CN115267586B - SOH (solid oxide fuel cell) evaluation method of lithium battery - Google Patents
SOH (solid oxide fuel cell) evaluation method of lithium battery Download PDFInfo
- Publication number
- CN115267586B CN115267586B CN202210811062.5A CN202210811062A CN115267586B CN 115267586 B CN115267586 B CN 115267586B CN 202210811062 A CN202210811062 A CN 202210811062A CN 115267586 B CN115267586 B CN 115267586B
- Authority
- CN
- China
- Prior art keywords
- battery
- soh
- data
- voltage
- neural network
- 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.)
- Active
Links
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 19
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 19
- 238000011156 evaluation Methods 0.000 title abstract description 20
- 239000000446 fuel Substances 0.000 title description 2
- 239000007787 solid Substances 0.000 title description 2
- 238000013528 artificial neural network Methods 0.000 claims abstract description 25
- 238000004146 energy storage Methods 0.000 claims abstract description 22
- 230000036541 health Effects 0.000 claims abstract description 19
- 238000011084 recovery Methods 0.000 claims abstract description 17
- 238000010606 normalization Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 34
- 238000012360 testing method Methods 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 6
- GELKBWJHTRAYNV-UHFFFAOYSA-K lithium iron phosphate Chemical compound [Li+].[Fe+2].[O-]P([O-])([O-])=O GELKBWJHTRAYNV-UHFFFAOYSA-K 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000015556 catabolic process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 238000006731 degradation reaction Methods 0.000 description 5
- 238000013178 mathematical model Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012983 electrochemical energy storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 229910001416 lithium ion Inorganic materials 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000005245 sintering Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The embodiment of the application provides a lithium battery SOH evaluation method for an energy storage power station, which relates to a recovery voltage characteristic, and comprises the following steps: acquiring influencing factors of the battery health state during each cycle; wherein the influencing factors of the battery state of health are characterized by a resistance and a recovery voltage; acquiring the battery capacity after each cycle to obtain the health state of the battery; converting the considered parameters into a neural network learning sample vector; carrying out normalization processing and inverse normalization processing on the acquired learning sample vector to obtain an inverse normalization vector; and training the neural network by using the normalized vector to obtain a neural network training model for predicting the SOH of the battery.
Description
Technical Field
The application provides a data processing method, in particular to a lithium battery SOH evaluation method.
Background
The mathematical modeling is to build a mathematical model according to the actual problem, solve the mathematical model, and then solve the actual problem according to the result. When an actual problem is required to be analyzed and studied from a quantitative perspective, people need to establish a mathematical model by expressing mathematical symbols and languages on the basis of the work of in-depth investigation, understanding of object information, making simplifying assumptions, analyzing internal rules and the like.
Electric energy is certainly an indispensable energy source for human life and work.
The lithium battery has the advantages of higher discharge platform, long cycle service life, environmental protection, safety and the like, and has become an important power source of the electric automobile. Meanwhile, with the rapid development of micro-grid technology, a large-scale electrochemical energy storage power station is an effective means for generating power by using renewable energy sources such as solar energy, wind power and the like. The lithium iron phosphate battery is widely applied due to the advantages of high charge and discharge efficiency, reliable operation, less pollution to the environment and the like. The energy storage power station can also increase the elasticity of the power grid, and reduce the impact range of the load impact of the power grid and the fault of the power grid. In the use process of the whole life cycle of the battery, the characteristic degradation phenomena such as capacity, energy and power of the battery can occur along with the increase of the use time and the charge and discharge cycle times of the battery, if the characteristic degradation phenomena cannot be found and processed in time, the degradation phenomena are more serious, so that the battery is bulged, broken, heated and the like, and when serious, the battery is subjected to thermal runaway and thermal diffusion, so that serious consequences such as fire disasters of automobiles and energy storage power stations are caused. For the scene of dense battery arrangement of automobiles and energy storage power stations, the occurrence of fire often leads to serious personal casualties and property loss. In order to ensure safe and reliable operation of the battery, the state of health (SOH) evaluation and accurate short-term state prediction are carried out on the battery, so that early warning defects or faulty batteries can be found in time, and accident potential is reduced. The technology has important significance for improving the safety of the electric automobile, expanding the scale of the energy storage power station and promoting the realization of the carbon neutralization target, and is a hot spot of current research.
The existing lithium battery SOH evaluation methods can be roughly divided into two main categories: model-based methods and data-driven based methods. The model-based method is mainly used for constructing a degradation mathematical model of the lithium battery based on an equivalent circuit model and an electrochemical mechanism model. The method is suitable for SOH evaluation of single or small amount of lithium batteries, and has large workload for building the model for the scenes of huge battery quantity of electric automobiles, energy storage power stations and the like, and the timeliness and the accuracy of the evaluation are greatly reduced. The method based on the data is to utilize the test data of the battery performance, and obtain the evolution rule of the lithium battery performance for the performance and life prediction by carrying out information mining on the data. The method can avoid constructing and updating complex models, has good prediction efficiency for a large number of battery packs, but only considers common parameters such as current, voltage, internal resistance and the like of the lithium battery when the prior art collects data for evaluation, and does not consider the design, installation and use modes of the lithium battery, so that the selection of driving data characteristics and the accuracy and reliability of the evaluation still need to be improved.
Chinese patent application number CN201811200371.9, filing date 2018-10-16, entitled "method for estimating health status of lithium ion battery on line"; the method discloses an on-line estimation method for the health state of a lithium ion battery. The method mainly comprises the following steps: the capacity increment method is adopted to obtain the characteristic parameters from the capacity increment curve, the multi-output Gaussian process regression model method is utilized to complete the establishment of the characteristic parameters and the SOH function model, the potential relevance between different outputs can be better utilized, and the estimation accuracy of SOH is improved. The battery does not need to undergo a complete charge and discharge process, the characteristic parameters are simply extracted, and the application of the method in the BMS is facilitated, but the method only considers the charge and discharge parameters of the battery, and does not consider the actual condition that the voltage of the battery changes when the battery stands still.
Chinese patent application number CN202010621694.6, filing date 2020-06-30, entitled "method and System for predicting the lifetime of Battery cells in an energy storage Power station"; the method and the system for predicting the service life of the battery monomer in the energy storage power station are disclosed. The method mainly comprises the following steps: and collecting historical test data of the cyclic degradation of the battery capacity, and secondarily screening out the characteristic with high sensitivity. The method considers the parameters of internal resistance, discharge time and specific voltage, but does not consider the change condition of the corresponding parameters when the battery voltage changes when the battery is still standing.
Disclosure of Invention
The application provides a data processing method which can be used for more accurately evaluating the SOH of the lithium battery for the energy storage power station taking the recovery voltage characteristic into consideration.
In order to achieve the above objective, an embodiment of the present application provides a lithium battery SOH evaluation method for an energy storage power station, which takes into account a recovery voltage characteristic, including:
Step 1, obtaining influencing factors of the battery health state in each cycle; wherein the influencing factors of the battery state of health are characterized by a resistance and a recovery voltage; acquiring the battery capacity after each cycle to obtain the health state of the battery;
The voltage ：U10,U11,U12,U13,U14,U15,U16,U17,U18,U19, of the battery is collected every 1 second within 10 seconds after the constant current charge or the constant current discharge is finished each time, wherein the voltage collected by the nth battery is as follows ：Un0,Un1,Un2,Un3,Un4,Un5,Un6,Un7,Un8,Un9;
The rated voltage of the battery is U N, and the measured voltage and the rated voltage difference of the battery in the mth second after the charging of the nth battery are calculated through a formula delta U nm＝UN-Unm;
ΔUn0,ΔUn1,ΔUn2,ΔUn3,ΔUn4,ΔUn5,ΔUn6,ΔUn7,ΔUn8,ΔUn9;
according to the strength of the relation between the lithium iron phosphate battery SOH and the characteristic parameters and the acquired experimental data, selecting the recovery voltage and the basic operation data of the energy storage battery to reconstruct into a sample, wherein the battery SOH is a sample label;
wherein the battery SOH utilization capacity is expressed as: Wherein, Q 0 is the design capacity of the battery, which is calibrated by manufacturers or obtained by a test mode, and Q now is the current maximum capacity of the battery;
Step 2, converting the considered parameters into a neural network learning sample vector, wherein the ith vector
Wherein I ci is the current of the charge of the ith cycle; u OCi is the Open Circuit voltage of the ith cycle; SOC i is the State of Charge (State of Charge) for the ith cycle, expressed as a percentage of battery remaining power; deltaU nm is the measured voltage and rated voltage difference of the battery in the m second after the battery in the nth battery is charged; SOH i is the State of Health (State of Health) of the battery in the ith cycle;
Step 3, carrying out normalization processing on the acquired learning sample vector, wherein a normalization formula is as follows: Wherein x max is the maximum value of the data; x min is the minimum of the data;
Normalizing the data obtained through the neural network, and performing inverse normalization processing; the inverse normalization formula is: x i'＝(xmax-xmin)xi+xmin;
The inverse normalized vector thus obtained:
And 4, training the neural network by using the normalized vector to obtain a neural network training model for predicting the SOH of the battery.
Further, the method further comprises:
collecting working current, voltage, resistance and working temperature parameters of a battery;
And transmitting the acquired data to a local database of the energy storage power station for storage, wherein the original data is reserved in the database in the station for at least 3 months for subsequent monitoring and use.
Further, the method further comprises:
and taking one part of the obtained normalized vector as a training set sample and the other part as a test set sample.
The technical scheme of the application has the following beneficial effects: the technical scheme provides a lithium battery SOH evaluation method for an energy storage power station considering the recovery voltage characteristics, and the scheme has at least one of the following advantages:
1. The recovery voltage is added as an input vector for evaluating the neural network, so that the accuracy of the evaluation effect is improved, and the evaluation speed is shortened;
2. the recovery voltage is obtained from the original voltage data of the battery, other sensing and recording equipment is not required to be added, and the increase of construction and maintenance cost is avoided;
3. The recovery voltage is added as an input vector, so that the generalization performance of the evaluation neural network is improved, the energy storage equipment for other different scales is convenient to transplant, and the repeated design evaluation method and the waste of time and funds are avoided;
4. The method has reasonable scheme, simple principle and easy realization, and can fully exert the advantages of the evaluation neural network.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present application;
Fig. 2 is a schematic diagram of a neural network according to an embodiment of the present application.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
The application aims to provide a lithium battery SOH evaluation method for an energy storage power station considering recovery voltage characteristics, which is used for solving the problem of accurate evaluation of the health state of a lithium iron phosphate energy storage battery in an electric automobile and a large-scale electrochemical energy storage power station.
The embodiment of the application provides a lithium battery SOH evaluation method for an energy storage power station, which takes the recovery voltage characteristic into consideration, wherein the flow is shown in a figure 1, and a neural network shown in a figure 2 is adopted; the method comprises the following steps:
And obtaining the resistance and the recovery voltage at each cycle as influencing factors representing the health state of the battery, and obtaining the battery capacity after each cycle to obtain the health state of the battery. The battery is put aside for a period of time after being charged or discharged with constant current each time so as to achieve electrochemical balance, and the voltage of the battery changes to a certain extent during the putting stage, and the voltage which changes due to the putting is called a recovery voltage. The voltage of the battery is collected every 1 second within 10 seconds after each constant current charge or constant current discharge is finished
U10,U11,U12,U13,U14,U15,U16,U17,U18,U19,
Wherein the voltage acquired by the nth battery is
Un0,Un1,Un2,Un3,Un4,Un5,Un6,Un7,Un8,Un9.
Wherein the rated voltage of the battery is U N, and the measured voltage and the rated voltage difference of the battery at the mth second after the charging of the nth battery are calculated through a formula delta U nm＝UN-Unm
ΔUn0,ΔUn1,ΔUn2,ΔUn3,ΔUn4,ΔUn5,ΔUn6,ΔUn7,ΔUn8,ΔUn9.
Besides recovering voltage data, parameters such as battery working current, voltage, resistance, working temperature and the like are collected at the same time, the collected data are transmitted to a local database of an energy storage power station for storage, and original data are reserved in the database in the station for at least 3 months, so that follow-up monitoring and use are facilitated.
And selecting the recovery voltage and the basic operation data of the energy storage battery to reconstruct into a sample according to the strength of the relation between the lithium iron phosphate battery SOH and the characteristic parameters and the acquired experimental data, wherein the battery SOH is a sample label. The battery SOH is represented by capacity, Q 0 is the battery design capacity, the parameter can be calibrated by the manufacturer or obtained by means of testing, Q now is the current maximum capacity of the battery, and this is used as a learning sample label, and the following relation is provided:
Converting the considered parameters into a neural network learning sample vector, wherein the ith vector
Wherein I ci is the current of the charge of the ith cycle; u OCi is the Open Circuit voltage of the ith cycle; SOC i is the State of Charge (State of Charge) for the ith cycle, expressed as a percentage of battery remaining power; deltaU nm is the measured voltage and rated voltage difference of the battery in the m second after the battery in the nth battery is charged; SOH i is the State of Health (State of Health) of the battery in the ith cycle.
In order to ensure the speed of processing data and the reliability of convergence of the neural network and prevent the possible influence of the type and the size of the data on the prediction result of the neural network, the data needs to be normalized to meet the preset condition. The normalization process may allow the data sizes to be relatively closer together so that some sample data values are widely separated and data with a smaller number of samples may be properly processed.
The normalization formula is:
The data obtained through the neural network is normalized and also needs to be subjected to inverse normalization processing.
The inverse normalization formula is:
xi'＝(xmax-xmin)xi+xmin
Wherein: x max represents the maximum value of the data; x min represents the minimum of the data.
The inverse normalized vector thus obtained:
Training the neural network after taking the vector as a sample to form the neural network for judging and predicting the SOH of the battery. Experimental group data set 80% of the samples as training sets and 20% as test sets. After the neural network is formed, a new sample is introduced for calculation, so that short-term SOH prediction of the battery in the energy storage power station is realized.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer programs. When the computer program is loaded and executed on a computer, the flow or functions according to the embodiments of the present application are fully or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer program may be stored in or transmitted from one computer readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means from one website, computer, server, or data center. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a high-density digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a solid-state disk (solid-state drive STATE DISK, SSD)), or the like.
Those of ordinary skill in the art will appreciate that: the first, second, etc. numbers referred to in the present application are merely for convenience of description and are not intended to limit the scope of the embodiments of the present application, but also to indicate the sequence.
At least one of the present application may also be described as one or more, and a plurality may be two, three, four or more, and the present application is not limited thereto. In the embodiment of the application, for a technical feature, the technical features of the technical feature are distinguished by a first, a second, a third, a, B, a C, a D and the like, and the technical features described by the first, the second, the third, the a, the B, the C, the D are not in sequence or in order of magnitude.
The correspondence relation shown in each table in the application can be configured or predefined. The values of the information in each table are merely examples, and may be configured as other values, and the present application is not limited thereto. In the case of the correspondence between the configuration information and each parameter, it is not necessarily required to configure all the correspondence shown in each table. For example, in the table of the present application, the correspondence relation shown by some rows may not be configured. For another example, appropriate morphing adjustments, e.g., splitting, merging, etc., may be made based on the tables described above. The names of the parameters indicated in the tables may be other names which are understood by the communication device, and the values or expressions of the parameters may be other values or expressions which are understood by the communication device. When the tables are implemented, other data structures may be used, for example, an array, a queue, a container, a stack, a linear table, a pointer, a linked list, a tree, a graph, a structure, a class, a heap, a hash table, or a hash table.
Predefined in the present application may be understood as defining, predefining, storing, pre-negotiating, pre-configuring, curing, or pre-sintering.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (3)
1. A lithium battery SOH assessment method, comprising:
Step 1, obtaining influencing factors of the battery health state in each cycle; wherein the influencing factors of the battery state of health are characterized by a resistance and a recovery voltage; acquiring the battery capacity after each cycle to obtain the health state of the battery;
The voltage ：U10,U11,U12,U13,U14,U15,U16,U17,U18,U19, of the battery is collected every 1 second within 10 seconds after the constant current charge or the constant current discharge is finished each time, wherein the voltage collected by the nth battery is as follows ：Un0,Un1,Un2,Un3,Un4,Un5,Un6,Un7,Un8,Un9;
The rated voltage of the battery is U N, and the measured voltage and the rated voltage difference of the battery in the mth second after the charging of the nth battery are calculated through a formula delta U nm＝UN-Unm;
ΔUn0,ΔUn1,ΔUn2,ΔUn3,ΔUn4,ΔUn5,ΔUn6,ΔUn7,ΔUn8,ΔUn9;
according to the strength of the relation between the lithium iron phosphate battery SOH and the characteristic parameters and the acquired experimental data, selecting the recovery voltage and the basic operation data of the energy storage battery to reconstruct into a sample, wherein the battery SOH is a sample label;
wherein the battery SOH utilization capacity is expressed as: Wherein, Q 0 is the design capacity of the battery, which is calibrated by manufacturers or obtained by a test mode, and Q now is the current maximum capacity of the battery;
Step 2, converting the considered parameters into a neural network learning sample vector, wherein the ith vector
Wherein I ci is the current of the charge of the ith cycle; u OCi is the open circuit voltage of the ith cycle; SOC i is the state of charge of the ith cycle, expressed as a percentage of the remaining battery power; deltaU nm is the measured voltage and rated voltage difference of the battery in the m second after the battery in the nth battery is charged; SOH i is the state of health of the battery in the ith cycle;
Step 3, carrying out normalization processing on the acquired learning sample vector, wherein a normalization formula is as follows: Wherein x max is the maximum value of the data; x min is the minimum of the data;
Normalizing the data obtained through the neural network, and performing inverse normalization processing; the inverse normalization formula is: x i'＝(xmax-xmin)xi+xmin;
The inverse normalized vector thus obtained:
Step 4, training the neural network by using the normalized vector to obtain a neural network training model for predicting the SOH of the battery;
The vector is used as a sample, then the neural network is trained, a neural network for judging and predicting the SOH of the battery is formed, 80% of samples are set as a training set in experimental group data, and 20% of samples are set as a testing set.
2. The lithium battery SOH assessment method according to claim 1, characterized in that the method further comprises:
collecting working current, voltage, resistance and working temperature parameters of a battery;
And transmitting the acquired data to a local database of the energy storage power station for storage, wherein the original data is reserved in the database in the station for at least 3 months for subsequent monitoring and use.
3. The lithium battery SOH assessment method according to claim 1, characterized in that the method further comprises:
and taking one part of the obtained normalized vector as a training set sample and the other part as a test set sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210811062.5A CN115267586B (en) | 2022-07-11 | 2022-07-11 | SOH (solid oxide fuel cell) evaluation method of lithium battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210811062.5A CN115267586B (en) | 2022-07-11 | 2022-07-11 | SOH (solid oxide fuel cell) evaluation method of lithium battery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115267586A CN115267586A (en) | 2022-11-01 |
| CN115267586B true CN115267586B (en) | 2024-10-15 |
Family
ID=83764477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210811062.5A Active CN115267586B (en) | 2022-07-11 | 2022-07-11 | SOH (solid oxide fuel cell) evaluation method of lithium battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115267586B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115616415B (en) * | 2022-12-06 | 2023-04-07 | 北京志翔科技股份有限公司 | Method, device and equipment for evaluating state of battery pack and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107329094A (en) * | 2017-08-23 | 2017-11-07 | 北京新能源汽车股份有限公司 | Power battery state of health estimation method and device |
| CN110515012A (en) * | 2019-09-04 | 2019-11-29 | 武汉美格科技股份有限公司 | The method for diagnosing battery health status |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007522450A (en) * | 2004-01-26 | 2007-08-09 | ジョンソン コントロールズ テクノロジー カンパニー | System and method for monitoring vehicle battery |
| US10459034B2 (en) * | 2014-12-26 | 2019-10-29 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating state of health (SOH) of battery |
| US10302709B2 (en) * | 2016-11-30 | 2019-05-28 | Cadex Electronics Inc. | Battery state-of-health determination using multi-factor normalization |
| CN108805217B (en) * | 2018-06-20 | 2020-10-23 | 山东大学 | Lithium ion battery health state estimation method and system based on support vector machine |
| DE102020212299A1 (en) * | 2020-09-29 | 2022-03-31 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method and device for operating a system for providing predicted aging states of electrical energy stores for a device using machine learning methods |
| CN113009349B (en) * | 2021-04-09 | 2024-01-05 | 哈尔滨工业大学 | Lithium ion battery health state diagnosis method based on deep learning model |
| CN113447823B (en) * | 2021-05-31 | 2022-06-21 | 国网山东省电力公司滨州供电公司 | Method for health prediction of storage battery pack |
| CN113917337A (en) * | 2021-10-13 | 2022-01-11 | 国网福建省电力有限公司 | Battery health state estimation method based on charging data and LSTM neural network |
| CN114675186A (en) * | 2022-02-24 | 2022-06-28 | 华南理工大学 | Lithium ion battery health state prediction method based on graph neural network |
| CN114578237A (en) * | 2022-02-28 | 2022-06-03 | 西安交通大学 | Method, system and equipment for rapidly estimating health state of lithium ion battery based on constant-current charging time |
-
2022
- 2022-07-11 CN CN202210811062.5A patent/CN115267586B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107329094A (en) * | 2017-08-23 | 2017-11-07 | 北京新能源汽车股份有限公司 | Power battery state of health estimation method and device |
| CN110515012A (en) * | 2019-09-04 | 2019-11-29 | 武汉美格科技股份有限公司 | The method for diagnosing battery health status |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115267586A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111584952B (en) | Method and system for online evaluation of electrochemical cells of energy storage power station | |
| Kaur et al. | Deep learning networks for capacity estimation for monitoring SOH of Li‐ion batteries for electric vehicles | |
| She et al. | Battery aging assessment for real-world electric buses based on incremental capacity analysis and radial basis function neural network | |
| CN110224192B (en) | Method for predicting service life of power battery by gradient utilization | |
| CN107290679B (en) | The Intelligentized battery method for detecting health status of charging pile is shared for electric car | |
| CN114280479B (en) | Retired battery rapid sorting method based on electrochemical impedance spectroscopy | |
| CN113281671A (en) | Lithium ion battery remaining service life prediction method and system based on IGS-SVM | |
| Chen et al. | State of health estimation of lithium-ion batteries based on equivalent circuit model and data-driven method | |
| CN112686380A (en) | Neural network-based echelon power cell consistency evaluation method and system | |
| CN112666479A (en) | Battery service life prediction method based on charging cycle fusion | |
| Binelo et al. | Mathematical modeling and parameter estimation of battery lifetime using a combined electrical model and a genetic algorithm | |
| CN111460656B (en) | Method and system for evaluating operation life of communication power supply of electric power machine room | |
| Khera et al. | Valve regulated lead acid battery diagnostic system based on infrared thermal imaging and fuzzy algorithm | |
| CN115267586B (en) | SOH (solid oxide fuel cell) evaluation method of lithium battery | |
| Singh et al. | State of charge estimation techniques of Li-ion battery of electric vehicles | |
| Tian et al. | Consistency evaluation of electric vehicle battery pack: multi-feature information fusion approach | |
| CN115128468A (en) | Chemical energy storage battery PHM undervoltage fault prediction method | |
| Chen et al. | Data-driven statistical analysis and diagnosis of networked battery systems | |
| Li et al. | Screening of retired lithium-Ion batteries using incremental capacity charging curve-based residual capacity estimation method for facilitating sustainable circular lithium-ion battery system | |
| Liu et al. | Data-driven internal temperature estimation methods for sodium-ion battery using electrochemical impedance spectroscopy | |
| CN113391214A (en) | Battery micro-fault diagnosis method based on battery charging voltage ranking change | |
| CN116449244A (en) | Lithium battery aging track early prediction method and system based on single discharge curve | |
| Li et al. | VRLA battery fault prediction for data center based on random forest model and feature enhancement method | |
| Huang et al. | Long-Term Health State Estimation of Energy Storage Lithium-Ion Battery Packs | |
| CN118446684B (en) | Chemical battery energy storage system optimization method based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |