A battery safety warning method and system for battery swelling behavior monitoring

Abstract

The application discloses a battery safety early warning method and system for battery swelling behavior monitoring, and relates to the technical field of battery monitoring data processing. The method comprises the following steps: analyzing the trend change difference between the temperature data of the battery pack, and screening characteristic temperature data; correcting the swelling pressure data according to the fluctuation similarity between the characteristic temperature data and the swelling pressure data; analyzing the lag correlation between the displacement data of the position around the battery cell and the swelling pressure value data, and the rising trend of the displacement data, and calculating the swelling probability; and combining the voltage data fluctuation of the battery cell and the swelling probability to perform safety early warning on the swelling behavior of the battery. The application improves the monitoring positioning accuracy of the battery swelling behavior, and further realizes timely and accurate early warning of the battery safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery monitoring data processing, in particular to a battery safety early warning method and system for battery swelling behavior monitoring. BACKGROUND

[0002] Battery swelling behavior refers to the problem of volume expansion of the battery or battery pack due to irreversible chemical or physical reactions inside the battery during use, storage or manufacturing. In recent years, battery swelling behavior monitoring technology has developed rapidly, and multi-sensor fusion monitoring technology is commonly used. Based on multi-dimensional sensor, the battery swelling force is monitored in real time, and the pressure, strain and temperature sensors are fused to obtain battery state information from different angles, which can realize all-around monitoring of each part of the battery.

[0003] The multi-sensor fusion monitoring technology has certain timeliness in battery swelling anomaly monitoring, but it is not accurate for capturing some early and small changes, and the monitoring accuracy needs to be further improved. Through more accurate data fusion analysis method, more accurate and timely early warning can be realized. SUMMARY

[0004] The purpose of the present application is to provide a battery safety early warning method and system for battery swelling behavior monitoring to solve the existing problems in the background art.

[0005] To achieve the above purpose, the present application provides the following technical scheme: a battery safety early warning method for battery swelling behavior monitoring, comprising the following steps:

[0006] S1, real-time acquisition of displacement data, swelling pressure data, temperature data and voltage data of each battery cell in the battery pack;

[0007] S2, analysis of the trend change difference between each group of temperature data and all other temperature data to obtain characteristic temperature data; according to the fluctuation similarity between the characteristic temperature data and the swelling pressure data, the swelling pressure data is corrected to obtain the swelling pressure correction value at each moment;

[0008] S3, analysis of the lag correlation between the displacement data of the position around each battery cell and the swelling pressure value data to obtain the data correlation coefficient of each battery cell; according to the rising trend of the displacement data of the position around each battery cell, the swelling significance value of each battery cell is calculated; the swelling probability of each battery cell is calculated by combining the data correlation coefficient and the swelling significance value of each battery cell;

[0009] S4, combining the voltage data fluctuation and the swelling probability of each battery cell, the safety early warning of the battery swelling behavior is carried out.

[0010] Further, the analysis of the trend change difference between each group of temperature data and all other temperature data screens out characteristic temperature data, including:

[0011] The DTW distance mean of each group of temperature data and all other temperature data is calculated to obtain the trend difference of each group of temperature data. The group of temperature data with the maximum trend difference is recorded as the characteristic temperature data.

[0012] Further, the expansion pressure data is corrected according to the fluctuation similarity between the characteristic temperature data and the expansion pressure data to obtain the expansion pressure correction value at each time, including:

[0013] For the i-th time, the coefficient of variation of the expansion pressure values of the preset number of time points before the i-th time is calculated, which is recorded as the pressure variation value of the i-th time;

[0014] The correlation coefficient between the sequence composed of the expansion pressure values of the preset number of time points before the i-th time and the sequence composed of the characteristic temperature values is calculated, which is recorded as the change similarity value of the i-th time;

[0015] The expansion pressure correction value is calculated according to the pressure variation value and the change similarity value of the i-th time.

[0016] Further, the specific formula for calculating the expansion pressure correction value includes:

[0017]

[0018] In the formula, is the expansion pressure correction value of the i-th time; is the expansion pressure value of the i-th time; is the change similarity value of the i-th time; is the pressure variation value of the i-th time.

[0019] Further, the method for obtaining the data correlation coefficient of each battery cell is:

[0020] The correlation coefficient between each adjacent displacement data of the battery cell and the expansion pressure correction value data is calculated using the correlation coefficient calculation method in the k-shape clustering algorithm. The mean of the correlation coefficients between all adjacent displacement data of the battery cell and the expansion pressure correction value data is recorded as the data correlation coefficient of the battery cell.

[0021] Further, the expansion significance value of each battery cell is calculated according to the rising trend of the displacement data around the position of each battery cell, including:

[0022] The difference sequence of each adjacent displacement data of the battery cell is obtained, which is recorded as each trend sequence of the battery cell. The rising significance degree of all trend sequences of the battery cell is analyzed to obtain the expansion significance value.

[0023] Further, the analysis of the rising degree of all trend sequences of the battery cell obtains an inflation significant value, including: taking the maximum value in the mean of all trend sequences of the battery cell as the inflation significant value of the battery cell.

[0024] Further, the calculation formula of the inflation probability of the battery cell is: ; in the formula, is the inflation probability value of the a th battery cell; is the data correlation coefficient of the a th battery cell; is the inflation significant value of the a th battery cell; is a linear normalization function.

[0025] Further, the battery safety warning module combines the voltage data fluctuation of each battery cell and the inflation probability to perform safety warning on the inflation behavior of the battery.

[0026] For each battery cell, if the inflation probability of the battery cell at the current time is greater than a first preset value, the battery is in a safe state; otherwise, the voltage standard deviation of the battery cell in a preset time period before the current time is calculated, and when the voltage standard deviation is less than a second preset value, the battery is in a safe state, and when the voltage standard deviation is greater than or equal to the second preset value, the battery has an inflation behavior, and a battery safety warning signal is sent.

[0027] On the other hand, the present application provides a battery safety warning system for battery inflation behavior monitoring, the battery safety warning system comprising:

[0028] A battery data monitoring module is configured to acquire displacement data, inflation pressure data, temperature data and voltage data of each battery cell in a battery pack in real time.

[0029] A battery data correction module is configured to analyze the trend change difference between each group of temperature data and all other temperature data, and to screen out characteristic temperature data; and to correct the inflation pressure data according to the fluctuation similarity between the characteristic temperature data and the inflation pressure data, to obtain inflation pressure correction values at each time.

[0030] A battery inflation analysis module is configured to analyze the lag correlation between the displacement data of the surrounding positions of each battery cell and the inflation pressure value data, to obtain data correlation coefficients of each battery cell; to calculate inflation significant values of each battery cell according to the rising trend of the displacement data of the surrounding positions of each battery cell; and to calculate the inflation probability of each battery cell in combination with the data correlation coefficient and the inflation significant value of the battery cell.

[0031] A battery safety warning module is configured to combine the voltage data fluctuation of each battery cell and the inflation probability to perform safety warning on the inflation behavior of the battery.

[0032] Compared with the prior art, the present application has the beneficial effects that:

[0033] The present application firstly analyzes the causes and effects of swelling in the battery pack, analyzes the synergistic changes of various monitoring data, corrects the swelling pressure data through the similarity of temperature data and swelling pressure data changes, eliminates the influence of external factors such as road conditions, environmental weather on the swelling pressure, and improves the data accuracy; further, in order to determine the position of the swelling behavior, the correlation degree of the displacement data and the swelling pressure value data of each battery cell position in the battery pack is analyzed, the swelling probability value of the battery cell is calculated, and the possibility of swelling of each battery cell is quantified. Finally, the voltage fluctuation of the swelling battery cell is analyzed, and the swelling behavior of the battery is safely warned combined with the voltage data fluctuation of each battery cell and the swelling probability, which improves the monitoring and positioning accuracy of the battery swelling behavior, and further realizes the timely and accurate warning of the battery safety. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 The flowchart of the battery safety warning method for battery swelling behavior monitoring of the present application;

[0035] Figure 2 The distribution diagram of the temperature sensor;

[0036] Figure 3 The block diagram of the battery safety warning system for battery swelling behavior monitoring of the present application. DETAILED DESCRIPTION

[0037] The technical scheme of the present application will be described in detail below with the help of the drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, and are not limitations of the technical scheme of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0038] The term "and / or", only describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent three cases of A alone, A and B together, and B alone.

[0039] Figure 1 The flowchart of the battery safety warning method for battery swelling behavior monitoring disclosed by the present embodiment is shown, and the steps are as follows:

[0040] S1, real-time acquisition of displacement data, swelling pressure data, temperature data and voltage data of each battery cell in the battery pack.

[0041] A specific implementation scenario of the embodiment is to monitor the swelling behavior of the power battery pack of a new energy vehicle. Based on multi-sensor monitoring, the embodiment analyzes the cooperative change of various monitoring data of the new energy vehicle in the use process, and further excludes the influence of external factors such as road conditions and environmental weather on battery safety monitoring.

[0042] First, based on the correlation between the occurrence of battery swelling behavior and the performance of the power battery pack, various battery monitoring data are collected by sensors, including: Figure 2 As shown in the figure, 1 is a battery pack, 2 is a cell, 3 is a temperature sensor, and 4 is a displacement sensor; the displacement sensor is placed between two cells, and the thickness change of the cell is measured non-contact, obtaining n sets of displacement data; the pressure sensor is attached to the inside of the module cover plate to monitor the pressure of the overall swelling on the shell, obtaining a set of swelling pressure data; as shown in the figure, Figure 2 The temperature sensor is deployed at the position shown in the figure to monitor the local temperature rise, obtaining m sets of temperature data; in the embodiment, m = 7; the voltage of the cell tab is collected to obtain the voltage data of each cell. The above-mentioned various battery monitoring data are collected in real time with an interval of 1s, and in the embodiment, 10min of data is used for data analysis, and the data length is 600. The implementer can set the data length according to the actual situation.

[0043] In order to facilitate subsequent data analysis, the missing values are filled by using the regression filling method, and the filled data is uniformly dimensioned by using the maximum and minimum normalization method, which also amplifies the data change characteristics. The specific implementation process of the regression filling method and the maximum and minimum normalization method is a known technology and will not be described here.

[0044] S2, analyze the trend change difference between each set of temperature data and all other temperature data, and screen to obtain characteristic temperature data; according to the fluctuation similarity between the characteristic temperature data and the swelling pressure data, the swelling pressure data is corrected to obtain the swelling pressure correction value at each moment.

[0045] In the process of analyzing the battery swelling behavior by multi-sensor fusion monitoring technology, the battery safety condition is usually identified by monitoring whether each data is within the normal range. However, the change of environment in the daily operation of the vehicle will have a certain influence on the monitoring data. For example, when driving the vehicle from a cold outdoor environment into an indoor environment, the influence on temperature monitoring and swelling pressure monitoring, the battery discharge current rises sharply when the vehicle is high-load driving such as overtaking and climbing, the phenomenon of rapid temperature rise of the cell, and sensor failure. These factors have great interference on the identification of battery swelling behavior, so it is necessary to comprehensively analyze the change trend of various data to identify the abnormal behavior of the battery.

[0046] Firstly, the most intuitive monitoring of the battery swelling behavior is the swelling pressure data, which is corrected by the temperature change in the embodiment.

[0047] The battery swelling behavior starts to occur in a certain cell position in a local area, and the temperature data near the position suddenly rises, while the temperature data at other positions remains relatively stable. Therefore, among the m groups of temperature data, the trend difference of each group of temperature data from all other temperature data is analyzed.

[0048] In the embodiment, the trend difference of each group of temperature data is obtained by calculating the DTW distance mean of each group of temperature data from all other temperature data. The group of temperature data with the maximum trend difference is recorded as the characteristic temperature data. The characteristic temperature data represents the group of data with the maximum difference from other temperature data, which excludes the interference of environmental temperature mutation on cell temperature monitoring.

[0049] Further, if the battery swelling behavior occurs, both the characteristic temperature data and the swelling pressure data will show an upward trend; if the battery does not swell, but the environmental temperature changes greatly, the characteristic temperature data will show an upward trend, while the swelling pressure data will not fluctuate greatly and remain stable.

[0050] For the ith moment, the coefficient of variation of the swelling pressure values of the previous x moments is calculated, which is recorded as the pressure variation value of the ith moment; in the embodiment, the preset number x = 20. The calculation process of the coefficient of variation is a known technology and will not be described in detail. The Pearson correlation coefficient between the sequence composed of the swelling pressure values of the previous x moments and the sequence composed of the characteristic temperature values is recorded as the change similarity value of the ith moment. According to the pressure variation value and the change similarity value of the ith moment, the swelling pressure value is corrected, and the swelling pressure correction value is calculated, and the specific formula is:

[0051]

[0052] In the formula, is the swelling pressure correction value of the ith moment; is the swelling pressure value of the ith moment; is the change similarity value of the ith moment; is the pressure variation value of the ith moment.

[0053] If the pressure variation value at the current time is less than 10%, it indicates that the inflation pressure in the past period of time is at a relatively stable level, and no correction is needed; if the pressure variation value at the current time is greater than 10%, the inflation pressure in the past period of time has obvious fluctuations, and the greater the absolute value of the change similarity value at this time, the more likely it is that the inflation pressure and temperature change trend are similar, and the more likely it is that the temperature and inflation pressure rise due to the inflation of a certain cell, and the smaller the correction of the inflation pressure value; on the contrary, the greater the absolute value of the change similarity value, the greater the difference between the inflation pressure and temperature change trend, and the more likely it is that the temperature change is caused by environmental factors, and the greater the correction of the inflation pressure value is needed, and the inflation pressure value at this time is reduced.

[0054] S3, analyze the lag correlation between the displacement data of the position around each cell and the inflation pressure value data to obtain the data correlation coefficient of each cell; according to the rising trend of the displacement data of the position around each cell, calculate the inflation significance value of each cell; combine the data correlation coefficient and the inflation significance value of the cell to calculate the inflation probability of the cell.

[0055] Through the above correction of the inflation pressure value, more accurate overall inflation pressure data is obtained, and the battery pack can be preliminarily determined to have an inflation behavior by using a common threshold analysis method, but it is difficult to determine the specific cell position where the inflation behavior occurs, which causes difficulties in maintenance work. Therefore, in order to further locate the cell position where the inflation behavior occurs, the embodiment calculates the inflation probability value of each cell by analyzing the cooperative change between the sequence composed of the displacement data at each cell uniformly distributed in the battery pack and the inflation pressure correction value. The sequence composed of the inflation pressure correction value at all times in chronological order is referred to as inflation pressure correction value data.

[0056] First, for each cell, the correlation between the displacement data of the position around the cell and the inflation pressure value data is analyzed. If the cell position has inflation, the surrounding displacement sensor will first perceive, and then transmit to the pressure sensor, which will have the same rising trend. Considering the lag phenomenon between the fluctuations of the two kinds of data, all displacement data of the adjacent position of the cell are obtained, which is referred to as the adjacent displacement data of the cell. In this embodiment, the correlation coefficient between the adjacent displacement data of the cell and the inflation pressure correction value data is calculated by the calculation method of the correlation coefficient in the k-shape clustering algorithm; the average of the correlation coefficient between all adjacent displacement data of the cell and the inflation pressure correction value data is referred to as the data correlation coefficient of the cell. The calculation of the correlation coefficient in the k-shape clustering algorithm is a known technology, and the specific calculation process is not described again.

[0057] Further, the more obvious the rising trend of the adjacent displacement data and the swelling pressure correction value data is, the greater the probability of swelling of the cell position is. A difference sequence of each adjacent displacement data of the cell is obtained, denoted as a trend sequence of the cell; the rising significance of all trend sequences of the cell is analyzed to obtain a swelling significance value.

[0058] In the embodiment, the maximum value of the mean of all trend sequences of the cell is taken as the swelling significance value of the cell. In combination with the data correlation coefficient and the swelling significance value of the cell, the swelling probability of the cell is calculated, and the calculation formula is:

[0059]

[0060] In the formula, is the swelling probability value of the a-th cell; is the data correlation coefficient of the a-th cell; is the swelling significance value of the a-th cell; is a linear normalization function.

[0061] For each cell, the greater the swelling probability is, the more obvious the synchronous rising trend of the adjacent displacement data and the swelling pressure correction value data is, at this time, the greater the swelling significance value is, the faster the rising trend rises, and then the greater the swelling probability value of the cell is, and the more likely the swelling behavior is.

[0062] S4, in combination with the voltage data fluctuation of each cell and the swelling probability, the swelling behavior of the battery is safely warned.

[0063] Since the swollen battery cell will appear voltage fluctuation and no longer maintain stable output voltage, finally, the cell swelling behavior needs to be judged in time in combination with the voltage data fluctuation of each cell to realize the safety warning of the battery. Since the voltage fluctuation in a small range will also occur occasionally during charging and normal working of the battery, therefore, in the embodiment, when the cell has a greater swelling probability, the voltage fluctuation is combined to warn the safety of the battery, and the specific steps are as follows:

[0064] For each cell, if the swelling probability of the cell at the current time is greater than a first preset value , the battery is in a safe state; otherwise, the voltage standard deviation of the cell in a preset period before the current time is calculated, when the voltage standard deviation is less than a second preset value , the battery is in a safe state, when the voltage standard deviation is greater than or equal to the second preset value , the battery has a swelling behavior, and a battery safety warning signal is sent. In the embodiment, the first preset value ; the second preset value , and the implementer can set it according to the actual situation.

[0065] So far, by analyzing the change characteristics of the dimensional data of the power battery pack in the operation process when the swelling behavior occurs, the precision of the battery swelling monitoring data is improved according to the linkage change between the data, and the prediction precision of the battery swelling behavior is improved, so that the timely and accurate battery safety early warning is realized.

[0066] Please refer to Figure 3 , Figure 3 is a battery safety early warning system framework for battery swelling behavior monitoring provided by an embodiment of the present application. In the embodiment, each unit included in the terminal is used to execute each step in the corresponding embodiment of the battery safety early warning method for battery swelling behavior monitoring. The battery safety early warning system comprises a battery data monitoring module, a battery data correction module, a battery swelling analysis module, and a battery safety early warning module.

[0067] The battery data monitoring module is used to acquire displacement data, swelling pressure data, temperature data, and voltage data of each battery cell in the battery pack in real time.

[0068] The battery data correction module is used to analyze the trend change difference between each group of temperature data and all other temperature data, and screen out characteristic temperature data; and correct the swelling pressure data according to the fluctuation similarity between the characteristic temperature data and the swelling pressure data, to obtain a swelling pressure correction value at each moment.

[0069] The battery swelling analysis module is used to analyze the lag correlation relationship between the displacement data of the position around each battery cell and the swelling pressure value data, to obtain a data correlation coefficient of each battery cell; calculate an expansion significance value of each battery cell according to the rising trend of the displacement data of the position around each battery cell; and combine the data correlation coefficient and the expansion significance value of the battery cell to calculate an expansion probability of the battery cell.

[0070] The battery safety early warning module is used to combine the voltage data fluctuation of each battery cell and the expansion probability to perform safety early warning on the swelling behavior of the battery.

[0071] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented 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.

[0072] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0073] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0074] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0075] The embodiments of the present application described above are merely intended to illustrate the present application, but not to limit the present application. The above-described embodiments are merely illustrative, but not limiting, and any person skilled in the art can make many modifications without departing from the spirit and scope of the present application, and these modifications are also within the scope of the present application.

Claims

1. A battery safety warning method for battery swelling behavior monitoring, characterized in that, The method comprises the following steps: S1, real-time acquisition of displacement data, swelling pressure data, temperature data and voltage data of each battery cell in the battery pack; S2, analysis of the trend change difference between each group of temperature data and all other temperature data, and screening of characteristic temperature data; according to the fluctuation similarity between the characteristic temperature data and the swelling pressure data, the swelling pressure data is corrected to obtain the swelling pressure correction value at each moment; S3, analysis of the lag correlation between the displacement data of the position around each battery cell and the swelling pressure value data, and obtaining of the data correlation coefficient of each battery cell; according to the rising trend of the displacement data of the position around each battery cell, the swelling significance value of each battery cell is calculated; the swelling probability of each battery cell is calculated by combining the data correlation coefficient and the swelling significance value of the battery cell; S4, combining the voltage data fluctuation of each battery cell and the swelling probability, the safety warning of the swelling behavior of the battery is carried out.

2. A battery safety warning method for battery swelling behavior monitoring as claimed in claim 1, wherein, The analysis of the trend change difference between each group of temperature data and all other temperature data, and the screening of characteristic temperature data, comprises: The DTW distance mean of each group of temperature data and all other temperature data is calculated to obtain the trend difference of each group of temperature data; the group of temperature data with the maximum trend difference is recorded as the characteristic temperature data.

3. The battery safety warning method for battery swelling behavior monitoring as claimed in claim 1 wherein, The swelling pressure data is corrected according to the fluctuation similarity between the characteristic temperature data and the swelling pressure data to obtain the swelling pressure correction value at each moment, which comprises: For the i-th moment, the variation coefficient of the swelling pressure value of the preset number of moments before the i-th moment is calculated, which is recorded as the pressure variation value of the i-th moment; The correlation coefficient between the sequence composed of the swelling pressure values of the preset number of moments before the i-th moment and the sequence composed of the characteristic temperature values is calculated, which is recorded as the change similarity value of the i-th moment; According to the pressure variation value and the change similarity value of the i-th moment, the swelling pressure value is corrected to calculate the swelling pressure correction value.

4. A battery safety warning method for battery swelling behavior monitoring as claimed in claim 3, wherein, The specific formula for calculating the swelling pressure correction value comprises: In the formula, is the expansion pressure correction value at the i-th moment; is the expansion pressure value at the i-th moment; is the change similarity value at the i-th moment; is the pressure variation value at the i-th moment.

5. The battery safety warning method for battery swelling behavior monitoring as claimed in claim 1 wherein, The method for obtaining the data correlation coefficient of each battery cell is: The correlation coefficient between each adjacent displacement data of the battery cell and the swelling pressure correction value data is calculated by using the correlation coefficient calculation method in the k-shape clustering algorithm; the mean of the correlation coefficients between all adjacent displacement data of the battery cell and the swelling pressure correction value data is recorded as the data correlation coefficient of the battery cell.

6. The battery safety warning method for battery swelling behavior monitoring as claimed in claim 1 wherein, According to the rising trend of the displacement data of the position around each battery cell, the swelling significance value of each battery cell is calculated, which comprises: The difference sequence of each adjacent displacement data of the battery cell is obtained, which is recorded as each trend sequence of the battery cell; the rising significance degree of all trend sequences of the battery cell is analyzed to obtain the swelling significance value.

7. A battery safety warning method for battery swelling behavior monitoring as claimed in claim 6, wherein, The rising significance degree of all trend sequences of the battery cell is analyzed to obtain the swelling significance value, which comprises: the maximum value in the mean of all trend sequences of the battery cell is taken as the swelling significance value of the battery cell.

8. The battery safety warning method for battery swelling behavior monitoring as claimed in claim 1 wherein, The calculation formula of the swelling probability of the battery cell is: ; wherein, is the swelling probability value of the a-th battery cell; is the data correlation coefficient of the a-th battery cell; is the swelling significant value of the a-th battery cell; is a linear normalization function.

9. The battery safety warning method for battery swelling behavior monitoring as claimed in claim 1 wherein, The safety warning of the swelling behavior of the battery is carried out by combining the voltage data fluctuation of each battery cell and the swelling probability, which comprises: For each battery cell, if the swelling probability of the battery cell at the current time is greater than a first preset value, the battery is in a safe state; otherwise, the voltage standard deviation of the battery cell within a preset period before the current time is calculated, and when the voltage standard deviation is less than a second preset value, the battery is in a safe state, and when the voltage standard deviation is greater than or equal to the second preset value, the battery has a swelling behavior, and a battery safety warning signal is sent.

10. A battery safety warning system for battery swelling behavior monitoring, implementing the method of any of claims 1-9, characterized in that, The battery safety warning system comprises: a battery data monitoring module for acquiring displacement data, swelling pressure data, temperature data and voltage data of each battery cell in the battery pack in real time; a battery data correction module for analyzing the trend change difference between each group of temperature data and all other temperature data to obtain characteristic temperature data; and correcting the swelling pressure data according to the fluctuation similarity between the characteristic temperature data and the swelling pressure data to obtain the swelling pressure correction value at each time; a battery swelling analysis module for analyzing the lag correlation between the displacement data of the positions around each battery cell and the swelling pressure value data to obtain the data correlation coefficient of each battery cell; calculating the swelling significance value of each battery cell according to the rising trend of the displacement data of the positions around each battery cell; and combining the data correlation coefficient and the swelling significance value of each battery cell to calculate the swelling probability of each battery cell; a battery safety warning module for combining the voltage data fluctuation of each battery cell and the swelling probability to perform safety warning on the swelling behavior of the battery.

Images