Method, device and energy storage system for predicting maximum available capacity of battery cells

Abstract

The present application provides a method, device and energy storage system for predicting the maximum available capacity of a battery cell, relating to the field of battery technology. The method comprises: acquiring a data set, the data set comprising a plurality of first segment data; inputting the first preset segment data and the plurality of first segment data into a preset model for a first voltage prediction, to obtain a plurality of first predicted voltage sequence data; when the predicted voltage corresponding to the first predicted voltage sequence data reaches a first cutoff voltage, stopping the prediction, and acquiring a first moment and target segment data; inputting the second preset segment data and the plurality of first segment data starting from the target segment data into the preset model for a second voltage prediction, to obtain a plurality of second predicted voltage sequence data; when the voltage corresponding to the second predicted voltage sequence data reaches a second cutoff voltage, stopping the prediction, and acquiring a second moment; and generating a predicted maximum available capacity of the battery cell based on standard operating condition information of the battery cell discharge, the first moment and the second moment.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a method, device, and energy storage system for predicting the maximum available capacity of a battery cell. Background Art

[0002] The maximum usable capacity of a battery cell refers to the maximum amount of power it can provide under specific charge and discharge conditions. By predicting the maximum usable capacity of a battery cell, we can estimate its state of health (SOH), thereby predicting its performance, service life, and degradation.

[0003] In the related art, methods based on testing, empirical formula, model and machine learning are usually used to predict the maximum available capacity of battery cells. However, there are problems such as low prediction accuracy and inability to apply to different operating conditions of battery cells. Summary of the Invention

[0004] The present application provides a method, device and energy storage system for predicting the maximum available capacity of a battery cell, which are suitable for predicting the maximum available capacity of a battery cell under different operating conditions and improving the prediction accuracy.

[0005] In a first aspect, the present application provides a method for predicting the maximum available capacity of a battery cell, comprising:

[0006] Acquire a data set, where the data set includes a plurality of first data segments arranged in a time series, and each first data segment includes current information, voltage information, and temperature information of a battery cell;

[0007] Inputting the first preset segment data and a plurality of first segment data into the trained preset model for a first voltage prediction to obtain a plurality of first predicted voltage sequence data, wherein the first preset segment data includes standard operating condition information of the battery cell charging;

[0008] When the predicted voltage corresponding to the first predicted voltage sequence data reaches the first cutoff voltage, the first voltage prediction is stopped, and the first moment and target segment data are obtained, where the first moment is the moment corresponding to the first cutoff voltage, and the target segment data is the last first segment data input when the first voltage prediction is stopped;

[0009] Inputting the second preset segment data and a plurality of first segment data starting from the target segment data into the trained preset model for a second voltage prediction to obtain a plurality of second predicted voltage sequence data, wherein the second preset segment data includes standard operating condition information of the battery cell discharge;

[0010] When the predicted voltage corresponding to the second predicted voltage sequence data reaches the second cut-off voltage, the second voltage prediction is stopped and a second moment is obtained, where the second moment is the moment corresponding to the second cut-off voltage;

[0011] Generate a predicted maximum available capacity of the battery cell based on the standard operating condition information of the battery cell discharge, the first moment, and the second moment;

[0012] Estimate the health status of the battery cell based on the predicted maximum available capacity of the battery cell.

[0013] In a second aspect, the present application provides a device for predicting the maximum available capacity of a battery cell, comprising:

[0014] An acquisition module is used to acquire a data set, where the data set includes a plurality of first data segments arranged in a time series, and each first data segment includes current information, voltage information, and temperature information of a battery cell;

[0015] a first voltage prediction module, configured to input the first preset segment data and a plurality of first segment data into a trained preset model to perform a first voltage prediction, thereby obtaining a plurality of first predicted voltage sequence data, wherein the first preset segment data includes standard operating condition information of battery cell charging;

[0016] When the predicted voltage corresponding to the first predicted voltage sequence data reaches the first cutoff voltage, the first voltage prediction is stopped, and the first moment and target segment data are obtained, where the first moment is the moment corresponding to the first cutoff voltage, and the target segment data is the last first segment data input when the first voltage prediction is stopped;

[0017] a second voltage prediction module, configured to input the second preset segment data and a plurality of first segment data starting from the target segment data into a trained preset model for second voltage prediction, thereby obtaining a plurality of second predicted voltage sequence data, wherein the second preset segment data includes standard operating condition information of the battery cell discharge;

[0018] When the predicted voltage corresponding to the second predicted voltage sequence data reaches the second cut-off voltage, the second voltage prediction is stopped and a second moment is obtained, where the second moment is the moment corresponding to the second cut-off voltage;

[0019] A generating module, configured to generate a predicted maximum available capacity of the battery cell according to the standard operating condition information of the battery cell discharge, the first moment, and the second moment;

[0020] The estimation module is used to estimate the health status of the battery cell based on the predicted maximum available capacity of the battery cell.

[0021] In a third aspect, the present application provides an energy storage system, which includes a battery management system and a battery pack. The battery pack includes multiple battery cells, and the battery management system is used to implement the method of predicting the maximum available capacity of the battery cell as in the first aspect.

[0022] The beneficial effects of this application are:

[0023] The present application provides a method for predicting the maximum available capacity of a battery cell, by inputting the voltage information, current information and temperature information of the battery cell, as well as the standard operating condition information of the battery cell charging into a preset model for the first voltage prediction, simulating the charging process of the battery cell under standard operating conditions, repeatedly iterating the prediction until the predicted voltage of the battery cell reaches the full charge voltage, and recording the moment when the full charge voltage is reached; then inputting the voltage information, current information and temperature information of the fully charged battery cell, as well as the standard operating condition information of the battery cell discharge into the preset model for the second voltage prediction, simulating the process of the battery cell discharging from a fully charged state under standard operating conditions, repeatedly iterating the prediction until the battery cell voltage reaches the full discharge voltage, and recording the moment when the full discharge voltage is reached. Then, by integrating the current of the battery cell from the full charge moment to the full discharge moment, the predicted maximum available capacity of the battery cell is obtained, and the health status of the battery cell is evaluated.

[0024] This application uses a preset model to predict the voltage of the battery cell under standard operating conditions, simulates the full charge and full discharge process of the battery cell, and eliminates the work of laboratory testing and capturing special points; no prior calibration and parameter identification are required; and this application uses a self-supervised deep learning model for training and prediction, eliminating the work of feature extraction and labeling, and uses the full amount of cloud data (i.e., data set) for training and prediction. The full amount of cloud data includes the parameters of the battery cell under various operating conditions such as charging, discharging, and static, so that the model can adapt to the different operating conditions of the battery cell, with strong adaptability, thereby improving the model's generalization ability and prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic flow chart of a method for predicting the maximum available capacity of a battery cell provided in an embodiment of the present application;

[0026] Figure 2 A schematic diagram of a process for forming a data set provided in an embodiment of the present application;

[0027] Figure 3 A flowchart of a method for training a preset model provided in an embodiment of the present application;

[0028] Figure 4 A schematic diagram of the structure of a device for predicting the maximum available capacity of a battery cell provided in an embodiment of the present application;

[0029] Figure 5 A schematic diagram of the structure of the energy storage system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In the embodiments of this application, unless otherwise specified, the character " / " indicates that the associated objects are in an "or" relationship. For example, A / B can represent A or B. "And / or" describes the relationship between the associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exists simultaneously, or B exists alone.

[0031] It should be pointed out that the words "first", "second", etc. involved in the embodiments of this application are only used for distinguishing description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated, nor can they be understood as indicating or implying order.

[0032] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. In addition, "at least one of the following" or similar expressions refers to any combination of these items, which may include any combination of single or plural items. For example, at least one of A, B, or C can mean: A, B, C, A and B, A and C, B and C, or A, B, and C. Each of A, B, and C can be an element itself or a set containing one or more elements.

[0033] In the embodiments of this application, the terms "exemplary," "in some embodiments," and "in another embodiment" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" in this application should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner.

[0034] In the embodiments of this application, the terms "of," "corresponding," and "relevant" may be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings are consistent. In the embodiments of this application, the terms "communication" and "transmission" may be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings are consistent. For example, "transmission" may include "sending" and / or "receiving," and may be either a noun or a verb.

[0035] In the embodiments of this application, "equal to" can be used in conjunction with "greater than" and is applicable to the technical solution adopted when "greater than" is used, and can also be used in conjunction with "less than" and is applicable to the technical solution adopted when "less than" is used. It should be noted that when "equal to" is used in conjunction with "greater than", it cannot be used in conjunction with "less than"; and when "equal to" is used in conjunction with "less than", it cannot be used in conjunction with "greater than".

[0036] In related technologies, methods based on testing, empirical formulas, models, and machine learning are commonly used to predict the maximum available capacity of battery cells. Among them, the test-based method can only conduct charge and discharge tests under standard operating conditions in experiments, perform capacity detection on battery cells, or rely on special points in actual use of the battery cells, such as full charge and discharge, and static conditions, to make capacity corrections. There are fewer available points and low coverage. The empirical formula-based method often has a single operating condition and is difficult to apply to the various operating conditions of battery cells in actual situations. The model-based method, whether it is an equivalent circuit or an electrochemical model, relies on a large amount of prior work on parameter calibration and parameter identification, which greatly affects its accuracy, and requires repeated calibration and identification as the battery ages. The machine learning-based method requires a large number of labeled samples, otherwise the model's generalization ability will be very weak.

[0037] Based on the above problems, an embodiment of the present application proposes a method for predicting the maximum available capacity of a battery cell, which is suitable for predicting the maximum available capacity of a battery cell under different working conditions and improves the prediction accuracy.

[0038] Now combined Figure 1-Figure 3 The method for predicting the maximum available capacity of a battery cell provided in an embodiment of the present application is described.

[0039] Figure 1 A flow chart of a method for predicting the maximum available capacity of a battery cell provided in an embodiment of the present application specifically includes the following steps:

[0040] Step S11: Acquire a data set, where the data set includes a plurality of first fragment data.

[0041] The plurality of first segment data are arranged in time series, and each first segment data includes current information, voltage information and temperature information of the battery cell.

[0042] Specifically, the data set can be obtained from a local database or a cloud database. Preferably, the edge uploads the cell's voltage, current, temperature, and other signals to the cloud and stores them in the cloud database. When predicting the cell's maximum available capacity, the data set is obtained from the cloud database and the full cloud data of the cell is used in model training to improve the model's training effectiveness and generalization capabilities.

[0043] Among them, such as Figure 2 As shown, Figure 2 This is a schematic diagram of a process for forming a data set provided in an embodiment of the present application. The process of forming the data set includes:

[0044] Step S21 : sampling the voltage, current, and temperature of the battery cell at a fixed sampling frequency to obtain historical time series data of the battery cell.

[0045] Specifically, the voltage, current, and temperature of the battery cell are sampled at a fixed sampling frequency (e.g., once every 20 seconds). The voltage, current, and temperature of the battery cell constitute each frame of data for the battery cell. Each frame of data refers to a set of battery cell parameters (including voltage, current, and temperature) collected within a fixed time interval (e.g., 20 seconds) according to the fixed sampling frequency. Each frame of data is arranged in chronological order to form the historical time series data of the battery cell.

[0046] Optionally, the temperature information of the battery cell may include the surface temperature of a target battery cell (the battery cell for which maximum available capacity prediction is performed), or may include an average temperature of multiple battery cells including the target battery cell.

[0047] In actual applications, battery packs composed of multiple cells have a large number of cells. Considering installation costs and battery pack space utilization, individual temperature sensors are not used to detect the surface temperature of the target cells. Therefore, in battery packs composed of multiple cells, the temperature information of the cells includes the average temperature, which is the average temperature of all cells in the battery pack.

[0048] Specifically, the method provided in the embodiment of the present application also includes: obtaining the highest cell temperature and the lowest cell temperature in the battery pack; calculating the average temperature based on the highest cell temperature and the lowest cell temperature, that is, the average temperature = (highest cell temperature + lowest cell temperature) / 2.

[0049] Step S22 , slicing and splitting the historical time series data in a frame-by-frame manner to obtain a plurality of first segment data.

[0050] Frame-by-frame shifting (also known as sliding windowing) is a commonly used method for processing time series data. It is used to split long series data (i.e., historical time series data) into multiple fixed-length subsequences (i.e., first fragment data). The specific steps of frame-by-frame shifting include:

[0051] (1) Define the window size:

[0052] The window size (also called slice length) refers to the length of each subsequence. For example, if the window size is 5, then each subsequence will contain 5 data points.

[0053] (2) Define the sliding step size:

[0054] The sliding step size is the number of steps to move each time. For example, if the sliding step size is 1, then the data point will be moved one at a time.

[0055] (3) Initialize data:

[0056] Prepare original time series data (i.e. historical time series data).

[0057] (4) Sliding window:

[0058] Starting from the starting position of the historical time series data, the data of the window size is extracted by moving the sliding step distance each time until the end of the data.

[0059] (5) Generate the first fragment data:

[0060] After each slide, the extracted data is saved as a first fragment of data.

[0061] For example, historical time series data consists of nine frames, represented as [x1,x2,x3,x4,x5,x6,x7,x8,x9]. Each frame contains the voltage, current, and temperature information of the battery cell. Using a frame-by-frame approach, with a window size of 3 and a sliding step of 1, the first data segment obtained by slicing is represented as: [x1,x2,x3], [x2,x3,x4], [x3,x4,x5], [x4,x5,x6], [x5,x6,x7], [x6,x7,x8], [x7,x8,x9].

[0062] Slicing and splitting historical time series data using a frame-by-frame approach to generate multiple first-segment data increases data diversity, providing more training samples for the model and helping to improve its generalization capabilities. Furthermore, the segmented data generated by frame-by-frame movement can be used to train more complex models, such as Transformer-based models, which can capture long-term dependencies in long-sequence data, thereby improving prediction accuracy and efficiency.

[0063] Step S23 , performing data preprocessing on the plurality of first segment data, where the data preprocessing includes removing abnormal data.

[0064] In order to ensure the accuracy of the prediction results and improve the stability and prediction accuracy of the model, the voltage, current and temperature in the first segment data must all be valid values. Therefore, it is necessary to preprocess the multiple first segment data, remove the abnormal data in the multiple first segment data, and retain the first segment data in which the voltage, current and temperature are all valid values.

[0065] Step S24: forming a data set from the plurality of first fragment data after data preprocessing.

[0066] Specifically, the plurality of first data segments obtained after processing in step S23 are combined into a data set. For example, as shown in the example of step S22, if the plurality of first data segments are all valid values, the data set D is represented as: {[x1, x2, x3], [x2, x3, x4], [x3, x4, x5], [x4, x5, x6], [x5, x6, x7], [x6, x7, x8], [x7, x8, x9]}.

[0067] In some optional embodiments, dataset D includes a 98% training set, a 1% validation set, and a 1% test set. Using a large amount of data from the dataset for model training can improve model performance and robustness. Using a smaller percentage of data for model validation and testing can quickly verify model performance and independently assess the model's generalization ability.

[0068] In step S12 , the first preset segment data and the plurality of first segment data are input into the trained preset model to perform a first voltage prediction, thereby obtaining a plurality of first predicted voltage sequence data.

[0069] The first preset segment data includes standard operating condition information of battery cell charging.

[0070] In this step, the standard operating condition information of the battery cell charging includes the first standard temperature and constant charging power, or the standard operating condition information of the battery cell charging includes the first standard temperature and constant charging current. For example, under the standard operating condition, the battery cell is charged at a constant temperature and constant power at 25°C and -0.5P. In order to meet the data input length requirements of the preset model, the length of the first preset segment data is the same as the length of the first segment data. Assume that the dimension of the first preset segment data is 1 3, expressed as [y1, y2, y3], that is, the first preset segment data includes 3 frames of data, each frame of data includes information that the temperature is 25°C and the power is -0.5P, and the voltage information in the first preset segment data is all 0.

[0071] The first preset segment data and multiple first segment data are input into the trained preset model respectively to perform the first voltage prediction. Specifically, taking the data set D: {[x1, x2, x3], [x2, x3, x4], [x3, x4, x5], [x4, x5, x6], [x5, x6, x7], [x6, x7, x8], [x7, x8, x9]} as an example, the input of the preset model includes multiple groups of input data consisting of the first preset segment data and multiple first segment data, and the multiple groups of input data include {[y1, y2, y3], [x1, x2, x3]}, {[y1, y2, y3], [ The output of the model is a plurality of first predicted voltage sequence data corresponding to multiple groups of input data. The dimension of the first predicted voltage sequence data is 1. 3. Used to characterize the predicted voltage of the battery cell when charged under standard operating conditions.

[0072] Step S13: When the predicted voltage corresponding to the first predicted voltage sequence data reaches a first cutoff voltage, the first voltage prediction is stopped, and the first moment and target segment data are acquired.

[0073] The first moment is the moment corresponding to the first cut-off voltage, and the target segment data is the last first segment data input when the first voltage prediction is stopped.

[0074] Specifically, the first cutoff voltage represents the fully charged voltage of the battery cell. When the predicted voltage corresponding to the first predicted voltage sequence data reaches the first cutoff voltage, it indicates that the battery cell has reached a fully charged state. At this time, the model stops data input and prediction, and the moment when the predicted voltage reaches the first cutoff voltage (i.e., the first moment) and the last first segment of data input to the model (i.e., the target segment data) are recorded, indicating that when the preset model inputs the target segment data for prediction, the corresponding predicted voltage of the battery cell reaches the first cutoff voltage.

[0075] It should be noted that the predicted voltage corresponding to the first predicted voltage sequence data reaches the first cut-off voltage means that the predicted voltage is greater than or equal to the first cut-off voltage, at which time it is considered that the battery cell has reached a fully charged state.

[0076] For example, in a trained preset model, data consisting of the first preset segment data and the first segment data are input one by one. When the input is {[y1, y2, y3], [x4, x5, x6]}, the output first predicted voltage sequence data is [u1, u2, u3], where u2 is equal to the first cutoff voltage (such as 3.6v). Then the data input and prediction of the model are stopped, and the moment T1 (i.e., the first moment) corresponding to the voltage u2 and the target segment data [x4, x5, x6) are recorded. It can be understood that the first predicted voltage sequence data is used to characterize the voltage predicted according to the first segment data under the standard working conditions of battery cell charging. The first predicted voltage sequence data corresponds one-to-one to the first segment data. The moment corresponding to the voltage u2 is also the moment corresponding to the frame data x5. Specifically, the first moment can be calculated by multiplying the length from x1 to x5 by the fixed time interval. For example, let x1 be the starting moment, the fixed time interval be 20s, the length from x1 to x5 be 4, and the first moment be 4. 20s=80s.

[0077] This application simulates the charging process of the battery cell under standard working conditions by inputting the voltage information, current information and temperature information of the battery cell, as well as the standard operating condition information of the battery cell charging into a preset model, repeatedly iterates the prediction until the predicted voltage of the battery cell reaches the full charge voltage, and records the moment when the full charge voltage is reached, eliminating the need for laboratory testing and capturing special points.

[0078] In step S14 , the second preset segment data and a plurality of first segment data starting from the target segment data are input into the trained preset model to perform a second voltage prediction, thereby obtaining a plurality of second predicted voltage sequence data.

[0079] The second preset segment data includes standard operating condition information of the battery cell discharge.

[0080] In this step, the standard operating condition information of the battery cell discharge includes the second standard temperature and constant discharge power, or the standard operating condition information of the battery cell discharge includes the second standard temperature and constant discharge current. For example, under the standard operating condition, the battery cell is discharged at a constant temperature and constant power at 25°C and 0.5P. In order to meet the data input length requirements of the preset model, the length of the second preset segment data is the same as the length of the first segment data. Assume that the dimension of the second preset segment data is 1 3, expressed as [y4, y5, y6], that is, the second preset segment data includes 3 frames of data, each frame of data includes information that the temperature is 25°C and the power is 0.5P, and the voltage information in the second preset segment data is all 0.

[0081] The second preset segment data and the multiple first segment data starting from the target segment data are input into the trained preset model for the second voltage prediction. Specifically, taking the data set D: {[x1, x2, x3], [x2, x3, x4], [x3, x4, x5], [x4, x5, x6], [x5, x6, x7], [x6, x7, x8], [x7, x8, x9]} as an example, the multiple first segment data starting from the target segment data [x4, x5, x6] include {[x4, x5, x6], [ x5,x6,x7], [x6,x7,x8], [x7,x8,x9]}, then the multiple sets of input data of the preset model include {[y4,y5,y6], [x4,x5,x6]}, {[y4,y5,y6], [x5,x6,x7]}, {[y4,y5,y6], [x6,x7,x8]}, {[y4,y5,y6], [x7,x8,x9]}, and the output of the model is a plurality of second predicted voltage sequence data corresponding to the multiple sets of input data. The dimension of the second predicted voltage sequence data is 1 3. Used to characterize the predicted discharge voltage of the battery cell under standard operating conditions.

[0082] Step S15: When the predicted voltage corresponding to the second predicted voltage sequence data reaches the second cutoff voltage, the second voltage prediction is stopped and a second moment is obtained.

[0083] The second moment is the moment corresponding to the second cut-off voltage.

[0084] Specifically, the second cutoff voltage represents the fully discharged voltage of the battery cell. When the predicted voltage corresponding to the second predicted voltage sequence data reaches the second cutoff voltage, it indicates that the battery cell has reached a fully discharged state. At this point, the model's data input and prediction are stopped, and the moment when the predicted voltage reaches the second cutoff voltage (i.e., the second moment) is recorded.

[0085] It should be noted that the predicted voltage corresponding to the second predicted voltage sequence data reaches the second cut-off voltage means that the predicted voltage is less than or equal to the second cut-off voltage, at which time it is considered that the battery cell has reached a fully discharged state.

[0086] For example, in a trained preset model, data consisting of a second preset segment data and a plurality of first segment data starting from the target segment data are input one by one. When the input is {[y4, y5, y6], [x7, x8, x9]}, the output second predicted voltage sequence data is [u4, u5, u6], where u5 is equal to the second cutoff voltage (such as 2.8v), then the data input and prediction of the model are stopped, and the moment T2 (i.e., the second moment) corresponding to the voltage u5 is recorded. It can be understood that the second predicted voltage sequence data is used to characterize the voltage predicted according to the first segment data under the standard working condition of the battery cell discharge. The second predicted voltage sequence data corresponds one-to-one to the first segment data. The moment corresponding to the voltage u5 is also the moment corresponding to the frame data x8. Specifically, the second moment can be calculated by multiplying the length from x1 to x8 by the fixed time interval. For example, let x1 be the starting moment, the fixed time interval be 20s, the length from x1 to x8 be 7, and the second moment be 7. 20s=140s.

[0087] This application inputs the voltage information, current information and temperature information of the fully charged battery cell, as well as the standard operating condition information of the battery cell discharge into a preset model, simulates the process of the battery cell discharging from a fully charged state under standard operating conditions, repeatedly iterates the prediction until the predicted voltage of the battery cell reaches the full discharge voltage, and records the moment when the full discharge voltage is reached, eliminating the need for laboratory testing and capturing special points.

[0088] In one possible embodiment, the preset model includes a self-supervised deep learning model, which is a Transformer model. The Transformer model includes an encoder and a decoder. The multiple first fragments include consecutive second fragments and third fragments. For example, the multiple first fragments include A0, A1, A2, A3, A4, and A5. Each first fragment includes m frames of data, and each frame includes voltage, current, and temperature information of the battery cell. The dimension of the first fragment is 3. The continuous second and third data segments can be [A0, A1], [A1, A2], [A2, A3], [A3, A4], and [A4, A5]. The following uses [A0, A1] as an example (i.e., the second data segment is A0 and the third data segment is A1) to illustrate the training method for the preset model.

[0089] Figure 3 A flow chart of the training method of the preset model provided in the embodiment of the present application is shown as follows: Figure 3 As shown, the training methods of the preset model include:

[0090] Step S31 : Reset the voltage information of the battery cell in the third data segment to zero to obtain the fourth data segment.

[0091] Specifically, the third segment data A1 includes m frames, and the voltage information of the battery cells in each frame is set to 0 to obtain the fourth segment data A1 ′.

[0092] Step S32: concatenate the second data segment and the fourth data segment to obtain the fifth data segment.

[0093] Specifically, the second data segment A0 and the fourth data segment A1′ are concatenated to obtain the fifth data segment [A0, A1′].

[0094] Step S33: input the second segment data into the encoder, input the fifth segment data into the decoder, predict the voltage information of the battery cell in the third segment data, and obtain predicted voltage sequence data.

[0095] Specifically, the second segment data A0 is input to the encoder, the fifth segment data [A0, A1'] is input to the decoder, and the voltage information of the battery cell in the third segment data A1 is predicted to obtain the predicted voltage sequence data, that is, the predicted voltage of the battery cell in each frame of the third segment data A1 is obtained. The dimension of the predicted voltage sequence data is 1 m.

[0096] Furthermore, the predicted voltage sequence data may be compared with the original voltage information in the third segment data A1, and an optimization algorithm may be used to optimize the parameters of the model to improve the prediction accuracy of the model.

[0097] In this application, a deep learning model with self-supervised learning is adopted, which eliminates the work of labeling and does not require prior calibration and parameter identification. The model has high prediction accuracy and can be trained using the full amount of cloud data. The full amount of cloud data includes data on battery cells under different working conditions (such as charging, discharging or static). The battery cell voltage can be predicted under different working conditions, and the training model can adapt to the different working conditions of the battery cells to improve the generalization ability of the model.

[0098] Step S16: Generate a predicted maximum available capacity of the battery cell according to the standard operating condition information of the battery cell discharge, the first moment, and the second moment.

[0099] In one embodiment, the standard operating condition information for charging the battery cell includes a first standard temperature and a constant charging power, and the standard operating condition information for discharging the battery cell includes a second standard temperature and a constant discharging power. The predicted maximum available capacity of the battery cell is generated based on the standard operating condition information for discharging the battery cell, the first moment and the second moment, including: obtaining the discharge current information of the battery cell between the first moment and the second moment based on the constant discharge power and the second predicted voltage sequence data; integrating the discharge current information of the battery cell between the first moment and the second moment to obtain the predicted maximum available capacity of the battery cell.

[0100] For example, if the standard operating conditions for charging a battery cell are 25°C and -0.5P, and the standard operating conditions for discharging a battery cell are 25°C and 0.5P, then the first time T1 and the second time T2, as well as the second predicted voltage sequence data, are obtained according to steps S11-S15. Since the battery cell discharges at a constant power, the discharge current information of the battery cell during the discharge process can be obtained based on the second predicted voltage sequence data, that is, the discharge current information of the battery cell between the first time T1 and the second time T2. By integrating the discharge current information using the current integration method (also known as the coulomb counting method), the predicted maximum available capacity of the battery cell can be obtained.

[0101] It should be noted that 0.5P indicates a charging power of 0.5 times the rated power of the battery. For example, if the rated power of the battery is 100W, a charging power of 0.5P is expressed as 50W (0.5 × 100 = 50). -0.5P indicates a discharging power of 0.5 times the rated power of the battery. For example, if the rated power of the battery is 100W, a discharging power of -0.5P is expressed as -50W (-0.5 × 100 = -50). The sign of the power value serves only to distinguish between the charging and discharging processes, with charging generally positive and discharging negative.

[0102] In another embodiment, the standard operating condition information for charging the battery cell includes a first standard temperature and a constant charging current, and the standard operating condition information for discharging the battery cell includes a second standard temperature and a constant discharge current. The predicted maximum available capacity of the battery cell is generated based on the standard operating condition information for discharging the battery cell, the first moment and the second moment, including: integrating the constant discharge current between the first moment and the second moment to obtain the predicted maximum available capacity of the battery cell.

[0103] For example, the standard operating condition information for charging a battery cell is 25°C and 0.3C, and the standard operating condition information for discharging a battery cell is 25°C and -0.3C. According to the above steps S11-S15, the first moment T1 and the second moment T2 are obtained. The constant discharge current (-0.3C) between the first moment T1 and the second moment T2 is integrated using the current integration method (also known as the coulomb counting method) to obtain the predicted maximum available capacity of the battery cell.

[0104] It should be noted that 0.3C indicates a charge current of 0.3 times the rated capacity of the battery. For example, if the battery's rated capacity is 100Ah, a charge current of 0.3C is expressed as 30A (0.3 × 100 = 30). -0.3C indicates a discharge current of 0.3 times the rated capacity of the battery. For example, if the battery's rated capacity is 100Ah, a discharge current of -0.3C is expressed as -30A (-0.3 × 100 = -30). The sign of the current value serves only to distinguish between the charging and discharging processes, with charging typically positive and discharging negative.

[0105] Step S17: estimating the health status of the battery cell according to the predicted maximum available capacity of the battery cell.

[0106] Specifically, according to the predicted maximum available capacity of the battery cell obtained in step S16 above, the predicted maximum available capacity of the battery cell is divided by the initial maximum available capacity of the battery cell to obtain the health status of the battery cell.

[0107] To improve the accuracy of the predicted maximum available capacity of a battery cell (or the estimated state of health of the battery cell), a preset model can be used to perform multiple full charge and discharge cycle tests. This involves repeating steps S11-S16, for example, three times. The average of the three predicted maximum available capacities is taken as the final prediction result. This application performs multiple predictions and takes the average value, which can improve the stability and accuracy of the prediction.

[0108] The method proposed in the embodiment of the present application is to input the voltage information, current information and temperature information of the battery cell, as well as the standard operating condition information of the battery cell charging, into a preset model for the first voltage prediction, simulate the charging process of the battery cell under the standard operating condition, repeatedly iterate the prediction until the predicted voltage of the battery cell reaches the full charge voltage, and record the time when the full charge voltage is reached; then input the voltage information, current information and temperature information of the fully charged battery cell, as well as the standard operating condition information of the battery cell discharge, into the preset model for the second voltage prediction, simulate the process of the battery cell discharging from a fully charged state under the standard operating condition, repeatedly iterate the prediction until the battery cell voltage reaches the full discharge voltage, and record the time when the full discharge voltage is reached. Then, by integrating the current of the battery cell from the full charge moment to the full discharge moment, the predicted maximum available capacity of the battery cell is obtained, and the health status of the battery cell is evaluated.

[0109] This application uses a preset model to predict the voltage of the battery cell under standard operating conditions, simulates the full charge and full discharge process of the battery cell, and eliminates the need for laboratory testing and capturing special points; no prior calibration and parameter identification are required, and the battery cell parameters can be automatically updated as the battery ages; and this application uses a self-supervised deep learning model for training and prediction, eliminating the need for feature extraction and labeling, and uses the full amount of cloud data (i.e., data set) for training and prediction. The full amount of cloud data includes the parameters of the battery cell under various operating conditions such as charging, discharging, and static conditions, so that the model can adapt to different operating conditions of the battery cell, has strong adaptability, and improves the model's generalization ability and prediction accuracy.

[0110] Based on the same idea, the embodiment of the present application also provides a device for predicting the maximum available capacity of a battery cell. Figure 4 A schematic diagram of the structure of a device for predicting the maximum available capacity of a battery cell provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the device 40 for predicting the maximum available capacity of the battery cell may include:

[0111] An acquisition module 41 is configured to acquire a data set, the data set including a plurality of first data segments arranged in a time series, each of the first data segments including current information, voltage information, and temperature information of a battery cell;

[0112] a first voltage prediction module 42 for inputting the first preset segment data and a plurality of first segment data into a trained preset model to perform a first voltage prediction, thereby obtaining a plurality of first predicted voltage sequence data, wherein the first preset segment data includes standard operating condition information of battery cell charging;

[0113] When the predicted voltage corresponding to the first predicted voltage sequence data reaches the first cutoff voltage, the first voltage prediction is stopped, and the first moment and target segment data are obtained, where the first moment is the moment corresponding to the first cutoff voltage, and the target segment data is the last first segment data input when the first voltage prediction is stopped;

[0114] a second voltage prediction module 43, configured to input the second preset segment data and a plurality of first segment data starting from the target segment data into the trained preset model for second voltage prediction, thereby obtaining a plurality of second predicted voltage sequence data, wherein the second preset segment data includes standard operating condition information of the battery cell discharge;

[0115] When the predicted voltage corresponding to the second predicted voltage sequence data reaches the second cut-off voltage, the second voltage prediction is stopped and a second moment is obtained, where the second moment is the moment corresponding to the second cut-off voltage;

[0116] A generating module 44 is configured to generate a predicted maximum available capacity of the battery cell according to the standard operating condition information of the battery cell discharge, the first moment, and the second moment;

[0117] The estimation module 45 is configured to estimate the health status of the battery cell according to the predicted maximum available capacity of the battery cell.

[0118] In one possible implementation, the preset model includes a self-supervised deep learning model, the self-supervised deep learning model is a Transformer model, the Transformer model includes an encoder and a decoder, the plurality of first segment data includes consecutive second segment data and third segment data, and the training method of the preset model includes:

[0119] Resetting the voltage information of the battery cell in the third segment data to zero to obtain the fourth segment data;

[0120] Concatenate the second fragment data and the fourth fragment data to obtain the fifth fragment data;

[0121] The second segment data is input into the encoder, the fifth segment data is input into the decoder, and the voltage information of the battery cell in the third segment data is predicted to obtain predicted voltage sequence data.

[0122] In one possible implementation, the standard operating condition information for charging the battery cell includes a first standard temperature and a constant charging power, and the standard operating condition information for discharging the battery cell includes a second standard temperature and a constant discharging power.

[0123] In one possible implementation, the generating module 44 may also be used to:

[0124] Obtain discharge current information of the battery cell between a first moment and a second moment according to the constant discharge power and the second predicted voltage sequence data;

[0125] The discharge current information of the battery cell between the first moment and the second moment is integrated to obtain the predicted maximum available capacity of the battery cell.

[0126] In one possible implementation, the standard operating condition information for charging the battery cell includes a first standard temperature and a constant charging current, and the standard operating condition information for discharging the battery cell includes a second standard temperature and a constant discharging current.

[0127] In one possible implementation, the generating module 44 may also be used to:

[0128] The constant discharge current between the first moment and the second moment is integrated to obtain the predicted maximum available capacity of the battery cell.

[0129] In one possible implementation, the estimation module 45 may also be used to:

[0130] Divide the predicted maximum available capacity of the battery cell by the initial maximum available capacity of the battery cell to obtain the health status of the battery cell.

[0131] In one possible implementation, the process of forming a data set includes:

[0132] The voltage, current and temperature of the battery cell are sampled at a fixed sampling frequency to obtain the historical time series data of the battery cell;

[0133] Slice and split the historical time series data using a frame-by-frame moving method to obtain multiple first segment data;

[0134] Performing data preprocessing on the plurality of first fragment data, the data preprocessing including removing abnormal data;

[0135] The data set is composed of a plurality of first fragments of data after data preprocessing.

[0136] In one possible implementation, the dataset consists of 98% training set, 1% validation set and 1% test set.

[0137] In one possible implementation, the temperature information includes an average temperature. A battery pack is composed of multiple battery cells. The acquisition module 41 is further configured to obtain the highest battery cell temperature and the lowest battery cell temperature in the battery pack. The device 40 for predicting the maximum available capacity of the battery cell further includes:

[0138] The calculation module is used to calculate the average temperature according to the maximum battery cell temperature and the minimum battery cell temperature.

[0139] Figure 4 The device 40 for predicting the maximum available capacity of a battery cell provided in the illustrated embodiment can be used to implement the technical solution of the method embodiment shown in this application. Its implementation principle and technical effects can be further referred to the relevant description in the method embodiment.

[0140] It should be understood that the above Figure 4 The division of the various modules of the device 40 for predicting the maximum available capacity of a battery cell shown is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, these modules can all be implemented in the form of software calling through processing elements; they can also all be implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. For example, the acquisition module can be a separately established processing element, or it can be integrated into a chip of an electronic device. The implementation of other modules is similar. In addition, these modules can all or partly be integrated together, or they can be implemented independently. During the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or the instructions in the form of software.

[0141] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more microprocessors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, these modules may be integrated together to implement a system-on-a-chip (SOC).

[0142] In each of the above embodiments, the processor involved may include, for example, a CPU, a DSP, a microcontroller, or a digital signal processor, and may also include a GPU, an embedded neural network processor (NPU), and an image signal processor (ISP). The processor may also include necessary hardware accelerators or logic processing hardware circuits, such as an ASIC, or one or more integrated circuits for controlling the execution of the program of the technical solution of this application. In addition, the processor may have the function of operating one or more software programs, and the software programs may be stored in a storage medium.

[0143] The embodiments of the present application further provide an energy storage system, which includes a battery management system (BMS) and a battery pack. The battery pack includes multiple battery cells. The battery management system is used to implement the method provided in the embodiments shown in the present application.

[0144] Figure 5 A schematic diagram of the structure of the energy storage system provided in the embodiment of the present application is shown in FIG. Figure 5 As shown, the energy storage system includes a battery pack 51 and a BMS 52, wherein the battery pack 51 includes multiple battery cells, and the BMS 52 is used to implement the method for predicting the maximum available capacity of the battery cells provided in the embodiment shown in the present application. Figure 5 The energy storage system described above is only used as an example, and the specific structure is not limited. There is no limitation on the location and number of battery packs and BMS included in the energy storage system.

[0145] The above description is merely a specific embodiment of the present application. Any person skilled in the art may easily conceive of variations or substitutions within the technical scope disclosed in this application, and such variations or substitutions shall be within the scope of protection of this application. The scope of protection of this application shall be subject to the scope of protection of the claims.

Claims

1. A method for predicting the maximum available capacity of a battery cell, characterized in that: The method comprises: Acquire a data set, the data set including a plurality of first fragment data, the plurality of first fragment data being arranged in a time series, each first fragment data including current information, voltage information, and temperature information of a battery cell; Inputting the first preset segment data and the plurality of first segment data into the trained preset model for a first voltage prediction to obtain a plurality of first predicted voltage sequence data, wherein the first preset segment data includes standard operating condition information of battery cell charging; When the predicted voltage corresponding to the first predicted voltage sequence data reaches a first cutoff voltage, stopping the first voltage prediction, acquiring a first time instant and target segment data, where the first time instant is the time instant corresponding to the first cutoff voltage, and the target segment data is the last first segment data input when stopping the first voltage prediction; Inputting the second preset segment data and a plurality of first segment data starting from the target segment data into the trained preset model for a second voltage prediction to obtain a plurality of second predicted voltage sequence data, wherein the second preset segment data includes standard operating condition information of the battery cell discharge; When the predicted voltage corresponding to the second predicted voltage sequence data reaches a second cutoff voltage, stopping the second voltage prediction and acquiring a second moment, where the second moment is the moment corresponding to the second cutoff voltage; generating a predicted maximum available capacity of the battery cell according to the standard operating condition information of the battery cell discharge, the first moment, and the second moment; The health status of the battery cell is estimated based on the predicted maximum available capacity of the battery cell.

2. The method for predicting the maximum available capacity of a battery cell according to claim 1, wherein: The preset model includes a self-supervised deep learning model, the self-supervised deep learning model is a Transformer model, the Transformer model includes an encoder and a decoder, the multiple first segment data include continuous second segment data and third segment data, The training method of the preset model includes: Resetting the voltage information of the battery cell in the third segment data to zero to obtain fourth segment data; concatenating the second data segment and the fourth data segment to obtain fifth data segment; The second segment data is input into the encoder, the fifth segment data is input into the decoder, and the voltage information of the battery cell in the third segment data is predicted to obtain predicted voltage sequence data.

3. The method for predicting the maximum available capacity of a battery cell according to claim 1, wherein: The standard operating condition information of the battery cell charging includes a first standard temperature and a constant charging power, and the standard operating condition information of the battery cell discharging includes a second standard temperature and a constant discharging power.

4. The method for predicting the maximum available capacity of a battery cell according to claim 3, wherein: Generating a predicted maximum available capacity of the battery cell according to the standard operating condition information of the battery cell discharge, the first moment, and the second moment includes: Obtaining discharge current information of the battery cell between the first moment and the second moment according to the constant discharge power and the second predicted voltage sequence data; The discharge current information of the battery cell between the first moment and the second moment is integrated to obtain a predicted maximum available capacity of the battery cell.

5. The method for predicting the maximum available capacity of a battery cell according to claim 1, wherein: The standard operating condition information of the battery cell charging includes a first standard temperature and a constant charging current, and the standard operating condition information of the battery cell discharging includes a second standard temperature and a constant discharging current.

6. The method for predicting the maximum available capacity of a battery cell according to claim 5, wherein: Generating a predicted maximum available capacity of the battery cell according to the standard operating condition information of the battery cell discharge, the first moment, and the second moment includes: The constant discharge current between the first moment and the second moment is integrated to obtain a predicted maximum available capacity of the battery cell.

7. The method for predicting the maximum available capacity of a battery cell according to any one of claims 1 to 6, characterized in that: The health status of the battery cell is estimated based on the predicted maximum available capacity of the battery cell, including: The predicted maximum available capacity of the battery cell is divided by the initial maximum available capacity of the battery cell to obtain the health status of the battery cell.

8. The method for predicting the maximum available capacity of a battery cell according to claim 1, wherein: The process of forming the data set includes: The voltage, current and temperature of the battery cell are sampled at a fixed sampling frequency to obtain the historical time series data of the battery cell; Slicing and splitting the historical time series data in a frame-by-frame manner to obtain the plurality of first segment data; Performing data preprocessing on the plurality of first fragment data, wherein the data preprocessing includes removing abnormal data; The data set is composed of a plurality of first fragments of data after the data preprocessing.

9. The method for predicting the maximum available capacity of a battery cell according to claim 8, wherein: The dataset consists of a 98% training set, a 1% validation set, and a 1% test set.

10. The method for predicting the maximum available capacity of a battery cell according to claim 1, wherein: The temperature information includes an average temperature, and a battery pack is composed of a plurality of battery cells. The method further includes: Obtaining the maximum cell temperature and the minimum cell temperature in the battery pack; The average temperature is calculated according to the maximum battery cell temperature and the minimum battery cell temperature.

11. A device for predicting the maximum available capacity of a battery cell, characterized in that: include: an acquisition module, configured to acquire a data set, the data set comprising a plurality of first data segments arranged in a time series, each first data segment comprising current information, voltage information, and temperature information of a battery cell; a first voltage prediction module, configured to input the first preset segment data and the plurality of first segment data into a trained preset model respectively to perform a first voltage prediction, thereby obtaining a plurality of first predicted voltage sequence data, wherein the first preset segment data includes standard operating condition information of battery cell charging; When the predicted voltage corresponding to the first predicted voltage sequence data reaches a first cutoff voltage, stopping the first voltage prediction, acquiring a first time instant and target segment data, where the first time instant is the time instant corresponding to the first cutoff voltage, and the target segment data is the last first segment data input when stopping the first voltage prediction; a second voltage prediction module, configured to input the second preset segment data and a plurality of first segment data starting from the target segment data into the trained preset model for second voltage prediction, thereby obtaining a plurality of second predicted voltage sequence data, wherein the second preset segment data includes standard operating condition information of battery cell discharge; When the predicted voltage corresponding to the second predicted voltage sequence data reaches a second cutoff voltage, stopping the second voltage prediction and acquiring a second moment, where the second moment is the moment corresponding to the second cutoff voltage; a generating module, configured to generate a predicted maximum available capacity of the battery cell based on the standard operating condition information of the battery cell discharge, the first moment, and the second moment; An estimation module is used to estimate the health status of the battery cell according to the predicted maximum available capacity of the battery cell.

12. An energy storage system, characterized in that: The energy storage system includes a battery management system and a battery pack, the battery pack includes a plurality of battery cells, and the battery management system is used to implement the method for predicting the maximum available capacity of a battery cell as described in any one of claims 1 to 10.

Images