Battery residual capacity estimation method, device and terminal equipment

Abstract

The application is suitable for the technical field of electric power, and provides a battery residual capacity estimation method, device and terminal equipment, the method comprising: obtaining the isobaric rise time of a target battery under the current charging and discharging times; wherein the isobaric rise time is the time required for charging the output voltage of the target battery from a first voltage to a second voltage at a constant current; inputting the isobaric rise time and the size of the constant current into a pre-trained capacity estimation model to obtain the residual capacity of the target battery under the current charging and discharging times. The application can conveniently and accurately estimate the residual capacity of the battery.

Description

Technical Field

[0001] The present invention belongs to the field of electric power technology, and in particular relates to a method, device and terminal equipment for estimating the remaining capacity of a battery. Background Art

[0002] For lead-acid batteries used in substation energy storage systems, electric vehicle power systems and other fields, their performance will continue to degrade with long-term floating charge and discharge cycles. In order to ensure the safety and reliability of power supply, it is necessary to estimate the remaining capacity of the battery. When the discharge capacity of the lead-acid battery is less than 80% of its rated capacity, the battery is considered to have failed and should be replaced.

[0003] Existing methods for estimating lead-acid battery capacity all have drawbacks. On the one hand, the accuracy of these methods needs to be improved; on the other hand, these methods should reduce their reliance on empirical formulas and use simple and easy-to-implement variables to increase their universality and accuracy. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, and terminal device for estimating the remaining capacity of a battery, so as to conveniently and accurately estimate the remaining capacity of a battery.

[0005] A first aspect of an embodiment of the present invention provides a method for estimating remaining battery capacity, comprising:

[0006] Obtaining the constant voltage rise time of the target battery under the current charge and discharge times; wherein the constant voltage rise time is the time required to charge the output voltage of the target battery from a first voltage to a second voltage at a constant current;

[0007] The constant voltage rise time and the constant current are input into the pre-trained capacity estimation model to obtain the remaining capacity of the target battery under the current charge and discharge times.

[0008] Optionally, the remaining battery capacity estimation method further includes:

[0009] Get the target battery's constant voltage rise time under historical charge and discharge times;

[0010] Based on the target battery's isobaric rise time under the current charge and discharge times and the historical charge and discharge times, the target battery's isobaric rise time under each charge and discharge times in the future is predicted;

[0011] The constant voltage rise time and constant current of the target battery under each future charge and discharge number are input into the capacity estimation model to obtain the remaining capacity of the target battery under each future charge and discharge number, and the remaining life of the target battery is predicted based on the remaining capacity of the target battery under each future charge and discharge number.

[0012] Optionally, based on the current charge and discharge times and the target battery's isobaric rise time under historical charge and discharge times, the target battery's isobaric rise time under each future charge and discharge times is predicted, including:

[0013] The isobaric rise time of the target battery under the current charge and discharge times and the historical charge and discharge times is input into the pre-trained ELM rolling prediction model to obtain the isobaric rise time of the target battery under each future charge and discharge times.

[0014] Optionally, the remaining life of the target battery is predicted based on the remaining capacity of the target battery at each future charge and discharge number, including:

[0015] Determine the number of charge and discharge times corresponding to when the remaining capacity of the target battery is less than a preset threshold;

[0016] The remaining life of the target battery is determined based on the current charge and discharge times of the target battery and the charge and discharge times corresponding to when the remaining capacity of the target battery is less than a preset threshold.

[0017] Optionally, the capacity estimation model is an RVM neural network model.

[0018] Optional training methods for the capacity estimation model include:

[0019] Get the training set;

[0020] The constant current magnitude and constant voltage rise time in the training set are used as inputs of the capacity estimation model, the corresponding remaining capacity is used as output of the capacity estimation model, the model parameters of the capacity estimation model are trained, and a pre-trained capacity estimation model is obtained.

[0021] Optionally, after obtaining the pre-trained capacity estimation model, the following is also included:

[0022] Obtain a test set; wherein the test set includes different constant voltage rise times and corresponding remaining capacities of a target battery under multiple constant currents;

[0023] Calculate the estimation error of the capacity estimation model based on the test set;

[0024] If the estimation error does not meet the preset conditions, the capacity estimation model is retrained.

[0025] A second aspect of an embodiment of the present invention provides a battery remaining capacity estimation device, including:

[0026] An acquisition module is used to obtain the constant voltage rise time of the target battery under the current charge and discharge times; wherein the constant voltage rise time is the time required to charge the output voltage of the target battery from a first voltage to a second voltage at a constant current;

[0027] The estimation module is used to input the constant voltage rise time and the constant current into the pre-trained capacity estimation model to obtain the remaining capacity of the target battery under the current charge and discharge times.

[0028] A third aspect of an embodiment of the present invention provides a terminal device, comprising 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 steps of the remaining battery capacity estimation method according to the first aspect are implemented.

[0029] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the steps of the battery remaining capacity estimation method according to the first aspect are implemented.

[0030] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0031] The present invention utilizes a pre-trained capacity estimation model. In actual use, the remaining capacity of a lead-acid battery can be estimated based solely on the constant voltage rise time and current during constant current charging, without discharging the battery. This allows for accurate prediction of the remaining capacity in a variety of scenarios. The method is simple and easy to implement, does not rely on empirical formulas, and has a wide range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 1 is a flow chart of a method for estimating remaining battery capacity according to an embodiment of the present invention;

[0034] Figure 2 This is a schematic diagram of equal voltage rise time corresponding to different charge and discharge times provided by an embodiment of the present invention;

[0035] Figure 3 1 is a schematic diagram of the absolute error of the remaining capacity provided by an embodiment of the present invention;

[0036] Figure 4 1 is a schematic diagram of the relative error of the remaining capacity provided by an embodiment of the present invention;

[0037] Figure 5 1 is a schematic diagram of a discharge capacity prediction process according to an embodiment of the present invention;

[0038] Figure 6 1 is a schematic structural diagram of a battery remaining capacity estimation device provided by an embodiment of the present invention;

[0039] Figure 7 It is a schematic diagram of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0041] In order to illustrate the technical solution of the present invention, specific embodiments are provided below.

[0042] Currently, the typical method for measuring the remaining capacity of a lead-acid battery is to fully charge the battery at 25°C and discharge it at a 10h discharge rate. The capacity released when the battery reaches 1.8V is the actual discharge capacity. When the discharge capacity falls below 80% of its rated capacity, the battery is considered to have failed and should be replaced. The core content of the capacity performance test requires a discharge process that consumes no energy, reduces lifespan, and is time-consuming. After discharge, recharging is required to return the battery to a normal power state, which also consumes time and lifespan.

[0043] Capacity estimation methods are typically data-driven. These methods avoid exploring internal battery failure mechanisms and developing complex models. Instead, they predict remaining capacity by extracting and processing implicit information, such as neural networks, support vector machines, and Wiener processes. Therefore, linking measurable data with dischargeable capacity to quickly and accurately estimate dischargeable capacity is crucial for improving the efficient application of lead-acid batteries for energy storage or power applications. Several achievements have been made in estimating the dischargeable capacity of lead-acid batteries. For example, existing document 1 discloses a lead-acid battery capacity estimation method. Based on an equivalent circuit model for lead-acid batteries, the relationship between battery capacity and open-circuit voltage is analyzed. However, the selection of the equivalent circuit model and the accuracy of the estimated model parameters can significantly affect the results. Existing document 2 proposes discharging the battery at a constant current for 2 hours, then allowing it to rest for 30 seconds to measure the battery's rebound voltage. This voltage is then used to estimate the battery's dischargeable capacity. However, the parameters in this capacity estimation equation are empirical constants, which may vary for different lead-acid batteries. In summary, there is an urgent need for a simpler and more accurate battery capacity estimation method.

[0044] See also Figure 1 As shown, an embodiment of the present invention provides a method for estimating the remaining capacity of a battery, the method comprising the following steps:

[0045] Step S101 , obtaining the constant voltage rise time of the target battery under the current charge and discharge times, where the constant voltage rise time is the time required to charge the output voltage of the target battery from a first voltage to a second voltage at a constant current.

[0046] In an embodiment of the present invention, the constant voltage rise time can be calculated by charging the battery's output voltage from a first voltage to a second voltage based on the constant current of the battery in actual application. The values ​​of the first and second voltages are consistent with the pre-trained capacity estimation model, with typical values ​​being: 1.8V for the first voltage and 2.4V for the second voltage. To ensure estimation accuracy, the process of obtaining the constant voltage rise time should be performed in an environment with a temperature of 25°C and a humidity of no more than 80% to eliminate the impact of environmental factors on battery charging and discharging.

[0047] In step S102 , the constant voltage rise time and the magnitude of the constant current are input into a pre-trained capacity estimation model to obtain the remaining capacity of the target battery under the current number of charge and discharge times.

[0048] In the embodiment of the present invention, since the constant voltage rise time and the charging current size in the constant current charging stage of the charging process are used as health factors, the capacity of the lead-acid battery can be quickly and accurately estimated in a complex real-world usage environment without discharging the battery or providing an additional constant current.

[0049] As can be seen, the embodiments of the present invention utilize a pre-trained capacity estimation model. In actual use, the remaining capacity of a lead-acid battery can be estimated based solely on the constant voltage rise time and current during constant current charging, without discharging the battery. This allows for accurate prediction of the remaining capacity in a variety of usage scenarios. The methods of the embodiments of the present invention are simple and easy to implement, do not rely on empirical formulas, and have a wide range of applications.

[0050] Optionally, the capacity estimation model is an RVM neural network model.

[0051] Optional training methods for the capacity estimation model include:

[0052] Get the training set;

[0053] The constant current magnitude and constant voltage rise time in the training set are used as inputs of the capacity estimation model, the corresponding remaining capacity is used as output of the capacity estimation model, the model parameters of the capacity estimation model are trained, and a pre-trained capacity estimation model is obtained.

[0054] In this embodiment of the present invention, the training set can be obtained in the following ways:

[0055] (1) In an environment with a temperature of 25°C and a humidity of no more than 80%, a lead-acid battery is charged to 2.40V at various charging currents I. Then, the battery is switched to constant voltage charging until the charging current drops to 2A. The time required for the battery output voltage to rise from 2.1V to 2.4V is recorded to obtain the constant voltage rise time at the current I. The accuracy of the discharge current in the sample data is 0.1A, the accuracy of the constant voltage rise time is 1min, and the accuracy of the discharge capacity is 0.01Ah. The lead-acid battery used in the discharge and charge experiments has a rated voltage of 2V and a rated capacity of 200Ah.

[0056] (2) Leave the lead-acid battery open circuit for 2 hours.

[0057] (3) When the battery surface temperature is 25℃±5℃, the discharge current I 10 The output voltage is reduced to 1.80V by constant current discharge. The constant current discharge time T is recorded and the measured capacity Q is calculated. t =T×I 10 , and convert it into the actual capacity Q at a reference temperature of 25°C:

[0058]

[0059] Where t is the average surface temperature of the battery during discharge, and λ is the temperature coefficient, which is 0.006.

[0060] The voltage curve of the battery during charging under different charge and discharge times N can be referred to Figure 2 As shown in the figure, it can be seen that the constant voltage rise time increases with the number of battery charge and discharge cycles. Therefore, the charging current I and the constant voltage rise time are used as the two-dimensional feature inputs of the model, and the actual discharge capacity Q is used as the output of the model to train the RVM neural network model. Specifically, during the training phase, the exponential kernel function is selected as follows:

[0061]

[0062] The kernel function parameters are optimized using a particle swarm intelligence algorithm and K-fold cross validation to minimize model error. K-fold cross validation involves further dividing the training set into K mutually exclusive subsets, selecting one subset each time as the test set and the remaining K-1 subsets as the training set. This increases the number of training runs while fully utilizing the sample data, reducing overfitting and making it easier to find parameter values ​​that optimize the model's generalization capabilities.

[0063] Optionally, after obtaining the pre-trained capacity estimation model, the following is also included:

[0064] Obtain a test set; wherein the test set includes different constant voltage rise times and corresponding remaining capacities of a target battery under multiple constant currents;

[0065] Calculate the estimation error of the capacity estimation model based on the test set;

[0066] If the estimation error does not meet the preset conditions, the capacity estimation model is retrained.

[0067] In the embodiment of the present invention, the absolute error of the remaining capacity, the relative error of the remaining capacity, and the root mean square error may be used as performance evaluation indicators to determine whether the capacity estimation model meets the requirements.

[0068] The calculation formula for the absolute error of remaining capacity is:

[0069]

[0070] The calculation formula for the relative error of remaining capacity is:

[0071]

[0072] The formula for calculating the root mean square error is:

[0073]

[0074] Where Q i is the actual value of discharge capacity, is the estimated discharge capacity.

[0075] According to the 44 sets of data collected, 39 sets of data were randomly selected to train the model, and the remaining 5 sets of data were used for verification. The absolute error of the remaining capacity and the relative error of the remaining capacity were as follows: Figure 3 and Figure 4 As shown, the root mean square error is 34.26, and the test sample reliability is 0.9440. It can be seen that the battery remaining capacity estimation method proposed in the embodiment of the present invention has high accuracy and reliability.

[0076] Optionally, the remaining battery capacity estimation method further includes:

[0077] Get the target battery's constant voltage rise time under historical charge and discharge times;

[0078] Based on the target battery's isobaric rise time under the current charge and discharge times and the historical charge and discharge times, the target battery's isobaric rise time under each charge and discharge times in the future is predicted;

[0079] The constant voltage rise time and constant current of the target battery under each future charge and discharge number are input into the capacity estimation model to obtain the remaining capacity of the target battery under each future charge and discharge number, and the remaining life of the target battery is predicted based on the remaining capacity of the target battery under each future charge and discharge number.

[0080] In the embodiment of the present invention, the historical charge and discharge times, the current charge and discharge times, and the future charge and discharge times can all be relative values. That is, the constant voltage rise time under charge and discharge times from nm to n can be measured as historical data. The current charge and discharge times are recorded as n, and the future charge and discharge times are recorded as n+1, n+2, etc. The remaining life can be calculated based on the difference between the future charge and discharge times and the current charge and discharge times. Figure 5 As shown, the constant voltage rise time and the constant current at each future charge and discharge number are input into the pre-trained RVM model, and the discharge capacity prediction value at each future charge and discharge number is output.

[0081] Optionally, based on the current charge and discharge times and the target battery's isobaric rise time under historical charge and discharge times, the target battery's isobaric rise time under each future charge and discharge times is predicted, including:

[0082] The isobaric rise time of the target battery under the current charge and discharge times and the historical charge and discharge times is input into the pre-trained ELM rolling prediction model to obtain the isobaric rise time of the target battery under each future charge and discharge times.

[0083] In the embodiment of the present invention, it is first necessary to establish an ELM rolling prediction model of equal pressure rise time. The number of hidden layer nodes of the model is:

[0084]

[0085] Where m is the number of input layer nodes, f is the number of output layer nodes, and λ is a constant between 1 and 10.

[0086] The ELM rolling prediction model parameters are trained by selecting an appropriate rolling window length l and the number of hidden layer nodes L. The first to lth isobaric rise times are used as input, the second to l+1th isobaric rise times are used as output, and so on. During the prediction phase, the results of each single-step prediction are used as input for the next prediction, thus completing the rolling prediction.

[0087] Optionally, the remaining life of the target battery is predicted based on the remaining capacity of the target battery at each future charge and discharge number, including:

[0088] Determine the number of charge and discharge times corresponding to when the remaining capacity of the target battery is less than a preset threshold;

[0089] The remaining life of the target battery is determined based on the current charge and discharge times of the target battery and the charge and discharge times corresponding to when the remaining capacity of the target battery is less than a preset threshold.

[0090] In the embodiment of the present invention, the condition for battery failure is that the discharge capacity drops to 80% of the rated capacity.

[0091] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean 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 the present invention.

[0092] See also Figure 6 As shown, an embodiment of the present invention provides a battery remaining capacity estimation device, the battery remaining capacity estimation device 60 includes:

[0093] The acquisition module 61 is used to obtain the constant voltage rise time of the target battery under the current charge and discharge times; wherein the constant voltage rise time is the time required to charge the output voltage of the target battery from a first voltage to a second voltage at a constant current.

[0094] The estimation module 62 is used to input the constant voltage rise time and the constant current into a pre-trained capacity estimation model to obtain the remaining capacity of the target battery under the current charge and discharge times.

[0095] Optionally, the device further includes a prediction module 63, configured to:

[0096] Get the target battery's constant voltage rise time under historical charge and discharge times;

[0097] Based on the target battery's isobaric rise time under the current charge and discharge times and the historical charge and discharge times, the target battery's isobaric rise time under each charge and discharge times in the future is predicted;

[0098] The constant voltage rise time and constant current of the target battery under each future charge and discharge number are input into the capacity estimation model to obtain the remaining capacity of the target battery under each future charge and discharge number, and the remaining life of the target battery is predicted based on the remaining capacity of the target battery under each future charge and discharge number.

[0099] Optionally, the prediction module 63 is specifically configured to:

[0100] The isobaric rise time of the target battery under the current charge and discharge times and the historical charge and discharge times is input into the pre-trained ELM rolling prediction model to obtain the isobaric rise time of the target battery under each future charge and discharge times.

[0101] Optionally, the prediction module 63 is specifically configured to:

[0102] Determine the number of charge and discharge times corresponding to when the remaining capacity of the target battery is less than a preset threshold;

[0103] The remaining life of the target battery is determined based on the current charge and discharge times of the target battery and the charge and discharge times corresponding to when the remaining capacity of the target battery is less than a preset threshold.

[0104] Optionally, the capacity estimation model is an RVM neural network model.

[0105] Optionally, the capacity estimation model training process includes:

[0106] Get the training set;

[0107] The constant current magnitude and constant voltage rise time in the training set are used as inputs of the capacity estimation model, the corresponding remaining capacity is used as output of the capacity estimation model, the model parameters of the capacity estimation model are trained, and a pre-trained capacity estimation model is obtained.

[0108] Optionally, after obtaining the pre-trained capacity estimation model, the following is also included:

[0109] Obtain a test set; wherein the test set includes different constant voltage rise times and corresponding remaining capacities of a target battery under multiple constant currents;

[0110] Calculate the estimation error of the capacity estimation model based on the test set;

[0111] If the estimation error does not meet the preset conditions, the capacity estimation model is retrained.

[0112] Figure 7 FIG is a schematic diagram of a terminal device 70 provided in an embodiment of the present invention. Figure 7 As shown, the terminal device 70 of this embodiment includes: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71, such as a battery remaining capacity estimation program. When the processor 71 executes the computer program 73, the steps in the above-mentioned embodiments of the battery remaining capacity estimation method are implemented, such as Figure 1 Alternatively, when the processor 71 executes the computer program 73, the functions of the modules in the above-mentioned device embodiments are realized, for example Figure 6 The functions of modules 61 to 62 are shown.

[0113] Exemplarily, the computer program 73 may be divided into one or more modules / units, one or more of which are stored in the memory 72 and executed by the processor 71 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 73 in the terminal device 70. For example, the computer program 73 may be divided into the acquisition module 61 and the estimation module 62 (modules in the virtual device), and the specific functions of each module are as follows:

[0114] The acquisition module 61 is used to obtain the constant voltage rise time of the target battery under the current charge and discharge times; wherein the constant voltage rise time is the time required to charge the output voltage of the target battery from a first voltage to a second voltage at a constant current.

[0115] The estimation module 62 is used to input the constant voltage rise time and the constant current into a pre-trained capacity estimation model to obtain the remaining capacity of the target battery under the current charge and discharge times.

[0116] The terminal device 70 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device 70 may include, but is not limited to, a processor 71 and a memory 72. Those skilled in the art will understand that Figure 7 It is merely an example of the terminal device 70 and does not constitute a limitation of the terminal device 70. The terminal device 70 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 70 may also include input and output devices, network access devices, buses, etc.

[0117] The processor 71 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0118] The memory 72 may be an internal storage unit of the terminal device 70, such as a hard disk or memory of the terminal device 70. The memory 72 may also be an external storage device of the terminal device 70, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the terminal device 70. Furthermore, the memory 72 may include both an internal storage unit of the terminal device 70 and an external storage device. The memory 72 is used to store computer programs and other programs and data required by the terminal device 70. The memory 72 may also be used to temporarily store data that has been output or is about to be output.

[0119] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the 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 embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0120] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0121] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0122] In the embodiments provided by the present invention, 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 example, the division of modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0123] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0124] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0125] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of each of the above-mentioned method embodiments. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0126] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for estimating the remaining capacity of a battery, characterized in that: include: Obtaining a constant voltage rise time of a target battery under the current number of charge and discharge cycles; wherein the constant voltage rise time is the time required to charge the output voltage of the target battery from a first voltage to a second voltage at a constant current; Inputting the constant voltage rise time and the constant current into a pre-trained capacity estimation model to obtain the remaining capacity of the target battery under the current charge and discharge times; Get the target battery's constant voltage rise time under historical charge and discharge times; Based on the target battery's isobaric rise time under the current charge and discharge times and the historical charge and discharge times, predicting the target battery's isobaric rise time under each future charge and discharge times, including: inputting the target battery's isobaric rise time under the current charge and discharge times and the historical charge and discharge times into a pre-trained ELM rolling prediction model to obtain the target battery's isobaric rise time under each future charge and discharge times; The constant voltage rise time of the target battery at each future charge and discharge number and the magnitude of the constant current are input into the capacity estimation model to obtain the remaining capacity of the target battery at each future charge and discharge number, and the remaining life of the target battery is predicted based on the remaining capacity of the target battery at each future charge and discharge number.

2. The method for estimating the remaining battery capacity according to claim 1, wherein: Predict the remaining life of the target battery based on the remaining capacity of the target battery at each future charge and discharge cycle, including: Determine the number of charge and discharge times corresponding to when the remaining capacity of the target battery is less than a preset threshold; The remaining life of the target battery is determined based on the current charge and discharge times of the target battery and the charge and discharge times corresponding to when the remaining capacity of the target battery is less than a preset threshold.

3. The method for estimating the remaining battery capacity according to claim 1 or 2, wherein: The capacity estimation model is an RVM neural network model.

4. The method for estimating the remaining battery capacity according to claim 3, wherein: The training method of the capacity estimation model includes: Get the training set; The constant current magnitude and constant voltage rise time in the training set are used as inputs of the capacity estimation model, the corresponding remaining capacity is used as output of the capacity estimation model, and the model parameters of the capacity estimation model are trained to obtain a pre-trained capacity estimation model.

5. The method for estimating the remaining battery capacity according to claim 4, wherein: After obtaining the pre-trained capacity estimation model, it also includes: Obtain a test set; wherein the test set includes different constant voltage rise times and corresponding remaining capacities of a target battery under multiple constant currents; Calculating an estimation error of the capacity estimation model based on the test set; If the estimation error does not meet a preset condition, the capacity estimation model is retrained.

6. A battery remaining capacity estimation device, characterized in that: include: An acquisition module is used to obtain the constant voltage rise time of the target battery under the current charge and discharge times; wherein the constant voltage rise time is the time required to charge the output voltage of the target battery from a first voltage to a second voltage at a constant current; an estimation module, configured to input the constant voltage rise time and the constant current into a pre-trained capacity estimation model to obtain the remaining capacity of the target battery under the current charge and discharge times; A prediction module is used to obtain the isobaric rise time of the target battery under historical charge and discharge times; based on the isobaric rise time of the target battery under the current charge and discharge times and the historical charge and discharge times, predict the isobaric rise time of the target battery under each future charge and discharge times; input the isobaric rise time of the target battery under each future charge and discharge times and the magnitude of the constant current into the capacity estimation model to obtain the remaining capacity of the target battery under each future charge and discharge times, and predict the remaining life of the target battery based on the remaining capacity of the target battery under each future charge and discharge times; the prediction module is used to: input the isobaric rise time of the target battery under the current charge and discharge times and the historical charge and discharge times into a pre-trained ELM rolling prediction model to obtain the isobaric rise time of the target battery under each future charge and discharge times.

7. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images