into a long strip image; All the strip images corresponding to the gas sensors are spliced ​​together to form a grayscale image.

4. The method according to any one of claims 1 to 3, characterized in that Before converting the timing signal into an image signal, the method includes: Normalization processing is performed on the time series signal.

5. The method according to any one of claims 1 to 4, characterized in that The target detection model includes a convolutional neural network and a long short-term memory network; the convolutional neural network is used to extract spatial features from the image signal; the long short-term memory network is used to extract temporal features based on the changes of the spatial features over time.

6. The method according to any one of claims 1 to 5, characterized in that The target detection model is trained based on the following method: Inputting training samples into an initial detection model to obtain predicted gas information output by the initial detection model; the training samples are obtained by collecting time series signals generated by a gas sensor when identifying different sample gases and then converting the time series signals into image signals; Constructing a loss function based on the predicted gas information and the real gas information; the real gas information includes the actual gas type and actual gas concentration of the corresponding sample gas; The model parameters of the initial detection model are optimized based on the loss function, and the optimized initial detection model is determined as the target detection model.

7. The method according to any one of claims 1 to 6, characterized in that Determining the risk of battery thermal runaway according to the target gas information includes: When the gas type predicted by the target detection model includes a specified gas, and the gas concentration predicted by the target detection model for the specified gas is greater than or equal to a preset concentration, it is determined that there is a risk of battery thermal runaway.

8. A battery thermal runaway detection device, characterized in that: The device comprises: an acquisition module, configured to acquire a timing signal generated by the gas sensor when identifying gas components released by the battery, and convert the timing signal into an image signal; a processing module, configured to process the image signal through a target detection model to obtain target gas information; the target gas information includes the gas type and gas concentration predicted by the target detection model; A determination module is used to determine the risk of battery thermal runaway based on the target gas information.

9. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images