CN113884905A - Power battery state of charge estimation method and system based on deep learning - Google Patents
Power battery state of charge estimation method and system based on deep learning Download PDFInfo
- Publication number
- CN113884905A CN113884905A CN202111290055.7A CN202111290055A CN113884905A CN 113884905 A CN113884905 A CN 113884905A CN 202111290055 A CN202111290055 A CN 202111290055A CN 113884905 A CN113884905 A CN 113884905A
- Authority
- CN
- China
- Prior art keywords
- charge
- state
- power battery
- value
- deep learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention provides a method and a system for estimating the state of charge of a power battery based on deep learning, which are used for acquiring the temperature, the discharge current and the open-circuit voltage of the power battery; calculating a reference state of charge value according to the obtained value of the open circuit voltage through a first prediction model obtained by pre-training by using a regression analysis method; calculating a corresponding state of charge difference value according to the acquired temperature and discharge current value of the power battery by using a second prediction model obtained by pre-training through a deep learning algorithm; and determining the state of charge of the power battery by calculating the sum of the obtained reference state of charge value and the corresponding state of charge difference value. The method can reasonably estimate the charge state of the battery and avoid the problems of overcharge, overdischarge and the like of the battery.
Description
Technical Field
The invention belongs to the technical field of battery management, and particularly relates to a method and a system for estimating the state of charge of a power battery based on deep learning.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the increasing serious problems of world energy crisis and environmental pollution, the quantity of new energy automobiles, especially electric automobiles taking power batteries as power sources, is increasing year by year, and the power batteries are widely used due to higher weight energy density and weight power density, better low-temperature adaptability and better reliability.
The biggest problem of the electric automobile is mileage anxiety, and the problems mainly include short total driving mileage of the automobile, difficulty in estimating state of charge (SOC) of a residual battery, long charging time, difficulty in finding a charging pile and the like. If the current residual capacity of the battery can be accurately calculated, the residual endurance mileage of the current automobile can be estimated, a reasonable trip plan can be conveniently made by an automobile owner, and the problem of mileage anxiety can be relieved to a certain extent.
Most of the existing power batteries are estimated in a single-factor estimation stage, and an open-circuit voltage method for predicting the SOC can predict the SOC to a certain extent, but has the defects of low precision, long time consumption and the like.
Disclosure of Invention
The invention provides a method and a system for estimating the state of charge of a power battery based on deep learning, aiming at solving the problems.
According to some embodiments, the invention adopts the following technical scheme:
a power battery state of charge estimation method based on deep learning comprises the following steps:
acquiring the temperature, the discharge current and the open-circuit voltage of the power battery;
calculating a reference state of charge value according to the obtained value of the open circuit voltage through a first prediction model obtained by pre-training by using a regression analysis method;
calculating a corresponding state of charge difference value according to the acquired temperature and discharge current value of the power battery by using a second prediction model obtained by pre-training through a deep learning algorithm;
and determining the state of charge of the power battery by calculating the sum of the obtained reference state of charge value and the corresponding state of charge difference value.
As an alternative embodiment, the training process of the two prediction models is preceded by the following steps: the method comprises the steps of carrying out power battery discharge tests at different temperatures and different discharge currents in advance to obtain test data, or obtaining power battery discharge test data at different temperatures and different discharge currents, determining the corresponding relation between the state of charge and the open-circuit voltage at different temperatures, different discharge currents and different open-circuit voltages, and forming a sample library.
In an alternative embodiment, the reference state is the lowest state of charge at the same open circuit voltage at different temperatures and discharge currents.
As an alternative embodiment, the training process of the first prediction model includes: and obtaining the corresponding relation between the charge state value of the reference state and the open-circuit voltage by utilizing four-time regression according to the corresponding data between the charge state value of the reference state and the open-circuit voltage.
As an alternative embodiment, the training process of the second prediction model includes: and calculating the difference value of the state of charge of the non-reference state and the reference state under the same open circuit voltage, and constructing and training a second prediction model by utilizing a support vector machine algorithm to determine the corresponding relation of the difference value of the state of charge along with the temperature and the discharge current.
As a further limited embodiment, when the second prediction model is trained by using the support vector machine algorithm, a part of data is selected as a training set and a part of data is selected as a test set in the sample library, and after the test is passed, the training is stopped.
As a further limited embodiment, all values are first normalized using a normalization formula for both the training set and the test set required for the support vector machine.
A deep learning based power battery state of charge estimation system comprising:
the parameter acquisition module is configured to acquire the temperature, the discharge current and the open-circuit voltage of the power battery;
a reference state of charge value calculation module configured to calculate a reference state of charge value according to the acquired value of the open-circuit voltage through a first prediction model pre-trained by using a regression analysis method;
the state of charge difference calculation module is configured to calculate a corresponding state of charge difference according to the acquired temperature and discharge current value of the power battery through a second prediction model obtained by utilizing a deep learning algorithm pre-training;
and the state of charge estimation module is configured to determine the state of charge of the power battery according to the calculated reference state of charge value and the corresponding state of charge difference value.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to carry out the steps of the above-mentioned method.
A terminal device comprising a processor and a computer readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions adapted to be loaded by a processor and to perform the steps of the above-described method.
Compared with the prior art, the invention has the beneficial effects that:
the invention utilizes the support vector machine to process samples obtained at different temperatures, different discharging currents and different open-circuit voltages, and corrects the SOC of the power battery by combining the discharging currents and the temperatures, thereby improving the display accuracy of the power battery management system on the SOC of the battery.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a process flow diagram of at least one embodiment of the invention.
The specific implementation mode is as follows:
the invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, a method for estimating the SOC of an automotive power battery based on deep learning includes the following steps:
acquiring the temperature, the discharge current and the open-circuit voltage of the current power battery;
calculating a reference state of charge value according to the obtained value of the open circuit voltage through a first prediction model obtained by pre-training by using a regression analysis method;
calculating a corresponding state of charge difference value according to the acquired temperature and discharge current value of the power battery by using a second prediction model obtained by pre-training through a deep learning algorithm;
and determining the current power battery charge state by calculating the sum of the reference state charge state value and the corresponding charge state difference value.
Before the steps of the method are executed, a construction process is needed, and the method specifically comprises the following steps:
the method comprises the steps of respectively testing the power battery at different temperatures (T) and different discharge currents (I), or acquiring existing test data, researching the relation between open-circuit voltage (OCV) and state of charge (SOC) and forming a data sample library.
Selecting the lowest state of charge under the same open-circuit voltage at different temperatures and discharge currents, and naming the state of charge as SOC0Obtaining OCV and SOC by regression analysis0Relation, obtaining SOC0The predictive model, i.e. the first predictive model.
Obtaining SOC values and SOC values corresponding to each open-circuit voltage under different temperatures and discharge currents according to the sample library0The difference of (d) is Δ SOC. And training the relation between different temperatures and currents and the delta SOC by using a deep learning algorithm SVM to obtain a delta SOC prediction model, namely a second prediction model.
The first embodiment is as follows:
in order to make the technical solution of the present invention more clear to those skilled in the art, the present embodiment explains the sequence from the construction process to the use process:
for a certain type of power battery, the discharge current of the power battery is controlled to be 0.33C, 0.5C, 1C, 1.5C and 2C respectively through battery testing equipment, the constant current discharge test is carried out at the environment temperature of 5 ℃, 15 ℃, 25 ℃, 35 ℃ and 45 ℃ respectively through the accurate temperature control of a constant temperature and humidity box, and the constant current discharge test is carried out at intervals
(wherein, I is a discharge current), namely, the power battery is allowed to stand for 1 hour at intervals of 0.1SOC, and then the open-circuit voltage OCV of the power battery at the discharge current, the discharge temperature and the SOC is measured. And performing all tests on the power battery to obtain corresponding SOC data sample libraries under different temperatures, different discharge currents and different open-circuit voltages.
Of course, in other embodiments, the parameters, such as the battery discharge current value, the temperature value, the interval and/or the standing time length, may be adjusted according to specific situations, which is easily conceivable by those skilled in the art and will not be described in detail herein.
Selecting the lowest state of charge SOC under the same open circuit voltage from a sample bank0Corresponding temperature T0And discharge current I0For the reference state, other temperatures T and other discharge currents I in the sample library are other states.
Selecting the lowest state of charge under the same open-circuit voltage at different temperatures and discharge currents in the sample library as a reference state, and naming the state as SOC0. And the SOC corresponding to other temperatures T and other discharge currents I in the sample library is in other states.
Further obtaining SOC under the reference state from the sample library0Corresponding data with OCV, and obtaining SOC by using quartic regression0Corresponding relation between the OCV and the four-time regression is as follows:
SOC0＝-1.18·OCV4+3.33·OCV3-3.19·OCV2+1.32·OCV+3.07
thereby obtaining the SOC0And (4) predicting the model.
Further obtain other state SOC and reference state SOC under the same open circuit voltage0Difference value delta SOC of lower SOC value
ΔSOC＝SOC-SOC0
Thus, a database of relationships between different temperatures T and different discharge currents I and Δ SOC is obtained.
And (3) establishing an SVM prediction model by adopting a Support Vector Machine (SVM) algorithm (SVM) in deep learning to train so as to obtain the corresponding relation of the delta SOC along with the temperature T and the discharge current I.
Selecting 80% of data as a training set and 20% of data as a test set from a database required by the SVM, and normalizing all values by using a normalization formula, wherein the normalization formula is as follows:
in the formula, x1Represents normalized data, x represents raw data, xmaxIs the maximum value of the parameter, xminIs the minimum value of the parameter.
In this embodiment, the SVM is trained by selecting a kernel function of a radial basis function, and the formula is as follows:
in the formula, m-dimensional vector
Is the input value of the ith training sample, an m-dimensional vector
Is the input value of the jth training sample, Yie.R is the corresponding output value, k*For an n-dimensional optimal solution, K (X)i,Xj)＝exp(-g||Xi-Xj||2),g>0 is the radial basis kernel function and epsilon represents the insensitivity coefficient. Finding out optimal penalty factor c and variance g by using cross-validation method, wherein the range of the set parameters c and g is [ -10,10 [ -10 [)]The appropriate combination of c and g is chosen. In this embodiment, the penalty factor c is selected to be 1.72 and the variance g is selected to be 0.76.
And (5) obtaining a delta SOC prediction model through SVM training.
Recording discharge current, discharge temperature and OCV during actual discharge, and substituting OCV into SOC obtained by regression analysis in reference state0Obtaining a rough predicted value SOC by the prediction model0And substituting the actual temperature and the discharge current into a delta SOC prediction model obtained by SVM training to obtain delta SOC, and combining the delta SOC prediction model and the delta SOC prediction model to obtain the true SOC:
SOC＝ΔSOC+SOC0
example two:
a deep learning based power battery state of charge estimation system comprising:
the parameter acquisition module is configured to acquire the temperature, the discharge current and the open-circuit voltage of the power battery;
a reference state of charge value calculation module configured to calculate a reference state of charge value according to the acquired value of the open-circuit voltage through a first prediction model pre-trained by using a regression analysis method;
the state of charge difference calculation module is configured to calculate a corresponding state of charge difference according to the acquired temperature and discharge current value of the power battery through a second prediction model obtained by utilizing a deep learning algorithm pre-training;
and the state of charge estimation module is configured to determine the state of charge of the power battery according to the calculated reference state of charge value and the corresponding state of charge difference value.
Example three:
a computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the steps of the method provided by the first embodiment.
Example four:
a terminal device comprising a processor and a computer readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions which are suitable for being loaded by a processor and executing the steps of the method provided by the first embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A power battery state of charge estimation method based on deep learning is characterized in that: the method comprises the following steps:
acquiring the temperature, the discharge current and the open-circuit voltage of the power battery;
calculating a reference state of charge value according to the obtained value of the open circuit voltage through a first prediction model obtained by pre-training by using a regression analysis method;
calculating a corresponding state of charge difference value according to the acquired temperature and discharge current value of the power battery by using a second prediction model obtained by pre-training through a deep learning algorithm;
and determining the state of charge of the power battery by calculating the sum of the obtained reference state of charge value and the corresponding state of charge difference value.
2. The deep learning-based power battery state of charge estimation method according to claim 1, characterized in that: before the training process of the two prediction models, the method comprises the following steps: the method comprises the steps of carrying out power battery discharge tests at different temperatures and different discharge currents in advance to obtain test data, or obtaining power battery discharge test data at different temperatures and different discharge currents, determining the corresponding relation between the state of charge and the open-circuit voltage at different temperatures, different discharge currents and different open-circuit voltages, and forming a sample library.
3. The deep learning-based power battery state of charge estimation method according to claim 1, characterized in that: the reference state is the lowest charge state under the same open-circuit voltage at different temperatures and discharge currents.
4. The deep learning-based power battery state of charge estimation method according to claim 1, characterized in that: the training process of the first prediction model comprises the following steps: and obtaining the corresponding relation between the charge state value of the reference state and the open-circuit voltage by utilizing four-time regression according to the corresponding data between the charge state value of the reference state and the open-circuit voltage.
5. The deep learning-based power battery state of charge estimation method according to claim 1, characterized in that: the training process of the second prediction model comprises the following steps: and calculating the difference value of the state of charge of the non-reference state and the reference state under the same open circuit voltage, and constructing and training a second prediction model by utilizing a support vector machine algorithm to determine the corresponding relation of the difference value of the state of charge along with the temperature and the discharge current.
6. The deep learning-based power battery state of charge estimation method of claim 5, wherein: and when the second prediction model is trained by using the support vector machine algorithm, selecting a part of data as a training set and a part of data as a test set in the sample library, and stopping training after the test is passed.
7. The deep learning-based power battery state of charge estimation method of claim 6, wherein: for the training set and the test set required by the support vector machine, all values are normalized by a normalization formula.
8. A power battery state of charge estimation system based on deep learning is characterized in that: the method comprises the following steps:
the parameter acquisition module is configured to acquire the temperature, the discharge current and the open-circuit voltage of the power battery;
a reference state of charge value calculation module configured to calculate a reference state of charge value according to the acquired value of the open-circuit voltage through a first prediction model pre-trained by using a regression analysis method;
the state of charge difference calculation module is configured to calculate a corresponding state of charge difference according to the acquired temperature and discharge current value of the power battery through a second prediction model obtained by utilizing a deep learning algorithm pre-training;
and the state of charge estimation module is configured to determine the state of charge of the power battery according to the calculated reference state of charge value and the corresponding state of charge difference value.
9. A computer-readable storage medium characterized by: in which a plurality of instructions are stored, said instructions being adapted to be loaded by a processor of a terminal device and to carry out the steps of the method according to any one of claims 1 to 7.
10. A terminal device is characterized in that: the system comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and for performing the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111290055.7A CN113884905B (en) | 2021-11-02 | 2021-11-02 | Power battery state of charge estimation method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111290055.7A CN113884905B (en) | 2021-11-02 | 2021-11-02 | Power battery state of charge estimation method and system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113884905A true CN113884905A (en) | 2022-01-04 |
| CN113884905B CN113884905B (en) | 2022-06-14 |
Family
ID=79015919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111290055.7A Active CN113884905B (en) | 2021-11-02 | 2021-11-02 | Power battery state of charge estimation method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113884905B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114966413A (en) * | 2022-05-27 | 2022-08-30 | 深圳先进技术研究院 | Method for predicting state of charge of energy storage battery pack |
| CN115219903A (en) * | 2022-03-11 | 2022-10-21 | 中国第一汽车股份有限公司 | Battery self-discharge rate abnormity judgment method and device based on Internet of vehicles data analysis |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104242393A (en) * | 2014-09-12 | 2014-12-24 | 安徽启光能源科技研究院有限公司 | Battery management system based on dynamic SOC estimation system |
| CN106646252A (en) * | 2016-12-01 | 2017-05-10 | 国网辽宁省电力有限公司电力科学研究院 | Lead acid battery service life prediction method |
| CN106772065A (en) * | 2016-11-25 | 2017-05-31 | 国电南瑞科技股份有限公司 | Micro-capacitance sensor energy storage SOC estimation method and system based on least square method supporting vector machine |
| CN110412470A (en) * | 2019-04-22 | 2019-11-05 | 上海博强微电子有限公司 | Electric automobile power battery SOC estimation method |
| CN111007399A (en) * | 2019-11-15 | 2020-04-14 | 浙江大学 | Lithium battery state of charge prediction method based on improved generation countermeasure network |
| US20200200825A1 (en) * | 2018-12-20 | 2020-06-25 | Toyota Jidosha Kabushiki Kaisha | Battery capacity estimation method and battery capacity estimation device |
| CN111919128A (en) * | 2018-04-06 | 2020-11-10 | 株式会社半导体能源研究所 | Method for estimating state of charge of power storage device and system for estimating state of charge of power storage device |
| CN112067998A (en) * | 2020-09-10 | 2020-12-11 | 昆明理工大学 | Lithium ion battery state of charge estimation method based on deep neural network |
| CN112083346A (en) * | 2020-08-03 | 2020-12-15 | 山东大学 | LSTM-based parallel battery pack internal current distribution estimation method and system |
| CN112083333A (en) * | 2020-08-11 | 2020-12-15 | 昆明理工大学 | Power battery pack state of charge estimation method based on machine learning model |
| CN112269134A (en) * | 2020-09-10 | 2021-01-26 | 杭州电子科技大学 | Battery SOC and SOH joint estimation method based on deep learning |
| US20210055352A1 (en) * | 2018-03-16 | 2021-02-25 | Semiconductor Energy Laboratory Co., Ltd. | Device estimating charge state of secondary battery, device detecting abnormality of secondary battery, abnormality detection method of secondary battery, and management system of secondary battery |
| US20210181256A1 (en) * | 2018-07-31 | 2021-06-17 | Honda Motor Co., Ltd. | Estimation system, estimation device, estimation method, program, and storage medium |
| US20210190877A1 (en) * | 2017-11-16 | 2021-06-24 | Semiconductor Energy Laboratory Co., Ltd. | Lifetime estimation device, lifetime estimation method, and abnormality detection method of secondary battery |
| CN113064093A (en) * | 2021-03-22 | 2021-07-02 | 山东建筑大学 | Energy storage battery state of charge and state of health joint estimation method and system |
-
2021
- 2021-11-02 CN CN202111290055.7A patent/CN113884905B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104242393A (en) * | 2014-09-12 | 2014-12-24 | 安徽启光能源科技研究院有限公司 | Battery management system based on dynamic SOC estimation system |
| CN106772065A (en) * | 2016-11-25 | 2017-05-31 | 国电南瑞科技股份有限公司 | Micro-capacitance sensor energy storage SOC estimation method and system based on least square method supporting vector machine |
| CN106646252A (en) * | 2016-12-01 | 2017-05-10 | 国网辽宁省电力有限公司电力科学研究院 | Lead acid battery service life prediction method |
| US20210190877A1 (en) * | 2017-11-16 | 2021-06-24 | Semiconductor Energy Laboratory Co., Ltd. | Lifetime estimation device, lifetime estimation method, and abnormality detection method of secondary battery |
| US20210055352A1 (en) * | 2018-03-16 | 2021-02-25 | Semiconductor Energy Laboratory Co., Ltd. | Device estimating charge state of secondary battery, device detecting abnormality of secondary battery, abnormality detection method of secondary battery, and management system of secondary battery |
| CN111919128A (en) * | 2018-04-06 | 2020-11-10 | 株式会社半导体能源研究所 | Method for estimating state of charge of power storage device and system for estimating state of charge of power storage device |
| US20210181256A1 (en) * | 2018-07-31 | 2021-06-17 | Honda Motor Co., Ltd. | Estimation system, estimation device, estimation method, program, and storage medium |
| US20200200825A1 (en) * | 2018-12-20 | 2020-06-25 | Toyota Jidosha Kabushiki Kaisha | Battery capacity estimation method and battery capacity estimation device |
| CN110412470A (en) * | 2019-04-22 | 2019-11-05 | 上海博强微电子有限公司 | Electric automobile power battery SOC estimation method |
| CN111007399A (en) * | 2019-11-15 | 2020-04-14 | 浙江大学 | Lithium battery state of charge prediction method based on improved generation countermeasure network |
| CN112083346A (en) * | 2020-08-03 | 2020-12-15 | 山东大学 | LSTM-based parallel battery pack internal current distribution estimation method and system |
| CN112083333A (en) * | 2020-08-11 | 2020-12-15 | 昆明理工大学 | Power battery pack state of charge estimation method based on machine learning model |
| CN112269134A (en) * | 2020-09-10 | 2021-01-26 | 杭州电子科技大学 | Battery SOC and SOH joint estimation method based on deep learning |
| CN112067998A (en) * | 2020-09-10 | 2020-12-11 | 昆明理工大学 | Lithium ion battery state of charge estimation method based on deep neural network |
| CN113064093A (en) * | 2021-03-22 | 2021-07-02 | 山东建筑大学 | Energy storage battery state of charge and state of health joint estimation method and system |
Non-Patent Citations (5)
| Title |
|---|
| CHAO LYU等: "State-of-Charge Estimation of Lithium-ion Batteries Based on Deep Neural Network", 《2020 GLOBAL RELIABILITY AND PROGNOSTICS AND HEALTH MANAGEMENT (PHM-SHANGHAI)》 * |
| M. A. HANNAN等: "SOC Estimation of Li-ion Batteries With Learning Rate-Optimized Deep Fully Convolutional Network", 《 IEEE TRANSACTIONS ON POWER ELECTRONICS》 * |
| 倪水平等: "基于一维卷积神经网络与长短期记忆网络结合的电池荷电状态预测方法", 《计算机应用》 * |
| 张照娓等: "电动汽车锂离子电池荷电状态估算方法研究综述", 《电子与信息学部》 * |
| 明彤彤等: "基于LSTM神经网络的锂离子电荷状态估算", 《广东电力》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115219903A (en) * | 2022-03-11 | 2022-10-21 | 中国第一汽车股份有限公司 | Battery self-discharge rate abnormity judgment method and device based on Internet of vehicles data analysis |
| CN114966413A (en) * | 2022-05-27 | 2022-08-30 | 深圳先进技术研究院 | Method for predicting state of charge of energy storage battery pack |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113884905B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Farmann et al. | Comparative study of reduced order equivalent circuit models for on-board state-of-available-power prediction of lithium-ion batteries in electric vehicles | |
| Hu et al. | State estimation for advanced battery management: Key challenges and future trends | |
| Wang et al. | An adaptive remaining energy prediction approach for lithium-ion batteries in electric vehicles | |
| Wang et al. | Probability based remaining capacity estimation using data-driven and neural network model | |
| Anton et al. | Support vector machines used to estimate the battery state of charge | |
| Sun et al. | Model-based dynamic multi-parameter method for peak power estimation of lithium–ion batteries | |
| CN103616647B (en) | A kind of estimation method of battery dump energy for cell management system of electric automobile | |
| CN111448467B (en) | Method and system for modeling and estimating battery capacity | |
| WO2017104497A1 (en) | Secondary battery control system | |
| CN113884905B (en) | Power battery state of charge estimation method and system based on deep learning | |
| US20150369875A1 (en) | Battery state estimating device | |
| KR20160067510A (en) | Method and apparatus for estimating state of battery | |
| Zhao et al. | State of charge estimation based on a new dual-polarization-resistance model for electric vehicles | |
| JP5740798B2 (en) | Secondary battery maximum capacity measuring device | |
| Li et al. | The lithium-ion battery state-of-charge estimation using random forest regression | |
| US20140184233A1 (en) | Method for checking deterioration of battery | |
| Zhu et al. | The SOH estimation of LiFePO4 battery based on internal resistance with Grey Markov Chain | |
| Wong et al. | Li-ion batteries state-of-charge estimation using deep lstm at various battery specifications and discharge cycles | |
| CN114609523A (en) | Online battery capacity detection method, electronic equipment and storage medium | |
| CN114879070A (en) | Battery state evaluation method and related equipment | |
| CN113125967B (en) | Lithium battery SOE calculation method based on temperature rise prediction | |
| CN117054892B (en) | Evaluation method, device and management method for battery state of energy storage power station | |
| KR20210036638A (en) | Battery Output Voltage Response and State-of-Charge Forecasting Optimization Method using Hybrid VARMA and LSTM | |
| Kumari et al. | Electric vehicle battery state-of-charge estimation based on optimized deep learning strategy with varying temperature at different C Rate | |
| EP4270033A1 (en) | Method and apparatus for estimating state of health of 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 |