CN110045292A - Lithium ion battery SOC prediction technique based on big data and bp neural network - Google Patents
Lithium ion battery SOC prediction technique based on big data and bp neural network Download PDFInfo
- Publication number
- CN110045292A CN110045292A CN201910377462.8A CN201910377462A CN110045292A CN 110045292 A CN110045292 A CN 110045292A CN 201910377462 A CN201910377462 A CN 201910377462A CN 110045292 A CN110045292 A CN 110045292A
- Authority
- CN
- China
- Prior art keywords
- neural network
- soc
- voltage
- capacitor
- big data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
-
- G—PHYSICS
- 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]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
Lithium ion battery SOC prediction technique provided by the invention based on big data and bp neural network, acquisition outside batteries characteristic parameter establish the data set of battery SOC big data;Establish training set and test set;Construct multiple bp neural network prediction model;Data set is respectively put into the bp neural network prediction model of different parameters, measurement accuracy is obtained;It is analyzed according to the obtained measurement accuracy of bp neural network prediction model of different parameters, obtains prediction result.Lithium ion battery SOC prediction technique provided by the invention based on big data and bp neural network, the large data sets predicted by SOC guarantee precision of prediction convenient for effectively being excavated to data;SOC is carried out to battery to outside batteries parameter by distribution bp neural network prediction model accurately to predict, precision with higher, especially under big data, outside batteries parameter constantly changes, this method can accurately still predict the value of battery SOC, with very high usability, can be used widely in practice.
Description
Technical field
The present invention relates to technical field of battery management, more particularly to a kind of based on big data and bp neural network
Lithium ion battery SOC prediction technique.
Background technique
Since the scarcity and environmental problem of the energy are increasingly severe, electric car replaces fossil fuel automobile to have become
Main trend.And lithium ion lithium battery is the core drive component of new-energy automobile.In order to guarantee that battery performance is good, extension makes
With the service life, it is necessary to effectively be managed battery, on condition that the state-of-charge of battery must accurately and reliably be learnt
(state of charge, SOC).SOC be inside battery characteristic directly it can not be measured, can only by its voltage,
Some external behavior parameter predictions measured directly such as electric current, temperature, internal resistance, capacitor obtain.
Currently used battery SOC prediction technique has conventional model method and intelligent method.The method of conventional model is in electricity
Establish battery equivalent circuit model on the basis of chemical reaction, final precision of prediction relies on the accuracy of model, and in reality
The model of battery is difficult to set up in.Intelligent method mainly includes neural network, support vector machine etc..Due to lithium ion battery
Non-linear behavior and modeling it is difficult, the advantages of these intelligent methods is exactly the difficulty for solving Nonlinear Modeling, improves prediction
Precision is high, and BP neural network is but neglected in small sample, nonlinear problem precision of prediction with higher with the increase of data volume
The slightly characteristic of battery data itself.There are many external behavior parameter type of battery, and as electric car is more and more, battery is produced
Raw data volume is also being continuously increased, most of to predict it is all three outside batteries spies of selection to battery SOC using neural network
Property parameter input, and under the trend of big data, influence outside batteries characterisitic parameter only have electric current, voltage, temperature, also
It should need to consider that internal resistance and capacitor estimate battery SOC, this prediction can not be applied very well in practice.
In view of the above problems, the present invention proposes a kind of method combined based on big data technology and bp neural network,
It is not to be all used to predict by all parameters in actual prediction, preferable prediction result can be obtained, prediction input will appear more
Kind combination, such as (electric current, voltage, capacitor), (electric current, voltage, temperature, internal resistance), (electric current, voltage, capacitor, internal resistance) etc.,
The prediction effect that different combinations may obtain also has difference, then the precision predicted is same, so best input is combined
Have to be determined.
Summary of the invention
The present invention is to exist to need to be used to predict by all parameters when existing battery SOC prediction technique being overcome to apply,
The technological deficiency that can not obtain practical application well provides a kind of lithium ion battery based on big data and bp neural network
SOC prediction technique.
In order to solve the above technical problems, technical scheme is as follows:
Lithium ion battery SOC prediction technique based on big data and bp neural network, comprising the following steps:
S1: a large amount of outside batteries characteristic parameter is acquired in real time, is built according to the true value of outside batteries characteristic parameter and SOC
The data set of vertical battery SOC big data;
S2: according to the data set of battery SOC big data, different parameters input, the training set of output sample and test are established
Collection;
S3: the multiple bp neural network prediction model of different input and output parameters is constructed;
S4: the data set of battery SOC big data is respectively put into the bp neural network prediction model of different parameters, to mould
Type carries out prediction and error analysis, obtains measurement accuracy;
S5: it is analyzed according to the obtained measurement accuracy of bp neural network prediction model of different parameters, obtains precision
Highest one group, and then determine optimal solution, obtain prediction result.
Wherein, in the step S1, the outside batteries characteristic parameter includes voltage U, electric current I, temperature T, capacitor
C, the true value of internal resistance R and battery SOC;Outside batteries characteristic parameter is normalized, outside batteries feature is joined
Several and battery SOC true value is between (0,1).
Wherein, the input of different parameters described in step S2, the training set of output sample and test set are 16 heavy data sets,
Specifically:
One: electric current, voltage, temperature;Two: electric current, voltage, internal resistance;Three: electric current, voltage, capacitor;Four: electric current, capacitor, interior
Resistance;Five: electric current, temperature, internal resistance;Six: voltage, capacitor, internal resistance;Seven: voltage, capacitor, temperature;Eight: temperature, capacitor, internal resistance;
Nine: temperature, internal resistance, voltage;Ten: temperature, capacitor, voltage;11: internal resistance, capacitor, electric current, voltage;12: voltage, temperature,
Capacitor, internal resistance;13: electric current, temperature, capacitor, internal resistance;14: electric current, voltage, temperature, capacitor;15: electric current, voltage, temperature
Degree, internal resistance;16: electric current, voltage, temperature, internal resistance, capacitor.
Wherein, multiple bp neural network prediction model described in step S3 is three-decker, including input layer, active coating
And output layer, in which:
The input layer includes input vector, i.e. data set described in step S2, is embodied as:
X=(T, U, I, R, C)T;
Activation primitive in the active coating is used for the SOC value of battery that arrives according to input vector, specific to calculate
Formula are as follows:
Wherein, y indicates that SOC value of battery, x indicate input vector;
The output vector of output layer is together constituted by the SOC value of battery that active coating obtains.
Wherein, multiple bp neural network prediction model described in step S3 is the bp neural network prediction mould of parallel distributed
Type, that is, have multiple input nodes, and bp neural network goes out input weight by the parallel decision of multiple input nodes, guarantee with it is single
The output weight of bp Decision of Neural Network is consistent.
Wherein, the process of the step S4 specifically:
S41: the training set of 16 weight data sets in the step S2 is put into the bp neural network prediction model of parallel distributed
Middle training, multiple and different parallel distributed bp neural network prediction models after being trained;
S42: the test set of input sample is respectively put into different parallel distributed bp neural network prediction models and is surveyed
Examination obtains the predicted value of different input battery SOCs;
S43: by the predicted value for inputting battery SOC, SOC true value carries out error analysis in the test set that sample exports,
In include mean square error, mean absolute error, wherein the precision of the smaller prediction of mean square deviation MSE is higher, and mean absolute error is more preferable
The actual conditions for reflecting SOC prediction error, so that it is determined that measurement accuracy.
Wherein, the mean square error specific formula for calculation are as follows:
The mean absolute error specific formula for calculation are as follows:
Wherein, OtIndicate the true value of battery SOC, PtIndicate the predicted value of battery SOC.
Compared with prior art, the beneficial effect of technical solution of the present invention is:
A kind of lithium ion battery SOC prediction technique based on big data and bp neural network provided by the invention, by building
A large amount of outside batteries characterisitic parameters that vertical large data sets will acquire are integrated, and the large data sets of SOC prediction are formed, so as to
Data are effectively excavated in the later period, guarantee precision of prediction;By distribution bp neural network prediction model to outside batteries
Parameter carries out SOC to battery and accurately predicts that precision with higher, especially under big data, outside batteries parameter constantly changes,
This method can accurately still predict the value of battery SOC, have very high usability, can be used widely in practice.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention;
Fig. 2 is that the present invention schemes multiple bp neural network prediction model schematic diagram;
Fig. 3 is the bp neural network structure figure of battery SOC of the present invention prediction.
Specific embodiment
The attached figures are only used for illustrative purposes and cannot be understood as limitating the patent;
In order to better illustrate this embodiment, the certain components of attached drawing have omission, zoom in or out, and do not represent actual product
Size;
To those skilled in the art, it is to be understood that certain known features and its explanation, which may be omitted, in attached drawing
's.
The following further describes the technical solution of the present invention with reference to the accompanying drawings and examples.
Embodiment 1
As shown in Figure 1, the lithium ion battery SOC prediction technique based on big data and bp neural network, comprising the following steps:
S1: a large amount of outside batteries characteristic parameter is acquired in real time, is built according to the true value of outside batteries characteristic parameter and SOC
The data set of vertical battery SOC big data;
S2: according to the data set of battery SOC big data, different parameters input, the training set of output sample and test are established
Collection;
S3: the multiple bp neural network prediction model of different input and output parameters is constructed;
S4: the data set of battery SOC big data is respectively put into the bp neural network prediction model of different parameters, to mould
Type carries out prediction and error analysis, obtains measurement accuracy;
S5: it is analyzed according to the obtained measurement accuracy of bp neural network prediction model of different parameters, obtains precision
Highest one group, and then determine optimal solution, obtain prediction result.
More specifically, in the step S1, the outside batteries characteristic parameter include voltage U, electric current I, temperature T,
The true value of capacitor C, internal resistance R and battery SOC;Outside batteries characteristic parameter is normalized, keeps outside batteries special
The true value of sign parameter and battery SOC is between (0,1).
More specifically, as shown in Fig. 2, different parameters described in the step S2 input, output sample training set and
Test set is 16 heavy data sets, specifically:
One: electric current, voltage, temperature;Two: electric current, voltage, internal resistance;Three: electric current, voltage, capacitor;Four: electric current, capacitor, interior
Resistance;Five: electric current, temperature, internal resistance;Six: voltage, capacitor, internal resistance;Seven: voltage, capacitor, temperature;Eight: temperature, capacitor, internal resistance;
Nine: temperature, internal resistance, voltage;Ten: temperature, capacitor, voltage;11: internal resistance, capacitor, electric current, voltage;12: voltage, temperature,
Capacitor, internal resistance;13: electric current, temperature, capacitor, internal resistance;14: electric current, voltage, temperature, capacitor;15: electric current, voltage, temperature
Degree, internal resistance;16: electric current, voltage, temperature, internal resistance, capacitor.
More specifically, as shown in figure 3, multiple bp neural network prediction model described in step S3 is three-decker, packet
Include input layer, active coating and output layer, in which:
The input layer includes input vector, i.e. data set described in step S2, is embodied as:
X=(T, U, I, R, C)T;
Activation primitive in the active coating is used to arrive SOC value of battery, specific formula for calculation according to input vector are as follows:
Wherein, y indicates that SOC value of battery, x indicate input vector;
The output vector of output layer is together constituted by the SOC value of battery that active coating obtains.
More specifically, multiple bp neural network prediction model described in step S3 is that the bp neural network of parallel distributed is pre-
Model is surveyed, that is, there are multiple input nodes, bp neural network goes out input weight by the parallel decision of multiple input nodes, guarantees and list
The output weight of a bp Decision of Neural Network is consistent.
In the specific implementation process, the multiple input node includes three input nodes, four input nodes and five
Input node, the bp neural network prediction model of parallel distributed can choose the parallel decision input weight of multiple input nodes, together
When can also guarantee it is consistent with the single output weight of bp Decision of Neural Network.Bp neural network prediction model is by multiple lists
The bp neural network of body is in parallel, is conducive to carry out rapid data excavation to outside batteries parameter big data, more pre- by analyzing
Measured value can fast and effeciently find the relationship of SOC Yu outside batteries parameter.
More specifically, the process of the step S4 specifically:
S41: the training set of 16 weight data sets in the step S2 is put into the bp neural network prediction model of parallel distributed
Middle training, multiple and different parallel distributed bp neural network prediction models after being trained;
S42: the test set of input sample is respectively put into different parallel distributed bp neural network prediction models and is surveyed
Examination obtains the predicted value of different input battery SOCs;
S43: by the predicted value for inputting battery SOC, SOC true value carries out error analysis in the test set that sample exports,
In include mean square error, mean absolute error, wherein the precision of the smaller prediction of mean square deviation MSE is higher, and mean absolute error is more preferable
The actual conditions for reflecting SOC prediction error, so that it is determined that measurement accuracy.
Wherein, the mean square error specific formula for calculation are as follows:
The mean absolute error specific formula for calculation are as follows:
Wherein, OtIndicate the true value of battery SOC, PtIndicate the predicted value of battery SOC.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
Made any modifications, equivalent replacements, and improvements etc., should be included in the claims in the present invention within the spirit and principle of invention
Protection scope within.
Claims (7)
1. the lithium ion battery SOC prediction technique based on big data and bp neural network, which comprises the following steps:
S1: acquiring a large amount of outside batteries characteristic parameter in real time, establishes electricity according to the true value of outside batteries characteristic parameter and SOC
The data set of pond SOC big data;
S2: according to the data set of battery SOC big data, the training set and test set of different parameters input, output sample are established;
S3: the multiple bp neural network prediction model of different input and output parameters is constructed;
S4: the data set of battery SOC big data is respectively put into the bp neural network prediction model of different parameters, to model into
Row prediction and error analysis, obtain measurement accuracy;
S5: it is analyzed according to the obtained measurement accuracy of bp neural network prediction model of different parameters, obtains precision highest
One group, and then determine optimal solution, obtain prediction result.
2. the lithium ion battery SOC prediction technique according to claim 1 based on big data and bp neural network, feature
Be: in the step S1, the outside batteries characteristic parameter include voltage U, electric current I, temperature T, capacitor C, internal resistance R with
And the true value of battery SOC;Outside batteries characteristic parameter is normalized, outside batteries characteristic parameter and battery are made
The true value of SOC is between (0,1).
3. the lithium ion battery SOC prediction technique according to claim 2 based on big data and bp neural network, feature
Be: the input of different parameters described in step S2, the training set of output sample and test set are 16 heavy data sets, specifically:
One: electric current, voltage, temperature;Two: electric current, voltage, internal resistance;Three: electric current, voltage, capacitor;Four: electric current, capacitor, internal resistance;
Five: electric current, temperature, internal resistance;Six: voltage, capacitor, internal resistance;Seven: voltage, capacitor, temperature;Eight: temperature, capacitor, internal resistance;Nine: temperature
Degree, internal resistance, voltage;Ten: temperature, capacitor, voltage;11: internal resistance, capacitor, electric current, voltage;12: voltage, temperature, capacitor,
Internal resistance;13: electric current, temperature, capacitor, internal resistance;14: electric current, voltage, temperature, capacitor;15: electric current, voltage, temperature, interior
Resistance;16: electric current, voltage, temperature, internal resistance, capacitor.
4. the lithium ion battery SOC prediction technique according to claim 3 based on big data and bp neural network, feature
Be: multiple bp neural network prediction model described in step S3 is three-decker, including input layer, active coating and output
Layer, in which:
The input layer includes input vector, i.e. data set described in step S2, is embodied as:
X=(T, U, I, R, C)T;
Activation primitive in the active coating is used to arrive SOC value of battery, specific formula for calculation according to input vector are as follows:
Wherein, y indicates that SOC value of battery, x indicate input vector;
The output vector of output layer is together constituted by the SOC value of battery that active coating obtains.
5. the lithium ion battery SOC prediction technique according to claim 4 based on big data and bp neural network, feature
Be: multiple bp neural network prediction model described in step S3 is the bp neural network prediction model of parallel distributed, that is, is had
Multiple input nodes, bp neural network go out input weight by the parallel decision of multiple input nodes, guarantee and single bp nerve
The output weight of network decision is consistent.
6. the lithium ion battery SOC prediction technique according to claim 5 based on big data and bp neural network, feature
It is: the process of the step S4 specifically:
S41: the training set of 16 weight data sets in the step S2 is put into the bp neural network prediction model of parallel distributed and is instructed
Practice, multiple and different parallel distributed bp neural network prediction models after being trained;
S42: the test set of input sample is respectively put into different parallel distributed bp neural network prediction models and is tested, is obtained
To the predicted value of different input battery SOCs;
S43: by the predicted value for inputting battery SOC, SOC true value carries out error analysis in the test set that sample exports, wherein wrapping
Mean square error, mean absolute error are included, wherein the precision of the smaller prediction of mean square deviation MSE is higher, and mean absolute error more preferably reflects
SOC predicts the actual conditions of error out, so that it is determined that measurement accuracy.
7. the lithium ion battery SOC prediction technique according to claim 6 based on big data and bp neural network, feature
It is: the mean square error specific formula for calculation are as follows:
The mean absolute error specific formula for calculation are as follows:
Wherein, OtIndicate the true value of battery SOC, PtIndicate the predicted value of battery SOC.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910377462.8A CN110045292A (en) | 2019-05-07 | 2019-05-07 | Lithium ion battery SOC prediction technique based on big data and bp neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910377462.8A CN110045292A (en) | 2019-05-07 | 2019-05-07 | Lithium ion battery SOC prediction technique based on big data and bp neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110045292A true CN110045292A (en) | 2019-07-23 |
Family
ID=67281192
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910377462.8A Pending CN110045292A (en) | 2019-05-07 | 2019-05-07 | Lithium ion battery SOC prediction technique based on big data and bp neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110045292A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110488202A (en) * | 2019-07-24 | 2019-11-22 | 北京航空航天大学 | Vehicular battery state-of-charge estimation method based on deep neural network |
CN110501651A (en) * | 2019-08-19 | 2019-11-26 | 国网河北省电力有限公司石家庄供电分公司 | Retired battery core holds detection method and device |
CN110673039A (en) * | 2019-11-11 | 2020-01-10 | 安徽优旦科技有限公司 | Lithium iron phosphate battery SOC charging online correction method based on big data |
CN111562499A (en) * | 2020-06-09 | 2020-08-21 | 温州长江汽车电子有限公司 | Thermal management simulation method for lithium power battery of new energy automobile |
CN111969703A (en) * | 2020-07-22 | 2020-11-20 | 傲普(上海)新能源有限公司 | User side mobile folding sunlight tracking storage system, method, terminal and storage medium |
WO2021201387A1 (en) * | 2020-03-30 | 2021-10-07 | (주)아르고스다인 | Neural network-based battery capacity estimation method and device |
CN113552489A (en) * | 2021-06-29 | 2021-10-26 | 广东工业大学 | Power station standby power supply state of charge estimation method based on grey neural network |
CN115524655A (en) * | 2022-10-14 | 2022-12-27 | 成都智邦科技有限公司 | Residual capacity prediction calibration method of energy storage battery |
CN116068449A (en) * | 2023-03-23 | 2023-05-05 | 中国科学技术大学 | Lithium battery evaluation system and method for physical model constraint deep neural network |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1488954A (en) * | 2002-10-07 | 2004-04-14 | 陈清泉 | Method for estimating residual capacity of storage battery for electric vehicle |
CN101488596A (en) * | 2008-01-18 | 2009-07-22 | 通用电气公司 | System and method for estimating battery state of charge |
CN106443453A (en) * | 2016-07-04 | 2017-02-22 | 陈逸涵 | Lithium battery SOC estimation method based on BP neural network |
CN107014339A (en) * | 2017-04-26 | 2017-08-04 | 北京理工大学 | A kind of high-precision angle sensor error compensating method for big data |
CN107843843A (en) * | 2017-09-30 | 2018-03-27 | 江苏理工学院 | A kind of on-vehicle battery SOC on-line prediction methods based on big data and extreme learning machine |
CN109143867A (en) * | 2018-09-26 | 2019-01-04 | 上海海事大学 | A kind of energy management method of the hybrid power ship based on ANN Control |
-
2019
- 2019-05-07 CN CN201910377462.8A patent/CN110045292A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1488954A (en) * | 2002-10-07 | 2004-04-14 | 陈清泉 | Method for estimating residual capacity of storage battery for electric vehicle |
CN101488596A (en) * | 2008-01-18 | 2009-07-22 | 通用电气公司 | System and method for estimating battery state of charge |
CN106443453A (en) * | 2016-07-04 | 2017-02-22 | 陈逸涵 | Lithium battery SOC estimation method based on BP neural network |
CN107014339A (en) * | 2017-04-26 | 2017-08-04 | 北京理工大学 | A kind of high-precision angle sensor error compensating method for big data |
CN107843843A (en) * | 2017-09-30 | 2018-03-27 | 江苏理工学院 | A kind of on-vehicle battery SOC on-line prediction methods based on big data and extreme learning machine |
CN109143867A (en) * | 2018-09-26 | 2019-01-04 | 上海海事大学 | A kind of energy management method of the hybrid power ship based on ANN Control |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110488202A (en) * | 2019-07-24 | 2019-11-22 | 北京航空航天大学 | Vehicular battery state-of-charge estimation method based on deep neural network |
CN110501651A (en) * | 2019-08-19 | 2019-11-26 | 国网河北省电力有限公司石家庄供电分公司 | Retired battery core holds detection method and device |
CN110673039A (en) * | 2019-11-11 | 2020-01-10 | 安徽优旦科技有限公司 | Lithium iron phosphate battery SOC charging online correction method based on big data |
CN110673039B (en) * | 2019-11-11 | 2022-02-08 | 安徽优旦科技有限公司 | Lithium iron phosphate battery SOC charging online correction method based on big data |
WO2021201387A1 (en) * | 2020-03-30 | 2021-10-07 | (주)아르고스다인 | Neural network-based battery capacity estimation method and device |
CN111562499A (en) * | 2020-06-09 | 2020-08-21 | 温州长江汽车电子有限公司 | Thermal management simulation method for lithium power battery of new energy automobile |
CN111969703A (en) * | 2020-07-22 | 2020-11-20 | 傲普(上海)新能源有限公司 | User side mobile folding sunlight tracking storage system, method, terminal and storage medium |
CN113552489A (en) * | 2021-06-29 | 2021-10-26 | 广东工业大学 | Power station standby power supply state of charge estimation method based on grey neural network |
CN113552489B (en) * | 2021-06-29 | 2022-03-11 | 广东工业大学 | Power station standby power supply state of charge estimation method based on grey neural network |
CN115524655A (en) * | 2022-10-14 | 2022-12-27 | 成都智邦科技有限公司 | Residual capacity prediction calibration method of energy storage battery |
CN115524655B (en) * | 2022-10-14 | 2023-11-07 | 成都智邦科技有限公司 | Residual electric quantity prediction calibration method of energy storage battery |
CN116068449A (en) * | 2023-03-23 | 2023-05-05 | 中国科学技术大学 | Lithium battery evaluation system and method for physical model constraint deep neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110045292A (en) | Lithium ion battery SOC prediction technique based on big data and bp neural network | |
Tran et al. | A comprehensive equivalent circuit model for lithium-ion batteries, incorporating the effects of state of health, state of charge, and temperature on model parameters | |
CN107957562B (en) | Online prediction method for residual life of lithium ion battery | |
CN106055775B (en) | A kind of service life of secondary cell prediction technique that particle filter is combined with mechanism model | |
CN108846227B (en) | Lithium ion battery capacity degradation prediction and evaluation method based on random forest and capacity self-recovery effect analysis | |
CN110488194A (en) | A kind of lithium battery SOC estimation method and its system based on Electrochemical Impedance Models | |
Li et al. | On-line estimation method of lithium-ion battery health status based on PSO-SVM | |
CN110568359A (en) | lithium battery residual life prediction method | |
CN111426957B (en) | SOC estimation optimization method for power battery under simulated vehicle working condition | |
CN111812515A (en) | XGboost model-based lithium ion battery state of charge estimation | |
CN113702843B (en) | Lithium battery parameter identification and SOC estimation method based on suburb optimization algorithm | |
CN110082682A (en) | A kind of lithium battery charge state estimation method | |
CN109143074A (en) | A kind of power battery model parameter identification method and system | |
Huang et al. | The state of health estimation of lithium-ion batteries based on data-driven and model fusion method | |
CN106597288A (en) | Power supply SOC estimation method | |
Wang et al. | Health diagnosis for lithium-ion battery by combining partial incremental capacity and deep belief network during insufficient discharge profile | |
CN109917299A (en) | A kind of three layers of filtering evaluation method of lithium battery charge state | |
Zhao et al. | The li-ion battery state of charge prediction of electric vehicle using deep neural network | |
CN110632520A (en) | Estimation device and estimation method for SOC of power battery | |
Zhao et al. | State-of-health estimation with anomalous aging indicator detection of lithium-ion batteries using regression generative adversarial network | |
CN204030697U (en) | Based on the battery management system of dynamic SOC estimating system | |
CN110824375A (en) | Method for calculating actual capacity of retired storage battery | |
Liu et al. | Review on degradation mechanism and health state estimation methods of lithium-ion batteries | |
Huang et al. | State of health estimation of lithium-ion batteries based on fine-tuning or rebuilding transfer learning strategies combined with new features mining | |
CN111274539B (en) | Lithium battery SOH estimation method based on alternate least square method |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190723 |