CN115754772A - Battery capacity attenuation processing method, device, equipment and storage medium - Google Patents
Battery capacity attenuation processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115754772A CN115754772A CN202211518459.1A CN202211518459A CN115754772A CN 115754772 A CN115754772 A CN 115754772A CN 202211518459 A CN202211518459 A CN 202211518459A CN 115754772 A CN115754772 A CN 115754772A
- Authority
- CN
- China
- Prior art keywords
- sample
- battery
- power battery
- capacity
- capacity attenuation
- 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.)
- Pending
Links
Images
Classifications
-
- 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
Abstract
The invention discloses a method, a device, equipment and a storage medium for battery capacity attenuation treatment, wherein the method comprises the following steps: adjusting an experimental capacity attenuation characteristic curve of a sample power battery measured in an experiment according to sample operation parameters of the sample power battery in a sample circulation period, and determining the sample capacity attenuation characteristic curve of the sample power battery; the sample capacity attenuation characteristic curve comprises a discharge depth change curve and a residual capacity change curve of the sample power battery; determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected. The accuracy of the sample capacity attenuation characteristic curve can be improved, and therefore the effect of improving the model accuracy of the battery capacity attenuation prediction model is achieved.
Description
Technical Field
The embodiment of the invention relates to the field of batteries, in particular to a battery capacity attenuation processing method, device, equipment and storage medium.
Background
At present, the application of power batteries is more and more extensive, and the safety problem of the power batteries draws wide attention of people. The operating temperature condition of the power battery directly affects the service life of the power battery. The power battery enters a battery capacity attenuation stage before the service life of the power battery is ended, and if the battery capacity attenuation of the power battery can be accurately known and the power battery is improved based on the battery capacity attenuation condition of the power battery, the service life of the power battery can be prolonged. At this stage, the battery capacity attenuation of the power battery is usually obtained by calculating the current of the electric equipment connected with the power battery and the rated capacity of the power battery provided by the manufacturer of the power battery, or is determined by a user according to the service time of the battery and the corresponding relation between the service time and the battery capacity attenuation provided by the manufacturer of the battery. The battery capacity attenuation accuracy of the power battery obtained by the existing battery capacity attenuation mode is low. Therefore, how to improve the calculation accuracy of the battery capacity attenuation of the power battery and save the labor cost for calculating the battery capacity attenuation is a problem to be solved.
Disclosure of Invention
The invention provides a battery capacity attenuation processing method, a device, equipment and a storage medium, which can predict the battery capacity attenuation of a power battery and improve the calculation efficiency and the calculation accuracy of the power battery capacity attenuation data.
According to an aspect of the present invention, there is provided a battery capacity fade processing method, including:
adjusting an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment according to sample operation parameters of the sample power battery in a sample circulation period, and determining the sample capacity attenuation characteristic curve of the sample power battery; the sample capacity attenuation characteristic curve comprises a discharge depth change curve and a residual capacity change curve of the sample power battery;
determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected.
According to another aspect of the present invention, there is provided a battery capacity fade processing device including:
the system comprises a sample power battery, a decay characteristic curve determining module, a sample capacity decay characteristic curve determining module and a sample capacity decay characteristic curve determining module, wherein the sample power battery is used for measuring the sample capacity decay characteristic curve of the sample power battery; the sample capacity attenuation characteristic curve comprises a discharge depth change curve and a residual capacity change curve of the sample power battery;
the attenuation prediction model determining module is used for determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting battery capacity attenuation data of the battery to be detected.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of battery capacity fade processing according to any one of the embodiments of the invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the battery capacity fade processing method according to any one of the embodiments of the present invention when the computer instructions are executed.
According to the technical scheme of the embodiment of the invention, the experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment is adjusted according to the sample operation parameters of the sample power battery in the sample circulation period, and the sample capacity attenuation characteristic curve of the sample power battery is determined; determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected. The problem of through the current of the consumer of connecting power battery and the rated capacity calculation power battery that power battery producer provided, calculate power battery's battery capacity attenuation, calculation accuracy is lower is solved. According to the scheme, a sample capacity attenuation characteristic curve which accords with the actual working condition of the sample power battery is determined according to the sample operation parameters of the sample power battery in the sample circulation period and the experimental capacity attenuation characteristic curve of the sample power battery, model training data are determined according to the sample capacity characteristic curve, a machine learning model is trained according to the model training data, and a battery capacity attenuation prediction model used for predicting the battery capacity attenuation data of the power battery to be detected is obtained. Model training data of the machine learning model are enriched, accuracy of a sample capacity attenuation characteristic curve is improved, and therefore the effect of model accuracy of the battery capacity attenuation prediction model is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a battery capacity fade processing method according to an embodiment of the present invention;
fig. 2 is a flowchart of a battery capacity fading processing method according to a second embodiment of the present invention;
fig. 3 is a flowchart of a battery capacity fading processing method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a battery capacity fade processing device according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "sample" and "to be tested" and the like in the description and claims of the present invention and the above drawings are used for distinguishing similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a battery capacity fade processing method according to an embodiment of the present invention, which is applicable to a case of processing battery capacity fade of a power battery. The method may be performed by a battery capacity fade processing device, which may be implemented in the form of hardware and/or software, and which may be configured in an electronic device. As shown in fig. 1, the method includes:
s110, adjusting an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment according to sample operation parameters of the sample power battery in a sample circulation period, and determining the sample capacity attenuation characteristic curve of the sample power battery.
The sample capacity attenuation characteristic curve comprises a discharge depth change curve and a residual capacity change curve of the sample power battery. The sample cycle period may be a predefined battery cycle period, which refers to a complete charge and discharge cycle of the battery. For example, the sample cycle period may include the tenth, thirty-th, fifty-th, and seventy-th battery cycle periods of the sample power cell. The battery attenuation parameters are parameters for measuring battery capacity attenuation data of the sample power battery, and the battery attenuation parameters comprise battery power attenuation, open-circuit voltage, battery capacity attenuation data, residual electric quantity and discharge depth of the sample power battery in a sample circulation period. The abscissa of the experimental capacity attenuation characteristic curve of the sample power battery and the abscissa of the sample capacity attenuation characteristic curve are both the cycle number of the sample power battery, and the ordinate is the battery capacity attenuation data of the sample power battery. The battery capacity fade data may be a battery capacity fade rate. Depth of discharge refers to the percentage of the battery's discharge capacity to the battery's rated capacity. The sample operation parameters refer to internal parameters of the sample power battery during operation. The sample operating parameters may include temperature, open circuit voltage, terminal voltage, ohmic internal resistance, charge and discharge circuitry, polarization capacitance, and polarization internal resistance of the sample power cell over a sample cycle period.
Specifically, an experimental capacity fading characteristic curve of the sample power battery, that is, an experimental capacity fading characteristic curve of the sample power battery measured experimentally, is obtained through an experiment in advance. And determining the residual electric quantity and the discharge electric quantity of the sample power battery in each sample circulation period according to the sample operation parameters of the sample power battery in the sample circulation period. And calculating the discharge depth of the sample power battery according to the discharge electric quantity and the rated capacity of the sample power battery. The remaining capacity of the sample power battery in the sample cycle period refers to the remaining capacity of the sample power battery at the end of the cycle period. And determining the battery capacity attenuation data of the sample power battery in the sample cycle period according to the residual electric quantity and the discharge depth of the sample power battery in the sample cycle period. And adjusting the experimental capacity attenuation data corresponding to the sample cycle period in the experimental capacity attenuation characteristic curve according to the battery capacity attenuation data of the sample power battery in the sample cycle period, adjusting the experimental capacity attenuation characteristic curve according to the adjusted experimental capacity attenuation data, and taking the adjusted experimental capacity attenuation characteristic curve as the sample capacity attenuation characteristic curve of the sample power battery.
S120, determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected.
Specifically, sample capacity fading characteristic parameters of the sample power battery in all cycle periods are determined according to the sample capacity fading characteristic curve, wherein the sample capacity fading characteristic parameters comprise capacity fading data, residual electric quantity and discharge depth. And taking the sample capacity attenuation characteristic parameters as model training data, and dividing the model training data into sample training data and sample testing data. And performing iterative training on the machine learning model by adopting the sample training data, testing the trained machine learning model by adopting the sample testing data, determining the model precision according to the test result, stopping training the machine learning model when the model precision of the machine learning model meets the preset condition, and taking the trained machine learning model as a battery capacity attenuation prediction model.
Illustratively, the battery capacity fade prediction model may be determined by training a machine learning model through the following sub-steps:
s1201, extracting cycle period capacity attenuation data, cycle period residual electric quantity and cycle period discharge depth corresponding to all battery cycle periods of the sample power battery from the sample capacity attenuation characteristic curve.
The cycle period capacity fading data refers to battery capacity fading data of the sample power battery in a single battery cycle period. The cycle residual capacity refers to the battery residual capacity of the sample power battery after the end of a single battery cycle. Cycle period depth of discharge refers to the depth of discharge of the battery of the sample power cell during a single battery cycle period.
Specifically, the abscissa of the sample capacity fading characteristic curve is the number of battery cycles, the ordinate is the battery capacity fading data, and each coordinate point includes the remaining capacity and the discharge depth of the sample power battery in a single battery cycle in the battery cycle. Therefore, the cycle period capacity fading data, the cycle period residual electric quantity and the cycle period discharge depth corresponding to all the battery cycle periods of the sample power battery can be extracted from the sample capacity fading characteristic curve.
And S1202, taking the cycle period capacity attenuation data, the cycle period residual electric quantity and the cycle period discharge depth as model training data, and performing iterative training on network parameters in the machine learning model according to the model training data to obtain a model loss function in the iterative training process.
Where the model loss function measures the ability of the model to predict the expected outcome.
Specifically, the cycle period capacity decay data, the cycle period residual electric quantity and the cycle period discharge depth are used as model training data. The cyclic period capacity fading data is model supervision data in the model training data. The model training data is divided into sample training data and sample test data. And carrying out iterative training on the network parameters in the machine learning model by adopting the sample training data, testing the machine learning model after the iterative training according to the sample testing data after each iterative training is finished, and determining the model loss function of the machine learning model after the iterative training.
For example, the machine learning model after iterative training may be tested according to sample test data, predicted capacity attenuation data corresponding to each sample test data is obtained, an average absolute error between each predicted capacity attenuation data and actual capacity attenuation data corresponding to each sample test data is calculated, and the average absolute error is used as a model loss function of the machine learning model. Wherein the average absolute error is an average of a sum of absolute differences between each of the actual capacity fade data and each of the predicted capacity fade data.
And S1203, determining whether the machine learning model after the iterative training is converged according to the model loss function, and if so, taking the machine learning model after the iterative training as a battery capacity attenuation prediction model.
Specifically, if the model loss function is smaller than a preset loss function threshold, determining that the machine learning model after iterative training is converged; and if the model loss function is larger than or equal to the loss function threshold value, determining that the machine learning model after the iterative training does not converge. And if the machine learning model after the iterative training is converged, taking the machine learning model after the iterative training as a battery capacity attenuation prediction model. And if the machine learning model after iterative training does not converge, continuing to carry out iterative training on the machine learning model until whether the machine learning model after iterative training converges.
It can be understood that the cycle period capacity attenuation data, the cycle period residual electric quantity and the cycle period discharge depth corresponding to all the battery cycle periods of the sample power battery are determined according to the sample capacity attenuation characteristic curve, extracted data are used as model training data to conduct iterative computation on the machine learning model, iterative computation is stopped when the model loss function of the machine learning model meets the preset iteration stop condition, the battery capacity attenuation prediction model is determined, and the prediction accuracy of the battery capacity attenuation data of the power battery to be detected by the battery capacity attenuation prediction model can be improved.
According to the technical scheme provided by the embodiment, the experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment is adjusted according to the sample operation parameters of the sample power battery in the sample circulation period, and the sample capacity attenuation characteristic curve of the sample power battery is determined; determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected. The problem of through the current of the consumer of connecting power battery and the rated capacity calculation power battery that power battery producer provided, calculate power battery's battery capacity attenuation, calculation accuracy is lower is solved. According to the scheme, a sample capacity attenuation characteristic curve which accords with the actual working condition of the sample power battery is determined according to the sample operation parameters of the sample power battery in the sample circulation period and the experimental capacity attenuation characteristic curve of the sample power battery, model training data are determined according to the sample capacity characteristic curve, a machine learning model is trained according to the model training data, and a battery capacity attenuation prediction model used for predicting the battery capacity attenuation data of the power battery to be detected is obtained. Model training data of the machine learning model are enriched, accuracy of a sample capacity attenuation characteristic curve is improved, and therefore the effect of improving model accuracy of the battery capacity attenuation prediction model is achieved.
Example two
Fig. 2 is a flowchart of a battery capacity fading processing method according to a second embodiment of the present invention, which is optimized based on the above embodiments, and provides a preferred embodiment of adjusting an experimental capacity fading characteristic curve of a sample power battery measured experimentally according to sample operating parameters of the sample power battery in a sample cycle period to determine the sample capacity fading characteristic curve of the sample power battery. Specifically, as shown in fig. 2, the method includes:
s210, determining an equivalent circuit model of the sample power battery in the sample circulation period according to sample operation parameters of the sample power battery in the sample circulation period.
Specifically, the method comprises the steps of obtaining operation parameters of a sample power battery in a sample cycle period through a sensor, determining parameter change information of the sample power battery according to the operation parameters, and determining an equivalent circuit model according to the parameter change information. The parameter change information of the sample power battery can be a change curve of each operation parameter of the sample power battery in a sample cycle period, and can also be a table for recording the operation parameters of the sample power battery at different moments in the sample cycle period. The expression of the equivalent circuit model is shown in formula (1):
wherein, X is the mark of the equivalent circuit model; u shape oc Is the open circuit voltage of the sample power cell; u shape L Is the sample power cell terminal voltage; I.C. A L The charging and discharging current of the sample power battery is obtained; r 1 And R 2 The polarization internal resistance of the sample power battery is obtained; c 1 And C 2 Is the polarization capacitance of the sample power cell.
And S220, determining the sample residual electric quantity and the sample discharge depth of the sample power battery in the sample cycle period according to the equivalent circuit model of the sample power battery.
Specifically, based on the equivalent circuit model, the ampere-hour integration method is adopted to calculate the variation of the residual capacity of the sample power battery in the sample cycle period. The calculation formula of the amount of change in the remaining amount of electricity is shown in formula (2):
wherein, the delta SOC is the variation of the residual capacity of the sample power battery; q N Is the rated capacity of the sample power battery; and K is the charge and discharge efficiency of the sample power battery.
And obtaining an initial SOC value of the sample power battery by looking up a table according to the open-circuit voltage of the sample power battery by adopting an open-circuit voltage method. And estimating the first to-be-corrected electric quantity of the sample power battery in real time by combining an ampere-hour integration method. The first to-be-corrected electric quantity refers to the residual electric quantity of the sample power battery to be corrected. The calculation formula of the first to-be-corrected electric quantity of the sample power battery is shown as formula (3):
SOC 1 ＝SOC 0 -ΔSOC (3)
therein, SOC 1 The first to-be-corrected electric quantity of the sample power battery is obtained; SOC 0 The charge and discharge initial state of the sample power battery is shown.
And finally, correcting the first to-be-corrected electric quantity and the second to-be-corrected electric quantity of the sample power battery by adopting a capacitance-voltage method, and determining the residual electric quantity of the sample power battery. The formula for calculating the residual capacity of the sample power battery is shown in formula (4):
the SOC is the sample residual electric quantity of the sample power battery; SOC 2 And the second electric quantity to be corrected. The second electric quantity to be corrected refers toAnd calculating the residual capacity of the sample power battery by a capacitance voltage method.
And taking the ratio of the variation of the residual capacity of the sample power battery in the sample cycle period to the rated capacity of the sample power battery as the sample discharge depth of the sample power battery in the sample cycle period.
And S230, adjusting the experimentally measured experimental capacity attenuation characteristic curve of the sample power battery based on the sample residual capacity and the sample discharge depth, and determining the sample capacity attenuation characteristic curve of the sample power battery.
The sample capacity attenuation characteristic curve comprises a discharge depth change curve and a residual capacity change curve of the sample power battery.
Specifically, the residual electric quantity and the discharge depth of the sample cycle period in an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment are extracted and used as the experimental residual electric quantity and the experimental discharge depth. And adjusting the experiment capacity decay characteristic curve of the sample power battery measured in the experiment based on the sample residual capacity and the sample depth of discharge, namely replacing the experiment residual capacity and the experiment depth of discharge in the experiment capacity decay characteristic curve by adopting the sample residual capacity and the sample depth of discharge of the sample power battery in the sample circulation period. And taking the adjusted experimental capacity attenuation characteristic curve as a sample capacity attenuation characteristic curve of the sample power battery.
For example, the method for determining the sample capacity decay characteristic curve of the sample power battery may further comprise: performing iterative training on an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment based on the sample residual electric quantity and the sample discharge depth, and acquiring residual data of the experimental capacity attenuation characteristic curve in the iterative training process; and when the residual data meet the preset residual condition, stopping the iterative training, and taking the trained experimental capacity attenuation characteristic curve as a sample capacity attenuation characteristic curve of the sample power battery.
The preset residual condition may be that the residual data is smaller than a preset residual threshold.
By the scheme, the acquisition efficiency and accuracy of the sample capacity attenuation characteristic curve can be improved.
S240, determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected.
According to the technical scheme of the embodiment, an equivalent circuit model of the sample power battery in the sample cycle period is determined according to sample operation parameters of the sample power battery in the sample cycle period; determining the sample residual capacity and the sample discharge depth of the sample power battery in the sample cycle period according to the equivalent circuit model of the sample power battery; adjusting an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment based on the sample residual electric quantity and the sample discharge depth, and determining the sample capacity attenuation characteristic curve of the sample power battery; determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected. According to the scheme, the sample residual capacity and the sample discharge depth of the sample power battery in the sample circulation period are calculated according to the sample operation parameters of the sample power battery in the sample circulation period, the actual residual capacity and the actual discharge depth of the sample power battery in the sample circulation period can be obtained, the experimental capacity attenuation characteristic curve of the sample power battery is adjusted according to the sample residual capacity and the sample discharge depth, a more accurate sample capacity attenuation characteristic curve can be obtained, and the sample capacity attenuation characteristic curve can better accord with the actual capacity attenuation condition of the sample power battery.
EXAMPLE III
Fig. 3 is a flowchart of a battery capacity fading processing method provided in the third embodiment of the present invention, and this embodiment optimizes the above embodiments and provides a preferred implementation of calculating battery capacity fading data of a power battery to be detected in a cycle period to be detected according to a battery capacity fading prediction model. Specifically, as shown in fig. 3, the method includes:
s310, adjusting an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment according to sample operation parameters of the sample power battery in a sample circulation period, and determining the sample capacity attenuation characteristic curve of the sample power battery.
The sample capacity attenuation characteristic curve comprises a discharge depth change curve and a residual capacity change curve of the sample power battery.
S320, determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected.
S330, determining the remaining electric quantity and the discharging depth of the power battery to be detected in the cycle period to be detected according to the target operation parameters of the power battery to be detected in the cycle period to be detected.
And the residual electric quantity of the battery to be detected is the residual electric quantity of the battery of the power battery to be detected when the cycle period to be detected is ended. The discharge depth of the battery to be detected is the discharge depth of the power battery to be detected in the cycle period to be detected.
Specifically, the target operation parameter may be determined according to the to-be-detected operation parameter of the to-be-detected power battery. The operation parameters to be detected can comprise the temperature, the open-circuit voltage, the terminal voltage, the ohmic internal resistance, the charging and discharging circuit, the polarization capacitor and the polarization internal resistance of the power battery to be detected in the sample cycle period. And calculating the remaining electric quantity of the to-be-detected battery and the discharging depth of the to-be-detected battery in the to-be-detected cycle period according to the target operation parameters.
For example, the calculation method of the target operation parameter may be: acquiring the to-be-detected operating parameters of the to-be-detected power battery acquired under the parameter acquisition conditions, respectively calculating the parameter average value of each to-be-detected operating parameter, and taking the parameter average value as the target operating parameter of the to-be-detected power battery in the to-be-detected cycle.
According to the scheme, when the target operation parameters are determined, the operation parameters to be detected of the power battery to be detected under different parameter acquisition conditions are fully considered, the parameter average value of each operation parameter to be detected is used as the target operation parameter, and when the residual capacity of the battery to be detected and the discharge depth of the battery to be detected are calculated according to the target operation parameters, a more accurate calculation result can be obtained.
S340, taking the target operation parameter, the residual electric quantity of the battery to be detected and the discharge depth of the battery to be detected as model input parameters of a battery capacity attenuation prediction model, and determining battery capacity attenuation data of the battery to be detected in the cycle period to be detected according to the model input parameters and the battery capacity attenuation prediction model.
Specifically, the target operation parameter, the residual electric quantity of the battery to be detected and the discharge depth of the battery to be detected are used as model input parameters of the battery capacity attenuation prediction model. And inputting the model input parameters into a battery capacity attenuation prediction model, wherein the output data of the battery capacity attenuation prediction model is the battery capacity attenuation data of the battery to be detected in the cycle period to be detected.
According to the technical scheme of the embodiment, an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment is adjusted according to sample operation parameters of the sample power battery in a sample circulation period, and the sample capacity attenuation characteristic curve of the sample power battery is determined; determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected; determining the remaining electric quantity and the discharging depth of the power battery to be detected in the cycle period to be detected according to the target operation parameters of the power battery to be detected in the cycle period to be detected; and determining the battery capacity attenuation data of the battery to be detected in the cycle period to be detected according to the model input parameters and the battery capacity attenuation prediction model. According to the scheme, the effect of improving the calculation efficiency and the calculation accuracy of the battery capacity attenuation data of the battery to be detected in the cycle period to be detected is achieved.
Example four
Fig. 4 is a schematic structural diagram of a battery capacity fading processing apparatus according to a fourth embodiment of the present invention. The embodiment can be applied to the situation of processing the battery capacity attenuation of the power battery. As shown in fig. 4, the battery capacity fade processing device includes: an attenuation profile determination module 410 and an attenuation prediction model determination module 420.
The attenuation characteristic curve determining module 410 is configured to adjust an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment according to a sample operation parameter of the sample power battery in a sample cycle period, and determine the sample capacity attenuation characteristic curve of the sample power battery; the sample capacity attenuation characteristic curve comprises a discharge depth change curve and a residual capacity change curve of the sample power battery;
the attenuation prediction model determining module 420 is configured to determine model training data according to the sample capacity attenuation characteristic curve, train the machine learning model by using the model training data, and determine a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected.
According to the technical scheme provided by the embodiment, an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment is adjusted according to sample operation parameters of the sample power battery in a sample circulation period, and the sample capacity attenuation characteristic curve of the sample power battery is determined; determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected. The problem of through the current of the consumer of connecting power battery and the rated capacity calculation power battery that power battery producer provided, calculate power battery's battery capacity attenuation, calculation accuracy is lower is solved. According to the scheme, a sample capacity attenuation characteristic curve which accords with the actual working condition of the sample power battery is determined according to sample operation parameters of the sample power battery in a sample circulation period and an experimental capacity attenuation characteristic curve of the sample power battery, model training data are determined according to the sample capacity characteristic curve, a machine learning model is trained according to the model training data, and a battery capacity attenuation prediction model used for predicting the battery capacity attenuation data of the power battery to be detected is obtained. Model training data of the machine learning model are enriched, accuracy of a sample capacity attenuation characteristic curve is improved, and therefore the effect of model accuracy of the battery capacity attenuation prediction model is improved.
Exemplary, the attenuation characteristic determination module 410 includes:
the equivalent circuit model determining unit is used for determining an equivalent circuit model of the sample power battery in a sample circulation period according to sample operation parameters of the sample power battery in the sample circulation period;
the sample residual capacity determining unit is used for determining the sample residual capacity and the sample discharge depth of the sample power battery in the sample cycle period according to the equivalent circuit model of the sample power battery;
and the attenuation characteristic curve adjusting unit is used for adjusting the experimental capacity attenuation characteristic curve of the sample power battery measured in the experiment based on the sample residual capacity and the sample discharge depth, and determining the sample capacity attenuation characteristic curve of the sample power battery.
Exemplarily, the attenuation characteristic curve adjustment unit is specifically configured to:
performing iterative training on an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment based on the sample residual electric quantity and the sample discharge depth, and acquiring residual data of the experimental capacity attenuation characteristic curve in the iterative training process;
and when the residual data meet the preset residual condition, stopping the iterative training, and taking the trained experimental capacity attenuation characteristic curve as a sample capacity attenuation characteristic curve of the sample power battery.
Illustratively, the attenuation prediction model determination module 420 is specifically configured to:
extracting cycle period capacity attenuation data, cycle period residual electric quantity and cycle period discharge depth corresponding to all battery cycle periods of the sample power battery from the sample capacity attenuation characteristic curve;
taking the cycle period capacity attenuation data, the cycle period residual electric quantity and the cycle period discharge depth as model training data, and performing iterative training on network parameters in the machine learning model according to the model training data to obtain a model loss function in the iterative training process;
and determining whether the machine learning model after the iterative training is converged according to the model loss function, and if so, taking the machine learning model after the iterative training as a battery capacity attenuation prediction model.
Exemplarily, the battery capacity fade processing apparatus further includes:
the target operation parameter analysis module is used for determining the residual electric quantity and the discharge depth of the to-be-detected battery of the to-be-detected power battery in the to-be-detected cycle period according to the target operation parameters of the to-be-detected power battery in the to-be-detected cycle period;
and the battery capacity attenuation determining module is used for taking the target operation parameters, the residual electric quantity of the battery to be detected and the discharge depth of the battery to be detected as model input parameters of the battery capacity attenuation predicting model and determining battery capacity attenuation data of the battery to be detected in the cycle period to be detected according to the model input parameters and the battery capacity attenuation predicting model.
Illustratively, the target operating parameter analysis module is specifically configured to:
acquiring the to-be-detected operating parameters of the to-be-detected power battery acquired under the parameter acquisition conditions, respectively calculating the parameter average value of each to-be-detected operating parameter, and taking the parameter average value as the target operating parameter of the to-be-detected power battery in the to-be-detected cycle.
The battery capacity fading processing device provided by the embodiment can be applied to the battery capacity fading processing method provided by any embodiment, and has corresponding functions and beneficial effects.
EXAMPLE five
FIG. 5 illustrates a schematic diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The processor 11 performs the various methods and processes described above, such as a battery capacity fade processing method.
In some embodiments, the battery capacity fade processing method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the battery capacity fade processing method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the battery capacity fade processing method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable battery capacity fade processing device, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A battery capacity fade processing method, comprising:
adjusting an experimental capacity attenuation characteristic curve of the sample power battery measured in an experiment according to sample operation parameters of the sample power battery in a sample circulation period, and determining the sample capacity attenuation characteristic curve of the sample power battery; the sample capacity attenuation characteristic curve comprises a discharge depth change curve and a residual capacity change curve of the sample power battery;
determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data, and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected.
2. The method of claim 1, wherein adjusting an experimentally measured experimental capacity fade characteristic curve of a sample power cell according to sample operating parameters of the sample power cell during a sample cycle, determining a sample capacity fade characteristic curve of the sample power cell, comprises:
determining an equivalent circuit model of the sample power battery in a sample cycle period according to sample operation parameters of the sample power battery in the sample cycle period;
determining the sample residual capacity and the sample discharge depth of the sample power battery in the sample cycle period according to the equivalent circuit model of the sample power battery;
and adjusting the experimentally measured experimental capacity attenuation characteristic curve of the sample power battery based on the sample residual electric quantity and the sample discharge depth, and determining the sample capacity attenuation characteristic curve of the sample power battery.
3. The method of claim 2, wherein adjusting an experimentally measured experimental capacity fade profile of a sample power cell based on the sample remaining power and the sample depth of discharge determines a sample capacity fade profile for the sample power cell, comprising:
performing iterative training on an experimental capacity attenuation characteristic curve of the sample power battery measured by the experiment based on the sample residual electric quantity and the sample discharge depth, and acquiring residual data of the experimental capacity attenuation characteristic curve in the iterative training process;
and when the residual data meet the preset residual condition, stopping iterative training, and taking the trained experimental capacity attenuation characteristic curve as a sample capacity attenuation characteristic curve of the sample power battery.
4. The method of claim 1, wherein determining model training data from the sample capacity fading characteristic curve, and using the model training data to train a machine learning model to determine a battery capacity fading prediction model, comprises:
extracting cycle period capacity attenuation data, cycle period residual electric quantity and cycle period discharge depth corresponding to all battery cycle periods of the sample power battery from the sample capacity attenuation characteristic curve;
taking the cycle period capacity attenuation data, the cycle period residual capacity and the cycle period discharge depth as model training data, and performing iterative training on network parameters in the machine learning model according to the model training data to obtain a model loss function in the iterative training process;
and determining whether the machine learning model after the iterative training is converged according to the model loss function, and if so, taking the machine learning model after the iterative training as a battery capacity attenuation prediction model.
5. The method of claim 1, further comprising:
determining the remaining electric quantity and the discharging depth of the power battery to be detected in the cycle period to be detected according to the target operation parameters of the power battery to be detected in the cycle period to be detected;
and determining the battery capacity attenuation data of the battery to be detected in the cycle period to be detected according to the model input parameters and the battery capacity attenuation prediction model.
6. The method according to claim 5, wherein according to the target operation parameters of the power battery to be detected in the cycle period to be detected, the method comprises the following steps:
acquiring the to-be-detected operating parameters of the to-be-detected power battery acquired under each parameter acquisition condition, respectively calculating the parameter average value of each to-be-detected operating parameter, and taking the parameter average value as the target operating parameter of the to-be-detected power battery in the to-be-detected cycle period.
7. A battery capacity fade processing device, characterized by comprising:
the system comprises a sample power battery, a decay characteristic curve determination module, a sample capacity decay characteristic curve determination module and a sample capacity storage module, wherein the sample power battery is used for storing a sample capacity decay characteristic curve of the sample power battery; the sample capacity attenuation characteristic curve comprises a discharge depth change curve and a residual capacity change curve of the sample power battery;
the attenuation prediction model determining module is used for determining model training data according to the sample capacity attenuation characteristic curve, training a machine learning model by adopting the model training data and determining a battery capacity attenuation prediction model; the battery capacity attenuation prediction model is used for predicting the battery capacity attenuation data of the battery to be detected.
8. The apparatus of claim 7, wherein the attenuation characteristic determination module comprises:
the equivalent circuit model determining unit is used for determining an equivalent circuit model of the sample power battery in a sample circulation period according to sample operation parameters of the sample power battery in the sample circulation period;
the sample residual capacity determining unit is used for determining the sample residual capacity and the sample discharge depth of the sample power battery in a sample cycle period according to the equivalent circuit model of the sample power battery;
and the attenuation characteristic curve adjusting unit is used for adjusting the experimental capacity attenuation characteristic curve of the sample power battery measured in the experiment based on the sample residual electric quantity and the sample discharge depth, and determining the sample capacity attenuation characteristic curve of the sample power battery.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the battery capacity fade processing method of any one of claims 1-6.
10. A computer-readable storage medium storing computer instructions for causing a processor to implement the battery capacity fade processing method of any one of claims 1-6 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211518459.1A CN115754772A (en) | 2022-11-29 | 2022-11-29 | Battery capacity attenuation processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211518459.1A CN115754772A (en) | 2022-11-29 | 2022-11-29 | Battery capacity attenuation processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115754772A true CN115754772A (en) | 2023-03-07 |
Family
ID=85340970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211518459.1A Pending CN115754772A (en) | 2022-11-29 | 2022-11-29 | Battery capacity attenuation processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115754772A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116699445A (en) * | 2023-08-07 | 2023-09-05 | 江苏天合储能有限公司 | Capacity prediction method and system for battery energy storage system |
-
2022
- 2022-11-29 CN CN202211518459.1A patent/CN115754772A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116699445A (en) * | 2023-08-07 | 2023-09-05 | 江苏天合储能有限公司 | Capacity prediction method and system for battery energy storage system |
| CN116699445B (en) * | 2023-08-07 | 2023-10-20 | 江苏天合储能有限公司 | Capacity prediction method and system for battery energy storage system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115718265A (en) | Method for correcting battery DC resistance test value, electronic device and storage medium | |
| CN116008827A (en) | Determination method and device for lithium ion battery lithium precipitation potential and electronic equipment | |
| CN115932634A (en) | Method, device, equipment and storage medium for evaluating health state of battery | |
| CN115932586A (en) | Method, device, equipment and medium for estimating state of charge of battery on line | |
| CN115754772A (en) | Battery capacity attenuation processing method, device, equipment and storage medium | |
| CN115372841A (en) | Method and device for evaluating thermal runaway risk of lithium ion battery monomer | |
| CN115902625A (en) | Performance prediction method, device, equipment and storage medium of battery system | |
| CN114779109A (en) | Method and device for determining battery health state, electronic equipment and storage medium | |
| CN114879042A (en) | Method and device for predicting partial capacity and discharge capacity of battery cell and electronic equipment | |
| CN115656834A (en) | Battery capacity prediction method and device and electronic equipment | |
| CN114994551A (en) | Method and device for determining residual energy of power battery, electronic equipment and storage medium | |
| CN115291111B (en) | Training method of battery rest time prediction model and rest time prediction method | |
| CN115792628A (en) | Power battery safety evaluation method, device, equipment and storage medium | |
| CN110888100A (en) | Single-phase intelligent electric energy meter online on-load detection system and method | |
| CN117420468A (en) | Battery state evaluation method, device, equipment and storage medium | |
| CN114814602A (en) | SOC measurement system evaluation method, device and system | |
| CN117706390B (en) | Rolling optimization estimation method and device for battery state of charge | |
| CN116819342A (en) | Battery life curve determining method and device, electronic equipment and storage medium | |
| CN116338467A (en) | Lithium battery capacity determining method, device, equipment and storage medium | |
| CN116381538A (en) | Method and device for correcting SOH based on big data platform, electronic equipment and medium | |
| CN116299013A (en) | SOH calibration method and device for energy storage battery system, electronic equipment and medium | |
| CN116559693A (en) | Battery SOC evaluation method and device, electronic equipment and storage medium | |
| CN114966439A (en) | Battery capacity grading test method and device, electronic equipment and storage medium | |
| CN115728656A (en) | Method, device and equipment for carrying out charge-discharge cycle test on battery cell | |
| CN115656858A (en) | Battery life determining method and device, electronic equipment and storage medium |
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 |