Battery ion concentration determination method and device, computer device, and storage medium

Abstract

The application relates to a battery ion concentration determination method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining battery working condition parameters of a to-be-tested battery at each time point in a current period; wherein the battery working condition parameters comprise current information, battery capacity and position information of lithium ions in the to-be-tested battery; based on a target diffusion single particle model of the to-be-tested battery, lithium ion concentrations of the to-be-tested battery at each time point in the current period are determined according to the battery working condition parameters of the to-be-tested battery at each time point in the current period; wherein the target diffusion single particle model is obtained by optimizing physical parameters in an initial diffusion single particle model based on a physical information neural network. The lithium ion concentration in the to-be-tested battery can be accurately and efficiently determined by using the method.

Description

Technical Field

[0001] This application relates to the field of electric vehicle technology, and in particular to a method, apparatus, computer device, and storage medium for determining the ion concentration of a battery. Background Technology

[0002] The development of electric vehicles (EVs) is widely considered an effective means to address the challenges of excessive carbon emissions and the depletion of fossil oil. Lithium-ion batteries (LIBs), with their advantages of high energy density and long lifespan, play a dominant role in energy storage for EVs. To better manage battery systems, establishing battery models and researching battery algorithms are crucial.

[0003] One widely used model in academia and industry is the pseudo-two-dimensional model. LIB mechanism models, represented by the pseudo-two-dimensional model, provide a very detailed description of the kinetics of lithium-ion insertion and extraction at the microscale. However, mechanistic models of lithium-ion batteries often require dozens of electrochemical parameters and consist of nonlinear partial differential equations, hindering their application in automotive battery management systems. Therefore, finding an accurate simplified model and quickly solving for it remains a challenge. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, and storage medium for determining ion concentration to address the aforementioned technical problems.

[0005] In a first aspect, this application provides a method for determining the ion concentration of a battery, comprising:

[0006] Obtain the battery operating parameters of the battery under test at various times within the current time period; wherein, the battery operating parameters include current information, battery capacity, and lithium ion position information in the battery under test;

[0007] Based on the target diffusion single-particle model of the battery under test, the lithium-ion concentration of the battery under test at each time point in the current time period is determined according to the battery operating parameters of the battery under test at each time point in the current time period; wherein, the target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network.

[0008] In one embodiment, the target diffusion single-particle model is obtained in the following manner:

[0009] Acquire sample data; wherein, the sample data includes the battery operating parameters and lithium-ion concentration of the battery under test at each historical moment within a historical period;

[0010] Based on the physical parameters in the initial diffusion single-particle model of the battery under test, the physical information neural network is initialized to obtain the physical information network model of the battery under test.

[0011] The physical information network model is trained using the sample data to obtain a target diffusion single-particle model.

[0012] In one embodiment, the initial diffusion single-particle model includes a solid-phase lithium-ion diffusion model and a liquid-phase lithium-ion diffusion model, and the initial diffusion single-particle model is obtained by means of:

[0013] The solid-phase lithium-ion diffusion model is constructed based on the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function; wherein, the solid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times.

[0014] The liquid-phase lithium-ion diffusion model is constructed based on the liquid-phase lithium-ion diffusion coefficient, electrolyte volume fraction, lithium-ion transport number, and liquid-phase lithium-ion concentration function; wherein, the liquid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times.

[0015] In one embodiment, training the physical information network model using the sample data to obtain a target diffusion single-particle model includes:

[0016] The physical information network model is trained using the target loss function and the sample data to obtain a target diffusion single-particle model; wherein the target loss function is constructed based on the mean square error function and boundary conditions of the solid-phase lithium-ion diffusion model, as well as the mean square error function and boundary conditions of the liquid-phase lithium-ion diffusion model.

[0017] In one embodiment, the target loss function is obtained in the following way:

[0018] Based on the mean square error function of the solid-phase lithium-ion diffusion model and the mean square error function of the liquid-phase lithium-ion diffusion model, an equation loss function is constructed.

[0019] Based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, a boundary loss function is constructed.

[0020] The initial value loss function is determined based on the values ​​of the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function at the moment the battery under test is powered on.

[0021] The sum of the equation loss function, the boundary loss function, and the initial value loss function is used as the target loss function.

[0022] In one embodiment, determining the ion concentration of the battery under test at various times within the current time period based on the target diffusion single-particle model of the battery under test and the battery operating parameters includes:

[0023] The battery operating condition parameters are normalized to obtain normalized battery operating condition parameters.

[0024] The normalized battery operating parameters are input into the target diffusion single-particle model to obtain the lithium-ion concentration of the battery under test at each time point in the current time period.

[0025] In one embodiment, the method further includes:

[0026] Based on the battery capacity and lithium-ion concentration of the battery under test at various times within the current time period, determine the corresponding curves of the battery capacity and lithium-ion concentration of the battery under test.

[0027] Secondly, this application also provides a battery ion concentration determination device, comprising:

[0028] The parameter acquisition module is used to acquire the battery operating condition parameters of the battery under test at various times within the current time period; wherein, the battery operating condition parameters include current information, battery capacity, and lithium ion position information in the battery under test;

[0029] The concentration determination module is used to determine the lithium-ion concentration of the battery under test at each moment in the current time period based on the target diffusion single-particle model of the battery under test and the battery operating parameters of the battery under test at each moment in the current time period; wherein, the target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network.

[0030] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0031] Obtain the battery operating parameters of the battery under test at various times within the current time period; wherein, the battery operating parameters include current information, battery capacity, and lithium ion position information in the battery under test;

[0032] Based on the target diffusion single-particle model of the battery under test, the lithium-ion concentration of the battery under test at each time point in the current time period is determined according to the battery operating parameters of the battery under test at each time point in the current time period; wherein, the target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network.

[0033] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0034] Obtain the battery operating parameters of the battery under test at various times within the current time period; wherein, the battery operating parameters include current information, battery capacity, and lithium ion position information in the battery under test;

[0035] Based on the target diffusion single-particle model of the battery under test, the lithium-ion concentration of the battery under test at each time point in the current time period is determined according to the battery operating parameters of the battery under test at each time point in the current time period; wherein, the target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network.

[0036] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0037] Obtain the battery operating parameters of the battery under test at various times within the current time period; wherein, the battery operating parameters include current information, battery capacity, and lithium ion position information in the battery under test;

[0038] Based on the target diffusion single-particle model of the battery under test, the lithium-ion concentration of the battery under test at each time point in the current time period is determined according to the battery operating parameters of the battery under test at each time point in the current time period; wherein, the target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network.

[0039] The aforementioned method, apparatus, computer equipment, and storage medium for determining the ion concentration of a battery acquire battery condition parameters, including current information, battery capacity, and the location of lithium ions within the battery at various times within the current time period. Based on a target diffusion single-event model of the battery, the lithium ion concentration of the battery at each time within the current time period is determined according to the battery condition parameters. The target diffusion single-event model is obtained by optimizing the physical parameters in the initial diffusion single-event model using a physical information neural network. This scheme optimizes the physical parameters in the initial diffusion single-event model using a physical information neural network, ensuring that the values ​​of each physical parameter in the target diffusion single-event model are optimal, thus further guaranteeing the accuracy of the target diffusion single-event model. Furthermore, by introducing current information and battery capacity, and combining them with the target diffusion single-event model, the accuracy of the determined lithium ion concentration in the battery is guaranteed, and the lithium ion concentration of the battery under various application current conditions and battery capacity states can be obtained, exhibiting stronger adaptability and scalability. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying 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.

[0041] Figure 1 This is a diagram illustrating the application environment of a battery ion concentration determination method in one embodiment.

[0042] Figure 2 This is a flowchart illustrating a method for determining the ion concentration of a battery in one embodiment.

[0043] Figure 3 This is a flowchart illustrating the process of constructing a target diffusion single-particle model in one embodiment;

[0044] Figure 4 This is a schematic diagram of the process for constructing an initial diffusion single-particle model in one embodiment;

[0045] Figure 5 This is a flowchart illustrating the process of constructing the target loss function in one embodiment;

[0046] Figure 6 This is a schematic diagram of the process for determining ion concentration in one embodiment;

[0047] Figure 7 This is a flowchart illustrating a method for determining the ion concentration of a battery in another embodiment;

[0048] Figure 8 This is a structural block diagram of a battery ion concentration determination device in one embodiment;

[0049] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] The battery ion concentration determination method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, the battery management system 101 is a system in the target vehicle used to monitor and manage the battery under test; the monitoring terminal 102 is used to monitor and calculate the lithium-ion concentration of the battery under test in the target vehicle; and the battery under test 103 is the power battery in the target vehicle. Optionally, the monitoring terminal 102 acquires the battery operating parameters of the battery under test 103 at various times within the current time period; wherein, the battery operating parameters include current information, battery capacity, and the location information of lithium ions in the battery under test; based on the target diffusion single-particle model of the battery under test, the lithium-ion concentration of the battery under test at various times within the current time period is determined according to the battery operating parameters of the battery under test at various times within the current time period; wherein, the target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on a physical information neural network.

[0052] In one embodiment, such as Figure 2 As shown, a method for determining the ion concentration of a battery is provided, which can be applied to... Figure 1 Taking monitoring terminal 102 as an example, the following steps are included:

[0053] S201, Obtain the battery operating parameters of the battery under test at various times within the current time period.

[0054] The battery under test is a lithium-ion battery whose lithium-ion concentration needs to be measured; the current time period is the time period within a preset duration before the current moment. Battery operating parameters characterize the operating conditions of the battery under test during operation; in this embodiment, battery operating parameters include, but are not limited to, current information, battery capacity, and the position information of lithium ions in the battery under test; the current information characterizes the charging and discharging current of the battery under test.

[0055] Optionally, the battery operating parameters of the battery under test at various times during the current period can be obtained through a monitoring device connected to the battery or from the battery management system.

[0056] For example, the current information, battery capacity, and lithium ion position information of the battery under test at various times within the current period can be extracted from the battery management system as battery condition parameters of the battery under test.

[0057] S202, based on the target diffusion single-particle model of the battery under test, determines the lithium-ion concentration of the battery under test at each moment in the current time period according to the battery operating parameters at each moment in the current time period.

[0058] The diffusion single-particle model describes the continuous movement and diffusion process of lithium ions in the battery; the target diffusion single-particle model describes the continuous movement and diffusion process of lithium ions in the battery under test. In this embodiment, the target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on a physical information neural network.

[0059] Optionally, the battery operating parameters of the battery under test at various times within the current time period can be input into the target diffusion single-particle model of the battery under test, so that the target diffusion single-particle model can calculate the battery operating parameters based on the optimized physical parameters and output the lithium-ion concentration of the battery under test at various times within the current time period.

[0060] The aforementioned method for determining the lithium ion concentration in a battery involves acquiring battery condition parameters, including current information, battery capacity, and the location of lithium ions within the battery at various times within the current time period. Based on a target diffusion single-event model (PEP) of the battery, the lithium ion concentration at each time point within the current time period is determined according to these battery condition parameters. The target PEP model is obtained by optimizing the physical parameters in the initial PEP model using a physical information neural network. This approach optimizes the physical parameters in the initial PEP model using a physical information neural network, ensuring that each physical parameter in the target PEP model reaches its optimal value, thus further guaranteeing the accuracy of the target PEP model. Furthermore, by incorporating current information and battery capacity, and combining them with the target PEP model, the accuracy of the determined lithium ion concentration in the battery is ensured. Moreover, the method can obtain the lithium ion concentration of the battery under various application current conditions and battery capacity states, exhibiting stronger adaptability and scalability.

[0061] Optionally, in one embodiment, such as Figure 3 As shown, a method for constructing a target diffusion single-particle model is provided, which specifically includes the following steps:

[0062] S301, Obtain sample data.

[0063] The sample data includes the battery operating parameters and lithium-ion concentration of the battery under test at various historical moments within a historical period.

[0064] Optionally, the battery operating parameters and lithium-ion concentration of the battery under test at various historical moments within a historical period can be obtained from the battery management system of the battery under test as sample data.

[0065] S302, based on the physical parameters in the initial diffusion single-particle model of the battery under test, the physical information neural network is initialized to obtain the physical information network model of the battery under test.

[0066] The initial diffusion single-particle model is a diffusion single-particle model without optimized physical parameters; the physical information neural network is a neural network that incorporates physical laws. The physical information network model is a physical information neural network that incorporates the physical parameters from the initial diffusion single-particle model.

[0067] Optionally, the physical information network model of the battery under test can be obtained by initializing the physical parameters in the initial diffusion single-particle model of the battery under test and using the physical parameters to initialize the framework of the physical information neural network.

[0068] S303 uses sample data to train the physical information network model, resulting in a single-particle model for target diffusion.

[0069] Optionally, sample data can be used to train the physical information network model to obtain the optimal solution for each physical parameter in the physical information network model, thus obtaining the target diffusion single-particle model.

[0070] In this embodiment, the physical information neural network is initialized using the physical parameters in the initial diffusion single-particle model of the battery under test, thus constructing a physical information network model that combines the physical information neural network and the initial diffusion single-particle model. Furthermore, the physical information network model is trained using sample data to ensure the accuracy of the obtained target diffusion single-particle model.

[0071] Optionally, the initial diffusion single-particle model includes a solid-phase lithium-ion diffusion model and a liquid-phase lithium-ion diffusion model. Based on the above embodiments, in one embodiment, such as... Figure 4 As shown, a method for constructing an initial diffusion single-particle model is provided, which specifically includes the following steps:

[0072] S401, a solid-phase lithium-ion diffusion model is constructed based on the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function.

[0073] Among them, the solid-phase lithium-ion diffusion coefficient is a measure of the speed and ease of lithium-ion diffusion in the battery under test; the solid-phase lithium-ion concentration function is a function characterizing the concentration of lithium-ions contained in the battery under test; in the embodiments of this application, the solid-phase lithium-ion concentration function is related to the position information of lithium-ions in the battery under test at different times.

[0074] Optionally, a solid-phase lithium-ion diffusion model can be constructed based on the solid-phase lithium-ion diffusion theory, according to the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function. Specifically, the constructed solid-phase lithium-ion diffusion model can be expressed by the following formula (1):

[0075] (1)

[0076] in, The area of ​​the battery cell to be tested. This is the negative pole region. For the diaphragm region, This is the positive pole region. Expressed as solid-phase lithium-ion concentration. The coordinates are in the radial direction and are determined by the location information. is the solid-phase lithium-ion diffusion coefficient.

[0077] S402. A liquid phase lithium ion diffusion model is constructed based on the liquid phase lithium ion diffusion coefficient, electrolyte volume fraction, lithium ion transport number, and liquid phase lithium ion concentration function.

[0078] Wherein, the liquid phase lithium ion diffusion coefficient is the rate of lithium ion diffusion in the electrode material; the liquid phase lithium ion concentration function is a function characterizing the concentration of liquid phase lithium ions between the positive and negative electrodes of the battery under test during charging and discharging; in the embodiments of this application, the liquid phase lithium ion concentration function is related to the position information of lithium ions in the battery under test at different times.

[0079] Optionally, a liquid-phase lithium-ion diffusion model can be constructed based on the theory of liquid-phase lithium-ion diffusion, according to the liquid-phase lithium-ion diffusion coefficient, electrolyte volume fraction, lithium-ion transport number, and liquid-phase lithium-ion concentration function. Specifically, the constructed liquid-phase lithium-ion diffusion model can be expressed by the following formula (2):

[0080] (2)

[0081] in, Expressed as solid-phase lithium-ion concentration. The effective liquid phase diffusion coefficient can be expressed as follows: express, Where is the liquid phase diffusion coefficient, This represents the electrolyte volume fraction. Brugmann's constant, Represents the lithium-ion transference number. The active surface area per unit electrode volume. The interface current density; Indicates location information.

[0082] In this embodiment of the application, by constructing a solid-phase lithium-ion diffusion model and a liquid-phase lithium-ion diffusion model respectively, it is ensured that the constructed initial diffusion single-particle model can fully represent the movement and diffusion state of lithium ions in the battery under test.

[0083] Optionally, in one embodiment, a target loss function and sample data can be used to train the physical information network model to obtain a target diffusion single-event model; wherein, the target loss function is constructed based on the mean square error function and boundary conditions of the solid-phase lithium-ion diffusion model, and the mean square error function and boundary conditions of the liquid-phase lithium-ion diffusion model. Optionally, sample data is used to train the physical information network model, and the training process is completed when the target loss function reaches a preset condition to obtain the target diffusion single-event model.

[0084] Optionally, to ensure the accuracy of the constructed target loss function, in one embodiment, such as Figure 5 As shown, a method for constructing a target loss function is provided, which specifically includes the following steps:

[0085] S501, based on the mean square error function of the solid-phase lithium-ion diffusion model and the mean square error function of the liquid-phase lithium-ion diffusion model, construct the equation loss function.

[0086] Optionally, based on the mean square error function of the solid-phase lithium-ion diffusion model and the mean square error function of the liquid-phase lithium-ion diffusion model, the process of constructing the equation loss function can be expressed by the following formula (3):

[0087] (3)

[0088] in, Represents the loss function of the equation; This represents the number of samples in the solid-phase diffusion equation; This represents the number of samples in the liquid phase diffusion equation.

[0089] S502. Based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, a boundary loss function is constructed.

[0090] Optionally, based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, the process of constructing the boundary loss function can be represented by the following formula (4):

[0091] (4)

[0092] in, Represents the boundary loss function; This indicates the number of samples representing the internal boundary conditions of the ion. This indicates the number of samples for ion surface boundary conditions; This indicates the number of lithium-ion concentration samples on the left side of the electrolyte diaphragm; This indicates the number of lithium-ion concentration samples on the right side of the electrolyte diaphragm; This indicates the number of samples representing the lithium-ion concentration gradient on the left side of the electrolyte diaphragm; This indicates the number of samples representing the lithium-ion concentration gradient on the right side of the electrolyte diaphragm; Indicates the coordinate value on the right side of the diaphragm; Indicates the coordinate value to the left of the positive pole; Indicates the coordinate value to the right of the negative pole; This indicates the coordinates of the left side of the diaphragm.

[0093] S503. Determine the initial value loss function based on the values ​​of the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function at the moment the battery under test is powered on.

[0094] The power-on moment refers to the moment when the battery under test changes from a non-powered state to a powered state during the charging or discharging process.

[0095] Optionally, the process of determining the initial value loss function based on the values ​​of the solid-phase lithium ion concentration function and the liquid-phase lithium ion concentration function of the battery under test at the moment of power-on can be expressed by the following formula (5):

[0096] (5)

[0097] in, Represents the boundary loss function; Indicates the initial lithium-ion concentration in the solid phase; Indicates the initial lithium-ion concentration in the liquid phase; This indicates the number of samples with initial lithium-ion concentration in the solid phase. This indicates the number of samples with initial lithium-ion concentration in the liquid phase.

[0098] S504 uses the sum of the equation loss function, boundary loss function, and initial value loss function as the target loss function.

[0099] Optionally, the equation loss function, boundary loss function, and initial value loss function can be added together, and the sum can be used as the target loss function. Specifically, the target loss function can be expressed by the following formula (6):

[0100] (6)

[0101] in, This represents the target loss function.

[0102] In this embodiment, by introducing an equation loss function, a boundary loss function, and an initial value loss function, the additional physical constraints brought about by the diffusion single-particle model are fully considered, ensuring the accuracy of the determined target loss function, and thus ensuring the accuracy of the target diffusion single-particle model trained based on the target loss function.

[0103] Optionally, in one embodiment, such as Figure 6 As shown, a method for determining ion concentration is provided, which specifically includes the following steps:

[0104] S601 normalizes the battery operating condition parameters to obtain the normalized battery operating condition parameters.

[0105] Optionally, to ensure the computational accuracy of the target diffusion single-event model and the fit between the battery operating parameters and the model, the battery operating parameters need to be normalized to convert them into values ​​between 0 and 1. Specifically, a normalization tool can be used to normalize the battery operating parameters to obtain normalized battery operating parameters.

[0106] S602, input the normalized battery operating parameters into the target diffusion single-particle model to obtain the lithium-ion concentration of the battery under test at each time point in the current period.

[0107] Optionally, the normalized battery operating parameters can be input into the target diffusion single-event model, so that the target diffusion single-event model can process and calculate the normalized battery operating parameters based on the physical parameters, and output the lithium-ion concentration of the battery under test at each time in the current period.

[0108] In this embodiment of the application, by normalizing the battery operating parameters, the calculation accuracy of the target diffusion single-event model and the fit between the battery operating parameters and the target diffusion single-event model are ensured.

[0109] Optionally, after obtaining the lithium-ion concentration of the battery under test at various times within the current time period, to more intuitively illustrate the correspondence between battery capacity and lithium-ion concentration, a curve showing the relationship between battery capacity and lithium-ion concentration can be determined based on the battery capacity and lithium-ion concentration at various times within the current time period. Specifically, the battery capacity and lithium-ion concentration of the battery under test at various times within the current time period can be input into a regression model so that the regression model outputs a curve showing the relationship between battery capacity and lithium-ion concentration.

[0110] Figure 7This is a flowchart illustrating a method for determining the ion concentration of a battery in another embodiment. Based on the above embodiments, this embodiment provides an optional example of a method for determining the ion concentration of a battery. (Combined with...) Figure 7 The specific implementation process is as follows:

[0111] S701, obtain the battery operating parameters of the battery under test at various times within the current time period.

[0112] Among them, battery operating parameters include current information, battery capacity, and the location information of lithium ions in the battery under test.

[0113] S702, Obtain sample data.

[0114] The sample data includes the battery operating parameters and lithium-ion concentration of the battery under test at various historical moments within a historical period.

[0115] S703, based on the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function, constructs a solid-phase lithium-ion diffusion model.

[0116] Among them, the solid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times.

[0117] S704. A liquid phase lithium ion diffusion model is constructed based on the liquid phase lithium ion diffusion coefficient, electrolyte volume fraction, lithium ion transport number, and liquid phase lithium ion concentration function.

[0118] Among them, the liquid phase lithium ion concentration function is related to the position information of lithium ions in the battery under test at different times.

[0119] S705, based on the physical parameters in the initial diffusion single-particle model of the battery under test, initializes the physical information neural network to obtain the physical information network model of the battery under test.

[0120] S706 uses sample data to train a physical information network model, resulting in a single-particle model for target diffusion.

[0121] Optionally, the physical information network model is trained using the target loss function and sample data to obtain the target diffusion single-particle model; wherein, the target loss function is constructed based on the mean square error function and boundary conditions of the solid-phase lithium-ion diffusion model, as well as the mean square error function and boundary conditions of the liquid-phase lithium-ion diffusion model.

[0122] Optionally, an equation loss function is constructed based on the mean square error function of the solid-phase lithium-ion diffusion model and the mean square error function of the liquid-phase lithium-ion diffusion model; a boundary loss function is constructed based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model; an initial value loss function is determined based on the values ​​of the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function at the time the battery under test is energized; and the sum of the equation loss function, the boundary loss function, and the initial value loss function is used as the target loss function.

[0123] S707 normalizes the battery operating parameters to obtain normalized battery operating parameters.

[0124] S708 inputs the normalized battery operating parameters into the target diffusion single-particle model to obtain the lithium-ion concentration of the battery under test at each time point in the current period.

[0125] The specific processes of S701-S708 described above can be found in the description of the above method embodiments. Their implementation principles and technical effects are similar, and will not be repeated here.

[0126] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0127] Based on the same inventive concept, this application also provides a battery ion concentration determination apparatus for implementing the battery ion concentration determination method described above. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more battery ion concentration determination apparatus embodiments provided below can be found in the limitations of the battery ion concentration determination method described above, and will not be repeated here.

[0128] In one embodiment, such as Figure 8 As shown, a battery ion concentration determination device 800 is provided, including: a parameter acquisition module 810 and a concentration determination module 820, wherein:

[0129] The parameter acquisition module 810 is used to acquire the battery operating parameters of the battery under test at various times within the current time period; among which, the battery operating parameters include current information, battery capacity and lithium ion position information in the battery under test;

[0130] The concentration determination module 820 is used to determine the lithium-ion concentration of the battery under test at each moment in the current time period based on the target diffusion single-particle model of the battery under test and the battery operating parameters at each moment in the current time period. The target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network.

[0131] The aforementioned battery ion concentration determination device acquires battery condition parameters, including current information, battery capacity, and the location of lithium ions in the battery at various times within the current time period. Based on a target diffusion single-event model of the battery, it determines the lithium ion concentration of the battery at each time point within the current time period according to the battery condition parameters. The target diffusion single-event model is obtained by optimizing the physical parameters in the initial diffusion single-event model using a physical information neural network. This scheme optimizes the physical parameters in the initial diffusion single-event model using a physical information neural network, ensuring that each physical parameter in the target diffusion single-event model takes optimal values, thus further guaranteeing the accuracy of the target diffusion single-event model. Furthermore, by introducing current information and battery capacity, and combining them with the target diffusion single-event model, the accuracy of the determined lithium ion concentration in the battery is guaranteed. It can also obtain the lithium ion concentration of the battery under various application current conditions and battery capacity states, exhibiting stronger adaptability and scalability.

[0132] In one embodiment, the battery ion concentration determining device 800 further includes:

[0133] The data acquisition module is used to acquire sample data, which includes the battery operating parameters and lithium-ion concentration of the battery under test at various historical moments within a historical period.

[0134] The model optimization module is used to initialize the physical information neural network based on the physical parameters in the initial diffusion single-particle model of the battery under test, so as to obtain the physical information network model of the battery under test.

[0135] The model training module is used to train the physical information network model using sample data to obtain the target diffusion single-particle model.

[0136] In one embodiment, the model optimization module is further used for:

[0137] A solid-phase lithium-ion diffusion model is constructed based on the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function; wherein the solid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times. A liquid-phase lithium-ion diffusion model is constructed based on the liquid-phase lithium-ion diffusion coefficient, electrolyte volume fraction, lithium-ion transport number, and liquid-phase lithium-ion concentration function; wherein the liquid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times.

[0138] In one embodiment, the model training module is specifically used for:

[0139] The physical information network model is trained using a target loss function and sample data to obtain a target diffusion single-particle model. The target loss function is constructed based on the mean square error function and boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model.

[0140] In one embodiment, the model training module is also used for:

[0141] Based on the mean square error functions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, an equation loss function is constructed; based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, a boundary loss function is constructed; based on the values ​​of the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function at the time the battery under test is energized, an initial value loss function is determined; the sum of the equation loss function, the boundary loss function, and the initial value loss function is taken as the target loss function.

[0142] In one embodiment, the concentration determination module 820 is used for:

[0143] The battery operating parameters are normalized to obtain normalized battery operating parameters; the normalized battery operating parameters are then input into the target diffusion single-particle model to obtain the lithium-ion concentration of the battery under test at each time point in the current period.

[0144] In one embodiment, the battery ion concentration determining device 800 is further used for:

[0145] Based on the battery capacity and lithium-ion concentration of the battery under test at various times within the current time period, determine the corresponding curves of battery capacity and lithium-ion concentration of the battery under test.

[0146] Each module in the aforementioned battery ion concentration determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0147] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for determining the ion concentration of a battery.

[0148] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0149] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0150] Obtain the battery operating parameters of the battery under test at various times within the current time period; among which, the battery operating parameters include current information, battery capacity, and lithium ion position information in the battery under test;

[0151] Based on the target diffusion single-particle model of the battery under test, the lithium-ion concentration of the battery under test at each time point in the current time period is determined according to the battery operating parameters at each time point in the current time period. The target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network.

[0152] In one embodiment, when the processor executes a computer program, it also performs the following steps:

[0153] Acquire sample data, which includes battery operating parameters and lithium-ion concentration of the battery under test at various historical moments within a historical period; initialize the physical information neural network based on the physical parameters in the initial diffusion single-particle model of the battery under test to obtain the physical information network model of the battery under test; train the physical information network model using the sample data to obtain the target diffusion single-particle model.

[0154] In one embodiment, the initial diffusion single-particle model includes a solid-phase lithium-ion diffusion model and a liquid-phase lithium-ion diffusion model, and the processor, when executing the computer program, further implements the following steps:

[0155] A solid-phase lithium-ion diffusion model is constructed based on the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function; wherein the solid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times. A liquid-phase lithium-ion diffusion model is constructed based on the liquid-phase lithium-ion diffusion coefficient, electrolyte volume fraction, lithium-ion transport number, and liquid-phase lithium-ion concentration function; wherein the liquid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times.

[0156] In one embodiment, when the processor executes a computer program to train a physical information network model using sample data to obtain a target diffusion single-particle model, it also performs the following steps:

[0157] The physical information network model is trained using a target loss function and sample data to obtain a target diffusion single-particle model. The target loss function is constructed based on the mean square error function and boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model.

[0158] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0159] Based on the mean square error functions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, an equation loss function is constructed; based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, a boundary loss function is constructed; based on the values ​​of the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function at the time the battery under test is energized, an initial value loss function is determined; the sum of the equation loss function, the boundary loss function, and the initial value loss function is taken as the target loss function.

[0160] In one embodiment, when the processor executes a computer program to determine the ion concentration of the battery under test at various times within the current time period based on the target diffusion single-particle model of the battery under test and the battery operating parameters, it also performs the following steps:

[0161] The battery operating parameters are normalized to obtain normalized battery operating parameters; the normalized battery operating parameters are then input into the target diffusion single-particle model to obtain the lithium-ion concentration of the battery under test at each time point in the current period.

[0162] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0163] Based on the battery capacity and lithium-ion concentration of the battery under test at various times within the current time period, determine the corresponding curves of battery capacity and lithium-ion concentration of the battery under test.

[0164] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0165] Obtain the battery operating parameters of the battery under test at various times within the current time period; among which, the battery operating parameters include current information, battery capacity, and lithium ion position information in the battery under test;

[0166] Based on the target diffusion single-particle model of the battery under test, the lithium-ion concentration of the battery under test at each time point in the current time period is determined according to the battery operating parameters at each time point in the current time period. The target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network.

[0167] In one embodiment, when the processor executes a computer program, it also performs the following steps:

[0168] Acquire sample data, which includes battery operating parameters and lithium-ion concentration of the battery under test at various historical moments within a historical period; initialize the physical information neural network based on the physical parameters in the initial diffusion single-particle model of the battery under test to obtain the physical information network model of the battery under test; train the physical information network model using the sample data to obtain the target diffusion single-particle model.

[0169] In one embodiment, the initial diffusion single-particle model includes a solid-phase lithium-ion diffusion model and a liquid-phase lithium-ion diffusion model, and the processor, when executing the computer program, further implements the following steps:

[0170] A solid-phase lithium-ion diffusion model is constructed based on the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function; wherein the solid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times. A liquid-phase lithium-ion diffusion model is constructed based on the liquid-phase lithium-ion diffusion coefficient, electrolyte volume fraction, lithium-ion transport number, and liquid-phase lithium-ion concentration function; wherein the liquid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times.

[0171] In one embodiment, when the processor executes a computer program to train a physical information network model using sample data to obtain a target diffusion single-particle model, it also performs the following steps:

[0172] The physical information network model is trained using a target loss function and sample data to obtain a target diffusion single-particle model. The target loss function is constructed based on the mean square error function and boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model.

[0173] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0174] Based on the mean square error functions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, an equation loss function is constructed; based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, a boundary loss function is constructed; based on the values ​​of the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function at the time the battery under test is energized, an initial value loss function is determined; the sum of the equation loss function, the boundary loss function, and the initial value loss function is taken as the target loss function.

[0175] In one embodiment, when the processor executes a computer program to determine the ion concentration of the battery under test at various times within the current time period based on the target diffusion single-particle model of the battery under test and the battery operating parameters, it also performs the following steps:

[0176] The battery operating parameters are normalized to obtain normalized battery operating parameters; the normalized battery operating parameters are then input into the target diffusion single-particle model to obtain the lithium-ion concentration of the battery under test at each time point in the current period.

[0177] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0178] Based on the battery capacity and lithium-ion concentration of the battery under test at various times within the current time period, determine the corresponding curves of battery capacity and lithium-ion concentration of the battery under test.

[0179] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0180] Obtain the battery operating parameters of the battery under test at various times within the current time period; among which, the battery operating parameters include current information, battery capacity, and lithium ion position information in the battery under test;

[0181] Based on the target diffusion single-particle model of the battery under test, the lithium-ion concentration of the battery under test at each time point in the current time period is determined according to the battery operating parameters at each time point in the current time period. The target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network.

[0182] In one embodiment, when the processor executes a computer program, it also performs the following steps:

[0183] Acquire sample data, which includes battery operating parameters and lithium-ion concentration of the battery under test at various historical moments within a historical period; initialize the physical information neural network based on the physical parameters in the initial diffusion single-particle model of the battery under test to obtain the physical information network model of the battery under test; train the physical information network model using the sample data to obtain the target diffusion single-particle model.

[0184] In one embodiment, the initial diffusion single-particle model includes a solid-phase lithium-ion diffusion model and a liquid-phase lithium-ion diffusion model, and the processor, when executing the computer program, further implements the following steps:

[0185] A solid-phase lithium-ion diffusion model is constructed based on the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function; wherein the solid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times. A liquid-phase lithium-ion diffusion model is constructed based on the liquid-phase lithium-ion diffusion coefficient, electrolyte volume fraction, lithium-ion transport number, and liquid-phase lithium-ion concentration function; wherein the liquid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times.

[0186] In one embodiment, when the processor executes a computer program to train a physical information network model using sample data to obtain a target diffusion single-particle model, it also performs the following steps:

[0187] The physical information network model is trained using a target loss function and sample data to obtain a target diffusion single-particle model. The target loss function is constructed based on the mean square error function and boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model.

[0188] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0189] Based on the mean square error functions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, an equation loss function is constructed; based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, a boundary loss function is constructed; based on the values ​​of the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function at the time the battery under test is energized, an initial value loss function is determined; the sum of the equation loss function, the boundary loss function, and the initial value loss function is taken as the target loss function.

[0190] In one embodiment, when the processor executes a computer program to determine the ion concentration of the battery under test at various times within the current time period based on the target diffusion single-particle model of the battery under test and the battery operating parameters, it also performs the following steps:

[0191] The battery operating parameters are normalized to obtain normalized battery operating parameters; the normalized battery operating parameters are then input into the target diffusion single-particle model to obtain the lithium-ion concentration of the battery under test at each time point in the current period.

[0192] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0193] Based on the battery capacity and lithium-ion concentration of the battery under test at various times within the current time period, determine the corresponding curves of battery capacity and lithium-ion concentration of the battery under test.

[0194] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data that have been fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0195] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0196] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0197] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining the ion concentration of a battery, characterized in that, The method includes: Obtain the battery operating parameters of the battery under test at various times within the current time period; wherein, the battery operating parameters include current information, battery capacity, and lithium ion position information in the battery under test; Based on the target diffusion single-particle model of the battery under test, the lithium-ion concentration of the battery under test at each time point in the current time period is determined according to the battery operating parameters of the battery under test at each time point in the current time period; wherein, the target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on a physical information neural network. The initial diffusion single-particle model includes a solid-phase lithium-ion diffusion model and a liquid-phase lithium-ion diffusion model, and the initial diffusion single-particle model is obtained in the following way: The solid-phase lithium-ion diffusion model is constructed based on the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function; wherein, the solid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times. The liquid-phase lithium-ion diffusion model is constructed based on the liquid-phase lithium-ion diffusion coefficient, electrolyte volume fraction, lithium-ion transport number, and liquid-phase lithium-ion concentration function; wherein, the liquid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times. The target diffusion single-particle model is obtained by training a physical information neural network model using a target loss function and sample data; wherein, the target loss function is constructed based on the mean square error function and boundary conditions of the solid-phase lithium-ion diffusion model, the mean square error function and boundary conditions of the liquid-phase lithium-ion diffusion model, as well as the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function. The target loss function is obtained in the following way: Based on the mean square error function of the solid-phase lithium-ion diffusion model and the mean square error function of the liquid-phase lithium-ion diffusion model, an equation loss function is constructed; based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model, a boundary loss function is constructed; based on the values ​​of the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function at the time the battery under test is energized, an initial value loss function is determined; the sum of the equation loss function, the boundary loss function, and the initial value loss function is taken as the target loss function. The method further includes: Based on the battery capacity and lithium-ion concentration of the battery under test at various times within the current time period, determine the corresponding curves of the battery capacity and lithium-ion concentration of the battery under test.

2. The method according to claim 1, characterized in that, The target diffusion single-particle model is obtained in the following way: Acquire sample data; wherein, the sample data includes the battery operating parameters and lithium-ion concentration of the battery under test at each historical moment within a historical period; Based on the physical parameters in the initial diffusion single-particle model of the battery under test, the physical information neural network is initialized to obtain the physical information neural network model of the battery under test. Using the sample data, the physical information neural network model is trained to obtain a target diffusion single-particle model.

3. The method according to claim 1, characterized in that, The target diffusion single-particle model based on the battery under test determines the ion concentration of the battery under test at various times within the current time period according to the battery operating parameters, including: The battery operating condition parameters are normalized to obtain normalized battery operating condition parameters. The normalized battery operating parameters are input into the target diffusion single-particle model to obtain the lithium-ion concentration of the battery under test at each time point in the current time period.

4. The method according to claim 1, characterized in that, The step of determining the corresponding curves of battery capacity and lithium-ion concentration of the battery under test based on the battery capacity and lithium-ion concentration at various times within the current time period includes: The battery capacity and lithium-ion concentration of the battery under test at various times within the current time period are input into the regression model, and the regression model is used to output the corresponding curves of the battery capacity and lithium-ion concentration of the battery under test.

5. The method according to claim 1, characterized in that, The energization time is the moment when the battery under test changes from a non-energized state to an energized state during the charging or discharging process.

6. A device for determining the ion concentration of a battery, characterized in that, The device includes: The parameter acquisition module is used to acquire the battery operating condition parameters of the battery under test at various times within the current time period; wherein, the battery operating condition parameters include current information, battery capacity, and lithium ion position information in the battery under test; The concentration determination module is used to determine the lithium-ion concentration of the battery under test at each moment in the current time period based on the target diffusion single-particle model of the battery under test and the battery operating parameters of the battery under test at each moment in the current time period; wherein, the target diffusion single-particle model is obtained by optimizing the physical parameters in the initial diffusion single-particle model based on the physical information neural network. The initial diffusion single-particle model includes a solid-phase lithium-ion diffusion model and a liquid-phase lithium-ion diffusion model; the device further includes: The model optimization module is used to construct a solid-phase lithium-ion diffusion model based on the solid-phase lithium-ion diffusion coefficient and the solid-phase lithium-ion concentration function; wherein the solid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times; and to construct a liquid-phase lithium-ion diffusion model based on the liquid-phase lithium-ion diffusion coefficient, electrolyte volume fraction, lithium-ion transport number, and liquid-phase lithium-ion concentration function; wherein the liquid-phase lithium-ion concentration function is related to the position information of lithium ions in the battery under test at different times. The target diffusion single-particle model is obtained by training a physical information neural network model using a target loss function and sample data; wherein, the target loss function is constructed based on the mean square error function and boundary conditions of the solid-phase lithium-ion diffusion model, the mean square error function and boundary conditions of the liquid-phase lithium-ion diffusion model, as well as the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function. The model training module is used to construct an equation loss function based on the mean square error function of the solid-phase lithium-ion diffusion model and the mean square error function of the liquid-phase lithium-ion diffusion model; construct a boundary loss function based on the boundary conditions of the solid-phase lithium-ion diffusion model and the liquid-phase lithium-ion diffusion model; determine an initial value loss function based on the values ​​of the solid-phase lithium-ion concentration function and the liquid-phase lithium-ion concentration function at the time the battery under test is powered on; and use the sum of the equation loss function, the boundary loss function, and the initial value loss function as the target loss function. The device is also used to determine the corresponding curves of the battery capacity and lithium ion concentration of the battery under test based on the battery capacity and lithium ion concentration of the battery under test at various times within the current time period.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images