Thermal runaway early warning method and system, electronic equipment and computer storage medium

Abstract

The invention relates to a thermal runaway early warning method and system, electronic equipment and a computer storage medium, and belongs to the technical field of battery management.The thermal runaway early warning method comprises the steps that synchronous signal components of a voltage signal of a battery cell, a temperature signal in the battery cell and an air pressure signal are obtained; performing multi-scale time sequence slicing on the synchronous signal component to obtain a multi-scale time sequence feature vector, and constructing a thermal runaway trend feature vector of the battery cell based on the multi-scale time sequence feature vector; and determining the thermal runaway trend of the battery cell based on the similarity between the thermal runaway trend feature vector and a preset thermal runaway standard trend vector, and carrying out multistage thermal runaway early warning on the battery cell based on the thermal runaway trend. According to the invention, the real-time performance and the accuracy of battery cell thermal runaway early warning can be improved.

Description

Technical Field

[0001] This invention relates to the field of battery management technology, and in particular to a thermal runaway early warning method, system, electronic device, and computer storage medium. Background Technology

[0002] Lithium iron phosphate batteries are widely used in new energy and energy storage fields due to their advantages such as high safety and long cycle life. However, under conditions such as overcharging, high temperature, and internal short circuit, thermal runaway may still occur. The uncontrolled chemical reaction inside the battery causes a sharp increase in temperature and pressure, which can lead to electrolyte leakage, fire or even explosion, seriously threatening the safety of equipment operation.

[0003] Existing thermal runaway early warning technologies for lithium iron phosphate batteries have significant limitations: most rely on single temperature monitoring, resulting in strong warning lag, often triggering alarms only in the later stages of thermal runaway; while some technologies add voltage monitoring, they are easily affected by charging fluctuations, leading to a high false alarm rate.

[0004] This shows that existing battery management technologies rely on a single source of predictive signals for cell thermal runaway warnings, resulting in untimely alarms and a high false alarm rate. Summary of the Invention

[0005] In view of this, it is necessary to provide a thermal runaway early warning method, system, electronic device and computer storage medium to solve the problems of existing battery management technology having a single source of predictive signals for cell thermal runaway early warning, insufficient alarm timeliness and high false alarm rate.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides a thermal runaway early warning method, comprising: Acquire the voltage signal of the battery cell, the temperature signal inside the battery cell, and the synchronization signal component of the air pressure signal; Multi-scale time-series slicing is performed on the synchronization signal components to obtain multi-scale time-series feature vectors, and thermal runaway trend feature vectors of the battery cell are constructed based on the multi-scale time-series feature vectors. The thermal runaway trend of the battery cell is determined based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector, and multi-level thermal runaway early warning is performed on the battery cell based on the thermal runaway trend.

[0007] In one possible implementation, acquiring the synchronization signal components of the battery cell's voltage signal, the temperature signal inside the battery cell, and the air pressure signal includes: Simultaneously acquire the voltage signal, internal temperature signal, and air pressure signal of the battery cell in real time; Adaptive filtering and signal decomposition are performed on voltage, temperature, and air pressure signals to obtain synchronous signal components of the voltage, temperature, and air pressure signals.

[0008] In one possible implementation, multi-scale time-series slices are performed on voltage, temperature, and air pressure to obtain a multi-scale time-series feature vector, including: Multi-scale time-series slicing is performed on the synchronization signal components of voltage, temperature, and air pressure signals to obtain multi-scale synchronization slice signals of voltage, temperature, and air pressure signals; Based on the variation trend of each signal in the multi-scale synchronous slice signal at different time scales, the variation trend of each signal at different time scales is determined, and the multi-scale temporal feature vector of each signal is constructed based on the variation trend.

[0009] In one possible implementation, a thermal runaway trend feature vector of the battery cell is constructed based on a multi-scale time-series feature vector, including: The multi-scale time-series feature vectors of each signal are fused according to the time scale to generate a multi-scale thermal runaway trend feature vector of the battery cell. The multi-scale thermal runaway trend feature vectors are fused according to their temporal relationship to obtain the thermal runaway trend feature vector of the battery cell.

[0010] In one possible implementation, the thermal runaway trend of the battery cell is determined based on the similarity between the thermal runaway trend feature vector and a preset thermal runaway standard trend vector, including: Determine the standard trend vector of thermal runaway of the battery cell based on the cell type; Calculate the similarity between the thermal runaway trend feature vector and the thermal runaway standard trend vector. When the similarity is greater than or equal to the first similarity threshold and less than the second similarity threshold, the cell is determined to be in a cell depressurization trend. When the similarity is greater than or equal to the second similarity threshold, the cell is determined to be in a thermal runaway trend.

[0011] In one possible implementation, multi-level thermal runaway early warning for the battery cell is performed based on the thermal runaway trend, including: When a battery cell is in a state of pressure leakage, a battery cell pressure leakage alarm is triggered. When a battery cell is in a state of thermal runaway, a battery cell thermal runaway alarm is triggered.

[0012] Secondly, the present invention also provides a thermal runaway early warning system, comprising: Sensors are used to collect data on the voltage, internal temperature, and air pressure of the battery cell. The data processing unit is used to perform multi-scale time-series slicing of voltage, temperature and air pressure to obtain multi-scale time-series feature vectors, and to construct a thermal runaway trend feature vector of the battery cell based on the multi-scale time-series feature vectors; and to determine the thermal runaway trend of the battery cell based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector. An alarm unit is used to provide multi-level thermal runaway early warning for battery cells based on thermal runaway trends.

[0013] In one possible implementation, the sensor includes a voltage sensor, a pressure sensor disposed inside the battery cell, and a temperature sensor.

[0014] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein, Memory, used to store programs; The processor, coupled to the memory, is used to execute a program stored in the memory to implement the steps in the thermal runaway early warning method of any of the above embodiments.

[0015] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps in the thermal runaway early warning method of any of the above embodiments.

[0016] The beneficial effects of this invention are as follows: The thermal runaway early warning method provided in this embodiment acquires the synchronous signal components of the battery cell's voltage signal, the temperature signal inside the battery cell, and the air pressure signal; it uses multiple data sources for thermal runaway early warning of the battery cell, avoiding untimely thermal runaway early warning due to a single data source and reducing the false alarm rate. By performing multi-scale time-series slicing on the synchronous signal components, multi-scale time-series feature vectors are obtained, and a thermal runaway trend feature vector of the battery cell is constructed based on the multi-scale time-series feature vectors. By analyzing signals at different time scales and determining the thermal runaway trend of the battery cell based on each signal, the thermal runaway trend of the battery cell can be predicted in advance, enabling early warning and further improving the real-time performance of the alarm. Furthermore, the thermal runaway trend of the battery cell is determined based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector. Multi-level thermal runaway early warning is then provided for the battery cell based on the thermal runaway trend. The thermal runaway trend of the battery cell is determined based on the thermal runaway trend feature vector and the preset thermal runaway standard trend vector. Multi-level alarms are then provided based on the thermal runaway trend. The alarms can be graded according to the severity of the thermal runaway, making it more applicable. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic flowchart of a thermal runaway early warning method provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating a signal acquisition method provided in an embodiment of the present invention; Figure 3 A flowchart illustrating a method for determining multi-scale temporal feature vectors provided in an embodiment of the present invention; Figure 4 A flowchart illustrating a method for constructing a thermal runaway trend feature vector according to an embodiment of the present invention; Figure 5 A flowchart illustrating a method for determining thermal runaway trends provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of a thermal runaway early warning system provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which constitute a part of the present invention and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0021] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] A specific embodiment of the present invention, such as Figure 1 As shown, a thermal runaway early warning method is disclosed, including: S101, acquire the voltage signal of the battery cell, the temperature signal inside the battery cell, and the synchronization signal component of the air pressure signal.

[0024] In this embodiment of the invention, the provided thermal runaway early warning method can realize thermal runaway early warning of the battery and can be applied to existing battery management systems. The charging device is connected to the lithium battery pack via cables or copper busbars. The battery management system starts up and completes communication self-test with the pressure sensor, temperature sensor, and voltage sensor to confirm that the data acquisition function of each sensor is normal and there is no communication interruption or data abnormality. During the charging process, the battery management system reads the data output by the pressure sensor inside the cell, the temperature sensor attached to the surface of the cell, and the voltage sensor connected in series in the battery circuit and uploads it to the battery management system via Ethernet or CAN communication.

[0025] S102, perform multi-scale time-series slicing on the synchronization signal components to obtain multi-scale time-series feature vectors, and construct the thermal runaway trend feature vector of the battery cell based on the multi-scale time-series feature vectors.

[0026] In this embodiment of the invention, the obtained voltage, temperature, and air pressure of the battery cell are data within a certain time period. It is necessary to determine the thermal runaway trend of the battery cell based on the voltage, temperature, and air pressure within this time period. To ensure the accuracy of the thermal runaway trend determination, multi-scale time-series slicing of the voltage, temperature, and air pressure can be performed. Based on the time length of different scales, the voltage, temperature, and air pressure are sliced ​​according to their temporal relationships, resulting in multiple slice data segments. Corresponding multi-scale time-series feature vectors are extracted from each slice data segment. Then, the multi-scale time-series feature vectors of voltage, temperature, and air pressure are fused to obtain the thermal runaway trend feature vector of the battery cell. This feature vector characterizes the thermal runaway trend of the battery cell. The construction of multi-scale time-series slicing and the thermal runaway trend feature vector of the battery cell will be described in detail later in this invention.

[0027] S103, the thermal runaway trend of the battery cell is determined based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector, and multi-level thermal runaway early warning is performed on the battery cell based on the thermal runaway trend.

[0028] In this embodiment of the invention, after determining the thermal runaway trend feature vector of the battery cell, the thermal runaway trend feature vector is compared with a preset thermal runaway standard trend feature vector, the similarity between the two is calculated, and the thermal runaway trend of the battery cell is determined based on the similarity. Then, multi-level thermal runaway early warning is performed on the battery cell based on the thermal runaway trend. Specifically, different degrees of thermal runaway correspond to different levels of thermal runaway early warning.

[0029] The thermal runaway early warning method provided in this invention acquires synchronous signal components of the battery cell's voltage signal, internal temperature signal, and air pressure signal. It utilizes multiple data sources for thermal runaway early warning, avoiding untimely warnings due to a single data source and reducing false alarm rates. By performing multi-scale time-series slicing on the synchronous signal components, multi-scale time-series feature vectors are obtained. Based on these feature vectors, a thermal runaway trend feature vector for the battery cell is constructed. Signals at different time scales are analyzed, and the thermal runaway trend of the battery cell is determined based on each signal. This allows for early prediction of the thermal runaway trend, enabling early warning and further improving the real-time performance of the alarm. Furthermore, the thermal runaway trend of the battery cell is determined based on the similarity between the thermal runaway trend feature vector and a preset thermal runaway standard trend vector. Multi-level thermal runaway early warning is then performed based on this trend. The thermal runaway trend is determined by comparing the feature vector with the preset standard trend vector, and multi-level alarms are implemented. This allows for graded alarms based on the severity of the thermal runaway, enhancing applicability.

[0030] In some possible embodiments of the present invention, such as Figure 2 As shown, the synchronization signal components for acquiring the voltage signal of the battery cell, the temperature signal inside the battery cell, and the air pressure signal include: S201 synchronously acquires the voltage signal, internal temperature signal, and air pressure signal of the battery cell in real time. S202 performs adaptive filtering and signal decomposition processing on the voltage signal, temperature signal, and air pressure signal to obtain the synchronization signal components of the voltage signal, temperature signal, and air pressure signal.

[0031] In this embodiment of the invention, the voltage, temperature, and air pressure of the battery cell can be acquired synchronously by a pressure sensor installed inside the battery cell, a temperature sensor attached to the surface of the battery cell, and a voltage sensor connected in series in the battery cell circuit. To ensure strict time synchronization, the signals from each sensor are digitized by a multi-channel synchronous sampling analog-to-digital converter driven by the same clock after being conditioned by a conditioning circuit, and a uniform timestamp is added to each sampling point.

[0032] Furthermore, noise disturbances occur during the acquisition of voltage, temperature, and pressure signals from the battery cell, causing signal fluctuations and noise contamination. It is necessary to extract essential characteristic components reflecting the internal electrochemical processes, thermal behavior, and mechanical changes of the battery cell from the noise-contaminated original synchronization signals. Through adaptive filtering and signal decomposition, the synchronization signal components of the voltage, temperature, and pressure signals can be obtained. Specifically, due to the complex operating environment of the battery cell, noise (such as switching noise from charging and discharging equipment, vehicle vibration noise, and electromagnetic interference) has non-stationary and time-varying characteristics, making it difficult for traditional fixed-parameter filters to achieve ideal results. This invention employs an adaptive filter based on the Least Mean Square (LMS) or Recursive Least Squares (RLS) algorithm to perform preliminary noise reduction on the signal of each channel. Its core idea is to dynamically adjust the filter weight coefficients using the signal's own characteristics or a reference noise source to suppress noise in the optimal way. Further, taking LMS adaptive filtering as an example, its weight coefficient update formula is:

[0033] in, Let be the filter weight coefficient vector at time n. Let be the filter weight coefficient vector at time n+1. Let n be the input signal vector at time n. This is the step size factor, which controls the convergence speed and stability. Let n be the error signal at time n. By performing preliminary filtering on the original voltage, temperature, and air pressure signals, we can obtain the denoised voltage, temperature, and air pressure.

[0034] Furthermore, to separate characteristic components related to the main physicochemical processes inside the battery cell (such as lithium-ion insertion / extraction, side reactions, heat generation, and gas generation) from the initially denoised signal, this invention employs signal decomposition technology to decompose the initially denoised signal, obtaining synchronous signal components of voltage, temperature, and gas pressure signals. For example, for the voltage signal... For example, the goal of signal decomposition is to decompose it into K-dimensional mode functions. This minimizes the sum of the estimated bandwidths of all modes. Specifically, the decomposition formula is as follows:

[0035]

[0036] in, voltage signal The k-th modal component, Let be the center frequency of the k-th modal component. For the Dirac function, This indicates taking the partial derivative with respect to the event, where j is the imaginary unit.

[0037] This invention ensures signal synchronization by synchronously acquiring cell voltage, temperature, and air pressure signals. At the same time, through adaptive filtering and signal decomposition, noise in the original signals can be removed, and the synchronization signal components of each signal can be obtained, which facilitates subsequent thermal runaway analysis.

[0038] In some possible embodiments of the present invention, such as Figure 3 As shown, multi-scale time-series slices are performed on voltage, temperature, and air pressure to obtain multi-scale time-series feature vectors, including: S301, perform multi-scale time-series slicing on the synchronization signal components of voltage signal, temperature signal and air pressure signal respectively to obtain multi-scale synchronization slice signals of voltage signal, temperature signal and air pressure signal; S302, based on the changing trends of each signal in the multi-scale synchronous slice signal at different time scales, determine the changing trends of each signal at different time scales, and construct the multi-scale temporal feature vector of each signal based on the changing trends.

[0039] In this embodiment of the invention, the multi-scale time-series slicing is used to transform the synchronization signal components obtained in the aforementioned embodiments from continuous time-domain waveforms into a series of discrete segments with clear time scales and contextual information. The multi-scale strategy aims to simultaneously capture the rapid transient response and slow evolution trends of processes within the battery cell, such as ion migration, instantaneous heat generation, accumulation of side reactions, and aging degradation. Specifically, for each synchronization signal component, multiple different time scales are constructed, each corresponding to a time observation perspective from short to long. For each synchronization signal component, at each preset time scale, a sliding window slice is performed along the time axis with a fixed or adaptive step size to obtain a multi-scale synchronization slice signal.

[0040] Furthermore, for each multi-scale synchronous slice signal, its trend features need to be extracted to determine the thermal runaway trend of the battery cell. For a single slice signal, its changing trend can be quantified by calculating the time-series characteristic parameters of the slice, such as linear slope trend, curvature or nonlinearity measure, extreme values ​​and fluctuations, statistical characteristics, etc. Furthermore, the co-current trends between various signals can also be calculated, such as trend synchronization, calculating the correlation coefficient or phase difference between the slopes of voltage and temperature slices to reflect the tightness of electrothermal coupling; and the trend amplitude ratio, the ratio of the slope of gas pressure change to the slope of temperature change, which can indirectly reflect the intensity relationship between gas generation and heat generation reactions. Based on the changing trends of each signal and the co-current trends, a multi-scale time-series feature vector of corresponding dimensions is constructed.

[0041] This invention provides a method for analyzing the thermal runaway trend of battery cells by performing multi-scale time-series slicing on signals, processing different signals separately, and analyzing the changing trends of each signal.

[0042] In some possible embodiments of the present invention, such as Figure 4 As shown, a feature vector for the thermal runaway trend of a battery cell is constructed based on multi-scale time-series feature vectors, including: S401 fuses the multi-scale time-series feature vectors of each signal according to the time scale to generate a multi-scale thermal runaway trend feature vector of the battery cell. S402 fuses the multi-scale thermal runaway trend feature vectors according to the temporal relationship to obtain the thermal runaway trend feature vector of the battery cell.

[0043] In this embodiment of the invention, after obtaining the multi-scale time-series feature vectors of each signal, the feature vectors of the same time scale of each signal are fused to generate a multi-scale thermal runaway trend feature vector of the battery cell. Then, the multi-scale thermal runaway trend feature vectors are fused according to the temporal relationship of each multi-scale thermal runaway trend feature vector to generate the final thermal runaway trend feature vector. For example, voltage, temperature, and air pressure signals each have three time-series feature vectors at three time scales. According to the time scale, voltage, temperature, and air pressure signals at the same time scale are fused to obtain three three-dimensional thermal runaway trend feature vectors. Then, these three three-dimensional thermal runaway trend feature vectors are fused to obtain a 9-dimensional thermal runaway trend feature vector. The specific method of feature fusion can be determined according to the actual situation, and this invention does not limit it.

[0044] The embodiments of the present invention fuse the multi-scale time-series feature vectors of each signal to obtain the multi-scale time-series feature vectors of each signal, which facilitates the subsequent identification of the thermal runaway trend of the battery cell.

[0045] In some possible embodiments of the present invention, such as Figure 5 As shown, the thermal runaway trend of the battery cell is determined based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector, including: S501, Determine the standard trend vector of thermal runaway of the battery cell based on the type of the battery cell; S502, calculate the similarity between the thermal runaway trend feature vector and the thermal runaway standard trend vector. When the similarity is greater than or equal to the first similarity threshold and less than the second similarity threshold, the cell is determined to be in a cell depressurization trend; when the similarity is greater than or equal to the second similarity threshold, the cell is determined to be in a thermal runaway trend.

[0046] In this embodiment of the invention, the thermal runaway standard trend vector may be different for different types and models of battery cells. The thermal runaway standard trend vector of various types and signals of battery cells can be determined by pre-experimentation. Then, according to the type of battery cell to be judged, the corresponding thermal runaway standard trend vector is determined. Then, the similarity between the thermal runaway trend feature vector of the battery cell to be judged and the thermal runaway standard trend vector is calculated. The similarity calculation method can adopt existing technology, such as pre-similarity, etc. Then, according to the relationship between the similarity and the pre-set similarity threshold, the thermal runaway trend of the battery cell is determined.

[0047] Furthermore, based on the thermal runaway trend, multi-level thermal runaway early warning systems are implemented for battery cells, including: When a battery cell is in a state of pressure leakage, a battery cell pressure leakage alarm is triggered. When a battery cell is in a state of thermal runaway, a battery cell thermal runaway alarm is triggered.

[0048] In this embodiment of the invention, when the similarity is greater than or equal to a first similarity threshold and less than a second similarity threshold, the battery cell is determined to be in a depressurization trend, triggering a depressurization alarm. For example, if the battery cell's pressure rise is greater than 3 kPa, it indicates that the battery cell may be depressurizing, and the battery management system will issue a depressurization trend alarm. When the similarity is greater than or equal to the second similarity threshold, the battery cell is determined to be in a thermal runaway trend, triggering a thermal runaway alarm. For example, if the temperature rise rate is ≥1℃ / s and lasts for more than 3 seconds, and the pressure rise exceeds 20 kPa, it indicates that the battery cell has a thermal runaway trend and may experience accidents such as deflagration or leakage, and the battery management system will issue a thermal runaway trend alarm.

[0049] This invention provides multi-level alarms based on different thermal runaway trends in battery cells, improving alarm accuracy and the applicability of thermal runaway early warning.

[0050] To better implement the thermal runaway early warning method in the embodiments of the present invention, based on the thermal runaway early warning method, correspondingly, such as Figure 6 As shown, this embodiment of the invention also provides a thermal runaway early warning system, the thermal runaway early warning system 600 including: Sensor 601 is used to collect the voltage signal of the battery cell, the temperature signal inside the battery cell, and the air pressure signal. The data processing unit 602 is used to perform multi-scale time-series slicing on voltage signals, temperature signals, and air pressure signals to obtain multi-scale time-series feature vectors, and to construct a thermal runaway trend feature vector of the battery cell based on the multi-scale time-series feature vectors; and to determine the thermal runaway trend of the battery cell based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector. Alarm unit 603 is used to provide multi-level thermal runaway early warning for the battery cell based on the thermal runaway trend.

[0051] The thermal runaway early warning system 600 provided in the above embodiments can realize the technical solutions described in the above thermal runaway early warning method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above thermal runaway early warning method embodiments, and will not be repeated here.

[0052] like Figure 7 As shown, the present invention also provides an electronic device 700. The electronic device 700 includes a processor 701, a memory 702, and a display 703. Figure 7 Only some components of the electronic device 700 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0053] In some embodiments, processor 701 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in memory 702 or process data, such as the thermal runaway early warning method of the present invention.

[0054] In some embodiments, processor 701 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 701 may be local or remote. In some embodiments, processor 701 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, or any combination thereof.

[0055] In some embodiments, memory 702 may be an internal storage unit of electronic device 700, such as a hard disk or memory of electronic device 700. In other embodiments, memory 702 may also be an external storage device of electronic device 700, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 700.

[0056] Furthermore, the memory 702 may include both internal storage units of the electronic device 700 and external storage devices. The memory 702 is used to store application software and various types of data installed on the electronic device 700.

[0057] In some embodiments, display 703 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 703 is used to display information from electronic device 700 and to display a visual user interface. Components 701-703 of electronic device 700 communicate with each other via a system bus.

[0058] In some embodiments, when the processor 701 executes the thermal runaway warning program in the memory 702, the following steps may be implemented: Acquire the voltage signal of the battery cell, the temperature signal inside the battery cell, and the synchronization signal component of the air pressure signal; Multi-scale time-series slicing is performed on the synchronization signal components to obtain multi-scale time-series feature vectors, and thermal runaway trend feature vectors of the battery cell are constructed based on the multi-scale time-series feature vectors. The thermal runaway trend of the battery cell is determined based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector, and multi-level thermal runaway early warning is performed on the battery cell based on the thermal runaway trend.

[0059] It should be understood that when the processor 701 executes the thermal runaway warning program in the memory 702, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0060] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 700 mentioned. Electronic device 700 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 700 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0061] Accordingly, embodiments of the present invention also provide a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the thermal runaway early warning methods provided in the above-described method embodiments.

[0062] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0063] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for early warning of thermal runaway, characterized in that, include: Acquire the voltage signal of the battery cell, the temperature signal inside the battery cell, and the synchronization signal component of the air pressure signal; The synchronization signal components are sliced ​​at multiple scales to obtain a multi-scale time-series feature vector, and the thermal runaway trend feature vector of the battery cell is constructed based on the multi-scale time-series feature vector. The thermal runaway trend of the battery cell is determined based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector, and multi-level thermal runaway early warning is performed on the battery cell based on the thermal runaway trend.

2. The thermal runaway early warning method according to claim 1, characterized in that, The synchronization signal components for acquiring the voltage signal of the battery cell, the temperature signal inside the battery cell, and the air pressure signal include: The voltage signal of the battery cell, the temperature signal inside the battery cell, and the air pressure signal are acquired synchronously in real time. Adaptive filtering and signal decomposition processing are performed on the voltage signal, the temperature signal, and the air pressure signal to obtain the synchronization signal components of the voltage signal, the temperature signal, and the air pressure signal.

3. The thermal runaway early warning method according to claim 2, characterized in that, The process of performing multi-scale time-series slicing on the voltage, temperature, and air pressure to obtain a multi-scale time-series feature vector includes: The synchronization signal components of the voltage signal, the temperature signal, and the air pressure signal are each subjected to multi-scale time-series slicing to obtain multi-scale synchronization slice signals of the voltage signal, the temperature signal, and the air pressure signal. Based on the changing trends of each signal in the multi-scale synchronous slice signal at different time scales, the changing trends of each signal at different time scales are determined, and multi-scale temporal feature vectors of each signal are constructed based on the changing trends.

4. The thermal runaway early warning method according to claim 3, characterized in that, The construction of the thermal runaway trend feature vector of the battery cell based on the multi-scale time-series feature vector includes: The multi-scale time-series feature vectors of each signal are fused according to the time scale to generate the multi-scale thermal runaway trend feature vector of the battery cell. The multi-scale thermal runaway trend feature vectors are fused according to their temporal relationship to obtain the thermal runaway trend feature vector of the battery cell.

5. The thermal runaway early warning method according to claim 1, characterized in that, Determining the thermal runaway trend of the battery cell based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector includes: Determine the standard trend vector of thermal runaway of the battery cell based on the type of the battery cell; Calculate the similarity between the thermal runaway trend feature vector and the thermal runaway standard trend vector. When the similarity is greater than or equal to a first similarity threshold and less than a second similarity threshold, determine that the cell is in a cell depressurization trend. When the similarity is greater than or equal to the second similarity threshold, determine that the cell is in a thermal runaway trend.

6. The thermal runaway early warning method according to claim 5, characterized in that, The multi-level thermal runaway early warning system for the battery cell based on the thermal runaway trend includes: When the battery cell is in a state of pressure leakage, a battery cell pressure leakage alarm is triggered; When the battery cell is in a state of thermal runaway, a battery cell thermal runaway alarm is triggered.

7. A thermal runaway early warning system, characterized in that, include: Sensors are used to collect voltage signals from the battery cell, temperature signals inside the battery cell, and air pressure signals. The data processing unit is used to perform multi-scale time-series slicing on the voltage signal, the temperature signal and the air pressure signal to obtain multi-scale time-series feature vectors, and to construct the thermal runaway trend feature vector of the battery cell based on the multi-scale time-series feature vectors. The thermal runaway trend of the battery cell is determined based on the similarity between the thermal runaway trend feature vector and the preset thermal runaway standard trend vector. An alarm unit is used to provide multi-level thermal runaway early warning for the battery cell based on the thermal runaway trend.

8. The thermal runaway early warning system according to claim 7, characterized in that, The sensors include a voltage sensor, a pressure sensor, and a temperature sensor located inside the battery cell.

9. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the thermal runaway early warning method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the thermal runaway early warning method according to any one of claims 1 to 7.

Images