CN110515001B - Two-stage battery performance prediction method based on charging and discharging - Google Patents
Two-stage battery performance prediction method based on charging and discharging Download PDFInfo
- Publication number
- CN110515001B CN110515001B CN201910844890.7A CN201910844890A CN110515001B CN 110515001 B CN110515001 B CN 110515001B CN 201910844890 A CN201910844890 A CN 201910844890A CN 110515001 B CN110515001 B CN 110515001B
- Authority
- CN
- China
- Prior art keywords
- voltage
- current
- model
- prediction
- charging
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
- G01R31/3842—Arrangements for monitoring battery or accumulator variables, e.g. SoC combining voltage and current measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
- G01R31/388—Determining ampere-hour charge capacity or SoC involving voltage measurements
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The invention discloses a two-stage battery performance prediction method based on charge and discharge, belonging to the field of battery performance detection, and comprising the following specific steps of: s1: according to the initial condition x of the battery charging and discharging process, giving out an initial recommended current A1 through a model, and judging whether an expected cut-off voltage meets a threshold value, if so, directly using the expected cut-off voltage for an actual battery cell test, and if not, executing a step S2; s2: the method is characterized in that actual tests are carried out to obtain the actual voltage V1 of the recommended current A1 after charging and discharging, the recommended current A2 is given through a model, the expected cut-off voltage meets a threshold value and is used for actual electric core tests, a two-stage battery performance prediction method is designed, a large number of manual test processes are replaced through accurate prediction, an optimal value is automatically found through modeling fitting, the method is not limited to prediction between current and voltage, and can also be used for relation prediction between any two related variables in battery detection, and the operation speed of the whole model algorithm is very high.
Description
Technical Field
The invention relates to the technical field of battery performance detection, in particular to a two-stage battery performance prediction method based on charge and discharge.
Background
Once complete electric vehicle core detection, multi-round charging and discharging tests are often required under various environmental conditions. When the battery is charged and discharged with a specified constant current value, a cut-off voltage is obtained after a certain period of time. In order to stabilize the cutoff voltage at a standard value of a certain country, it is usually necessary to specify an initial current value by manual experience; or when a charge and discharge test is performed at a given initial current under different environments, the cutoff voltage needs to be estimated. The current and voltage values of different cells in different environments are modeled, so that the actual manual test times can be greatly reduced, and the efficiency of battery performance evaluation and detection is improved.
The existing publications such as the flexible evaluation and sorting method for the performance of power batteries with publication number CN109604186A do not have a modeling method for clearly defining the relationship between the variables of some key parameters such as the current and the voltage of the battery in the battery detection, and how to set the initial value of another parameter given the target parameter.
Based on the above, the invention designs a two-stage battery performance prediction method based on charge and discharge to solve the above-mentioned problems.
Disclosure of Invention
The present invention is directed to a two-stage battery performance prediction method based on charging and discharging to solve the problems set forth in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: a two-stage battery performance prediction method based on charge and discharge comprises the following specific steps:
s1: according to the initial condition x of the battery charging and discharging process, giving out an initial recommended current A1 through a voltage prediction current model, judging whether an expected cut-off voltage obtained by the current prediction voltage model meets a threshold value, if so, directly using the expected cut-off voltage for an actual battery cell test, and if not, executing a step S2;
s2: carrying out actual test to obtain the actual voltage of the recommended current A1 after charging and discharging, giving out the recommended current A2 through a voltage prediction current model, if the expected cut-off voltage obtained through the current prediction voltage model meets a threshold value, using the expected cut-off voltage for actual electric core test,
the training method of the current prediction voltage model and the voltage prediction current model comprises the following specific steps:
s100: data extraction: selecting a data record of the complete charging and discharging time from the historical charging and discharging data;
s200: data supplement: for a long-time charge and discharge test, the voltage change of each second can be recorded in the discharge process;
s300: associating data obtained by data extraction and data supplement with battery information, cleaning some obvious abnormalities, and dividing a training set and a test set of a data set;
s400: performing regression prediction by using a regression algorithm, and respectively training a current prediction voltage model and a voltage prediction current model, wherein the two generated regression models are as follows:
v1 ═ f1(x, a1) and a1 ═ g1(x, V1),
wherein f1 is a model for predicting voltage V1 from current, g1 is a model for predicting current a1 from voltage;
s500: difference is made on the data set: comparing positive and negative two items of charging and discharging records of the same battery cell in pairs, comparing a difference value DeltaA of two preset currents, a difference value DeltaV of two cut-off voltages and the percentage percent of current or voltage change, and dividing data again;
s600: respectively training two models, wherein the generated two regression models are as follows:
v2 ═ f2(x, a1, V1, a2, DeltaA,% change in current)
And a2 ═ g2(x, V1, a1, V2, DeltaV,% change in voltage%),
where f2 is a model of the predicted voltage V2 from the previous round current, voltage and current round current, g2 is a model of the predicted current A2 from the previous round voltage, current and current round voltage,
further screening and confirmation are added to the recommended current A1, and the specific method is as follows:
s401: when the target cutoff voltage is specified, an initial current a1 is calculated using model g 1;
s402: an input a1, a predicted voltage v1 is given by using an f1 model;
s403: checking whether v1 satisfies the threshold difference and the number of repeated verifications reaches the upper limit, if yes, proceeding to step S405; otherwise, go to step S404;
s404: the first method is as follows: inputting a1, v1, and obtaining a new current a2 by using a g2 model; input a1, a2 predicts a voltage using the f2 model;
the second method comprises the following steps: using an f1 model, but using a1 as an initial value, searching by taking the absolute difference of front and rear currents as a variable quantity at a certain learning rate, increasing the iteration times, and then entering the step S403;
s405: the prediction results are arranged into a dictionary, the difference value of the prediction voltage and the target voltage is taken as key, and the current and prediction voltage pair is taken as value;
s406: expanding a current and voltage pair list, and finding out a sequence with the longest current and voltage meeting synchronous increase or decrease by using a dynamic programming method;
s407: and (4) selecting the key with the minimum difference between the predicted voltage and the target voltage for the above sequence, and using the corresponding current for first recommendation.
Preferably, the initial condition x includes parameters of a remaining capacity, a temperature, an initial internal resistance, an initial voltage, an initial weight, a charge and discharge time period, a battery capacity, a charge current, and a cut-off voltage.
Preferably, the step S200 further includes supplementing the data set with a discharge duration that occurred in the step S100 during the discharge process.
Preferably, in the step 400, the regression algorithm is one of RF, GBDT, LR or deep neural network regression algorithm.
Compared with the prior art, the invention has the beneficial effects that: by designing a two-stage battery performance prediction method, the accuracy rate in the first prediction is about 85%; the accuracy rate is over 95% in the second prediction; the method is not limited to be used for predicting current and voltage, but also can be used for predicting the relation between any two related variables in battery detection, and the operation speed of the whole model algorithm is very high.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings 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 that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a flow chart of a model training method of the present invention;
fig. 3 is a flow chart of a method for further screening and confirmation based on a1 according to the present invention.
Detailed Description
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.
Referring to fig. 1, the present invention provides a technical solution: a two-stage battery performance prediction method based on charge and discharge comprises the following specific steps:
s1: according to the initial condition x of the battery charging and discharging process, giving out an initial recommended current A1 through a voltage prediction current model, judging whether an expected cut-off voltage obtained by the current prediction voltage model meets a threshold value, if so, directly using the expected cut-off voltage for an actual battery cell test, and if not, executing a step S2;
s2: carrying out actual test to obtain the actual voltage of the recommended current A1 after charging and discharging, giving out the recommended current A2 through a voltage prediction current model, if the expected cut-off voltage obtained through the current prediction voltage model meets a threshold value, using the expected cut-off voltage for actual electric core test,
the initial condition x comprises parameters of residual electricity quantity, temperature, initial internal resistance, initial voltage, initial weight, charging and discharging time, battery capacity, charging current and cut-off voltage.
As shown in fig. 2, the training method of the current prediction voltage model and the voltage prediction current model includes the following specific steps:
s100: data extraction: selecting a data record of the complete charging and discharging time from the historical charging and discharging data;
s200: data supplement: for a long-time charge and discharge test, for example, the discharge time is 180S, the discharge process records the voltage change every second, and the method further includes supplementing the discharge duration, such as data of intermediate states of 30S, 60S and the like, appearing in step S100 in the discharge process to a data set;
s300: associating data obtained by data extraction and data supplement with battery information, cleaning some obvious abnormalities, and dividing a training set and a test set of a data set;
s400: performing regression prediction by using a regression algorithm, and respectively training a current prediction voltage model and a voltage prediction current model, wherein the two generated regression models are as follows:
v1 ═ f1(x, a1) and a1 ═ g1(x, V1),
wherein f1 is a model for predicting voltage V1 from current, g1 is a model for predicting current a1 from voltage;
s500: difference is made on the data set: comparing positive and negative two items of charging and discharging records of the same battery cell in pairs, comparing a difference value DeltaA of two preset currents, a difference value DeltaV of two cut-off voltages and the percentage percent of current or voltage change, and dividing data again;
s600: respectively training two models, wherein the generated two regression models are as follows:
v2 ═ f2(x, a1, V1, a2, DeltaA,% change in current)
And a2 ═ g2(x, V1, a1, V2, DeltaV,% change in voltage%),
where f2 is a model of the predicted voltage V2 from the previous round current, voltage and current round current, g2 is a model of the predicted current A2 from the previous round voltage, current and current round voltage,
referring to fig. 3, referring to fig. 1, for the recommendation of the first-stage current value a1, the current can be directly calculated by using the g1 algorithm obtained in fig. 2, but the invention provides a better method, which does not directly use a1, but further screening and confirmation are carried out on the basis of a1, and the specific method is as follows:
s401: when the target cutoff voltage is specified, an initial current a1 is calculated using model g 1;
s402: an input a1, a predicted voltage v1 is given by using an f1 model;
s403: checking whether v1 satisfies the threshold difference and the number of repeated verifications reaches the upper limit, if yes, proceeding to step S405; otherwise, go to step S404;
s404: the first method is as follows: inputting a1, v1, and obtaining a new current a2 by using a g2 model; input a1, a2 predicts a voltage using the f2 model;
the second method comprises the following steps: using an f1 model, but using a1 as an initial value, using a certain learning rate such as 0.2, and using the absolute difference of the front current and the rear current as a variation to search, increasing the iteration number, and then entering step S403;
s405: the prediction results are arranged into a dictionary, the difference value of the prediction voltage and the target voltage is taken as key, and the current and prediction voltage pair is taken as value;
s406: expanding a current and voltage pair list, and finding out a sequence with the longest current and voltage meeting synchronous increase or decrease by using a dynamic programming method;
s407: and (4) selecting the key with the minimum difference between the predicted voltage and the target voltage for the above sequence, and using the corresponding current for first recommendation.
The specific principle is as follows:
according to the historical charging and discharging data of the lithium battery, the incidence relation between some important parameters, such as whether the current and the voltage have certain correlation under different environments, can be established and predicted. The correlation is modeled with a model, and given an expected cutoff voltage, a suitable initial current is predicted as an input to the charging and discharging process. Considering that the variety of batteries and the environmental factors are greatly changed in practical application, in order to improve the generalization capability, the invention designs a two-stage method: in the first stage, according to an initial condition x, a prediction model is used for giving a recommendation of an initial current A1, the accuracy of the first stage is very high in most cases, and the first stage can be directly used for actual cell testing; if the fluctuation range of the cut-off voltage is met, usually +/-0.05 v, the model is operated once. For the last new battery type, inaccurate recommendation may be made in the first stage, and the actual cut-off voltage V1 can be obtained after the actual charge and discharge test. With the first test it is possible to capture exactly some characteristics of the new battery. The model is used to make a second prediction of the current.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (4)
1. A two-stage battery performance prediction method based on charge and discharge is characterized in that: the method comprises the following specific steps:
s1: according to the initial condition x of the battery charging and discharging process, giving out an initial recommended current A1 through a voltage prediction current model, judging whether an expected cut-off voltage obtained by the current prediction voltage model meets a threshold value, if so, directly using the expected cut-off voltage for an actual battery cell test, and if not, executing a step S2;
s2: carrying out actual test to obtain the actual voltage of the recommended current A1 after charging and discharging, giving out the recommended current A2 through a voltage prediction current model, if the expected cut-off voltage obtained through the current prediction voltage model meets a threshold value, using the expected cut-off voltage for actual electric core test,
the training method of the current prediction voltage model and the voltage prediction current model comprises the following specific steps:
s100: data extraction: selecting a data record of the complete charging and discharging time from the historical charging and discharging data;
s200: data supplement: for a long-time charge and discharge test, the voltage change of each second can be recorded in the discharge process;
s300: associating data obtained by data extraction and data supplement with battery information, cleaning some obvious abnormalities, and dividing a training set and a test set of a data set;
s400: performing regression prediction by using a regression algorithm, and respectively training a current prediction voltage model and a voltage prediction current model, wherein the two generated regression models are as follows:
v1 ═ f1(x, a1) and a1 ═ g1(x, V1),
wherein f1 is a model for predicting voltage V1 from current, g1 is a model for predicting current a1 from voltage;
s500: difference is made on the data set: comparing positive and negative two items of charging and discharging records of the same battery cell in pairs, comparing a difference value DeltaA of two preset currents, a difference value DeltaV of two cut-off voltages and the percentage percent of current or voltage change, and dividing data again;
s600: respectively training two models, wherein the generated two regression models are as follows:
v2 ═ f2(x, a1, V1, a2, DeltaA,% change in current)
And a2 ═ g2(x, V1, a1, V2, DeltaV,% change in voltage%),
where f2 is a model of the predicted voltage V2 from the previous round current, voltage and current round current, g2 is a model of the predicted current A2 from the previous round voltage, current and current round voltage,
further screening and confirmation are added to the recommended current A1, and the specific method is as follows:
s401: when the target cutoff voltage is specified, an initial current a1 is calculated using model g 1;
s402: an input a1, a predicted voltage v1 is given by using an f1 model;
s403: checking whether v1 satisfies the threshold difference and the number of repeated verifications reaches the upper limit, if yes, proceeding to step S405; otherwise, go to step S404;
s404: the first method is as follows: inputting a1, v1, and obtaining a new current a2 by using a g2 model; input a1, a2 predicts a voltage using the f2 model;
the second method comprises the following steps: using an f1 model, but using a1 as an initial value, searching by taking the absolute difference of front and rear currents as a variable quantity at a certain learning rate, increasing the iteration times, and then entering the step S403;
s405: the prediction results are arranged into a dictionary, the difference value of the prediction voltage and the target voltage is taken as key, and the current and prediction voltage pair is taken as value;
s406: expanding a current and voltage pair list, and finding out a sequence with the longest current and voltage meeting synchronous increase or decrease by using a dynamic programming method;
s407: and (4) selecting the key with the minimum difference between the predicted voltage and the target voltage for the above sequence, and using the corresponding current for first recommendation.
2. The method for predicting the performance of the two-stage battery based on the charge and the discharge according to claim 1, wherein the method comprises the following steps: the initial condition x includes parameters of remaining capacity, temperature, initial internal resistance, initial voltage, initial weight, charge and discharge time, battery capacity, charge current, and cut-off voltage.
3. The method for predicting the performance of the two-stage battery based on the charge and the discharge according to claim 1, wherein the method comprises the following steps: the step S200 further includes supplementing the data set with the discharge duration that occurred in the step S100 during the discharge process.
4. The method for predicting the performance of the two-stage battery based on the charge and the discharge according to claim 1, wherein the method comprises the following steps: in step S400, the regression algorithm is one of RF, GBDT, LR, or deep neural network regression algorithms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910844890.7A CN110515001B (en) | 2019-09-07 | 2019-09-07 | Two-stage battery performance prediction method based on charging and discharging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910844890.7A CN110515001B (en) | 2019-09-07 | 2019-09-07 | Two-stage battery performance prediction method based on charging and discharging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110515001A CN110515001A (en) | 2019-11-29 |
| CN110515001B true CN110515001B (en) | 2020-12-29 |
Family
ID=68631423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910844890.7A Active CN110515001B (en) | 2019-09-07 | 2019-09-07 | Two-stage battery performance prediction method based on charging and discharging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110515001B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111413625A (en) * | 2020-04-16 | 2020-07-14 | 创新奇智(上海)科技有限公司 | Method and device for obtaining test current |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5783122B2 (en) * | 2012-04-11 | 2015-09-24 | トヨタ自動車株式会社 | Battery state estimation device |
| CN103645377B (en) * | 2013-12-24 | 2016-02-24 | 山东大学 | Based on the battery nominal power Forecasting Methodology of Dynamic array control algorithm |
| CN105429249B (en) * | 2016-01-19 | 2018-08-24 | 宁德新能源科技有限公司 | Battery control device and the method for controlling battery |
| JP6649814B2 (en) * | 2016-03-09 | 2020-02-19 | プライムアースＥｖエナジー株式会社 | Secondary battery charge rate estimation method, charge rate estimation device, and charge rate estimation program |
| US10670662B2 (en) * | 2017-03-02 | 2020-06-02 | Mediatek Inc. | Method and apparatus for calibrating coulomb counting based state-of-charge estimation |
| CN107024664B (en) * | 2017-04-01 | 2019-04-12 | 湖南银杏数据科技有限公司 | Lithium battery remaining life quick predict method based on constant-current charge segment |
| CN107359376B (en) * | 2017-06-30 | 2020-06-23 | 宁德时代新能源科技股份有限公司 | Battery charging method, device and equipment |
| CN107831441B (en) * | 2017-09-20 | 2019-11-05 | 哈尔滨理工大学 | Prediction technique, forecasting system and a kind of charging unit of lithium battery charging current |
| CN107612075A (en) * | 2017-09-27 | 2018-01-19 | 宁德时代新能源科技股份有限公司 | Battery charging method, device, equipment and storage medium |
| CN108008306A (en) * | 2017-11-09 | 2018-05-08 | 陕西盛迈石油有限公司 | A kind of power battery method for separating |
| CN109683094B (en) * | 2018-12-19 | 2021-05-04 | 武汉新能源研究院有限公司 | Quick sorting method and sorting device for lithium ion batteries |
| CN109655751A (en) * | 2019-02-28 | 2019-04-19 | 哈尔滨理工大学 | A kind of method and system using Gaussian process regression estimates battery charging state |
| CN110137584B (en) * | 2019-03-20 | 2020-12-11 | 北京车和家信息技术有限公司 | Charging voltage threshold determination method and charging strategy determination method |
| CN110154822A (en) * | 2019-05-14 | 2019-08-23 | 中科院合肥技术创新工程院 | A kind of charge/discharge control method applied to electric car Intelligent battery management system |
-
2019
- 2019-09-07 CN CN201910844890.7A patent/CN110515001B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110515001A (en) | 2019-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110568359B (en) | Lithium battery residual life prediction method | |
| CN112380630B (en) | New energy automobile battery thermal runaway risk prediction method based on Internet of vehicles data | |
| JP7095110B2 (en) | Battery status estimation method | |
| CN111366848A (en) | Battery health state prediction method based on PSO-ELM algorithm | |
| JP2013217897A (en) | System for predicting lifetime of battery | |
| CN110082682B (en) | Lithium battery state of charge estimation method | |
| CN113887601A (en) | Retired power battery recombination method based on cluster sorting | |
| CN107340476B (en) | Battery electrical state monitoring system and electrical state monitoring method | |
| CN110673039A (en) | Lithium iron phosphate battery SOC charging online correction method based on big data | |
| CN114114038A (en) | Lithium battery SOC and available capacity joint estimation method under full-life and full-temperature conditions | |
| CN116609686B (en) | Battery cell consistency assessment method based on cloud platform big data | |
| CN114545279B (en) | Lithium battery health state estimation method based on neural network ordinary differential equation | |
| KR20140137181A (en) | System for predicting thickness of battery and method for predicting thickness of battery | |
| CN115754726A (en) | Battery life prediction and maintenance method, electronic equipment and storage medium | |
| CN117330964A (en) | Lithium battery state of charge three-interval fusion estimation method based on fitness value | |
| Sangwan et al. | Estimation of battery parameters of the equivalent circuit models using meta-heuristic techniques | |
| Long et al. | Multi-parameter optimization method for remaining useful life prediction of lithium-ion batteries | |
| CN111983464B (en) | Lithium battery lithium separation testing method based on pure electric vehicle | |
| CN115494400B (en) | Lithium battery lithium separation state online monitoring method based on ensemble learning | |
| CN110515001B (en) | Two-stage battery performance prediction method based on charging and discharging | |
| CN110232432B (en) | Lithium battery pack SOC prediction method based on artificial life model | |
| CN114839537A (en) | Battery state of charge prediction method and device | |
| CN117169743A (en) | Battery health state estimation method and device based on partial data and model fusion | |
| Choi et al. | Artificial Intelligence-based Battery State-of-Health (SoH) Prediction through battery data characteristics analysis | |
| CN113466718B (en) | SOC correction method for mobile phone battery |
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 |