CN113627671A - SOH prediction calculation method for single battery in energy storage scene - Google Patents
SOH prediction calculation method for single battery in energy storage scene Download PDFInfo
- Publication number
- CN113627671A CN113627671A CN202110918428.4A CN202110918428A CN113627671A CN 113627671 A CN113627671 A CN 113627671A CN 202110918428 A CN202110918428 A CN 202110918428A CN 113627671 A CN113627671 A CN 113627671A
- Authority
- CN
- China
- Prior art keywords
- battery
- curve
- data
- voltage
- peak
- 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
- 238000004146 energy storage Methods 0.000 title claims abstract description 25
- 238000004364 calculation method Methods 0.000 title claims abstract description 15
- 230000008859 change Effects 0.000 claims abstract description 11
- 238000003062 neural network model Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 24
- 210000002569 neuron Anatomy 0.000 claims description 21
- 210000004027 cell Anatomy 0.000 claims description 20
- 238000007600 charging Methods 0.000 claims description 16
- 230000007423 decrease Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000010277 constant-current charging Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 230000001502 supplementing effect Effects 0.000 claims description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 abstract description 8
- 229910001416 lithium ion Inorganic materials 0.000 abstract description 8
- 230000036541 health Effects 0.000 abstract description 7
- 230000032683 aging Effects 0.000 abstract description 4
- 238000010219 correlation analysis Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- GELKBWJHTRAYNV-UHFFFAOYSA-K lithium iron phosphate Chemical compound [Li+].[Fe+2].[O-]P([O-])([O-])=O GELKBWJHTRAYNV-UHFFFAOYSA-K 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Secondary Cells (AREA)
Abstract
The invention provides a prediction and calculation method for SOH of a single battery in an energy storage scene, which is used for researching the internal change trend of a lithium ion battery in the aging process and the change rule of a capacity increment curve and analyzing the change rule of the capacity increment curve and the internal change rule of the battery; extracting and estimating the characteristic parameters of the battery health state by using the capacity increment curve data, analyzing the change rule of the capacity increment curve, and selecting key characteristic parameters capable of representing the battery health state estimation according to the correlation analysis result; a lithium ion battery SOH estimation model based on the characteristic parameters of the capacity increment curve is established, the characteristic parameters in the capacity increment curve are determined to be used as model input quantity, the battery residual capacity is used as model output quantity, and the estimation of the battery SOH is realized by utilizing a neural network model.
Description
Technical Field
The invention belongs to the technical field of electric power, and particularly relates to a prediction calculation method for single battery SOH in an energy storage scene.
Background
The State Of Health (SOH) Of a Battery is a comprehensive evaluation index for judging the aging degree Of the Battery, is directly related to the stable operation and power output capability Of an energy storage System, and is one Of the difficulties in online estimation Of a Battery Management System (BMS). The capacity increment analysis is an important method for analyzing the fading mechanism of the lithium ion battery, and reveals the relationship between the external characteristics and the internal changes of the battery. The invention provides an efficient and accurate battery SOH estimation method by combining key information contained in an Increment Analysis (ICA) curve and a battery SOH estimation model established by original data in the charging process, and is beneficial to the refined operation and management of an energy storage system.
Disclosure of Invention
The invention aims to solve the technical problems and provides a method for predicting and calculating the SOH of a single battery in an energy storage scene.
In order to achieve the purpose, the invention adopts the following technical scheme:
a prediction calculation method for single battery SOH in an energy storage scene comprises the following steps:
step 1, collecting operation data of a battery of an energy storage system, wherein the operation data comprises voltage and current data of a single battery, cleaning the battery data, filtering abnormal data and filling missing data;
step 2, grading the voltage of the single batteries according to the charging end time and calculating the capacity of part of the batteries according to an ampere-hour method;
step 3, calculating a capacity increment curve, namely an IC curve, according to the operation data of the battery;
step 4, extracting the characteristics of the IC curve according to the IC curve;
step 5, constructing a neural network model, taking the IC curve characteristics and the charging data as the characteristics as the data of an input layer, and taking the corresponding capacity as an output layer to train the network;
and 6, taking the battery with the capacity which is not calculated by adopting an ampere-hour method as a belt prediction sample, predicting the belt prediction sample by using a neural network to obtain the capacity of the single battery and calculating the SOH.
Preferably, in the step 1, the input acquisition mode changes according to different use scenes, and if real-time calculation is needed, data transmission and calculation need to be carried out through a cloud end; offline computation processes the local data after it is exported.
Preferably, in step 2, the step of grading the single batteries is as follows: greater than 3.55V, defined as a class i cell, indicating a cell with more severe attenuation; less than 3.55V and greater than 3.4V, defined as class II cells, representing cells with less attenuation; less than 3.4V, defined as class III battery, indicating a battery with a better state;
finding out voltage and current data belonging to the same battery pack in the class I battery aiming at class II battery data, supplementing the voltage and the current which are larger than the voltage value in the class I battery into the class II battery by taking the voltage at the moment of finishing charging in the class II battery as a reference, and adopting the same operation aiming at the class III battery; after the voltage of the battery reaches 3.6V, the voltage data of the later time are set to be 2.8V;
the capacities of the I-type and II-type batteries are directly calculated by an ampere-hour method, and the capacity of the III-type batteries is obtained by predicting by a neural network model.
Preferably, in step 3, the IC curve is calculated by calculating dQ/dV, Q represents the amount of charge of the battery, V represents the voltage of the battery, and reflects the ratio of the amount of charge per unit of the battery to the corresponding voltage variation; the IC curve is calculated as follows:
when the constant current charging current is I, the charging amount Q is It, and dQ is I · dt, then:
dQ/dV＝I·dt/dV；
in a more general scenario, dQ/dV can be expressed as a function of V:
preferably, in step 4, the peak value of the peak ii and the peak position in the IC curve decrease and the envelope area of the peak ii moves to the right and decreases over time in the same battery, and the peak value of the peak ii moves backward and the peak value of the peak i decreases in two batteries in the same period, so the peak values of the peak i, the peak ii and the peak iii and the voltages and envelope areas corresponding to the peak value of the peak ii are extracted from the IC curve and used as the extraction features of the IC curve.
Preferably, in step 5, the neural network model includes an input layer, a hidden layer and an output layer; 363 neurons are contained in the input layer, and 1-360 neurons are used for inputting voltage data; 361-363 neurons were used to input IC curve features; the hidden layer has 2 layers, each layer comprises 20 neurons; the output layer has 1 neuron, which represents the predicted capacity; the connecting mode of the neuron in the previous layer and the neuron in the current layer is full connection, and no loop exists.
After the technical scheme is adopted, the invention has the following advantages:
1. according to the invention, the internal change trend of the lithium ion battery and the change rule of the capacity increment curve in the aging process are researched, the change of the capacity increment curve and the change rule of the battery are analyzed, and the theoretical basis for acquiring the health state information of the battery by using the capacity increment curve is obtained.
2. The invention extracts and estimates the characteristic parameters of the battery health state by using the capacity increment curve data, analyzes the change rule of the capacity increment curve, selects the voltage value corresponding to each peak value and peak value in the curve as a comparison sequence, and uses the battery residual capacity as a reference sequence. And comparing the relevance between each parameter and the residual capacity of the battery, and selecting a key characteristic parameter capable of representing the estimation of the health state of the battery according to the relevance analysis result.
3. The method establishes a lithium ion battery SOH estimation model based on the characteristic parameters of the capacity increment curve, determines the characteristic parameters in the capacity increment curve as model input quantity, uses the battery residual capacity as model output quantity, and realizes the estimation of the battery SOH by using a neural network model. And training the model by using the battery cycle aging data, and analyzing model precision difference and confidence interval influence under different training parameters. The model estimation accuracy is detected through verifying the data result, and the result shows that the estimation model has higher accuracy.
Drawings
FIG. 1 is a flow chart of a calculation method for predicting SOH of a single battery in an energy storage scene;
FIG. 2 is a voltage curve of a single battery in an energy storage scenario;
FIG. 3 is an IC curve of a single cell in an energy storage scenario;
fig. 4 is an IC curve of a single battery at different periods in an energy storage scenario;
fig. 5 is an IC curve of different unit cells in the same period in an energy storage scenario;
fig. 6 is a schematic diagram of a partial connection structure of a neural network.
Detailed Description
The present invention will be described in further detail with reference to the following drawings and specific examples.
As shown in fig. 1, a method for predicting and calculating SOH of a single battery in an energy storage scenario includes the following steps:
step 1, data acquisition:
collecting battery operation data of an energy storage system, wherein the voltage collection precision is required to be within 10 mv;
the input acquisition mode changes according to different use scenes, and if real-time calculation is needed, data transmission and calculation are needed through a cloud end; offline computation processes the local data after it is exported. The data required in the present invention includes voltage and current data of the unit cells.
And cleaning the operation data of the battery, filtering abnormal data and filling missing data.
Step 2, data preprocessing:
firstly, grading the battery according to the voltage at the moment when the battery finishes charging: greater than 3.55V, defined as a class i cell, indicating a cell with more severe attenuation; less than 3.55V and greater than 3.4V, defined as class II cells, representing cells with less attenuation; less than 3.4V, defined as a class iii cell, indicates a cell in a more favorable state.
For class II battery data, voltage and current data belonging to the same battery pack in the class I battery are required to be found out, and the voltage and the current which are larger than the voltage value in the class I battery are supplemented to the class II battery by taking the voltage at the moment of finishing charging in the class II battery as a reference. The same operation is also taken for class iii batteries.
After the battery voltage after the above-mentioned processing reached 3.6V, the voltage data of the subsequent time was set to 2.8V. For example, when the 1# battery is at 4:35, the voltage reaches 3.6V and the charging is finished, and the voltage data after the time becomes 2.8V.
The capacities of the I-type and II-type batteries can be directly calculated by an ampere-hour method, and the capacity of the III-type batteries can be predicted by a model.
Step 3, calculating an IC curve:
the capacity increment analysis method of the lithium ion battery, namely ICA, is a commonly used method for researching the decay mechanism analysis of the lithium ion battery. The method can convert a flat voltage plateau to a peak in the incremental curve. From the data over the battery cycle, a capacity increment curve can be calculated, which can be characterized as the internal electrochemical changes of the battery.
The capacity increment curve is calculated as dQ/dV, wherein Q represents the amount of charge of the battery and V represents the voltage of the battery. The index reflects the ratio of the charging capacity of the battery unit to the corresponding voltage variation, and at the voltage platform, the voltage variation is small, while the charging capacity is large, and the index value is large. This value can be calculated as follows:
a common capacity increment curve is calculated based on battery data in a constant current charging process, where a constant current charging current is I, a charging amount Q is It, and dQ is I · dt, then:
dQ/dV＝I·dt/dV
in a more general scenario, dQ/dV can be expressed as a function of V:
fig. 2 and fig. 3 are voltage curves of a single battery and corresponding IC curves in an energy storage scenario. Fig. 4 is an IC curve of a single battery at different periods in an energy storage scenario; fig. 5 is an IC curve of different unit cells in the same period in an energy storage scenario;
and 4, extracting characteristics:
through the observation of a large number of IC curves and the combination of a large number of papers[1],[2]The following conclusions were found:
1. as the same battery goes on with the passage of time (the attenuation degree is increased), the peak value of the II peak in the IC curve is reduced, the peak position (the voltage corresponding to the peak value) is shifted to the right, and the envelope area of the II peak is reduced;
2. in two batteries in the same period, the peak position of the battery II with more serious attenuation is shifted backwards, and the peak value of the battery I is reduced.
And extracting the peak values of the peak I, the peak II and the peak III, and the voltage and the envelope surface area corresponding to the peak value of the peak II from the IC curve. It should be noted that, in addition to extracting features from the IC curve, voltage data during charging is also taken as features.
Among them, reference is made to:
[1] zhanghao, lithium ion battery SOH estimation based on IC curve characteristic parameters and DSP implementation [ D ]. Beijing: Beijing traffic university.2018.
[2] The application of a Shaoxing red, Zhengying, Qianlian, Hongkun, Liubo lithium iron phosphate storage battery IC curve in a health state estimation algorithm [ C ]. Chongqing, China society of automotive Engineers (annual meeting) culture collection 2020.
Step 5, constructing and training a model:
the invention takes a neural network as a model, and constructs a functional relation between input characteristics and capacity through the excellent nonlinear fitting capacity of the neural network, wherein the network is divided into 3 parts: an input layer, a hidden layer, and an output layer. 363 neurons are contained in the input layer, and 1-360 neurons are used for inputting voltage data; the 361-363 neurons were used to input the characteristics of the IC curves. The hidden layer has 2 layers, each layer containing 20 neurons. The output layer has 1 neuron, representing the predicted volume. The connecting mode of the neuron in the previous layer and the neuron in the current layer is full connection, and no loop exists. Fig. 6 shows a part of the connection structure of the network part.
The data used to train the model here were samples of class i and class ii battery compositions, with the data set for class iii battery compositions as the test set. Through the adjustment of the model parameters, the error on the verification set is about 2.5%.
Step 6, predicting and calculating SOH:
transmitting the data characteristics of the III batteries into the model to obtain predicted value capacity; the capacities of class I and class II were calculated by the ampere-hour method. And the final SOH value is calculated by dividing the current capacity by the capacity of the single battery from the factory.
Taking an energy storage power station matched with a certain data center as an example, the rated capacity of a single battery core used by the power station is 250Ah, the rated voltage is 3.2V, and the initial capacity is 0.8 kwh. After 14 months of operation, data were collected for all cells in the plant, their IC curves were calculated and characteristics were obtained, and the capacities of all cells were calculated and SOH was calculated using the method described above. The predicted results are shown in the following table:
TABLE 1 prediction results
Statistics shows that the SOH of the single battery is 70.85% in the range of 80% to 90%, the SOH of the single battery is 27.05% in the range of 70% to 80%, and the SOH of the rest of batteries is below 70%.
Other embodiments of the present invention than the preferred embodiments described above will be apparent to those skilled in the art from the present invention, and various changes and modifications can be made therein without departing from the spirit of the present invention as defined in the appended claims.
Claims (6)
1. A prediction calculation method for single battery SOH in an energy storage scene is characterized by comprising the following steps:
step 1, collecting operation data of a battery of an energy storage system, wherein the operation data comprises voltage and current data of a single battery, cleaning the battery data, filtering abnormal data and filling missing data;
step 2, grading the voltage of the single batteries according to the charging end time and calculating the capacity of part of the batteries according to an ampere-hour method;
step 3, calculating a capacity increment curve, namely an IC curve, according to the operation data of the battery;
step 4, extracting the characteristics of the IC curve according to the IC curve;
step 5, constructing a neural network model, taking the IC curve characteristics and the charging data as the characteristics as the data of an input layer, and taking the corresponding capacity as an output layer to train the network;
and 6, taking the battery with the capacity which is not calculated by adopting an ampere-hour method as a belt prediction sample, predicting the belt prediction sample by using a neural network to obtain the capacity of the single battery and calculating the SOH.
2. The energy storage scene single battery SOH prediction calculation method of claim 1, wherein in the step 1, the input acquisition mode changes according to different use scenes, and if real-time calculation is needed, data transmission and calculation are needed through a cloud end; offline computation processes the local data after it is exported.
3. The method for predicting and calculating the SOH of the single batteries in the energy storage scene according to claim 1, wherein in the step 2, the step of grading the single batteries is as follows: greater than 3.55V, defined as a class i cell, indicating a cell with more severe attenuation; less than 3.55V and greater than 3.4V, defined as class II cells, representing cells with less attenuation; less than 3.4V, defined as class III battery, indicating a battery with a better state;
finding out voltage and current data belonging to the same battery pack in the class I battery aiming at class II battery data, supplementing the voltage and the current which are larger than the voltage value in the class I battery into the class II battery by taking the voltage at the moment of finishing charging in the class II battery as a reference, and adopting the same operation aiming at the class III battery; after the voltage of the battery reaches 3.6V, the voltage data of the later time are set to be 2.8V;
the capacities of the I-type and II-type batteries are directly calculated by an ampere-hour method, and the capacity of the III-type batteries is obtained by predicting by a neural network model.
4. The method according to claim 1, wherein in step 3, the IC curve is calculated dQ/dV, Q represents the amount of charge of the battery, V represents the voltage of the battery, and reflects the ratio of the amount of charge per unit of the battery to the amount of change in the corresponding voltage; the IC curve is calculated as follows:
when the constant current charging current is I, the charging amount Q is It, and dQ is I · dt, then:
dQ/dV＝I·dt/dV；
in a more general scenario, dQ/dV can be expressed as a function of V:
5. the method as claimed in claim 1, wherein in step 4, the peak value of the ii peak in the IC curve decreases and the peak position shifts to the right and the envelope area of the ii peak decreases with the passage of time, and the peak value of the ii peak of the battery with more severe attenuation shifts back and the peak value of the i peak decreases with the passage of time in the same battery, so that the peak values of the i peak, the ii peak and the iii peak and the voltage and the envelope area corresponding to the ii peak are extracted from the IC curve as the extraction features of the IC curve.
6. The energy storage scene single battery SOH prediction calculation method of claim 1, wherein in the step 5, the neural network model comprises an input layer, a hidden layer and an output layer; 363 neurons are contained in the input layer, and 1-360 neurons are used for inputting voltage data; 361-363 neurons were used to input IC curve features; the hidden layer has 2 layers, each layer comprises 20 neurons; the output layer has 1 neuron, which represents the predicted capacity; the connecting mode of the neuron in the previous layer and the neuron in the current layer is full connection, and no loop exists.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110918428.4A CN113627671A (en) | 2021-08-11 | 2021-08-11 | SOH prediction calculation method for single battery in energy storage scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110918428.4A CN113627671A (en) | 2021-08-11 | 2021-08-11 | SOH prediction calculation method for single battery in energy storage scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113627671A true CN113627671A (en) | 2021-11-09 |
Family
ID=78384339
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110918428.4A Pending CN113627671A (en) | 2021-08-11 | 2021-08-11 | SOH prediction calculation method for single battery in energy storage scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627671A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114942392A (en) * | 2022-04-14 | 2022-08-26 | 中国长江三峡集团有限公司 | Electrochemical aging mechanism and data-driven SOH estimation method for energy storage lithium battery |
| CN115219913A (en) * | 2022-09-19 | 2022-10-21 | 合肥原力众合能源科技有限公司 | Power battery full-life-cycle management system based on capacity increment method |
| WO2023130776A1 (en) * | 2022-01-07 | 2023-07-13 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting working condition health status of battery in energy storage power station |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108445406A (en) * | 2018-03-13 | 2018-08-24 | 桂林电子科技大学 | A kind of power battery health status method of estimation |
| CN111443293A (en) * | 2020-03-30 | 2020-07-24 | 青岛大学 | Lithium battery state of health (SOH) estimation method based on data driving |
| WO2020191800A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Method for predicting remaining service life of lithium-ion battery employing wde-optimized lstm network |
-
2021
- 2021-08-11 CN CN202110918428.4A patent/CN113627671A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108445406A (en) * | 2018-03-13 | 2018-08-24 | 桂林电子科技大学 | A kind of power battery health status method of estimation |
| WO2020191800A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Method for predicting remaining service life of lithium-ion battery employing wde-optimized lstm network |
| CN111443293A (en) * | 2020-03-30 | 2020-07-24 | 青岛大学 | Lithium battery state of health (SOH) estimation method based on data driving |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023130776A1 (en) * | 2022-01-07 | 2023-07-13 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting working condition health status of battery in energy storage power station |
| CN114942392A (en) * | 2022-04-14 | 2022-08-26 | 中国长江三峡集团有限公司 | Electrochemical aging mechanism and data-driven SOH estimation method for energy storage lithium battery |
| CN114942392B (en) * | 2022-04-14 | 2024-03-22 | 中国长江三峡集团有限公司 | Electrochemical aging mechanism and data driving-based SOH estimation method for energy storage lithium battery |
| CN115219913A (en) * | 2022-09-19 | 2022-10-21 | 合肥原力众合能源科技有限公司 | Power battery full-life-cycle management system based on capacity increment method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113627671A (en) | SOH prediction calculation method for single battery in energy storage scene | |
| CN112034356B (en) | GP-UKF-based online SOH estimation method for electric vehicle power battery | |
| CN106443474B (en) | A kind of electrokinetic cell system service life Decline traits quickly know method for distinguishing | |
| CN112433169B (en) | Cloud power battery health degree evaluation system and method | |
| CN111443293A (en) | Lithium battery state of health (SOH) estimation method based on data driving | |
| CN110045298A (en) | A kind of diagnostic method of power battery pack parameter inconsistency | |
| CN111948546A (en) | Lithium battery health degree evaluation method and system | |
| CN112051511A (en) | Power battery state of health estimation method and system based on multichannel technology | |
| CN111352032A (en) | Lithium battery dynamic peak power prediction method | |
| CN109633456B (en) | Power lithium battery pack SOC estimation method based on segmented voltage identification method | |
| CN111064253A (en) | Battery health degree rapid evaluation method based on average discrete Frechet distance | |
| CN106998086A (en) | MW class energy-accumulating power station battery management method and its system | |
| CN112433170B (en) | Method for identifying parameter difference of single batteries of series battery pack | |
| CN111366864B (en) | Battery SOH on-line estimation method based on fixed voltage rise interval | |
| Sun et al. | Study of parameters identification method of Li-ion battery model for EV power profile based on transient characteristics data | |
| CN113640674B (en) | Lithium ion battery available capacity estimation method based on optimized Gaussian process regression | |
| CN111123136A (en) | Online measuring device and online measuring method for health state of lithium ion battery | |
| CN115389936A (en) | Online prediction method for continuous peak power capability of digital-analog hybrid driven lithium battery | |
| CN114609523A (en) | Online battery capacity detection method, electronic equipment and storage medium | |
| CN116298934A (en) | Modeling method of prediction network for lithium battery health state estimation | |
| CN114966411A (en) | Method for rapidly estimating battery capacity based on battery charging segment data | |
| CN109116246B (en) | Lead-acid storage battery abuse overdischarge performance evaluation method and capacity recovery method | |
| CN206542219U (en) | A kind of MW class energy-accumulating power station battery management system | |
| Zhao et al. | From Grayscale Image to Battery Aging Awareness—A New Battery Capacity Estimation Model With Computer Vision Approach | |
| CN110007234B (en) | Performance test method and system of power battery/battery pack and electric automobile |
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 |