Battery safety early warning method and system for battery expansion behavior monitoring

Abstract

The invention discloses a battery safety early warning method and system for battery expansion behavior monitoring, and relates to the technical field of battery monitoring data processing, and the method comprises the steps: analyzing the trend change difference between the group temperature data in a battery pack, and carrying out the screening to obtain characteristic temperature data; correcting the expansion pressure data according to the fluctuation similarity between the characteristic temperature data and the expansion pressure data; analyzing a lag association relationship between the displacement data and the expansion pressure value data of the surrounding position of the battery cell and a rising trend condition of the displacement data, and calculating an expansion probability; and performing safety early warning on the expansion behavior of the battery in combination with the voltage data fluctuation condition and the expansion probability of the battery cell. According to the invention, the monitoring and positioning precision of the battery expansion behavior is improved, so that timely and accurate early warning of battery safety is realized.

Description

Technical Field

[0001] This invention relates to the field of battery monitoring data processing technology, specifically to a battery safety early warning method and system for monitoring battery expansion behavior. Background Technology

[0002] Battery swelling behavior refers to the expansion of a battery cell or pack during use, storage, or manufacturing due to irreversible chemical or physical reactions that generate gas. In recent years, battery swelling behavior monitoring technology has developed rapidly, often employing multi-sensor fusion monitoring techniques. Real-time monitoring of battery swelling force based on multi-dimensional sensors integrates pressure, strain, and temperature sensors to acquire battery status information from different angles, enabling comprehensive monitoring of all parts of the battery.

[0003] Multi-sensor fusion monitoring technology has a certain timeliness in monitoring abnormal battery expansion, but it is not accurate in capturing some early and minute changes. Further improvements are needed to enhance the accuracy of monitoring and achieve more precise and timely early warnings through more accurate data fusion analysis methods. Summary of the Invention

[0004] The purpose of this invention is to provide a battery safety early warning method and system for monitoring battery swelling behavior, so as to solve the existing problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a battery safety early warning method for monitoring battery swelling behavior, comprising the following steps: S1 acquires real-time displacement data, expansion pressure data, temperature data, and voltage data of each cell within the battery pack; S2, analyze the trend changes of each group of temperature data and all other temperature data, and select characteristic temperature data; based on the fluctuation similarity between the characteristic temperature data and the expansion pressure data, correct the expansion pressure data to obtain the corrected expansion pressure value at each time. S3. Analyze the lag correlation between the displacement data and expansion pressure data around each cell to obtain the data correlation coefficient of each cell; calculate the expansion significance value of each cell based on the upward trend of the displacement data around each cell; combine the data correlation coefficient and expansion significance value of the cells to calculate the expansion probability of the cells. S4, by combining the voltage fluctuation data and expansion probability of each cell, provides a safety warning for the battery's expansion behavior.

[0006] Furthermore, the analysis examines the differences in trend changes between each group of temperature data and all other temperature data, and filters out characteristic temperature data, including: Calculate the average DTW distance of each group of temperature data to all other temperature data to obtain the trend difference of each group of temperature data; the group of temperature data with the largest trend difference is recorded as the characteristic temperature data.

[0007] Furthermore, the step of correcting the expansion pressure data based on the fluctuation similarity between the characteristic temperature data and the expansion pressure data to obtain the corrected expansion pressure value at each time moment includes: For the i-th time, calculate the coefficient of variation of the expansion pressure value for a preset number of time points before the i-th time, and denot it as the pressure variation value at the i-th time. Calculate the correlation coefficient between the sequence of expansion pressure values ​​at a predetermined number of time points before the i-th time point and the sequence of characteristic temperature values, and denot it as the change similarity value at the i-th time point; Based on the pressure variation value and the similarity value of change at time i, the expansion pressure value is corrected, and the expansion pressure correction value is calculated.

[0008] Furthermore, the specific formula for calculating the expansion pressure correction value includes: In the formula, This is the expansion pressure correction value at time i; Let be the expansion pressure value at time i. The value representing the similarity of change at time i; Let be the pressure variation value at time i.

[0009] Furthermore, the method for obtaining the data correlation coefficient of each battery cell is as follows: The correlation coefficient is calculated using the correlation coefficient calculation method in the k-shape clustering algorithm. The correlation coefficient between each adjacent displacement data of the battery cell and the expansion pressure correction value data is calculated. The average correlation coefficient between all adjacent displacement data of the battery cell and the expansion pressure correction value data is denoted as the data correlation coefficient of the battery cell.

[0010] Furthermore, the calculation of the significant expansion value of each battery cell based on the upward trend of displacement data around each cell includes: Obtain the difference sequence of adjacent displacement data of the battery cell, and denote it as the trend sequence of the battery cell; analyze the degree of increase of all trend sequences of the battery cell to obtain the expansion significance value.

[0011] Furthermore, the analysis of the degree of increase in all trend sequences of the battery cell to obtain the expansion significance value includes: taking the maximum value among the mean values ​​of all trend sequences of the battery cell as the expansion significance value of the battery cell.

[0012] Furthermore, the formula for calculating the expansion probability of the battery cell is as follows: In the formula, Let be the expansion probability value of the a-th cell; Let be the correlation coefficient of the data for the a-th cell; The significant expansion value of the a-th cell; It is a linear normalization function.

[0013] Furthermore, the method of combining the voltage fluctuation data and expansion probability of each cell to provide a safety warning for the battery's expansion behavior includes: For each cell, if the probability of cell expansion at the current moment is greater than a first preset value, the battery is in a safe state; otherwise, the standard deviation of the cell's voltage in the preset period before the current moment is calculated. When the standard deviation of the voltage is less than a second preset value, the battery is in a safe state. When the standard deviation of the voltage is greater than or equal to the second preset value, the battery expands and a battery safety warning signal is issued.

[0014] On the other hand, the present invention provides a battery safety early warning system for monitoring battery swelling behavior, the battery safety early warning system comprising: The battery data monitoring module is used to acquire displacement data, expansion pressure data, temperature data, and voltage data of each cell in the battery pack in real time. The battery data correction module is used to analyze the trend changes of each group of temperature data and all other temperature data, and filter out the characteristic temperature data; based on the fluctuation similarity between the characteristic temperature data and the expansion pressure data, the expansion pressure data is corrected to obtain the expansion pressure correction value at each time. The battery expansion analysis module is used to analyze the hysteresis correlation between the displacement data and expansion pressure value data around each cell, and obtain the data correlation coefficient of each cell; based on the upward trend of the displacement data around each cell, the expansion significance value of each cell is calculated; and combining the data correlation coefficient and expansion significance value of the cells, the expansion probability of the cells is calculated. The battery safety warning module is used to provide safety warnings for battery expansion behavior by combining the voltage fluctuation data and expansion probability of each cell.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention first analyzes the causes and effects of expansion within the battery pack, examining the coordinated changes in various monitoring data. It corrects the expansion pressure data by analyzing the similarity between temperature and expansion pressure changes, eliminating the influence of external factors such as road conditions and weather on the expansion pressure, thus improving data accuracy. Furthermore, to determine the location of the expansion, it analyzes the correlation between the displacement data of each cell within the battery pack and the expansion pressure value, calculating the expansion probability of each cell and quantifying the likelihood of expansion for each cell. Finally, it analyzes the voltage fluctuations that occur in expanded battery cells. By combining the voltage fluctuation data and expansion probability of each cell, a safety warning is issued for battery expansion, improving the monitoring and location accuracy of battery expansion and achieving timely and accurate early warning for battery safety. Attached Figure Description

[0016] Figure 1 This is a schematic flowchart of a battery safety early warning method for monitoring battery swelling behavior according to the present invention. Figure 2 This is a schematic diagram showing the distribution of temperature sensors; Figure 3 This is a block diagram of a battery safety early warning system for monitoring battery swelling behavior according to the present invention. Detailed Implementation

[0017] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0018] The term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone.

[0019] Figure 1 A schematic flowchart of a battery safety early warning method for monitoring battery swelling behavior disclosed in this embodiment is shown, and the steps are as follows: S1 acquires real-time displacement data, expansion pressure data, temperature data, and voltage data of each cell within the battery pack.

[0020] One specific implementation scenario of this embodiment is the monitoring of the expansion behavior of a power battery pack in a new energy vehicle. Based on multi-sensor monitoring, this embodiment analyzes the coordinated changes in various monitoring data during the use of the new energy vehicle, further eliminating the influence of external factors such as road conditions and ambient weather on battery safety monitoring.

[0021] First, based on the correlation between battery swelling behavior and various performance characteristics of the power battery pack, various battery monitoring data are collected through sensors, including: Figure 2 As shown, 1 represents the battery pack, 2 represents the battery cell, 3 represents the temperature sensor, and 4 represents the displacement sensor. The displacement sensor is placed between pairs of battery cells to non-contactly measure changes in cell thickness, obtaining n sets of displacement data. A pressure sensor is attached to the inside of the module cover to monitor the pressure exerted on the casing by overall expansion, obtaining a set of expansion pressure data. Figure 2 Temperature sensors are deployed at the locations shown to monitor local temperature rise and obtain m sets of temperature data; in this embodiment, m=7. Voltage data for each cell is obtained by collecting voltage data through the cell tabs. All the above battery monitoring data are collected in real time at 1-second intervals. In this embodiment, data analysis is performed using 10-minute data sets with a data length of 600. Implementers can set the data length according to their actual needs.

[0022] To facilitate subsequent data analysis, regression imputation was used to fill in missing values, and the min-max normalization method was used to standardize the dimensions of the imputed data, while also amplifying the data variation characteristics. The specific implementation processes of the regression imputation method and the min-max normalization method are well-known techniques and will not be described in detail here.

[0023] S2, analyze the trend changes of each group of temperature data and all other temperature data, and select characteristic temperature data; based on the fluctuation similarity between the characteristic temperature data and the expansion pressure data, correct the expansion pressure data to obtain the corrected expansion pressure value at each time.

[0024] In the analysis of battery expansion behavior using multi-sensor fusion monitoring technology, the battery's safety status is typically identified by monitoring whether various data points are within normal ranges. However, environmental changes during daily vehicle operation can significantly impact the monitoring data. For example, driving a vehicle from a cold outdoor environment into an indoor environment can affect temperature and expansion pressure monitoring; high-load driving such as high-speed overtaking and hill climbing can cause a sudden increase in battery discharge current and a rapid rise in cell temperature; and sensor malfunctions can also contribute to the problem. These factors significantly interfere with the identification of battery expansion behavior; therefore, it is necessary to comprehensively consider the trends in various data points to identify abnormal battery behavior.

[0025] First, the most intuitive way to monitor battery expansion behavior is through expansion pressure data. In this embodiment, the expansion pressure data is corrected based on temperature changes.

[0026] The battery swelling behavior begins at a specific cell location within a localized area, where the temperature suddenly rises, while the temperature at other locations remains relatively stable. Therefore, for the m sets of temperature data, we analyze the trend differences between each set and all other temperature data.

[0027] In this embodiment, the trend difference of each group of temperature data is obtained by calculating the average DTW distance of each group of temperature data from all other temperature data. The group of temperature data with the largest trend difference is recorded as the characteristic temperature data. The characteristic temperature data represents the group of data with the largest difference from other temperature data, thus eliminating the interference of sudden changes in ambient temperature on cell temperature monitoring.

[0028] Furthermore, if the battery expands, both the characteristic temperature data and the expansion pressure data will show an upward trend; if the battery does not expand but the ambient temperature changes significantly, the characteristic temperature data will show an upward trend, while the expansion pressure data will not fluctuate significantly and will remain at a stable value.

[0029] For the i-th time moment, calculate the coefficient of variation of the expansion pressure values ​​over the x time moments preceding the i-th time moment, denoted as the pressure variation value at the i-th time moment; in this embodiment, the preset number x=20. The calculation process of the coefficient of variation is a well-known technique and will not be elaborated further. Calculate the Pearson correlation coefficient between the sequence of expansion pressure values ​​over the x time moments preceding the i-th time moment and the sequence of characteristic temperature values, denoted as the change similarity value at the i-th time moment. Based on the pressure variation value and the similarity value at time i, the expansion pressure value is corrected. The specific formula for calculating the corrected expansion pressure value is as follows: In the formula, This is the expansion pressure correction value at time i; Let be the expansion pressure value at time i. The value representing the similarity of change at time i; Let be the pressure variation value at time i.

[0030] If the pressure variation value at the current moment is less than 10%, it indicates that the expansion pressure has been at a relatively stable level over the past period, and no correction is needed. If the pressure variation value at the current moment is greater than 10%, it indicates that the expansion pressure has fluctuated significantly over the past period. The larger the absolute value of the similarity value, the more similar the trend of expansion pressure and temperature changes, and the more likely the increase in temperature and expansion pressure is caused by the expansion of a certain cell. The smaller the correction for the expansion pressure value, the smaller the correction. Conversely, the larger the absolute value of the similarity value, the greater the difference between the trend of expansion pressure and temperature changes. It is more likely that the temperature change is caused by environmental factors, and a larger correction for the expansion pressure value is needed to reduce the expansion pressure value at this moment.

[0031] S3. Analyze the hysteresis relationship between the displacement data and expansion pressure value data around each cell to obtain the data correlation coefficient of each cell; calculate the expansion significance value of each cell based on the upward trend of the displacement data around each cell; combine the data correlation coefficient and expansion significance value of the cells to calculate the expansion probability of the cells.

[0032] By correcting the expansion pressure values ​​as described above, relatively accurate overall expansion pressure data is obtained. While the commonly used threshold analysis method can preliminarily determine whether the battery pack has experienced expansion, it is difficult to pinpoint the specific cell location where expansion has occurred, posing challenges to maintenance. Therefore, to further locate the cells experiencing expansion, this embodiment analyzes the coordinated changes between the displacement data of each uniformly distributed cell in the battery pack and the sequence of expansion pressure correction values ​​to calculate the expansion probability value of each cell. The sequence of expansion pressure correction values ​​at all times, arranged in chronological order, is recorded as the expansion pressure correction value data.

[0033] First, for each battery cell, the correlation between displacement data and expansion pressure value data around the cell is analyzed. If expansion occurs at a certain location of the cell, the displacement sensors around it will detect it first, followed by the pressure sensor, showing the same upward trend. Considering the lag between the two types of data, all displacement data of adjacent locations of the cell are obtained and recorded as the adjacent displacement data of the cell. In this embodiment, the correlation coefficient between each adjacent displacement data of the cell and the expansion pressure correction value data is calculated using the correlation coefficient calculation method in the k-shape clustering algorithm. The average of the correlation coefficients between all adjacent displacement data and the expansion pressure correction value data of the cell is recorded as the data correlation coefficient of the cell. The calculation of the correlation coefficient in the k-shape clustering algorithm is a well-known technique, and the specific calculation process will not be described in detail.

[0034] Furthermore, the more pronounced the upward trend of adjacent displacement data and expansion pressure correction values, the greater the probability of cell expansion. The difference sequences of adjacent displacement data for each cell are obtained and denoted as the cell's trend sequences; the degree of significance of the increase in all trend sequences of the cell is analyzed to obtain the expansion significance value.

[0035] In this embodiment, the maximum value of the mean of all trend sequences of the battery cell is taken as the significant value of the battery cell's expansion. Combining the data correlation coefficient and the significant value of expansion, the probability of battery cell expansion is calculated using the following formula: In the formula, Let be the expansion probability value of the a-th cell; Let be the correlation coefficient of the data for the a-th cell; The significant expansion value of the a-th cell; It is a linear normalization function.

[0036] For each cell, the higher the expansion probability, the more obvious the synchronous upward trend of adjacent displacement data and expansion pressure correction value data. At this time, the larger the expansion significance value, the faster the upward trend rises, and the higher the expansion probability value of the cell, the more likely expansion behavior is to occur.

[0037] S4, by combining the voltage fluctuation data and expansion probability of each cell, provides a safety warning for the battery's expansion behavior.

[0038] Because swollen battery cells experience voltage fluctuations and no longer maintain a stable output voltage, it is still necessary to combine the voltage fluctuation data of each cell to promptly determine the cell's swelling behavior and provide a safety warning for the battery. Since small-scale voltage fluctuations occasionally occur during charging and normal battery operation, this embodiment, when determining that a cell has a high probability of swelling, combines voltage fluctuations to issue a warning for battery safety. The specific steps are as follows: For each battery cell, if the probability of expansion of the cell at the current moment is greater than a first preset value... If the voltage standard deviation is less than a second preset value, the battery is in a safe state. Otherwise, the standard deviation of the battery cell's voltage over a preset period of time prior to the current moment is calculated. When the battery is in a safe state, and the voltage standard deviation is greater than or equal to the second preset value. When the battery expands, a battery safety warning signal is issued. The first preset value in this embodiment... Second preset value Implementers can set it according to the actual situation.

[0039] Thus, this embodiment analyzes the changes in various dimensions of data when the power battery pack expands during operation, and improves the accuracy of battery expansion monitoring data based on the linkage changes between data, thereby improving the prediction accuracy of battery expansion behavior and achieving timely and accurate battery safety warnings.

[0040] Please see Figure 3 , Figure 3 This is a framework diagram of a battery safety early warning system for monitoring battery swelling behavior provided by an embodiment of the present invention. In this embodiment, the terminal includes various units that execute steps in a corresponding embodiment of a battery safety early warning method for monitoring battery swelling behavior. The battery safety early warning system includes: a battery data monitoring module, a battery data correction module, a battery swelling analysis module, and a battery safety early warning module.

[0041] The battery data monitoring module is used to acquire displacement data, expansion pressure data, temperature data, and voltage data of each cell in the battery pack in real time. The battery data correction module is used to analyze the trend changes of each group of temperature data and all other temperature data, and filter out the characteristic temperature data; based on the fluctuation similarity between the characteristic temperature data and the expansion pressure data, the expansion pressure data is corrected to obtain the expansion pressure correction value at each time. The battery expansion analysis module is used to analyze the hysteresis correlation between the displacement data and expansion pressure value data around each cell, and obtain the data correlation coefficient of each cell; based on the upward trend of the displacement data around each cell, the expansion significance value of each cell is calculated; and combining the data correlation coefficient and expansion significance value of the cells, the expansion probability of the cells is calculated. The battery safety warning module is used to provide safety warnings for battery expansion behavior by combining the voltage fluctuation data and expansion probability of each cell.

[0042] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0043] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0044] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0045] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0046] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A battery safety early warning method for monitoring battery swelling behavior, characterized in that, The method includes the following steps: S1 acquires real-time displacement data, expansion pressure data, temperature data, and voltage data of each cell within the battery pack; S2, analyze the trend changes of each group of temperature data and all other temperature data, and select characteristic temperature data; based on the fluctuation similarity between the characteristic temperature data and the expansion pressure data, correct the expansion pressure data to obtain the corrected expansion pressure value at each time. S3. Analyze the lag correlation between the displacement data and expansion pressure data around each cell to obtain the data correlation coefficient of each cell; calculate the expansion significance value of each cell based on the upward trend of the displacement data around each cell; combine the data correlation coefficient and expansion significance value of the cells to calculate the expansion probability of the cells. S4, by combining the voltage fluctuation data and expansion probability of each cell, provides a safety warning for the battery's expansion behavior.

2. The battery safety early warning method for monitoring battery swelling behavior according to claim 1, characterized in that, The analysis examines the differences in trend changes between each group of temperature data and all other temperature data, and filters out characteristic temperature data, including: Calculate the average DTW distance of each group of temperature data to all other temperature data to obtain the trend difference of each group of temperature data; the group of temperature data with the largest trend difference is recorded as the characteristic temperature data.

3. The battery safety early warning method for monitoring battery swelling behavior according to claim 1, characterized in that, The step of correcting the expansion pressure data based on the fluctuation similarity between characteristic temperature data and expansion pressure data to obtain the corrected expansion pressure value at each time moment includes: For the i-th time, calculate the coefficient of variation of the expansion pressure value for a preset number of time points before the i-th time, and denot it as the pressure variation value at the i-th time. Calculate the correlation coefficient between the sequence of expansion pressure values ​​at a predetermined number of time points before time i and the sequence of characteristic temperature values, and denot it as the change similarity value at time i. Based on the pressure variation value and the similarity value of change at time i, the expansion pressure value is corrected, and the expansion pressure correction value is calculated.

4. A battery safety early warning method for monitoring battery swelling behavior according to claim 3, characterized in that, The specific formula for calculating the expansion pressure correction value includes: In the formula, This is the expansion pressure correction value at time i; Let be the expansion pressure value at time i. The value representing the similarity of change at time i; Let be the pressure variation value at time i.

5. A battery safety early warning method for monitoring battery swelling behavior according to claim 1, characterized in that, The method for obtaining the data correlation coefficient of each battery cell is as follows: The correlation coefficient is calculated using the correlation coefficient calculation method in the k-shape clustering algorithm. The correlation coefficient between each adjacent displacement data of the battery cell and the expansion pressure correction value data is calculated. The average correlation coefficient between all adjacent displacement data of the battery cell and the expansion pressure correction value data is denoted as the data correlation coefficient of the battery cell.

6. A battery safety early warning method for monitoring battery swelling behavior according to claim 1, characterized in that, The step of calculating the significant expansion value of each battery cell based on the upward trend of displacement data around each cell includes: Obtain the difference sequence of adjacent displacement data of the battery cell, and denote it as the trend sequence of the battery cell; analyze the degree of increase of all trend sequences of the battery cell to obtain the expansion significance value.

7. A battery safety early warning method for monitoring battery swelling behavior according to claim 6, characterized in that, The analysis of the magnitude of the rise of all trend sequences of the battery cell to obtain the expansion significance value includes: taking the maximum value among the mean values ​​of all trend sequences of the battery cell as the expansion significance value of the battery cell.

8. A battery safety early warning method for monitoring battery swelling behavior according to claim 1, characterized in that, The formula for calculating the expansion probability of the battery cell is: In the formula, Let be the expansion probability value of the a-th cell; Let be the correlation coefficient of the data for the a-th cell; The significant expansion value of the a-th cell; It is a linear normalization function.

9. A battery safety early warning method for monitoring battery swelling behavior according to claim 1, characterized in that, The method combines voltage fluctuation data and expansion probability of each cell to provide a safety warning for battery expansion behavior, including: For each cell, if the probability of cell expansion at the current moment is greater than a first preset value, the battery is in a safe state; otherwise, the standard deviation of the cell's voltage in the preset period before the current moment is calculated. When the standard deviation of the voltage is less than a second preset value, the battery is in a safe state. When the standard deviation of the voltage is greater than or equal to the second preset value, the battery expands and a battery safety warning signal is issued.

10. A battery safety early warning system for monitoring battery swelling behavior, implementing the method as described in any one of claims 1-9, characterized in that, The battery safety early warning system includes: The battery data monitoring module is used to acquire displacement data, expansion pressure data, temperature data, and voltage data of each cell in the battery pack in real time. The battery data correction module is used to analyze the trend changes of each group of temperature data and all other temperature data, and filter out the characteristic temperature data; based on the fluctuation similarity between the characteristic temperature data and the expansion pressure data, the expansion pressure data is corrected to obtain the expansion pressure correction value at each time. The battery expansion analysis module is used to analyze the hysteresis correlation between the displacement data and expansion pressure value data around each cell, and obtain the data correlation coefficient of each cell; based on the upward trend of the displacement data around each cell, the expansion significance value of each cell is calculated; and combining the data correlation coefficient and expansion significance value of the cells, the expansion probability of the cells is calculated. The battery safety warning module is used to provide safety warnings for battery expansion behavior by combining the voltage fluctuation data and expansion probability of each cell.

Images