Testing method and apparatus for SOH of lithium battery, and electronic device and storage medium

Abstract

A testing method and apparatus for the SOH of a lithium battery, and an electronic device and a storage medium. The testing method comprises: during a charging cycle of a target lithium battery, collecting N charging data sequences corresponding to N charging parameters, wherein N is an integer greater than or equal to 3 (S110); processing the N charging data sequences by using a grey relation analysis method, so as to obtain N charging health features (S120); inputting the N charging health features into a pre-trained neural network model, so as to obtain a predicted capacity degradation value (S130); and determining the SOH of the lithium battery on the basis of the capacity degradation value (S140). Input parameters of a pre-trained neural network model are charging health features of N charging parameters that are obtained by means of a grey relation analysis method, such that health features more related to an SOH have higher weights, which is equivalent to weighting an input neural network model in advance, and thus a predicted capacity degradation value which is output by the neural network model is more accurate.

Description

Lithium battery SOH detection method, device, electronic device and storage medium

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on September 26, 2023, with application number 202311264329.4 and application name “Detection method, device, electronic device and storage medium for lithium battery SOH”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application belongs to the field of energy storage technology, and in particular relates to a method, device, electronic device and storage medium for detecting the state of health (SOH) of a lithium battery. Background Art

[0003] A lithium battery's State of Health (SOH) refers to its health or lifespan. It's a crucial indicator for measuring battery performance and remaining lifespan, making it extremely useful for evaluating and monitoring the battery's condition. SOH describes the ratio of a battery's actual capacity to its initial capacity, reflecting the battery's degradation during use. Typically, SOH is expressed as a percentage, ranging from 0% (indicating a dead battery) to 100% (indicating an intact battery).

[0004] As lithium batteries age, their ability to store charge decreases. Accurately predicting the SOH of lithium batteries can reduce safety incidents caused by aging and provide a reference for battery retirement, ensuring their stability and safety during use. Therefore, accurately predicting the SOH of lithium batteries has become a pressing issue.

[0005] Application Contents

[0006] The present application provides a lithium battery SOH detection method, device, electronic device and storage medium, which can solve the problem of accurately predicting at least part of the lithium battery SOH.

[0007] In a first aspect, an embodiment of the present application provides a method for detecting SOH of a lithium battery, comprising:

[0008] During the charging cycle of the target lithium battery, N charging data sequences corresponding to N charging parameters are collected, where N is an integer greater than or equal to 3;

[0009] Processing the N charging data sequences using a grey correlation analysis method to obtain N charging health features;

[0010] Inputting the N charging health features into a pre-trained neural network model to obtain a predicted capacity degradation value;

[0011] The SOH of the lithium battery is determined according to the capacity degradation value.

[0012] It should be understood that since the input parameters of the pre-trained neural network model use the charging health characteristics of N charging parameters obtained by the grey correlation analysis method, the health characteristics that are more relevant to SOH have higher weights, which is equivalent to pre-weighting the input neural network model. In this way, the predicted capacity degradation value output by the neural network model will be more accurate.

[0013] In a second aspect, an embodiment of the present application provides a device for detecting SOH of a lithium battery, comprising:

[0014] A charging data acquisition module, configured to acquire N charging data sequences corresponding to N charging parameters during a charging cycle of a target lithium battery, where N is an integer greater than or equal to 3;

[0015] a charging health feature acquisition module, configured to process the N charging data sequences using a grey correlation analysis method to obtain N charging health features;

[0016] a predicted capacity degradation value determination module, configured to input the N charging health features into a pre-trained neural network model to obtain a predicted capacity degradation value;

[0017] The lithium battery SOH determination module is used to determine the lithium battery SOH according to the capacity degradation value.

[0018] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0019] A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the method steps described in the first aspect.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising: the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in the first aspect are implemented.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute the method steps described in the first aspect above.

[0022] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0024] FIG1 is a flow chart of a method for detecting SOH of a lithium battery provided in one embodiment of the present application;

[0025] FIG2 is a schematic diagram of a process for performing error compensation on the BP neural network model using a grey model according to an embodiment of the present application;

[0026] FIG3 is a schematic structural diagram of a lithium battery SOH detection device provided in an embodiment of the present application;

[0027] FIG4 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. Modes for Carrying Out the Invention

[0028] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0029] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0030] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0032] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0033] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0034] Before explaining the method for detecting SOH of a lithium battery provided in the embodiment of the present application, in order to facilitate understanding of the embodiment of the present application, the relevant concepts involved in the embodiment of the present application are explained below.

[0035] Grey relational analysis is a method used to study and evaluate the correlation between multiple factors. It is suitable for analysis when the data is incomplete, vague or lacks historical information.

[0036] The grey model system is a system modeling method used to deal with incomplete, fuzzy, or lacking historical data. Based on grey system theory, it aims to reveal the inherent laws behind the data by analyzing and predicting data sequences, providing decision support and forecasting capabilities.

[0037] Whitening differential equations are a type of differential equation that aims to transform the original equation into a simpler form through a transformation. Using a method called "whitening the variables," they can eliminate or reduce nonlinear terms, high-order terms, or other difficult-to-handle characteristics in the original equation.

[0038] A BP neural network, also known as a backpropagation neural network, is an artificial neural network model used to solve problems such as classification and regression. A BP neural network consists of multiple nodes (neurons) and connections, typically divided into an input layer, a hidden layer, and an output layer. Each node has an activation function that converts input signals into output signals. Each connection has a weight that adjusts the strength of the signal transmission.

[0039] The charging cycle of a lithium battery refers to the process of restoring the battery from a discharged state to a fully charged state, which usually includes the following states: pre-charging, constant current charging, constant voltage charging and charging cutoff.

[0040] The present application provides a method for online estimation of the SOH of lithium-ion batteries based on a neural network model, the purpose of which is to improve the accuracy of SOH estimation in the prior art. The present application collects parameters related to voltage, current, and temperature at different charging stages, uses a gray correlation analysis method to extract parameter sequences, obtains battery health characteristics, uses a trained BP neural network to use the lithium battery charging health characteristics extracted by the gray correlation analysis as input, and calculates the capacity degradation value of the lithium-ion battery. The lithium battery charging health characteristics extracted by the gray correlation analysis have higher weights than health characteristics that are more relevant to SOH, which is equivalent to pre-weighting the input neural network model, making the SOH estimation more accurate.

[0041] Example 1

[0042] FIG1 shows a method for detecting SOH of a lithium battery provided by an embodiment of the present application, which is applied to an electronic device for detecting SOH of a lithium battery and can be implemented by software and / or hardware of the electronic device. As shown in FIG1 , the method includes steps S110 to S140. The specific implementation principles of each step are as follows:

[0043] S110 , during a charging cycle of a target lithium battery, collecting N charging data sequences corresponding to N charging parameters, where N is an integer greater than or equal to 3.

[0044] In some embodiments, the target lithium battery is a lithium battery to be tested for which SOH needs to be obtained. During the charging cycle of the target lithium battery, N charging data sequences corresponding to N charging parameters are collected, where N is an integer greater than or equal to 3. That is, for each charging parameter, a corresponding charging data sequence is collected. It should be noted that the number of elements k in the charging data sequence can be selected according to actual conditions. Specifically, N charging parameters can be collected separately and fitted into curves, and the curves corresponding to each parameter are sampled according to a preset sampling step size to obtain the corresponding charging data sequence. It can be understood that the process of obtaining a charging sequence corresponding to a charging parameter can be that the currently sampled parameter is the kth sampling parameter, and the previously sampled k-1 parameters constitute the charging data sequence corresponding to the charging parameter.

[0045] The N charging parameters include at least three of the following parameters: constant voltage charging time , constant current charging time , the ratio of constant voltage charging time to constant current charging time , constant voltage charging current The integral value over time, constant current charging current The integral value over time, constant voltage charging temperature The integral value over time, constant current charging temperature The integral value over time, the maximum slope of the charging voltage versus time curve , the maximum slope of the charging current versus time curve , constant voltage charging temperature Integral value over time / constant voltage charging current The integral value over time, constant current charging temperature Integral value over time / constant current charging current The N charging parameters include at least parameters related to voltage, current, and temperature. In some specific examples, at least one parameter related to voltage, current, and temperature is selected. Of course, selecting all 11 charging parameters can make the detected SOH more accurate.

[0046] The operating conditions of lithium batteries during the discharge process are uncertain, and indirect health characteristics of lithium-ion batteries are usually extracted from the charging stage. The charging process of the currently used lithium-ion batteries is constant current charging followed by constant voltage charging. The voltage, current and temperature can be collected at different charging stages, and the charging health characteristics can be extracted based on the collected information.

[0047] S120 , using a grey correlation analysis method to process the N charging data sequences to obtain N charging health features.

[0048] In some embodiments, the following steps may be specifically included:

[0049] Perform dimensionless processing on N data sequences and use the capacity sequence obtained by dimensionless processing as the reference sequence , the charging data sequence is set as the comparison sequence , i=1, 2, 3..., N;

[0050] According to the correlation coefficient formula

[0051] , solve the grey correlation coefficient of each charging data sequence and capacity sequence ;

[0052] According to the formula

[0053]

[0054] Calculate the average value of the grey correlation coefficient of the i-th charging data sequence and use it as the charging health feature of the i-th charging data sequence;

[0055] Where n is the number of data in the sequence, and ρ is the resolution coefficient, which ranges from [0, 1]. Specifically, ρ can be 0.5.

[0056] S130 , inputting N charging health features into a pre-trained neural network model to obtain a predicted capacity degradation value.

[0057] The pre-trained neural network model is a BP neural network model, the number of input nodes of the BP neural network model is N nodes, and the number of output nodes is 1 node. In some embodiments, the number of hidden layers is 1, and the number of hidden layer nodes is 8.

[0058] Specifically, N charging health features are input into a pre-trained neural network model. Since the weights between the nodes of the pre-trained neural network model have been determined, it can output the predicted capacity degradation value.

[0059] S140: Determine the SOH of the lithium battery according to the capacity degradation value.

[0060] In some embodiments, the formula

[0061]

[0062] Calculating the estimated value of a lithium battery .

[0063] in, is the initial capacity of the lithium battery, Get the predicted capacity degradation value for the pre-trained neural network model.

[0064] It should be understood that grey system theory proposes the concept of grey relational analysis of each subsystem, intending to use certain methods to find the numerical relationship between subsystems in the system. Therefore, grey relational analysis provides a quantitative measure of the development and change of a system, which is very suitable for dynamic process analysis.

[0065] Since the input parameters of the pre-trained neural network model use the charging health characteristics of N charging parameters obtained by the grey correlation analysis method, the health characteristics that are more relevant to SOH have higher weights, which is equivalent to pre-weighting the input neural network model. In this way, the predicted capacity degradation value output by the neural network model will be more accurate.

[0066] Example 2

[0067] In the process of charging the target lithium battery in a cycle, before the step of collecting N charging data sequences corresponding to N charging parameters, a process of training the BP neural network model is also included.

[0068] In some embodiments, multiple sets of charging data sequence samples corresponding to N types of charging parameters are collected during a complete charging cycle, and capacity degradation value samples corresponding to each set of charging data sequence samples are obtained, where each set of charging data sequence samples includes N charging data sequences. Each set of charging data sequence samples is processed using a gray correlation analysis method to obtain a corresponding charging health feature. The charging health feature corresponding to each set of charging data sequence samples is used as the input value of the input node of a BP neural network model, and the capacity degradation value samples are used as the output value of the BP neural network model. The BP neural network model is trained, and during the training process, the gray model is used to compensate for the error of the BP neural network model, thereby obtaining a pre-trained neural network model.

[0069] Specifically, multiple groups of charging data sequence samples corresponding to multiple groups of N charging parameters may be obtained in multiple charging cycles, and the capacity degradation value samples corresponding to each group of charging data sequence samples may be detected and obtained simultaneously.

[0070] For examples of performing grey correlation analysis on multiple groups of charging data sequence samples corresponding to N types of charging parameters, reference may be made to other embodiments of the present application, which will not be described in detail here.

[0071] Since the BP neural network has a simple structure and a fast update speed when a reasonable correction algorithm is selected, it can meet the needs of real-time SOH prediction. Therefore, the BP neural network is selected to predict the battery SOH.

[0072] When training the neural network, the grey correlation analysis method is used to extract the charging health characteristics of the lithium battery as the input of the neural network algorithm, and the capacity degradation value is used as the output to build the neural network model. The specific process of building the neural network model includes the following steps:

[0073] Step A: Initialize the neural network. The number of input and output layer neuron nodes is selected based on the input and output dimensions. Specifically, the number of input layer nodes is determined based on the charging parameter N selected in this embodiment. For example, if the charging parameter N is 11, then the number of input layer nodes is 11, the number of output layer nodes is 1, and the number of hidden layer nodes is 8. The number of hidden layer layers and nodes can be selected based on actual conditions.

[0074] Initialize the connection weights and thresholds between adjacent layers, set appropriate training targets and learning rates, and select appropriate neuron activation functions.

[0075] Step B: Calculate the hidden layer output based on the selected neuron activation function. The output calculation formula is as follows:

[0076]

[0077]

[0078] in, is the output of the jth neural node in the hidden layer, is the i-th input of the input layer, is the threshold of the jth neuron in the hidden layer, is the activation function of the hidden layer.

[0079] Step C, calculate the output of the output layer. The output calculation formula is as follows:

[0080]

[0081] in, is the output of the kth neural node in the output layer, is the threshold of the kth neural node in the output layer.

[0082] Step D: Calculate the neural network estimation error. The error calculation formula is as follows:

[0083]

[0084] in, The output error of the kth neural node in the output layer, is the expected output of the kth node in the output layer.

[0085] It should be pointed out that when the output node of the BP neural network is 1 node, k in the above steps of training the neural network is 1.

[0086] Step E: Use the steepest descent method to update the weights and thresholds.

[0087] Step F: Determine whether the iteration of the neural network algorithm is completed. If not, return to step B.

[0088] The BP neural network has a simple structure and a fast update speed when a reasonable correction algorithm is selected, which can meet the needs of real-time SOH prediction. Therefore, the BP neural network is selected to predict the battery SOH.

[0089] Example 3

[0090] On the basis of the second embodiment, as shown in FIG2 , the gray model is used to compensate the error of the BP neural network model, that is, the error of the neural network estimation of the current output is Perform error compensation.

[0091] The method includes steps S210 to S220:

[0092] Step 1 ( S210 ) Error accumulation is generated.

[0093] Get the k-1 neural network estimation errors before the current k-th output of the BP neural network model , ..., , as the original sequence, and set the predicted value .

[0094] Specifically, the formula Perform a cumulative generation operation on the original sequence.

[0095] Step 2 (S220) establishes a whitened form differential equation.

[0096]

[0097] The least squares method is used to determine the unknown parameters a and b. The least squares method is used to determine the unknown parameters a and b, specifically using the following formula:

[0098] parameter vector ,

[0099] ,

[0100] ,

[0101] .

[0102] Step 3 (S230), solving the predicted value of the whitening differential equation :

[0103] Step 4 (S240) uses an inverse cumulative generation operation to solve the error estimate.

[0104] Specifically, the formula Solve the current corrected capacity degradation estimation error Estimated value of .

[0105] Step 5 ( S250 ) is to calculate the corrected capacity degradation amount of the aging cycle.

[0106] Specifically, the formula Calculate the corrected capacity degradation of the kth aging cycle of the current output of the BP neural network model, where k is the number of sampling times.

[0107] In order to improve the estimation accuracy of SOH, a grey model feedforward error compensation system is designed when training the BP neural network. The estimation error of capacity degradation is calculated based on historical capacity data and estimated capacity degradation. The grey model is used to correct the capacity degradation at each step, making the trained BP neural network's prediction of SOH more accurate.

[0108] Example 4

[0109] Corresponding to the lithium battery SOH detection method shown in FIG1 , FIG3 shows a lithium battery SOH detection device M100 provided in an embodiment of the present application, comprising:

[0110] The charging data acquisition module M110 is used to collect N charging data sequences corresponding to N charging parameters during the charging cycle of the target lithium battery, where N is an integer greater than or equal to 3;

[0111] A charging health feature acquisition module M120 is used to process N charging data sequences using a grey correlation analysis method to obtain N charging health features;

[0112] A predicted capacity degradation value determination module M130 is configured to input N charging health features into a pre-trained neural network model to obtain a predicted capacity degradation value;

[0113] The lithium battery SOH determination module M140 is configured to determine the lithium battery SOH according to the capacity degradation value.

[0114] It should be noted that, for the convenience and simplicity of description, the specific working process of the lithium battery SOH detection device can refer to the corresponding process of the above-mentioned lithium battery SOH detection method, and will not be repeated here.

[0115] It can be understood that the various implementation methods and implementation combinations and their beneficial effects in the above embodiments are also applicable to this embodiment and will not be described in detail here.

[0116] Example 5

[0117] Figure 4 is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. As shown in Figure 4, the electronic device D10 of this embodiment includes: at least one processor D100 (only one is shown in Figure 4), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100. When the processor D100 executes the computer program D102, the steps of any of the above-described method embodiments are implemented.

[0118] The electronic device D10 may be a computing device such as a desktop computer, a laptop, a PDA, or a cloud server. The electronic device may include, but is not limited to, a processor D100 and a memory D101. Those skilled in the art will appreciate that FIG4 is merely an example of the electronic device D10 and does not limit the electronic device D10. The electronic device D10 may include more or fewer components than shown, or may combine certain components or different components. For example, it may also include input / output devices, network access devices, etc.

[0119] The processor D100 may be a central processing unit (CPU), or may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0120] In some embodiments, memory D101 may be an internal storage unit of electronic device D10, such as a hard disk or memory of electronic device D10. In other embodiments, memory D101 may also be an external storage device of electronic device D10, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on electronic device D10. Furthermore, memory D101 may include both an internal storage unit of electronic device D10 and an external storage device. Memory D101 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of a computer program. Memory D101 may also be used to temporarily store data that has been output or is about to be output.

[0121] 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 this application.

[0122] 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, and will not be repeated here.

[0123] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0124] An embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0125] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. Computer-readable media can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording media, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunications signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunications signals.

[0126] 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.

[0127] 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. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0128] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. 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.

[0129] 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.

[0130] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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 application, and should all be included in the scope of protection of the present application.

[0131] The above disclosure is only a preferred embodiment of the present application, and certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A method for detecting SOH of a lithium battery, characterized in that: include: During the charging cycle of the target lithium battery, N charging data sequences corresponding to N charging parameters are collected, where N is an integer greater than or equal to 3; The N charging data sequences are processed by using a grey correlation analysis method to obtain N charging health features; Inputting the N charging health features into a pre-trained neural network model to obtain a predicted capacity degradation value; The SOH of the lithium battery is determined according to the capacity degradation value.

2. The detection method according to claim 1, characterized in that The N charging parameters include at least three of the following parameters: Constant voltage charging time , constant current charging time , the ratio of constant voltage charging time to constant current charging time , constant voltage charging current The integral value over time, constant current charging current The integral value over time, constant voltage charging temperature The integral value over time, constant current charging temperature The integral value over time, the maximum slope of the charging voltage versus time curve , the maximum slope of the charging current versus time curve , constant voltage charging temperature Integrated value over time / constant voltage charging current The integral value over time, constant current charging temperature Integrated value over time / constant current charging current The integral value over time.

3. [Corrected 17.04.2024 in accordance with Rule 91] The detection method as claimed in claim 1, characterized in that The N charging data sequences are processed by using a grey correlation analysis method to obtain N charging health features, including: The N data sequences are dimensionlessly processed, and the capacity sequence obtained by the dimensionless processing is used as the reference sequence X0={x0(k)}, and the charging data sequence is set as the comparison sequence X0={x0(k)}. i ={x i (k)}, i=1, 2, 3..., N; According to the correlation coefficient formula Solve the grey correlation coefficient ξ of each charging data sequence and capacity sequence i (k); According to the formula Calculate the average value of the grey correlation coefficient of the i-th charging data sequence and use it as the charging health feature of the i-th charging data sequence; Where n is the number of data in the sequence; ρ is the resolution coefficient, which ranges from [0,1].

4. [Corrected 17.04.2024 in accordance with Rule 91] The detection method as claimed in claim 1, characterized in that The pre-trained neural network model is a BP neural network model, the number of input nodes of the BP neural network model is N, and the number of output nodes is 1; In the process of charging the target lithium battery in a cycle, before the step of collecting N charging data sequences corresponding to N charging parameters, the method further includes: Collecting multiple groups of charging data sequence samples corresponding to N charging parameters in a complete charging cycle, and obtaining capacity degradation value samples corresponding to each group of the charging data sequence samples, each group of charging data sequence samples comprising N charging data sequences; Using grey correlation analysis method to process each group of charging data sequence samples to obtain corresponding charging health characteristics; The charging health feature corresponding to each group of charging data sequence samples is used as the input value of the input node of the BP neural network model, and the capacity degradation value sample is used as the output value of the BP neural network model. The BP neural network model is trained, and the gray model is used to compensate the error of the BP neural network model during the training process to obtain the pre-trained neural network model.

5. [Corrected 17.04.2024 in accordance with Rule 91] The detection method according to claim 4, characterized in that The gray model is used to perform error compensation on the BP neural network model, including: Step 1: Obtain the output errors err1, err2, ..., err1 before the current k-1 output of the BP neural network model k-1 , as the original sequence, and set the predicted value Using formula Performing a cumulative generation operation on the original sequence; Step 2: Establish the whitened differential equation model And the least square method is used to determine the unknown parameters a and b; Step 3: Solve the predicted value of the whitening differential equation Step 4, use the formula Solve the current corrected capacity degradation estimation error err k Estimated value of Step 5, use the formula Calculate the corrected capacity degradation of the kth aging cycle currently output by the BP neural network model, Among them, k is the number of sampling times.

6. [Corrected 17.04.2024 in accordance with Rule 91] The detection method according to claim 5, characterized in that The unknown parameters a and b are determined by the least square method, including calculating the parameters a and b by the following formula: Parameter vector Y k =[err2 err3 … err k-1 ] T 。 7. [Corrected 17.04.2024 in accordance with Rule 91] A method of detection as claimed in claims 1 to 6, characterized in that Determining the SOH of the lithium battery according to the capacity degradation value includes: Using formula Calculate the estimated SOH of a lithium battery, Where C is the initial capacity of the lithium battery, Get the predicted capacity degradation value for the pre-trained neural network model.

8. [Corrected 17.04.2024 in accordance with Rule 91] A device for detecting SOH of a lithium battery, characterized in that: include: A charging data acquisition module, used to collect N charging data sequences corresponding to N charging parameters during the charging cycle of the target lithium battery, where N is an integer greater than or equal to 3; A charging health feature acquisition module, used to process the N charging data sequences using a grey correlation analysis method to obtain N charging health features; A predicted capacity degradation value determination module, used for inputting the N charging health features into a pre-trained neural network model to obtain a predicted capacity degradation value; The lithium battery SOH determination module is used to determine the lithium battery SOH according to the capacity degradation value.

9. [Corrected 17.04.2024 in accordance with Rule 91] An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. [Corrected 17.04.2024 in accordance with Rule 91] A computer-readable storage medium storing a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. [Corrected 17.04.2024 in accordance with Rule 91][Deleted] 12. [Corrected 17.04.2024 in accordance with Rule 91][Deleted]

Images