Method and device for quickly estimating residual capacity of retired battery, electronic equipment and medium

Abstract

The invention provides a method and device for quickly estimating the residual capacity of a decommissioned battery, electronic equipment and a medium, and belongs to the field of battery capacity tests.The method comprises the steps that a sample impedance characteristic spectrum of a sample decommissioned battery is obtained, and parameter identification circuit fitting is carried out to obtain circuit element parameters; performing feature screening on the circuit element parameters to obtain a first feature subset, performing feature screening on the sample impedance feature spectrum to obtain a second feature subset, and combining the first feature subset and the second feature subset to obtain a comprehensive feature parameter set; and performing iterative optimization according to the comprehensive characteristic parameter set to obtain a battery residual capacity prediction model, and performing rapid capacity estimation on the to-be-detected retired battery according to the battery residual capacity prediction model to obtain a residual capacity evaluation result. According to the method, the battery residual capacity is estimated through the impedance characteristic spectrum of the decommissioned battery, the measurement speed is high, the battery capacity estimation efficiency is effectively improved, meanwhile, only a certain degree of charging is needed, and resource waste in the discharging process is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of battery capacity testing, and in particular to a method, device, electronic equipment and medium for quickly estimating the remaining capacity of a retired battery. Background Art

[0002] With the development of new energy technologies and the rapid popularization of new energy vehicles, the scale of lithium battery use continues to increase, and a large number of waste lithium batteries are facing the problem of safe recycling and environmentally friendly treatment. Generally, retired lithium batteries of electric vehicles still have about 80% of residual capacity, which has a high use value and can be used in energy storage power stations, low-speed electric vehicles, power tools and other scenarios that do not require high battery performance. The cascade utilization of retired lithium batteries can improve their use value throughout their life cycle, which has a huge market scale and benefits.

[0003] However, due to capacity attenuation, the consistency between single cells of retired lithium battery packs is poor, resulting in unknown health status of retired lithium batteries before cascade utilization. They need to be re-evaluated before they can be reused. The current mainstream method for estimating the capacity of retired batteries is to calibrate the capacity by charging and discharging the battery, which can obtain relatively accurate measurement results. However, when the battery capacity is large, its charging and discharging time will be too long. The existing battery capacity evaluation method is difficult to meet the needs of large-scale retired lithium battery capacity estimation, and the discharged electricity cannot be reused, resulting in a large waste of resources.

[0004] Therefore, the existing technology has the technical problems of too long charging and discharging time, low capacity estimation efficiency, and difficulty in meeting the demand for capacity estimation of large quantities of retired batteries. At the same time, the discharged electricity cannot be reused, resulting in waste of resources, which needs to be improved. Summary of the invention

[0005] In view of this, it is necessary to provide a method, device, electronic device and medium for quickly estimating the remaining capacity of retired batteries, so as to solve the technical problems existing in the prior art that the charging and discharging time is too long, the capacity estimation efficiency is low, it is difficult to meet the demand for capacity estimation of large quantities of retired batteries, and the discharged electricity cannot be reused, resulting in waste of resources.

[0006] In order to solve the above problems, on the one hand, the present invention provides a method for quickly estimating the remaining capacity of a retired battery, comprising: Obtain a sample impedance characteristic spectrum of a sample retired battery, and perform parameter identification circuit fitting based on the sample impedance characteristic spectrum to obtain circuit element parameters; Performing feature screening on circuit element parameters to obtain a first feature subset, performing feature screening on sample impedance characteristic spectrum to obtain a second feature subset, and combining the first feature subset and the second feature subset to obtain a comprehensive feature parameter set; The initial battery remaining capacity prediction model is iteratively optimized according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, and the capacity of the retired battery to be detected is quickly estimated according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result.

[0007] In a possible implementation, the test environment of the sample retired battery and the retired battery to be tested is consistent, and the test charge state is fully charged.

[0008] In a possible implementation, obtaining a sample impedance characteristic spectrum of a sample retired battery includes: After applying an AC excitation signal to the sample retired battery, current and voltage sampling is performed to obtain current sampling data and voltage sampling data, and a sample impedance characteristic spectrum is constructed according to the current sampling data, voltage sampling data and the preset calibrated remaining capacity of the sample retired battery.

[0009] In a possible implementation, performing parameter identification circuit fitting according to the sample impedance characteristic spectrum to obtain circuit element parameters includes: Construct an initial equivalent circuit model and determine preliminary component parameters of the initial equivalent circuit model based on particle swarm optimization method; The fitting error is determined according to the sample impedance characteristic spectrum, and the circuit component parameters are obtained by performing least squares parameter identification on the preliminary component parameters.

[0010] In a possible implementation, feature screening is performed on circuit element parameters to obtain a first feature subset, and feature screening is performed on sample impedance characteristic spectrum to obtain a second feature subset, including: Performing correlation analysis on circuit element parameters and preset calibrated residual capacity to obtain a first feature subset; A second feature subset is obtained by performing a correlation analysis between the sample impedance characteristic spectrum and the preset calibrated remaining capacity.

[0011] In a possible implementation, the initial battery remaining capacity prediction model is iteratively optimized according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, including: Construct an initial battery remaining capacity prediction model based on the Gaussian process regression model; The comprehensive feature parameter set is input into the initial battery remaining capacity prediction model, and the fitting error of the initial battery remaining capacity prediction model is determined based on the root mean square error method. According to the fitting error, the initial battery remaining capacity prediction model is iteratively optimized by the particle swarm algorithm to obtain a fully trained battery remaining capacity prediction model.

[0012] In a possible implementation, the remaining capacity evaluation result is obtained by quickly estimating the capacity of the retired battery to be detected according to the battery remaining capacity prediction model, including: Collect the impedance characteristic spectrum of the retired battery to be detected, and perform parameter identification circuit fitting according to the impedance characteristic spectrum to be detected to obtain the parameters of the circuit components to be detected; The battery characteristic parameters of the retired battery to be detected are constructed according to the impedance characteristic spectrum to be detected and the circuit component parameters to be detected. The battery characteristic parameters are input into a well-trained battery remaining capacity prediction model to output the remaining capacity evaluation result.

[0013] On the other hand, the present invention also provides a device for quickly estimating the remaining capacity of a retired battery, comprising: A data acquisition unit, used to acquire a sample impedance characteristic spectrum of a sample retired battery, and perform parameter identification circuit fitting according to the sample impedance characteristic spectrum to obtain circuit element parameters; A feature screening unit, used to perform feature screening on circuit element parameters to obtain a first feature subset, perform feature screening on sample impedance characteristic spectrum to obtain a second feature subset, and combine the first feature subset and the second feature subset to obtain a comprehensive feature parameter set; The model building unit is used to iteratively optimize the initial battery remaining capacity prediction model according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, and quickly estimate the capacity of the retired battery to be detected according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result.

[0014] On the other hand, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned method for quickly estimating the remaining capacity of a retired battery is implemented.

[0015] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned method for quickly estimating the remaining capacity of a retired battery is implemented.

[0016] The beneficial effects of the present invention are as follows: in the method for rapidly estimating the remaining capacity of retired batteries provided by the present invention, firstly, a sample impedance characteristic spectrum of a sample retired battery is obtained, and a parameter identification circuit fitting is performed according to the sample impedance characteristic spectrum to obtain circuit element parameters; then, the circuit element parameters are feature screened to obtain a first feature subset, and the sample impedance characteristic spectrum is feature screened to obtain a second feature subset, and the first feature subset and the second feature subset are merged to obtain a comprehensive feature parameter set; finally, the initial battery remaining capacity prediction model is iteratively optimized according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, and the capacity of the retired battery to be detected is rapidly estimated according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result. The present invention estimates the remaining capacity of the battery through the impedance characteristic spectrum of the retired battery, and the battery impedance measurement speed is relatively fast, which effectively improves the efficiency of the battery capacity estimation, and at the same time, only a certain degree of charging is required, avoiding the waste of resources in the discharge process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for rapidly estimating the remaining capacity of a retired battery provided by the present invention; Figure 2 A schematic diagram of a parameter identification circuit fitting process according to an embodiment of the present invention; Figure 3 is a schematic diagram of an equivalent circuit model of an embodiment of the present invention; Figure 4 A schematic diagram of a feature screening process according to an embodiment of the present invention; Figure 5 A schematic diagram of a process of iteratively optimizing an initial battery remaining capacity prediction model according to an embodiment of the present invention; Figure 6 A schematic diagram of a process for quickly estimating the capacity of a retired battery to be detected according to an embodiment of the present invention; Figure 7 A schematic diagram of the structure of an embodiment of a device for rapidly estimating the remaining capacity of a retired battery provided by the present invention; Figure 8 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0021] The descriptions of "first" and "second" in the embodiments of the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0022] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] The present invention provides a method, device, electronic device and medium for quickly estimating the remaining capacity of a retired battery, which are described below respectively.

[0024] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for rapidly estimating the remaining capacity of a retired battery provided by the present invention is shown in FIG. Figure 1 As shown, the method for quickly estimating the remaining capacity of retired batteries includes: S101, obtaining a sample impedance characteristic spectrum of a sample retired battery, and performing parameter identification circuit fitting according to the sample impedance characteristic spectrum to obtain circuit element parameters; S102, feature screening the circuit element parameters to obtain a first feature subset, feature screening the sample impedance characteristic spectrum to obtain a second feature subset, and combining the first feature subset and the second feature subset to obtain a comprehensive feature parameter set; S103, iteratively optimizing the initial battery remaining capacity prediction model according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, and quickly estimating the capacity of the retired battery to be detected according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result.

[0025] Compared with the prior art, in the method for rapidly estimating the remaining capacity of retired batteries provided by the embodiment of the present invention, firstly, a sample impedance characteristic spectrum of a sample retired battery is obtained, and a parameter identification circuit fitting is performed according to the sample impedance characteristic spectrum to obtain circuit element parameters; then, the circuit element parameters are feature screened to obtain a first feature subset, and the sample impedance characteristic spectrum is feature screened to obtain a second feature subset, and the first feature subset and the second feature subset are merged to obtain a comprehensive feature parameter set; finally, the initial battery remaining capacity prediction model is iteratively optimized according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, and the capacity of the retired battery to be detected is rapidly estimated according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result. The present invention estimates the remaining capacity of the battery through the impedance characteristic spectrum of the retired battery, and the battery impedance measurement speed is relatively fast, which effectively improves the efficiency of the battery capacity estimation, and at the same time, only a certain degree of charging is required, avoiding the waste of resources in the discharge process.

[0026] In some embodiments of the present invention, the test environment of the sample retired battery and the retired battery to be tested is consistent, and the test charge state is fully charged.

[0027] Specifically, to ensure the validity of the collected sample data, the sample retired battery and the retired battery to be tested in the embodiment are batteries of the same model. During the impedance test of the sample retired battery and the retired battery to be tested, the test environment is kept consistent, and an ambient temperature of 25°C is used in the embodiment. During the test, the sample retired battery and the retired battery to be tested are charged to a fully charged state, that is, a 100% charged state. The selected charging method is a standard charging method, such as the charging method specified in the GB / T31486-2015 standard. When testing the electrochemical impedance characteristic spectrum curve of the lithium battery, the battery needs to be left to stand for a period of time in advance. In the embodiment, the time can be set to 15 minutes or more.

[0028] In some embodiments of the present invention, obtaining a sample impedance characteristic spectrum of a sample retired battery includes: After applying an AC excitation signal to the sample retired battery, current and voltage sampling is performed to obtain current sampling data and voltage sampling data, and a sample impedance characteristic spectrum is constructed according to the current sampling data, voltage sampling data and the preset calibrated remaining capacity of the sample retired battery.

[0029] Specifically, the sample impedance characteristic spectrum data of the sample retired battery in the embodiment includes the real part, imaginary part, modulus and phase angle of the impedance of the battery at any test frequency. The test equipment of the impedance characteristic spectrum can be an electrochemical workstation, or it can be other electrochemical impedance characteristic spectrum test circuits made based on single-chip microcomputers or sensors. By excitation of AC sine wave current or AC sine wave voltage at a preset frequency, the current and voltage of the battery are sampled at the same time, and the electrochemical impedance of the battery is obtained according to the current sampling data and the voltage sampling data, so as to construct the sample impedance characteristic spectrum. Among them, the sample impedance characteristic spectrum constructed in the embodiment can be a Nyquist diagram or a Bode diagram.

[0030] In an embodiment, the scanning frequency of the battery is set to 0.01 Hz to 1000 Hz, and the scanning mode can be selected as logarithmic scanning or linear scanning. For example, the logarithmic scanning can be selected as 10 points per decade between 0.01 Hz and 1000 Hz, and the linear scanning can be selected as 60 points at equal intervals between 0.01 Hz and 1000 Hz.

[0031] In some embodiments of the present invention, Figure 2 FIG. 1 is a flow chart of parameter identification circuit fitting according to an embodiment of the present invention. Figure 2 As shown, the circuit element parameters are obtained by performing parameter identification circuit fitting based on the sample impedance characteristic spectrum, including: S201, constructing an initial equivalent circuit model, and determining preliminary component parameters of the initial equivalent circuit model based on a particle swarm optimization method; S202 , determining a fitting error according to the sample impedance characteristic spectrum, and performing least squares parameter identification on preliminary component parameters to obtain circuit component parameters.

[0032] Specifically, the measured electrochemical impedance is not directly used as the input of the model in the embodiment. In order to improve the accuracy of capacity estimation, considering that the analog circuit model parameters of the lithium battery can reflect the electrochemical characteristics and aging status of the battery, the embodiment constructs an equivalent circuit model by performing circuit fitting on the battery, and parameterizes the circuit element parameters in the equivalent circuit model.

[0033] In the embodiment, the fitting of the equivalent circuit of the retired lithium battery is performed using Simpwin software. In other embodiments, MATLAB programming software or other programming languages ​​can also be used. The established model can be integer order or fractional order. The integer order can be a first-order RC circuit, a second-order RC circuit, etc. In this embodiment, Figure 3 is a schematic diagram of an equivalent circuit model of an embodiment of the present invention, combined with Figure 3 From the perspective of the embodiment, the Figure 3The second-order fractional model is fitted, and the circuit element parameters fitted include ohmic resistance, charge transfer structure diffusion coefficient, charge transfer impedance, solid electrolyte interface impedance, solid electrolyte interface diffusion coefficient and equivalent capacitance in Weber impedance.

[0034] In the embodiment, considering that the offline parameter identification algorithm such as the nonlinear least square method is too dependent on the initial value, in the parameter identification process, the embodiment first uses the particle swarm optimization algorithm for preliminary fitting, and the objective function is the fitting error, that is, the cumulative square error sum of the measured sample impedance characteristic spectrum and the fitting value, and the convergence condition is that the cumulative square error sum is less than 0.001. Then, the final convergence result of the particle swarm optimization algorithm, that is, the preliminary component parameters, is used as the initial value of the nonlinear least square method, and the parameter identification is performed again to improve the circuit component parameter identification accuracy of the equivalent circuit model.

[0035] It should be noted that, in some other embodiments, the initial parameter identification algorithm may also be a genetic algorithm, a differential evolution algorithm, or a simulated annealing algorithm. The optimization results of these intelligent optimization algorithms are used as the initial values ​​of the nonlinear least squares method. The model convergence condition may also be the number of iterations or other convergence criteria that characterize the fitting error.

[0036] In some embodiments of the present invention, Figure 4 FIG. 1 is a flow chart of feature screening according to an embodiment of the present invention. Figure 4 As shown, the circuit element parameters are characteristically screened to obtain a first characteristic subset, and the sample impedance characteristic spectrum is characteristically screened to obtain a second characteristic subset, including: S401, performing correlation analysis on circuit element parameters and preset calibrated remaining capacity to obtain a first feature subset; S402: Perform correlation analysis on the sample impedance characteristic spectrum and the preset calibrated remaining capacity to obtain a second characteristic subset.

[0037] Specifically, considering that not every parameter in the circuit element parameters and the sample impedance characteristic spectrum has a high correlation with the battery remaining capacity of the type of battery evaluated in the embodiment, the embodiment also performs correlation analysis on the circuit element parameters and the sample impedance characteristic spectrum with the preset calibrated remaining capacity, removes some data with low correlation, and effectively reduces the model complexity and model training time through feature screening.

[0038] In the embodiment, the correlation analysis method adopts Pearson correlation analysis, and the formula is expressed as:

[0039] in, represents the correlation coefficient, and represents the parameters for correlation analysis, and Indicates the corresponding average value.

[0040] The embodiment performs correlation analysis on the parameters of circuit elements such as ohmic resistance, diffusion coefficient of charge transfer structure, charge transfer resistance, solid electrolyte interface resistance, solid electrolyte interface diffusion coefficient and equivalent capacitance in Weber impedance and the preset calibrated remaining capacity of the sample retired battery, and selects some parameters with the strongest correlation (correlation coefficient The first feature subset is constructed by performing correlation analysis on the real part, imaginary part, modulus, phase angle of the impedance characteristic spectrum of the sample and the preset calibrated remaining capacity of the retired battery of the sample, and selecting some parameters with the strongest correlation (correlation coefficient is greater than 0.8), construct the second feature subset. Finally, merge the first feature subset and the second feature subset to form a comprehensive feature parameter set.

[0041] In some embodiments of the present invention, Figure 5 FIG. 1 is a flow chart of iteratively optimizing the initial battery remaining capacity prediction model according to an embodiment of the present invention. Figure 5 As shown, the initial battery remaining capacity prediction model is iteratively optimized according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, including: S501, constructing an initial battery remaining capacity prediction model based on a Gaussian process regression model; S502, inputting the comprehensive characteristic parameter set into the initial battery remaining capacity prediction model, determining the fitting error of the initial battery remaining capacity prediction model based on the root mean square error method, and performing particle swarm algorithm iterative optimization on the initial battery remaining capacity prediction model according to the fitting error to obtain a fully trained battery remaining capacity prediction model.

[0042] Specifically, in this embodiment, an optimized Gaussian process regression model is used to establish an initial battery remaining capacity prediction model, with a comprehensive feature parameter set screened by correlation analysis as the model input, and the calibrated actual capacity of the battery as the model output. In the embodiment, particle swarm optimization Gaussian process regression is selected, and the optimization target of its regression function is the fitting error, and the root mean square error is selected. The square exponential covariance is selected as the kernel function, and the distance between the input variables is used to characterize the correlation. The square exponential covariance function formula is expressed as:

[0043] in, represents the hyperparameter signal variance, represents the length scale, Represents the input parameter. The embodiment uses particle swarm optimization algorithm to optimize the hyperparameter variance and length scale Perform global optimization to improve the accuracy and reliability of the Gaussian regression algorithm.

[0044] It should be noted that, in some other embodiments, the upper layer optimization algorithm may be at least one of the gray wolf algorithm, the whale algorithm, the genetic algorithm or the particle swarm algorithm, and the lower layer multivariate prediction regression model may be at least one of the support vector regression model, the Gaussian process regression model or the random forest model. The optimized multivariate prediction regression model may be a combination of the above-mentioned upper layer algorithms and the lower layer algorithms. What is optimized in the upper layer model is the hyperparameter of the lower layer multivariate regression prediction algorithm.

[0045] In some embodiments of the present invention, Figure 6 FIG. 1 is a flow chart of a method for quickly estimating the capacity of a retired battery to be detected according to an embodiment of the present invention. Figure 6 As shown in the figure, the remaining capacity evaluation result is obtained by quickly estimating the capacity of the retired battery to be detected according to the battery remaining capacity prediction model, including: S601, collecting the impedance characteristic spectrum to be detected of the retired battery to be detected, and performing parameter identification circuit fitting according to the impedance characteristic spectrum to be detected to obtain the parameters of the circuit components to be detected; S602, constructing battery characteristic parameters of the retired battery to be detected according to the impedance characteristic spectrum to be detected and the circuit element parameters to be detected, inputting the battery characteristic parameters into a well-trained battery remaining capacity prediction model, and outputting a remaining capacity evaluation result.

[0046] Specifically, in the embodiment, during the process of rapid capacity estimation of retired batteries to be detected, the battery impedance data of the same type of retired batteries to be detected at 100% SOC at 25°C are collected under the same test environment, and the characteristic impedance spectrum to be detected is extracted according to the same steps, and then the parameters of the circuit components to be detected are determined, and the battery characteristic parameters of the retired batteries to be detected are determined according to the parameter types selected by correlation analysis, and then the remaining battery capacity is estimated through the battery remaining capacity prediction model. Thus, rapid capacity estimation of large-scale and multi-batch retired lithium batteries is achieved.

[0047] In summary, the present invention first obtains the sample impedance characteristic spectrum of the sample retired battery, performs parameter identification circuit fitting based on the sample impedance characteristic spectrum to obtain circuit element parameters; then performs feature screening on the circuit element parameters to obtain a first feature subset, performs feature screening on the sample impedance characteristic spectrum to obtain a second feature subset, and combines the first feature subset and the second feature subset to obtain a comprehensive feature parameter set; finally, iteratively optimizes the initial battery remaining capacity prediction model based on the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, and performs a rapid capacity estimation on the retired battery to be detected based on the battery remaining capacity prediction model to obtain a remaining capacity evaluation result. The present invention estimates the remaining capacity of the battery through the impedance characteristic spectrum of the retired battery, and the battery impedance measurement speed is relatively fast, which effectively improves the efficiency of battery capacity estimation, and at the same time only requires a certain degree of charging, avoiding resource waste in the discharge process.

[0048] In order to better implement the method for quickly estimating the remaining capacity of a retired battery in an embodiment of the present invention, based on the method for quickly estimating the remaining capacity of a retired battery, correspondingly, Figure 7 As shown, the present invention also provides a device for quickly estimating the remaining capacity of a retired battery. The device 700 for quickly estimating the remaining capacity of a retired battery includes: The data acquisition unit 701 is used to acquire a sample impedance characteristic spectrum of a sample retired battery, and perform parameter identification circuit fitting according to the sample impedance characteristic spectrum to obtain circuit element parameters; A feature screening unit 702 is used to perform feature screening on circuit element parameters to obtain a first feature subset, perform feature screening on sample impedance characteristic spectrum to obtain a second feature subset, and combine the first feature subset and the second feature subset to obtain a comprehensive feature parameter set; The model building unit 703 is used to iteratively optimize the initial battery remaining capacity prediction model according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, and quickly estimate the capacity of the retired battery to be detected according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result.

[0049] The device 700 for quickly estimating the remaining capacity of retired batteries provided in the above embodiment can implement the technical solution described in the above embodiment of the method for quickly estimating the remaining capacity of retired batteries. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above embodiment of the method for quickly estimating the remaining capacity of retired batteries, which will not be repeated here.

[0050] like Figure 8 As shown, the present invention also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802 and a display 803. Figure 8 Only some components of the electronic device 800 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0051] In some embodiments, the processor 801 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 802, such as the method for quickly estimating the remaining capacity of retired batteries in the present invention.

[0052] In some embodiments, the processor 801 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 801 may be local or remote. In some embodiments, the processor 801 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0053] In some embodiments, the memory 802 may be an internal storage unit of the electronic device 800, such as a hard disk or memory of the electronic device 800. In other embodiments, the memory 802 may also be an external storage device of the electronic device 800, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 800.

[0054] Furthermore, the memory 802 may include both an internal storage unit of the electronic device 800 and an external storage device. The memory 802 is used to store application software installed in the electronic device 800 and various data.

[0055] In some embodiments, the display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 803 is used to display information of the electronic device 800 and to display a visual user interface. The components 801-803 of the electronic device 800 communicate with each other via a system bus.

[0056] In one embodiment, when the processor 801 executes the retired battery remaining capacity fast estimation program in the memory 802, the following steps may be implemented: Obtain a sample impedance characteristic spectrum of a sample retired battery, and perform parameter identification circuit fitting based on the sample impedance characteristic spectrum to obtain circuit element parameters; Performing feature screening on circuit element parameters to obtain a first feature subset, performing feature screening on sample impedance characteristic spectrum to obtain a second feature subset, and combining the first feature subset and the second feature subset to obtain a comprehensive feature parameter set; The initial battery remaining capacity prediction model is iteratively optimized according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, and the capacity of the retired battery to be detected is quickly estimated according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result.

[0057] It should be understood that: when the processor 801 executes the retired battery remaining capacity rapid estimation program in the memory 802, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0058] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions of the method for quickly estimating the remaining capacity of retired batteries provided in the above-mentioned method embodiments can be implemented.

[0059] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0060] The above is a detailed introduction to the method, device, electronic device and storage medium for quickly estimating the remaining capacity of retired batteries provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for quickly estimating the remaining capacity of retired batteries, characterized in that: include: Obtaining a sample impedance characteristic spectrum of a sample retired battery, and performing parameter identification circuit fitting according to the sample impedance characteristic spectrum to obtain circuit element parameters; Performing feature screening on the circuit element parameters to obtain a first feature subset, performing feature screening on the sample impedance characteristic spectrum to obtain a second feature subset, and combining the first feature subset and the second feature subset to obtain a comprehensive feature parameter set; The initial battery remaining capacity prediction model is iteratively optimized according to the comprehensive characteristic parameter set to obtain a fully trained battery remaining capacity prediction model, and the capacity of the retired battery to be detected is quickly estimated according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result.

2. The method for rapidly estimating the remaining capacity of retired batteries according to claim 1, characterized in that: The test environment of the sample retired battery is consistent with that of the retired battery to be tested, and the test charge states are both fully charged.

3. The method for rapidly estimating the remaining capacity of retired batteries according to claim 1, characterized in that: The step of obtaining a sample impedance characteristic spectrum of a sample retired battery includes: After applying an AC excitation signal to the sample retired battery, current and voltage sampling is performed to obtain current sampling data and voltage sampling data, and a sample impedance characteristic spectrum is constructed according to the current sampling data, the voltage sampling data and the preset calibrated remaining capacity of the sample retired battery.

4. The method for rapidly estimating the remaining capacity of retired batteries according to claim 1, characterized in that: The method of performing parameter identification circuit fitting according to the sample impedance characteristic spectrum to obtain circuit element parameters includes: Constructing an initial equivalent circuit model, and determining preliminary component parameters of the initial equivalent circuit model based on a particle swarm optimization method; The fitting error is determined according to the sample impedance characteristic spectrum, and the circuit component parameters are obtained by performing least squares parameter identification on the preliminary component parameters.

5. The method for rapidly estimating the remaining capacity of retired batteries according to claim 3, characterized in that: The method of performing feature screening on the circuit element parameters to obtain a first feature subset and performing feature screening on the sample impedance characteristic spectrum to obtain a second feature subset includes: Performing a correlation analysis on the circuit element parameters and the preset calibrated residual capacity to obtain a first feature subset; A second feature subset is obtained by performing a correlation analysis on the sample impedance characteristic spectrum and the preset calibrated residual capacity.

6. The method for rapidly estimating the remaining capacity of retired batteries according to claim 1, characterized in that: The iterative optimization of the initial battery remaining capacity prediction model according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model includes: Construct an initial battery remaining capacity prediction model based on the Gaussian process regression model; The comprehensive characteristic parameter set is input into the initial battery remaining capacity prediction model, the fitting error of the initial battery remaining capacity prediction model is determined based on the root mean square error method, and the initial battery remaining capacity prediction model is iteratively optimized by the particle swarm algorithm according to the fitting error to obtain a fully trained battery remaining capacity prediction model.

7. The method for rapidly estimating the remaining capacity of retired batteries according to claim 1, characterized in that: The method of quickly estimating the capacity of the retired battery to be detected according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result includes: Collecting the impedance characteristic spectrum to be detected of the retired battery to be detected, and performing parameter identification circuit fitting according to the impedance characteristic spectrum to be detected to obtain the parameters of the circuit element to be detected; The battery characteristic parameters of the retired battery to be detected are constructed according to the impedance characteristic spectrum to be detected and the circuit element parameters to be detected, and the battery characteristic parameters are input into a well-trained battery remaining capacity prediction model to output a remaining capacity evaluation result.

8. A device for quickly estimating the remaining capacity of a retired battery, characterized in that: include: A data acquisition unit, used to acquire a sample impedance characteristic spectrum of a sample retired battery, and perform parameter identification circuit fitting according to the sample impedance characteristic spectrum to obtain circuit element parameters; A feature screening unit, configured to perform feature screening on the circuit element parameters to obtain a first feature subset, perform feature screening on the sample impedance characteristic spectrum to obtain a second feature subset, and combine the first feature subset and the second feature subset to obtain a comprehensive feature parameter set; The model building unit is used to iteratively optimize the initial battery remaining capacity prediction model according to the comprehensive feature parameter set to obtain a fully trained battery remaining capacity prediction model, and to quickly estimate the capacity of the retired battery to be detected according to the battery remaining capacity prediction model to obtain a remaining capacity evaluation result.

9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for quickly estimating the remaining capacity of a retired battery according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for quickly estimating the remaining capacity of a retired battery according to any one of claims 1 to 7 is implemented.

Images