Battery cell detection method, detection system and storage medium

Abstract

The invention relates to a battery cell detection method, a battery cell detection system and a storage medium, and belongs to the field of battery cell moisture detection. The method comprises the following steps: acquiring corresponding electrochemical impedance values of a battery cell under a plurality of frequencies; inputting the plurality of corresponding electrochemical impedance values into a trained moisture prediction model to obtain predicted moisture of the battery cell; and judging whether the predicted moisture of the battery cell meets a preset battery cell moisture evaluation standard or not, and judging that the battery cell meets a drying requirement when the predicted moisture of the battery cell meets the battery cell moisture evaluation standard. The problems that in the prior art, when the moisture of the battery cell is detected, the internal structure of the battery cell needs to be damaged, so that the battery cell cannot be continuously used, and the detection precision is not high are solved.

Description

Technical Field

[0001] The present invention relates to the field of battery cell moisture detection, and in particular to a battery cell detection method, a detection system and a storage medium. Background Art

[0002] The production of battery cells requires processes such as homogenization, winding, shelling, baking, injection, formation and sealing. Among them, baking is performed after the battery cells are assembled and before the electrolyte is injected. The battery cells are baked to remove the residual moisture in the battery cells to the maximum extent. In the subsequent production process, the battery cells are prevented from deteriorating in quality, exploding and other undesirable phenomena due to excessive moisture content in the battery cells, and even causing the entire product to be scrapped. Therefore, before the battery cells are initially injected with electrolyte, they need to be baked and dehydrated by vacuum baking.

[0003] After baking, in order to detect whether the baked battery cell meets the requirements, it is necessary to test the moisture content of the baked dry battery cell. The commonly used method is the Karl Fischer moisture determination method. By sampling, the center electrode of the sampled battery cell is cut and the moisture content is determined using the Karl Fischer solution. However, this method of detection takes a long time and requires the battery cell to be destroyed, resulting in the inability to continue to use the destroyed battery cell, which increases the solid consumption of the battery cell. In addition, since the measured value is easily interfered by moisture in the air, or the Karl Fischer solution fails, and the sampled battery cell cannot accurately reflect the situation of all the battery cells, the final test result presents a large error. Therefore, it is necessary to provide a battery cell detection method to solve the above problems. Summary of the invention

[0004] The present invention provides a battery cell detection method, detection system and storage medium to solve the problem that when detecting the moisture content of the battery cell in the prior art, the internal structure of the battery cell needs to be destroyed, so that the battery cell cannot be used any more and the detection accuracy is low.

[0005] The present invention provides a method for detecting a battery cell, comprising:

[0006] Obtaining electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies;

[0007] Inputting a plurality of corresponding electrochemical impedance values ​​into a trained moisture prediction model to obtain predicted moisture of the battery cell; and

[0008] It is determined whether the predicted moisture content of the battery cell meets a preset battery cell moisture evaluation standard, and when the predicted moisture content of the battery cell meets the battery cell moisture evaluation standard, it is determined that the battery cell meets the drying requirement.

[0009] In one embodiment of the present invention, obtaining the electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies includes:

[0010] Based on a preset frequency sweep interval, performing a frequency sweep test on the battery cell at a preset frequency interval; and

[0011] Based on the sweep frequency test results, the electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies are obtained, wherein during the sweep frequency test, the amplitude of the sweep frequency signal at multiple frequencies remains consistent.

[0012] In one embodiment of the present invention, after obtaining the electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies, the method further includes: screening the electrochemical impedance values ​​corresponding to the multiple frequencies for abnormal data, wherein the abnormal data screening includes:

[0013] Based on the identification of the battery cell, searching for a standard impedance interval corresponding to each frequency, wherein the standard impedance interval is associated with the identification of the battery cell;

[0014] Determining whether each electrochemical impedance value of the battery cell is within a corresponding standard impedance range;

[0015] If the electrochemical impedance values ​​of the battery cell are all within the corresponding standard impedance range, the battery cell is marked as a normal battery cell;

[0016] If at least one electrochemical impedance value of the battery cell is not within the corresponding standard impedance range, the battery cell is marked as an abnormal battery cell.

[0017] In an embodiment of the present invention, after marking the battery cell as an abnormal battery cell, the method further includes: stopping detecting the abnormal battery cell and sending a warning message.

[0018] In one embodiment of the present invention, after stopping detecting the abnormal battery cell, the method further includes:

[0019] Based on a preset abnormality type determination condition, determining the abnormality type to which the abnormal battery cell belongs; and

[0020] Based on the exception type, a warning message corresponding to the exception type is sent.

[0021] In one embodiment of the present invention, before inputting the plurality of corresponding electrochemical impedance values ​​into the trained moisture prediction model, the method further includes: performing impedance temperature compensation on the electrochemical impedance values ​​corresponding to the battery cells at each frequency based on the temperature of the battery cells.

[0022] In one embodiment of the present invention, the impedance temperature compensation is performed on the electrochemical impedance value corresponding to each frequency of the battery cell based on the temperature of the battery cell, including:

[0023] Acquire the current temperature of the battery cell and the standard temperature corresponding to the moisture prediction model, wherein the standard temperature is a preset temperature when training the moisture prediction model;

[0024] According to the identification of the battery cell, searching for the impedance change rate corresponding to the current temperature to the standard temperature; and

[0025] Based on the impedance change rate, the electrochemical impedance value corresponding to each frequency is compensated to obtain the electrochemical impedance value corresponding to each frequency after compensation.

[0026] In one embodiment of the present invention, the moisture prediction model is a linear regression model.

[0027] In one embodiment of the present invention, the predicted moisture content of the battery cell includes a first predicted moisture content and a second predicted moisture content, and the step of determining whether the predicted moisture content of the battery cell meets a preset battery cell moisture evaluation standard includes:

[0028] Determine whether the first predicted moisture content is less than or equal to a preset first moisture content threshold, and whether the second predicted moisture content is less than or equal to a preset second moisture content threshold;

[0029] If the first predicted moisture content is less than or equal to the first moisture threshold, and the second predicted moisture content is less than or equal to the second moisture threshold, the predicted moisture content of the battery cell meets the battery cell moisture evaluation standard;

[0030] If the first predicted moisture content is greater than the first moisture threshold, and / or the second predicted moisture content is greater than the second moisture threshold, the predicted moisture content of the battery cell does not meet the battery cell moisture evaluation standard.

[0031] In another aspect of the present invention, a battery cell detection system is provided, the system comprising:

[0032] An impedance acquisition module, used to obtain electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies;

[0033] a moisture prediction module, used for inputting a plurality of corresponding electrochemical impedance values ​​into a trained moisture prediction model to obtain the predicted moisture of the battery cell; and

[0034] The drying requirement judgment module is used to judge whether the predicted moisture content of the battery cell meets the preset battery cell moisture evaluation standard, and when the predicted moisture content of the battery cell meets the battery cell moisture evaluation standard, determine that the battery cell meets the drying requirement.

[0035] In another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0036] The present invention obtains the electrochemical impedance values ​​of the battery cell at multiple different frequencies, and inputs the obtained electrochemical impedance values ​​into a moisture prediction model, and the output of the moisture prediction model is the predicted moisture of the battery cell. It is judged whether the predicted moisture of the battery cell meets the battery cell moisture evaluation standard, and when it meets the battery cell moisture evaluation standard, it is determined that the battery cell meets the drying requirements. The present invention replaces the traditional Karl Fischer moisture determination method with a moisture prediction model, and can detect the moisture of the battery cell without damaging the battery cell, thereby reducing the solid consumption of the battery cell. For the baked battery cell, the residual moisture value of the battery cell can be detected non-destructively, efficiently and accurately, effectively improving the efficiency and accuracy of the battery cell moisture detection, and has strong universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Shown is a schematic flow chart of a method for detecting a battery cell in one embodiment of the present invention;

[0038] Figure 2 Shown is a schematic diagram of a process for obtaining an electrochemical impedance value in one embodiment of the present invention;

[0039] Figure 3 Shown is a schematic diagram of a process for screening abnormal data in one embodiment of the present invention;

[0040] Figure 4 Shown is a schematic diagram of a process for determining early warning information in one embodiment of the present invention;

[0041] Figure 5 Shown is a schematic diagram of a temperature compensation process in one embodiment of the present invention;

[0042] Figure 6 Shown is a schematic diagram of a process for evaluating the moisture content of a battery cell according to an embodiment of the present invention;

[0043] Figure 7 Shown is an electrochemical impedance spectrum of an embodiment of the present invention;

[0044] Figure 8 Shown is a schematic diagram of the types of abnormal data in one embodiment of the present invention;

[0045] Fig. 9 Shown is a schematic diagram of input and output data of a moisture prediction model in one embodiment of the present invention.

[0046] Fig.10 Shown is a high temperature curve diagram of a battery cell after baking in one embodiment of the present invention;

[0047] Fig.11 Shown are the predicted moisture values ​​of different battery cells in one embodiment of the present invention;

[0048] Fig.12 Shown is a structural block diagram of a battery cell detection system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0050] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0051] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0052] The present invention provides a method for detecting a battery cell, by obtaining electrochemical impedance values ​​of the battery cell at multiple different frequencies, and inputting each obtained electrochemical impedance value into a moisture prediction model, the output of the moisture prediction model is the predicted moisture of the battery cell. It is judged whether the predicted moisture of the battery cell meets the battery cell moisture evaluation standard, and when it meets the battery cell moisture evaluation standard, it is determined that the battery cell meets the drying requirement. The present invention replaces the traditional Karl Fischer moisture determination method with a moisture prediction model, does not need to destroy the battery cell, and avoids the situation where the detection value is less than the true value due to the failure of the Karl Fischer solution, and the measured value is easily interfered by moisture in the air, resulting in a large error between the final measured moisture result and the actual value. And the present invention can efficiently and accurately predict the residual moisture value of the battery cell according to each electrochemical impedance value of the battery cell after baking through the moisture prediction model, realize non-destructive detection of the battery cell, and greatly reduce the solid consumption of the battery cell. By combining the electrochemical impedance value with the moisture prediction model, the online detection of the residual water content in the battery cell is realized, and a full inspection scheme for the dry battery cell after baking can be realized, which has strong universality.

[0053] See also Figure 1 , Figure 7 , Figure 1 It is a schematic diagram showing a flow chart of a method for detecting a battery cell according to an embodiment of the present invention. Figure 7The electrochemical impedance spectrum of an embodiment of the present invention is shown. The detection method comprises the following steps:

[0054] S1. Obtain the electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies.

[0055] Perform a frequency sweep test on the baked battery cell, for example, apply a small sinusoidal potential signal to the battery cell, and obtain an electrochemical impedance spectrum (EIS) by changing the frequency of the sinusoidal wave, wherein the electrochemical impedance spectrum is composed of the electrochemical impedance values ​​(EIS impedance values) corresponding to the battery cell at a series of different frequencies. The electrochemical impedance value includes information such as the real impedance Zre, the imaginary impedance Zim, the impedance modulus |Z|, and the impedance phase angle Phrase.

[0056] Specifically, see Figure 2 , Figure 2 The figure shows a flow chart of obtaining electrochemical impedance values ​​in one embodiment of the present invention. In one embodiment of the present invention, in step S1, obtaining electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies includes:

[0057] S101, based on a preset frequency sweep interval, performing a frequency sweep test on the battery cell at a preset frequency interval; and

[0058] S102. Based on the sweep frequency test result, obtain the electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies, wherein during the sweep frequency test, the amplitude of the sweep frequency signal at multiple frequencies remains consistent.

[0059] In the frequency sweep interval, an AC sinusoidal potential wave with a stable amplitude is applied to the battery cell, and the frequency of the AC potential is continuously changed through a preset frequency interval, and the ratio of the AC potential to the current flowing through the battery cell is measured, which is the electrochemical impedance value corresponding to the battery cell at the current frequency. Among them, the change in the frequency of the AC potential can be a decrease from high frequency to low frequency, or an increase from low frequency to high frequency, which is not limited here. In order to measure the electrochemical impedance values ​​of multiple battery cells at the same time, a single multi-channel measurement method can be used to measure multiple battery cells at the same time. And compared with the Karl Fischer moisture measurement method, the technical solution of the embodiment of the present invention is time-consuming, and the single measurement time is 10 seconds, so that the electrochemical impedance values ​​of several battery cells can be quickly measured. It can be understood that the range of the frequency sweep interval and the amplitude value of the frequency sweep signal can be set based on the performance of the battery cell, the accuracy requirements of the test results, etc., and for example, in one embodiment of the present invention, the frequency sweep interval is [1000HZ, 1HZ], and the amplitude of the frequency sweep signal is 1000mv.

[0060] In one embodiment of the present invention, after obtaining the electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies, the method further includes: S11, screening abnormal data of the electrochemical impedance values ​​corresponding to the multiple frequencies. Figure 3 and Figure 8 , Figure 3 It is a schematic diagram of a process of abnormal data screening in one embodiment of the present invention. Figure 8 The diagram shows the types of abnormal data in one embodiment of the present invention. The abnormal data screening includes:

[0061] S111. Based on the identification of the battery cell, searching for a standard impedance range corresponding to each frequency; wherein the standard impedance range is associated with the identification of the battery cell;

[0062] S112, determining whether each electrochemical impedance value of the battery cell is within the corresponding standard impedance range;

[0063] S113. If the electrochemical impedance values ​​of the battery cell are all within the corresponding standard impedance range, the battery cell is marked as a normal battery cell;

[0064] S114: If at least one electrochemical impedance value of the battery cell is not within the corresponding standard impedance range, the battery cell is marked as an abnormal battery cell.

[0065] Considering that the battery cell may be abnormal due to various reasons during the various manufacturing processes at the front end, such as misalignment of the tab, poor tab welding, tab folding, poor ultrasonic welding, poor welding of the adapter, or poor welding of the top cover, which may cause the battery cell to short-circuit or micro-short-circuit. In order to improve the detection efficiency of the battery cell, these abnormal batteries can be excluded, and there is no need to predict the water content of the abnormal batteries. Therefore, based on the identification of the battery cell, the information table corresponding to the battery cell can be obtained, and the standard impedance interval corresponding to each frequency within the range of the frequency sweep interval is pre-stored in the information table. Among them, the identification of the battery cell can be all information that can characterize the characteristics of the battery cell, including but not limited to the brand of the battery cell, the model of the battery cell, the specification parameters of the battery cell, etc. Traverse multiple frequencies in the frequency sweep interval to determine whether the electrochemical impedance value measured by the battery cell at each frequency is within the standard impedance interval of the corresponding frequency. If all the electrochemical impedance values ​​of the battery cell in the frequency sweep interval are within the corresponding standard impedance interval, it means that the battery cell performance is normal, and the battery cell can be marked as a normal battery cell. If within the frequency sweep interval, the battery cell has one or more electrochemical impedance values ​​that are not within the corresponding standard impedance interval, it means that the battery cell performance is abnormal, and the battery cell can be marked as an abnormal battery cell. It should be noted that for the same battery cell, at different frequencies, the corresponding standard impedance interval can remain the same, or different standard impedance intervals can be set. Those skilled in the art can set it based on the adaptability of the battery cell performance, which is not limited here. Furthermore, in order to remind the operator to terminate the detection of abnormal batteries in time, in one embodiment of the present invention, after marking the battery cell as an abnormal battery cell, it also includes: stopping the detection of abnormal batteries and sending a warning message.

[0066] See also Figure 4 , Figure 4 The figure is a flow chart of early warning information determination in one embodiment of the present invention. In one embodiment of the present invention, after stopping detecting abnormal cells, the method further includes:

[0067] S1141, based on the preset abnormality type determination condition, determine the abnormality type to which the abnormal battery cell belongs; and

[0068] S1142. Based on the abnormality type, send warning information corresponding to the abnormality type.

[0069] Since different abnormal cell types have different corresponding abnormal impedance values, for abnormal cells, the electrochemical impedance values ​​of the abnormal cells at different frequencies can be compared with the preset abnormal impedance values ​​at the frequency to determine the abnormal type of the cells. Based on the abnormal type, a corresponding warning message is set to warn the operator to deal with the abnormal cell in time, wherein the warning message can be an acoustic and photoelectric warning signal. Exemplarily, the warning message of poor welding of the tab is a flashing red light, and the warning message of the tab folding is a continuous beep, etc. It should be noted that for the moisture detection of a single cell, if the cell is an abnormal cell, the detection of the cell is stopped, another cell is reselected, and the moisture of the new cell is detected from step S1. For multiple cells, moisture detection is performed simultaneously. If one or more cells are abnormal cells, the abnormal cells are removed from the above multiple cells, and the moisture of the normal cells is continued to be detected.

[0070] S2. Input a plurality of corresponding electrochemical impedance values ​​into a trained moisture prediction model to obtain the predicted moisture of the battery cell.

[0071] See also Fig. 9 , Fig. 9 The schematic diagram of the input and output data of the moisture prediction model in one embodiment of the present invention is shown. The electrochemical impedance values ​​at multiple frequencies are input into the pre-trained moisture prediction model, and the moisture prediction model extracts the characteristics of the electrochemical impedance values ​​at each frequency and outputs the predicted moisture of the battery cell. And based on the predicted moisture of the battery cell, it can be determined whether the moisture content of the battery cell after baking meets the drying requirements.

[0072] Further, considering that there are high requirements for detection accuracy and detection speed in the actual production environment, the model volume trained using the deep learning method is often large. After it takes a long time to complete the training, once the battery model or brand is changed, the previously trained model cannot automatically correct the learning results due to the lag of the deep learning model, and cannot timely and accurately predict the moisture content of the new battery, which is not suitable for the actual production environment. In addition, a large-volume deep learning model will occupy more memory resources when running, and has high requirements for the computing power of the device, and is not universal. Therefore, in one embodiment of the present invention, the moisture prediction model is a linear regression model. The linear regression model trained using the traditional machine learning method has a much faster training speed than the model of the deep learning architecture, and accurately predicts the water content of different types of batteries. And the linear regression model is small in size, has low requirements for the computing power of the equipment, and has good universality. In addition, under the same training data, the possibility of overfitting of the linear regression model is much smaller than that of the deep learning model, so the linear regression model can be based on a small amount of training data to achieve accurate prediction of the moisture content of the battery.

[0073] In one embodiment of the present invention, before inputting a plurality of corresponding electrochemical impedance values ​​into the trained moisture prediction model, the method further includes: S11, performing impedance temperature compensation on the electrochemical impedance values ​​corresponding to the battery cells at each frequency based on the temperature of the battery cells.

[0074] When the moisture prediction model is trained, the training data used is the electrochemical impedance value at a certain standard temperature. Considering that when the electrochemical impedance value of the baked battery cell is tested, the temperature of the battery cell will gradually decrease under normal temperature, resulting in the current temperature of the battery cell being different from the standard temperature set during model training. The electrochemical impedance value is extremely sensitive to temperature changes. In order to accurately predict the water content of the battery cell, the measured electrochemical impedance value needs to be compensated for impedance temperature, so as to compensate the electrochemical impedance value at the current temperature to the electrochemical impedance value at the preset standard temperature.

[0075] See also Figure 5 and Fig.10 , Figure 5 It is a schematic diagram of the temperature compensation process in one embodiment of the present invention. Fig.10 The figure shows a high temperature curve of a cell after baking in one embodiment of the present invention. In one embodiment of the present invention, based on the temperature of the cell, impedance temperature compensation is performed on the electrochemical impedance value of the cell at each frequency, including:

[0076] S121, obtaining the current temperature of the battery cell and the standard temperature corresponding to the moisture prediction model; wherein the standard temperature is the temperature preset when training the moisture prediction model;

[0077] S122, searching for the impedance change rate corresponding to the current temperature to the standard temperature according to the identification of the battery cell; and

[0078] S123. Based on the impedance change rate, the electrochemical impedance value corresponding to each frequency is compensated to obtain the electrochemical impedance value corresponding to each frequency after compensation.

[0079] The current temperature of the battery cell can be obtained using a temperature probe, and the standard temperature required for training corresponding to the identification can be found from the database through the battery cell identification. By calculating the difference between the current temperature and the standard temperature, the impedance change rate corresponding to the difference is obtained. Based on the impedance change rate, the electrochemical impedance values ​​corresponding to different frequencies of the battery cell at the current temperature are temperature compensated to obtain the electrochemical impedance values ​​corresponding to each frequency after compensation. The electrochemical impedance values ​​input to the moisture prediction model are all obtained at the same temperature, which can eliminate the interference of temperature on the electrochemical impedance value and make the prediction result more accurate. It should be noted that the database pre-stores standard temperatures corresponding to a variety of different battery cell identifications and electrochemical impedance values ​​corresponding to each temperature difference. Exemplarily, the standard temperature is 90 degrees, the current temperature of the battery cell is 80 degrees, the temperature difference between the two is 10 degrees, and the corresponding impedance change rate is 2%. If the battery cell is at the current temperature, the electrochemical impedance value corresponding to 1HZ is 360, and the electrochemical impedance value corresponding to 5HZ is 287. After impedance temperature compensation, the electrochemical impedance value of the battery cell at standard temperature is 367.2 for 1HZ and 292.74 for 5HZ. It can be understood that the corresponding impedance change rate is different under different temperature differences.

[0080] S3. Determine whether the predicted moisture content of the battery cell meets a preset battery cell moisture evaluation standard, and determine that the battery cell meets the drying requirement when the predicted moisture content of the battery cell meets the battery cell moisture evaluation standard.

[0081] After using the moisture prediction model to obtain the predicted moisture content of the battery cell, it is necessary to determine whether the moisture content of the battery cell meets the drying requirements based on the predicted moisture content of the battery cell and the battery cell moisture evaluation standard. If it does, the subsequent process can be carried out. If it does not, the battery cell needs to be screened out and the subsequent processing process of the battery cell needs to be stopped.

[0082] Specifically, see Figure 6 , Figure 6 The flowchart of the water content evaluation of the battery cell in one embodiment of the present invention is shown. In one embodiment of the present invention, the predicted water content of the battery cell includes a first predicted water content and a second predicted water content, and judging whether the predicted water content of the battery cell meets the preset water content evaluation standard of the battery cell includes:

[0083] S301, determining whether the first predicted moisture content is less than or equal to a preset first moisture content threshold, and whether the second predicted moisture content is less than or equal to a preset second moisture content threshold;

[0084] S302: If the first predicted moisture content is less than or equal to the first moisture content threshold, and the second predicted moisture content is less than or equal to the second moisture content threshold, the predicted moisture content of the battery cell meets the battery cell moisture evaluation standard;

[0085] S303: If the first predicted moisture content is greater than the first moisture threshold, and / or the second predicted moisture content is greater than the second moisture threshold, the predicted moisture content of the battery cell does not meet the battery cell moisture evaluation standard.

[0086] In order to ensure the safety of the battery cell, it is necessary to simultaneously detect whether the water content of the positive electrode sheet of the battery cell and the water content of the negative electrode sheet are qualified. In this embodiment, after the electrochemical impedance values ​​corresponding to different frequencies are input into the moisture prediction model, the moisture prediction model will obtain the first predicted moisture content and the second predicted moisture content of the battery cell based on a series of electrochemical impedance values, and compare the first predicted moisture content and the first moisture threshold, and the second predicted moisture content and the second moisture threshold value. Among them, the first predicted moisture content is the predicted moisture content of the positive electrode sheet, the second predicted moisture content is the predicted moisture content of the negative electrode sheet, the first moisture threshold is the moisture threshold of the positive electrode sheet, and the second moisture threshold is the moisture threshold of the negative electrode sheet. It should be noted that the first moisture threshold and the second moisture threshold can be adaptively set to the corresponding values ​​based on the specific characteristics of the battery cell, and are not limited here. If the first predicted moisture content is less than or equal to the first moisture threshold, and the second predicted moisture content is less than or equal to the second moisture threshold, it means that the moisture content of the battery cell after baking is less, which meets the battery cell moisture evaluation standard, and the subsequent process can be carried out. If the first predicted moisture content is greater than the first moisture threshold and the second predicted moisture content is greater than the second moisture threshold, at least one of the two is true, indicating that at least one of the moisture content of the positive electrode sheet or the negative electrode sheet of the battery cell after baking exceeds the standard and does not meet the battery cell moisture evaluation standard, and the battery cell needs to be marked as an unqualified battery cell. For example, if the first moisture threshold is 400ppm and the second moisture threshold is 300ppm, the battery cell status judgment is shown in Table 1:

[0087] Table 1 Battery status judgment table

[0088] First predicted moisture Second predicted moisture Battery status 402 200 Failure 300 350 Failure 450 320 Failure 320 220 qualified

[0089] See also Fig.11 , Fig.11 The predicted moisture values ​​of different battery cells in one embodiment of the present invention are displayed. By judging the relationship between the moisture prediction value of each battery cell and the preset moisture threshold, it is possible to quickly judge whether the residual moisture of the battery cell meets the moisture evaluation standard. In order to intuitively display the specific moisture prediction value of each batch of battery cells and the degree of deviation from the preset moisture threshold, a bar graph, a data density distribution graph or a box plot can be used for presentation. For example Fig.11In, when the predicted moisture is higher than the standard line of the moisture threshold, it is considered that the battery cell has a large amount of residual moisture and does not meet the drying requirements. Furthermore, due to the same process, the predicted moisture obtained by the moisture prediction model for the same batch of baked batteries should fluctuate around the moisture threshold, and the fluctuation range is small. Therefore, when the fluctuation range is large, it is necessary to verify the reliability of the data and the state of the current battery cell to determine whether the entire detection process is due to human error and other reasons, resulting in deviations in the measured electrochemical impedance value, causing the final result to be incorrect. Among them, the method of verifying the reliability of the data is not limited here. For example, the 6sigma method can be used, combined with the distribution of past data, to analyze the reliability of the data, or the Kramers-Kronig fitting method can be used to verify the reliability of EIS. It should be noted that the size of the fluctuation range can be set based on adaptability such as detection accuracy, which will not be repeated here.

[0090] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of sequence, and the order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0091] See also Fig.12 , Fig.12 Shown is a structural block diagram of a battery cell detection system in one embodiment of the present invention. In one embodiment, a battery cell detection system is provided. The battery cell detection system 200 corresponds one-to-one to the battery cell detection method in the above embodiment. The battery cell detection system 200 includes an impedance acquisition module 210, a moisture prediction module 220, and a drying requirement judgment module 230. The impedance acquisition module 210 is used to obtain the electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies. The moisture prediction module 220 is used to input multiple corresponding electrochemical impedance values ​​into a trained moisture prediction model to obtain the predicted moisture of the battery cell. The drying requirement judgment module 230 is used to determine whether the predicted moisture of the battery cell meets the preset battery cell moisture evaluation standard, and when the predicted moisture of the battery cell meets the battery cell moisture evaluation standard, it is determined that the battery cell meets the drying requirement.

[0092] Furthermore, the battery cell detection system 200 also includes an abnormal data screening module 211 and a temperature compensation module 212. The abnormal data screening module 211 is used to screen abnormal data of electrochemical impedance values ​​corresponding to multiple frequencies. The temperature compensation module 212 is used to perform impedance temperature compensation on the electrochemical impedance values ​​corresponding to the battery cell at each frequency based on the temperature of the battery cell.

[0093] It should be noted that, in order to highlight the innovative part of the present invention, the present embodiment does not introduce modules that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other modules in the present embodiment.

[0094] In addition, those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0095] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0096] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional units.

[0097] This embodiment also proposes a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to make the computer execute the above-mentioned battery inspection method. The storage medium can be an electronic medium, a magnetic medium, an optical medium, an electromagnetic medium, an infrared medium or a semiconductor system or a propagation medium. The storage medium can also include a semiconductor or solid-state memory, a magnetic tape, a removable computer disk, a random access memory (RAM), a read-only memory (ROM), a hard disk and an optical disk. The optical disk can include a compact disk-read only memory (CD-ROM), a compact disk-read / write (CD-RW) and a DVD.

[0098] In summary, the present invention discloses a method, system and storage medium for detecting a battery cell. Through a moisture prediction model, according to each electrochemical impedance value of the battery cell after baking, the residual moisture value of the battery cell can be efficiently and accurately predicted, thereby realizing non-destructive detection of the battery cell and greatly reducing the solid consumption of the battery cell. By combining the electrochemical impedance value with the moisture prediction model, online detection of the residual water content in the battery cell can be realized, and all the battery cells after baking can be quickly detected, which has strong universality. The beat and output of the overall production line are greatly improved, and battery cells with abnormal moisture content can be captured more accurately and efficiently, effectively avoiding these battery cells with abnormal moisture content from flowing into subsequent processes and causing more property losses. Therefore, the present invention effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0099] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for detecting a battery cell, characterized in that: The detection method comprises: Obtaining electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies; Inputting a plurality of corresponding electrochemical impedance values ​​into a trained moisture prediction model to obtain predicted moisture of the battery cell; and It is determined whether the predicted moisture content of the battery cell meets a preset battery cell moisture evaluation standard, and when the predicted moisture content of the battery cell meets the battery cell moisture evaluation standard, it is determined that the battery cell meets the drying requirement.

2. The detection method according to claim 1, characterized in that: The obtaining of electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies includes: Based on a preset frequency sweep interval, performing a frequency sweep test on the battery cell at a preset frequency interval; and Based on the sweep frequency test results, the electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies are obtained, wherein during the sweep frequency test, the amplitude of the sweep frequency signal at multiple frequencies remains consistent.

3. The detection method according to claim 1, characterized in that: After obtaining the electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies, the method further includes: screening the electrochemical impedance values ​​corresponding to the multiple frequencies for abnormal data, wherein the abnormal data screening includes: Based on the identification of the battery cell, searching for a standard impedance interval corresponding to each frequency, wherein the standard impedance interval is associated with the identification of the battery cell; Determining whether each electrochemical impedance value of the battery cell is within a corresponding standard impedance range; If the electrochemical impedance values ​​of the battery cell are all within the corresponding standard impedance range, the battery cell is marked as a normal battery cell; If at least one electrochemical impedance value of the battery cell is not within the corresponding standard impedance range, the battery cell is marked as an abnormal battery cell.

4. The detection method according to claim 3, characterized in that: After marking the battery cell as an abnormal battery cell, the method further includes: stopping detecting the abnormal battery cell and sending an early warning message.

5. The detection method according to claim 4, characterized in that: After stopping detecting the abnormal battery cell, the method further includes: Based on a preset abnormality type determination condition, determining the abnormality type to which the abnormal battery cell belongs; and Based on the exception type, a warning message corresponding to the exception type is sent.

6. The method for detecting a battery cell according to claim 1, characterized in that: Before inputting the plurality of corresponding electrochemical impedance values ​​into the trained moisture prediction model, the method further includes: performing impedance temperature compensation on the electrochemical impedance values ​​corresponding to the battery cells at each frequency based on the temperature of the battery cells.

7. The detection method according to claim 6, characterized in that: The impedance temperature compensation is performed on the electrochemical impedance value corresponding to the battery cell at each frequency based on the temperature of the battery cell, including: Acquire the current temperature of the battery cell and the standard temperature corresponding to the moisture prediction model, wherein the standard temperature is a preset temperature when training the moisture prediction model; According to the identification of the battery cell, searching for the impedance change rate corresponding to the current temperature to the standard temperature; and Based on the impedance change rate, the electrochemical impedance value corresponding to each frequency is compensated to obtain the electrochemical impedance value corresponding to each frequency after compensation.

8. The detection method according to claim 1, characterized in that: The moisture prediction model is a linear regression model.

9. The detection method according to claim 1, characterized in that: The predicted moisture content of the battery cell includes a first predicted moisture content and a second predicted moisture content, and judging whether the predicted moisture content of the battery cell meets a preset battery cell moisture evaluation standard includes: Determine whether the first predicted moisture content is less than or equal to a preset first moisture content threshold, and whether the second predicted moisture content is less than or equal to a preset second moisture content threshold; If the first predicted moisture content is less than or equal to the first moisture threshold, and the second predicted moisture content is less than or equal to the second moisture threshold, the predicted moisture content of the battery cell meets the battery cell moisture evaluation standard; If the first predicted moisture content is greater than the first moisture threshold, and / or the second predicted moisture content is greater than the second moisture threshold, the predicted moisture content of the battery cell does not meet the battery cell moisture evaluation standard.

10. A battery cell detection system, characterized in that: The system comprises: An impedance acquisition module, used to obtain electrochemical impedance values ​​corresponding to the battery cell at multiple frequencies; a moisture prediction module, used for inputting a plurality of corresponding electrochemical impedance values ​​into a trained moisture prediction model to obtain the predicted moisture of the battery cell; and The drying requirement judgment module is used to judge whether the predicted moisture content of the battery cell meets the preset battery cell moisture evaluation standard, and when the predicted moisture content of the battery cell meets the battery cell moisture evaluation standard, determine that the battery cell meets the drying requirement.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images