CN117254562B - Battery charging management method, device, equipment and storage medium - Google Patents
Battery charging management method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117254562B CN117254562B CN202311407073.8A CN202311407073A CN117254562B CN 117254562 B CN117254562 B CN 117254562B CN 202311407073 A CN202311407073 A CN 202311407073A CN 117254562 B CN117254562 B CN 117254562B
- Authority
- CN
- China
- Prior art keywords
- battery
- charging
- model
- parameter
- predicted
- 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.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 150
- 238000000034 method Methods 0.000 claims abstract description 65
- 230000002159 abnormal effect Effects 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 61
- 238000013507 mapping Methods 0.000 claims description 34
- 238000012360 testing method Methods 0.000 claims description 22
- 238000012937 correction Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003062 neural network model Methods 0.000 claims description 11
- 230000005856 abnormality Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 230000010287 polarization Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/00032—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries characterised by data exchange
- H02J7/00034—Charger exchanging data with an electronic device, i.e. telephone, whose internal battery is under charge
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
-
- 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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/44—Methods for charging or discharging
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/007—Regulation of charging or discharging current or voltage
- H02J7/00712—Regulation of charging or discharging current or voltage the cycle being controlled or terminated in response to electric parameters
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Manufacturing & Machinery (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The application relates to the technical field of battery charging management, and provides a battery charging management method, device, equipment and storage medium, wherein the method comprises the following steps: determining a first predicted remaining life of the battery based on historical operating information of the battery; controlling charging equipment to charge the battery for a preset time period based on a preset charging voltage, acquiring first charging parameter information of the battery in a charging process, and inputting the first charging parameter information into a preset battery life prediction model to obtain a second predicted residual life of the battery; judging whether the battery is abnormal or not based on the first predicted remaining life and the second predicted remaining life; if the battery is not abnormal, generating a battery charging management model based on the historical working information of the battery and the second predicted remaining life; the method can improve the safety of the battery in the charging process by controlling the charging equipment to charge the battery based on the charging management model.
Description
Technical Field
The present application relates to the field of battery charging management technologies, and in particular, to a method, an apparatus, a device, and a storage medium for battery charging management.
Background
With the continuous development of battery technology, rechargeable batteries are widely used in various industries, such as: mobile devices, electric vehicles, etc. In order to ensure that the battery can stably operate for a long time, it is important to manage the battery during the charging process. The conventional charging management method mainly performs charging control based on preset charging voltage and time, but the actual state of the battery cannot be fully considered, so that potential safety hazards are easily caused in the charging process.
Disclosure of Invention
The application provides a battery charging management method, device, equipment and storage medium, which are used for improving the safety of a battery in a charging process.
In a first aspect, the present application provides a method for managing charging of a battery, including:
Responding to a charging request of a battery, acquiring an identification code of the battery, and acquiring historical working information of the battery and historical working information of an associated battery of the battery based on the identification code; wherein the associated battery is the same as the battery in model number, and the associated battery comprises a plurality of batteries;
determining a first predicted remaining life of the battery based on historical operating information of the battery;
Controlling a charging device to charge the battery for a preset time period based on a preset charging voltage, acquiring first charging parameter information of the battery in a charging process, and inputting the first charging parameter information into a preset battery life prediction model to obtain a second predicted remaining life of the battery;
Judging whether or not there is an abnormality in the battery based on the first predicted remaining life and the second predicted remaining life;
If the battery is not abnormal, generating a charge management model of the battery based on the historical working information of the associated battery and the second predicted remaining life;
And controlling the charging equipment to charge the battery based on the charging management model.
In one possible implementation manner, the first charging parameter information includes an SOC value, and the method for acquiring the SOC value includes:
acquiring an SOC prediction parameter set through a battery parameter testing device;
Acquiring an SOC correlation value based on the predicted parameters and a target SOC predicted parameter-SOC curve graph for each predicted parameter in the SOC predicted parameter set; the target SOC prediction parameter-SOC curve graph is a preset SOC prediction parameter-SOC curve graph corresponding to the prediction parameter, and the SOC correlation value is an SOC value corresponding to the preset SOC prediction parameter-SOC curve graph when the SOC prediction parameter is the prediction parameter;
calculating a product between a weight of the predicted parameter and the SOC-associated value corresponding to the predicted parameter for each predicted parameter in the SOC parameter set;
and acquiring the SOC value based on all the products.
In one possible implementation manner, the training method of the battery life prediction model includes:
Acquiring a training data set, and dividing the training data set into a training set, a testing set and a correction set; the training data set comprises a plurality of mapping relations, wherein the mapping relations are the mapping relations between the residual life of the experimental battery with the same model as the battery and second charging parameter information; the second charging parameter information is charging parameter information obtained after the experimental battery is charged for the preset time period by the charging equipment with the preset charging voltage, and the training set comprises a plurality of training sets;
Constructing a neural network model, and respectively training the neural network model by utilizing a plurality of training sets to obtain a plurality of first intermediate battery life prediction models;
testing a plurality of first intermediate battery life prediction models based on the test set respectively to obtain the prediction accuracy of each first intermediate battery life prediction model;
comparing each prediction accuracy with a preset accuracy, and taking the first intermediate battery life prediction model corresponding to the prediction accuracy as a second intermediate battery life prediction model when the prediction accuracy is not smaller than the preset accuracy;
Fusing the model parameters of each second intermediate battery life prediction model to obtain fused model parameters, and updating the model parameters of any one of the first intermediate battery life prediction models or any one of the second intermediate battery life prediction models based on the fused model parameters to obtain a third intermediate battery life prediction model;
acquiring a weight coefficient of each charging parameter in the second charging parameter information based on the training data set;
optimizing model parameters of the third intermediate battery life prediction model based on all the weight coefficients to obtain a fourth intermediate battery life prediction model;
Respectively inputting each piece of second charging parameter information in the correction set into the fourth intermediate battery life prediction model to obtain a predicted battery remaining life corresponding to each piece of second charging parameter information in the correction set;
Constructing an actual battery remaining life-predicted battery remaining life mapping relation table based on the actual battery remaining life and the predicted battery remaining life corresponding to each piece of second charging parameter information in the correction set;
calculating a predicted loss value of the fourth intermediate battery life prediction model based on the actual battery remaining life-predicted battery remaining life mapping relation table;
And adjusting model parameters of the fourth intermediate battery life prediction model based on the predicted loss value to obtain the battery life prediction model.
In one possible implementation manner, the acquiring, based on the training data set, a weight coefficient of each charging parameter in the second charging parameter information includes:
acquiring a first curve set corresponding to the second charging parameter information aiming at each mapping relation of the training data set; wherein the first set of curves includes a change curve of each of the charging parameters in the second charging parameter information over time within the preset time period;
Clustering and combining the change curves corresponding to the same charging parameter in all the change curves to obtain a plurality of second curve sets; wherein the second curve set is a set of the change curves corresponding to the same charging parameter;
calculating a similarity coefficient of the second curve set for each second curve set;
and assigning a corresponding weight coefficient to each charging parameter based on all the similarity coefficients.
In one possible implementation, the generating the charge management model of the battery based on the historical operating information of the associated battery and the second predicted remaining life includes:
Acquiring an initial charge management model of the battery based on the second predicted remaining life;
Determining a target associated battery based on the initial charge management model and historical operating information of the associated battery; wherein the historical operating information of the target associated battery includes a process of performing charge management on the target associated battery based on the initial charge management model, the target associated battery including a plurality of;
Acquiring third charging parameter information when the target associated battery is subjected to charging management based on the initial charging management model for each target associated battery;
Judging whether potential safety hazards exist in the initial charge management model or not based on all the third charge parameter information;
and if the initial charge management model does not have potential safety hazards, determining the initial charge management model as the charge management model.
In one possible implementation manner, the determining whether the initial charge management model has a potential safety hazard based on all the third charge parameter information includes:
Extracting a first parameter feature and a plurality of second parameter features based on a preset parameter feature extraction model; the first parameter features are parameter features corresponding to preset charging parameter information, the second parameter features are parameter features corresponding to the third charging parameter information, and the preset charging parameter information is charging parameter information matched with the initial charging management model;
Respectively calculating the similarity between the first parameter characteristic and each second parameter characteristic, and comparing each similarity with a preset similarity;
if all the similarities are not smaller than the preset similarity, judging that the initial charge management model has no potential safety hazard;
if any similarity is smaller than the preset similarity, judging that the potential safety hazard exists in the initial charge management model.
In one possible implementation manner, after determining whether the initial charge management model has a potential safety hazard based on all the third charge parameter information, the method further includes:
If the initial charge management model has potential safety hazards, adjusting model parameters of the initial charge management model based on the preset charge parameter information and the target third charge parameter information, and determining the initial charge management model after adjustment as the charge management model; the target third charging parameter information is the third charging parameter information corresponding to the similarity when the similarity is smaller than the preset similarity.
In a second aspect, the present application provides a battery charge management device comprising:
The acquisition module is used for responding to a charging request of the battery, acquiring an identification code of the battery and acquiring historical working information of the battery and historical working information of an associated battery of the battery based on the identification code; wherein the associated battery is the same as the battery in model number, and the associated battery comprises a plurality of batteries;
A determining module for determining a first predicted remaining life of the battery based on the historical operating information;
the first control module is used for controlling the charging equipment to charge the battery for a preset time period based on a preset charging voltage, acquiring first charging parameter information of the battery in a charging process, and inputting the first charging parameter information into a preset battery life prediction model to obtain a second predicted residual life of the battery;
A judging module configured to judge whether or not there is an abnormality in the battery based on the first predicted remaining life and the second predicted remaining life;
The generation module is used for generating a charge management model of the battery based on the historical working information of the associated battery and the second predicted remaining life if the battery is not abnormal;
And the second control module is used for controlling the charging equipment to charge the battery based on the charging management model.
In a third aspect, the present application provides a terminal device comprising a processor, a memory and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements a method of charge management of any one of the batteries as described above.
In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any of the battery charging management methods described above.
The application provides a battery charging management method, a device, equipment and a storage medium. Wherein the method comprises the following steps: responding to a charging request of a battery, acquiring an identification code of the battery, and acquiring historical working information of the battery and historical working information of an associated battery of the battery based on the identification code; wherein the associated battery is the same as the battery in model number, and the associated battery comprises a plurality of batteries; determining a first predicted remaining life of the battery based on historical operating information of the battery; controlling a charging device to charge the battery for a preset time period based on a preset charging voltage, acquiring first charging parameter information of the battery in a charging process, and inputting the first charging parameter information into a preset battery life prediction model to obtain a second predicted remaining life of the battery; judging whether or not there is an abnormality in the battery based on the first predicted remaining life and the second predicted remaining life; if the battery is not abnormal, generating a charge management model of the battery based on the historical working information of the associated battery and the second predicted remaining life; and controlling the charging equipment to charge the battery based on the charging management model. According to the method, the charging management model of the battery can be generated according to the actual state of the battery, so that the safety of the battery in the charging process is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a battery charging management method according to an embodiment of the present application;
Fig. 2 is a schematic block diagram of a battery charging management device according to an embodiment of the present application;
fig. 3 is a schematic block diagram of a structure of a terminal device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
It is also to be understood that the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
With the continuous development of battery technology, rechargeable batteries are widely used in various industries, such as: mobile devices, electric vehicles, etc. In order to ensure that the battery can stably operate for a long time, it is important to manage the battery during the charging process. The conventional charging management method mainly performs charging control based on preset charging voltage and time, but the actual state of the battery cannot be fully considered, so that potential safety hazards are easily caused in the charging process. To this end, the present application provides a battery charge management method, apparatus, device, and storage medium to solve the above-mentioned problems.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for managing battery charging according to an embodiment of the present application, and as shown in fig. 1, the method for managing battery charging according to an embodiment of the present application includes steps S100 to S600.
Step S100, responding to a charging request of a battery, acquiring an identification code of the battery, and acquiring historical working information of the battery and historical working information of an associated battery of the battery based on the identification code; wherein, the type of the associated battery is the same as that of the battery, and the associated battery comprises a plurality of batteries.
Wherein, the history work information at least comprises the charge and discharge cycle times of the battery.
Step S200, determining a first predicted remaining life of the battery based on the historical operation information of the battery.
Step S300, controlling charging equipment to charge the battery for a preset time period based on a preset charging voltage, acquiring first charging parameter information of the battery in a charging process, and inputting the first charging parameter information into a preset battery life prediction model to obtain a second predicted remaining life of the battery.
Wherein the first charging parameter information includes information of a plurality of charging parameters, including but not limited to current information, voltage information, and temperature information.
Step S400, determining whether there is an abnormality in the battery based on the first predicted remaining life and the second predicted remaining life.
Illustratively, step S400 may be implemented by steps S401 through S402.
Step S401, calculating an absolute value of a difference between the first predicted remaining life and the second predicted remaining life, and comparing the absolute value with a preset absolute value.
And step S402, judging that the battery is not abnormal if the absolute value is not larger than the preset absolute value, and judging that the battery is abnormal if the absolute value is larger than the preset absolute value.
It can be appreciated that judging whether or not the battery is abnormal based on the first predicted remaining life and the second predicted remaining life can improve the safety of the battery during charging.
And step S500, if the battery is not abnormal, generating a charge management model of the battery based on the historical working information of the associated battery and the second predicted remaining life.
It can be understood that, based on the historical working information of the battery and the charging management model generated by the second predicted remaining life, on one hand, the suitability of the charging management model and the battery can be improved, the personalized requirement of the battery in the charging process can be met, and on the other hand, the safety of the battery in the charging process can be further improved.
And step S600, controlling the charging equipment to charge the battery based on the charging management model.
The method provided by the embodiment can generate the charge management model for the battery based on the actual state of the battery, so that the safety of the battery in the charging process is improved.
In some embodiments, the first charging parameter information includes an SOC value, and the method for acquiring the SOC value includes steps S301 to S30:
Step S301, obtaining an SOC prediction parameter set through a battery parameter testing device.
The battery parameter testing device may measure all parameter values of the battery during the charging process, including but not limited to a charging current, a charging voltage, a battery temperature, a battery internal resistance, an open circuit voltage, a reactive polarization electromotive force, a concentration polarization electromotive force and an ohmic polarization electromotive force, but not every parameter value is related to the SOC value of the battery among all parameter values measured by the battery parameter testing device, so that it is only necessary to obtain a parameter value related to the SOC value of the battery from all parameter values measured by the battery parameter testing device to form the SOC prediction parameter set, and a parameter value related to the SOC value of the battery may be obtained experimentally.
Step S302, for each prediction parameter in the SOC prediction parameter set, acquiring an SOC related value based on the prediction parameter and a target SOC prediction parameter-SOC curve graph; the target SOC prediction parameter-SOC graph is a preset SOC prediction parameter-SOC graph corresponding to the prediction parameter, and the SOC correlation value is an SOC value corresponding to the SOC prediction parameter when the SOC prediction parameter is the prediction parameter on the preset SOC prediction parameter-SOC graph.
The preset SOC prediction parameter-SOC graph corresponding to each prediction parameter in the SOC prediction parameter set may be obtained through experiments, and it may be understood that the number of the SOC-related values is equal to the number of the prediction parameters in the SOC prediction parameter set, for example, the number of the SOC-related values is two if the SOC prediction parameter set includes a voltage value and a current value, the SOC-related value corresponding to the voltage value is obtained on a voltage-SOC curve for the voltage value, and the SOC-related value corresponding to the current value is obtained on a current-SOC curve for the current value.
Step S303, for each prediction parameter in the SOC parameter set, calculating a product between a weight of the prediction parameter and the SOC-related value corresponding to the prediction parameter.
It is understood that the degree of influence of each prediction parameter in the SOC parameter set on the SOC value of the battery is different, and different weights are given to the prediction parameters based on the degree of influence of each prediction parameter on the SOC value of the battery, and the weight of each prediction parameter can be obtained through experiments.
And step S304, acquiring the SOC value based on all the products.
For example, the SOC value may be obtained by adding all the products.
By adopting the method of the embodiment, the accuracy of the SOC value can be improved, so that the accuracy of the second predicted residual life is improved, and the safety of the battery in the charging process is further improved.
In some embodiments, the method of training the battery life prediction model includes steps S3010 to S3110.
Step S3010, acquiring a training data set, and dividing the training data set into a training set, a testing set and a correction set; the training data set comprises a plurality of mapping relations, wherein the mapping relations are the mapping relations between the residual life of the experimental battery with the same model as the battery and second charging parameter information; the second charging parameter information is obtained after the experimental battery is charged for the preset time period by the charging equipment with the preset charging voltage, and the training set comprises a plurality of training sets.
Wherein the second charging parameter information includes information of a plurality of charging parameters, the second charging parameter information includes but is not limited to current information, voltage information and temperature information, and it is understood that the first charging parameter information and the second charging parameter information include the same kind of charging parameters.
Step S3020, constructing a neural network model, and training the neural network model by using a plurality of training sets, respectively, to obtain a plurality of first intermediate battery life prediction models.
Step S3030, testing the plurality of first intermediate battery life prediction models based on the test set, so as to obtain the prediction accuracy of each first intermediate battery life prediction model.
Step S3040, comparing each prediction accuracy with a preset accuracy, and when the prediction accuracy is not less than the preset accuracy, using the first intermediate battery life prediction model corresponding to the prediction accuracy as a second intermediate battery life prediction model.
Step S3050, fusing model parameters of each second intermediate battery life prediction model to obtain fused model parameters, and updating model parameters of any one of the first intermediate battery life prediction models or any one of the second intermediate battery life prediction models based on the fused model parameters to obtain a third intermediate battery life prediction model.
Step S3060, acquiring a weight coefficient of each charging parameter in the second charging parameter information based on the training data set.
And step S3070, optimizing model parameters of the third intermediate battery life prediction model based on all the weight coefficients to obtain a fourth intermediate battery life prediction model.
For example, a specific method for optimizing the model parameters of the third intermediate battery life prediction model based on all the weight coefficients may be to find, for each charging parameter, a unit corresponding to the charging parameter in the third intermediate battery life prediction model, and multiply the weight coefficient corresponding to the charging parameter by the unit corresponding to the charging parameter.
For example, the third intermediate battery life prediction model is shown in formula (1).
Y+λZ +++(1)
Where L represents the remaining life of the battery and X, Y, Z represents different charging parameters, respectively.
And (2) obtaining that the weight coefficient of X is 0.3, the weight coefficient of Y is 0.2 and the weight coefficient of Z is 0.5 through the step S3006, wherein the fourth intermediate battery life prediction model is shown in the formula (2).
Y+0.5λZ ++ 0.2+(2)
Step S3080, respectively inputting each piece of second charging parameter information in the correction set into the fourth intermediate battery life prediction model, to obtain a predicted remaining battery life corresponding to each piece of second charging parameter information in the correction set.
Step S3090, an actual battery remaining life-predicted battery remaining life mapping relation table is constructed based on the actual battery remaining life and the predicted battery remaining life corresponding to each piece of the second charging parameter information in the correction set.
Step S3100, calculating a predicted loss value of the fourth intermediate battery life prediction model based on the actual battery life remaining-predicted battery life remaining mapping relation table.
And step 3110, adjusting model parameters of the fourth intermediate battery life prediction model based on the predicted loss value to obtain the battery life prediction model.
By adopting the method of the embodiment, the training effect of the battery life prediction model can be improved, so that the prediction accuracy of the battery life prediction model is improved, and the safety of the battery in the charging process is further improved.
In some embodiments, the acquiring the weight coefficient of each charging parameter in the second charging parameter information based on the training data set includes step S3061 to step S3064.
Step 3061, obtaining a first curve set corresponding to the second charging parameter information according to each mapping relation of the training data set; wherein the first set of curves includes a change curve of each of the charging parameters in the second charging parameter information over time within the preset time period.
It may be understood that each of the mapping relationships corresponds to one of the first curve sets, and for each of the mapping relationships, the first curve set is a curve set obtained by drawing a time-dependent change curve of each of the charging parameters according to the second charging parameter information corresponding to the mapping relationship.
Step 3062, clustering and combining the change curves corresponding to the same charging parameter in all the change curves to obtain a plurality of second curve sets; the second curve set is a set of the change curves corresponding to the same charging parameter.
It may be appreciated that the number of the second curve sets is the same as the number of the types of the charging parameters in the second charging parameter information, for example, the second charging parameter information includes voltage information, current information and temperature information, and then the number of the second curve sets is 3, which are the second curve sets corresponding to the voltage information, the second curve sets corresponding to the current information and the second curve sets corresponding to the temperature information, respectively, and the number of the curves in the second curve sets is the same as the number of the mapping relations in the training data set, for example, the training data set includes 200 mapping relations, and then each second curve set includes 200 curves.
Step S3063, calculating a similarity coefficient of the second curve set for each of the second curve sets.
Illustratively, the calculating the similarity coefficient of the second curve set may be performed through steps S11 to S12.
Step S11, calculating the similarity between each curve in the second curve set and each curve except the curve respectively.
Step S12, calculating the average of the sum of all the similarities, and taking the average as a similarity coefficient of the second curve set.
And step 3064, assigning a corresponding weight coefficient to each charging parameter based on all the similarity coefficients.
It can be understood that the smaller the similarity coefficient of the second curve set, the greater the influence degree of the charging parameter corresponding to the second curve set on the remaining life of the battery is, and the greater the weight coefficient of the charging parameter corresponding to the second curve set is.
Illustratively, the assigning of the respective weight coefficient to each of the charging parameters based on all the similarity coefficients may be achieved through steps S21 to S23.
Step S21, calculating a difference between the similarity coefficient and the number "1" for the similarity coefficient corresponding to each of the second curve sets.
Step S22, calculating the sum of all the differences.
Step S23, calculating a ratio between the difference value corresponding to each second curve set and the sum of all the difference values, and regarding each second curve set, using the ratio corresponding to the second curve set as a weight coefficient of the charging parameter corresponding to the second curve set.
For example, the curve set includes the second curve set corresponding to voltage information, the second curve set corresponding to current information, and the second curve set corresponding to temperature information, where a similarity coefficient of the second curve set corresponding to voltage information is 0.8, a similarity coefficient of the second curve set corresponding to current information is 0.6, a similarity coefficient of the second curve set corresponding to temperature information is 0.4, the difference value of the second curve set corresponding to voltage information is 0.2, the difference value of the second curve set corresponding to current information is 0.4, the difference value of the second curve set corresponding to temperature information is 0.6, a weight coefficient of the second curve set corresponding to voltage information is 0.2/(0.2+0.4+0.6) =0.17, a weight coefficient of the second curve set corresponding to current information is 0.4/(0.2+0.4+0.6) =0.33, and the weight coefficient of the second curve set corresponding to current information is 0.2/(0.2+0.6) =0.33.
By adopting the method of the embodiment, the influence degree of each charging parameter in the second charging parameter information on the residual life of the battery can be accurately analyzed, so that corresponding weight can be more accurately given to each charging parameter, and the prediction accuracy of the battery life prediction model is improved.
In some embodiments, the generating a charge management model of the battery based on the historical operating information of the associated battery and the second predicted remaining life includes steps S510 to S550.
Step S510, obtaining an initial charge management model of the battery based on the second predicted remaining life.
It will be appreciated that when there is no abnormality in the battery, a different initial charge management model is set in the database for a different second predicted remaining life.
Step S520, determining a target associated battery based on the initial charge management model and the historical operation information of the associated battery; the historical working information of the target associated battery comprises a process of carrying out charging management on the target associated battery based on the initial charging management model, and the target associated battery comprises a plurality of target associated batteries.
Step S530, for each target associated battery, obtaining third charging parameter information when the target associated battery is charged and managed based on the initial charging management model.
It is understood that the third charging parameter information is charging parameter information of the entire process when the target associated battery is charged and managed based on the initial charging management model.
And step S540, judging whether potential safety hazards exist in the initial charge management model or not based on all the third charge parameter information.
Step S550, if the initial charge management model does not have potential safety hazards, determining the initial charge management model as the charge management model.
According to the method provided by the embodiment, whether the initial charge management model has potential safety hazards or not is judged through the third charge parameter information of the target associated battery, so that the rigor of the charge management method of the battery is improved, the charging process of the battery is more accurately managed, and the safety of the battery in the charging process is further improved.
In some embodiments, the determining whether the initial charge management model has a safety hazard based on all the third charge parameter information includes steps S541 to S544.
Step S541, extracting a first parameter feature and a plurality of second parameter features based on a preset parameter feature extraction model; the first parameter features are parameter features corresponding to preset charging parameter information, the second parameter features are parameter features corresponding to the third charging parameter information, and the preset charging parameter information is charging parameter information matched with the initial charging management model.
The parameter feature extraction model is obtained through training of a neural network model, and understandably, the preset charging parameter information is standard reference charging parameter information of the third charging parameter information.
Step S542, calculating the similarity between the first parameter feature and each of the second parameter features, and comparing each of the similarities with a preset similarity.
And S543, if all the similarities are not smaller than the preset similarity, judging that the initial charge management model has no potential safety hazard.
Step S544, if any one of the similarities is smaller than the preset similarity, determining that the initial charge management model has a potential safety hazard.
According to the embodiment of the application, by judging that the initial charge management model has no potential safety hazard when all the similarities are not smaller than the preset similarity and judging that the initial charge management model has potential safety hazard when any one of the similarities is smaller than the preset similarity, whether the initial charge management model has potential safety hazard can be strictly judged, so that the safety of the battery in the charging process is further improved.
In some embodiments, after determining whether the initial charge management model has a potential safety hazard based on all of the third charge parameter information, the method further comprises:
If the initial charge management model has potential safety hazards, adjusting model parameters of the initial charge management model based on the preset charge parameter information and the target third charge parameter information, and determining the initial charge management model after adjustment as the charge management model; the target third charging parameter information is the third charging parameter information corresponding to the similarity when the similarity is smaller than the preset similarity.
The adjusting the model parameters of the initial charge management model based on the preset charge parameter information and the target third charge parameter information means adjusting the model parameters of the initial charge management model according to difference information between the preset charge parameter information and the target third charge parameter information, so that the adjusted initial charge management model has higher safety, if the target third charge parameter information comprises a plurality of pieces, for each target third charge parameter information, the difference information between the target charge parameter information and the preset charge parameter information is analyzed, the difference information corresponding to each target third charge parameter information is fused with each other, fusion difference information is obtained, and the model parameters of the initial charge management model are adjusted based on the fusion difference information.
Referring to fig. 2, fig. 2 is a schematic block diagram illustrating a structure of a battery charging management device 100 according to an embodiment of the present application, and as shown in fig. 2, the battery charging management device 100 according to an embodiment of the present application includes:
An obtaining module 110, configured to respond to a charging request of a battery, obtain an identification code of the battery, and obtain historical working information of the battery and historical working information of an associated battery of the battery based on the identification code; wherein, the type of the associated battery is the same as that of the battery, and the associated battery comprises a plurality of batteries.
A determination module 120 is configured to determine a first predicted remaining life of the battery based on the historical operating information.
The first control module 130 is configured to control the charging device to charge the battery for a preset period of time based on a preset charging voltage, obtain first charging parameter information of the battery during the charging process, and input the first charging parameter information into a preset battery life prediction model to obtain a second predicted remaining life of the battery.
A determination module 140 for determining whether the battery is abnormal based on the first predicted remaining life and the second predicted remaining life.
And a generating module 150, configured to generate a charge management model of the battery based on the historical operating information of the associated battery and the second predicted remaining life if the battery is not abnormal.
And a second control module 160 for controlling the charging device to charge the battery based on the charge management model.
It should be noted that, for convenience and brevity of description, specific working processes of the above-described apparatus and each module and unit may refer to corresponding processes in the foregoing embodiments of the battery charging management method, and will not be described in detail herein.
The battery charge management device 100 provided in the above-described embodiment may be implemented in the form of a computer program that can be run on the terminal apparatus 200 as shown in fig. 3.
Referring to fig. 3, fig. 3 is a schematic block diagram of a structure of a terminal device 200 according to an embodiment of the present application, where the terminal device 200 includes a processor 201 and a memory 202, and the processor 201 and the memory 202 are connected through a system bus 203, and the memory 202 may include a nonvolatile storage medium and an internal memory.
The non-volatile storage medium may store a computer program. The computer program comprises program instructions which, when executed by the processor 201, cause the processor 201 to perform any of the battery charging management methods described above.
The processor 201 is used to provide computing and control capabilities supporting the operation of the overall terminal device 200.
The internal memory provides an environment for the execution of a computer program in a non-volatile storage medium that, when executed by the processor 201, causes the processor 201 to perform any of the battery charging management methods described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 3 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation of the terminal device 200 related to the present application, and that a specific terminal device 200 may include more or less components than those shown in the drawings, or may combine some components, or have a different arrangement of components.
It should be appreciated that the Processor 201 may be a central processing unit (Central Processing Unit, CPU), and the Processor 201 may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application SPECIFIC INTEGRATED Circuits (ASICs), field-Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In some embodiments, the processor 201 is configured to execute a computer program stored in the memory to implement the following steps:
Responding to a charging request of a battery, acquiring an identification code of the battery, and acquiring historical working information of the battery and historical working information of an associated battery of the battery based on the identification code; wherein the associated battery is the same as the battery in model number, and the associated battery comprises a plurality of batteries;
determining a first predicted remaining life of the battery based on historical operating information of the battery;
Controlling a charging device to charge the battery for a preset time period based on a preset charging voltage, acquiring first charging parameter information of the battery in a charging process, and inputting the first charging parameter information into a preset battery life prediction model to obtain a second predicted remaining life of the battery;
Judging whether or not there is an abnormality in the battery based on the first predicted remaining life and the second predicted remaining life;
If the battery is not abnormal, generating a charge management model of the battery based on the historical working information of the associated battery and the second predicted remaining life;
And controlling the charging equipment to charge the battery based on the charging management model.
In some embodiments, the first charging parameter information includes an SOC value, and when the SOC value is obtained, the processor 201 is configured to implement:
acquiring an SOC prediction parameter set through a battery parameter testing device;
Acquiring an SOC correlation value based on the predicted parameters and a target SOC predicted parameter-SOC curve graph for each predicted parameter in the SOC predicted parameter set; the target SOC prediction parameter-SOC curve graph is a preset SOC prediction parameter-SOC curve graph corresponding to the prediction parameter, and the SOC correlation value is an SOC value corresponding to the preset SOC prediction parameter-SOC curve graph when the SOC prediction parameter is the prediction parameter;
calculating a product between a weight of the predicted parameter and the SOC-associated value corresponding to the predicted parameter for each predicted parameter in the SOC parameter set;
and acquiring the SOC value based on all the products.
In some embodiments, the processor 201 is further configured to implement:
Acquiring a training data set, and dividing the training data set into a training set, a testing set and a correction set; the training data set comprises a plurality of mapping relations, wherein the mapping relations are the mapping relations between the residual life of the experimental battery with the same model as the battery and second charging parameter information; the second charging parameter information is charging parameter information obtained after the experimental battery is charged for the preset time period by the charging equipment with the preset charging voltage, and the training set comprises a plurality of training sets;
Constructing a neural network model, and respectively training the neural network model by utilizing a plurality of training sets to obtain a plurality of first intermediate battery life prediction models;
testing a plurality of first intermediate battery life prediction models based on the test set respectively to obtain the prediction accuracy of each first intermediate battery life prediction model;
comparing each prediction accuracy with a preset accuracy, and taking the first intermediate battery life prediction model corresponding to the prediction accuracy as a second intermediate battery life prediction model when the prediction accuracy is not smaller than the preset accuracy;
Fusing the model parameters of each second intermediate battery life prediction model to obtain fused model parameters, and updating the model parameters of any one of the first intermediate battery life prediction models or any one of the second intermediate battery life prediction models based on the fused model parameters to obtain a third intermediate battery life prediction model;
acquiring a weight coefficient of each charging parameter in the second charging parameter information based on the training data set;
optimizing model parameters of the third intermediate battery life prediction model based on all the weight coefficients to obtain a fourth intermediate battery life prediction model;
Respectively inputting each piece of second charging parameter information in the correction set into the fourth intermediate battery life prediction model to obtain a predicted battery remaining life corresponding to each piece of second charging parameter information in the correction set;
Constructing an actual battery remaining life-predicted battery remaining life mapping relation table based on the actual battery remaining life and the predicted battery remaining life corresponding to each piece of second charging parameter information in the correction set;
calculating a predicted loss value of the fourth intermediate battery life prediction model based on the actual battery remaining life-predicted battery remaining life mapping relation table;
And adjusting model parameters of the fourth intermediate battery life prediction model based on the predicted loss value to obtain the battery life prediction model.
In some embodiments, when implementing the acquiring the weight coefficient of each charging parameter in the second charging parameter information based on the training data set, the processor 201 is configured to implement:
acquiring a first curve set corresponding to the second charging parameter information aiming at each mapping relation of the training data set; wherein the first set of curves includes a change curve of each of the charging parameters in the second charging parameter information over time within the preset time period;
Clustering and combining the change curves corresponding to the same charging parameter in all the change curves to obtain a plurality of second curve sets; wherein the second curve set is a set of the change curves corresponding to the same charging parameter;
calculating a similarity coefficient of the second curve set for each second curve set;
and assigning a corresponding weight coefficient to each charging parameter based on all the similarity coefficients.
In some embodiments, the processor 201, when implementing the generating a charge management model for the battery based on the historical operating information of the associated battery and the second predicted remaining life, is configured to implement:
Acquiring an initial charge management model of the battery based on the second predicted remaining life;
Determining a target associated battery based on the initial charge management model and historical operating information of the associated battery; wherein the historical operating information of the target associated battery includes a process of performing charge management on the target associated battery based on the initial charge management model, the target associated battery including a plurality of;
Acquiring third charging parameter information when the target associated battery is subjected to charging management based on the initial charging management model for each target associated battery;
Judging whether potential safety hazards exist in the initial charge management model or not based on all the third charge parameter information;
and if the initial charge management model does not have potential safety hazards, determining the initial charge management model as the charge management model.
In some embodiments, when implementing the determining whether the initial charge management model has a safety hazard based on all the third charge parameter information, the processor 201 is configured to implement:
Extracting a first parameter feature and a plurality of second parameter features based on a preset parameter feature extraction model; the first parameter features are parameter features corresponding to preset charging parameter information, the second parameter features are parameter features corresponding to the third charging parameter information, and the preset charging parameter information is charging parameter information matched with the initial charging management model;
Respectively calculating the similarity between the first parameter characteristic and each second parameter characteristic, and comparing each similarity with a preset similarity;
if all the similarities are not smaller than the preset similarity, judging that the initial charge management model has no potential safety hazard;
if any similarity is smaller than the preset similarity, judging that the potential safety hazard exists in the initial charge management model.
In some embodiments, after implementing the determining whether the initial charge management model has a potential safety hazard based on all the third charge parameter information, the processor 201 is further configured to implement:
If the initial charge management model has potential safety hazards, adjusting model parameters of the initial charge management model based on the preset charge parameter information and the target third charge parameter information, and determining the initial charge management model after adjustment as the charge management model; the target third charging parameter information is the third charging parameter information corresponding to the similarity when the similarity is smaller than the preset similarity.
It should be noted that, for convenience and brevity of description, specific operation of the terminal apparatus 200 described above may refer to the corresponding procedure of the battery charging management method described above, and will not be described herein.
Embodiments of the present application also provide a computer-readable storage medium storing a computer program that, when executed by one or more processors, causes the one or more processors to implement a method for managing charging of a battery as provided by the embodiments of the present application.
The computer readable storage medium may be an internal storage unit of the terminal device 200 of the foregoing embodiment, for example, a hard disk or a memory of the terminal device 200. The computer readable storage medium may also be an external storage device of the terminal device 200, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like, which the terminal device 200 is equipped with.
While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (8)
1. A method of managing charging of a battery, comprising:
Responding to a charging request of a battery, acquiring an identification code of the battery, and acquiring historical working information of the battery and historical working information of an associated battery of the battery based on the identification code; wherein the associated battery is the same as the battery in model number, and the associated battery comprises a plurality of batteries;
determining a first predicted remaining life of the battery based on historical operating information of the battery;
Controlling a charging device to charge the battery for a preset time period based on a preset charging voltage, acquiring first charging parameter information of the battery in a charging process, and inputting the first charging parameter information into a preset battery life prediction model to obtain a second predicted remaining life of the battery;
Judging whether or not there is an abnormality in the battery based on the first predicted remaining life and the second predicted remaining life;
If the battery is not abnormal, generating a charge management model of the battery based on the historical working information of the associated battery and the second predicted remaining life;
controlling the charging device to charge the battery based on the charging management model;
The training method of the battery life prediction model comprises the following steps:
Acquiring a training data set, and dividing the training data set into a training set, a testing set and a correction set; the training data set comprises a plurality of mapping relations, wherein the mapping relations are the mapping relations between the residual life of the experimental battery with the same model as the battery and second charging parameter information; the second charging parameter information is charging parameter information obtained after the experimental battery is charged for the preset time period by the charging equipment with the preset charging voltage, and the training set comprises a plurality of training sets;
Constructing a neural network model, and respectively training the neural network model by utilizing a plurality of training sets to obtain a plurality of first intermediate battery life prediction models;
testing a plurality of first intermediate battery life prediction models based on the test set respectively to obtain the prediction accuracy of each first intermediate battery life prediction model;
comparing each prediction accuracy with a preset accuracy, and taking the first intermediate battery life prediction model corresponding to the prediction accuracy as a second intermediate battery life prediction model when the prediction accuracy is not smaller than the preset accuracy;
Fusing the model parameters of each second intermediate battery life prediction model to obtain fused model parameters, and updating the model parameters of any one of the first intermediate battery life prediction models or any one of the second intermediate battery life prediction models based on the fused model parameters to obtain a third intermediate battery life prediction model;
acquiring a weight coefficient of each charging parameter in the second charging parameter information based on the training data set;
optimizing model parameters of the third intermediate battery life prediction model based on all the weight coefficients to obtain a fourth intermediate battery life prediction model;
Respectively inputting each piece of second charging parameter information in the correction set into the fourth intermediate battery life prediction model to obtain a predicted battery remaining life corresponding to each piece of second charging parameter information in the correction set;
Constructing an actual battery remaining life-predicted battery remaining life mapping relation table based on the actual battery remaining life and the predicted battery remaining life corresponding to each piece of second charging parameter information in the correction set;
calculating a predicted loss value of the fourth intermediate battery life prediction model based on the actual battery remaining life-predicted battery remaining life mapping relation table;
Adjusting model parameters of the fourth intermediate battery life prediction model based on the predicted loss value to obtain the battery life prediction model;
The generating a charge management model for the battery based on the historical operating information of the associated battery and the second predicted remaining life comprises:
Acquiring an initial charge management model of the battery based on the second predicted remaining life;
Determining a target associated battery based on the initial charge management model and historical operating information of the associated battery; wherein the historical operating information of the target associated battery includes a process of performing charge management on the target associated battery based on the initial charge management model, the target associated battery including a plurality of;
Acquiring third charging parameter information when the target associated battery is subjected to charging management based on the initial charging management model for each target associated battery;
Judging whether potential safety hazards exist in the initial charge management model or not based on all the third charge parameter information;
and if the initial charge management model does not have potential safety hazards, determining the initial charge management model as the charge management model.
2. The charge management method of a battery according to claim 1, wherein the first charge parameter information includes an SOC value, and the acquiring method of the SOC value includes:
acquiring an SOC prediction parameter set through a battery parameter testing device;
Acquiring an SOC correlation value based on the predicted parameters and a target SOC predicted parameter-SOC curve graph for each predicted parameter in the SOC predicted parameter set; the target SOC prediction parameter-SOC curve graph is a preset SOC prediction parameter-SOC curve graph corresponding to the prediction parameter, and the SOC correlation value is an SOC value corresponding to the preset SOC prediction parameter-SOC curve graph when the SOC prediction parameter is the prediction parameter;
calculating a product between a weight of the predicted parameter and the SOC-associated value corresponding to the predicted parameter for each predicted parameter in the SOC-predicted parameter set;
and acquiring the SOC value based on all the products.
3. The method according to claim 2, wherein the acquiring the weight coefficient of each charging parameter in the second charging parameter information based on the training data set includes:
acquiring a first curve set corresponding to the second charging parameter information aiming at each mapping relation of the training data set; wherein the first set of curves includes a change curve of each of the charging parameters in the second charging parameter information over time within the preset time period;
Clustering and combining the change curves corresponding to the same charging parameter in all the change curves to obtain a plurality of second curve sets; wherein the second curve set is a set of the change curves corresponding to the same charging parameter;
calculating a similarity coefficient of the second curve set for each second curve set;
and assigning a corresponding weight coefficient to each charging parameter based on all the similarity coefficients.
4. The method according to claim 1, wherein the determining whether the initial charge management model has a potential safety hazard based on all the third charge parameter information includes:
Extracting a first parameter feature and a plurality of second parameter features based on a preset parameter feature extraction model; the first parameter features are parameter features corresponding to preset charging parameter information, the second parameter features are parameter features corresponding to the third charging parameter information, and the preset charging parameter information is charging parameter information matched with the initial charging management model;
Respectively calculating the similarity between the first parameter characteristic and each second parameter characteristic, and comparing each similarity with a preset similarity;
if all the similarities are not smaller than the preset similarity, judging that the initial charge management model has no potential safety hazard;
if any similarity is smaller than the preset similarity, judging that the potential safety hazard exists in the initial charge management model.
5. The method according to claim 4, wherein after judging whether or not the initial charge management model has a potential safety hazard based on all the third charge parameter information, the method further comprises:
If the initial charge management model has potential safety hazards, adjusting model parameters of the initial charge management model based on the preset charge parameter information and the target third charge parameter information, and determining the initial charge management model after adjustment as the charge management model; the target third charging parameter information is the third charging parameter information corresponding to the similarity when the similarity is smaller than the preset similarity.
6. A battery charge management device, comprising:
The acquisition module is used for responding to a charging request of the battery, acquiring an identification code of the battery and acquiring historical working information of the battery and historical working information of an associated battery of the battery based on the identification code; wherein the associated battery is the same as the battery in model number, and the associated battery comprises a plurality of batteries;
A determining module for determining a first predicted remaining life of the battery based on the historical operating information;
the first control module is used for controlling the charging equipment to charge the battery for a preset time period based on a preset charging voltage, acquiring first charging parameter information of the battery in a charging process, and inputting the first charging parameter information into a preset battery life prediction model to obtain a second predicted residual life of the battery;
A judging module configured to judge whether or not there is an abnormality in the battery based on the first predicted remaining life and the second predicted remaining life;
The generation module is used for generating a charge management model of the battery based on the historical working information of the associated battery and the second predicted remaining life if the battery is not abnormal;
A second control module for controlling the charging device to charge the battery based on the charge management model;
The training method of the battery life prediction model comprises the following steps:
Acquiring a training data set, and dividing the training data set into a training set, a testing set and a correction set; the training data set comprises a plurality of mapping relations, wherein the mapping relations are the mapping relations between the residual life of the experimental battery with the same model as the battery and second charging parameter information; the second charging parameter information is charging parameter information obtained after the experimental battery is charged for the preset time period by the charging equipment with the preset charging voltage, and the training set comprises a plurality of training sets;
Constructing a neural network model, and respectively training the neural network model by utilizing a plurality of training sets to obtain a plurality of first intermediate battery life prediction models;
testing a plurality of first intermediate battery life prediction models based on the test set respectively to obtain the prediction accuracy of each first intermediate battery life prediction model;
comparing each prediction accuracy with a preset accuracy, and taking the first intermediate battery life prediction model corresponding to the prediction accuracy as a second intermediate battery life prediction model when the prediction accuracy is not smaller than the preset accuracy;
Fusing the model parameters of each second intermediate battery life prediction model to obtain fused model parameters, and updating the model parameters of any one of the first intermediate battery life prediction models or any one of the second intermediate battery life prediction models based on the fused model parameters to obtain a third intermediate battery life prediction model;
acquiring a weight coefficient of each charging parameter in the second charging parameter information based on the training data set;
optimizing model parameters of the third intermediate battery life prediction model based on all the weight coefficients to obtain a fourth intermediate battery life prediction model;
Respectively inputting each piece of second charging parameter information in the correction set into the fourth intermediate battery life prediction model to obtain a predicted battery remaining life corresponding to each piece of second charging parameter information in the correction set;
Constructing an actual battery remaining life-predicted battery remaining life mapping relation table based on the actual battery remaining life and the predicted battery remaining life corresponding to each piece of second charging parameter information in the correction set;
calculating a predicted loss value of the fourth intermediate battery life prediction model based on the actual battery remaining life-predicted battery remaining life mapping relation table;
Adjusting model parameters of the fourth intermediate battery life prediction model based on the predicted loss value to obtain the battery life prediction model;
The generating a charge management model for the battery based on the historical operating information of the associated battery and the second predicted remaining life comprises:
Acquiring an initial charge management model of the battery based on the second predicted remaining life;
Determining a target associated battery based on the initial charge management model and historical operating information of the associated battery; wherein the historical operating information of the target associated battery includes a process of performing charge management on the target associated battery based on the initial charge management model, the target associated battery including a plurality of;
Acquiring third charging parameter information when the target associated battery is subjected to charging management based on the initial charging management model for each target associated battery;
Judging whether potential safety hazards exist in the initial charge management model or not based on all the third charge parameter information;
and if the initial charge management model does not have potential safety hazards, determining the initial charge management model as the charge management model.
7. A terminal device comprising a processor, a memory and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the method of charging management of a battery according to any one of claims 1 to 5.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program, wherein the computer program, when executed by a processor, implements the battery charge management method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311407073.8A CN117254562B (en) | 2023-10-27 | 2023-10-27 | Battery charging management method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311407073.8A CN117254562B (en) | 2023-10-27 | 2023-10-27 | Battery charging management method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117254562A CN117254562A (en) | 2023-12-19 |
| CN117254562B true CN117254562B (en) | 2024-07-16 |
Family
ID=89127732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311407073.8A Active CN117254562B (en) | 2023-10-27 | 2023-10-27 | Battery charging management method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117254562B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115236526A (en) * | 2022-04-22 | 2022-10-25 | 长城汽车股份有限公司 | Method and device for predicting residual charging time, storage medium and vehicle |
| CN116819346A (en) * | 2023-08-29 | 2023-09-29 | 深圳凌奈智控有限公司 | Battery SOC estimation method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7182476B2 (en) * | 2019-01-21 | 2022-12-02 | 株式会社日立製作所 | Remaining life diagnostic method and remaining life diagnostic system for secondary battery module |
-
2023
- 2023-10-27 CN CN202311407073.8A patent/CN117254562B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115236526A (en) * | 2022-04-22 | 2022-10-25 | 长城汽车股份有限公司 | Method and device for predicting residual charging time, storage medium and vehicle |
| CN116819346A (en) * | 2023-08-29 | 2023-09-29 | 深圳凌奈智控有限公司 | Battery SOC estimation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117254562A (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3264562B1 (en) | Method for determining an estimated combined battery state-parameter vector | |
| US7965059B2 (en) | System, method, and article of manufacture for determining an estimated battery parameter vector | |
| TWI521360B (en) | Metrology sampling method and computer program product thereof | |
| US20160231386A1 (en) | Method and apparatus for estimating state of battery | |
| US8412658B2 (en) | System and method for estimating long term characteristics of battery | |
| US20110191278A1 (en) | System and method for estimating long term characteristics of battery | |
| EP3526851B1 (en) | Battery model and control application calibration systems and methods | |
| White et al. | Methodological tools | |
| CN116819346B (en) | Battery SOC estimation method, device, equipment and storage medium | |
| JP6421411B2 (en) | Estimation program for estimating battery charging rate, estimation method for estimating battery charging rate, and estimation device for estimating battery charging rate | |
| US20240012054A1 (en) | Technique for estimation of internal battery temperature | |
| Lin et al. | Reliability prediction of battery management system for electric vehicles based on accelerated degradation test: A semi-parametric approach | |
| CN115047349A (en) | Method and device for evaluating consistency state of battery pack, electronic equipment and storage medium | |
| Man et al. | Remaining useful life prediction for hard failures using joint model with extended hazard | |
| CN117254562B (en) | Battery charging management method, device, equipment and storage medium | |
| Zhan et al. | Application of adaptive extended Kalman algorithm based on strong tracking fading factor in Stat-of-Charge estimation of lithium-ion battery | |
| CN111665443A (en) | Fitting method and device of battery performance formula, storage medium and computer equipment | |
| EP4293373A1 (en) | Method and apparatus with battery short detection | |
| US20210326755A1 (en) | Learning model creation device, material property prediction device, and learning model creation method and program | |
| CN115840864A (en) | Method and device for operating a technical system | |
| CN115015786A (en) | Power battery state of charge determining method and device and electronic equipment | |
| Liao et al. | Supplier selection based on normal process yield: the Bayesian inference | |
| Radaš et al. | A Method for Estimating the State of Charge and Identifying the Type of a Lithium-Ion Cell Based on the Transfer Function of the Cell | |
| Gubarev et al. | Classification measurements: methods and implementation | |
| CN115219916A (en) | Battery temperature rise condition detection method and device and electronic equipment |
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 |