A battery capacity prediction method, prediction device and related equipment

Abstract

The present invention discloses a battery capacity prediction method, prediction device and related equipment, and relates to the field of battery technology; wherein the battery capacity prediction method includes the following steps: discharge until the battery pack is exhausted; obtain data of each battery cell in the battery pack based on a data interface and predict the capacity of each battery cell in combination with the inherent properties of the battery cell; obtain data of each battery cell in the battery pack based on a data interface and predict the remaining power of the battery cell in combination with the corresponding relationship between the battery cell voltage and power; obtain the predicted battery capacity based on the capacity of each battery cell and the remaining power of each battery cell. The present invention only needs to analyze the data at the end of battery discharge to complete the prediction, shortening the capacity prediction time and improving the test efficiency; obtain the data of each battery cell through the data interface to predict the capacity of each battery cell and the remaining power of the battery cell, and then obtain the predicted battery capacity, thereby improving the accuracy of the prediction.

Description

Technical Field

[0001] The present invention relates to the field of battery technology, and in particular to a battery capacity prediction method, a prediction device and related equipment. Background Art

[0002] Existing battery capacity prediction technologies usually require multiple complete charge and discharge cycles, which is not only time-consuming but also consumes a lot of energy.

[0003] Additionally, these techniques often have difficulty accurately handling changes in battery performance under different conditions, especially when the battery is at different temperatures and usage states. Summary of the invention

[0004] To solve the above problems, the present invention provides a battery capacity prediction method, comprising the following steps:

[0005] Discharge until the battery pack is exhausted;

[0006] Based on the data interface, the data of each cell in the battery pack is obtained and the capacity of each cell is predicted by combining the inherent properties of the cell;

[0007] Based on the data interface, the data of each battery cell in the battery pack is obtained and the remaining battery capacity is predicted based on the corresponding relationship between the battery cell voltage and the battery capacity;

[0008] The predicted battery capacity is obtained based on the capacity of each battery cell and the remaining power of each battery cell.

[0009] In one embodiment, the acquiring of data of each battery cell in the battery pack based on the data interface and predicting the capacity of each battery cell includes acquiring the internal resistance, OCV voltage, temperature and standing time of each battery cell; excessive internal resistance of each battery cell will lead to reduced capacity of the battery cell; predicting the capacity of the battery cell based on the OCV voltage; changes in the temperature will affect the internal resistance of each battery cell; and different standing times will cause changes in the OCV voltage.

[0010] In one embodiment, the method corrects the predicted result of the capacity of each battery cell based on the internal resistance, OCV voltage, temperature and standing time of each battery cell.

[0011] In one embodiment, the method further includes setting a capacity threshold, comparing the cell capacity prediction result with the capacity threshold, and determining whether the battery can work normally.

[0012] In one embodiment, obtaining data of each battery cell in the battery pack based on the data interface and predicting the remaining power of the battery cells includes obtaining the voltage of each battery cell, obtaining a fitting curve of the voltage and power of each battery cell using a neural network model, and obtaining the remaining power of the battery cell based on the corresponding relationship and the voltage of each battery cell.

[0013] In one embodiment, acquiring data of each battery cell in the battery pack based on the data interface and predicting the remaining power of the battery cells includes acquiring temperature and resistance, and adjusting the fitting curve of voltage and power of each battery cell based on the temperature and the resistance.

[0014] In one embodiment, the data interface acquires the battery cell data by acquiring a unique serial number of each battery cell, and determines a corresponding relationship between the battery cell data and each battery cell based on the unique serial number.

[0015] The present invention also provides a battery capacity prediction device using any of the above battery capacity prediction methods, comprising:

[0016] A data interface module, the data interface module is used to obtain data of each battery cell and perform exception processing on the data of each battery cell;

[0017] A cell capacity prediction module, wherein the cell capacity prediction module receives the cell data acquired by the data interface module to perform cell capacity prediction;

[0018] A battery cell remaining power prediction module, wherein the battery cell remaining power prediction module receives the battery cell data acquired by the data interface module to perform battery cell remaining power prediction;

[0019] A battery capacity prediction module is used to obtain a battery capacity prediction value based on a cell capacity prediction value and a cell remaining power prediction value.

[0020] The present invention provides an electronic device, comprising: a memory and a processor coupled to each other, wherein the processor is used to execute program instructions stored in the memory to implement the battery capacity prediction method as described in any one of the above items.

[0021] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores program data, and the program data can be executed by a processor to implement the battery capacity prediction method as described in any one of the above items.

[0022] Beneficial effects of the present invention: Different from the prior art, the present invention discloses a battery capacity prediction method, prediction device and related equipment; wherein the battery capacity prediction method includes the following steps: discharge until the battery pack is exhausted; obtain the data of each battery cell in the battery pack based on the data interface and predict the capacity of each battery cell; obtain the data of each battery cell in the battery pack based on the data interface and predict the remaining power of the battery cell; obtain the predicted battery capacity based on the capacity of each battery cell and the remaining power of each battery cell. The present invention only needs to analyze the data at the end of battery discharge to complete the prediction, shortening the capacity prediction time and improving the test efficiency; obtain the data of each battery cell through the data interface to predict the capacity of each battery cell and the remaining power of the battery cell, and then obtain the predicted battery capacity, thereby improving the accuracy of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of a flow chart of an embodiment of a battery capacity prediction method provided by the present invention;

[0024] Figure 2 A schematic diagram of the structure of an embodiment of a battery prediction device provided by the present invention;

[0025] Figure 3 A schematic diagram of the structure of an electronic device according to an embodiment of the present invention;

[0026] Figure 4 A schematic diagram of the structure of an embodiment of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0027] The following are specific embodiments of the present invention and the accompanying drawings to further describe the technical solution of the present invention, but the present invention is not limited to these embodiments.

[0028] Due to manufacturing differences, aging or other differences in characteristics, the cells in a battery pack are often not completely consistent. The differences between different cells will cause the battery pack to perform unevenly during the charging and discharging process, which in turn affects the overall capacity of the battery pack. However, existing prediction methods often only consider the overall state of the battery and make predictions based directly on the overall state of the battery, while ignoring the capacity differences caused by the inconsistency between cells, and failing to deeply analyze and consider the impact of the differences in individual cells.

[0029] See also Figure 1 As shown, Figure 1 A schematic flow chart of an embodiment of a battery capacity prediction method provided by the present invention; it should be clarified that the battery capacity prediction method of the present invention can be applied to lithium batteries, nickel-hydrogen batteries, sodium-ion batteries, etc.; no limitation is made here.

[0030] Step S11: Discharge until the battery pack is exhausted. By discharging until the battery pack is exhausted, the capacity of the battery in a fully discharged state can be measured; fully discharging can accurately evaluate the actual capacity of the battery and the capacity consistency between each battery cell.

[0031] Step S12: Based on the data interface, the data of each cell in the battery pack is obtained and combined with the inherent properties of the cell to predict the capacity of each cell; the inherent properties of the cell include the cell model, manufacturing batch and chemical composition, etc.; considering the inherent properties of the cell is helpful for personalized prediction and improves the prediction accuracy; directly obtaining the real-time data of each cell in the battery pack through the data interface, such as voltage, current, temperature, etc., can provide more detailed information for training the prediction model. By obtaining the data of the cell in real time and then monitoring the status of the cell, safety hazards can be discovered in time and corresponding safety measures can be taken.

[0032] Step S13: Based on the data interface, the data of each battery cell in the battery pack is obtained, and the remaining power of the battery cell is predicted in combination with the corresponding relationship between the battery cell voltage and power; the relationship between voltage and power is learned through a neural network model to improve the accuracy of predicting the remaining power of the battery cell; based on real-time voltage data, real-time prediction of the remaining power of the battery cell can be achieved; by obtaining detailed data of each battery cell, balanced charging / discharging between the battery cells can be better achieved to ensure the optimal performance of the battery pack; predicting the remaining power of the battery cell helps to more effectively manage the capacity allocation of the battery pack and ensure the overall performance of the battery pack.

[0033] Step S14: derive the predicted capacity of the battery based on the capacity of each battery cell and the remaining power of each battery cell; add up the predicted capacities of all battery cells to obtain the predicted capacity of the battery pack, and add up the predicted remaining power of all battery cells to obtain the predicted remaining power of the battery pack; combine the "charge high and discharge low" strategy of the battery pack to convert the predicted battery cell capacity and remaining power into the overall predicted capacity of the battery pack.

[0034] In summary, the present invention discloses a battery capacity prediction method, including the following steps: discharge until the battery pack is exhausted; obtain data of each battery cell in the battery pack based on a data interface and predict the capacity of each battery cell in combination with the inherent properties of the battery cell; obtain data of each battery cell in the battery pack based on a data interface and predict the remaining power of the battery cell; obtain the predicted capacity of the battery based on the capacity of each battery cell and the remaining power of each battery cell. The present invention only needs to analyze the data at the end of the battery discharge to complete the prediction, shortening the capacity prediction time and improving the test efficiency; obtain the data of each battery cell through the data interface to predict the capacity of each battery cell and the remaining power of the battery cell, and then obtain the predicted capacity of the battery, thereby improving the accuracy of the prediction.

[0035] In one embodiment, after the battery pack is fully discharged, the battery capacity is predicted, and after the prediction is completed, the battery pack is charged and the charging is stopped after the battery pack is charged to 50%; the battery pack is shipped out after it is in a half-charged state.

[0036] In one embodiment, obtaining data of each battery cell in a battery pack based on a data interface and predicting the capacity of each battery cell includes obtaining the internal resistance, OCV voltage, temperature and standing time of each battery cell; excessive internal resistance of each battery cell will lead to a reduction in the battery cell capacity, and a higher internal resistance will cause the battery voltage to drop rapidly when discharging at a large current, thereby affecting the effective discharge time of the battery; the OCV voltage refers to the voltage across the battery when there is no load, and the battery will have different OCV voltages under different states of charge; the capacity of the battery cell is predicted based on the OCV voltage; changes in temperature will affect the internal resistance of the battery cells, and changes in temperature will also affect the chemical reaction rate of the battery, thereby affecting the discharge capacity of the battery; the standing time will affect the stability and consistency of the battery, because the chemical substances inside the battery need time to redistribute, and different standing times will cause the OCV voltage to change.

[0037] In one embodiment, the battery capacity prediction method corrects the capacity prediction result of each battery cell based on the internal resistance, OCV voltage, temperature and standing time of each battery cell; by analyzing key data such as the internal resistance of the battery cell and the number of days between charging, the performance of the battery cell under different process steps and depth conditions is learned; not only the basic electrical characteristics of the battery cell (such as internal resistance, open circuit voltage OCV, etc.) are considered, but also the influence of external factors (such as temperature, standing time, etc.) is comprehensively considered, thereby effectively improving the accuracy and reliability of the prediction.

[0038] In one embodiment, the battery capacity prediction method also includes setting a capacity threshold, comparing the cell capacity prediction result with the capacity threshold to determine whether the battery can work normally. If not, an alarm may be issued. According to the battery specifications and usage requirements, a reasonable capacity threshold is set, and the cell capacity prediction result is compared with the set capacity threshold. If the predicted capacity of the cell is lower than the set capacity threshold, it is considered that the battery performance has declined or there is a fault, and an alarm is issued.

[0039] In summary, by setting the capacity threshold, bad batteries can be effectively identified and screened, which facilitates subsequent quality control; by promptly discovering cells with degraded performance, measures can be taken to avoid the deterioration of the overall performance of the battery pack, thereby extending the overall life of the battery.

[0040] In battery management, charging and discharging follow the principle of "charge high and discharge low": when the voltage of any cell reaches or exceeds the preset charging voltage threshold, the battery is considered to be fully charged; conversely, when the voltage of any cell is lower than the set discharge voltage threshold, the battery is considered to be discharged. However, due to the differences in characteristics during the production of cells and the inconsistency of the initial state, the overall charge and discharge state of the battery may not fully reflect the charge status of each cell. In fact, as long as the charge of one of the cells drops below the discharge threshold, the entire battery is considered to be discharged, even if other cells still have remaining power. Therefore, in battery capacity prediction, by calculating the remaining power of each cell when the battery is discharged, capacity prediction can be performed more accurately.

[0041] In one embodiment, obtaining data of each battery cell in a battery pack based on a data interface and predicting the remaining power of the battery cells includes obtaining the voltage of each battery cell, obtaining a fitting curve of the voltage and power of each battery cell using a neural network model, and obtaining the remaining power of the battery cell based on the corresponding relationship and the voltage of each battery cell; by learning the relationship between voltage and power through the neural network model, the accuracy of predicting the remaining power of the battery cell can be improved; by obtaining the voltage data of each battery cell in real time, the status of the battery pack can be monitored in real time, which is helpful to discover potential problems in time; by monitoring the changing trend of the battery cell voltage in real time, abnormal conditions of the battery cell, such as overheating, overvoltage, etc., can be detected early, so that measures can be taken in time to prevent the occurrence of failures.

[0042] In one embodiment, obtaining data of each battery cell in a battery pack based on a data interface and predicting the remaining power of the battery cells includes obtaining temperature and resistance, and adjusting a fitting curve of voltage and power of each battery cell based on the temperature and resistance; introducing a temperature correction factor to correct the fitting curve of voltage and power according to the influence of temperature on the electrochemical reaction rate of the battery cell; considering the change of the internal resistance of the battery cell with temperature and usage status, further correcting the fitting curve of voltage and power by introducing a resistance correction factor; and obtaining the remaining power of the battery cell through the voltage value of each battery cell according to the corresponding relationship between the corrected voltage and power.

[0043] By considering the effects of temperature and resistance, the accuracy of predicting the remaining power of the battery cell can be improved, and the method can better cope with the combination of batteries under different temperature and resistance conditions, making it suitable for various battery systems.

[0044] In one embodiment, the data interface obtains the battery cell data including obtaining the unique serial number of each battery cell, and determining the correspondence between the battery cell data and each battery cell based on the unique serial number; the accuracy of data processing is ensured by corresponding the unique serial number of each battery cell to the battery cell; when the battery cell data is abnormal, the faulty battery cell can be located in time through the unique serial number, and replaced or repaired, thereby improving the safety of the battery pack.

[0045] Corresponding to the above embodiment, the present invention further provides a battery capacity prediction device, the battery capacity prediction device includes: Figure 2 As shown, Figure 2 A schematic diagram of the structure of an embodiment of a battery prediction device provided by the present invention;

[0046] The data interface module is used to obtain the data of each battery cell and perform exception processing on the data of each battery cell; by performing exception processing on the data, erroneous or abnormal data points can be excluded to improve the accuracy of the prediction.

[0047] A cell capacity prediction module receives the cell data obtained by the data interface module to perform cell capacity prediction;

[0048] The battery cell remaining power prediction module receives the data of each battery cell obtained by the data interface module to predict the remaining power of the battery cell; the voltage, temperature and resistance data of each battery cell are obtained in real time, and the status of the battery pack can be monitored in real time, which helps to discover potential problems in time.

[0049] The battery capacity prediction module obtains the battery capacity prediction value based on the battery cell capacity prediction value and the battery cell remaining power prediction value; combining the battery cell capacity prediction value and the battery cell remaining power prediction value can improve the overall accuracy of the battery capacity prediction.

[0050] In other embodiments, the battery capacity prediction device further includes an abnormal battery management module (not shown), which is specifically used to identify and record information about defective batteries, including key data such as battery number, product type, defect cause, and test time. Through the systematic organization and analysis of these data, potential quality problems and production defects can be quickly identified, thereby improving overall product quality.

[0051] For the above embodiment, the present invention provides a computer device, see Figure 3 , Figure 3 The computer device of the present invention comprises a memory and a processor, wherein the memory and the processor are coupled to each other, the memory stores program data, and the processor is used to execute the program data to implement the steps of any embodiment of the above-mentioned battery capacity prediction method.

[0052] In this embodiment, the processor may also be referred to as a CPU (Central Processing Unit). The processor may be an integrated circuit chip having signal processing capabilities. The processor may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0053] The method of the above embodiment can be implemented in the form of a computer program, so the present invention provides a computer readable storage medium, see Figure 4 , Figure 4 The figure is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention. The computer-readable storage medium stores program data that can be run by a processor, and the program data can be executed by the processor to implement the steps of any embodiment of the above-mentioned battery capacity prediction method.

[0054] The computer-readable storage medium in this embodiment may be a medium that can store program data, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or may be a server that stores the program data. The server may send the stored program data to other devices for execution, or may execute the stored program data by itself.

[0055] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A battery capacity prediction method, characterized in that: The steps include: The battery pack does not need to be charged and is discharged directly until the battery pack is exhausted; Based on the data interface, the data of each battery cell in the battery pack is obtained and the capacity of each battery cell is predicted; including obtaining the internal resistance, OCV voltage, temperature and standing time of each battery cell; excessive internal resistance of each battery cell will lead to reduced capacity of the battery cell; the capacity of the battery cell is predicted based on the OCV voltage; the change of the temperature will affect the internal resistance of each battery cell; the difference in the standing time will cause the OCV voltage to change; the predicted result of the capacity of each battery cell is corrected based on the internal resistance, OCV voltage, temperature and standing time of each battery cell; the predicted capacity of all batteries is added to obtain the predicted capacity of the battery pack; Based on the data interface, the data of each battery cell in the battery pack is obtained and the remaining power of the battery cell is predicted; when the voltage of any battery cell is lower than the set discharge voltage threshold, the battery pack is in an empty state; the remaining power of the battery cell is the remaining power of each battery cell when the battery pack is empty; the predicted remaining power of all battery cells is added together to obtain the predicted remaining power of the battery pack; based on the calculation of the remaining power of each battery cell when the battery is empty, accurate capacity prediction is achieved; The capacity of each battery cell and the remaining power of each battery cell are used to obtain the predicted battery capacity based on the high-charge and low-discharge strategy.

2. The method according to claim 1, characterized in that: The method further includes setting a capacity threshold, comparing the cell capacity prediction result with the capacity threshold, and determining whether the battery can operate normally.

3. The method according to claim 2, characterized in that The method of obtaining data of each battery cell in the battery pack based on the data interface and predicting the remaining power of the battery cell includes obtaining the voltage of each battery cell, obtaining a fitting curve of the voltage and power of each battery cell by using a neural network model, and obtaining the remaining power of the battery cell based on the corresponding relationship and the voltage of each battery cell.

4. The method according to claim 3, characterized in that The acquiring data of each battery cell in the battery pack based on the data interface and predicting the remaining power of the battery cell includes acquiring temperature and resistance, and adjusting the fitting curve of the voltage and power of each battery cell based on the temperature and the resistance.

5. The method according to any one of claims 1 to 4, characterized in that: The data interface acquires the battery cell data by acquiring a unique serial number of each battery cell, and determines a corresponding relationship between the battery cell data and each battery cell based on the unique serial number.

6. A battery capacity prediction device using the battery capacity prediction method according to any one of claims 1 to 5, characterized in that: include: A data interface module, the data interface module is used to obtain data of each battery cell and perform exception processing on the data of each battery cell; A cell capacity prediction module, wherein the cell capacity prediction module receives the cell data acquired by the data interface module to perform cell capacity prediction; A battery cell remaining power prediction module, wherein the battery cell remaining power prediction module receives the battery cell data acquired by the data interface module to perform battery cell remaining power prediction; A battery capacity prediction module is used to obtain a battery capacity prediction value based on a cell capacity prediction value and a cell remaining power prediction value.

7. An electronic device, characterized in that: The electronic device comprises: a memory and a processor coupled to each other, wherein the processor is used to execute program instructions stored in the memory to implement the battery capacity prediction method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program data, and the program data can be executed by a processor to implement the battery capacity prediction method according to any one of claims 1 to 5.

Images