Formation control method and device of battery, electronic equipment, medium and product

Abstract

The invention discloses a battery formation control method and device, electronic equipment, a medium and a product, and the method comprises the steps: respectively obtaining a thermal imaging image and an actual control parameter of a battery in a battery formation process; the actual control parameter comprises at least one of actual current and actual voltage; using a pre-trained target model to determine a target control parameter of the battery at a target moment based on the image acquisition moment and the thermal imaging image of the battery acquired at the image acquisition moment, the interval between the target moment and the image acquisition moment being a preset duration; and adjusting the actual control parameter into the target control parameter at the target moment. Therefore, the influence of the individual difference of the batteries on the formation process is considered, and the control precision and the formation quality in the formation process can be improved.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to a battery formation control method, apparatus, electronic device, medium, and product. Background Technology

[0002] Battery formation is a crucial step in the lithium-ion battery production process. Its purpose is to activate the internal materials of the battery and form a stable solid electrolyte interphase (SEI) film through the first charge-discharge process, thereby improving battery performance and consistency. Currently, forming multiple batteries with different initial conditions using a preset fixed control strategy may result in SEI films that differ from the ideal state in different batteries. Summary of the Invention

[0003] This application mainly provides a battery formation control method, device, electronic device, medium, and product, which takes into account the influence of individual battery differences on the formation process and can improve the control accuracy and formation quality in the formation process.

[0004] The technical solution of this application is implemented as follows: In a first aspect, embodiments of this application provide a battery formation control method, wherein during the battery formation process, thermal imaging images of the battery and actual control parameters are acquired respectively; the actual control parameters include at least one of actual current and actual voltage; using a pre-trained target model, based on the image acquisition time and the thermal imaging image of the battery acquired at the image acquisition time, the target control parameters of the battery at a target time are determined, the target time being a preset time interval from the image acquisition time; at the target time, the actual control parameters are adjusted to the target control parameters.

[0005] Through the aforementioned technical means, firstly, during the battery formation process, thermal imaging images and actual control parameters of the battery are acquired. These actual control parameters include at least one of the actual current and actual voltage. By acquiring multi-dimensional data, accurate data related to individual differences among batteries can be obtained during the formation process, thereby enabling timely detection of potential risks. Secondly, based on the battery's image acquisition time and the corresponding thermal imaging image, target control parameters for the battery at a target time are determined, and the actual control parameters are adjusted to the target control parameters at the target time. Thus, during the battery formation process, individual differences among batteries can be taken into account, providing refined control and improving the control accuracy during the formation process, thereby improving the formation quality and consistency of the batteries.

[0006] In some embodiments, determining target control parameters of the battery at a target time based on the image acquisition time and the thermal imaging image of the battery acquired at the image acquisition time includes: extracting features from the thermal imaging image to obtain thermal features of the battery; the thermal features include at least one of a temperature distribution uniformity index, an actual temperature value of at least one region, and a temperature rise rate; and determining the target control parameters based on the thermal features and the image acquisition time.

[0007] By employing the aforementioned techniques and utilizing a pre-trained target model, features are extracted from the battery's thermal imaging images to obtain the thermal characteristics represented by the images. Furthermore, based on these thermal characteristics and the image acquisition time, the target control parameters for the battery at the target time are determined. Thus, by using the thermal characteristics and image acquisition time during the battery formation process, a refined model of the battery's heat distribution is achieved, making the output target control parameters more reasonable and reliable. This enables refined control and intelligent sensing of the battery, improving control accuracy and the quality of battery formation.

[0008] In some embodiments, the pre-trained target model is obtained by: acquiring model training data; the model training data includes the acquisition time of the battery with a solid electrolyte interface membrane conforming to a preset standard during the formation process, as well as the acquisition current and thermal imaging images acquired during the acquisition time; and training the initial model based on the model training data to obtain the target model.

[0009] By using the above-mentioned technical means, high-quality model training datasets are constructed by collecting current, thermal imaging images, and time data of batteries that meet the solid electrolyte interface membrane standard during the formation process. Then, the initial model is trained using supervised learning methods based on the model training data, so that the target model obtained after training can accurately output the target control parameters at the target time. In this way, not only is the training quality of the target model guaranteed, but the reliability and practicality of the target model in practical applications are also improved.

[0010] In some embodiments, feature extraction of thermal imaging images to obtain thermal features of the battery includes: segmenting the thermal imaging image to determine a thermal energy distribution map of at least one region corresponding to the thermal imaging image; determining the actual temperature value of at least one region of the battery based on the thermal energy distribution map of at least one region; determining a temperature distribution uniformity index of the battery based on the actual temperature value of at least one region; and determining the temperature rise rate of at least one region of the battery based on the actual temperature value and historical temperature value of at least one region.

[0011] By employing the aforementioned techniques, segmenting thermal imaging images and generating thermal distribution maps, and then comparing actual temperature values ​​with historical temperature values, a comprehensive assessment of the battery's thermal state and operational status can be achieved. This method of segmenting thermal imaging images, generating thermal distribution maps, and comparing actual temperature values ​​with historical temperature values ​​enhances the intelligence level of battery thermal management, effectively preventing overheating risks, thereby extending battery life and ensuring operational safety.

[0012] In some embodiments, the method further includes at least one of the following: when the temperature rise rate of a first region of the battery is greater than a first preset value, determining the operating power of the battery's heat dissipation unit in the first region based on the target control parameters and the temperature rise rate of the first region; when the actual temperature value of a second region of the battery is greater than a second preset value, determining the operating power of the battery's heat dissipation unit in the second region based on the target control parameters and the actual temperature value of the second region; when the temperature distribution uniformity index of the battery is less than a third preset value, determining the operating power of the battery's heat dissipation unit in each of the at least one region based on the target control parameters and the actual temperature value of the battery in at least one region.

[0013] By employing the aforementioned technical methods and implementing temperature monitoring and heat dissipation control logic in different areas of the battery, the operating power of the heat dissipation unit can be dynamically adjusted under various abnormal conditions (such as excessively rapid temperature rise, exceeding temperature limits, and uneven temperature distribution). This enables precise temperature control during the formation process, ensuring the temperature remains within an ideal temperature window, improving battery formation quality, enhancing SEI film formation quality, and effectively preventing potential risks such as thermal runaway. Ultimately, this significantly improves battery reliability and lifespan.

[0014] In some embodiments, after battery formation is completed, the method further includes: acquiring a sequence of thermal imaging images and a sequence of actual control parameters collected during the formation process; using a target model to determine a target control parameter sequence corresponding to the thermal imaging image sequence of the battery; and evaluating the formation quality of the battery based on the actual control parameter sequence and the target control parameter sequence.

[0015] By employing the aforementioned technical methods, thermal imaging image sequences and actual control parameter sequences are acquired, and a target control parameter sequence is generated using a target model. The battery formation quality is then evaluated based on a comparison of these two sequences. This enables intelligent monitoring and quality traceability of the battery manufacturing process, allowing for accurate identification of potential defects and ultimately improving overall product quality and production efficiency.

[0016] In some embodiments, the method further includes: evaluating the structural design of the battery based on a sequence of thermal imaging images acquired during the battery formation process, and generating a battery design analysis report.

[0017] By employing the aforementioned technical means, evaluating at least one battery structure design based on thermal imaging image sequences, and generating a corresponding battery design analysis report, this application embodiment can identify potential design defects or process problems in the early stages of battery production. This application embodiment can adjust design parameters or manufacturing processes in a timely manner, thereby improving the safety, consistency, and overall performance of at least one battery.

[0018] Secondly, embodiments of this application provide a battery formation control device, comprising: an acquisition module, configured to acquire thermal imaging images and actual control parameters of the battery during the battery formation process; the actual control parameters include at least one of actual current and actual voltage; a determination module, configured to determine target control parameters of the battery at a target time based on a pre-trained target model and the thermal imaging images of the battery acquired at the image acquisition time, wherein the target time is spaced apart from the image acquisition time by a preset time interval; and an adjustment module, configured to adjust the actual control parameters to the target control parameters at the target time.

[0019] Thirdly, embodiments of this application provide an electronic device, which includes a memory and a processor, wherein: the memory is used to store a computer program that can run on the processor; and the processor is used to execute the computer program in the memory to implement the steps of the method in any of the first aspects.

[0020] Fourthly, embodiments of this application provide a computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the method in any of the first aspects.

[0021] Fifthly, embodiments of this application provide a computer program product, including a computer program or instructions, which, when executed by a processor, implement the method in any of the first aspects.

[0022] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of this application. Attached Figure Description

[0023] Figure 1 A flowchart illustrating a battery formation control method provided in this application embodiment. Figure 1 ; Figure 2 A flowchart illustrating a battery formation control method provided in this application embodiment. Figure 2 ; Figure 3 A flowchart illustrating a battery formation control method provided in this application embodiment. Figure 3 ; Figure 4A flowchart illustrating a battery formation control method provided in this application embodiment. Figure 4 ; Figure 5 A flowchart illustrating a battery formation control method provided in this application embodiment. Figure 5 ; Figure 6 A flowchart illustrating a battery formation control method provided in this application embodiment. Figure 6 ; Figure 7 A schematic diagram of the composition structure of a battery formation control device provided in an embodiment of this application; Figure 8 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] In order to gain a more detailed understanding of the features and technical content of the embodiments of this application, the implementation of the embodiments of this application will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for reference and illustration only and are not intended to limit the embodiments of this application.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0026] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0027] It should also be noted that the terms "first, second, and third" used in the embodiments of this application are only used to distinguish similar objects and do not represent a specific order of objects. It is understood that "first, second, and third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0028] Furthermore, the reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0029] The following is a description of the relevant technologies used in this application.

[0030] The formation of a battery is actually the "first charging" process of a lithium battery, which aims to transform the battery from a "semi-finished product" into a usable state.

[0031] The significance of battery formation for battery manufacturing is as follows: 1. Formation of SEI film: A stable SEI film is generated on the surface of the negative electrode of the battery to prevent the electrolyte from continuously decomposing during subsequent cycles; 2. Activation of active materials: Lithium ions are inserted into the negative electrode for the first time, completing the electrochemical activation of the electrode; 3. Removal of moisture and gas: Trace amounts of residual moisture and reaction gases in the electrode are removed through the charging and discharging process.

[0032] Currently, during the simultaneous formation of multiple batteries, a pre-set fixed control strategy is adopted, such as keeping the current, formation time, temperature, and negative pressure constant during the formation process. However, different batteries have different initial conditions, and adopting this fixed control strategy may result in a certain difference between the SEI film formed by different batteries and the ideal state.

[0033] Based on this, embodiments of this application provide a battery formation control method, apparatus, electronic device, medium, and product. First, during the battery formation process, thermal imaging images and actual control parameters of the battery are acquired. The actual control parameters include at least one of actual current and actual voltage. Thus, by acquiring multi-dimensional data, accurate data related to individual differences in the batteries during the formation process can be collected, thereby timely identifying potential risks during battery formation. Second, based on the individual thermal imaging images of each battery and the image acquisition time, target control parameters for the battery at a target time are determined, and at the target time, the actual control parameters of the battery are adjusted to the target control parameters. In this way, individual differences in the batteries can be taken into account during the battery formation process, providing refined control for the batteries, improving the control accuracy during the formation process, and thus improving the formation quality and consistency of the batteries.

[0034] The present application will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0035] In one embodiment of this application, Figure 1 A flowchart illustrating a battery formation control method provided in this application embodiment. Figure 1 This method can be applied to a battery controller that is connected to a battery management system (BMS) in at least one battery. For example... Figure 1 As shown, the method may include the following steps S101 to S103.

[0036] S101, during the battery formation process, acquires thermal imaging images and actual control parameters of the battery respectively.

[0037] The actual control parameters include at least one of the actual current and the actual voltage.

[0038] In the embodiments of this application, different colors or grayscale values ​​of the thermal imaging image represent different temperature regions, which can reflect the spatial distribution information of heat at the moment the thermal imaging image is collected during the battery formation process. For example, it can reflect whether the internal formation reaction of the battery is uniform or whether there is an abnormal temperature rise.

[0039] In the embodiments of this application, multiple batteries may be formed simultaneously, and there may be slight differences in the initial state and electrolyte state of different batteries. This means that if the same current control is used during the simultaneous formation of multiple batteries, the formation states of the different batteries will differ. In this application and the following embodiments, the formation of one battery is used as an example for illustration; the formation process of other batteries can be referred to this battery.

[0040] During the battery formation process, at the image acquisition moment, thermal images of the battery are acquired using devices such as infrared thermal imagers, obtaining the corresponding thermal images at the respective image acquisition moments.

[0041] It should be noted that an infrared thermal imager can be installed at each battery formation station to acquire a thermal image of the corresponding battery. Furthermore, at least one infrared thermal imager is connected to the battery controller, sending the acquired thermal image of the battery to the controller.

[0042] In the embodiments of this application, actual control parameters refer to physical quantities that reflect the current formation state of the battery during the battery formation process and affect the heat generation or dissipation during the battery formation process. For example, they may include actual current and actual voltage.

[0043] In some embodiments, the actual control parameters may also include actual power, etc.

[0044] In this embodiment, during battery formation, at the time of image acquisition, actual control parameters of at least one battery, including actual current and actual voltage, are collected using devices such as current sensors and voltage sensors. This obtains the actual control parameters corresponding to each of the at least one battery at the time of image acquisition. It should be noted that the devices collecting the actual control parameters can be connected to the battery management system (BMS) within the battery. The BMS can then aggregate the actual control parameters collected by each device and send them to the battery controller, or they can be sent directly to the battery controller.

[0045] The thermal imaging images and actual control parameters of the battery can be acquired periodically. For example, the image acquisition time can be spaced apart from the first time the thermal imaging images and actual control parameters of the battery were acquired by a preset time interval.

[0046] S102, using a pre-trained target model, determines the target control parameters of the battery at the target time based on the image acquisition time and the thermal imaging image of the battery acquired at the image acquisition time.

[0047] The time interval between the target time and the image acquisition time is preset.

[0048] In this embodiment of the application, the target time may be different from the image acquisition time of the thermal imaging image and the actual control parameters in the above steps. For example, the target time may be separated from the image acquisition time by a preset time interval.

[0049] In this embodiment, the target control parameter is the control parameter for the battery to be in an idealized state at a target time. The content of the target control parameter can correspond to the actual control parameters, and may include at least one of target current, target voltage, and target power.

[0050] In this embodiment, the spatial distribution of battery temperature differs at different times during the battery formation process. A pre-trained target model can learn to establish a mapping relationship between the ideal thermal imaging image, control parameters, and acquisition time.

[0051] The process involves acquiring thermal imaging images of the battery and the image acquisition time. A pre-trained target model can be used to analyze the thermal imaging image of the battery in an ideal state at the image acquisition time, along with the corresponding control parameters under that ideal state. Furthermore, the acquired thermal imaging image of the battery is compared with the thermal imaging image under the ideal state, and the control parameters under the ideal state are corrected based on the differences. Finally, the target control parameters of the battery at the target time are predicted. The corrected value for the control parameters under the ideal state is correlated with the difference between the thermal imaging image under the ideal and actual states.

[0052] For example, the current under ideal conditions at the time of image acquisition is 2A. However, the temperature of the thermal imaging image actually acquired by the battery is too high compared with that under ideal conditions. Based on the temperature difference, the current under ideal conditions is corrected, and the target control parameter at the target time is determined to be 1.8A.

[0053] It should be noted that the target control parameters may differ for different batteries.

[0054] It should be noted that, in some embodiments, the image acquisition time can be determined based on actual control parameters. The timing of the first peak and the first trough of the curve can be determined to reduce the computational resources required by the battery controller and improve control efficiency.

[0055] S103, at the target time, adjust the actual control parameters to the target control parameters.

[0056] In this embodiment, after determining the actual control parameters of the battery, the battery controller sends control signals to the respective actuators of the battery's control parameters, such as the current regulator and the power supply, to adjust the actual control parameters of the battery to the corresponding target control parameters.

[0057] For example, if the actual current collected by the battery is 1.5A, and based on the aforementioned steps it is determined that if it needs to generate an ideal SEI film, the target current is 2A, then the battery controller adjusts the current corresponding to the battery to 2A.

[0058] This application provides a battery formation control method. First, during the battery formation process, thermal imaging images and actual control parameters of the battery are acquired. The actual control parameters include at least one of actual current and actual voltage. By acquiring multi-dimensional data, accurate data related to individual differences among batteries can be obtained during the formation process, thereby enabling timely detection of potential risks. Second, based on the individual thermal imaging images of each battery and the image acquisition time, target control parameters for the battery at a target time are determined. At the target time, the actual control parameters of the battery are adjusted to the target control parameters. Thus, during the battery formation process, individual differences among batteries can be taken into account, providing refined control and improving the control accuracy during the formation process, thereby improving the formation quality and consistency of the battery.

[0059] In some embodiments, for step S102, based on the image acquisition time and the thermal imaging image of the battery acquired at the image acquisition time, the target control parameters of the battery at the target time are determined, such as... Figure 2 As shown, it may include the following steps S201 to S202.

[0060] S201, extract features from the thermal imaging image to obtain the thermal characteristics of the battery.

[0061] The thermal characteristics include at least one of the following: temperature distribution uniformity index, actual temperature value of at least one region, and temperature rise rate.

[0062] In this embodiment of the application, after obtaining the thermal imaging image of the battery, the thermal imaging image can first be processed by noise reduction, filtering, registration, etc., to facilitate subsequent analysis.

[0063] In this embodiment of the application, a pre-trained target model is used to extract features from the thermal imaging image of the battery to obtain the thermal features represented by the thermal imaging image of the battery.

[0064] In this embodiment, the thermal characteristics may include the actual temperature value of at least one region. Specifically, the average actual temperature value of the entire battery can be determined based on a thermal imaging image, or the thermal imaging image can be divided into different regions, such as a cell region and an electrolyte region, and the actual temperature value of each region can be determined separately.

[0065] In this embodiment of the application, the thermal feature may also include a temperature distribution uniformity index. This feature is used to quantify the non-uniformity of the temperature field on the battery surface. Its value can be determined by statistical analysis based on the temperature values ​​of each pixel or region in the thermal imaging image of the battery.

[0066] In this embodiment of the application, the thermal feature may further include the temperature rise rate of at least one region. The temperature rise rate is a dynamic feature. The temperature rise rate of each region of the battery at the time of image acquisition reflects the time period between the time of image acquisition and the first moment of the previous thermal imaging image acquisition, and the speed at which each region of the battery generates heat.

[0067] It should be noted that thermal characteristics may also include other characteristics related to heat distribution during battery formation, which are not specifically limited here.

[0068] S202, based on thermal characteristics and image acquisition time, determine the target control parameters.

[0069] In this embodiment, a pre-trained target model is used to determine the control parameters of the battery in an ideal state and the thermal features of the thermal imaging image based on the image acquisition time after obtaining the thermal features corresponding to the thermal imaging image of the battery. The thermal features corresponding to the actual thermal imaging image of the battery are then compared with the thermal features corresponding to the thermal imaging image in the ideal state to determine the difference. The control parameters in the ideal state are then corrected based on this difference. Finally, based on the corrected control parameters, the pre-trained target model predicts the target control parameters at the target time.

[0070] In this process, the correction step is a feedback correction for the difference between the thermal characteristics of the battery at the time of image acquisition and the thermal characteristics under ideal conditions. This eliminates the problem that the different initial states of different batteries and the individual differences of batteries during the formation process lead to inconsistencies with the control parameters of the ideal formation process, which in turn leads to the problem that the generated SEI film does not meet the requirements.

[0071] It should be noted that the prediction stage is performed on the revised new baseline to determine the optimal target control parameters at the target time. Since thermal imaging images and actual control parameters are acquired during image acquisition, and the subsequent steps to determine the target control parameters require processing time, predicting the target control parameters at the target time allows sufficient time for data processing and control.

[0072] Thus, by iterating at multiple moments and repeating steps S101 to S103 and steps S201 to S202 at the next moment, the actual control parameters of the battery during the formation process approach the target control parameters under the ideal state, thereby making the SEI film generated by the battery approach the SEI film under the ideal state.

[0073] For example, if the actual temperature value reflected by the thermal imaging image of the battery is not within the ideal temperature window of the formation process, the actual control parameters under the actual state can be adjusted to be within the ideal temperature window, and the target control parameters of the battery at the target time can be predicted based on the adjusted actual control parameters under the actual state.

[0074] This application provides a battery formation control method. Using a pre-trained target model, features are extracted from the battery's thermal imaging images to obtain the thermal characteristics represented by the images. Furthermore, based on these thermal characteristics and the image acquisition time, target control parameters for the battery at a target time are determined. Thus, based on the thermal characteristics during battery formation and the image acquisition time, a refined model of the battery's heat distribution is achieved, making the output target control parameters more reasonable and reliable. This enables refined control and intelligent sensing of the battery, improving control accuracy and battery formation quality.

[0075] In some embodiments, such as Figure 3 As shown, the pre-trained target model is obtained based on the following steps S301 to S302.

[0076] S301, Obtain model training data.

[0077] The model training data includes the acquisition time of batteries with solid electrolyte interface membranes meeting preset standards during the formation process, as well as the acquisition current and thermal imaging images acquired during the acquisition time.

[0078] In the embodiments of this application, during the formation process, multiple sets of formation data are collected for each of the multiple batteries used as tests at preset time intervals, wherein each set of formation data may include the battery's current, thermal imaging image, and time.

[0079] Alternatively, in some embodiments, during the formation process of multiple batteries used as tests, the parameters can be determined based on actual control parameters. The acquisition current, thermal imaging image, and acquisition time are obtained at the first peak and first trough of the curve. Based on these key points, model training data is constructed. The initial model is trained based on the model training data, which can reduce the number of control operations and reduce the computational resources occupied by the battery controller.

[0080] In this embodiment of the application, after the formation of multiple batteries used as experiments is completed, the SEI film of each battery is analyzed. If the thickness and density of the SEI film generated by one or more batteries meet the preset standards, the multiple sets of formation data collected during the formation process of these one or more batteries are used as the acquisition current, acquisition thermal imaging image and acquisition time of the battery under ideal formation conditions to construct model training data.

[0081] In this embodiment, another set of experiments can be constructed. During the formation process of multiple batteries (serving as another set of experiments), the differences between the thermal imaging images of each battery and the thermal imaging images of the batteries conforming to preset standards are obtained. Based on these differences, the control parameter correction values ​​for each battery are adjusted, and the control parameters for the next moment are predicted. After formation, if the SEI film thickness and density of one or more batteries meet the preset standards, model training data is constructed based on the differences, correction values, and predicted control parameters between the thermal imaging images of these one or more batteries during formation and those of batteries conforming to the preset standards.

[0082] Thus, by constructing model training data based on the formation data collected during the formation process of batteries with SEI films that meet preset standards, and using this data as training samples for the initial model, it can be ensured that the target model trained learns the mapping relationship between control parameters, thermoforming images, and time under ideal conditions.

[0083] S302, based on the model training data, train the initial model to obtain the target model.

[0084] In the embodiments of this application, the initial model is typically an untrained deep neural network structure, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), where the parameters of the initial model have not yet converged.

[0085] In this embodiment, a supervised learning method is used to train an initial model based on model training data, and the error is measured by a preset loss function to obtain the target model.

[0086] In the embodiments of this application, the target model can determine the difference between the thermal characteristics of the thermal imaging image at the time of image acquisition and the thermal characteristics under the ideal state, and optimize the corresponding control parameters under the ideal state based on the difference; and the target model can also predict the target control parameters at the future target time based on the optimized control parameters at the time of image acquisition.

[0087] It should be noted that, under ideal conditions, thermal features, control parameters, etc., can be learned by the target model, or can be used as the target model's dataset and called upon during use.

[0088] It should also be noted that different battery models may have different control parameters and thermal characteristics. These can be correlated with a dataset constructed by linking the battery model with the corresponding target model, thermal characteristics under ideal conditions, and control parameters.

[0089] This application provides a battery formation control method. By collecting current, thermal imaging images, and time data of a battery conforming to the solid electrolyte interface membrane standard during the formation process, a high-quality model training dataset is constructed. Then, the initial model is trained using a supervised learning method based on the model training data, so that the target model obtained after training can accurately output the target control parameters at the target time. In this way, not only is the training quality of the target model guaranteed, but the reliability and practicality of the target model in practical applications are also improved.

[0090] In some embodiments, for step S201, feature extraction is performed on the thermal imaging image to obtain the thermal features of the battery, such as... Figure 4 As shown, it may include the following steps S401 to S404.

[0091] S401, Segment the thermal imaging image to determine the thermal energy distribution map of at least one region corresponding to the thermal imaging image.

[0092] In this embodiment, a thermal distribution map refers to an image result that divides a thermal imaging image into multiple regions and visualizes the thermal intensity within each region. The thermal distribution map can intuitively display the degree of heat concentration and distribution trend in different regions. For example, for any battery, if the thermal energy in a certain region is abnormally concentrated, it may indicate a risk of localized overheating or an internal short circuit problem.

[0093] In this embodiment, the thermal distribution map can be in matrix form, with each region of the battery corresponding to an actual temperature value.

[0094] S402, based on the thermal energy distribution map of at least one region, determine the actual temperature value of at least one region of the battery.

[0095] In this embodiment, the actual temperature value is a specific temperature value calculated based on the thermal intensity of each region in the battery's thermal distribution map, combined with the calibration parameters of the infrared thermal imaging device. For example, nonlinear correction, emissivity compensation, etc., can be used, but are not specifically limited here.

[0096] In the embodiments of this application, the actual temperature value can be expressed in degrees Celsius to evaluate the thermal state of each region of the battery.

[0097] S403, based on the actual temperature value of at least one region, determine the temperature distribution uniformity index of the battery.

[0098] In the embodiments of this application, the temperature distribution uniformity index can be used to measure the degree of temperature difference between at least one region of each battery. The temperature distribution uniformity index can be determined by weighted calculation, for example, by calculating the maximum temperature difference, standard deviation or variance between the actual temperature values ​​of each region in the battery, and is used to evaluate thermal management and battery consistency.

[0099] S404, based on the actual temperature value and historical temperature value of at least one region, determine the temperature rise rate of at least one region of the battery.

[0100] In this embodiment, the temperature rise rate refers to the change in the actual temperature value of a certain area in the battery per unit time, reflecting the trend of temperature rise during the formation process. For example, it can be achieved by using... It is expressed in the way that...

[0101] Among them, the actual temperature value of at least one area of ​​the battery at the previous image acquisition time, i.e., the second time, is the historical temperature value of at least one area of ​​the battery.

[0102] In this embodiment of the application, the temperature rise rate can be calculated and determined based on the actual temperature value of at least one region of the battery at the time of image acquisition, the temperature difference between the actual temperature value of the battery in the corresponding region and the historical temperature value of the corresponding region, and the time difference between the time of image acquisition and the second time.

[0103] This application provides a battery formation control method. By segmenting thermal imaging images and generating thermal energy distribution maps, and then combining the calculated actual temperature values ​​with historical temperature values, the thermal state and operating status of the battery can be comprehensively evaluated. Through the aforementioned method of segmenting thermal imaging images and generating thermal energy distribution maps, combined with the calculation of actual temperature values ​​and comparison with historical temperature values, the level of intelligence in battery thermal management can be improved, thereby effectively preventing overheating risks, extending battery life, and ensuring operational safety.

[0104] In some embodiments, the method further includes at least one of the following (1)-(3).

[0105] (1) When the temperature rise rate of the first region of the battery is greater than the first preset value, the working power of the heat dissipation unit of the battery in the first region is determined based on the target control parameters and the temperature rise rate of the first region.

[0106] (2) When the actual temperature value of the second region of the battery is greater than the second preset value, the working power of the heat dissipation unit of the battery in the second region is determined based on the target control parameters and the actual temperature value of the second region.

[0107] (3) When the temperature distribution uniformity index of the battery is less than the third preset value, the working power of the heat dissipation unit of the battery in at least one region is determined based on the target control parameters and the actual temperature value of the battery in at least one region.

[0108] In this embodiment of the application, for (1), if the temperature rise rate of the first region of the battery exceeds the first preset value during the battery formation process, it indicates that there is a risk of local overheating in the first region of the battery. This risk of local overheating may affect the performance and life of the battery.

[0109] In this embodiment of the application, the battery can be any battery, and the first region can be any region in the battery where the temperature rise rate exceeds a first preset value.

[0110] In this embodiment, the operating power of the heat dissipation unit refers to the amount of energy output by the heat dissipation device (such as a fan, liquid cooling pump, etc.) in each area of ​​each battery, typically measured in watts (W). Each battery can be configured with a corresponding heat dissipation unit, and the operating power of the heat dissipation unit in different areas of the corresponding battery can be different. In some embodiments, the heat dissipation unit has spatial directional adjustment capabilities, such as adjustable dampers, zoned liquid cooling valves, semiconductor cooling arrays, etc., to control the heat dissipation of different areas of the battery.

[0111] In this embodiment, when the battery controller determines that the temperature rise rate of the first region of the battery is greater than a first preset value, it determines that there is a risk of local overheating in the first region of the battery. Based on the target control parameters, it can use a preset mapping function to determine the reference heat generation of the battery in the first region, and combine the temperature rise rate of the first region of the battery to determine the local operating power of the battery cell in the first region.

[0112] For example, the battery controller can determine the actual heat generation of the battery in the first region by superimposing the deviation temperature of the first temperature rise rate exceeding the first preset value with the reference heat generation of the battery under the target control parameters. It can further determine the operating power of the heat dissipation unit required for the temperature rise rate to drop back to the first preset value when the battery is operating under the target control parameters. Under the constraint of the operating power supported by the heat dissipation unit, it can determine the operating power of the heat dissipation unit in the first region of the battery to ensure that the temperature in the first region is reduced to below the safe first preset value, while avoiding overcooling of other regions of the battery.

[0113] In this embodiment of the application, for (2), when the actual temperature value of the second region of the battery exceeds the second preset value, it indicates that the second region of the battery is already in a high temperature state. This high temperature state may have an adverse effect on the battery formation process, or even cause thermal runaway.

[0114] In this embodiment, the battery can be any battery, and the second region can be any region where the actual temperature of any battery exceeds a second preset value.

[0115] In this embodiment of the application, when the actual temperature value of the second region of the battery is greater than the second preset value, the reference heat generation of the battery in the second region under the target control parameters is determined based on the target control parameters and using a preset mapping function. Combined with the actual temperature value of the second region of the battery, the local operating power of the battery cell in the second region is determined.

[0116] In this embodiment, the deviation temperature between the actual temperature of the battery and the second preset value can be calculated. The deviation temperature is then superimposed with the reference heat generation of the second region under the target control parameters of the battery to determine the operating power required for the actual temperature of the battery to drop back to the second preset value when the battery is operating under the target control parameters. Under the constraint of the operating power supported by the heat dissipation unit, the operating power of the heat dissipation unit in the second region of the battery is determined to ensure that the second region is reduced to a safe level below the second preset value, while avoiding overcooling of other regions of the battery.

[0117] In this embodiment of the application, for (3), when the temperature distribution uniformity index is lower than the third preset value, it indicates that the internal temperature distribution of the battery is uneven, and there may be local hot spots or cold spots inside the battery, thereby affecting the overall performance of the battery. In this case, it is necessary to comprehensively consider the actual temperature values ​​of multiple regions and allocate heat dissipation power to different regions of the battery according to the target control parameters, so that the temperature distribution of the battery tends to be more balanced.

[0118] In this embodiment, the battery can be any battery, and the third region can be a region where the temperature distribution uniformity index of any battery is less than a third preset value.

[0119] In this embodiment, when the battery's temperature distribution uniformity index is less than a third preset value, a preset mapping function is used to determine the baseline heat generation of the battery in each region under the target control parameters. This baseline heat generation is then superimposed with the deviation of the actual temperature value of at least one region from the first preset value to determine the actual heat generation of the battery in each region under the target control parameters. Further, based on the actual heat generation of the battery in each region under the target control parameters, and under the constraint of the operating power supported by the heat dissipation unit, the operating power of the heat dissipation unit in each region of the battery is determined to ensure that the battery's temperature distribution uniformity index is reduced to below the third preset value.

[0120] For example, hotter areas receive relatively more heat dissipation resources, while colder areas receive relatively less heat dissipation resources, thereby actively compressing temperature dispersion and reducing the battery's temperature distribution uniformity index while maintaining the total power consumption constant.

[0121] It should be noted that the target control parameters in the above embodiments can be replaced with actual control parameters, or replaced with both target control parameters and actual control parameters to form new embodiments, which are not specifically limited here.

[0122] This application provides a battery formation control method. By setting temperature monitoring and heat dissipation control logic in different areas of the battery, the operating power of the heat dissipation unit can be dynamically adjusted under various abnormal conditions (such as excessively rapid temperature rise, excessive temperature, and uneven temperature distribution). This enables precise temperature control of the battery during the formation process, keeping the temperature within an ideal temperature window, improving the formation quality of the battery, enhancing the quality of the SEI film formation, and effectively preventing potential risks such as thermal runaway. Ultimately, this significantly improves the reliability and lifespan of the battery.

[0123] In some embodiments, after at least one battery formation is completed, such as Figure 5 As shown, the method may further include the following steps S501 to S503.

[0124] S501, acquire the thermal imaging image sequence and actual control parameter sequence collected during the battery formation process.

[0125] In this embodiment, based on the foregoing embodiments, thermal imaging images are acquired at preset time intervals during the battery formation process. All thermal imaging images of the battery obtained after formation are completed are referred to as the thermal imaging sequence corresponding to that battery. The thermal imaging sequence includes a set of continuous thermal imaging images indexed by time, capable of reflecting the thermal change trend of the battery during the formation process.

[0126] In this embodiment, during the battery formation process, actual control parameters are collected at preset time intervals. All actual control parameters obtained after formation are completed are referred to as the actual control parameter sequence for this battery. The actual control parameter sequence includes a set of continuous control parameter sequences indexed by time, reflecting the changing trends of control parameters such as current and voltage during the formation stage.

[0127] S502, using the target model, determines the target control parameter sequence corresponding to the thermal imaging image sequence of the battery.

[0128] In this embodiment of the application, the thermal imaging image sequence of the battery is input into the target model, and the target control parameter sequence corresponding to the thermal imaging image sequence is output.

[0129] It should be noted that in the above steps, the target control parameters for the corresponding target time are determined based on the thermal imaging images of the battery, and the actual control parameters are adjusted to the target control parameters. Deviations may occur during the adjustment and control process; the actual control parameters may approach the target control parameters but fail to reach the optimal operating state. This error gradually accumulates, causing the SEI film of the formed battery to fail to meet the preset standard. Therefore, in this embodiment, the thermal imaging image sequence of the battery is input into the target model again to obtain the target control parameters for each thermal imaging image of the battery at its respective target time. The target times for different thermal imaging images are different.

[0130] S503 evaluates the formation quality of batteries based on the actual control parameter sequence and the target control parameter sequence.

[0131] In the embodiments of this application, formation quality refers to whether the internal chemical structure of the battery is stable, whether it has good electrochemical performance, and whether it meets product specifications after the formation process is completed.

[0132] In this embodiment, by comparing and analyzing the differences between the actual control parameter sequence and the corresponding target control parameter sequence, it can be determined whether there are deviations, abnormalities, or defects in the battery formation process. For example, in a certain formation process, if the actual current value in the actual control parameter sequence at a certain moment is significantly lower than the target current value in the target control parameter sequence at the same moment, and the actual current value never reaches the target current value level in subsequent moments, it may mean that there is a problem with the battery or a problem with the control device, such as poor contact or uneven distribution of active material.

[0133] This application provides a battery formation control method. It acquires thermal imaging image sequences and actual control parameter sequences, generates target control parameter sequences using a target model, and then evaluates the battery formation quality based on a comparison of the two. This enables intelligent monitoring and quality traceability of the battery manufacturing process, accurately identifying potential defects and improving overall product quality and production efficiency.

[0134] In some embodiments, the method may further include: evaluating the structural design of the battery based on a sequence of thermal imaging images acquired during the battery formation process, and generating a battery design analysis report.

[0135] In the embodiments of this application, the thermal imaging image sequence reflects the heat generation and distribution during the electrochemical reaction process inside the battery during the formation process, and can indirectly reflect the uniformity of the battery's internal structure, material properties, and consistency of the manufacturing process. For example, in the early stages of formation, the battery may experience localized abnormal temperature rises due to uneven electrolyte penetration or poor electrode bonding, and thermal imaging images can capture and record such abnormalities.

[0136] In this embodiment, each frame of the thermal imaging image sequence contains temporal and spatial information, which can be used to track the thermal behavior changes of the battery at different stages. By comparing and analyzing multiple frames of images, key parameters such as hot spots and temperature gradient changes during the battery formation process can be identified.

[0137] In this embodiment, battery structure design evaluation is a process of judging the overall structural rationality of the battery based on key features extracted from thermal imaging image sequences, combined with battery manufacturing specifications and expected performance indicators. Battery structure design evaluation may include, but is not limited to, the following: whether the tab layout affects the heat dissipation path, whether the electrode material distribution is uniform, and whether the encapsulation sealing is good. The evaluation results can be used to optimize the battery structure design and improve its safety and consistency.

[0138] In this embodiment, the battery design analysis report is a document or data file generated based on the aforementioned evaluation results. It summarizes the battery's thermal behavior during the formation process and the strengths and weaknesses of its structural design. The battery design analysis report typically includes image analysis conclusions, thermal behavior curves, anomaly markers, and improvement suggestions. The battery design analysis report serves as an important basis for subsequent battery design improvements, process optimization, and quality control.

[0139] This application provides a battery formation control method that evaluates at least one battery structure design based on a thermal imaging image sequence and generates a corresponding battery design analysis report. This application can detect potential design defects or process problems in the early stages of battery production. This application can adjust design parameters or manufacturing processes in a timely manner. This application can improve the safety, consistency and overall performance of at least one battery.

[0140] The battery formation control method and apparatus provided in this application embodiment will be described in detail below with reference to specific application scenarios.

[0141] like Figure 6 As shown in this embodiment, during the initial model training process, the cell formation process is controlled by current. During the cell formation process, a fixed preset time interval (or within a current-defined formation curve) is used. The current and temperature distribution through the battery are collected at key locations on the curve (such as the first peak and the first trough). The temperature distribution is determined based on images acquired by a thermal imaging instrument.

[0142] The mapping relationship between current, time, and temperature distribution represented by thermal imaging images is established through supervised machine learning and convolutional neural networks (image processing networks, such as CNN neural networks).

[0143] In this embodiment of the application, after the target model is trained, in actual application, the model calculates the theoretical current by inputting the time of thermal imaging image acquisition and the thermal imaging image through real-time thermal imaging images. By comparing the relationship between the theoretical current calculated by the model and the actual current, the actual current is adjusted to the theoretical current by the controller.

[0144] Based on the above embodiments, this application also provides a battery formation control device. Figure 7 This is a schematic diagram of the composition structure of a battery formation control device provided in an embodiment of this application, as shown below. Figure 7 As shown, the battery formation control device 700 includes the following modules.

[0145] The acquisition module 7001 is used to acquire thermal imaging images and actual control parameters of the battery during the battery formation process; the actual control parameters include at least one of actual current and actual voltage.

[0146] The determination module 7002 is used to determine the target control parameters of the battery at the target time based on the image acquisition time and the thermal imaging image of the battery acquired at the image acquisition time using a pre-trained target model. The interval between the target time and the image acquisition time is a preset time.

[0147] The adjustment module 7003 is used to adjust the actual control parameters to the target control parameters at the target time.

[0148] In some embodiments, the determining module 7002 is further configured to extract features from the thermal imaging image to obtain the thermal features of the battery; the thermal features include at least one of a temperature distribution uniformity index, an actual temperature value of at least one region, and a temperature rise rate; and to determine target control parameters based on the thermal features and the image acquisition time.

[0149] In some embodiments, the pre-trained target model is obtained by: acquiring model training data; the model training data includes the acquisition time of the battery with a solid electrolyte interface membrane conforming to a preset standard during the formation process, as well as the acquisition current and thermal imaging images acquired during the acquisition time; and training the initial model based on the model training data to obtain the target model.

[0150] In some embodiments, the determining module 7002 is further configured to segment the thermal imaging image to determine a thermal energy distribution map of at least one region corresponding to the thermal imaging image; determine the actual temperature value of at least one region of the battery based on the thermal energy distribution map of at least one region; determine the temperature distribution uniformity index of the battery based on the actual temperature value of at least one region; and determine the temperature rise rate of at least one region of the battery based on the actual temperature value and historical temperature value of at least one region.

[0151] In some embodiments, the determining module 7002 is further configured to: determine the operating power of the battery's heat dissipation unit in the first region based on the target control parameters and the temperature rise rate of the first region when the temperature rise rate of the first region of the battery is greater than a first preset value; determine the operating power of the battery's heat dissipation unit in the second region based on the target control parameters and the actual temperature value of the second region when the actual temperature value of the second region of the battery is greater than a second preset value; and determine the operating power of the battery's heat dissipation unit in at least one region based on the target control parameters and the actual temperature value of the battery in at least one region when the temperature distribution uniformity index of the battery is less than a third preset value.

[0152] In some embodiments, the determining module 7002 is further configured to, after the battery formation is completed, acquire the thermal imaging image sequence and the actual control parameter sequence collected during the formation process; use the target model to determine the target control parameter sequence corresponding to the thermal imaging image sequence of the battery; and evaluate the formation quality of the battery based on the actual control parameter sequence and the target control parameter sequence.

[0153] In some embodiments, the determining module 7002 is further configured to evaluate the structural design of the battery based on the thermal imaging image sequence acquired during the battery formation process, and generate a battery design analysis report.

[0154] In some embodiments, Figure 8 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Figure 8 As shown, electronic device 80 may include: a communication interface 801, a memory 802, and a processor 803; the various components are coupled together via a bus system 804. It is understood that the bus system 804 is used to implement communication between these components. In addition to a data bus, the bus system 804 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 8 The general designates all buses as Bus System 804. Among them: The communication interface 801 is used for receiving and sending signals during the process of sending and receiving information with the power supply equipment; Memory 802 is used to store computer programs that can run on processor 803; Processor 803 is used to execute the following when running computer programs: During the battery formation process, thermal imaging images of the battery and actual control parameters are acquired respectively; the actual control parameters include at least one of actual current and actual voltage. Using a pre-trained target model, the target control parameters of the battery at the target time are determined based on the image acquisition time and the thermal imaging image of the battery acquired at the image acquisition time. The interval between the target time and the image acquisition time is a preset time. At the target time, the actual control parameters are adjusted to the target control parameters.

[0155] It is understood that the memory 802 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 802 of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0156] The processor 803 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 803 or by instructions in software form. The processor 803 can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 802, and the processor 803 reads the information in memory 802 and, in conjunction with its hardware, completes the steps of the above method.

[0157] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions of this application, or combinations thereof.

[0158] For software implementation, the techniques described herein can be achieved through modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in memory and executed by a processor. Memory can be implemented within the processor or externally.

[0159] Alternatively, as another embodiment, the processor 803 is also configured to perform the steps of any of the methods in the foregoing embodiments when running a computer program.

[0160] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. The computer-readable storage medium can be transient or non-transient.

[0161] This application also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement some or all of the steps in the above-described method. This computer program product can be implemented specifically through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0162] It should be understood that the phrases "one embodiment," "an embodiment," or "some embodiments" mentioned throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment," "in one embodiment," or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution 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 this application. The sequence numbers of the above-described embodiments are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments; their similarities or commonalities can be referred to mutually, and for the sake of brevity, they will not be repeated here.

[0163] It should also be noted that, in this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0164] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0165] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0166] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0167] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0168] The above are merely preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for controlling the formation of a battery, characterized in that, The method includes: During the battery formation process, thermal imaging images and actual control parameters of the battery are acquired respectively; the actual control parameters include at least one of actual current and actual voltage. Using a pre-trained target model, the target control parameters of the battery at a target time are determined based on the image acquisition time and the thermal imaging image of the battery acquired at the image acquisition time, wherein the target time is separated from the image acquisition time by a preset time interval. At the target time, the actual control parameters are adjusted to the target control parameters.

2. The method according to claim 1, characterized in that, The determination of target control parameters for the battery at a target time based on the image acquisition time and the thermal imaging image of the battery acquired at the image acquisition time includes: Feature extraction is performed on the thermal imaging image to obtain the thermal characteristics of the battery; the thermal characteristics include at least one of the following: temperature distribution uniformity index, actual temperature value of at least one region, and temperature rise rate; The target control parameters are determined based on the thermal characteristics and the image acquisition time.

3. The method according to claim 1, characterized in that, The pre-trained target model is obtained through training in the following manner: Acquire model training data; the model training data includes the acquisition time of the battery with a solid electrolyte interface membrane conforming to a preset standard during the formation process, as well as the acquisition current and thermal imaging images acquired during the acquisition time; Based on the model training data, the initial model is trained to obtain the target model.

4. The method according to claim 2, characterized in that, The step of extracting features from the thermal imaging image to obtain the thermal features of the battery includes: The thermal imaging image is segmented to determine the thermal energy distribution map of at least one region corresponding to the thermal imaging image; Based on the thermal energy distribution map of the at least one region, determine the actual temperature value of at least one region of the battery; Based on the actual temperature value of the at least one region, the temperature distribution uniformity index of the battery is determined; The temperature rise rate of at least one region of the battery is determined based on the actual temperature value and historical temperature value of the at least one region.

5. The method according to any one of claims 1-4, characterized in that, The method further includes at least one of the following: If the temperature rise rate of the first region of the battery is greater than a first preset value, the operating power of the heat dissipation unit of the battery in the first region is determined based on the target control parameters and the temperature rise rate of the first region. If the actual temperature value of the second region of the battery is greater than the second preset value, the working power of the heat dissipation unit of the battery in the second region is determined based on the target control parameter and the actual temperature value of the second region. If the temperature distribution uniformity index of the battery is less than a third preset value, the operating power of the heat dissipation unit of the battery in at least one region is determined based on the target control parameters and the actual temperature value of the battery in at least one region.

6. The method according to any one of claims 1-4, characterized in that, After the battery formation is completed, the method further includes: Acquire the thermal imaging image sequence and actual control parameter sequence collected during the battery formation process; Using the target model, the target control parameter sequence corresponding to the thermal imaging image sequence of the battery is determined; The formation quality of the battery is evaluated based on the actual control parameter sequence and the target control parameter sequence.

7. The method according to any one of claims 1-4, characterized in that, The method further includes: Based on the thermal imaging image sequence acquired during the battery formation process, the structural design of the battery is evaluated, and a battery design analysis report is generated.

8. A battery formation control device, characterized in that, include: The acquisition module is used to acquire thermal imaging images and actual control parameters of the battery during the battery formation process. The actual control parameters include at least one of the actual current and the actual voltage; The determination module is used to determine the target control parameters of the battery at a target time based on the image acquisition time and the thermal imaging image of the battery acquired at the image acquisition time, using a pre-trained target model, wherein the target time is separated from the image acquisition time by a preset time interval. An adjustment module is used to adjust the actual control parameters to the target control parameters at the target time.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, wherein: The memory is used to store computer programs that can run on the processor; The processor is configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1-7.

10. A computer storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 7.

11. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the method of any one of claims 1 to 7.

Images