Prediction Method, Device, Equipment and Storage Medium for Inflection Point of Battery Capacity

Abstract

The present application discloses a method, apparatus, device and storage medium for predicting a battery capacity inflection point, and relates to the field of battery technology. The method discloses a method for predicting a battery capacity inflection point, including: obtaining cycle data of a battery to be predicted during a calendar aging test phase; wherein the cycle data includes a correspondence between different storage times collected during the calendar aging test phase and the maximum discharge capacity of the battery to be predicted; inputting the cycle data into a pre-trained battery capacity inflection point prediction model, and having the battery capacity inflection point prediction model predict the battery capacity inflection point of the battery to be predicted based on the cycle data. The present application uses a prediction model to predict the battery capacity inflection point based on the cycle data, which has a higher accuracy than manual prediction, and the present application is suitable for scenarios in which the location of the battery capacity inflection point is quickly obtained during the battery R&D phase, without the need for additional testing, and can provide test acceleration for the battery R&D process, significantly speeding up the R&D process.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a method, device, equipment, and storage medium for predicting a battery capacity inflection point. Background Art

[0002] In recent years, with the rapid development of new energy vehicles and the energy storage industry, the performance stability and reliability of new energy batteries have received increasing attention. Battery lifespan is a key concern for consumers, directly impacting both cost of use and customer experience. Ideally, batteries would have an infinite lifespan, but in reality, batteries experience not only capacity degradation but also capacity drop during use. Capacity drop occurs when a battery's capacity drops to a certain level (also known as reaching a capacity inflection point), then suddenly accelerates, reaching end-of-life within a relatively short period of time. This can render the battery pack inoperable and significantly impact battery lifespan and performance.

[0003] Currently, the capacity drop phenomenon not only seriously affects the user experience, but also poses certain safety risks. Therefore, how to accurately predict the battery capacity inflection point is a technical problem that needs to be solved urgently. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, equipment and storage medium for predicting the inflection point of battery capacity, aiming to solve the problem of how to accurately predict the inflection point of battery capacity.

[0005] To achieve the above objectives, the present application proposes a method for predicting the battery capacity inflection point, the method comprising:

[0006] Acquiring cycle data of the battery to be predicted during a calendar aging test phase; wherein the cycle data includes a correspondence between different storage times collected during the calendar aging test phase and a maximum discharge capacity of the battery to be predicted;

[0007] The cycle data is input into a pre-trained battery capacity inflection point prediction model, and the battery capacity inflection point prediction model predicts the battery capacity inflection point of the battery to be predicted based on the cycle data.

[0008] In one embodiment, inputting the cycle data into a pre-trained battery capacity inflection point prediction model, and predicting the battery capacity inflection point of the battery to be predicted based on the cycle data by the battery capacity inflection point prediction model, includes:

[0009] Inputting the cycle data and the auxiliary prediction information into a pre-trained battery capacity inflection point prediction model, and having the battery capacity inflection point prediction model predict the battery capacity inflection point of the battery to be predicted based on the cycle data and the auxiliary prediction information;

[0010] The auxiliary prediction information includes at least one of a storage sampling interval, a storage temperature, and a battery formula parameter.

[0011] In this embodiment, when using the model to predict the battery capacity inflection point, the influence of different storage temperatures and storage sampling intervals on batteries with different formulations is fully considered, thereby improving the rationality, reliability and versatility of the battery capacity inflection point prediction.

[0012] In one embodiment, before inputting the cycle data into a pre-trained battery capacity inflection point prediction model, the method further includes:

[0013] Obtain the maximum discharge capacity of the test battery corresponding to different storage times during the calendar aging test phase;

[0014] Determining a capacity decay curve of the test battery based on the maximum discharge capacity corresponding to different storage times of the test battery; wherein the capacity decay curve represents a corresponding relationship between different storage times and the battery state of health (SOH);

[0015] In the capacity decay curve, determining a target battery capacity inflection point of the test battery;

[0016] Constructing a training data set based on a correspondence between the capacity decay curve and the target battery capacity inflection point;

[0017] The training data set is used to train a preset candidate model, and the trained model is obtained as the battery capacity inflection point prediction model.

[0018] In this embodiment, a specific implementation method for training a battery capacity inflection point prediction model is provided. Specifically, the maximum discharge capacity corresponding to different storage times of the test battery during the calendar aging test phase is first obtained. Then, based on the maximum discharge capacity corresponding to different storage times of the test battery, the capacity decay curve of the test battery is determined. In the capacity decay curve, the target battery capacity inflection point of the test battery is determined. Then, based on the correspondence between the capacity decay curve and the target battery capacity inflection point, a training data set can be constructed. The target battery capacity inflection point is used as the predicted label of the capacity decay curve, and supervised training is performed on the candidate model to obtain the trained model as the battery capacity inflection point prediction model.

[0019] In one embodiment, before constructing the training data set based on the correspondence between the capacity decay curve and the target battery capacity inflection point, the method further includes:

[0020] Obtaining storage sampling interval, storage temperature, and battery formula parameters of the test battery during a calendar aging test phase;

[0021] The constructing of a training data set based on the correspondence between the capacity decay curve and the target battery capacity inflection point includes:

[0022] A training data set is constructed based on the corresponding relationship between the capacity decay curve and the target battery capacity inflection point, the storage sampling interval, the storage temperature and the battery formula parameters.

[0023] In this embodiment, when training the battery capacity inflection point prediction model, the influence of different storage temperatures and storage sampling intervals on batteries with different formulations is fully considered. Specifically, based on the correspondence between the capacity decay curve and the target battery capacity inflection point, the storage sampling interval, the storage temperature and the battery formulation parameters, a training data set is constructed to train the candidate model, thereby improving the rationality, reliability and versatility of the trained model in predicting the battery capacity inflection point, and making the prediction more accurate.

[0024] In one embodiment, determining the capacity decay curve of the test battery based on the maximum discharge capacity corresponding to different storage times of the test battery includes:

[0025] Calculate the ratio of the maximum discharge capacity corresponding to different storage times to the maximum discharge capacity of the initial storage as the SOH of the test battery at different storage times;

[0026] Determining a first capacity decay curve corresponding to the test battery based on the SOH of the test battery at different storage times; wherein the first capacity decay curve represents a corresponding relationship between the SOH and different storage times;

[0027] Using the box plot corresponding to the first capacity decay curve, filtering the discrete points in the first capacity decay curve to obtain a second capacity decay curve;

[0028] Based on the second capacity fade curve, a capacity fade curve of the test battery is determined.

[0029] This embodiment provides a specific implementation method for determining the capacity decay curve of a test battery. First, by calculating the ratio between the maximum discharge capacity corresponding to different storage times and the maximum discharge capacity of initial storage, a first capacity decay curve representing the SOH corresponding to different storage times is determined. A box plot is then used to filter out discrete points in the first capacity decay curve to obtain a second capacity decay curve. Based on the second capacity decay curve, the capacity decay curve of the test battery is determined. Using the box plot filtering method, the impact of discrete points on subsequent model training can be reduced, thereby reducing the interference of noise data on model training, thereby improving the prediction effect of the trained battery capacity inflection point prediction model.

[0030] In one embodiment, the filtering of discrete points in the first capacity decay curve using the box plot corresponding to the first capacity decay curve to obtain the second capacity decay curve includes:

[0031] Calculate the quartile and upper quartile corresponding to the first capacity decay curve;

[0032] Calculating an interquartile range corresponding to the first capacity decay curve based on the quartile and the upper quartile;

[0033] determining a first threshold based on the quartiles and the interquartile range;

[0034] determining a second threshold based on the upper quartile and the interquartile range;

[0035] In the first capacity decay curve, points where the SOH is less than the first threshold or the SOH is greater than the second threshold are regarded as discrete points;

[0036] The discrete points are filtered out from the first capacity decay curve, and linear interpolation filling is performed at the storage times corresponding to the discrete points to obtain the second capacity decay curve.

[0037] In this embodiment, a specific implementation method for filtering discrete points through a box plot is provided. Specifically, the quartiles and upper quartiles corresponding to the first capacity decay curve are first calculated, and the corresponding interquartile range is calculated. Then, the first threshold is calculated based on the quartiles and the interquartile range, and the second threshold is calculated based on the upper quartile and the interquartile range. The discrete points that are not between the first and second thresholds are filtered out, and then linear interpolation is used to fill in the positions of the filtered discrete points to ensure the number of points in the capacity decay curve while ensuring the smoothness of the curve, which is conducive to the subsequent effective training of the model.

[0038] In one embodiment, determining the capacity decay curve of the test battery based on the second capacity decay curve includes:

[0039] Calculating a variance value of SOH in the second capacity decay curve;

[0040] When the variance value is greater than a preset third threshold, filtering the second capacity decay curve using a one-dimensional Gaussian filter to obtain a capacity decay curve of the test battery;

[0041] When the variance value is less than or equal to the third threshold, the second capacity decay curve is filtered by using an SG filter to obtain the capacity decay curve of the test battery.

[0042] In this embodiment, after determining the second capacity decay curve, if the variance value of SOH in the second capacity decay curve is large, the second capacity decay curve can be further filtered for smoothing. Specifically, when the variance value is greater than the third threshold, using an SG filter for filtering may cause anomalies, so a one-dimensional Gaussian filter is used for filtering. When the variance value is less than or equal to the third threshold, the SG filter is used for filtering. The smoothed second capacity decay curve is helpful for subsequent effective training of the model.

[0043] In one embodiment, constructing a training data set based on the correspondence between the capacity decay curve and the target battery capacity inflection point, storage sampling interval, storage temperature, and battery formulation parameters includes:

[0044] Generate a two-dimensional array corresponding to the test battery based on the correspondence between the capacity decay curve and the target battery capacity inflection point, the storage sampling interval, the storage temperature, and the battery formula parameters; wherein the two-dimensional array includes N groups of SOH, storage sampling interval, storage temperature, battery formula parameters, and time from the inflection point corresponding to different storage times, the time from the inflection point representing the difference between different storage times and the time corresponding to the target battery capacity inflection point, and N is an integer greater than 2;

[0045] The time from the inflection point is used as a prediction label, and the N groups of data in the two-dimensional array are sequentially slid according to a preset sliding window length to generate a time series data set as the training data set.

[0046] In this embodiment, after generating a two-dimensional array corresponding to the test battery based on the relevant data of the test battery, a sliding window can be used to slide on the rows of each two-dimensional array to generate a time series data set, so as to increase the data volume of the training data set, which helps to improve the efficiency and effectiveness of model training.

[0047] In one embodiment, the candidate model uses a Transformer algorithm;

[0048] Before using the training data set to train a preset candidate model to obtain the trained model as the battery capacity inflection point prediction model, the method further includes:

[0049] A function obtained by weighted summation of a mean absolute error function and at least one regularization penalty term is used as a loss function for training the candidate model;

[0050] The regularization penalty term is used to control the range of the battery capacity inflection point predicted by the trained battery capacity inflection point prediction model.

[0051] In this embodiment, the candidate model using the Transformer algorithm has an attention mechanism, and uses time series regression with attention to slide and predict the inflection point of battery capacity, which can capture the potential relationship of battery aging and perform real-time prediction. As the test data increases, it can further help the model improve the effect; in addition, the new loss function helps to improve the prediction accuracy and robustness of the algorithm.

[0052] In one embodiment, the using the training data set to train a preset candidate model to obtain the trained model as the battery capacity inflection point prediction model includes:

[0053] Using the training data set to train a preset candidate model to obtain a trained model;

[0054] The mean absolute error function is set as the optimization target of the trained model, and at least one of the learning rate, number of iterations, batch size, dropout value, and dropout value of the fully connected layer is set as the optimization parameter of the trained model. The trained model is optimized using the Bayesian algorithm to obtain the battery capacity inflection point prediction model.

[0055] In this embodiment, the Bayesian algorithm is used to optimize the optimization parameters of the trained model to obtain the optimal model, thereby improving the prediction accuracy of the battery capacity inflection point prediction model.

[0056] In addition, to achieve the above-mentioned purpose, the present application also proposes a device for predicting the inflection point of battery capacity, the device comprising:

[0057] An acquisition module, configured to acquire cycle data of a battery to be predicted during a calendar aging test phase; wherein the cycle data includes a correspondence between different storage times collected during the calendar aging test phase and a maximum discharge capacity of the battery to be predicted;

[0058] The prediction module is used to input the cycle data into a pre-trained battery capacity inflection point prediction model, and the battery capacity inflection point prediction model predicts the battery capacity inflection point of the battery to be predicted based on the cycle data.

[0059] In addition, to achieve the above-mentioned purpose, the present application also proposes a device for predicting the inflection point of battery capacity, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for predicting the inflection point of battery capacity as described above.

[0060] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the battery capacity inflection point prediction method as described above are implemented.

[0061] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the battery capacity inflection point prediction method as described above.

[0062] One or more technical solutions proposed in this application have at least the following technical effects:

[0063] 1) Input the cycle data of the battery to be predicted during the calendar aging test phase into a pre-trained battery capacity inflection point prediction model, so that the prediction model can predict the battery capacity inflection point based on the cycle data, which is more accurate than manual prediction.

[0064] 2) By using the historical cycle data of the calendar aging stage, the battery capacity inflection point can be predicted through the model. This is suitable for application scenarios where the location of the battery capacity inflection point can be quickly obtained during the battery R&D stage. No additional testing is required, which can provide test acceleration for the battery R&D process and significantly speed up the R&D process. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0067] Figure 1 This is one of the flow charts of the method for predicting the battery capacity inflection point provided in this application;

[0068] Figure 2 This is the second flow chart of the method for predicting the battery capacity inflection point provided by this application;

[0069] Figure 3 This is the third flow chart of the method for predicting the battery capacity inflection point provided by this application;

[0070] Figure 4 This is the fourth flow chart of the method for predicting the battery capacity inflection point provided by this application;

[0071] Figure 5 This is the fifth flow chart of the method for predicting the battery capacity inflection point provided by this application;

[0072] Figure 6 This is the sixth flow chart of the method for predicting the battery capacity inflection point provided by this application;

[0073] Figure 7 This is the seventh flow chart of the method for predicting the battery capacity inflection point provided by this application;

[0074] Figure 8 This is a schematic diagram of a discharge capacity curve of a storage battery in the method for predicting the battery capacity inflection point provided in this application;

[0075] Figure 9 This is a schematic diagram of a capacity decay curve of a storage battery in the method for predicting the battery capacity inflection point provided in this application;

[0076] Figure 10 This is a flow chart of generating a training data set in the method for predicting the battery capacity inflection point provided in this application;

[0077] Figure 11 This is a flow chart of using a sliding window to generate a data set in the method for predicting the battery capacity inflection point provided by this application;

[0078] Figure 12 1 is a flow chart of Bayesian optimization of hyperparameters in the method for predicting the battery capacity inflection point provided in this application;

[0079] Figure 13 Schematic diagram of the structure of the device for predicting the inflection point of battery capacity provided by this application;

[0080] Figure 14 This is a structural diagram provided by the device for predicting the inflection point of battery capacity in this application.

[0081] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0082] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0083] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0084] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly indicate the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is two or more, unless otherwise specifically defined.

[0085] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0086] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0087] In related technologies, battery aging is divided into calendar aging and cycle aging. Calendar aging of a battery refers to the phenomenon that its performance gradually decreases during long-term storage without use; cycle aging of a battery refers to the phenomenon that its performance gradually decreases during repeated charge and discharge cycles.

[0088] It can be seen that the time consumption of calendar aging test is mainly storage rather than charge and discharge test. No charge and discharge test is performed during storage, and there is no lithium ion deintercalation and intercalation process. Many curves required to predict the battery capacity inflection point in related technologies (such as capacity differential) do not have a complete life cycle in calendar aging test.

[0089] In addition, the calendar aging test is to characterize the capacity by performing 1 to 3 cycles after storage. Since the storage time may be of variable length, the test interval after each storage may also be of variable length. During the entire storage battery test cycle, the total number of times the capacity needs to be measured is the number of storage times plus the first measurement, and the total number is relatively small. Because each storage requires human intervention, the relatively small number of measurements is objectively unavoidable, while the number of cycles in the cyclic aging test is very large (lithium-ion batteries generally have more than 500 cycles), and the number of cycles is increasing and equally spaced. The technology for predicting the inflection point of battery capacity in related technologies requires conducting aging test experiments under different battery capacity influencing parameters and calculating model parameters, which takes a long time and is not suitable for quickly obtaining the inflection point position of the battery during the battery research and development stage.

[0090] Furthermore, the techniques used in related art to predict the battery capacity inflection point fail to consider the impact of battery storage temperature on the capacity inflection point, nor do they consider the impact of different battery formulations on the capacity inflection point. The choice of positive electrode material directly affects the battery's energy density, cycle stability, and safety. Different positive electrode materials undergo different chemical reactions during the charge and discharge process, thus affecting the battery's lifespan. The electrolyte acts as an ion transporter within the battery, and its type and properties directly affect the battery's cycle performance and lifespan. Different electrolytes have varying ion conductivity, chemical stability, and thermal stability, thus affecting the battery's charge and discharge efficiency and cycle life. Adjusting the ratio of positive and negative electrode materials and changing the electrolyte composition and concentration can all have a positive impact on the battery's lifespan. Furthermore, at high temperatures, the activity of the chemical substances within the battery increases, the frequency of molecular collisions increases, and the reaction rate accelerates. This accelerates the consumption and corrosion of the battery's internal substances, leading to aging and damage to the battery plates, thereby shortening the battery's lifespan. Furthermore, high temperatures can cause the evaporation of chemical substances within the battery and the expansion of the electrolyte liquid, further damaging the battery's structure and performance.

[0091] In response to the above technical problems, the present application provides a method for predicting the inflection point of battery capacity, aiming to find a method for accurately predicting the position of the inflection point of battery capacity with different formulations and storage temperatures without conducting additional testing experiments.

[0092] It should be noted that the execution subject of the embodiments of the present application can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions, a battery capacity inflection point prediction device, etc. The following uses the battery capacity inflection point prediction device as an example to illustrate the embodiments of the present application and the following embodiments.

[0093] The present application embodiment provides a method for predicting the inflection point of battery capacity. Figure 1 , Figure 1 This is one of the flow charts of the method for predicting the battery capacity inflection point provided in this application.

[0094] In this embodiment, the method for predicting the battery capacity inflection point includes steps S101 to S102:

[0095] Step S101, obtaining cycle data of the battery to be predicted during the calendar aging test phase;

[0096] The cycle data includes the corresponding relationship between different storage times collected during the calendar aging test phase and the maximum discharge capacity of the battery to be predicted.

[0097] It should be noted that during the calendar aging test phase, the maximum discharge capacity mentioned above is derived from a cycle test performed by the operator after each storage cycle to calibrate the capacity. This cycle test data only includes a maximum of three cycles of charge and discharge (charge and discharge process: rest → discharge → charge → rest → discharge). The maximum discharge capacity of the second cycle is generally used, and this value is considered to be the most accurate representation of the actual usable capacity of the stored battery. Each storage cycle is accompanied by a cycle test, resulting in a point data point.

[0098] Step S102 : inputting the cycle data into a pre-trained battery capacity inflection point prediction model, and having the battery capacity inflection point prediction model predict the battery capacity inflection point of the battery to be predicted based on the cycle data.

[0099] Specifically, by utilizing the existing cycle data of the battery to be predicted during the calendar aging test phase and inputting it into a trained battery capacity inflection point prediction model, the battery capacity inflection point prediction model can first determine the SOH (State of Health) corresponding to different storage times based on the correspondence between different storage times and the maximum discharge capacity in the cycle data, and then predict the battery capacity inflection point of the battery to be predicted.

[0100] Among them, SOH is used to measure the degree of battery degradation and remaining service life, usually expressed as a percentage.

[0101] In some embodiments, the battery capacity inflection point may be output as a specific time or as a time from the inflection point (Day to Knee Point: DTK). The specific time corresponding to the battery capacity inflection point may also be derived from the DTK.

[0102] For example, if the battery capacity inflection point prediction model outputs a DTK of 45 days, it is considered that the battery capacity will reach the inflection point 45 days later. The current date plus 45 days is considered to be the specific date corresponding to the battery capacity inflection point.

[0103] In the battery capacity inflection point prediction method provided in the embodiment of the present application, the cycle data of the battery to be predicted in the calendar aging test stage is input into a pre-trained battery capacity inflection point prediction model, so that the prediction model predicts the battery capacity inflection point based on the cycle data, which is more accurate than manual prediction; in addition, the present application uses the cycle data of the calendar aging stage obtained historically to predict the battery capacity inflection point through the model, which is suitable for application scenarios in which the battery capacity inflection point position is quickly obtained in the battery research and development stage, without the need for additional testing, and can provide test acceleration for the battery research and development process, significantly speeding up the research and development process.

[0104] The following describes a specific implementation method for predicting the battery capacity inflection point by referring to the auxiliary prediction information in combination with feasible implementation methods:

[0105] In one possible implementation, Figure 1 Based on the corresponding embodiment, refer to Figure 2 , Figure 2 This is the second flow chart of the method for predicting the battery capacity inflection point provided by the present application. The above step S102 includes the following steps S1021:

[0106] Step S1021, inputting the cycle data and the auxiliary prediction information into a pre-trained battery capacity inflection point prediction model, and having the battery capacity inflection point prediction model predict the battery capacity inflection point of the battery to be predicted based on the cycle data and the auxiliary prediction information;

[0107] The auxiliary prediction information includes at least one of a storage sampling interval, a storage temperature, and a battery formula parameter.

[0108] It should be noted that the storage sampling interval refers to the difference in days between two storage days, for example, 9 days; the storage temperature is, for example, 60°C; the battery formula parameters can be multiple, for example, including the physical and chemical content of the positive electrode, the electrolyte formula and the binder content, etc., which are only used as examples in this application and are not limited to this.

[0109] In the embodiment of the present application, when using the model to predict the battery capacity inflection point, the influence of different storage temperatures and storage sampling intervals on batteries with different formulations is fully considered, thereby improving the rationality, reliability and versatility of the battery capacity inflection point prediction.

[0110] The following describes how to train a battery capacity inflection point prediction model based on feasible implementation methods:

[0111] In one possible embodiment, referring to Figure 3 , Figure 3 This is the third flow chart of the method for predicting the battery capacity inflection point provided by the present application. Before the above step S102, the following steps S301 to S305 are also included:

[0112] Step S301 , obtaining the maximum discharge capacity of the test battery corresponding to different storage times during the calendar aging test phase.

[0113] In some embodiments, the second cycle data may be selected, and the maximum discharge capacity corresponding to the data at different storage times may be obtained, for example, 0.019 Ah.

[0114] Step S302, determining a capacity decay curve of the test battery based on the maximum discharge capacity corresponding to different storage times of the test battery;

[0115] The capacity decay curve represents the corresponding relationship between different storage times and SOH.

[0116] It should be noted that the capacity decay curve can also be called the SOH curve.

[0117] Step S303 : determining a target battery capacity inflection point of the test battery in the capacity decay curve.

[0118] Step S304 : constructing a training data set based on the corresponding relationship between the capacity decay curve and the target battery capacity inflection point.

[0119] In some embodiments, multiple people can independently mark potential inflection points on the SOH curve, and a multi-vote process is used to determine the final inflection point location. The inflection point locations of parallel samples of the same formulation are kept as close as possible to ensure a certain degree of label consistency. This is because different people may define the inflection point locations of the same SOH curve differently, which is a result of human error. The DTK value for each point is ultimately calculated and used as the predicted label by the regression algorithm.

[0120] Step S305 , using the training data set to train a preset candidate model, and obtaining the trained model as the battery capacity inflection point prediction model.

[0121] In an embodiment of the present application, a specific implementation method for training a battery capacity inflection point prediction model is provided. Specifically, the maximum discharge capacity corresponding to different storage times of the test battery in the calendar aging test phase is first obtained, and then the capacity decay curve of the test battery is determined based on the maximum discharge capacity corresponding to different storage times of the test battery. In the capacity decay curve, the target battery capacity inflection point of the test battery is determined. Then, based on the correspondence between the capacity decay curve and the target battery capacity inflection point, a training data set can be constructed. The target battery capacity inflection point is used as the prediction label of the capacity decay curve, and a supervised training is performed on the candidate model to obtain the trained model as the battery capacity inflection point prediction model.

[0122] The following describes how to construct a training dataset in detail, combined with feasible implementation methods:

[0123] In one possible implementation, Figure 3 Based on the corresponding embodiment, refer to Figure 4 , Figure 4 This is the fourth flow chart of the method for predicting the battery capacity inflection point provided by the present application. Before the above step S304, the following step S306 is also included:

[0124] Step S306 , obtaining the storage sampling interval, storage temperature, and battery formula parameters of the test battery during the calendar aging test phase.

[0125] It should be noted that this application does not limit step S306 to be performed only before step S304. Figure 4 The order of executing the steps in the embodiment is merely an example of a feasible embodiment and is not limited in this application.

[0126] Accordingly, the above step S304 includes step S3041-1:

[0127] Step S3041-1: construct a training data set based on the corresponding relationship between the capacity decay curve and the target battery capacity inflection point, the storage sampling interval, the storage temperature and the battery formula parameters.

[0128] In the embodiment of the present application, when training the battery capacity inflection point prediction model, the influence of different storage temperatures and storage sampling intervals on batteries with different formulations is fully considered. Specifically, based on the correspondence between the capacity decay curve and the target battery capacity inflection point, the storage sampling interval, the storage temperature and the battery formulation parameters, a training data set is constructed to train the candidate model, thereby improving the rationality, reliability and versatility of the trained model in predicting the battery capacity inflection point, and making the prediction more accurate.

[0129] In another feasible implementation, the above step S3041-1 includes the following steps:

[0130] Generate a two-dimensional array corresponding to the test battery based on the correspondence between the capacity decay curve and the target battery capacity inflection point, the storage sampling interval, the storage temperature, and the battery formula parameters; wherein the two-dimensional array includes N groups of SOH, storage sampling interval, storage temperature, battery formula parameters, and time from the inflection point corresponding to different storage times, the time from the inflection point representing the difference between different storage times and the time corresponding to the target battery capacity inflection point, and N is an integer greater than 2;

[0131] The time from the inflection point is used as a prediction label, and the N groups of data in the two-dimensional array are sequentially slid according to a preset sliding window length to generate a time series data set as the training data set.

[0132] Specifically, each test battery corresponds to a two-dimensional array, where each column is a model input dimension / feature and each row is the stored data of the battery.

[0133] It should be noted that the battery storage temperature is the ambient temperature set before the calendar aging test begins. This temperature remains unchanged during the test. The storage sampling interval is actually the current storage time minus the next storage time.

[0134] For example, the first storage test lasts 8.5 days, during which the first capacity is measured; the second storage test lasts 15.5 days, during which the second capacity is measured; and the third storage test lasts 26 days, during which the third capacity is measured. The sampling intervals during these three storage tests are 7 and 10.5 days, respectively. After these three storage tests, three discharge capacity values are obtained and calculated as the SOH. The same applies to the remaining values. Since there is no further storage at the final interval, the interval is set to 0, resulting in the final interval values of 7, 10.5, 9, 15, 19, and 0 days. The data for each battery is a two-dimensional array, the structure of which is shown in Table 1.

[0135] Table 1 Two-dimensional array corresponding to the battery

[0136]

[0137] When generating a time series dataset, first traverse the two-dimensional array of all batteries, then use DTK as the label for the regression algorithm and use a sliding window length of 3 to generate the dataset:

[0138] 1) During the first slide, the label is DTK 45, and the first sequence is obtained, whose content is the data in the 1st, 2nd, and 3rd rows of the two-dimensional array.

[0139] 2) During the second slide, the label is DTK 36, and the second sequence is obtained, whose content is the data in the 2nd, 3rd, and 4th rows of the two-dimensional array.

[0140] 3) During the third slide, the label is DTK 21, and the third sequence is obtained, whose content is the data in rows 3, 4, and 5 of the two-dimensional array. And so on until the inflection point.

[0141] It should be noted that the above sliding window length can be set according to actual conditions.

[0142] In some embodiments, if the two-dimensional data is too scarce and the quality is uneven, the sliding window can continue to slide after the inflection point, but the data after the inflection point cannot be used when predicting the inflection point, nor can the prediction results after the inflection point be used (meaningless). It is only used to verify the model.

[0143] In an embodiment of the present application, after generating a two-dimensional array corresponding to the test battery based on the relevant data of the test battery, a sliding window can be used to slide on the rows of each two-dimensional array to generate a time series data set, so as to increase the data volume of the training data set, which helps to improve the efficiency and effectiveness of model training.

[0144] In some embodiments, the candidate model may use a Transformer algorithm. A specific implementation method for determining the loss function of the candidate model is provided. Specifically, the following steps are further included before step S305:

[0145] A function obtained by weighted summation of a mean absolute error function and at least one regularization penalty term is used as a loss function for training the candidate model;

[0146] The regularization penalty term is used to control the range of the battery capacity inflection point predicted by the trained battery capacity inflection point prediction model.

[0147] It should be noted that the Transformer algorithm is a neural network model based on the self-attention mechanism, which is mainly used to process sequence data. This application may use the multivariate time series transformer, referred to as TST, instead of the original Transformer.

[0148] In some embodiments, the mean absolute error function is, for example:

[0149] .

[0150] in, Characterize the predicted DTK value, Characterize the true DTK value, Characterize the total number of samples.

[0151] In some embodiments, the regularization penalty term includes, for example:

[0152] .

[0153] Specifically, a custom function is selected as the loss function of the training model, which is the weighted sum of the three parts mentioned above. The mean absolute error (MAE) is chosen as the loss function when training the model, mainly because MAE is less sensitive to outliers. When there is a lot of noise and uneven storage time in the data, which leads to a large error in the predicted label (the number of days from the inflection point), using MAE as the loss function can make the model easier to fit. This is because MAE does not amplify the impact of outlier errors on the total loss like the root mean square error (RMSE).

[0154] At the same time, a regularization penalty term is embedded in the neural network training to observe the effect of the training validation set. When the value is less than 0 or greater than 200 (the interval [0, 200] should be selected based on the data, and is only used as an example), a regularization term is added to the MAE. By introducing the α and β parameters, the weight of the regularization term is dynamically controlled. ReLU (Rectified Linear Unit) is a widely used activation function, especially in deep learning and neural networks.

[0155] In an embodiment of the present application, the candidate model using the Transformer algorithm has an attention mechanism, and uses time series regression with attention to slide and predict the inflection point of battery capacity, which can capture the potential relationship of battery aging and perform real-time prediction. As the test data increases, it can further help the model improve the effect; in addition, the new loss function helps to improve the prediction accuracy and robustness of the algorithm.

[0156] In other embodiments, a specific implementation method for further optimizing the battery capacity inflection point prediction model is provided. Specifically, the above step S305 includes the following steps:

[0157] Using the training data set to train a preset candidate model to obtain a trained model;

[0158] The mean absolute error function is set as the optimization target of the trained model, and at least one of the learning rate, number of iterations, batch size, dropout value, and dropout value of the fully connected layer is set as the optimization parameter of the trained model. The trained model is optimized using the Bayesian algorithm to obtain the battery capacity inflection point prediction model.

[0159] It's important to note that Bayesian optimization (also known as Bayesian hyperparameter optimization) is a method used in machine learning to find the optimal combination of hyperparameters. Hyperparameters are parameters that need to be manually set before training a machine learning model. They are not adjusted by the optimization algorithm during training, but are determined by developers or researchers based on experience, experimentation, or automated tuning methods.

[0160] It should also be noted that the mean absolute error function in this embodiment is similar to the formula of the mean absolute error function in the above embodiment. The reason for using MAE here is the same as in the above embodiment, but the role of this error and loss function is completely different.

[0161] In some embodiments, when using the Bayesian algorithm for optimization, the number of optimization iterations can also be set. The more times, the slower the optimization process, but better parameters may be found. The range of parameters should be narrowed here, otherwise the time cost will be huge, especially for large data sets.

[0162] In an embodiment of the present application, a Bayesian algorithm is used to optimize the optimization parameters of the trained model in order to obtain the optimal model. Specifically, the optimal hyperparameters of the model are quickly found within a limited time, and the final model is trained using the hyperparameters, which can effectively improve the prediction accuracy of the battery capacity inflection point prediction model.

[0163] The following describes how to determine the capacity decay curve of a test battery in conjunction with feasible implementation methods:

[0164] In one possible implementation, Figure 3 Based on the corresponding embodiment, refer to Figure 5 , Figure 5 This is the fifth flow chart of the method for predicting the battery capacity inflection point provided by this application. The above step S302 includes the following steps S3021 to S3024:

[0165] Step S3021 , calculating the ratio of the maximum discharge capacity corresponding to different storage times to the maximum discharge capacity of the initial storage as the SOH of the test battery at different storage times.

[0166] Step S3022: determining a first capacity decay curve corresponding to the test battery based on the SOH of the test battery at different storage times;

[0167] The first capacity decay curve represents the corresponding relationship between the SOH and different storage times.

[0168] Step S3023 : Using the box plot corresponding to the first capacity decay curve, filter the discrete points in the first capacity decay curve to obtain a second capacity decay curve.

[0169] Step S3024: determining a capacity decay curve of the test battery based on the second capacity decay curve.

[0170] It should be noted that a box plot, also known as a box and whisker plot, is a statistical chart used to display the dispersion of a set of data. It describes the distribution of a data set using five key values: minimum value, first quartile Q1, median Q2, third quartile Q3, and maximum value.

[0171] It should also be noted that the above-mentioned outliers are individual values in a set of battery data or performance parameters that are significantly different from other data or parameters. These values may be caused by measurement errors, improper operation, abnormalities of the battery itself, or performance under specific conditions.

[0172] In an embodiment of the present application, a specific implementation method for determining the capacity decay curve of a test battery is provided. First, by calculating the ratio between the maximum discharge capacity corresponding to different storage times and the maximum discharge capacity of initial storage, a first capacity decay curve representing the SOH corresponding to different storage times is determined. A box plot is then used to filter out discrete points in the first capacity decay curve to obtain a second capacity decay curve. Based on the second capacity decay curve, the capacity decay curve of the test battery is determined. By filtering with a box plot, the influence of discrete points on subsequent model training can be reduced, thereby reducing the interference of noise data on model training, thereby improving the prediction effect of the trained battery capacity inflection point prediction model.

[0173] In another possible embodiment, referring to Figure 6 , Figure 6 This is the sixth flow chart of the method for predicting the battery capacity inflection point provided by this application. The above step S3023 includes the following steps S3023-1 to S3023-6:

[0174] Step S3023-1: Calculate the quartile and upper quartile corresponding to the first capacity decay curve.

[0175] Step S3023-2: Calculate the interquartile range corresponding to the first capacity decay curve based on the quartile and the upper quartile.

[0176] In some embodiments, the interquartile range IQR in step S3023-2 can be calculated by the following formula: IQR=Q3-Q1; wherein, Q3 represents the upper quartile, Q1 represents the upper quartile, and Q1 and Q3 can be calculated using the np.percentile function from the NumPy library of Python, which is widely used in vectorized calculations.

[0177] Step S3023-3: Determine a first threshold based on the quartiles and the interquartile range.

[0178] Step S3023-4: Determine a second threshold based on the upper quartile and the interquartile range.

[0179] It should be noted that this application does not limit the order of executing step S3023-3 and step S3023-4, that is, the first threshold can be determined first, the second threshold can be determined first, or the first threshold and the second threshold can be determined in parallel.

[0180] In some embodiments, the first threshold value can be determined in step S3023-3 by the following formula:

[0181] First threshold = Q1-k*IQR;

[0182] The second threshold value in step S3023-4 can be determined by the following formula:

[0183] Second threshold = Q3 + k*IQR;

[0184] Here, k represents the weight. The larger k is, the more discrete points are filtered out. It can usually be set to an empirical value, for example, 1.5.

[0185] Step S3023-5: In the first capacity decay curve, points where the SOH is less than the first threshold or the SOH is greater than the second threshold are taken as discrete points.

[0186] Step S3023-6: Filter out the discrete points from the first capacity decay curve, and perform linear interpolation filling at the storage times corresponding to the discrete points to obtain the second capacity decay curve.

[0187] It should be noted that linear interpolation is a mathematical method used to estimate or construct a new data point between two known data points, whose value is calculated based on the values of the two known points and their relative positions through a linear relationship (i.e. a straight line).

[0188] In an embodiment of the present application, a specific implementation method for filtering discrete points through a box plot is provided. Specifically, the quartiles and upper quartiles corresponding to the first capacity decay curve are first calculated, and the corresponding interquartile range is calculated. Then, the first threshold is calculated based on the quartiles and the interquartile range, and the second threshold is calculated based on the upper quartile and the interquartile range. The discrete points that are not between the first threshold and the second threshold are filtered out, and then linear interpolation is used to fill in the positions of the filtered discrete points to ensure the number of points in the capacity decay curve while ensuring the smoothness of the curve, which is helpful for the subsequent effective training of the model.

[0189] In another feasible implementation, the above step S3024 includes the following steps:

[0190] The variance value of SOH in the second capacity decay curve is calculated.

[0191] When the variance value is greater than a preset third threshold, the second capacity decay curve is filtered by using a one-dimensional Gaussian filter to obtain the capacity decay curve of the test battery.

[0192] When the variance value is less than or equal to the third threshold, the second capacity decay curve is filtered by using an SG filter to obtain the capacity decay curve of the test battery.

[0193] It should be noted that the SG filter, full name Savitzky-Golay filter, is a filtering method based on polynomial least squares fitting in the time domain.

[0194] In an embodiment of the present application, after determining the second capacity decay curve, if the variance value of the SOH in the second capacity decay curve is large, the second capacity decay curve can be further filtered for smoothing. Specifically, when the variance value is greater than the third threshold, filtering using an SG filter may cause anomalies, so a one-dimensional Gaussian filter is used for filtering. When the variance value is less than or equal to the third threshold, the SG filter is used for filtering. The smoothed second capacity decay curve is helpful for subsequent effective model training.

[0195] The following example illustrates the method for predicting the battery capacity inflection point provided by the embodiment of the present application. It is specifically implemented by the following steps: obtaining the maximum discharge capacity of the battery after storage → calculating the capacity decay curve (SOH curve) of the battery → using a variety of data processing technologies to process the SOH curve and mark the position of the battery capacity inflection point → obtaining the battery's storage temperature, storage sampling interval, positive and negative electrode formula and other design information, and combining SOH to construct a complete data set → using a sliding window to slide on the SOH curve to generate a time series data set → using the Transformer algorithm to model the data, and the label of the model is how many storage days are left from the current storage day to the inflection point (that is, the time from the inflection point) → using five-fold cross-validation to evaluate the model → finding the optimal model hyperparameters based on Bayesian hyperparameter optimization technology.

[0196] In addition, the system-of-hours (SOH) curve can also be processed to improve data quality and enhance the robustness of the model: obtain the maximum discharge capacity of the battery after storage → calculate the battery's capacity decay curve (SOH curve) → use box plots to filter outliers on the SOH curve → use linear interpolation techniques to fill in the filtered SOH curve points → use SG filters and Gaussian filters to smooth the SOH curve to obtain the final SOH curve for constructing a complete dataset. Finally, to improve the model's robustness to abnormal data, a new loss function was developed. The improved loss function can help the model improve its prediction results.

[0197] Figure 7 This is the seventh flow chart of the method for predicting the battery capacity inflection point provided by this application, such as Figure 7 As shown, it includes steps S701 to S706:

[0198] Step S701 , reading cycle data and obtaining the maximum discharge capacity of the battery during the discharge phase.

[0199] Specifically, the maximum discharge capacity is derived from a cycle test performed by the operator after each storage cycle to calibrate the capacity. This cycle test covers a maximum of three cycles of charge and discharge (charge and discharge process: rest → discharge → charge → rest → discharge). The maximum discharge capacity of the second cycle is typically used, and this value represents the actual usable capacity of the stored battery as determined by the battery cell engineer. Each storage cycle is accompanied by a cycle test, resulting in a single point of data.

[0200] For example, to obtain the maximum discharge capacity of the battery expressed in DQ, the calculation formula is: DQ=max(abs(Qs));

[0201] The DQ in the formula is defined as the maximum capacity of the second discharge phase when the operator performs a cycle test after the battery is stored. Qs is the capacity sequence of the second discharge phase of the cycle test. The abs function represents the absolute value, and the max function represents the maximum value. The length of the capacity sequence depends on the rated capacity, discharge current, discharge time, and sampling frequency of the battery. After being processed by the max function in this step, each stored cycle sequence is converted into a discharge capacity. Within a storage life cycle, the data of all storage points constitute a capacity curve, such as Figure 8 As shown, Figure 8 It is a schematic diagram of the discharge capacity curve of a storage battery in the method for predicting the battery capacity inflection point provided in this application.

[0202] It should be noted that the storage time here is equivalent to the storage days, both of which represent the cumulative total number of days from the start of storage to the end of this storage. The storage time of the first point is 0 days. The first one is only used as a capacity benchmark and can be discarded in the SOH curve.

[0203] Step S702 : Calculate the SOH curve and process it. Multiple people mark and vote to determine the number of days at the inflection point and calculate the DTK value.

[0204] Specifically, the maximum discharge capacity of each storage is calculated, and the SOH is calculated with the first initial capacity. All storages constitute the SOH curve. A box plot is used to filter outliers in the SOH curve, and then linear interpolation is used to fill the filtered SOH curve. Finally, the SG filter is used to smooth the SOH curve.

[0205] For the SOH curve, multiple people independently mark potential inflection points. The final inflection point location is determined through multi-voting. The inflection points of parallel samples with the same formulation are kept as close as possible to ensure label consistency. This is because different people may define the inflection point location differently for the same SOH curve, which is due to human error. Finally, the DTK value for each point is calculated and used as the predicted label for the regression algorithm.

[0206] For example, the formula for calculating SOH is: SOH=DQ / DQ0, where DQ represents the discharge capacity and DQ0 represents the first discharge capacity.

[0207] The steps for filtering discrete points of the SOH curve in the box plot are as follows:

[0208] 1) Calculate the lower quartile Q1 and Q3 (upper quartile); then calculate the IQR (interquartile range), where IQR = Q3 - Q1.

[0209] 2) Calculate the outlier detection range, usually from Q1 - k * IQR to Q3 + k * IQR. That is, when SOH > Q3 + k * IQR or SOH < Q1 - k * IQR, it is an outlier. Here, k = 1.5 is set.

[0210] 3) Identify and mark the index positions of the outliers, and filter out the outliers through the indexes.

[0211] 4) Set the filtered outliers to NA and fill them with linear interpolation.

[0212] In some embodiments, the fitting and smoothing process is optional. It aims to make the curve smoother while ensuring the curve trend remains unchanged. Its implementation is as follows: when the variance value of the SOH curve exceeds the variance threshold, a 1D Gaussian filter is used, and when it is relatively small, a Savitzky - Golay filter is used. They are calculated using the gaussian_filter1d function from the scipy.ndimage library and the savgol_filter function from the scipy.signal library in Python respectively. The number of points on the processed SOH curve does not change, so there is no need to perform interpolation filling again. As Figure 9 shown, Figure 9 is a schematic diagram of the capacity decay curve of a certain storage battery in the method for predicting the inflection point of the battery capacity provided by this application.

[0213] Among them, the outliers have been filtered. Suppose the position of the inflection point finally confirmed manually is 71.0 days, which is framed by a rectangular box. Next, calculate the DTK value of each point before the inflection point (including the inflection point) to the inflection point.

[0214] The DTK value is defined as: how many more storage days are needed for the current storage days to reach the inflection point position; its calculation formula is: DTK = storage time at the inflection point position (days) - storage time of each point (days). For Figure 9 , there are 6 points before the inflection point, and the DTK values are respectively: 71 - 8.5 (62.5 days), 71 - 15.5 (55.5 days), 71 - 26 (45 days), 71 - 35 (36 days), 71 - 50 (21 days), 71 - 71 (0 days).

[0215] It should be noted that the above variance threshold depends on the specific data set. The threshold set in this embodiment can be 0.09.

[0216] It's also worth noting that the input parameters of the savgol_filter function are x (the SOH curve), window (the window width), and polyorder (the order). The window width is calculated as follows: window = min(len(x), 15), and polyorder is set to 3. The min function in this formula selects the minimum between two numbers, and the len function represents the number of points in the SOH curve, that is, the length of the curve formed by the discrete points.

[0217] The input parameters of the gaussian_filter1d function are input (the SOH curve) and sigma (which controls the width of the Gaussian kernel). A larger sigma results in a more smoothing effect. In this example, sigma is set to 0.45.

[0218] Step S703 , obtaining design information of the battery, such as storage temperature, storage sampling interval, positive and negative electrode formula, etc.

[0219] Specifically, the storage temperature of each battery is obtained. The storage sampling interval is the difference in days between two storage days. Combined with the recipe information, each battery is converted into a two-dimensional array, where each column is a model input dimension / feature and each row is a storage of the battery.

[0220] For example, the two-dimensional array is, for example, Table 1. Table 1 is only an example because the formula ingredients are usually confidential. However, the solution of this application is not limited to a specific formula and is therefore also applicable to other calendar-aged and cycle-aged batteries. In actual applications, the number of storage times may be between 3 and 50 times (considering the balance between the accuracy of capacity calibration and labor costs). The number of storage times should not be less than the sliding window length mentioned above. The sliding window length should be continuously tried and adjusted as needed. If the data and hardware allow, the longer the sliding window length, the more information it contains, and the better the effect may be.

[0221] The data listed in Table 1 only shows 6 storages, in which the storage temperature and formula are fixed values. Because the temperature and formula remain unchanged during the storage process. It is mainly used to assist model prediction. In addition to the positive electrode physical and chemical content, electrolyte, binder content provided in Table 1, there may also be negative electrode physical and chemical content, diaphragm, battery cell type and other formula parameters, which are not restricted in this application. Here are the effective parameters obtained after preliminary screening by battery experts. Among them, the positive electrode physical and chemical content can be divided into multiple more detailed data, such as the carbon content and water content of the battery positive electrode, and other formulas are similar.

[0222] Step S704 : Using the DTK value as the prediction label, a sliding window is used to slide on the SOH curve to generate a time series data set.

[0223] Specifically, based on the M1 two-dimensional arrays obtained above (where M1 is the number of batteries), a sliding window is used to slide across the rows of each two-dimensional array to generate a time series dataset. For example, if the sliding window length is 3, and the window slides one point at a time, the battery data must contain at least 3 points to be used. The shape of the time series dataset is: (number of records, number of feature dimensions, sequence length), where the number of records is the total number of records generated by all batteries after the sliding window operation, the number of feature dimensions is the number of features including all inputs such as temperature, SOH, and recipe, and the sequence length is the size of the sliding window.

[0224] For example, Figure 10 This is a flow chart of generating a training data set in the method for predicting the battery capacity inflection point provided in this application, such as Figure 10 As shown, the core process of this step is to generate a time series regression data set, which specifically includes steps S1001 to S1004:

[0225] Step S1001: traverse the two-dimensional array of all batteries, the structure of which is shown in Table 1 above.

[0226] Step S1002: Sliding window generates a sequence.

[0227] Specifically, DTK is used as the label of the regression algorithm and a sliding window length of 3 is used to generate the data set. Figure 11 This is a flow chart of using a sliding window to generate a data set in the method for predicting the battery capacity inflection point provided by this application, such as Figure 11 As shown, each time a dotted line connects three data points, it represents a slide. The following is a detailed description:

[0228] 1) During the first slide, the label is DTK 45, and the first sequence is obtained, whose content is the data in the 1st, 2nd, and 3rd rows of the two-dimensional array.

[0229] 2) During the second slide, the label is DTK 36, and the second sequence is obtained, whose content is the data in the 2nd, 3rd, and 4th rows of the two-dimensional array.

[0230] 3) During the third slide, the label is DTK 21, and the third sequence is obtained, whose content is the data in rows 3, 4, and 5 of the two-dimensional array. And so on, until the inflection point.

[0231] Step S1003: Merge the data generated by sliding each battery into a set. Specifically, merge the data generated by sliding each battery into a set.

[0232] Step S1004: Divide the model data set into a training set, a validation set, and a test set in a ratio of 6:2:2.

[0233] Step S705: Use the Transformer algorithm to build a model and predict how many storage days are left from the current storage day to the inflection point.

[0234] Specifically, the Transformer is a very popular deep learning algorithm that can be used to capture the underlying relationships in complex time series. Based on this, a time series regression model is built to predict a DTK value based on three data points for each battery. Because the time window length is three, three data points are required for each prediction.

[0235] For example, when using the Transformer algorithm to build a model, it is only necessary to use the training set divided in step S1004 to train the model, the validation set to verify the model, and the test set to test the final effect of the model.

[0236] The loss function for the training model is a custom function, which is the weighted sum of the following three parts:

[0237] ;

[0238] .

[0239] Step S706: Find the optimal model hyperparameters using Bayesian hyperparameter optimization technology.

[0240] Specifically, after the modeling is completed, based on the Bayesian optimization method, the optimal hyperparameters of the model are quickly found within a limited time, and the final model is trained using the hyperparameters.

[0241] For example, this step uses Bayesian techniques to optimize hyperparameters in order to obtain the best model. Figure 12 This is a flow chart of Bayesian optimization of hyperparameters in the battery capacity inflection point prediction method provided in this application, such as Figure 12 As shown, the following steps are included:

[0242] Step S1201: construct a Bayesian optimization framework.

[0243] Specifically, the open source framework optuna is used as the implementation of Bayesian optimization technology.

[0244] Step S1202, setting the optimization target: validation set evaluation error.

[0245] Specifically, the error is set as the optimization target, and the error calculation formula is:

[0246] .

[0247] It should be noted that the reason for using MAE is the same as that for loss functions. However, the error and loss function have completely different functions.

[0248] Among them, MAE is used to measure the mean absolute error between the predicted value and the true value. The smaller the MAE, the better the model. is the predicted value, is the true value, is the total number of samples.

[0249] Step S1203: Set the parameters and ranges to be optimized.

[0250] Specifically, the parameters that need to be optimized in the model are: learning rate, number of iterations, batch size, dropout value, and fully connected layer dropout value.

[0251] Step S1204, set the number of iterations and start training the model.

[0252] Specifically, the number of optimization iterations is set. A higher number of iterations results in a slower optimization process, but may lead to better parameters. The range of parameters should be narrowed, otherwise the time cost will be enormous, especially for large datasets.

[0253] It's important to note that the learning rate and number of iterations have a significant impact. Their values can range from 0.0005 to 0.004 and 100 to 150, respectively. Setting appropriate ranges can speed up optimization. After finding the optimal parameters, retrain the model to obtain the optimal model. For deployment, the full dataset can be used for training the model, without splitting it into training and test sets.

[0254] In the embodiments of the present application, there are at least the following beneficial effects:

[0255] 1) Fully consider the impact of different temperatures on batteries with different formulas, ensure the rationality, reliability and versatility of the prediction of battery inflection points, provide test acceleration for the battery R&D process, and significantly speed up the R&D process, that is, the battery does not need to wait for storage.

[0256] 2) Using time-series regression with attention to slide the prediction inflection point can capture the potential relationship of battery aging and enable real-time prediction. As the test data increases, it can further help the model improve its performance.

[0257] 3) Data quality is crucial for small sample sizes. Considering measurement errors during battery testing, and the fact that storage testing involves operators placing batteries in a designated area, removing them after the storage time expires, and then performing cycle testing to characterize capacity, these cycles can include issues such as non-standard operation, varying measurement accuracy between machines, and varying storage intervals between operators. Data cleaning and smoothing can reduce the impact of noisy data on the model, and a new loss function can improve the algorithm's predictive accuracy and robustness.

[0258] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for predicting the battery capacity inflection point of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0259] This application also provides a device for predicting the inflection point of battery capacity. Figure 13 , Figure 13 : is a schematic diagram of the structure of the device for predicting the battery capacity inflection point provided by the present application, the device for predicting the battery capacity inflection point comprises:

[0260] An acquisition module 1301 is configured to acquire cycle data of a battery to be predicted during a calendar aging test phase; wherein the cycle data includes a correspondence between different storage times collected during the calendar aging test phase and a maximum discharge capacity of the battery to be predicted;

[0261] The prediction module 1302 is configured to input the cycle data into a pre-trained battery capacity inflection point prediction model, and have the battery capacity inflection point prediction model predict the battery capacity inflection point of the battery to be predicted based on the cycle data.

[0262] The device for predicting the battery capacity inflection point provided in the present application adopts the method for predicting the battery capacity inflection point in the above embodiment, and can solve the problem of how to accurately predict the battery capacity inflection point.

[0263] Compared with the related art, the beneficial effects of the battery capacity inflection point prediction device provided in the present application are the same as the beneficial effects of the battery capacity inflection point prediction method provided in the above embodiment, and the other technical features in the battery capacity inflection point prediction device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0264] The present application provides a device for predicting a battery capacity inflection point, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for predicting a battery capacity inflection point in any of the above-mentioned embodiments.

[0265] Reference below Figure 14 , Figure 14The figure is a schematic diagram of the structure of the device for predicting the battery capacity inflection point of the present application, which shows a schematic diagram of the structure of the device for predicting the battery capacity inflection point suitable for implementing the embodiment of the present application. The device for predicting the battery capacity inflection point in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 14 The battery capacity inflection point prediction device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0266] like Figure 14 As shown, the device for predicting the battery capacity inflection point may include a processing device 1401 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1402 or programs loaded from a storage device 1403 into a random access memory (RAM) 1404. RAM 1404 also stores various programs and data required for the operation of the device for predicting the battery capacity inflection point. Processing device 1401, ROM 1402, and RAM 1404 are interconnected via a bus 1405. An input / output (I / O) interface 1406 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1406: input devices 1407 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1408 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1403 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1409. The communication device 1409 can allow the device for predicting the battery capacity inflection point to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a device for predicting the battery capacity inflection point with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0267] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1403, or installed from a ROM 1402. When the computer program is executed by the processing device 1401, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0268] The battery capacity inflection point prediction device provided in this application utilizes the battery capacity inflection point prediction method described in the above-mentioned embodiment to solve the problem of accurately predicting the battery capacity inflection point. Compared to related technologies, the battery capacity inflection point prediction device provided in this application has the same beneficial effects as the battery capacity inflection point prediction method described in the above-mentioned embodiment. Other technical features of the battery capacity inflection point prediction device are the same as those disclosed in the above-mentioned embodiment and are not further described here.

[0269] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0270] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0271] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the battery capacity inflection point prediction method in the above-mentioned embodiment.

[0272] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0273] The computer-readable storage medium may be included in the device for predicting the battery capacity inflection point, or may exist independently without being incorporated into the device for predicting the battery capacity inflection point.

[0274] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a battery capacity inflection point prediction device, the battery capacity inflection point prediction device performs the following steps: obtaining cycle data of the battery to be predicted during the calendar aging test phase; wherein the cycle data includes the correspondence between different storage times collected during the calendar aging test phase and the maximum discharge capacity of the battery to be predicted; inputting the cycle data into a pre-trained battery capacity inflection point prediction model, and the battery capacity inflection point prediction model predicts the battery capacity inflection point of the battery to be predicted based on the cycle data.

[0275] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0276] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0277] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0278] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for predicting the battery capacity inflection point. This computer-readable storage medium addresses the problem of accurately predicting the battery capacity inflection point. Compared to related technologies, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the battery capacity inflection point prediction method provided in the aforementioned embodiment, and are not further elaborated here.

[0279] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned method for predicting the battery capacity inflection point when executed by a processor.

[0280] The computer program product provided in this application can solve the problem of how to accurately predict the battery capacity inflection point. Compared with the related art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the battery capacity inflection point prediction method provided in the above embodiment, and will not be repeated here.

[0281] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for predicting a battery capacity inflection point, characterized in that: The method comprises: Acquiring cycle data of the battery to be predicted during a calendar aging test phase; wherein the cycle data includes a correspondence between different storage times collected during the calendar aging test phase and a maximum discharge capacity of the battery to be predicted; Inputting the cycle data into a pre-trained battery capacity inflection point prediction model, and having the battery capacity inflection point prediction model predict the battery capacity inflection point of the battery to be predicted based on the cycle data; The step of inputting the cycle data into a pre-trained battery capacity inflection point prediction model, and predicting the battery capacity inflection point of the battery to be predicted based on the cycle data by the battery capacity inflection point prediction model, includes: Inputting the cycle data and the auxiliary prediction information into a pre-trained battery capacity inflection point prediction model, and having the battery capacity inflection point prediction model predict the battery capacity inflection point of the battery to be predicted based on the cycle data and the auxiliary prediction information; The auxiliary prediction information includes at least one of a storage sampling interval, a storage temperature, and a battery formula parameter.

2. The method according to claim 1, wherein Before inputting the cycle data into a pre-trained battery capacity inflection point prediction model, the method further includes: Obtain the maximum discharge capacity of the test battery corresponding to different storage times during the calendar aging test phase; Determining a capacity decay curve of the test battery based on the maximum discharge capacity corresponding to different storage times of the test battery; wherein the capacity decay curve represents a corresponding relationship between different storage times and the battery state of health (SOH); In the capacity decay curve, determining a target battery capacity inflection point of the test battery; Constructing a training data set based on a correspondence between the capacity decay curve and the target battery capacity inflection point; The training data set is used to train a preset candidate model, and the trained model is obtained as the battery capacity inflection point prediction model.

3. The method according to claim 2, wherein Before constructing a training data set based on the correspondence between the capacity decay curve and the target battery capacity inflection point, the method further includes: Obtaining storage sampling interval, storage temperature, and battery formula parameters of the test battery during a calendar aging test phase; The constructing of a training data set based on the correspondence between the capacity decay curve and the target battery capacity inflection point includes: A training data set is constructed based on the corresponding relationship between the capacity decay curve and the target battery capacity inflection point, the storage sampling interval, the storage temperature and the battery formula parameters.

4. The method according to claim 2, wherein The determining the capacity decay curve of the test battery based on the maximum discharge capacity corresponding to different storage times of the test battery includes: Calculate the ratio of the maximum discharge capacity corresponding to different storage times to the maximum discharge capacity of the initial storage as the SOH of the test battery at different storage times; Determining a first capacity decay curve corresponding to the test battery based on the SOH of the test battery at different storage times; wherein the first capacity decay curve represents a corresponding relationship between the SOH and different storage times; Using the box plot corresponding to the first capacity decay curve, filtering the discrete points in the first capacity decay curve to obtain a second capacity decay curve; Based on the second capacity fade curve, a capacity fade curve of the test battery is determined.

5. The method according to claim 4, wherein The filtering of discrete points in the first capacity decay curve using the box plot corresponding to the first capacity decay curve to obtain a second capacity decay curve includes: Calculate the quartile and upper quartile corresponding to the first capacity decay curve; Calculating an interquartile range corresponding to the first capacity decay curve based on the quartile and the upper quartile; determining a first threshold based on the quartiles and the interquartile range; determining a second threshold based on the upper quartile and the interquartile range; In the first capacity decay curve, points where the SOH is less than the first threshold or the SOH is greater than the second threshold are regarded as discrete points; The discrete points are filtered out from the first capacity decay curve, and linear interpolation filling is performed at the storage times corresponding to the discrete points to obtain the second capacity decay curve.

6. The method according to claim 5, wherein The determining the capacity decay curve of the test battery based on the second capacity decay curve includes: Calculating a variance value of SOH in the second capacity decay curve; When the variance value is greater than a preset third threshold, filtering the second capacity decay curve using a one-dimensional Gaussian filter to obtain a capacity decay curve of the test battery; When the variance value is less than or equal to the third threshold, the second capacity decay curve is filtered by using an SG filter to obtain the capacity decay curve of the test battery.

7. The method according to claim 3, wherein The constructing of a training data set based on the correspondence between the capacity decay curve and the target battery capacity inflection point, the storage sampling interval, the storage temperature, and the battery formula parameters includes: Generate a two-dimensional array corresponding to the test battery based on the correspondence between the capacity decay curve and the target battery capacity inflection point, the storage sampling interval, the storage temperature, and the battery formula parameters; wherein the two-dimensional array includes N groups of SOH, storage sampling interval, storage temperature, battery formula parameters, and time from the inflection point corresponding to different storage times, the time from the inflection point representing the difference between different storage times and the time corresponding to the target battery capacity inflection point, and N is an integer greater than 2; The time from the inflection point is used as a prediction label, and the N groups of data in the two-dimensional array are sequentially slid according to a preset sliding window length to generate a time series data set as the training data set.

8. The method according to claim 2, wherein The candidate model adopts the Transformer algorithm; Before using the training data set to train a preset candidate model to obtain the trained model as the battery capacity inflection point prediction model, the method further includes: A function obtained by weighted summation of a mean absolute error function and at least one regularization penalty term is used as a loss function for training the candidate model; The regularization penalty term is used to control the range of the battery capacity inflection point predicted by the trained battery capacity inflection point prediction model.

9. The method according to claim 2, wherein The method of using the training data set to train a preset candidate model to obtain the trained model as the battery capacity inflection point prediction model includes: Using the training data set to train a preset candidate model to obtain a trained model; The mean absolute error function is set as the optimization target of the trained model, and at least one of the learning rate, number of iterations, batch size, dropout value, and dropout value of the fully connected layer is set as the optimization parameter of the trained model. The trained model is optimized using the Bayesian algorithm to obtain the battery capacity inflection point prediction model.

10. A device for predicting a battery capacity inflection point, characterized in that: The device comprises: An acquisition module, configured to acquire cycle data of a battery to be predicted during a calendar aging test phase; wherein the cycle data includes a correspondence between different storage times collected during the calendar aging test phase and a maximum discharge capacity of the battery to be predicted; A prediction module, configured to input the cycle data into a pre-trained battery capacity inflection point prediction model, and have the battery capacity inflection point prediction model predict the battery capacity inflection point of the battery to be predicted based on the cycle data; The prediction module is specifically configured to input the cycle data and the auxiliary prediction information into a pre-trained battery capacity inflection point prediction model, and the battery capacity inflection point prediction model predicts the battery capacity inflection point of the battery to be predicted based on the cycle data and the auxiliary prediction information; The auxiliary prediction information includes at least one of a storage sampling interval, a storage temperature, and a battery formula parameter.

11. A device for predicting a battery capacity inflection point, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for predicting a battery capacity inflection point according to any one of claims 1 to 9.

12. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for predicting the battery capacity inflection point according to any one of claims 1 to 9 are implemented.

13. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method for predicting the battery capacity inflection point according to any one of claims 1 to 9 are implemented.

Images