Battery cell temperature prediction method, device, equipment and program product

Abstract

The invention relates to the field of battery temperature management, in particular to a battery cell temperature prediction method, device and equipment and a program product. The method comprises the following steps: acquiring the sampling temperature of a sampling battery cell, the position of the sampling battery cell in a battery and the working condition parameter of the sampling battery cell; obtaining the position of a to-be-predicted battery cell in the battery, and determining a related sampling battery cell associated with the to-be-predicted battery cell according to the position of the sampling battery cell and the position of the to-be-predicted battery cell; determining the internal temperature of the related sampling battery cell according to the working condition parameters; and determining the internal temperature of the to-be-predicted battery cell by combining the internal temperature of the related sampling battery cell based on a predetermined temperature prediction model. According to the method, the temperatures of the battery cells except the sampling battery cell in the battery can be obtained through prediction, so that the temperatures of all the battery cells of the battery can be obtained, and more refined management of the battery is facilitated.

Description

Technical Field

[0001] This application relates to the field of battery temperature management, and more particularly to a method, apparatus, device, and program product for predicting the cell temperature of a battery. Background Technology

[0002] The battery cell is the basic unit for generating electricity in a battery. The internal temperature of the battery cell is a key parameter for the battery management system to analyze battery performance.

[0003] When obtaining the internal temperature of a battery cell, the surface temperature of the battery is sampled, and the internal temperature of the battery cell is predicted based on the surface temperature. However, this method can only predict the internal temperature of the battery cell with sampling points, which is not convenient for more refined management of the battery. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, device, and program product for predicting the cell temperature of a battery, in order to solve the problem that the prior art can only predict the internal temperature of the cell with sampling points, which is not convenient for more refined management of the battery.

[0005] A first aspect of this application provides a method for predicting the cell temperature of a battery. The battery includes multiple cells, including a cell to be predicted and a sample cell with surface temperature sampling points. The method includes: acquiring the sampling temperature of the sample cell, the position of the sample cell in the battery, and the operating parameters of the sample cell; acquiring the position of the cell to be predicted in the battery; determining related sample cells associated with the cell to be predicted based on the positions of the sample cells and the cell to be predicted; predicting the internal temperature of the related sample cells based on the operating parameters and the sampling temperatures of the related sample cells; and determining the internal temperature of the cell to be predicted based on a predetermined temperature prediction model and the internal temperatures of the related sample cells.

[0006] In the above scheme, surface temperature sampling points are set at the sampling cells to collect the sampling temperatures of multiple sampling cells and obtain the location of the cell to be predicted. Based on the location of the cell to be predicted and the location of the sampling cells, related sampling cells associated with the cell to be predicted are identified among the sampling cells. Based on the operating parameters and the sampling temperatures of the related sampling cells, the internal temperature of the related sampling cells is predicted. Based on the internal temperature of the related sampling cells, a pre-determined temperature prediction model is used to perform prediction calculations to obtain the internal temperature of the cell to be predicted. Thus, the temperature of cells other than the sampling cells in the battery can be predicted from the internal temperature of the related sampling cells determined by the operating parameters, thereby obtaining the temperature of all cells in the battery, which is beneficial for more refined battery management.

[0007] In conjunction with the first aspect, in a first possible implementation of the first aspect, predicting the internal temperature of the relevant sampled cell based on the aforementioned operating condition parameters and the sampling temperature of the relevant sampled cell includes: detecting whether the relevant sampled cell meets a predetermined thermal imbalance condition based on the aforementioned operating condition parameters; and predicting the internal temperature of the relevant sampled cell based on the sampling temperature of the relevant sampled cell if it is determined from the aforementioned operating condition parameters that the relevant sampled cell meets the predetermined thermal imbalance condition.

[0008] In this embodiment, to more accurately describe the temperature of each cell, the operating parameters of the sampled cells can be obtained. Based on these parameters, it can be determined whether the sampled cells meet the predetermined thermal imbalance conditions. If the surface temperature and internal temperature of a cell are relatively balanced, i.e., the predetermined thermal imbalance conditions are not met, the sampling temperature obtained from the surface temperature sampling point can be directly used as the internal temperature to predict the internal temperature of other cells to be predicted. If the surface temperature and internal temperature of a cell differ significantly (e.g., the heat generated by the cell is greater than the heat dissipated by the cell, the internal temperature of the cell will be significantly higher than the sampling temperature of the cell surface), in order to more accurately manage the battery, the internal temperature of the sampled cells can be predicted based on the sampling temperature of the cells, thus more accurately reflecting the operating status of the cells.

[0009] In conjunction with the first possible implementation of the first aspect, in the second possible implementation of the first aspect, the operating parameters of the sampled battery cell include the charge / discharge rate; determining that the sampled battery cell meets the predetermined thermal imbalance condition based on the operating parameters includes: determining that the sampled battery cell meets the predetermined thermal imbalance condition when the charge / discharge rate is greater than a predetermined rate threshold.

[0010] During battery operation, measuring the internal temperature of the battery is costly and inconvenient for determining the internal and external temperature differences of the cell. To reduce testing costs and improve testing efficiency, this application embodiment can detect the battery's charge rate or discharge rate. If the battery's charge rate or discharge rate is greater than a predetermined rate threshold, it indicates that the internal and external temperature differences of the sampled cell are significant, meeting a predetermined thermal imbalance condition, i.e., the internal and external temperature difference exceeds a predetermined difference threshold. By detecting the charge rate or discharge rate, it is possible to detect whether the sampled cell meets the predetermined thermal imbalance condition in a low-cost and efficient manner.

[0011] In conjunction with the first possible implementation of the first aspect, in the third possible implementation of the first aspect, the operating parameters of the aforementioned sampled battery cell include a first temperature difference between the sampling temperature and the cooling temperature; determining that the aforementioned sampled battery cell meets a predetermined thermal imbalance condition based on the aforementioned operating parameters includes: determining that the aforementioned sampled battery cell meets the predetermined thermal imbalance condition when the aforementioned sampling temperature is greater than a first temperature threshold and a second temperature difference determined based on the input temperature and output temperature of the battery's coolant temperature is greater than a predetermined first temperature difference threshold.

[0012] One way to reduce testing costs is to detect the first temperature difference between the cooling temperature and the sampling temperature of the sampled battery cell. If the input coolant temperature is the same, a higher output coolant temperature indicates that more heat is carried away by the coolant. Furthermore, if the sampling temperature is greater than a first temperature threshold, it indicates that the surface temperature of the battery cell (e.g., the upper surface) is higher. In this case, the difference between the internal temperature and the surface temperature of the sampled battery cell is significant, and the sampled battery cell meets the predetermined thermal imbalance requirement. In either of these two methods—either by charging / discharging rate or by comparing the first temperature threshold with the sampling temperature, the first temperature difference, and the first temperature difference threshold—if any one of these conditions is met, it can be inferred that the sampled battery cell meets the predetermined thermal imbalance condition.

[0013] In conjunction with the first possible implementation of the first aspect, in the fourth possible implementation of the first aspect, the internal temperature of the battery cell to be predicted is determined based on a predetermined temperature prediction model and in conjunction with the internal temperature of the aforementioned relevant sampled battery cells, including: inputting the internal temperature of the aforementioned relevant sampled battery cells into the predetermined temperature prediction model to predict the internal temperature of the battery cell to be predicted.

[0014] When the internal temperature and surface temperature of a battery cell differ significantly, i.e., when the predetermined thermal imbalance requirement is met, in order to obtain accurate operating condition data of other unsampled battery cells, the internal temperature of the sampled battery cell can be obtained through the temperature conduction model of a single battery cell. The internal temperature of the sampled battery cell is then input into the temperature prediction model (based on the temperature conduction model between different battery cells) to predict the internal temperature of the battery cell to be predicted, thereby more accurately reflecting the state information of the battery cell.

[0015] In conjunction with the first possible implementation of the first aspect, in the fifth possible implementation of the first aspect, before determining the internal temperature of the cell to be predicted based on a predetermined temperature prediction model and the internal temperature of the relevant sampled cells, the method further includes: acquiring the heat generated by the cell to be predicted; when the operating parameters indicate that the sampled cells meet predetermined thermal imbalance conditions, determining the internal temperature of the cell to be predicted based on a predetermined temperature prediction model and the internal temperature of the relevant sampled cells, including: inputting the internal temperature of the relevant sampled cells and the heat generated into the predetermined temperature prediction model to predict the internal temperature of the cell to be predicted.

[0016] To further improve the accuracy of cell temperature prediction, the temperature prediction model in this embodiment also includes the heat generated by the cell to be predicted. Based on the heat generated by the battery and the internal temperature of the cell, the internal temperature of the cell to be predicted is determined by the temperature prediction model. Since the temperature prediction model further incorporates the heat generated by the cell, the accuracy of the calculated internal temperature is higher.

[0017] In conjunction with the first possible implementation of the first aspect, in the sixth possible implementation of the first aspect, after detecting whether the relevant sampled cell meets the predetermined thermal imbalance condition based on the above operating condition parameters, the method further includes: if it is determined based on the above operating condition parameters that the sampled cell does not meet the predetermined thermal imbalance condition, the sampling temperature of the sampled cell is taken as the internal temperature of the sampled cell.

[0018] To improve the prediction efficiency of the internal temperature of the battery cell to be predicted, when the sampled battery cell does not meet the predetermined thermal imbalance condition, it indicates that the difference between the internal temperature of the sampled battery cell and the sampling temperature is small. In this case, the sampling temperature of the relevant sampled battery cell can be directly used as the internal temperature of the relevant sampled battery cell, so that the internal temperature of the battery cell to be predicted can be obtained from the internal temperature of the sampled battery cell.

[0019] In a seventh possible implementation of the first aspect, in combination with any one of the first to sixth possible implementations of the first aspect, before determining the internal temperature of the cell to be predicted based on a predetermined temperature prediction model and the sampling temperature of the relevant sampled cells, the method further includes: acquiring model training data, the model training data including the sampling temperature of the sampled cells of the battery and the internal temperature of the cell to be predicted, the positional relationship between the sampled cells and the cell to be predicted, and the operating parameters of the sampled cells; determining the relevant sampled cells based on the positional relationship, and determining the internal temperature of the relevant sampled cells based on the operating parameters; training the temperature prediction model using the internal temperatures of the relevant sampled cells and the cell to be predicted, determining the parameters of the temperature prediction model, and obtaining the trained temperature prediction model.

[0020] Before using a temperature prediction model for forecasting calculations, it is necessary to determine the parameters of the model. These parameters can be determined through fitting calculations or by training a neural network model. Based on the trained temperature prediction model, efficient temperature prediction processing can be easily performed.

[0021] In combination with any one of the first aspect to the sixth possible implementation of the first aspect, in the eighth possible implementation of the first aspect, the above-mentioned temperature sampling points are determined based on the temperature extreme points and distribution balance principle of each row or column of cells in the battery.

[0022] To improve the accuracy of temperature prediction models, multiple regions can be divided on the battery when determining temperature sampling points. Temperature sampling points can be set at the cells with the maximum and / or minimum temperatures in each region. This allows for better acquisition of extreme value data of the cells in the battery. Furthermore, to reduce the collection of too many similar cell temperatures, cells with other non-extreme values ​​can be selected as sampling cells based on the principle of balance. This facilitates more accurate temperature prediction based on extreme value data and improves the accuracy of battery temperature management.

[0023] A second aspect of this application provides a battery cell temperature prediction device, wherein the battery includes a plurality of cells, the plurality of cells including a cell to be predicted and a sampling cell having surface temperature sampling points, and the device includes: The data acquisition unit is used to acquire the sampling temperature of the sampled cell, the position of the sampled cell in the battery, and the operating parameters of the sampled cell. The relevant sampling cell determination unit is used to obtain the position of the cell to be predicted in the battery, and determine the relevant sampling cell associated with the cell to be predicted based on the position of the sampling cell and the position of the cell to be predicted. The first temperature prediction unit is used to predict the internal temperature of the relevant sampled battery cell based on the above operating parameters and the sampling temperature of the relevant sampled battery cell. The second temperature prediction unit is used to determine the internal temperature of the battery cell to be predicted based on a pre-determined temperature prediction model and the internal temperature of the aforementioned sampled battery cell.

[0024] In conjunction with the second aspect, in a first possible implementation of the second aspect, the first temperature prediction unit includes: a condition judgment subunit, used to detect whether the relevant sampled cell meets a predetermined thermal imbalance condition based on the operating parameters; and an internal temperature prediction subunit, used to predict the internal temperature of the relevant sampled cell based on the sampling temperature of the relevant sampled cell when it is determined from the operating parameters that the relevant sampled cell meets the predetermined thermal imbalance condition.

[0025] In conjunction with the first possible implementation of the second aspect, in the second possible implementation of the second aspect, the operating parameters of the sampled battery cell include the charge / discharge rate; the internal temperature prediction subunit is further used to determine that the sampled battery cell meets a predetermined thermal imbalance condition when the charge / discharge rate is greater than a predetermined rate threshold.

[0026] In conjunction with the first possible implementation of the second aspect, in the third possible implementation of the second aspect, the operating parameters of the sampled cell include a first temperature difference between the sampling temperature and the cooling temperature; the internal temperature prediction subunit is further configured to determine that the sampled cell meets a predetermined thermal imbalance condition when the sampling temperature is greater than a first temperature threshold and the second temperature difference determined based on the input temperature and output temperature of the battery coolant is greater than a predetermined first temperature difference threshold.

[0027] In conjunction with the first possible implementation of the second aspect, in the fourth possible implementation of the second aspect, the second temperature prediction unit is further used to input the internal temperature of the aforementioned relevant sampled battery cell into a predetermined temperature prediction model to predict the internal temperature of the aforementioned battery cell to be predicted.

[0028] In conjunction with the first possible implementation of the second aspect, in the fifth possible implementation of the second aspect, the apparatus further includes: a heat generation acquisition unit, used to acquire the heat generation of the battery cell to be predicted; when the operating parameters indicate that the sampled battery cell meets the predetermined thermal imbalance condition, the second temperature prediction unit is further used to input the internal temperature of the relevant sampled battery cell and the heat generation into a predetermined temperature prediction model to predict the internal temperature of the battery cell to be predicted.

[0029] In conjunction with the first possible implementation of the second aspect, in the sixth possible implementation of the second aspect, the aforementioned internal temperature prediction subunit is further configured to use the sampling temperature of the aforementioned sampling cell as the internal temperature of the aforementioned sampling cell.

[0030] In conjunction with any one of the second aspect to the sixth possible implementation of the second aspect, in the seventh possible implementation of the second aspect, the apparatus further includes: a training data acquisition unit, configured to acquire model training data, the model training data including the sampling temperature of the sampled cell of the battery and the internal temperature of the cell to be predicted, the positional relationship between the sampled cell and the cell to be predicted, and the operating parameters of the sampled cell; and a training unit, configured to determine the relevant sampled cell based on the positional relationship, determine the internal temperature of the relevant sampled cell based on the operating parameters, train the temperature prediction model using the sampling temperature of the relevant sampled cell and the internal temperature of the cell to be predicted, determine the parameters of the temperature prediction model, and obtain the trained temperature prediction model.

[0031] In combination with any one of the second aspect to the sixth possible implementation of the second aspect, in the eighth possible implementation of the second aspect, the above-mentioned temperature sampling points are determined based on the temperature extreme points and distribution balance principle of each row or column of cells in the above-mentioned battery.

[0032] A third aspect of this application provides a battery cell temperature prediction device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the battery cell temperature prediction device implements the method described in any of the first aspects.

[0033] A fourth aspect of this application provides a computer program product that, when run on a computer, causes the computer to execute the methods described in the first aspect or its various implementations.

[0034] A fifth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0035] A sixth aspect of this application provides a chip for implementing the methods in the various implementations of the first aspect described above. Specifically, the chip includes a processor for calling and running a computer program from a memory, causing a device equipped with the chip to perform the methods as described in the first aspect or its various implementations.

[0036] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram illustrating an implementation scenario of a battery cell temperature prediction method provided in this application embodiment; Figure 2 This is a schematic diagram illustrating the implementation process of a battery cell temperature prediction method provided in an embodiment of this application. Figure 3 This is a schematic diagram of the cell distribution of a battery provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the training of a temperature prediction model provided in an embodiment of this application; Figure 5 This is a flowchart illustrating a method for determining the internal temperature of a sampled battery cell, provided in an embodiment of this application. Figure 6 This is a schematic diagram illustrating the implementation process of a cell temperature prediction method that includes heat generation, provided in an embodiment of this application. Figure 7 This is a schematic diagram of a battery cell temperature prediction device provided in an embodiment of this application; Figure 8 This is a schematic diagram of a battery cell temperature prediction device provided in an embodiment of this application. Detailed Implementation

[0039] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0040] To illustrate the above-mentioned technical solutions of this application, specific embodiments are described below.

[0041] The battery cell is the smallest energy unit in a battery, and its internal temperature directly determines the battery's performance, lifespan, and safety. To save costs, temperature sensors are usually installed on the surface of a few cells to sample the temperature, and the internal temperature of the corresponding cell is estimated based on the surface temperature of the sampling point. Although the internal temperature of a cell can be predicted from its surface temperature, the temperature of the vast majority of cells without temperature sensors cannot be known, which is not conducive to refined cell management of the battery.

[0042] To address this issue, this application proposes a method for predicting battery cell temperature. While sampling the temperature of a sampled cell with surface temperature sampling points, the location of the cell to be predicted and the sampling cells are determined, thus obtaining the positional relationship between the cell to be predicted and the sampling cells. Based on this positional relationship, related sampling cells associated with the battery to be predicted can be obtained. According to the operating parameters of the related sampling cells, their internal temperatures can be predicted. Using the internal temperatures of the related sampling cells, combined with a temperature prediction model, the internal temperatures of other cells to be predicted that do not have temperature sensors can be predicted. This allows for obtaining the internal temperatures of all battery cells, facilitating refined cell management. After obtaining the temperatures of all cells, the Battery Management System (BMS) can improve the previously coarse-grained control granularity to the "single cell" level, including cell-level early warning of thermal runaway, cell-level dynamic derating, precise correction of cell SOC (State of Charge) / SOH (State of Health), cell-level temperature control, cell-by-cell equalization, cell-level lifespan prediction, and cell-level fault location.

[0043] Figure 1 This is a schematic diagram illustrating an implementation scenario of a battery cell temperature prediction method proposed in this application. Figure 1As shown, this implementation scenario includes a battery 1, a temperature sensor 2, and a cell temperature prediction device 3. The battery 1 contains multiple cells 11. Temperature sensors 2 are installed on the surface of some cells, such as the upper surface. The cells 11 with temperature sensors 2 are designated as sampling cells, and the temperature measured at these sampling cells is the sampling temperature. The sampling cells can be selected from extreme temperature points within the battery. For example, the battery can be divided into multiple regions, and cells with maximum and / or minimum temperatures in each region can be selected as sampling cells. Considering the principle of temperature balance, the middle position of each region can also be designated as a sampling cell. The cell temperature prediction device 3 can be a battery management system or other battery management devices, such as energy storage devices. The cell temperature prediction device 3 acquires the sampling temperature and operating parameters of the sampled cells with surface temperature sampling points in the battery under test, as well as the position of the sampled cells with surface temperature sampling points in the battery; it acquires the position of the cell to be predicted in the battery and determines the positional relationship between the cell to be predicted and the sampled cells; based on the operating parameters and the sampling temperature of the relevant sampled cells, it predicts the internal temperature of the relevant sampled cells; based on a pre-determined temperature prediction model, combined with the internal temperature and positional relationship, it determines the internal temperature of the cell to be predicted. Thus, it can acquire the temperature of all cells in the battery with a small number of temperature sensors, which facilitates more precise battery management.

[0044] Figure 2 This application provides a schematic flowchart of a battery cell temperature prediction method. The battery includes multiple cells, including the cell to be predicted and a sampling cell with surface temperature sampling points. The method is described in detail below: In S201, the sampling temperature of the sampled cell, the position of the sampled cell in the battery, and the operating parameters of the sampled cell are obtained.

[0045] The battery under test in this application embodiment can be a power battery in a vehicle or an energy storage battery in an energy storage device. A battery includes multiple cells. For ease of management, the cells are typically arranged according to predetermined row or column requirements. For example... Figure 3 The cell layout diagram shown depicts a battery with four rows of cells, each row containing 28 cells. However, in practical applications, the choice of the number of rows and the specific number of cells in each row is not limited.

[0046] During battery operation, the battery temperature changes due to heat generated by internal resistance and chemical reactions. Therefore, it is necessary to obtain the temperature of the battery cells to enable precise control and management of the cells. However, installing a temperature sensor at each battery cell would incur significant costs.

[0047] Therefore, this application embodiment makes predictions based on the sampling temperatures obtained from a small number of sampled cells. Based on the sampling temperatures of the sampled cells, it predicts the internal temperatures of other cells that are not sampled by temperature sensors, thereby achieving refined battery management at low cost.

[0048] To improve the effectiveness of the sampling cells, i.e., the temperature sampling point settings, the embodiments of this application can be determined based on the temperature extreme points and distribution balance principle of each row or column of cells in the battery.

[0049] for example Figure 3 As shown, when dividing the battery into multiple regions, it can be divided into four rows. First, when determining the temperature sampling points for the cells in the first row, since no temperature sampling points have been set previously, they can be set only based on the extreme temperature points. Temperature sampling points can be set in the middle and at both ends of the row. When setting the temperature sampling points for the second row, since temperature sampling points already exist in the first row, considering that the temperatures of nearby locations are relatively similar, to avoid collecting too many temperatures from cells in close proximity, the principle of balanced distribution is prioritized. Therefore, the temperature sampling points for the second row can be set in the middle of the temperature sampling points in the first row. When considering the temperature sampling points for the third row, since the extreme temperature points in the third row are far from the temperature sampling points in the second row, the extreme temperature points in the third row, including the cells with temperature peaks and valleys, can be directly used as temperature sampling points. Following a similar method to the second row, the temperature sampling points for the fourth row can be determined, including the middle position of the temperature sampling points in the third row. In addition, in order to effectively compare the temperature of each row, a temperature sampling point can be set at the same corresponding position, such as the beginning of each row, so that the temperature of each row can be compared based on the sampling temperature obtained at the beginning of the row.

[0050] The location of the sampling cell can be determined after the temperature sensor is set up. For cells arranged in rows and columns, the location of the sampling cell can be determined by the row number and column number. For example... Figure 3 As shown, the sampling cell positions include the first row, first column, the first row, sixteenth column, and the first row, twenty-eighth column, etc.

[0051] The temperature sensor can include, for example, an NTC thermistor, a thermocouple, or an infrared temperature sensing chip. The temperature sensor can be fixed to the surface of the battery cell using thermally conductive adhesive, such as on the upper surface of the cell, facilitating installation and maintenance.

[0052] The operating parameters of the sampled battery cell may include at least one of the following parameters: charge rate, discharge rate, surface temperature, and cooling temperature.

[0053] In S202, the position of the cell to be predicted in the battery is obtained, and the relevant sampled cells associated with the cell to be predicted are determined based on the position of the sampled cells and the position of the cell to be predicted.

[0054] The relevant sampled cells are those cells that are associated with the cell to be predicted and can be used to predict the internal temperature of the cell to be predicted.

[0055] The battery cell to be predicted in this embodiment can be any battery cell without a temperature sensor. The position of the battery cell to be predicted can be determined in a similar way to that of the sampled battery cell, such as the position of the battery cell to be predicted being in the second row and third column.

[0056] After determining the location of the sampled cell and the cell to be predicted, the relevant sampled cells associated with the cell to be predicted can be determined based on their locations. These are the sampled cells used to predict and calculate the internal temperature of the cell to be predicted.

[0057] When determining the relevant sampled cells associated with the cell to be predicted, the associated sampled cells can be determined based on the interval distance. The interval distance includes row interval distance and column interval distance. Generally, the interval distance between cells in the same row is small, while the interval distance between cells in the same column is large. Furthermore, at the same interval distance, the thermal coupling efficiency between cells in the same row differs from that between cells in the same column. The thermal coupling distance can be determined based on the interval distance and the thermal coupling coefficient corresponding to the interval pattern (row interval and column interval). Sampled cells can then be screened according to a predetermined thermal coupling distance threshold to determine the relevant sampled cells used for prediction calculations. However, this is not the only limitation; relevant sampled cells can also be determined based on parameters such as the heat transfer efficiency of the heat transfer material and distance.

[0058] For example, 'a' represents the row spacing distance (unit: grid) between the cell to be predicted and the sampled cell in the row direction, and 'b' represents the column spacing distance (unit: grid) between the cell to be predicted and the sampled cell in the column direction. The thermal coupling coefficient for the row spacing distance is x1, and the thermal coupling coefficient for the column spacing distance is x2. Therefore, the thermal coupling distance is... If the predetermined thermal coupling distance threshold is Lt, then if the thermal coupling distance L1 between a sampled cell and the cell to be predicted is greater than Lt, the sampled cell is ignored; if the thermal coupling distance L1 between the sampled cell and the cell to be predicted is less than or equal to Lt, then it is determined as the relevant sampled cell for calculating the cell to be predicted.

[0059] In one possible implementation, after the temperature of the battery cell is predicted by a temperature prediction model, the cell can be updated to a cell with a known temperature. This cell with a known temperature can be used as a sample cell, together with the original sample cell, to determine the internal temperature of the cell to be predicted.

[0060] In S203, based on the above operating parameters and the sampling temperature of the above-mentioned related sampled cells, the internal temperature of the above-mentioned related sampled cells is predicted.

[0061] This application embodiment can determine whether the sampled cell meets the predetermined thermal imbalance condition based on the value of the operating parameters. If the thermal imbalance condition is met, the internal temperature of the sampled cell can be predicted through the sampling temperature of the relevant sampled cell. If the thermal imbalance condition is not met, that is, the sampled cell is in a thermal equilibrium state, the sampling temperature of the relevant sampled cell can be directly used as the internal temperature of the relevant sampled cell.

[0062] In S204, based on a predetermined temperature prediction model and combined with the internal temperature of the aforementioned sampled cells, the internal temperature of the cell to be predicted is determined.

[0063] The temperature prediction model in this embodiment can be a fitted curve of the temperature of each sampled cell, or it can be a learning model such as a neural network model. The fitted curve can be a first-order curve, a second-order curve, or other higher-order curves.

[0064] After determining one or more sampled cells for calculation based on their positional relationships, the temperatures of the relevant sampled cells can be input into a fitted curve. The internal temperature of the cell to be predicted can then be calculated based on pre-determined weighting coefficients on the fitted curve. Alternatively, the temperatures of the sampled cells can be input into a pre-trained neural network model, which will then output the internal temperature of the cell to be predicted.

[0065] For example, the fitted curve can be represented as: Where n represents the number of sampled cells used for prediction, and k1, k2…k n The weighting coefficients for each relevant sampled cell, T1, T2…T n Let f(t) be the sampling temperature of each relevant sampled cell, and f(t) be the internal temperature of the cell to be predicted.

[0066] Alternatively, the fitted curve can also be represented as a quadratic or higher-order equation, for example, the fitted curve can be represented as: Among them, k i1 k ij2 k i3 T represents the weighting coefficient. i T j Let f(t) be the sampling temperature of two related sampled cells, and f(t) be the internal temperature of the cell to be predicted.

[0067] Before performing calculations using fitted curves or neural network models, a large amount of model training data can be obtained, and the training process can be as follows: Figure 4As shown, it includes: In S401, obtain the model training data.

[0068] The model training data includes the sampling temperature of the sampled cells of the battery and the internal temperature of the cell to be predicted, the positional relationship between the sampled cells and the cell to be predicted, and the operating parameters of the sampled cells.

[0069] The model training data includes the sampled cell temperature, the temperature of the cell to be predicted, and the positional relationship between the sampled cell and the cell to be predicted. If the difference between the surface temperature and the internal temperature of the cell is small, the sampled temperature of the sampled cell and the internal temperature of the cell to be predicted can be detected by a temperature sensor placed at the surface temperature sampling point. If the difference between the surface temperature and the internal temperature of the cell is large, a temperature sensor can be placed inside the cell to accurately obtain the internal temperature of both the sampled and predicted cells. Alternatively, the internal temperatures of both cells can be obtained through simulation modeling.

[0070] In S402, the relevant sampling cells are determined based on the above positional relationship, and the internal temperature of the relevant sampling cells is determined based on the above operating parameters.

[0071] The thermal coupling distance between the sampled cell and the cell to be predicted can be determined based on their positional relationship. The thermal coupling distance is then compared with a predetermined thermal coupling distance threshold, and the sampled cell whose thermal coupling distance is less than the thermal coupling distance threshold is identified as the relevant sampled cell.

[0072] The method is not limited to determining the relevant sampled cells by thermal coupling distance; it can also determine the relevant sampled cells by detecting and comparing thermal resistance and Euclidean distance.

[0073] In this embodiment, the accuracy of the neural network model or the fitting precision of the fitting curve can be determined by adjusting thresholds such as the thermal coupling distance threshold, and the threshold corresponding to the highest accuracy or fitting precision can be selected for screening related sampled cells.

[0074] In S403, the temperature prediction model is trained by sampling the internal temperature of the battery cell and the internal temperature of the battery cell to be predicted, the parameters of the temperature prediction model are determined, and the trained temperature prediction model is obtained.

[0075] By using the sampled temperature of relevant battery cells and the internal temperature of the battery cell to be predicted, a temperature prediction model can be trained. After training, the parameters of the temperature prediction model can be determined, and the trained temperature prediction model can be obtained.

[0076] In training the parameters of the fitting curve, the sampling temperature of the relevant sampled cells and the internal temperature of the cell to be predicted can be input into the equation corresponding to the fitting curve. By adjusting the parameters in the fitting curve, the fitting error of the fitting curve is made to be less than a predetermined error threshold, thereby completing the training of the fitting curve equation.

[0077] When training the learning model, the sampled temperature of the relevant sampled cells can be input into the learning model. The learning model calculates and outputs the predicted temperature of the cell to be predicted. The calculated predicted temperature is compared with the internal temperature of the cell to be predicted in the training data. The parameters in the learning model are adjusted based on the difference between the two until the difference is less than a predetermined difference threshold, thus completing the training of the learning model.

[0078] To improve the accuracy of predicting the internal temperature of the battery cell, this embodiment of the application can determine the prediction path based on battery operating parameters before using the temperature prediction model to predict the temperature. This includes predicting directly from the surface temperature or predicting from the internal temperature of the battery cell. This decision-making process can be as follows: Figure 5 As shown, it includes: In S501, the relevant sampled cells are checked to see if they meet the predetermined thermal imbalance conditions based on the above operating parameters.

[0079] Since directly measuring the internal temperature of the battery cell is costly and complicated, the operating parameters in this application embodiment may include parameters that indirectly reflect the internal and external temperature differences of the sampled battery cell, such as charging rate, discharging rate, surface temperature, and cooling temperature.

[0080] The temperature difference between the surface and internal temperatures of a battery cell is related to its heat generation and dissipation. If the cell generates a large amount of heat, the heat dissipation will be less than the heat generated, leading to an increased internal and external temperature difference. Therefore, this difference can be detected using operating parameters that generate significant heat, such as the cell's charging or discharging rate. Specifically, if the battery's charging or discharging rate is detected to be greater than a predetermined threshold, the sampled cell is determined to meet a predetermined thermal imbalance condition, meaning the internal and external temperature difference of the sampled cell is greater than a predetermined temperature difference threshold.

[0081] Furthermore, the sampling temperature of the battery cell and the temperature of the coolant used to cool the battery can be used to comprehensively detect whether the battery cell is in a state of thermal imbalance. For example, if the detected sampling temperature (usually the temperature of the top surface of the battery cell) is greater than a first temperature threshold, it indicates that the current temperature of the battery cell is high. At the same time, if the second temperature difference between the input and output temperatures of the coolant is greater than a predetermined first temperature difference threshold, it indicates that the coolant is carrying away a lot of heat, and the battery cell is in a high-heat-generating operating state. In this case, the internal and external temperature difference of the battery cell is greater than the predetermined temperature difference threshold, which determines that the battery cell meets the predetermined thermal imbalance condition.

[0082] In S502, if the relevant sampled cell meets the predetermined thermal imbalance condition based on the above operating condition parameters, the internal temperature of the relevant sampled cell is predicted based on the sampling temperature of the relevant sampled cell.

[0083] When the battery cell meets the predetermined thermal imbalance condition based on the operating parameters, i.e., the temperature difference between the inside and outside of the battery cell is large, it is not convenient to directly use the sampling temperature to determine the internal temperature of the battery cell to be predicted. Therefore, the embodiments of this application can predict the internal temperature of the sampled battery cell based on the sampling temperature of the sampled battery cell (usually the sampling temperature of the upper surface), and then predict the internal temperature of the battery cell to be predicted by using a temperature prediction model determined based on the heat transfer inside the battery cell (to distinguish between internal temperature prediction and external temperature prediction, the temperature prediction model used for internal temperature prediction can be called the internal temperature prediction model, and the temperature prediction model used for external temperature prediction can be called the external temperature prediction model).

[0084] When predicting the internal temperature of a sampled battery cell based on its sampled temperature, one can set one or more temperature sampling points on the cell surface to collect the sampled temperature. Based on these sampling temperatures and the weighting coefficients of each sampling point in a pre-determined temperature conduction model, the internal temperature of the sampled battery cell can be calculated. Alternatively, a learning model such as a neural network model can be used to determine the relationship between each sampling temperature and the internal temperature of the sampled battery cell.

[0085] In one possible implementation, when the temperature difference between the inside and outside of the sampled cell is small and the predetermined thermal imbalance condition is not met, in order to improve the cell temperature prediction efficiency, the sampling temperature of the relevant sampled cell can be input into a pre-determined temperature prediction model. The sampling temperature of the relevant sampled cell can be directly calculated through the temperature prediction model to obtain the surface temperature of the cell to be predicted. Under this condition, the difference between the surface temperature and the internal temperature of the cell to be predicted is small, and the predicted surface temperature of the cell to be predicted can be directly used as the internal temperature of the cell to be predicted.

[0086] In this embodiment of the application, to further improve the accuracy of temperature prediction, a comprehensive prediction can be made by combining the heat generation factors of the battery cell. The prediction process can be as follows: Figure 6 As shown, it includes: In S601, the heat generation of the battery cell to be predicted is obtained.

[0087] The heat generation of the cell to be predicted is related to the current, including the heat generated by the battery chemical reaction and the heat generated by the cell's internal resistance when the current flows through it. The heat generation of the cell under different current conditions can be determined by collecting and calibrating multiple sets of data, or by simulation.

[0088] In S602, the internal temperature of the aforementioned sampled battery cell and the aforementioned heat generation are input into a pre-determined temperature prediction model to predict the internal temperature of the battery cell to be predicted.

[0089] The temperature prediction model can be an equation of the fitted curve or a learning model. This equation can be a linear equation or an equation of degree two or higher.

[0090] For example, the fitted curve of a linear equation can be represented as: Where n represents the number of sampled cells used for prediction, and k1, k2…k n The weighting coefficients for each relevant sampled cell, T1, T2…T n Let f(t) be the sampling temperature of each relevant sampled cell, f(t) be the internal temperature of the cell to be predicted, and Q(i) be the heat generated by the cell to be predicted.

[0091] Similarly, higher-order equations can be expressed as: , where k i1 k ij2 k i3 T represents the weighting coefficient. i T j Let f(t) be the sampling temperature of two related sampled cells, f(t) be the internal temperature of the cell to be predicted, and Q(i) be the heat generated by the cell to be predicted.

[0092] When using a learning model to perform temperature prediction calculations, the sampled temperature of the relevant sampled cells, combined with the heat generated by the cell to be predicted, can be input into the learning model, and the internal temperature of the cell to be predicted can be calculated through the learning model.

[0093] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0094] Figure 7 This is a schematic diagram of a cell temperature prediction device proposed in an embodiment of this application. The battery under test includes multiple cells, and the multiple cells include the cell to be predicted and a sampling cell with surface temperature sampling points. The device includes: The data acquisition unit 701 is used to acquire the sampling temperature of the sampled cell, the position of the sampled cell in the battery, and the operating parameters of the sampled cell.

[0095] The relevant sampling cell determination unit 702 is used to obtain the position of the cell to be predicted in the battery, and determine the relevant sampling cell associated with the cell to be predicted based on the position of the sampling cell and the position of the cell to be predicted.

[0096] The first temperature prediction unit 703 is used to predict the internal temperature of the relevant sampled battery cell based on the aforementioned operating parameters and the sampling temperature of the relevant sampled battery cell. The second temperature prediction unit 704 is used to determine the internal temperature of the battery cell to be predicted based on a pre-determined temperature prediction model and in combination with the internal temperature of the aforementioned sampled battery cell.

[0097] In a possible implementation, the first temperature prediction unit includes: a condition judgment subunit, used to detect whether the relevant sampled cell meets a predetermined thermal imbalance condition based on the operating parameters; and an internal temperature prediction subunit, used to predict the internal temperature of the relevant sampled cell based on the sampling temperature of the relevant sampled cell when it is determined from the operating parameters that the relevant sampled cell meets the predetermined thermal imbalance condition.

[0098] In a possible implementation, the operating parameters of the sampled battery cell include the charge / discharge rate; the internal temperature prediction subunit is also used to determine that the sampled battery cell meets a predetermined thermal imbalance condition when the charge / discharge rate is greater than a predetermined rate threshold.

[0099] In a possible implementation, the operating parameters of the sampled cell include a first temperature difference between the sampling temperature and the cooling temperature; the internal temperature prediction subunit is further configured to determine that the sampled cell meets a predetermined thermal imbalance condition when the sampling temperature is greater than a first temperature threshold and a second temperature difference determined based on the input temperature and output temperature of the battery's coolant temperature is greater than a predetermined first temperature difference threshold.

[0100] In a possible implementation, the second temperature prediction unit is also used to input the internal temperature of the aforementioned relevant sampled battery cell into a predetermined temperature prediction model to predict the internal temperature of the aforementioned battery cell to be predicted.

[0101] In a possible implementation, the above-mentioned device further includes: a heat generation acquisition unit, used to acquire the heat generation of the battery cell to be predicted; when the operating parameters indicate that the sampled battery cell meets the predetermined thermal imbalance condition, the second temperature prediction unit is further used to input the internal temperature of the relevant sampled battery cell and the heat generation into a predetermined temperature prediction model to predict the internal temperature of the battery cell to be predicted.

[0102] In a possible implementation, the aforementioned internal temperature prediction subunit is further configured to use the sampling temperature of the aforementioned sampling cell as the internal temperature of the aforementioned sampling cell.

[0103] In a possible implementation, the above apparatus further includes: a training data acquisition unit, configured to acquire model training data, the model training data including the sampling temperature of the sampled cells of the battery and the internal temperature of the cell to be predicted, the positional relationship between the sampled cells and the cell to be predicted, and the operating parameters of the sampled cells; and a training unit, configured to determine the relevant sampled cells based on the positional relationship, determine the internal temperature of the relevant sampled cells based on the operating parameters, train the temperature prediction model using the sampling temperature of the relevant sampled cells and the internal temperature of the cell to be predicted, determine the parameters of the temperature prediction model, and obtain the trained temperature prediction model.

[0104] In a possible implementation, the temperature sampling points are determined based on the temperature extreme points and distribution balance principle of each row or column of cells in the battery.

[0105] Figure 8 This is a schematic diagram of a battery cell temperature prediction device provided in an embodiment of this application. Figure 8 As shown, the battery cell temperature prediction device 8 of this embodiment includes: a processor 80, a memory 81, and a computer program 82 stored in the memory 81 and executable on the processor 80, such as a cell temperature prediction program. When the processor 80 executes the computer program 82, it implements the steps in the various cell temperature prediction method embodiments described above. Alternatively, when the processor 80 executes the computer program 82, it implements the functions of each module / unit in the various device embodiments described above.

[0106] For example, the computer program 82 described above can be divided into one or more modules / units, which are stored in the memory 81 and executed by the processor 80 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 82 in the battery cell temperature prediction device 8.

[0107] The cell temperature prediction device 8 for the aforementioned battery can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The aforementioned cell temperature prediction device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will understand that... Figure 8This is merely an example of a battery cell temperature prediction device 8 and does not constitute a limitation on the battery cell temperature prediction device 8. It may include more or fewer components than shown, or combine certain components, or different components. For example, the battery cell temperature prediction device described above may also include input / output devices, network access devices, buses, etc.

[0108] The processor 80 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0109] The aforementioned memory 81 can be an internal storage unit of the battery cell temperature prediction device 8, such as a hard disk or memory of the battery cell temperature prediction device 8. The aforementioned memory 81 can also be an external storage device of the battery cell temperature prediction device 8, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the battery cell temperature prediction device 8. Furthermore, the aforementioned memory 81 can include both internal storage units and external storage devices of the battery cell temperature prediction device 8. The aforementioned memory 81 is used to store the aforementioned computer program and other programs and data required by the battery cell temperature prediction device. The aforementioned memory 81 can also be used to temporarily store data that has been output or will be output.

[0110] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0111] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0112] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0113] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0114] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated modules / units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by hardware related to computer program instructions. The computer program described above can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program described above includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium described above can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0117] In addition, this application also provides a computer program product that, when run on a computer, causes the computer to execute the methods in the above-described implementations.

[0118] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method of predicting a temperature of a battery cell, the method comprising: The battery includes a plurality of battery cells, the plurality of battery cells including a to-be-predicted battery cell and a sampling battery cell provided with a surface temperature sampling point, and the method includes: obtaining a sampling temperature of the sampling battery cell, a position of the sampling battery cell in the battery, and a working condition parameter of the sampling battery cell; obtaining a position of the to-be-predicted battery cell in the battery, and determining a relevant sampling battery cell associated with the to-be-predicted battery cell according to the position of the sampling battery cell and the position of the to-be-predicted battery cell; predicting an internal temperature of the relevant sampling battery cell according to the working condition parameter and the sampling temperature of the relevant sampling battery cell; determining an internal temperature of the to-be-predicted battery cell based on a predetermined temperature prediction model and in combination with the internal temperature of the relevant sampling battery cell.

2. The method of claim 1, wherein, The method further includes: detecting whether the relevant sampling battery cell satisfies a predetermined thermal imbalance condition according to the working condition parameter; predicting the internal temperature of the relevant sampling battery cell according to the sampling temperature of the relevant sampling battery cell in a case where it is determined that the relevant sampling battery cell satisfies the predetermined thermal imbalance condition according to the working condition parameter.

3. The method of claim 2, wherein, The working condition parameter of the sampling battery cell includes a charge-discharge rate; determining that the sampling battery cell satisfies the predetermined thermal imbalance condition in a case where the charge-discharge rate is greater than a predetermined rate threshold. The working condition parameter of the sampling battery cell includes a first temperature difference between the sampling temperature and a cooling temperature; 4. The method of claim 2, wherein, determining that the sampling battery cell satisfies the predetermined thermal imbalance condition in a case where the sampling temperature is greater than a first temperature threshold, and a second temperature difference determined based on an input temperature and an output temperature of a cooling liquid temperature of the battery is greater than a predetermined first temperature difference threshold. The method further includes: inputting the internal temperature of the relevant sampling battery cell into the predetermined temperature prediction model to predict the internal temperature of the to-be-predicted battery cell.

5. The method of claim 2, wherein, The method further includes: obtaining a heat generation amount of the to-be-predicted battery cell; 6. The method of claim 2, wherein, determining the internal temperature of the to-be-predicted battery cell based on the predetermined temperature prediction model and in combination with the internal temperature of the relevant sampling battery cell when the working condition parameter indicates that the sampling battery cell satisfies the predetermined thermal imbalance condition, including: inputting the internal temperature of the relevant sampling battery cell and the heat generation amount into the predetermined temperature prediction model to predict the internal temperature of the to-be-predicted battery cell. The method further includes: detecting whether the relevant sampling battery cell satisfies a predetermined thermal imbalance condition according to the working condition parameter; 7. The method of claim 2, wherein, ​ In a case where it is determined according to the working condition parameter that the sampled battery cell does not satisfy the predetermined thermal imbalance condition, the sampling temperature of the sampled battery cell is taken as the internal temperature of the sampled battery cell.

8. The method according to any one of claims 1 to 7, characterized in that, Before determining the internal temperature of the battery cell to be predicted based on the predetermined temperature prediction model and in combination with the internal temperature of the relevant sampled battery cell, the method further comprises: obtaining model training data, the model training data comprising the sampling temperature of the sampled battery cell of the battery, the internal temperature of the battery cell to be predicted, the positional relationship between the sampled battery cell and the battery cell to be predicted, and the working condition parameter of the sampled battery cell; determining a relevant sampled battery cell according to the positional relationship and determining the internal temperature of the relevant sampled battery cell according to the working condition parameter; training the temperature prediction model by using the internal temperature of the relevant sampled battery cell and the internal temperature of the battery cell to be predicted, determining the parameters of the temperature prediction model, and obtaining the trained temperature prediction model.

9. The method according to any one of claims 1 to 7, characterized in that, The temperature sampling points are determined according to the temperature extreme points in each row or each column of battery cells in the battery and the distribution balance principle.

10. A battery cell temperature prediction device, characterized by comprising: The battery comprises a plurality of battery cells, the plurality of battery cells comprising a battery cell to be predicted and a sampled battery cell provided with a surface temperature sampling point, and the device comprises: a data acquisition unit configured to acquire the sampling temperature of the sampled battery cell, the position of the sampled battery cell in the battery, and the working condition parameter of the sampled battery cell; a relevant sampled battery cell determination unit configured to acquire the position of the battery cell to be predicted in the battery, and determine a relevant sampled battery cell associated with the battery cell to be predicted according to the position of the sampled battery cell and the position of the battery cell to be predicted; a first temperature prediction unit configured to predict the internal temperature of the relevant sampled battery cell according to the working condition parameter and the sampling temperature of the relevant sampled battery cell; a second temperature prediction unit configured to determine the internal temperature of the battery cell to be predicted based on a predetermined temperature prediction model and in combination with the internal temperature of the relevant sampled battery cell.

11. A battery cell temperature prediction device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program, so that the battery cell temperature prediction device implements the method according to any one of claims 1-9.

12. A computer program product comprising computer program instructions, characterised in that, The computer program is executed, so that the method according to any one of claims 1-9 is performed.

Images