CN111948539A - Kalman filtering lithium ion battery SOC estimation method based on deep reinforcement learning - Google Patents
Kalman filtering lithium ion battery SOC estimation method based on deep reinforcement learning Download PDFInfo
- Publication number
- CN111948539A CN111948539A CN201910422522.3A CN201910422522A CN111948539A CN 111948539 A CN111948539 A CN 111948539A CN 201910422522 A CN201910422522 A CN 201910422522A CN 111948539 A CN111948539 A CN 111948539A
- Authority
- CN
- China
- Prior art keywords
- lithium ion
- ion battery
- battery
- kalman filtering
- soc
- 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
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 title claims abstract description 81
- 229910001416 lithium ion Inorganic materials 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000002787 reinforcement Effects 0.000 title claims abstract description 33
- 238000001914 filtration Methods 0.000 title claims abstract description 31
- 238000013178 mathematical model Methods 0.000 claims abstract description 18
- 238000004088 simulation Methods 0.000 claims abstract description 8
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 7
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims description 10
- 229910052744 lithium Inorganic materials 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 230000010287 polarization Effects 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 6
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 238000007599 discharging Methods 0.000 description 2
- 238000004146 energy storage Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003487 electrochemical reaction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000013468 resource allocation 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tests Of Electric Status Of Batteries (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention relates to a method for estimating the SOC of a lithium ion battery based on deep reinforcement learning Kalman filtering, which is mainly technically characterized by comprising the following steps: the invention establishes a discrete system mathematical model through a second-order RC equivalent circuit topology of the lithium ion battery, and provides a novel deep reinforcement learning Kalman filtering lithium ion battery SOC estimation method. Firstly, a state space model of the battery is established by analyzing a second-order RC equivalent circuit model of the lithium ion battery, and a discrete system mathematical model of the lithium ion battery is established by utilizing a traditional Kalman filtering algorithm. And further designing a deep reinforcement learning Kalman filtering lithium ion battery SOC estimation method by combining with an artificial intelligence thought. Finally, the best covariance is ensured by bayesian rules. Simulation results show that the estimation method can ensure the optimal covariance of the system through the Bayesian rule on the basis of utilizing the advantages of two algorithms, effectively reduces the calculated amount in the estimation process, further improves the accuracy of SOC estimation, and has better practicability.
Description
Technical Field
The invention belongs to the field of lithium ion battery energy storage, and particularly relates to an estimation method of a lithium ion battery SOC based on deep reinforcement learning Kalman filtering.
Background
With the popularization of new energy vehicles, lithium ion batteries have a wide application space. State estimation of lithium ion batteries is one of the important components of energy storage systems. The accuracy of the state estimation of the lithium ion battery is closely related to the charging and discharging processes of the battery and the running state of a new energy vehicle. In order to improve the accuracy of state estimation of lithium ion batteries, a great deal of research is carried out by relevant scholars at home and abroad.
Kalman filtering (Kalman filter) is an algorithm that uses a linear system state equation to perform optimal estimation on the system by inputting and outputting observation data. Since the observation data includes the influence of noise and interference in the system, the optimal estimation can also be regarded as a filtering process, and is a common lithium ion battery state estimation algorithm. The lithium ion battery has complex operation state, and the state estimation is interfered by a plurality of factors. Aiming at the identification and state estimation of the inconsistency of the series lithium ion battery pack, the Gesneklung and the like, an STF & LM algorithm is provided, the algorithm controls the state and internal resistance estimation errors of each monomer within a reasonable range, and the identification and state estimation of the inconsistency of the battery pack are improved. Chengzi and others combine the Sage-Husa adaptive filtering idea with the traditional Square Root Unscented Kalman Filter (SRUKF) on the basis of analyzing the second-order RC equivalent circuit of the lithium ion battery to construct an adaptive square root unscented Kalman filtering algorithm, and the algorithm improves the estimation of ohmic resistance and capacity of the battery. The deep reinforcement learning combines the deep learning perception capability and the reinforcement learning decision capability, can be directly controlled according to an input image, and is an artificial intelligence method closer to a human thinking mode. Minho Kim et al provide a state estimation algorithm of a lithium ion battery for reinforcement learning by using deep reinforcement learning thinking, the method is more accurate and flexible for state estimation of the lithium ion battery, and the defect is that parameter changing is difficult. Sbarufatti C and Dang X J, etc. combine the neural network and the kalman filter algorithm, respectively, propose two different algorithms, and experiments all verify that the precision of the state estimation of the lithium ion battery can be improved.
Disclosure of Invention
The invention establishes a discrete system mathematical model through a second-order RC equivalent circuit topology of the lithium ion battery, and provides a novel deep reinforcement learning Kalman filtering lithium ion battery SOC estimation method.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
a method for estimating the SOC of a lithium ion battery based on deep reinforcement learning Kalman filtering comprises the following steps:
And 2, further designing a deep reinforcement learning Kalman filtering lithium ion battery SOC estimation method according to the mathematical model in the step 1 and by combining an artificial intelligence thought.
And 3, ensuring the optimal covariance according to the mathematical model in the step 1 under the Bayes rule. After the simulation result is obtained, the method can be shown to be capable of improving the SOC precision.
Moreover, the second-order RC mathematical model of the lithium ion battery is as follows:
wherein r isoIs internal resistance of lithium ion battery, r1、r2、C1、C2Is the polarization internal resistance and polarization capacitance, i, of the lithium ion batterytIs the current of a lithium ion battery, uoIs the voltage of a resistance in a lithium ion battery, uOCVFor the open circuit voltage, u, of a lithium ion battery1、u2Respectively the internal polarization resistance r of the lithium ion battery1、r2Voltage of utThe open circuit terminal voltage of the lithium ion battery.
Furthermore, there is a SOC of the lithium ion battery by the ampere-hour integration method:
wherein λ is the coulombic efficiency coefficient, QcCalibrating capacity, t, for the battery0And t is the start time and the end time, It is the current of the battery at time t,
and StThe SOC of the battery at the start and end.
And, the state space model of the lithium ion battery is:
wherein, tau1＝r1C1、τ2＝r2C2，uk(uk＝it，k) To control a variable, yk(yk＝ut，k) For observing variables, wk(wk＝[w1，k w2，k w3，k]T) For system noise interference, covariance is Q, vkTo observe noise interference, the covariance is R.
The discrete system mathematical model of the lithium ion battery is as follows:
wherein the noise interferes with wk、vkAre respectively set as wk∈(0，Q)，vk∈(0，R)。
In addition, the method for estimating the SOC of the lithium ion battery by the deep reinforcement learning Kalman filtering is to combine Kalman filtering algorithm and the deep reinforcement learning to estimate the SOC of the lithium ion battery, and has an action state value function:
wherein s ist∈χ，ut∈η，r(st，ut)，t∈[1，T]，π(ut|st)∈ρπ(st)，
γ ∈ (0, 1) is the discount factor. When r(s)t，ut)+γ max Q[st+1，ut+1]-Q[st，ut]On a time scale of → 0,
this is true. Can pass through min L (theta)Q)＝min{r(st，ut)+γ max Q[st+1，ut+1]-Q[st，ut]And optimizing and obtaining parameter replacement.
Defining the optimal Q function as:
using bayesian rules, the equation can be rewritten as:
wherein f is a transition function, i.e. sk+1＝f(sk，uk，ak). From this, set sk，ukFor the decision quantity, the best covariance can be obtained.
The invention has the advantages and positive effects that:
1. the lithium ion battery has a complex operation state, involves a plurality of coupled processes such as electrochemical reaction and charge transfer, and has strong nonlinear dynamic characteristics. For SOC estimation of a lithium ion battery, students establish different models which mainly comprise an equivalent circuit model, an electrochemical model and an artificial neuron network model. The invention uses an equivalent circuit model, which can more accurately express the external characteristics of the lithium ion battery and can represent the dynamic characteristic linear model of the battery.
2. The invention applies deep reinforcement learning, which combines the deep learning perception capability and the reinforcement learning decision capability, continuously interacts with the environment in a trial and error mode, and obtains the optimal strategy in a mode of maximizing accumulated rewards. The method can be directly controlled according to the input image, and is an artificial intelligence method closer to the human thinking mode. Such an algorithm may make the decision more reasonable.
3. The invention can ensure the optimal covariance of the system through the Bayesian rule, effectively reduces the calculated amount in the estimation process, further improves the SOC estimation precision, and has better practicability.
Drawings
FIG. 1 is a schematic diagram of an equivalent circuit of a lithium ion battery;
FIG. 2 is an OCV-SOC characteristic curve of a lithium ion battery;
FIG. 3 is a Kalman filtering SOC estimation schematic diagram of deep reinforcement learning;
FIG. 4 is a SOC estimation curve;
fig. 5 is a SOC estimation error comparison curve.
Detailed Description
The embodiments of the invention will be described in further detail below with reference to the accompanying drawings:
the invention establishes a discrete system mathematical model through a second-order RC equivalent circuit topology of the lithium ion battery, and provides a novel deep reinforcement learning Kalman filtering lithium ion battery SOC estimation method. Firstly, a state space model of the battery is established by analyzing a second-order RC equivalent circuit model of the lithium ion battery, and a discrete system mathematical model of the lithium ion battery is established by utilizing a traditional Kalman filtering algorithm. And further designing a deep reinforcement learning Kalman filtering lithium ion battery SOC estimation method by combining with an artificial intelligence thought. Finally, the best covariance is ensured by bayesian rules. Simulation results show that the SOC precision can be better improved by the algorithm.
A method for estimating the SOC of a lithium ion battery based on deep reinforcement learning Kalman filtering comprises the following steps:
The invention takes a second-order equivalent circuit model as a research object as shown in figure 1, and the mathematical model is as follows:
wherein r isoIs internal resistance of lithium ion battery, r1、r2、C1、C2Is the polarization internal resistance and polarization capacitance, i, of the lithium ion batterytIs the current of a lithium ion battery, uoIs the voltage of a resistance in a lithium ion battery, uOCVFor the open circuit voltage, u, of a lithium ion battery1、u2Respectively the internal polarization resistance r of the lithium ion battery1、r2Voltage of utThe open circuit terminal voltage of the lithium ion battery.
The SOC of the lithium ion battery is obtained by adopting an ampere-hour integration method:
wherein λ is the coulombic efficiency coefficient, QcCalibrating capacity, t, for the battery0And t is the start time and the end time, It is the current of the battery at time t,
and StThe SOC of the battery at the start and end.
Defining a state variable xk＝[sk u1，k u2，k]TCombining the formulas (1) and (2), the state space model of the lithium ion battery can be obtainedType (2):
wherein, tau1＝r1C1、τ2＝r2C2，uk(uk＝it，k) To control a variable, yk(yk＝ut，k) For observing variables, wk(wk＝[w1，k w2，k w3，k]T) For system noise interference, covariance is Q, vkTo observe noise interference, the covariance is R.
The SOC-OCV relation can be obtained through a discharge experiment. FIG. 2 is a SOC-OCV characteristic curve diagram of 18650 type lithium ion produced by Tianjin Lieshen at normal temperature (20-25 ℃).
And (3) establishing a discrete system mathematical model of the lithium ion battery by combining the formulas (1) to (3) and applying a Kalman filter:
wherein the noise interferes with wk、vkAre respectively set as wk∈(0，Q)，vk∈(0，R)。
And 2, further designing a deep reinforcement learning Kalman filtering lithium ion battery SOC estimation method according to the mathematical model in the step 1 and by combining an artificial intelligence thought.
The reinforcement learning is developed from theories such as animal learning and parameter disturbance adaptive control, and is a machine learning algorithm. Deep reinforcement learning combines the perception capability of deep learning and the decision-making capability of reinforcement learning, continuously interacts with the environment in a trial and error mode, and obtains an optimal strategy in a mode of maximizing accumulated rewards [10 ]. The resource allocation problem is solved specifically by adopting a deep Q-network (DQN), the core idea is that a value network is used as a judgment module, various actions in the current observation state are traversed based on the value network, real-time interaction is carried out with the environment, the states, the actions and reward and punishment values are stored in a memory unit, the value network is trained repeatedly by adopting a Q-learning algorithm, and finally the action capable of obtaining the maximum value is selected as output. The basic framework of the Kalman lithium battery SOC estimation based on deep reinforcement learning is shown in FIG. 3.
S in FIG. 3kFor the corresponding observation of the algorithm up to the t ( t 1, 2.. k.. n) step, ukTo observe skThe action performed below, r(s)k，uk)＝rkTo observe skLower execution action ukThe reward (or penalty) obtained is then.
The method combines a Kalman filtering algorithm with deep reinforcement learning to estimate the SOC of the lithium ion battery, and has an action state value function:
wherein s ist∈χ，ut∈η，r(st，ut)，t∈[1，T]，π(ut|st)∈ρπ(st)，
γ ∈ (0, 1) is the discount factor. When r(s)t，ut)+γ max Q[st+1，ut+1]-Q[st，ut]On a time scale of → 0,
this is true. Can pass through min L (theta)Q)＝min{r(st，ut)+γ max Q[st+1，ut+1]-Q[st，ut]And optimizing and obtaining parameter replacement.
Defining the optimal Q function as:
using bayes' rule, equation (6) can be rewritten as:
wherein f is a transition function, i.e. sk+1＝f(sk，uk，ak). From this, set sk，ukFor the decision quantity, the best covariance can be obtained.
And step 3, simulation and experimental analysis, and the best covariance is ensured through a Bayesian rule. After the simulation result is obtained, the method can be shown to be capable of improving the SOC precision.
In Matlab environment, 18650 type lithium ion charging and discharging process produced by Tianjin Lieshen company is simulated, the simulation data adopts the data of FIG. 2, and the estimation curves are shown in FIGS. 4 and 5. The initial value of the true SOC is 1, and the initial value is set to 0.9 in the experiment. Fig. 4 is a square root high order cubature kalman filter and a deep reinforcement learning kalman filter SOC estimation curve, from which it can be seen that both methods can more accurately track the setting value of the lithium ion battery SOC, wherein the method provided herein is closer to the setting value of the SOC. Fig. 5 is a comparison curve of two methods (square-root-unscented Kalman filter, SRUKF and deep-reinforcement learning Kalman filter, RLKF) for SOC estimation error, from which it can be seen that the error between the square-root unscented Kalman filter strategy estimation value and the set value is maintained at about 0.16, the error between the estimation value and the set value of the method proposed herein is maintained at about 0.14, the error is smaller than that of the former method, indicating that the SOC estimation accuracy for the lithium ion battery is higher. And further proving that the SOC estimation precision of the lithium ion battery can be improved by the deep reinforcement learning Kalman filtering.
Claims (5)
1. A method for estimating the SOC of a lithium ion battery based on deep reinforcement learning Kalman filtering comprises the following steps:
step 1, establishing a state space model of the lithium battery by analyzing a second-order RC equivalent circuit model of the lithium battery and adopting an ampere-hour integration method, carrying out parameter identification on the battery model, and constructing a discrete system mathematical model of the lithium battery by utilizing a traditional Kalman filtering algorithm.
And 2, further designing a deep reinforcement learning Kalman filtering lithium ion battery SOC estimation method according to the mathematical model in the step 1 and by combining an artificial intelligence thought.
And step 3, simulation and experimental analysis, and the best covariance is ensured through a Bayesian rule. After the simulation result is obtained, the method can be shown to be capable of improving the SOC precision.
2. The second order RC mathematical model of the lithium ion battery of claim 1 is:
wherein r isoIs internal resistance of lithium ion battery, r1、r2、C1、C2Is the polarization internal resistance and polarization capacitance, i, of the lithium ion batterytIs the current of a lithium ion battery, uoIs the voltage of a resistance in a lithium ion battery, uOCVFor the open circuit voltage, u, of a lithium ion battery1、u2Respectively the internal polarization resistance r of the lithium ion battery1、r2Voltage of utThe open circuit terminal voltage of the lithium ion battery.
Furthermore, there is a SOC of the lithium ion battery by the ampere-hour integration method:
wherein λ is the coulombic efficiency coefficient, QcCalibrating capacity, t, for the battery0And t is the start time and the end time, It is the current of the battery at time t,
and StThe SOC of the battery at the start and end.
3. The state space model of the lithium ion battery of claim 1:
wherein, tau1＝r1C1、τ2＝r2C2，uk(uk＝it，k) To control a variable, yk(yk＝ut，k) For observing variables, wk(wk＝[w1，k w2，k w3，k]T) For system noise interference, covariance is Q, vkTo observe noise interference, the covariance is R.
4. The discrete system mathematical model of a lithium-ion battery of claim 1:
wherein the noise interferes with wk、vkAre respectively set as wk∈(0，Q)，vk∈(0，R)。
5. The deep reinforcement learning Kalman filtering lithium ion battery SOC estimation method of claim 1, which combines Kalman filtering algorithm and deep reinforcement learning to estimate the lithium ion battery SOC, and has an action state value function:
wherein s ist∈χ，ut∈η，r(st，ut)，t∈[1，T]，π(ut|st)∈ρπ(st)，
γ ∈ (0, 1) is the discount factor. When r(s)t，ut)+γmax Q[st+1，ut+1]-Q[st，ut]On a time scale of → 0,
this is true. Can pass through min L (theta)Q)＝min{r(st，ut)+γmax Q[st+1，ut+1]-Q[st，ut]And optimizing and obtaining parameter replacement.
Defining the optimal Q function as:
using bayesian rules, the equation can be rewritten as:
wherein f is a transition function, i.e. sk+1＝f(sk，uk，ak). From this, set sk，ukFor the decision quantity, the best covariance can be obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910422522.3A CN111948539A (en) | 2019-05-17 | 2019-05-17 | Kalman filtering lithium ion battery SOC estimation method based on deep reinforcement learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910422522.3A CN111948539A (en) | 2019-05-17 | 2019-05-17 | Kalman filtering lithium ion battery SOC estimation method based on deep reinforcement learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111948539A true CN111948539A (en) | 2020-11-17 |
Family
ID=73336502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910422522.3A Pending CN111948539A (en) | 2019-05-17 | 2019-05-17 | Kalman filtering lithium ion battery SOC estimation method based on deep reinforcement learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111948539A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112858928A (en) * | 2021-03-08 | 2021-05-28 | 安徽理工大学 | Lithium battery SOC estimation method based on online parameter identification |
| CN113125965A (en) * | 2021-04-01 | 2021-07-16 | 清华大学 | Method, device and equipment for detecting lithium separation of battery and storage medium |
| CN113420444A (en) * | 2021-06-23 | 2021-09-21 | 南通大学 | Lithium ion battery SOC estimation method based on parameter online identification |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105699903A (en) * | 2016-01-15 | 2016-06-22 | 宁波飞拓电器有限公司 | Emergency lamp cell SOC estimation method based on variational Bayesian CKF |
| US20180100898A1 (en) * | 2016-10-06 | 2018-04-12 | Mitsubishi Electric Research Laboratories, Inc. | Hybrid Battery State Sensor |
| CN108896924A (en) * | 2018-07-09 | 2018-11-27 | 哈尔滨工业大学 | The charge states of lithium ion battery estimation method merged based on depth confidence network and Kalman filtering |
| CN109407007A (en) * | 2018-12-24 | 2019-03-01 | 广东省智能制造研究所 | A kind of battery charge state detection method and device |
| CN109669134A (en) * | 2019-02-27 | 2019-04-23 | 浙江科技学院 | A kind of evaluation method of the SOC based on Kalman filtering method |
| CN109669132A (en) * | 2019-01-21 | 2019-04-23 | 西北工业大学 | A kind of battery charge state estimation method based on variation Bayesian filter |
-
2019
- 2019-05-17 CN CN201910422522.3A patent/CN111948539A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105699903A (en) * | 2016-01-15 | 2016-06-22 | 宁波飞拓电器有限公司 | Emergency lamp cell SOC estimation method based on variational Bayesian CKF |
| US20180100898A1 (en) * | 2016-10-06 | 2018-04-12 | Mitsubishi Electric Research Laboratories, Inc. | Hybrid Battery State Sensor |
| CN108896924A (en) * | 2018-07-09 | 2018-11-27 | 哈尔滨工业大学 | The charge states of lithium ion battery estimation method merged based on depth confidence network and Kalman filtering |
| CN109407007A (en) * | 2018-12-24 | 2019-03-01 | 广东省智能制造研究所 | A kind of battery charge state detection method and device |
| CN109669132A (en) * | 2019-01-21 | 2019-04-23 | 西北工业大学 | A kind of battery charge state estimation method based on variation Bayesian filter |
| CN109669134A (en) * | 2019-02-27 | 2019-04-23 | 浙江科技学院 | A kind of evaluation method of the SOC based on Kalman filtering method |
Non-Patent Citations (3)
| Title |
|---|
| MINKO KIM等: "State of Charge Estimation for Lithium Ion Battery Based on Reinforcement Learning", 《IFAC-PAPERSONLINE》 * |
| 李司光等: "锂离子电池荷电状态预测方法研究", 《北京理工大学学报》 * |
| 高洪森等: "基于深度强化学习卡尔曼滤波锂离子电池SOC估计", 《天津科技大学学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112858928A (en) * | 2021-03-08 | 2021-05-28 | 安徽理工大学 | Lithium battery SOC estimation method based on online parameter identification |
| CN112858928B (en) * | 2021-03-08 | 2024-02-06 | 安徽理工大学 | Lithium battery SOC estimation method based on online parameter identification |
| CN113125965A (en) * | 2021-04-01 | 2021-07-16 | 清华大学 | Method, device and equipment for detecting lithium separation of battery and storage medium |
| CN113125965B (en) * | 2021-04-01 | 2021-11-19 | 清华大学 | Method, device and equipment for detecting lithium separation of battery and storage medium |
| CN113420444A (en) * | 2021-06-23 | 2021-09-21 | 南通大学 | Lithium ion battery SOC estimation method based on parameter online identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lin et al. | State of charge estimation with the adaptive unscented Kalman filter based on an accurate equivalent circuit model | |
| CN110568361B (en) | Method for predicting health state of power battery | |
| Liu et al. | State of charge prediction framework for lithium-ion batteries incorporating long short-term memory network and transfer learning | |
| CN111007399B (en) | Lithium battery state of charge prediction method based on improved generation countermeasure network | |
| Ma et al. | Co-estimation of state of charge and state of health for lithium-ion batteries based on fractional-order model with multi-innovations unscented Kalman filter method | |
| Ismail et al. | Battery state of charge estimation using an Artificial Neural Network | |
| He et al. | State-of-charge estimation of lithium ion batteries based on adaptive iterative extended Kalman filter | |
| CN111581904A (en) | Lithium battery SOC and SOH collaborative estimation method considering influence of cycle number | |
| CN113740736B (en) | Electric vehicle lithium battery SOH estimation method based on deep network self-adaption | |
| Mamo et al. | Long short-term memory with attention mechanism for state of charge estimation of lithium-ion batteries | |
| Xie et al. | Optimized multi-hidden layer long short-term memory modeling and suboptimal fading extended Kalman filtering strategies for the synthetic state of charge estimation of lithium-ion batteries | |
| CN110941929A (en) | Battery health state assessment method based on ARMA and Elman neural network combined modeling | |
| CN107741569A (en) | A kind of evaluation method of the lithium battery charge state based on segment extension Kalman filtering | |
| CN109001640B (en) | Data processing method and device for power battery | |
| Li et al. | Review of lithium-ion battery state of charge estimation | |
| CN111948560A (en) | Lithium battery health state estimation method based on multi-factor evaluation model | |
| CN112098878B (en) | End-to-end neural network establishment method for SOH estimation and RUL prediction of lithium battery | |
| CN111337832A (en) | Power battery multidimensional fusion SOC and SOH online joint estimation method | |
| CN111948539A (en) | Kalman filtering lithium ion battery SOC estimation method based on deep reinforcement learning | |
| CN109839599B (en) | Lithium ion battery SOC estimation method based on second-order EKF algorithm | |
| CN107741568A (en) | A kind of lithium battery SOC estimation method that optimization RBF neural is shifted based on state | |
| Xu et al. | State of charge estimation for liquid metal battery based on an improved sliding mode observer | |
| CN114660464A (en) | Lithium ion battery state of charge estimation method | |
| CN114114038A (en) | Lithium battery SOC and available capacity joint estimation method under full-life and full-temperature conditions | |
| CN116359742B (en) | Energy storage battery state of charge on-line estimation method and system based on deep learning combination extended Kalman filtering |
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: 20201117 |