CN112557908A - SOC and SOH joint estimation method for lithium ion power battery - Google Patents
SOC and SOH joint estimation method for lithium ion power battery Download PDFInfo
- Publication number
- CN112557908A CN112557908A CN202011495978.1A CN202011495978A CN112557908A CN 112557908 A CN112557908 A CN 112557908A CN 202011495978 A CN202011495978 A CN 202011495978A CN 112557908 A CN112557908 A CN 112557908A
- Authority
- CN
- China
- Prior art keywords
- soh
- soc
- lithium
- voltage
- temperature
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 title claims abstract description 23
- 229910001416 lithium ion Inorganic materials 0.000 title claims abstract description 23
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims abstract description 27
- 229910052744 lithium Inorganic materials 0.000 claims abstract description 27
- 238000002474 experimental method Methods 0.000 claims abstract description 23
- 230000008859 change Effects 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims description 30
- 238000007600 charging Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000007599 discharging Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000010280 constant potential charging Methods 0.000 claims description 3
- 238000010277 constant-current charging Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 19
- 230000008878 coupling Effects 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 5
- 238000005859 coupling reaction Methods 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 5
- 230000004913 activation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000032683 aging Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005184 irreversible process Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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]
- G01R31/378—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
-
- 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
Abstract
The invention discloses a lithium ion power battery SOC and SOH joint estimation method, which comprises the following steps: step 1: acquiring current, voltage, temperature and charge-discharge capacity change data of a lithium battery charge-discharge experiment, and preprocessing the current, voltage, temperature and charge-discharge capacity change data; step 2: constructing a training sample by using the preprocessed voltage, current and temperature data, and taking the three data quantities as the input of the SOH algorithm network to further obtain the output of the SOH algorithm network; and 3, taking the output of the SOH algorithm network in the step 2 and the preprocessed voltage, current and temperature data as the input of an SOC estimation algorithm to estimate the SOC. The method has the advantages of accurate estimation result and high precision.
Description
Technical Field
The invention relates to the technical field of battery management systems, in particular to a lithium ion power battery SOC and SOH joint estimation method.
Background
In recent years, the technology of the pure electric vehicle is rapidly developed, and the power battery is used as the only energy source of the pure electric vehicle and provides energy required by running for the pure electric vehicle. The battery state monitoring is the most basic function of a battery management system and is the premise and the basis of other functions. The State of Charge (SOC) is also called the remaining capacity, and the value of the SOC can represent the driving mileage of the electric vehicle, and the estimated discharge time and Charge time of the electric vehicle can be known according to the SOC of the battery, so that the overcharge and overdischarge of the battery can be effectively avoided, the safety of the battery can be protected, and the service life of the battery can be prolonged. The SOH (state of health) of a battery, which may also be referred to as the state of life or the degree of aging and degradation of the battery, describes a slowly changing, irreversible process in which the SOH of the battery gradually decays as the number of battery charges and discharges increases, until the end of its life. When the battery life reaches a critical value, the battery may explode due to the continuous charging and discharging of the battery, which threatens the lives of the driver and the passenger. Therefore, the SOC and SOH states of the power lithium battery can be effectively monitored in real time, and the method has very important significance on the safety, reliability and dynamic property of the electric automobile. At present, a part of scholars at home and abroad carry out decoupling estimation on the SOC and the SOH, namely only one state quantity is considered, and the influence of the other state quantity is not considered, so that the estimation method inevitably influences the estimation precision of the SOC and the SOH. Of course, another part of scholars jointly estimate the SOC and SOH by using the dual kalman filter or the jointly improved kalman filter algorithm, but the estimation result of the kalman filter algorithm on the non-linear strong physical quantity is not ideal. Therefore, the SOC and the SOH are jointly estimated by a data driving algorithm in consideration of the coupling relation of the SOC and the SOH and the strong nonlinear relation of the SOC and the SOH, and the estimation accuracy is improved.
Disclosure of Invention
The invention aims to provide a lithium ion power battery SOC and SOH joint estimation method. The method has the advantages of accurate estimation result and high precision.
The technical scheme of the invention is as follows: a lithium ion power battery SOC and SOH joint estimation method comprises the following steps:
step 1: acquiring current, voltage, temperature and charge-discharge capacity change data of a lithium battery charge-discharge experiment, and preprocessing the current, voltage, temperature and charge-discharge capacity change data;
step 2: constructing a training sample by using the preprocessed voltage, current and temperature data, and taking the three data quantities as the input of the SOH algorithm network to further obtain the output of the SOH algorithm network;
and 3, taking the output of the SOH algorithm network in the step 2 and the preprocessed voltage, current and temperature data as the input of an SOC estimation algorithm to estimate the SOC.
According to the lithium ion power battery SOC and SOH joint estimation method, the temperature of the charging and discharging experiment environment of the lithium battery is set to be 0 ℃, 25 ℃ and 45 ℃, and low temperature, normal temperature and high temperature in actual driving are simulated respectively; the lithium battery charging and discharging experiment comprises a charging experiment and a discharging experiment, wherein the charging experiment is to perform constant current charging to upper cut-off voltage by 1C multiplying power, then perform constant voltage charging to current reduction of 1/20C by the upper cut-off voltage, and finish charging; the discharge experiment simulates the discharge condition in the actual driving process by three different discharge multiplying factors of 1C, 3C and 5C.
According to the method for jointly estimating the SOC and the SOH of the lithium-ion power battery, the preprocessing comprises missing value processing, normalization processing and standardization processing.
In the foregoing method for jointly estimating SOC and SOH of the lithium-ion power battery, in step 2, the SOH algorithm network is a DNN neural network.
According to the lithium ion power battery SOC and SOH joint estimation method, the DNN neural network is adopted to output the SOH of the lithium battery once every time the lithium ion power battery is charged and discharged.
In the above combined estimation method for the SOC and SOH of the lithium ion power battery, in step 3, the SOC estimation algorithm employs a gated neural network.
Compared with the prior art, the SOC and SOH joint estimation method has the advantages that the SOC and SOH are jointly estimated by considering the coupling relation of the SOC and the SOH, and the estimation accuracy of the SOC and the SOH is improved; because the battery model of the lithium battery is difficult to construct and the constructed model is inaccurate, the method adopts a large amount of experimental data, and performs combined estimation on the SOC and the SOH through the neural network, thereby omitting the complexity of modeling, considering the high nonlinearity of the two state quantities, and having the advantages of accurate estimation result and high precision. In addition, the SOH estimation method considers the long-term time-varying property of the SOH estimation and does not need to predict frequently, so the SOH is estimated by adopting the DNN neural network, and the DNN neural network has a simple network structure (such as the number of hidden neurons and the number of hidden layers are simple and easy to adjust), so the SOH estimation method is more suitable for the SOH estimation requirement; considering the short-term time variability of the SOC, the estimation of the SOC needs to be carried out frequently in a short time, and the one-dimensional time sequence dependency of the SOC is estimated by adopting a gated neural network (GRU) in deep learning, and the GRU algorithm can fully consider the dependency on time steps before and after the SOC and the influence of historical data on the current estimation, so that the method is very suitable for the estimation of the SOC. The method can effectively improve the estimation precision of the SOC and has wide application prospect.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic block diagram of the DNN deep neural network algorithm of the present invention;
FIG. 3 is a schematic block diagram of a gated neural network algorithm (GRU) of the present invention;
FIG. 4 is a diagram of the temporal logic structure for SOC estimation by GRU algorithm according to the present invention;
FIG. 5 is a graph of SOH results estimated by the DNN algorithm provided by an example of the present invention;
FIG. 6 is a graph of the SOH error estimated by the DNN algorithm provided by the example of the present invention;
FIG. 7 is a graph of SOC results estimated by the GRU algorithm provided by an example of the present invention;
FIG. 8 is a graph of the estimated SOC error for the GRU algorithm provided by an example of the present invention;
FIG. 9 is a graph of SOC results estimated by the GRU algorithm in view of the SOH effect according to an embodiment of the present invention;
FIG. 10 is a graph of the estimated SOC error of the GRU algorithm in view of the SOH effect according to an embodiment of the present invention.
Detailed Description
The invention is further illustrated by the following figures and examples, which are not to be construed as limiting the invention.
Example (b): a combined estimation method for SOC and SOH of a lithium ion power battery is shown in FIG. 1, and comprises the following steps:
step 1: acquiring current, voltage, temperature and charge-discharge capacity change data of a lithium battery charge-discharge experiment, wherein the ambient temperature of the lithium battery charge-discharge experiment is set to be 0 ℃, 25 ℃ and 45 ℃, and low temperature, normal temperature and high temperature in actual driving are simulated respectively; the lithium battery charging and discharging experiment comprises a charging experiment and a discharging experiment, wherein the charging experiment is to perform constant current charging to upper cut-off voltage by 1C multiplying power, then perform constant voltage charging to current reduction of 1/20C by the upper cut-off voltage, and finish charging; the discharge experiment simulates the discharge condition in the actual driving process by three different discharge multiplying factors of 1C, 3C and 5C; data are acquired through a sensor, and mainly battery end voltage, battery current and battery temperature are acquired, and capacity change is obtained through an ampere-hour integration method.
The experimental data preprocessing is mainly to perform some common data processing means on the obtained original data so that the data can be better input into a neural network for predicting results, the common data processing means include missing value processing, normalization processing, standardization processing and the like, the missing value processing is to fill some missing values in the obtained original data by some methods, and values which cannot be filled are discarded; the normalization processing is to unify the numerical values in different size ranges of different dimensions into the same numerical value range; in this embodiment, the data preprocessing is performed on the original data obtained in step 1, which mainly includes filling and deleting missing data values, and in order to balance the influence of the input data on the network, the data is normalized, and then the data obtained through different charge and discharge cycles are filled and cut off, so that the dimensionality of the data input to the network is consistent.
Step 2: constructing a training sample by using the preprocessed voltage, current and temperature data, taking the three data quantities as the input of the SOH algorithm network to obtain optimal parameters, and training to obtain the output of the SOH algorithm network; the SOH algorithm network is a DNN neural network; in the training process, because the SOH of the lithium battery is a long-time variable quantity, the DNN neural network is adopted to output the SOH of the lithium battery once every time the lithium battery is charged and discharged.
in the above, for the detailed description of an example of the method for jointly estimating SOC and SOH of the lithium-ion power battery according to the embodiment of the present invention, another example of the method for jointly estimating SOC and SOH of the lithium-ion power battery based on data driving according to the embodiment of the present invention will be described in detail below.
As shown in fig. 2, another example of a method for jointly estimating SOC and SOH of a lithium-ion power battery provided by an embodiment of the present invention includes:
the first layer is an input layer, the obtained data is mainly input into a neural network, and a mathematical formula from the neural network of the input layer to a hidden layer is as follows:
a＝Z(W1·X+b1)
where X denotes a vector composed of input data, and X ═ X (X)1,x2,...,xn)T，W1Weight matrix representing the first layer of neural network, b1A bias matrix representing a first layer of neural network, passing through W1·X+b1After the operation, the relationship is linear, in order to solve the nonlinear relationship, an activation function Z is introduced, the activation function Z generally includes common activation functions such as sigmoid function, relu function and tanh function, and a represents the result output by the first-layer neural network.
The layers other than the input layer and the output layer are collectively referred to as the hidden layer, and similarly, the output of the previous layer is the input of the next layer, similar to the input layer to the hidden layer, and the formula is as follows:
hθ i(x)＝Z(Wi·ai-1+bi)；
wherein, ai-1Representing the output of the layer i-1 neural network; wiWeight matrix representing the i-layer neurons, biA bias matrix representing layer i neurons.
The number of output layer neurons is mainly determined according to the number of output results, if the output results are one-dimensional, the output layer neurons can be set to be one, and the output layer results are y.
The basic idea of deep neural network back propagation is to compare a predicted value obtained by the network with an actually obtained observation value, set a target loss function (generally, root mean square error RMSE and mean absolute error MAE are used as loss functions), and then solve a partial derivative from the loss functions to the weight and bias of each layer through a gradient descent algorithm, so that the reverse transfer of errors is realized, and the minimization of the target loss function is realized. The formula is as follows:
loss function:
the loss function derives the weight W:
the loss function is derived for the bias b:
wherein J (W, b, x, y) represents a loss function, Wi，Zi，biRespectively representing the weight, activation function and bias of the ith layer.
Weights and biases of all layers of the model are trained through forward propagation and reverse error transmission of the deep neural network, and after optimal training parameters are obtained, the model is determined, so that the estimation of the SOH of the lithium battery can be realized through the DNN neural network.
As shown in fig. 3 and 4, an example of a method for jointly estimating SOC and SOH of a lithium-ion power battery provided by an embodiment of the present invention includes:
as shown in fig. 3, the input of the gated neural network unit (GRU) is mainly composed of two parts, the output ht-1 of the previous time step and the input Xt of the current time step are spliced to form the input of the current network, the network unit includes a reset gate rt and an update gate zt, the two gates mainly express the retention degree of the past information and the absorption degree of the new information, the values of the two gates are between 0 and 1, if 0 represents that the information is not stored, and if 1 represents that the information is completely stored. And two network unit outputs are provided, one output ht is transmitted to the next time step to realize the transmission of the historical information, and the other output y represents the output result of the current network unit. The mathematical formula of the network element is as follows:
zt＝σ(wz[ht-1,xt]+bz)；
rt＝σ(wr[ht-1,xt]+br)；
C＝tanh(wc[rt ht-1,xt]+bc)；
ht＝(1-zt)ht-1+zt C；
where zt and rt denote an update gate and a reset gate, C denotes a state quantity of a network element determined by both a previous time step and a current time step, ht-1 denotes an output of the previous time step, w and b denote a weight and an offset, and σ and tanh denote a sigmoid function and a hyperbolic tangent function.
As shown in fig. 4, a structure diagram of gated neural network (GRU) units developed according to time steps is shown, the neural network has network units as its subjects, and the network actually has only one network unit, but the network units at different times are arranged according to a time axis as in fig. 4, so that the implementation manner of the network is more visualized and easier to understand. The inputs to the GRU network are the collected voltage, current, temperature and SOH values estimated by the DNN network, and the SOC values are output at each instant.
The example shown in fig. 5 and 6 is a SOH result graph and an error graph estimated by the DNN algorithm, and it can be found that the effect of the state of SOH of the lithium battery estimated by the DNN algorithm can reach the current actual demand condition, and through error analysis, it can be seen that the error of the SOH of the lithium battery estimated by the DNN algorithm is within 3% in total.
Fig. 7 and 8 show an SOC result map and an estimated error map of the GRU algorithm according to the present invention, where the estimated result is an estimated result without considering the influence of battery aging on the SOC estimation of the lithium battery, and the error of the estimated result is about 5%, and although the estimated result is still acceptable, there is a certain difference from the SOC error estimated by most researchers about 3%.
Fig. 9 and 10 are an SOC result graph and an error graph estimated by the GRU algorithm in consideration of the SOH influence, which are provided by the example of the present invention, and the example is an improvement of the previous example, in consideration of the coupling relationship between the SOC and the SOH, the SOH state quantity is taken into consideration when estimating the SOC of the lithium battery, and it can be found from the estimation result and the estimation error that the estimation error is reduced from 5% to about 2.3% of the current, and compared with the error estimated by an ordinary researcher or a technician of about 3%, the accuracy of the estimation algorithm is improved by the present invention.
In conclusion, the embodiment of the invention can realize the combined estimation of the SOC and the SOH of the lithium battery, fully considers the coupling relation of the SOC and the SOH, considers the influence of the battery aging on the SOC estimation through the SOH and can improve the accuracy of the SOC estimation result; in addition, the strong nonlinear relationship between the estimation of SOC and SOH and the original data is considered, so that the two states are estimated in a data-driven mode, and the difficulties of traditional complex battery modeling process and inaccurate modeling are avoided. The gating neural network in the deep learning considers the long-term dependence of SOC estimation time and the characteristic that the SOC needs to be acquired frequently in a short time, so that the GRU network is applied to SOC estimation, and the estimation accuracy of the SOC is improved. And meanwhile, the SOH has long-term variability, namely the SOH can be regarded as constant in a short time, so that the SOH can be estimated less frequently, and the SOH of the lithium battery can be estimated by adopting a deep neural network DNN. Therefore, the invention comprehensively considers the coupling relation of SOC and SOH, improves the precision of the state estimation of the lithium battery, can realize more accurate estimation, and verifies the feasibility and effectiveness of the example through experiments and algorithms.
Claims (6)
1. A lithium ion power battery SOC and SOH joint estimation method is characterized in that: the method comprises the following steps:
step 1: acquiring current, voltage, temperature and charge-discharge capacity change data of a lithium battery charge-discharge experiment, and preprocessing the current, voltage, temperature and charge-discharge capacity change data;
step 2: constructing a training sample by using the preprocessed voltage, current and temperature data, and taking the three data quantities as the input of the SOH algorithm network to further obtain the output of the SOH algorithm network;
and 3, taking the output of the SOH algorithm network in the step 2 and the preprocessed voltage, current and temperature data as the input of an SOC estimation algorithm to estimate the SOC.
2. The lithium-ion power battery SOC and SOH joint estimation method of claim 1, wherein: the temperature of the lithium battery charging and discharging experiment environment is set to be 0 ℃, 25 ℃ and 45 ℃, and low temperature, normal temperature and high temperature in actual driving are simulated respectively; the lithium battery charging and discharging experiment comprises a charging experiment and a discharging experiment, wherein the charging experiment is to perform constant current charging to upper cut-off voltage by 1C multiplying power, then perform constant voltage charging to current reduction of 1/20C by the upper cut-off voltage, and finish charging; the discharge experiment simulates the discharge condition in the actual driving process by three different discharge multiplying factors of 1C, 3C and 5C.
3. The lithium-ion power battery SOC and SOH joint estimation method of claim 1, wherein: the preprocessing comprises missing value processing, normalization processing and normalization processing.
4. The lithium-ion power battery SOC and SOH joint estimation method of claim 1, wherein: in step 2, the SOH algorithm network is a DNN neural network.
5. The lithium-ion power battery SOC and SOH joint estimation method of claim 4, wherein: and outputting the SOH of the lithium battery once by adopting the DNN neural network every time the lithium battery is charged and discharged.
6. The lithium-ion power battery SOC and SOH joint estimation method of claim 1, wherein: in step 3, the SOC estimation algorithm adopts a gated neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011495978.1A CN112557908A (en) | 2020-12-17 | 2020-12-17 | SOC and SOH joint estimation method for lithium ion power battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011495978.1A CN112557908A (en) | 2020-12-17 | 2020-12-17 | SOC and SOH joint estimation method for lithium ion power battery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112557908A true CN112557908A (en) | 2021-03-26 |
Family
ID=75064581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011495978.1A Pending CN112557908A (en) | 2020-12-17 | 2020-12-17 | SOC and SOH joint estimation method for lithium ion power battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112557908A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113253128A (en) * | 2021-05-12 | 2021-08-13 | 合肥国轩高科动力能源有限公司 | Battery system SOC consistency evaluation method and internal resistance consistency evaluation method |
| CN113687242A (en) * | 2021-09-29 | 2021-11-23 | 温州大学 | Lithium ion battery SOH estimation method for optimizing and improving GRU neural network based on GA algorithm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881001A (en) * | 2014-04-25 | 2015-09-02 | 安徽贵博新能科技有限公司 | Energy storage battery management system based on deep learning network |
| CN110888058A (en) * | 2019-12-02 | 2020-03-17 | 西安科技大学 | Algorithm based on power battery SOC and SOH joint estimation |
-
2020
- 2020-12-17 CN CN202011495978.1A patent/CN112557908A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881001A (en) * | 2014-04-25 | 2015-09-02 | 安徽贵博新能科技有限公司 | Energy storage battery management system based on deep learning network |
| CN110888058A (en) * | 2019-12-02 | 2020-03-17 | 西安科技大学 | Algorithm based on power battery SOC and SOH joint estimation |
Non-Patent Citations (1)
| Title |
|---|
| 吴彦威等: "GRU 网络在电动汽车 SOC 估算中的应用", 《机械装备研发》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113253128A (en) * | 2021-05-12 | 2021-08-13 | 合肥国轩高科动力能源有限公司 | Battery system SOC consistency evaluation method and internal resistance consistency evaluation method |
| CN113253128B (en) * | 2021-05-12 | 2022-04-12 | 合肥国轩高科动力能源有限公司 | Battery system SOC consistency evaluation method and internal resistance consistency evaluation method |
| CN113687242A (en) * | 2021-09-29 | 2021-11-23 | 温州大学 | Lithium ion battery SOH estimation method for optimizing and improving GRU neural network based on GA algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hong et al. | Online accurate state of health estimation for battery systems on real-world electric vehicles with variable driving conditions considered | |
| Li et al. | Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks | |
| Farmann et al. | A comprehensive review of on-board State-of-Available-Power prediction techniques for lithium-ion batteries in electric vehicles | |
| EP3748380A1 (en) | Battery capacity prediction system using charge and discharge cycles of a battery to predict capacity variations, and associated method | |
| Zhao et al. | Elman neural network using ant colony optimization algorithm for estimating of state of charge of lithium-ion battery | |
| CN105277896B (en) | Lithium battery method for predicting residual useful life based on ELM MUKF | |
| Fan et al. | SOC estimation of Li-ion battery using convolutional neural network with U-Net architecture | |
| Yang et al. | A deep learning approach to state of charge estimation of lithium-ion batteries based on dual-stage attention mechanism | |
| CN111007401A (en) | Electric vehicle battery fault diagnosis method and device based on artificial intelligence | |
| Zhang et al. | Remaining useful life estimation of lithium-ion batteries based on thermal dynamics | |
| CN113419187B (en) | Lithium ion battery health estimation method | |
| Zhou et al. | Battery health prognosis using improved temporal convolutional network modeling | |
| KR102297343B1 (en) | Battery Output Voltage Response and State-of-Charge Forecasting Method using Hybrid VARMA and LSTM | |
| CN112782594B (en) | Method for estimating SOC (state of charge) of lithium battery by data-driven algorithm considering internal resistance | |
| US20220057451A1 (en) | System and method for estimation of battery state and health | |
| CN112557908A (en) | SOC and SOH joint estimation method for lithium ion power battery | |
| CN110412470A (en) | Electric automobile power battery SOC estimation method | |
| CN113917336A (en) | Lithium ion battery health state prediction method based on segment charging time and GRU | |
| Lin et al. | Simultaneous and rapid estimation of state of health and state of charge for lithium-ion battery based on response characteristics of load surges | |
| Adedeji et al. | A feedforward deep neural network for predicting the state-of-charge of lithium-ion battery in electric vehicles | |
| CN116125306A (en) | Power battery thermal runaway diagnosis method and system based on hybrid prediction framework | |
| Bak et al. | Accurate estimation of battery SOH and RUL based on a progressive lstm with a time compensated entropy index | |
| Lyu et al. | State-of-charge estimation of lithium-ion batteries based on deep neural network | |
| Song et al. | Capacity estimation method of lithium-ion batteries based on deep convolution neural network | |
| CN112327169A (en) | Lithium battery residual life prediction 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: 20210326 |