CN106093615A - The health status method of estimation of super capacitor energy-storage module - Google Patents
The health status method of estimation of super capacitor energy-storage module Download PDFInfo
- Publication number
- CN106093615A CN106093615A CN201610364241.3A CN201610364241A CN106093615A CN 106093615 A CN106093615 A CN 106093615A CN 201610364241 A CN201610364241 A CN 201610364241A CN 106093615 A CN106093615 A CN 106093615A
- Authority
- CN
- China
- Prior art keywords
- super capacitor
- module
- monomer
- energy
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- 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
Abstract
The invention discloses the health status method of estimation of a kind of super capacitor energy-storage module, comprise the following steps: S100: set super-capacitor module monomer electric parameter threshold value;S200: the service data of Real-time Collection super capacitor module;S300: combined the electric characteristic parameter of each monomer in neural network model determines super capacitor module by described service data;S400: judge whether the electric characteristic parameter of each monomer falls into threshold values interval;S500: super capacitor energy-storage module is carried out Breakdown Maintenance.The health status method of estimation of a kind of super capacitor energy-storage module that the present invention provides, can meet extensive super capacitor energy-storage systematic difference needs, can provide data support for the repair based on condition of component of energy-storage system.
Description
Technical field
The invention belongs to technical field of energy storage, specifically, the health status relating to a kind of super capacitor energy-storage module is estimated
Meter method.
Background technology
With wind energy and solar energy, the generation of electricity by new energy technology as representative is to solve environmental pollution and the weight of fossil energy shortage
Want means.But in actual applications, output electric energy difficulty unstable, grid-connected and electric energy can be caused due to the undulatory property of this type of energy
The shortcoming such as of poor quality.For solving this problem, energy storage technology is considered as generation of electricity by new energy technology and the important support ring in application
Joint, thus by the most attention of countries in the world research worker.
In various electrochemical energy storing device, the combination property of super capacitor between traditional capacitor and accumulator,
In energy density and power density aspect of performance, there is the most complementary performance.Can high current charge-discharge and making additionally, also have
By advantages such as temperature range width, therefore in technical field of energy storage, there is broad prospect of application.
In actual application, super capacitor energy-storage system is generally made up of super-capacitor module connection in series-parallel, each inside modules
It is again to be constituted by more piece super capacitor is monomer series-connected.Therefore the reliability of energy-storage system overall performance, depends on each monomer
Reliability.Due to super-capacitor module in use by performance discordance, ambient temperature, discharge and recharge between internal each monomer
The impact of the factors such as multiplying power and recycling number of times can produce the deterioration of performance.The important application such as this external field of new energy generation
Safety and reliability is had higher requirements by occasion, it is therefore desirable to know the key messages such as the health status of super capacitor in time
Dawn.If that is, the health status of super-capacitor module can be estimated exactly in actual moving process, just can be in time
Reasonably whole energy-storage system safeguarded and overhaul, thus being conducive to improving the reliability of energy-storage system and extending it using
Life-span.
At present, in examined literature borders, the health status method of estimation about super-capacitor module is reported less, lacks
A kind of super-capacitor module health status method of estimation being applicable to practical implementation.
Summary of the invention
In view of this, the technical problem to be solved is to provide the health status of a kind of super capacitor energy-storage module
Method of estimation.
In order to solve above-mentioned technical problem, the invention discloses the health status estimation side of a kind of super capacitor energy-storage module
Method, comprises the following steps:
S100: set super-capacitor module monomer electric parameter threshold value;
S200: the service data of Real-time Collection super capacitor module;
S300: combined the electric characteristic of each monomer in neural network model determines super capacitor module by described service data
Parameter;
S400: judge whether the electric characteristic parameter of each monomer falls into threshold values interval;
S500: super capacitor energy-storage module is carried out Breakdown Maintenance.
Further, in described S100, described super-capacitor module monomer electric parameter threshold value is, super capacitor energy-storage mould
The normal range of operation of the electric characteristic parameter of each super capacitor monomer in block.
Further, in described S200, described service data include: operating current, running voltage, working environment temperature
Degree.
Further, in described S200, described service data is real-time in super capacitor energy-storage module actual moving process
Gather.
Further, in described S300, described electric characteristic parameter includes: equivalent series impedance and capacitance.
Further, in described S300, the modeling method of described neural network model comprises the following steps:
S310: utilize neural metwork training data set that neural network model is trained, the model after being trained;
S320: utilize model measurement data set that neural network model is tested;
S330: carry out error relative analysis by the output of neural network model and super capacitor monomer are truly exported
Judge the precision of neural network model;
S331: if precision meets requirement, i.e. modeling terminate;
S332: if precision is unsatisfactory for requirement, then re-start training and test, until model accuracy meets requirement and is
Only.
Further, described neural metwork training data set includes: electric current, voltage and temperature data.
Further, described model measurement data set includes: electric current, voltage and temperature data.
Further, in described S320, described method of testing is:
S321: described model measurement data set is applied to described neural network model and obtains model prediction output;
S322: described model measurement data set is applied on described super capacitor monomer obtain object and truly exports;
S323: described model prediction output truly exports with described object and carries out error relative analysis.
Further, in described S500, if fault is to be lost efficacy by certain several monomer in this module to cause, then can use
These fault monomers are replaced process, if all monomers all lost efficacy in this module, then change this super capacitor energy-storage
Module.
Compared with prior art, the present invention can obtain and include techniques below effect:
1) the health status method of estimation for super capacitor energy-storage module of the present invention, can meet extensive super electricity
The application holding energy-storage system needs, and can provide data support for the repair based on condition of component of energy-storage system.
2) the health status method of estimation for super capacitor energy-storage module of the present invention, each monomer in analyzing module
The neural network model used during current electric characteristic parameter value, has generalization ability strong, and the feature that model accuracy is high is permissible
Ensure to obtain health status estimated result more accurately.
3) the health status method of estimation for super capacitor energy-storage module of the present invention, its estimated result can navigate to
Specifically occurring the monomer that health status deteriorates in module, data are pointed to clearly, therefore when energy-storage module is carried out Breakdown Maintenance
Can replace and occur that the monomer of deterioration retains the normal monomer of health status, reduce system maintenance cost.
4) the health status method of estimation for super capacitor energy-storage module of the present invention, uses threshold value comparative approach, side
Method the most easily realizes, workable, has the good suitability and using value.
5) the health status method of estimation for super capacitor energy-storage module of the present invention can be as energy-storage system management
A submodule in system is applied when running with system in real time, it is possible to be applied to super capacitor system as an independent functional independence
Making the experimental analysis of business, acquired results has directive significance for improvement and the optimization of super capacitor production technology.Certainly, implement
Arbitrary product of the present invention must be not necessarily required to reach all the above technique effect simultaneously.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the present invention, this
Bright schematic description and description is used for explaining the present invention, is not intended that inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the super capacitor energy-storage module health status method of estimation flow chart that the embodiment of the present invention provides;
Fig. 2 is the super capacitor monomer neural network model modeling method figure that the embodiment of the present invention provides.
Detailed description of the invention
Describe embodiments of the present invention in detail below in conjunction with drawings and Examples, thereby how the present invention is applied
Technological means solves technical problem and reaches the process that realizes of technology effect and can fully understand and implement according to this.
The health status method of estimation of a kind of super capacitor energy-storage module that embodiments of the invention provide, as it is shown in figure 1,
Comprise the following steps:
S100: set super-capacitor module monomer electric parameter threshold value;
S200: the service data of Real-time Collection super capacitor module;
S300: combined the electric characteristic of each monomer in neural network model determines super capacitor module by described service data
Parameter;
S400: judge whether the electric characteristic parameter of each monomer falls into threshold values interval;
S500: super capacitor energy-storage module is carried out Breakdown Maintenance.
In the present embodiment, in described S100, described super-capacitor module monomer electric parameter threshold value is, super capacitor energy-storage
The normal range of operation of the electric characteristic parameter of each super capacitor monomer in module.
Alternatively, in described S200, described service data include: operating current, running voltage, operating ambient temperature.
Alternatively, in described S200, described service data is adopted in super capacitor energy-storage module actual moving process in real time
Collection.
Alternatively, in described S300, described electric characteristic parameter includes: equivalent series impedance and capacitance.
Alternatively, in described S500, if fault is to be lost efficacy by certain several monomer in this module to cause, then it is right to use
These fault monomers are replaced process, if all monomers all lost efficacy in this module, then change this super capacitor energy-storage mould
Block.
As in figure 2 it is shown, the modeling method of the described neural network model in S300, comprise the following steps:
S310: utilize neural metwork training data set 100 that neural network model is trained, the nerve after being trained
Network model 200;
S320: utilize model measurement data set 300 that neural network model 200 is tested;
S330: true by the model prediction of neural network model 200 being exported the object of 210 and super capacitor monomer 400
Real output 410 carries out error relative analysis to judge the precision of neural network model;
S331: if precision meets requirement, i.e. modeling terminate;
S332: if precision is unsatisfactory for requirement, then re-start training and test, until model accuracy meets requirement and is
Only.
Alternatively, described neural metwork training data set includes: electric current, voltage and temperature data.
Alternatively, described model measurement data set includes: electric current, voltage and temperature data.
Described method of testing in S320 is:
S321: described model measurement data set is applied to described neural network model and obtains model prediction output;
S322: described model measurement data set is applied on described super capacitor monomer obtain object and truly exports;
S323: described model prediction output truly exports with described object and carries out error relative analysis.
The health status method of estimation of a kind of super capacitor energy-storage module provided in embodiments of the invention, including following
Technique effect:
1) the health status method of estimation for super capacitor energy-storage module of the present invention, can meet extensive super electricity
The application holding energy-storage system needs, and can provide data support for the repair based on condition of component of energy-storage system.
2) the health status method of estimation for super capacitor energy-storage module of the present invention, each monomer in analyzing module
The neural network model used during current electric characteristic parameter value, has generalization ability strong, and the feature that model accuracy is high is permissible
Ensure to obtain health status estimated result more accurately.
3) the health status method of estimation for super capacitor energy-storage module of the present invention, its estimated result can navigate to
Specifically occurring the monomer that health status deteriorates in module, data are pointed to clearly, therefore when energy-storage module is carried out Breakdown Maintenance
Can replace and occur that the monomer of deterioration retains the normal monomer of health status, reduce system maintenance cost.
4) the health status method of estimation for super capacitor energy-storage module of the present invention, uses threshold value comparative approach, side
Method the most easily realizes, workable, has the good suitability and using value.
5) the health status method of estimation for super capacitor energy-storage module of the present invention can be as energy-storage system management
A submodule in system is applied when running with system in real time, it is possible to be applied to super capacitor system as an independent functional independence
Making the experimental analysis of business, acquired results has directive significance for improvement and the optimization of super capacitor production technology.
Also, it should be noted term " includes " or its any other variant is intended to comprising of nonexcludability, from
And make to include that the commodity of a series of key element or system not only include those key elements, but also its including being not expressly set out
His key element, or also include the key element intrinsic for this commodity or system.In the case of there is no more restriction, by language
The key element that sentence " including ... " limits, it is not excluded that there is also other in the commodity including described key element or system
Identical element.
Described above illustrate and describes some preferred embodiments of the present invention, but as previously mentioned, it should be understood that the present invention
Be not limited to form disclosed herein, be not to be taken as the eliminating to other embodiments, and can be used for other combinations various,
Amendment and environment, and can be in invention contemplated scope described herein, by above-mentioned teaching or the technology of association area or knowledge
It is modified.And the change that those skilled in the art are carried out and change are without departing from the spirit and scope of the present invention, the most all should be at this
In the protection domain of bright claims.
Claims (10)
1. the health status method of estimation of a super capacitor energy-storage module, it is characterised in that comprise the following steps:
S100: set super-capacitor module monomer electric parameter threshold value;
S200: the service data of Real-time Collection super capacitor module;
S300: combined the electric characteristic ginseng of each monomer in neural network model determines super capacitor module by described service data
Number;
S400: judge whether the electric characteristic parameter of each monomer falls into threshold values interval;
S500: super capacitor energy-storage module is carried out Breakdown Maintenance.
2. the method for claim 1, it is characterised in that in described S100, described super-capacitor module monomer is electrically joined
Number threshold value is, the normal range of operation of the electric characteristic parameter of each super capacitor monomer in super capacitor energy-storage module.
3. the method for claim 1, it is characterised in that in described S200, described service data includes: operating current,
Running voltage, operating ambient temperature.
4. the method for claim 1, it is characterised in that in described S200, described service data is at super capacitor energy-storage
Real-time Collection in module actual moving process.
5. the method for claim 1, it is characterised in that in described S300, described electric characteristic parameter includes: equivalent string
Connection resistance value and capacitance.
6. the method for claim 1, it is characterised in that in described S300, the modeling method of described neural network model
Comprise the following steps:
S310: utilize neural metwork training data set that neural network model is trained, the model after being trained;
S320: utilize model measurement data set that neural network model is tested;
S330: carry out error relative analysis judge by the output of neural network model and super capacitor monomer are truly exported
The precision of neural network model;
S331: if precision meets requirement, i.e. modeling terminate;
S332: if precision is unsatisfactory for requirement, then re-start training and test, require until model accuracy meets.
7. method as claimed in claim 6, it is characterised in that in described S320, described neural metwork training data set includes:
Electric current, voltage and temperature data.
8. method as claimed in claim 6, it is characterised in that in described S320, described model measurement data set includes: electricity
Stream, voltage and temperature data.
9. method as claimed in claim 6, it is characterised in that in described S320, the method for described test is:
S321: described model measurement data set is applied to described neural network model and obtains model prediction output;
S322: described model measurement data set is applied on described super capacitor monomer obtain object and truly exports;
S323: described model prediction output truly exports with described object and carries out error relative analysis.
10. the method for claim 1, it is characterised in that in described S500, if fault is by this module, certain is several
Monomer lost efficacy and caused, then use and these fault monomers are replaced process, if all monomers all lost efficacy in this module, then
Change this super capacitor energy-storage module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610364241.3A CN106093615A (en) | 2016-05-26 | 2016-05-26 | The health status method of estimation of super capacitor energy-storage module |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610364241.3A CN106093615A (en) | 2016-05-26 | 2016-05-26 | The health status method of estimation of super capacitor energy-storage module |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106093615A true CN106093615A (en) | 2016-11-09 |
Family
ID=57229345
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610364241.3A Pending CN106093615A (en) | 2016-05-26 | 2016-05-26 | The health status method of estimation of super capacitor energy-storage module |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106093615A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109239485A (en) * | 2018-08-20 | 2019-01-18 | 国电南瑞科技股份有限公司 | Energy storage tramcar super capacitor fault recognition method and system based on BP neural network |
CN109239489A (en) * | 2018-08-29 | 2019-01-18 | 中车株洲电力机车有限公司 | A kind of health status on-line analysis, device and medium for energy-storage system |
CN110531163A (en) * | 2019-04-18 | 2019-12-03 | 中国人民解放军国防科技大学 | Bus capacitance state monitoring method for suspension chopper of maglev train |
CN110929451A (en) * | 2019-10-24 | 2020-03-27 | 同济大学 | Fuel cell single voltage consistency prediction method |
CN113281607A (en) * | 2021-04-30 | 2021-08-20 | 南通江海电容器股份有限公司 | Detection system and display device based on super capacitor module monomer voltage |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103389426A (en) * | 2013-07-31 | 2013-11-13 | 上海仪器仪表研究所 | Super-capacitor consistency testing device and testing method |
CN104062504A (en) * | 2014-06-13 | 2014-09-24 | 华为技术有限公司 | Super-capacitor detecting circuit |
CN104300685A (en) * | 2013-07-15 | 2015-01-21 | 同济大学 | Monitoring system for large scale super capacitor energy storage module |
CN104297577A (en) * | 2013-07-15 | 2015-01-21 | 同济大学 | Super capacitor-based aging state estimation detection system and method |
CN105480101A (en) * | 2015-11-17 | 2016-04-13 | 北京长城华冠汽车科技股份有限公司 | Power distribution method and device for hybrid power supply electric automobile |
-
2016
- 2016-05-26 CN CN201610364241.3A patent/CN106093615A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104300685A (en) * | 2013-07-15 | 2015-01-21 | 同济大学 | Monitoring system for large scale super capacitor energy storage module |
CN104297577A (en) * | 2013-07-15 | 2015-01-21 | 同济大学 | Super capacitor-based aging state estimation detection system and method |
CN103389426A (en) * | 2013-07-31 | 2013-11-13 | 上海仪器仪表研究所 | Super-capacitor consistency testing device and testing method |
CN104062504A (en) * | 2014-06-13 | 2014-09-24 | 华为技术有限公司 | Super-capacitor detecting circuit |
CN105480101A (en) * | 2015-11-17 | 2016-04-13 | 北京长城华冠汽车科技股份有限公司 | Power distribution method and device for hybrid power supply electric automobile |
Non-Patent Citations (1)
Title |
---|
闫晓磊 等: "HEV超级电容自适应模糊神经网络建模研究", 《湖南大学学报(自然科学版)》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109239485A (en) * | 2018-08-20 | 2019-01-18 | 国电南瑞科技股份有限公司 | Energy storage tramcar super capacitor fault recognition method and system based on BP neural network |
CN109239489A (en) * | 2018-08-29 | 2019-01-18 | 中车株洲电力机车有限公司 | A kind of health status on-line analysis, device and medium for energy-storage system |
WO2020042441A1 (en) * | 2018-08-29 | 2020-03-05 | 中车株洲电力机车有限公司 | Online health status analysis method for energy storage system, device, and medium |
CN110531163A (en) * | 2019-04-18 | 2019-12-03 | 中国人民解放军国防科技大学 | Bus capacitance state monitoring method for suspension chopper of maglev train |
CN110929451A (en) * | 2019-10-24 | 2020-03-27 | 同济大学 | Fuel cell single voltage consistency prediction method |
CN113281607A (en) * | 2021-04-30 | 2021-08-20 | 南通江海电容器股份有限公司 | Detection system and display device based on super capacitor module monomer voltage |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111584952B (en) | Method and system for online evaluation of electrochemical cells of energy storage power station | |
CN106093615A (en) | The health status method of estimation of super capacitor energy-storage module | |
CN105977553B (en) | The retired battery echelon multiplexed network grade bidirectional energy-storage supervising platform of electric car | |
CN104270091B (en) | A kind of photovoltaic power generation equipment method for diagnosing faults based on monitoring system | |
CN103472331B (en) | A kind of photovoltaic generation fault diagnosis system based on photovoltaic physical model | |
CN105789716A (en) | Generalized battery management system | |
CN104297577B (en) | Ageing state estimation detecting system and method based on ultracapacitor | |
CN105652106A (en) | Comprehensive performance testing method and apparatus of energy storage system | |
CN103176138B (en) | A kind of electric battery preservation & testing method | |
CN110174555A (en) | Traction drive support capacitor life estimation method based on multi-state operation | |
CN106154180A (en) | Energy-storage battery charge/discharge anomaly detection method and detecting system | |
CN105938578A (en) | Large-scale photovoltaic power station equivalent modeling method based on clustering analysis | |
CN107145707A (en) | It is a kind of to count and photovoltaic is exerted oneself the power distribution network transformer planing method of uncertain and overall life cycle cost | |
CN106845562B (en) | The fault monitoring system and data processing method of photovoltaic module | |
CN103887792B (en) | A kind of low-voltage distribution network modeling method containing distributed power source | |
CN106230378A (en) | A kind of diagnostic method of photovoltaic plant group string fault | |
CN103728569B (en) | A kind of accumulator capacity Forecasting Methodology based on multifactor Grey Relational Model | |
CN110363334A (en) | Grid-connected grid line loss prediction technique based on Grey Neural Network Model | |
CN109615273A (en) | A kind of electric car electrically-charging equipment method for evaluating state and system | |
Ferdowsi et al. | New monitoring approach for distribution systems | |
CN105406818A (en) | Photovoltaic electricity generating assembly optimized monitoring method and photovoltaic electricity generating assembly optimized monitoring system | |
CN109992911B (en) | Photovoltaic module rapid modeling method based on extreme learning machine and IV characteristics | |
CN113595132B (en) | Photovoltaic online parameter identification method based on maximum power point and hybrid optimization algorithm | |
CN106093638A (en) | A kind of Voltage Drop root-mean-square value and the mode identification method falling frequency estimation | |
Zhu et al. | Online state of charge EKF estimation for LiFePO 4 battery management systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20161109 |