CN119846484A - Battery capacity prediction method, device, computer equipment and storage medium - Google Patents
Battery capacity prediction method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN119846484A CN119846484A CN202510346954.6A CN202510346954A CN119846484A CN 119846484 A CN119846484 A CN 119846484A CN 202510346954 A CN202510346954 A CN 202510346954A CN 119846484 A CN119846484 A CN 119846484A
- Authority
- CN
- China
- Prior art keywords
- capacity
- curve
- battery
- fitting
- tested
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Secondary Cells (AREA)
Abstract
本申请涉及一种电池容量预测方法、装置、计算机设备和存储介质。所述方法包括：针对预设的每一个拟合模型，利用待测电池在多次充放电循环下的容量数据对待测电池的容量衰减曲线进行拟合，生成待测电池在各拟合模型下的容量衰减曲线；各容量衰减曲线包括基于容量数据拟合得到的拟合曲线和基于容量数据预测得到的预测曲线；根据各容量衰减曲线中预测曲线的特征信息，确定待测电池的候选容量衰减曲线；根据候选容量衰减曲线对应的拟合模型的决定系数，确定待测电池的目标容量衰减曲线。提高了拟合模型与待测电池的匹配度和目标容量衰减曲线的准确度。
The present application relates to a battery capacity prediction method, device, computer equipment and storage medium. The method comprises: for each preset fitting model, the capacity data of the battery to be tested under multiple charge and discharge cycles are used to fit the capacity decay curve of the battery to be tested, and the capacity decay curve of the battery to be tested under each fitting model is generated; each capacity decay curve includes a fitting curve obtained by fitting based on the capacity data and a prediction curve obtained by predicting the capacity data; according to the characteristic information of the prediction curve in each capacity decay curve, the candidate capacity decay curve of the battery to be tested is determined; according to the determination coefficient of the fitting model corresponding to the candidate capacity decay curve, the target capacity decay curve of the battery to be tested is determined. The matching degree between the fitting model and the battery to be tested and the accuracy of the target capacity decay curve are improved.
Description
Technical Field
The present application relates to the field of lithium ion battery technologies, and in particular, to a battery capacity prediction method, a device, a computer device, and a storage medium.
Background
The lithium ion battery has the characteristics of high energy density, long cycle life and environmental friendliness, and is widely applied to the fields of portable electronic equipment, electric vehicles, energy storage systems and the like, but as the service time of the lithium ion battery increases, the capacity of the lithium ion battery gradually decays, so that the battery is stopped being used. Therefore, predicting the capacity fade curve of a lithium ion battery is of great significance in evaluating battery performance, guiding battery design, optimizing battery management, finding potential problems, and reducing development costs and time.
In the conventional technology, the capacity fading curves of the lithium ion batteries of different types are predicted by adopting the same fitting method. However, the conventional technology has a problem in that the accuracy of predicting the capacity fade curve of the battery is low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a battery capacity prediction method, apparatus, computer device, and storage medium that can improve the accuracy of capacity fade curve prediction of a battery.
In a first aspect, the present application provides a battery capacity prediction method, including:
For each preset fitting model, fitting a capacity attenuation curve of the battery to be tested by utilizing capacity data of the battery to be tested under multiple charge and discharge cycles to generate a capacity attenuation curve of the battery to be tested under each fitting model;
According to the characteristic information of the prediction curve in each capacity attenuation curve, determining a candidate capacity attenuation curve of the battery to be tested;
and determining a target capacity attenuation curve of the battery to be tested according to the decision coefficient of the fitting model corresponding to the candidate capacity attenuation curve.
In one embodiment, the characteristic information includes an end point value of a predicted curve, and the determining the candidate capacity fading curve of the battery to be measured according to the characteristic information of the predicted curve in each capacity fading curve includes:
Determining a capacity fading curve with the end point value of the prediction curve being larger than a preset threshold value as an alternative capacity fading curve;
the candidate capacity fade curve is determined from the candidate capacity fade curves.
In one embodiment, the characteristic information further includes a slope of a predicted curve, and the determining the candidate capacity-fading curve from the candidate capacity-fading curves includes:
And determining an alternative capacity fading curve with the slope of the prediction curve smaller than a preset slope threshold as the candidate capacity fading curve.
In one embodiment, the determining the target capacity fading curve of the battery to be measured according to the decision coefficient of the fitting model corresponding to the candidate capacity fading curve includes:
sorting the decision coefficients of the fitting model corresponding to the candidate capacity fading curve;
And determining a candidate capacity fading curve corresponding to the fitting model with the maximum determining coefficient as the target capacity fading curve.
In one embodiment, the method further comprises:
For each preset fitting model, in the process of fitting a capacity attenuation curve of a battery to be measured by utilizing capacity data of the battery to be measured under multiple charge and discharge cycles, acquiring a total square sum and a residual square sum of each fitting model, wherein the total square sum is determined according to an average value of the capacity data and the capacity data under each charge and discharge cycle, and the residual square sum is determined according to an average value of the capacity data and a predicted value corresponding to each charge and discharge cycle in the fitting curve;
and determining the decision coefficient of each fitting model according to the total square sum and the residual square sum of each fitting model.
In one embodiment, for each preset fitting model, fitting a capacity attenuation curve of a battery to be measured by using capacity data of the battery to be measured under multiple charge and discharge cycles, to generate a capacity attenuation curve of the battery to be measured under each fitting model, including:
In the process of fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data aiming at each fitting model, optimizing parameters of the fitting model by adopting an iterative optimization algorithm to obtain an optimized fitting model;
And generating each capacity attenuation curve by using the charge and discharge cycle times of the battery to be tested and each optimized fitting model.
In one embodiment, the method further comprises:
And analyzing the performance data of the battery to be tested according to the target capacity attenuation curve of the battery to be tested.
In a second aspect, the present application also provides a battery capacity prediction apparatus, including:
the generating module is used for fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data of the battery to be tested under multiple charge and discharge cycles aiming at each preset fitting model to generate the capacity attenuation curve of the battery to be tested under each fitting model;
The first determining module is used for determining candidate capacity fading curves of the battery to be tested according to the characteristic information of the prediction curves in the capacity fading curves;
And the second determining module is used for determining the target capacity attenuation curve of the battery to be tested according to the decision coefficient of the fitting model corresponding to the candidate capacity attenuation curve.
In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
For each preset fitting model, fitting a capacity attenuation curve of the battery to be tested by utilizing capacity data of the battery to be tested under multiple charge and discharge cycles to generate a capacity attenuation curve of the battery to be tested under each fitting model;
According to the characteristic information of the prediction curve in each capacity attenuation curve, determining a candidate capacity attenuation curve of the battery to be tested;
and determining a target capacity attenuation curve of the battery to be tested according to the decision coefficient of the fitting model corresponding to the candidate capacity attenuation curve.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
For each preset fitting model, fitting a capacity attenuation curve of the battery to be tested by utilizing capacity data of the battery to be tested under multiple charge and discharge cycles to generate a capacity attenuation curve of the battery to be tested under each fitting model;
According to the characteristic information of the prediction curve in each capacity attenuation curve, determining a candidate capacity attenuation curve of the battery to be tested;
and determining a target capacity attenuation curve of the battery to be tested according to the decision coefficient of the fitting model corresponding to the candidate capacity attenuation curve.
In a fifth aspect, the application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:
For each preset fitting model, fitting a capacity attenuation curve of the battery to be tested by utilizing capacity data of the battery to be tested under multiple charge and discharge cycles to generate a capacity attenuation curve of the battery to be tested under each fitting model;
According to the characteristic information of the prediction curve in each capacity attenuation curve, determining a candidate capacity attenuation curve of the battery to be tested;
and determining a target capacity attenuation curve of the battery to be tested according to the decision coefficient of the fitting model corresponding to the candidate capacity attenuation curve.
The battery capacity prediction method, the device, the computer equipment and the storage medium are used for fitting capacity attenuation curves of the battery to be measured by utilizing capacity data of the battery to be measured under multiple charge and discharge cycles according to each preset fitting model to generate capacity attenuation curves of the battery to be measured under each fitting model, wherein each capacity attenuation curve comprises a fitting curve obtained by fitting based on the capacity data and a prediction curve obtained by predicting based on the capacity data, candidate capacity attenuation curves of the battery to be measured are determined according to characteristic information of the prediction curves in each capacity attenuation curve, and target capacity attenuation curves of the battery to be measured are determined according to decision coefficients of the fitting models corresponding to the candidate capacity attenuation curves. And screening the capacity attenuation curve corresponding to each fitting model twice according to the characteristic information of the prediction curve in the capacity attenuation curve and the decision coefficient of each fitting model, determining the fitting model with the highest accuracy of capacity prediction of the battery to be detected, and improving the matching degree of the fitting model and the battery to be detected and the accuracy of the target capacity attenuation curve.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are needed in the description of the embodiments of the present application or the related technologies will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other related drawings may be obtained according to these drawings without inventive effort to those of ordinary skill in the art.
FIG. 1 is an application environment diagram of a battery capacity prediction method in one embodiment;
FIG. 2 is a flow chart of a method of battery capacity prediction in one embodiment;
FIG. 3 is a flowchart of another embodiment of a method for predicting battery capacity;
FIG. 4 is a second flowchart of a battery capacity prediction method according to another embodiment;
FIG. 5 is a third flow chart of a battery capacity prediction method according to another embodiment;
FIG. 6 is a flowchart of a battery capacity prediction method according to another embodiment;
FIG. 7 is a schematic diagram of all capacity fade curves for battery 1 in one embodiment;
FIG. 8 is a schematic diagram of a target capacity fade curve for battery 1 in one embodiment;
FIG. 9 is a schematic diagram of all capacity fade curves for battery 2 in one embodiment;
FIG. 10 is a schematic diagram of a target capacity fade curve for battery 2 in one embodiment;
FIG. 11 is a schematic diagram of all capacity fade curves for battery 3 in one embodiment;
FIG. 12 is a schematic diagram of a target capacity fade curve for battery 3 in one embodiment;
FIG. 13 is a flowchart of a battery capacity prediction method according to another embodiment;
FIG. 14 is a flowchart of a battery capacity prediction method according to another embodiment;
fig. 15 is a block diagram showing the structure of a battery capacity prediction apparatus in one embodiment;
Fig. 16 is an internal structural view of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The battery capacity prediction method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the data acquisition device 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The server 104 may obtain the capacity data of the battery to be measured under the multiple charge and discharge cycles from the data acquisition device 102, so as to determine a capacity attenuation curve of the battery to be measured by using the capacity data of the battery to be measured under the multiple charge and discharge cycles and the fitting model. The server 104 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud computing services.
In one embodiment, as shown in fig. 2, a battery capacity prediction method is provided, and the method is applied to the server in fig. 1 for illustration, and includes:
S201, fitting capacity attenuation curves of the battery to be tested by utilizing capacity data of the battery to be tested under multiple charge and discharge cycles according to each preset fitting model to generate capacity attenuation curves of the battery to be tested under each fitting model, wherein each capacity attenuation curve comprises a fitting curve obtained by fitting based on the capacity data and a prediction curve obtained by predicting based on the capacity data.
The fitting model in this embodiment may be at least one of a double-exponential fitting model, a linear-exponential mixing model, a linear fitting model, a single-exponential fitting model, and a polynomial fitting model. The capacity data may be a pair of data composed of the number of cycles and the battery capacity corresponding to the number of cycles, and for example, the number of cycles may be expressed as x and the battery capacity as y, and the capacity data is (x, y) for each cycle.
The polynomial fitting model may be expressed asThe method comprises the steps that a 0、a1、...、an is a model parameter to be determined, a polynomial fitting model is used for capturing complex nonlinear trend and multi-inflection point characteristics in data, and an optimization process can be efficiently completed in a control search range by setting initial coefficients and parameter constraints for polynomial fitting, so that a fitting result with higher flexibility and accuracy is obtained;
Optionally, a data acquisition request may be sent to the data acquisition device, so that capacity data of the battery to be measured under multiple charge and discharge cycles is acquired according to data returned by the data acquisition device, and for example, operations such as data cleaning processing and standardization processing may be performed on the data returned by the data acquisition device, and the processed data is determined to be the capacity data of the battery to be measured under multiple charge and discharge cycles.
In the embodiment of the application, for each preset fitting model, firstly, fitting model parameters of the fitting model corresponding to the battery to be tested and fitting curves of the battery capacity of the battery to be tested under multiple charge and discharge cycles according to capacity data of the battery to be tested under multiple charge and discharge cycles, and substituting the model parameters into an initial fitting model to obtain the fitting model corresponding to the battery to be tested, so that the fitting model is utilized to predict the capacity attenuation curve of the battery to obtain a prediction curve corresponding to the cycle times after the multiple charge and discharge cycles, and further, obtaining the capacity attenuation curve comprising the fitting curve and the prediction curve. Alternatively, the number of end-point cycles of the prediction curve may be set, so that the prediction curve is generated according to the fitting model and the number of end-point cycles.
For example, the double-exponential fit model may be expressed asWherein A, B, C is a model parameter to be determined, the double-exponential fit model is suitable for a data scene which represents double-exponential dynamics, such as a complex multi-stage attenuation or growth process, the effectiveness and accuracy of the fit algorithm can be significantly improved by presetting initial parameters and parameter boundaries for the model, and the linear-exponential mixture model can be expressed asWherein A, B, C, D is a model parameter to be determined, the linear-exponential mixture model can simultaneously embody the characteristics of linear and exponential changes, is suitable for being applied to the situation that data has linear trend and has rapid change of the exponential, can quickly converge and obtain stable parameter solution by reasonably setting initial parameters and boundary conditions, and can be expressed as a linear fitting modelWherein A, B is a model parameter to be determined, the linear fitting model is suitable for a scene in which the whole data presents an approximate linear relationship, a reasonable initial value and a strict boundary range can be specified for the parameter, the optimization process is ensured to be completed efficiently in a reasonable parameter domain, and unreasonable local extremum is avoided, and the single-index fitting model can be expressed asThe A, B, C is a model parameter to be determined, the single-index fitting model has higher applicability to data showing single-index trend, and the model can be ensured to quickly converge and obtain a high-precision fitting result by setting proper initial parameters and upper and lower boundaries of the parameters.
S202, determining a candidate capacity fading curve of the battery to be tested according to the characteristic information of the prediction curve in each capacity fading curve.
The characteristic information of the prediction curve in the capacity fading curve may include a variation trend of the prediction curve, a predicted capacity range corresponding to the prediction curve, and the like.
In the embodiment of the application, the credibility of each capacity attenuation curve can be determined according to the characteristic information of the prediction curve in each capacity attenuation curve, so that each capacity attenuation curve with the unreliable capacity attenuation curve removed is determined as the candidate capacity attenuation curve of the battery to be tested.
Alternatively, the capacity range threshold may be preset, the capacity fading curve in which the predicted capacity range does not completely belong to the capacity range threshold may be determined as an unreliable capacity fading curve, or the trend of change in the predicted curve may be an increased capacity fading curve and may be determined as an unreliable capacity fading curve.
S203, determining a target capacity attenuation curve of the battery to be tested according to the decision coefficient of the fitting model corresponding to the candidate capacity attenuation curve.
In the embodiment of the application, the decision coefficients of the fitting model corresponding to the candidate capacity fading curve are determined according to the candidate capacity fading curve and the capacity data, so that the target capacity fading curve of the battery to be measured is determined from the candidate capacity fading curve according to the decision coefficients.
Alternatively, the decision coefficient range threshold may be set in advance so that the candidate capacity fade curve for which the decision coefficient is in the decision coefficient range threshold is determined as the target capacity fade curve.
According to the battery capacity prediction method, capacity data of a battery to be detected under multiple charge and discharge cycles are utilized to fit capacity attenuation curves of the battery to be detected according to each preset fit model, capacity attenuation curves of the battery to be detected under each fit model are generated, each capacity attenuation curve comprises a fit curve obtained by fitting the capacity data and a prediction curve obtained by predicting the capacity data, candidate capacity attenuation curves of the battery to be detected are determined according to characteristic information of the prediction curves in each capacity attenuation curve, and target capacity attenuation curves of the battery to be detected are determined according to decision coefficients of the fit models corresponding to the candidate capacity attenuation curves. And screening the capacity attenuation curve corresponding to each fitting model twice according to the characteristic information of the prediction curve in the capacity attenuation curve and the decision coefficient of each fitting model, determining the fitting model with the highest accuracy of capacity prediction of the battery to be detected, and improving the matching degree of the fitting model and the battery to be detected and the accuracy of the target capacity attenuation curve.
In one embodiment, an implementation manner of the foregoing S202 is provided, where the feature information includes an end point value of a prediction curve, as shown in fig. 3, and the foregoing "determining a candidate capacity fade curve of the battery to be measured according to the feature information of the prediction curve in each capacity fade curve" includes:
and S301, determining a capacity attenuation curve with the end point value of the prediction curve being larger than a preset threshold value as an alternative capacity attenuation curve.
In the embodiment of the application, according to the number of terminal cycles of predicting the battery to be detected, the terminal value of the prediction curve is read from each capacity fading curve, further, whether the terminal value of each prediction curve is larger than a preset threshold value is determined, if the terminal value of the prediction curve is larger than the preset threshold value, the capacity fading curve corresponding to the prediction curve is determined to be an alternative capacity fading curve, and if the terminal value of the prediction curve is not larger than the preset threshold value, the capacity fading curve corresponding to the prediction curve is not credible.
Alternatively, since the battery capacity is not necessarily negative, the preset threshold may be 0, and in this embodiment, a capacity fading curve in which the end point value of the predicted curve is greater than 0 may be determined as the candidate capacity fading curve.
S302, determining a candidate capacity attenuation curve from the candidate capacity attenuation curves.
In the embodiment of the application, the candidate capacity fading curve can be determined from the candidate capacity fading curves according to the characteristic information of the prediction curve. For example, a candidate capacity fade curve may be determined from the candidate capacity fade curves based on the trend of the predicted curve.
Optionally, the characteristic information further includes a slope of a predicted curve, and determining a candidate capacity-fading curve from the candidate capacity-fading curves may include determining the candidate capacity-fading curve, in which the slope of the predicted curve is smaller than a preset slope threshold, as the candidate capacity-fading curve.
It should be noted that, since the capacity of the battery decays as the service time increases, the capacity decay curve has a decreasing trend, i.e., the slope of all points in the decay curve should be less than 0. In this embodiment, the slopes of the plurality of points in the prediction curve are determined, and the candidate capacity-fading curve in which the slopes of the plurality of points are all smaller than the preset slope threshold is determined as the candidate capacity-fading curve, for example, the candidate capacity-fading curve in which the slopes of the plurality of points are all smaller than 0 is determined as the candidate capacity-fading curve. Alternatively, the plurality of points may be points corresponding to the number of cycles in the decay curve, or the plurality of points may be points at preset positions.
In the embodiment of the application, the capacity fading curve is screened for the first time according to the characteristic information of the prediction curve, the unreliable capacity fading curve in the capacity fading curve is removed, the candidate capacity fading curve is obtained, the reliability of the candidate capacity fading curve is improved, and the efficiency of determining the target capacity fading curve from the candidate capacity fading curve is improved.
In one embodiment, an implementation manner of S203 is provided, as shown in fig. 4, where "determining the target capacity fading curve of the battery to be measured according to the decision coefficient of the fitting model corresponding to the candidate capacity fading curve" includes:
s401, sorting the decision coefficients of the fitting model corresponding to the candidate capacity fading curve.
In the embodiment of the application, the decision coefficients of the fitting model corresponding to the candidate capacity fading curve are ranked, so that a ranking queue is obtained. For example, if the decision coefficient of the fitting model 1 is 0.2, the decision coefficient of the fitting model 2 is 0.9, and the decision coefficient of the fitting model 3 is 0.3, the ranking queue may be the fitting model 2, the fitting model 3, and the fitting model 1.
S402, determining a candidate capacity fading curve corresponding to the fitting model with the largest determining coefficient as a target capacity fading curve.
It should be noted that the determining coefficient is an index for measuring the goodness of fit of the model, and is used for evaluating the variance interpretation degree of the model to the actual value, wherein the value of R2 is between [0,1], if r2=1, the model can completely interpret all the variances of the target variable, and if r2=0, the model has no interpretation capability.
In the embodiment of the present application, a candidate capacity-fading curve corresponding to a fitting model with the largest determining coefficient is determined as a target capacity-fading curve, for example, if the ranking queue of the candidate capacity-fading curves is a fitting model 2, a fitting model 3, and a fitting model 1, the capacity-fading curve corresponding to the fitting model 2 is determined as the target capacity-fading curve.
In the embodiment of the application, the target capacity attenuation curve is determined from the candidate capacity attenuation curves according to the size of the decision coefficient, so that the accuracy and reliability of the target capacity attenuation curve are improved.
In one embodiment, as shown in fig. 5, the battery capacity prediction method further includes:
S204, for each preset fitting model, in the process of fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data of the battery to be tested under multiple charge and discharge cycles, acquiring the total square sum and residual square sum of each fitting model, wherein the total square sum is determined according to the average value of the capacity data and the capacity data under each charge and discharge cycle, and the residual square sum is determined according to the average value of the capacity data and the prediction value corresponding to each charge and discharge cycle in the fitting curve.
In the embodiment of the present application, for each cycle number, the process of determining the total sum of squares may be shown in equation 1, and the process of determining the residual sum of squares may be shown in equation 2:
(1)
(2)
Wherein SST is total sum of squares, data fluctuation quantity used for representing capacity data, SSR is residual sum of squares,For the average of the battery capacities of all sample batteries at this number of cycles,To fit the fitting value for the number of cycles in the curve,And the capacity value corresponding to the ith battery sample in the capacity data.
S205, determining the determination coefficient of each fitting model according to the total square sum and the residual square sum of each fitting model.
In the embodiment of the present application, the decision coefficient R 2 of each intermediate feature is determined according to the ratio of the sum of squares of the total squares and the sum of squares of the residual errors of the fitting model, and the determination process of the decision coefficient is shown in equation 3:
(3)
In the embodiment of the application, the decision coefficient of each fitting model is determined according to the capacity data and the fitting curve, and the fitting result of the fitting model is compared with the average value of the known data, namely the fitting model is evaluated by the known average value, so that the reliability of judging the accuracy of the fitting model is improved.
In an embodiment, as shown in fig. 6, the "fitting, for each preset fitting model, the capacity attenuation curve of the battery to be measured with the capacity data of the battery to be measured under multiple charge and discharge cycles to generate the capacity attenuation curve of the battery to be measured under each fitting model" in an embodiment, provided in S201 includes:
s501, optimizing parameters of the fitting model by adopting an iterative optimization algorithm in the process of fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data aiming at each fitting model, so as to obtain an optimized fitting model.
In the embodiment of the application, for each fitting model, a nonlinear least square method can be used for carrying out parameter optimization on the fitting model to obtain a fitting curve. Specifically, in the parameter optimization process, an iterative optimization algorithm, such as a gaussian-newton method or a Levenberg-Marquardt algorithm, may be used to gradually modify the initial parameters to obtain an optimal parameter combination based on minimizing an error function. The step-by-step correction can include guiding the parameter to continuously update in the direction of decreasing the error according to the gradient information of the parameter by the error function, and finishing the iteration when the parameter adjustment meets the set convergence condition, for example, the convergence condition can be that the parameter variation or the error function variation is lower than a preset threshold, or the iteration number reaches the maximum iteration.
S502, generating each capacity attenuation curve by using the charge and discharge cycle times of the battery to be tested and each optimized fitting model.
In the embodiment of the application, the capacity attenuation curve corresponding to each optimized fitting model can be generated according to the optimized fitting model and a preset drawing tool. For example, fig. 7 shows all capacity fade curves corresponding to the battery 1, wherein r2= 0.9981 of the double-exponential fit model, r2=0.9949 of the single-exponential fit model, r2= 0.7736 of the linear fit model, and r2= 0.9535 of the polynomial fit model, fig. 8 shows all capacity fade curves corresponding to the battery 2, wherein r2=0.9993 of the double-exponential fit model, r2=0.9993 of the linear-exponential fit model, r2=0.8636 of the single-exponential fit model, r2=0.9729 of the polynomial fit model, and r2=0.9729 of the polynomial fit model, fig. 10 shows all capacity fade curves corresponding to the battery 3, wherein r2= 0.9983 of the double-exponential fit model, r2= 0.9938 of the single-exponential fit model, r2= 0.7367 of the polynomial fit model, and r2=623 of the target battery are determined by the above-mentioned S202 and S203, and fig. 11 shows all capacity fade curves corresponding to the battery 3, and the target capacity fade curves corresponding to the battery 3, respectively.
Optionally, in an embodiment, as shown in fig. 13, the method for predicting battery capacity further includes:
s206, analyzing the performance data of the battery to be tested according to the target capacity attenuation curve of the battery to be tested.
In the embodiment of the application, the prediction data in the target capacity fading curve can be extracted, statistical analysis and other operations can be performed on the prediction data, so that the service life of each battery can be estimated according to the prediction data, or the target capacity fading curve can be used as the improvement basis or the estimation index of the battery.
In the embodiment of the application, the initial fitting model is subjected to iterative optimization according to the preset algorithm to obtain the optimized fitting model, so that the matching degree of the fitting model and the battery to be tested and the accuracy of the capacity fading curve are improved.
In one embodiment, a complete battery capacity prediction method is provided, as shown in fig. 14, comprising:
S1, optimizing parameters of the fitting model by adopting an iterative optimization algorithm in the process of fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data aiming at each fitting model, so as to obtain an optimized fitting model.
S2, generating each capacity attenuation curve by using the charge and discharge cycle times of the battery to be tested and each optimized fitting model.
And S3, determining a capacity attenuation curve with the end point value of the prediction curve being larger than a preset threshold value as an alternative capacity attenuation curve.
And S4, determining an alternative capacity attenuation curve with the slope of the prediction curve smaller than a preset slope threshold as the candidate capacity attenuation curve.
S5, for each preset fitting model, in the process of fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data of the battery to be tested under multiple charge and discharge cycles, acquiring the total square sum and residual square sum of each fitting model, wherein the total square sum is determined according to the average value of the capacity data and the capacity data under each charge and discharge cycle, and the residual square sum is determined according to the average value of the capacity data and the predicted value corresponding to each charge and discharge cycle in the fitting curve.
And S6, determining the decision coefficient of each fitting model according to the total square sum and the residual square sum of each fitting model.
And S7, sorting the decision coefficients of the fitting model corresponding to the candidate capacity fading curve.
And S8, determining a candidate capacity fading curve corresponding to the fitting model with the maximum determining coefficient as a target capacity fading curve.
S9, analyzing the performance data of the battery to be tested according to the target capacity attenuation curve of the battery to be tested.
According to the battery capacity prediction method, capacity data of a battery to be detected under multiple charge and discharge cycles are utilized to fit capacity attenuation curves of the battery to be detected according to each preset fit model, capacity attenuation curves of the battery to be detected under each fit model are generated, each capacity attenuation curve comprises a fit curve obtained by fitting the capacity data and a prediction curve obtained by predicting the capacity data, candidate capacity attenuation curves of the battery to be detected are determined according to characteristic information of the prediction curves in each capacity attenuation curve, and target capacity attenuation curves of the battery to be detected are determined according to decision coefficients of the fit models corresponding to the candidate capacity attenuation curves. And screening the capacity attenuation curve corresponding to each fitting model twice according to the characteristic information of the prediction curve in the capacity attenuation curve and the decision coefficient of each fitting model, determining the fitting model with the highest accuracy of capacity prediction of the battery to be detected, and improving the matching degree of the fitting model and the battery to be detected and the accuracy of the target capacity attenuation curve.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a battery capacity prediction device for realizing the above-mentioned related battery capacity prediction method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the battery capacity prediction device or devices provided below may be referred to the limitation of the battery capacity prediction method hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 15, there is provided a battery capacity prediction apparatus including a generation module 10, a first determination module 11, and a second determination module 12, wherein:
The generating module 10 is configured to fit, for each preset fitting model, a capacity attenuation curve of the battery to be measured by using capacity data of the battery to be measured under multiple charge and discharge cycles, so as to generate capacity attenuation curves of the battery to be measured under each fitting model, where each capacity attenuation curve includes a fitting curve obtained by fitting based on the capacity data and a prediction curve obtained by predicting based on the capacity data.
The first determining module 11 is configured to determine a candidate capacity-fading curve of the battery to be measured according to the characteristic information of the prediction curve in each capacity-fading curve.
A second determining module 12 is configured to determine a target attenuation curve from the plurality of candidate attenuation curves based on the capacity data and the extension curve of the attenuation curves.
In one embodiment, the first determining module 11 includes a first determining unit and a second determining unit, where:
And the first determining unit is used for determining the capacity fading curve with the end point value of the prediction curve larger than a preset threshold value as an alternative capacity fading curve.
And a second determining unit for determining a candidate capacity fading curve from the candidate capacity fading curves.
In one embodiment, the second determining unit is specifically configured to determine, as the candidate capacity fade curve, an alternative capacity fade curve whose slope of the predicted curve is smaller than a preset slope threshold.
In one embodiment, the second determining module includes a sorting unit and a third determining unit, where:
And the sorting unit is used for sorting the decision coefficients of the fitting model corresponding to the candidate capacity fading curve.
And a third determining unit, configured to determine, as the target capacity fade curve, a candidate capacity fade curve corresponding to the fitting model with the largest decision coefficient.
In one embodiment, the battery capacity prediction apparatus further includes an acquisition module and a third determination module, wherein:
the device comprises an acquisition module, a calculation module and a calculation module, wherein the acquisition module is used for acquiring a total square sum and a residual square sum of each fitting model in the process of fitting a capacity attenuation curve of a battery to be measured by utilizing capacity data of the battery to be measured under multiple charge and discharge cycles, aiming at each preset fitting model, wherein the total square sum is determined according to an average value of the capacity data and the capacity data under each charge and discharge cycle, and the residual square sum is determined according to the average value of the capacity data and a predicted value corresponding to each charge and discharge cycle in the fitting curve.
And the third determining module is used for determining the decision coefficient of each fitting model according to the total square sum and the residual square sum of each fitting model.
In one embodiment, the generating module comprises an optimizing unit and a generating unit, wherein:
And the optimization unit is used for optimizing parameters of the fitting model by adopting an iterative optimization algorithm in the process of fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data aiming at each fitting model to obtain an optimized fitting model.
And the generating unit is used for generating each capacity attenuation curve by using the charge and discharge cycle times of the battery to be tested and each optimized fitting model.
In one embodiment, the battery capacity prediction device further comprises an analysis module, which is used for analyzing the performance data of the battery to be tested according to the target capacity attenuation curve of the battery to be tested.
Each of the modules in the above-described battery capacity prediction apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 16. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing battery capacity prediction data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a battery capacity prediction method.
It will be appreciated by those skilled in the art that the structure shown in FIG. 16 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
For each preset fitting model, fitting a capacity attenuation curve of the battery to be measured by utilizing capacity data of the battery to be measured under multiple charge and discharge cycles to generate a capacity attenuation curve of the battery to be measured under each fitting model;
According to the characteristic information of the prediction curve in each capacity attenuation curve, determining a candidate capacity attenuation curve of the battery to be tested;
And determining a target capacity attenuation curve of the battery to be tested according to the decision coefficient of the fitting model corresponding to the candidate capacity attenuation curve.
In one embodiment, the processor when executing the computer program further performs the steps of:
Determining a capacity fading curve with the end point value of the prediction curve being larger than a preset threshold value as an alternative capacity fading curve;
A candidate capacity fade curve is determined from the candidate capacity fade curves.
In one embodiment, the processor when executing the computer program further performs the steps of:
and determining an alternative capacity fading curve with the slope of the prediction curve smaller than a preset slope threshold as the candidate capacity fading curve.
In one embodiment, the processor when executing the computer program further performs the steps of:
Sorting the decision coefficients of the fitting model corresponding to the candidate capacity fading curve;
and determining a candidate capacity fading curve corresponding to the fitting model with the maximum determining coefficient as a target capacity fading curve.
In one embodiment, the processor when executing the computer program further performs the steps of:
For each preset fitting model, in the process of fitting a capacity attenuation curve of the battery to be measured by utilizing capacity data of the battery to be measured under multiple charge and discharge cycles, acquiring a total square sum and a residual square sum of each fitting model, wherein the total square sum is determined according to an average value of the capacity data and the capacity data under each charge and discharge cycle, and the residual square sum is determined according to the average value of the capacity data and a predicted value corresponding to each charge and discharge cycle in the fitting curve;
And determining the decision coefficient of each fitting model according to the total square sum and the residual square sum of each fitting model.
In one embodiment, the processor when executing the computer program further performs the steps of:
In the process of fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data aiming at each fitting model, optimizing parameters of the fitting model by adopting an iterative optimization algorithm to obtain an optimized fitting model;
and generating each capacity attenuation curve by using the charge and discharge cycle times of the battery to be tested and each optimized fitting model.
In one embodiment, the processor when executing the computer program further performs the steps of:
And analyzing the performance data of the battery to be tested according to the target capacity attenuation curve of the battery to be tested.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
For each preset fitting model, fitting a capacity attenuation curve of the battery to be measured by utilizing capacity data of the battery to be measured under multiple charge and discharge cycles to generate a capacity attenuation curve of the battery to be measured under each fitting model;
According to the characteristic information of the prediction curve in each capacity attenuation curve, determining a candidate capacity attenuation curve of the battery to be tested;
And determining a target capacity attenuation curve of the battery to be tested according to the decision coefficient of the fitting model corresponding to the candidate capacity attenuation curve.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Determining a capacity fading curve with the end point value of the prediction curve being larger than a preset threshold value as an alternative capacity fading curve;
A candidate capacity fade curve is determined from the candidate capacity fade curves.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and determining an alternative capacity fading curve with the slope of the prediction curve smaller than a preset slope threshold as the candidate capacity fading curve.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Sorting the decision coefficients of the fitting model corresponding to the candidate capacity fading curve;
and determining a candidate capacity fading curve corresponding to the fitting model with the maximum determining coefficient as a target capacity fading curve.
In one embodiment, the computer program when executed by the processor further performs the steps of:
For each preset fitting model, in the process of fitting a capacity attenuation curve of the battery to be measured by utilizing capacity data of the battery to be measured under multiple charge and discharge cycles, acquiring a total square sum and a residual square sum of each fitting model, wherein the total square sum is determined according to an average value of the capacity data and the capacity data under each charge and discharge cycle, and the residual square sum is determined according to the average value of the capacity data and a predicted value corresponding to each charge and discharge cycle in the fitting curve;
And determining the decision coefficient of each fitting model according to the total square sum and the residual square sum of each fitting model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
In the process of fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data aiming at each fitting model, optimizing parameters of the fitting model by adopting an iterative optimization algorithm to obtain an optimized fitting model;
and generating each capacity attenuation curve by using the charge and discharge cycle times of the battery to be tested and each optimized fitting model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
And analyzing the performance data of the battery to be tested according to the target capacity attenuation curve of the battery to be tested.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
For each preset fitting model, fitting a capacity attenuation curve of the battery to be measured by utilizing capacity data of the battery to be measured under multiple charge and discharge cycles to generate a capacity attenuation curve of the battery to be measured under each fitting model;
According to the characteristic information of the prediction curve in each capacity attenuation curve, determining a candidate capacity attenuation curve of the battery to be tested;
And determining a target capacity attenuation curve of the battery to be tested according to the decision coefficient of the fitting model corresponding to the candidate capacity attenuation curve.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Determining a capacity fading curve with the end point value of the prediction curve being larger than a preset threshold value as an alternative capacity fading curve;
A candidate capacity fade curve is determined from the candidate capacity fade curves.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and determining an alternative capacity fading curve with the slope of the prediction curve smaller than a preset slope threshold as the candidate capacity fading curve.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Sorting the decision coefficients of the fitting model corresponding to the candidate capacity fading curve;
and determining a candidate capacity fading curve corresponding to the fitting model with the maximum determining coefficient as a target capacity fading curve.
In one embodiment, the computer program when executed by the processor further performs the steps of:
For each preset fitting model, in the process of fitting a capacity attenuation curve of the battery to be measured by utilizing capacity data of the battery to be measured under multiple charge and discharge cycles, acquiring a total square sum and a residual square sum of each fitting model, wherein the total square sum is determined according to an average value of the capacity data and the capacity data under each charge and discharge cycle, and the residual square sum is determined according to the average value of the capacity data and a predicted value corresponding to each charge and discharge cycle in the fitting curve;
And determining the decision coefficient of each fitting model according to the total square sum and the residual square sum of each fitting model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
In the process of fitting the capacity attenuation curve of the battery to be tested by utilizing the capacity data aiming at each fitting model, optimizing parameters of the fitting model by adopting an iterative optimization algorithm to obtain an optimized fitting model;
and generating each capacity attenuation curve by using the charge and discharge cycle times of the battery to be tested and each optimized fitting model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
And analyzing the performance data of the battery to be tested according to the target capacity attenuation curve of the battery to be tested.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile memory and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (RESISTIVE RANDOM ACCESS MEMORY, reRAM), magneto-resistive Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computation, an artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) processor, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the present application.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510346954.6A CN119846484B (en) | 2025-03-24 | 2025-03-24 | Battery capacity prediction method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510346954.6A CN119846484B (en) | 2025-03-24 | 2025-03-24 | Battery capacity prediction method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119846484A true CN119846484A (en) | 2025-04-18 |
| CN119846484B CN119846484B (en) | 2025-08-26 |
Family
ID=95363498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510346954.6A Active CN119846484B (en) | 2025-03-24 | 2025-03-24 | Battery capacity prediction method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119846484B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140129163A1 (en) * | 2012-11-02 | 2014-05-08 | Fairfield Industries, Inc. | Battery capacity and durability prediction method |
| CN107219461A (en) * | 2016-03-22 | 2017-09-29 | 珠海光宇电池有限公司 | The life-span prediction method and method for managing power supply of secondary cell |
| WO2022068652A1 (en) * | 2020-09-30 | 2022-04-07 | 比亚迪股份有限公司 | Method and apparatus for obtaining battery capacity, storage medium and server |
| JP2024031219A (en) * | 2022-08-26 | 2024-03-07 | トヨタ自動車株式会社 | Full charge capacity estimation method |
-
2025
- 2025-03-24 CN CN202510346954.6A patent/CN119846484B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140129163A1 (en) * | 2012-11-02 | 2014-05-08 | Fairfield Industries, Inc. | Battery capacity and durability prediction method |
| CN107219461A (en) * | 2016-03-22 | 2017-09-29 | 珠海光宇电池有限公司 | The life-span prediction method and method for managing power supply of secondary cell |
| WO2022068652A1 (en) * | 2020-09-30 | 2022-04-07 | 比亚迪股份有限公司 | Method and apparatus for obtaining battery capacity, storage medium and server |
| JP2024031219A (en) * | 2022-08-26 | 2024-03-07 | トヨタ自動車株式会社 | Full charge capacity estimation method |
Non-Patent Citations (1)
| Title |
|---|
| 焦君宇 等: "电池大数据智能分析平台的研发与应用", 《储能科学与技术》, vol. 13, no. 9, 30 September 2024 (2024-09-30), pages 3198 - 3213 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119846484B (en) | 2025-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695301A (en) | Method and device for predicting battery charge state, storage medium and equipment | |
| US11262407B2 (en) | Method and apparatus with battery state estimation | |
| CN116127785B (en) | Reliability evaluation method, device and equipment based on multiple performance degradation | |
| CN116166511B (en) | Methods, apparatus, equipment, and storage media for assessing the service life of electrical connectors | |
| CN115795928B (en) | Gamma process-based accelerated degradation test data processing method and device | |
| CN113946986A (en) | Method and device for evaluating the mean time to failure of products based on accelerated degradation test | |
| CN119846484B (en) | Battery capacity prediction method, device, computer equipment and storage medium | |
| CN118917267B (en) | Chip layout method, apparatus, computer device, storage medium and computer program product | |
| CN119597605A (en) | Distributed storage performance testing method, device, computer equipment, readable storage medium and program product | |
| CN119416022A (en) | Health status assessment method, device, computer equipment, medium and product for electrochemical energy storage system | |
| CN115933597B (en) | Control system parameter setting method, system and computer equipment | |
| CN114566201B (en) | Method, device and electronic device for determining optimal reading voltage | |
| CN118226281B (en) | Method, device, equipment and storage medium for predicting attenuation track of lithium ion battery | |
| CN115587677A (en) | Mutual information-based method and device for analyzing associated factors of power system load | |
| CN116306030A (en) | Dynamic Scenario Generation Method for New Energy Forecasting Considering Forecast Error and Fluctuation Distribution | |
| CN116191398A (en) | Load forecasting method, device, computer equipment and storage medium | |
| CN118822294B (en) | Method, apparatus, computer device, storage medium, and product for predicting electric load | |
| CN120722228B (en) | Battery equivalent circuit parameter identification method and storage medium | |
| CN117171600B (en) | User clustering methods, apparatus, devices, storage media, and program products | |
| CN119939404B (en) | Method and device for constructing capacity retention rate estimation model and computer equipment | |
| CN116821147B (en) | Data search tools identify methods, devices, equipment, and storage media. | |
| CN117937477B (en) | Method and device for predicting reactive power boundary value of generator set and computer equipment | |
| CN119830775B (en) | Key area identification method, device, equipment and medium based on multi-objective optimization | |
| CN121231533A (en) | Method, device, equipment, medium and product for optimizing electron back scattering diffraction parameter | |
| CN119939404A (en) | Method, device and computer equipment for constructing capacity retention rate estimation model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |