CN110146817A - The diagnostic method of lithium battery failure - Google Patents
The diagnostic method of lithium battery failure Download PDFInfo
- Publication number
- CN110146817A CN110146817A CN201910393300.3A CN201910393300A CN110146817A CN 110146817 A CN110146817 A CN 110146817A CN 201910393300 A CN201910393300 A CN 201910393300A CN 110146817 A CN110146817 A CN 110146817A
- Authority
- CN
- China
- Prior art keywords
- classifier
- lithium battery
- battery failure
- diagnostic method
- parameter
- 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
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/3644—Constructional arrangements
- G01R31/3648—Constructional arrangements comprising digital calculation means, e.g. for performing an algorithm
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
Abstract
This application discloses a kind of diagnostic methods of lithium battery failure, comprising: s1, based on single classifier constructs integrated classifier, establishes lithium battery failure modes prediction model；S2, feature, and the input as lithium battery failure modes prediction model are extracted from battery BMS system.Method of the invention can be improved the fault location and maintenance efficiency of battery management system.It is also beneficial to the weak link of discovery system simultaneously, optimization battery management system design carries out, fundamentally lifting system stability.
Description
Technical field
This application involves technical field of new energy, more particularly to a kind of diagnostic method of lithium battery failure.
Background technique
Lithium-ion battery systems also have become group indispensable in electric car and distributed micro-grid energy storage system
At part.But along with power battery manufacturing technology level and the uncertain factor of running conditions of vehicle, power battery is being transported
It unavoidably will appear overtension or too low in row, electric current is excessive or too small, the states such as too high or too low for temperature, use process
In severe operating environment, aging, abuse etc., will lead to the generation of dependent failure.Battery failures pole without detection has can
Irreversible damage can be caused to battery, or even catastrophic failure can occur in extreme circumstances.Therefore, timely and accurately
Diagnosis is carried out to the failure in battery operation to be very important.Battery management system is usually by battery status monitoring, battery shape
The subsystems such as state analysis, cell safety protection, energy hole management, battery information management are constituted.Some battery management systems are also
With the modules such as internal communication bus and computer communication link.Since structure is complicated, system is huge, failure for battery management system
Has the characteristics that uncertainty, to accurate, the quick positioning of failure, high-efficient maintenance proposes challenge.
Fault definition is system due to there is at least one or more parameter, characteristic lower than normal index, system occurs
Lose the behavior of normal usage function.Fault diagnosis is referred to abnormal to occurring by the various methods that can be checked and test
The reason of position of state is diagnosed, and finds out its functional disturbance, the abnormal conditions occurred to system judge, determine failure
The reason of, type, size, position and time of origin.Using the monitoring data of battery management system come in time to the more of battery pack
Kind failure is predicted, is achieved the goal and is detected failure, proposes that equipment breakdown precautionary measures are the research hotspots of control field.
The main task of fault diagnosis technology is fast and accurately to make evaluation and decision to failure, and system can be sentenced in time
Size, position and the time of generation of disconnected failure.In general, fault detection is easy and time-consuming few, and the diagnosis of failure due to
Judge position, the time reason etc. of system jam, and short time consumption is long.
In the prior art, expert system be it is a kind of by existing knowledge come the program of reasoning practical problem, passed through in conjunction with expert
It tests and solves those challenges with knowledge.Existing method is established on experts database, according to the fault message combination phase of input
It answers computerized algorithm to make inferences classification, completes fault diagnosis and decision, accuracy depends on the degree of perfection of experts database, that is, needs
A large amount of engineering experience knowledge is wanted, there are serious forgiveness in expert system is low, expert low for the accuracy rate of diagnosis of uncertain information
Knowledge experience obtains the problems such as difficult and maintenance difficulties are big.
Neural network is mainly based upon neuron and a kind of mathematical model for establishing, outputs and inputs and passes through this between information
A little neuron connections.Neural network model is larger to the Diagnostic Superiority of processing unascertained information due to itself characteristic, but by
A large amount of sample is needed in the training of neural network, a large amount of fault message sample data is difficult to obtain, by combining fuzzy set
Theoretical or regional compartmentalization is deep not enough come the research for reducing the difficulty of sample data acquisition, is poorly suited for use in battery event
Hinder diagnostic system.
Bayesian network combines probability theory and graph theory, is used to reasoning reconciliation never certain knowledge, in power grid
It is good that unascertained information diagnosis effect is handled in fault diagnosis.Electric network failure diagnosis is examined about Bayesian network in existing research
The more combining rough set correlation theories of research of disconnected method.Bayesian network node valuation needs to statistically analyze or actual observation is true
Fixed and Bayesian network training is difficult, how to solve modeling of the Bayesian network in the case where handling complex situations, network training
The problems such as still have difficulty.
It allows system to generate residual signals using certain technical method by the mathematical model of system, recycles generation
Residual signals apply corresponding evaluation rule, or it is directly allowed to be compared with given threshold values, to reach failure modes
Purpose.It mainly include parameter identification method, state estimate and parity space method, major defect is to rely on the mathematical modulo of system
The levels of precision of type, mathematical model will affect the effect of fault diagnosis.The shortcomings that parity space method is that major part can only be linear
It is used in system, and is just difficult to play a role in nonlinear system.
Digraph method and Fault Tree are substantially exactly to utilize the causal logic relationship between failure mode and failure cause
Classify to the system failure.When the fault diagnosis of large-scale complicated system, since the failure mode of system is various, failure dependency
The odjective causes such as complexity cause its fault diagnosis accuracy to be difficult to ensure.
Summary of the invention
The purpose of the present invention is to provide a kind of diagnostic methods of lithium battery failure, to overcome deficiency in the prior art.
To achieve the above object, the invention provides the following technical scheme:
The embodiment of the present application discloses a kind of diagnostic method of lithium battery failure, comprising:
S1, based on single classifier, construct integrated classifier, establish lithium battery failure modes prediction model；
S2, feature, and the input as lithium battery failure modes prediction model are extracted from battery BMS system.
Preferably, in the diagnostic method of above-mentioned lithium battery failure, integrated classifier using Boosting class or
Bagging class.
Preferably, in the diagnostic method of above-mentioned lithium battery failure, integrated classifier uses Bagging algorithm, comprising:
Assuming that R lithium ion battery data set D,
D={ (S1,S2,...,Sn)}k (1)
M data is randomly choosed in data set D, forms new sample set D1,
D={ (S1,S2,...,Sn)}m (2)
On new data set, classification results are provided using single classifier.Finally further according to the failure after parameter prediction
The factor repeats T random sampling procedure, will obtain the mean value of T model as last output result.
Preferably, in the diagnostic method of above-mentioned lithium battery failure, integrated classifier uses Adaboost algorithm, packet
It includes:
(1), data-oriented collection D, it is assumed that n data of selection
D={ (S1,S2,...,Sn)}k
(2), initial weight w={ 1/n } is set；
(3), For i=1:T
N data are generated by weight w in D, form new data set Di；
In new data set DiThe middle parameter using principle of least square method estimation model obtains optimal function Fi；
Calculate FiModel is in data set DiOn RMSE error and update weight Fwi；
(4), it exports
Preferably, in the diagnostic method of above-mentioned lithium battery failure, single classifier is selected from decision tree classifier, nerve net
Network classifier, support vector machine classifier, Bayes classifier and logistic regression classifier.
Preferably, in the diagnostic method of above-mentioned lithium battery failure, single classifier uses support vector machine classifier.
Preferably, in the diagnostic method of above-mentioned lithium battery failure, support vector machine classifier algorithm includes:
1) supporting vector for describing each section is chosen:
Training sample is divided into n section, according to the complexity CP value in each section, generates corresponding regression parameter,
Each section is returned according to regression parameter, iteration obtains corresponding support vector；
2) new training sample set is generated
According to the support vector in each region, new training sample set SV is constructeds={ TS1, TS2..., TSk}=
{SVi}I=1 m；Wherein TSkFor the corresponding supporting vector in k-th of region.
3) approximation to function
It is measurement with the complexity of new training sample set, regression parameter is set, the sample interval after fitting divides respectively；
4) classify:
Preset parameter set the p:{ ε, σ, C in general support vector machines are replaced with the parameter that formula (3) is calculated }, so
Classify afterwards to test sample.
Compared with the prior art, the advantages of the present invention are as follows:
1, the present invention proposes the lithium battery fault diagnosis model based on integrated study, the model using Bagging and
The realization of adboost method integrates multiple classifiers, obtains better nicety of grading, improves the accurate of lithium battery fault diagnosis
Degree.
2, the single classifier in the present invention is adapted to different data distribution features using flexible support vector machines, from
And the model parameter that adaptive formation is different, the classification performance of model is improved, it is final to improve whole fault diagnosis precision.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application, for those of ordinary skill in the art, without creative efforts,
It is also possible to obtain other drawings based on these drawings.
Fig. 1 show lithium battery fault diagnosis system schematic illustration in the specific embodiment of the invention；
Fig. 2 show the flow diagram of the diagnostic method of lithium battery failure in the specific embodiment of the invention.
Specific embodiment
In the following description, for explanatory purposes, detail is illustrated in order to provide the understanding of the present invention.However, will
It should be apparent to those skilled in the art that the present invention can be practiced in the case where without these details.In addition, this field
It will be recognized that invention described below embodiment can (such as process, device, be in various ways
System, equipment or method) implement in non-transitory computer-readable medium.
Component shown in the accompanying drawings or module are the exemplary illustrations of embodiment of the present invention, and are intended to avoid making this
It invents unclear.It should also be understood that it (may include sub single that component, which can be described as individual functional unit, in the full text of this discussion
Member), but those skilled in the art will recognize that, various assemblies or part thereof can be divided into independent assembly, or can integrate
Together (including being incorporated into single system or component).It should pay close attention to, functionality discussed herein or operation are implementable for group
Part.Component can be implemented with software, hardware or their combination.
In addition, the connection between component or system in attached drawing is not intended to be limited to be directly connected to.On the contrary, in these components
Between data can be modified by intermediate module, reformat or otherwise change.Further, it is possible to use in addition or less
Connection.It should also pay close attention to, term " connection ", " connection " or " communicatedly coupling " are understood to include and are directly connected to, by one
Or multiple intermediate equipments being indirectly connected with and being wirelessly connected come what is carried out.
In the present specification to " embodiment ", " preferred embodiment ", " embodiment ", " multiple embodiments "
Refer to expression combine embodiment described in specific features, structure, characteristic or function include at least one of the invention
In embodiment.In addition, each place of this specification occur above mentioned phrase might not all refer to it is identical
Embodiment or multiple identical embodiments.
It is intended to indicate that in each place of this specification using certain terms, and is understood not to limit.Clothes
Business, function or resource are not limited to individually service, individual feature or single resource；The use of these terms can be referred to related clothes
Business, the grouping for being distributed or polymerizeing of function or resource.Term " includes ", " including ", "comprising", " including " are interpreted as
Open term, and content of listing any thereafter is all example, and it is not limited to listed item.Term " image " Ying Li
Solution be include still image or video image.Any title used herein merely to organizational goal, and should not by with
In limitation specification or the scope of the claims.The each bibliography mentioned in patent document passes through reference simultaneously in its entirety
Enter herein.
In addition, it will be recognized by one skilled in the art that (1) certain steps can be executed optionally；(2) step can be unlimited
In certain order described in this paper；(3) certain steps can be perform in different order；And (4) certain steps can be simultaneously
It carries out.
The safety differentiation of lithium ion battery is divided into two kinds of situations: one is cell performance decay, i.e. battery itself agings
Caused reliability reduces, and is a kind of slow change procedure.Lithium battery capacity decaying dominant mechanism includes electrode activity material
Dissolution, phase change and the structure change of material, side reaction, formation of positive and negative anodes surface passivated membrane etc..It overcharges, over-discharge, low temperature, height
The factors such as temperature are to lead to the principal element of lithium ion battery aging；Another kind is the mutability failure of lithium ion battery, some prominent
Hair event causes lithium ion battery to damage and causes cell safety accident.Security fault specifically includes that
1) charge-discharge circuit failure.
Charge and discharge short trouble is the major failure for influencing the batteries of electric automobile service life, and charge-discharge circuit failure gently can then be made
It is damaged at lithium battery, the heavy then safety accidents such as battery explosion or electric car can be caused natural.Analyze battery charging and discharging
Caused by failure is mainly following reason；(1) lithium battery monomer inconsistency；(2) charging and discharging lithium battery is excessive.
2) battery failure.
During battery pack operation, the inconsistency of battery cell is built up and amplification causes single battery tired
Damage, causes the overall performance of battery pack to fail, while causing battery cell in battery pack and electric discharge occur excessively.
3) BMS failure.
BMS system mainly carries out monitoring and managerial role to electric car, since BMS system has multiple single-chip microcontrollers etc.
It constitutes, therefore its factor to break down is relatively more, it is therefore desirable to take effective measures optimization BMS system.
All kinds of failures that the present invention diagnoses include: that voltage is inconsistent；Internal resistance is inconsistent；Polarizing voltage is inconsistent；Connector
It loosens；Degradation failure；Internal resistance is inconsistent；Temperature is inconsistent；SOC is inconsistent.
The method of the present embodiment can be improved the fault location and maintenance efficiency of battery management system, optimize battery management system
System promotes BMS system stability.
As shown in connection with fig. 1, the present embodiment provides a kind of diagnostic systems of lithium battery failure, comprising:
(1) fault modeling.
According to according to the mapping relations between input and output, the sample information of a mathematical model of the system failure is established,
Model as fault detection and diagnosis；
(2) detection of fault message.
Collected system parameter message is analyzed, judges whether to break down, once breaking down, alarm should be issued immediately
Information；
(3) diagnosis of failure.
The type and the extent of damage that judgement distinguishes out of order property, judges failure.
As shown in connection with fig. 2, the present embodiment provides a kind of diagnostic methods of lithium battery failure, comprising:
S1, based on single classifier, construct integrated classifier, establish lithium battery failure modes prediction model；
S2, feature, and the input as lithium battery failure modes prediction model are extracted from battery BMS system.
In a preferred embodiment, in order to solve the prediction or nicety of grading of weak model or Weak Classifier, this case is used
A variety of disaggregated models are combined by integrated study, to improve nicety of grading.It proposes with Adbosst method to lithium ion battery
Failure is classified, and the precision of lithium ion battery failure diagnosis is improved.
Assuming that lithium ion battery data set D,
D={ (S1,S2,...,Sn)}k (1)
M data is randomly choosed in data set D, forms new sample set D1,
D={ (S1,S2,...,Sn)}m (2)
On new data set, unknown parameter is estimated using linear regression algorithmFinally further according to parameter prediction
Fault compression later repeats T random sampling procedure, will obtain the mean value of T model as last output result.
In one embodiment, a kind of lithium ion battery failure classification method based on Adaboost algorithm is provided.
The core concept of Adaboost algorithm is: the weight for being selected training data when initialization is identical, through resampling
New training dataset is obtained afterwards, the error of each sample is obtained according to each fallout predictor, the biggish sample of error is with more probably
Rate is chosen again constitutes new training sample set, this process of repetition obtains multiple submodels, and according to each submodel
Error calculation calculates corresponding weight.Adaboost algorithm description is as shown in table 3.
3 Adaboost algorithm of table
In one embodiment, the failure modes function of single classifier is realized using flexible support vector machines, realizes process
It is as follows:
1) supporting vector for describing each section is chosen:
Training sample is divided into n section, according to the complexity CP value in each section, generates corresponding regression parameter,
Each section is returned according to regression parameter, iteration obtains corresponding support vector；
2) new training sample set is generated
According to the support vector in each region, new training sample set SV is constructeds={ TS1, TS2..., TSk}=
{SVi}I=1 m；Wherein TSkFor the corresponding supporting vector in k-th of region.
3) approximation to function
It is measurement with the complexity of new training sample set, regression parameter is set, the sample interval after fitting divides respectively；
4) classify:
Preset parameter set the p:{ ε, σ, C in general support vector machines are replaced with the parameter that formula (3) is calculated }, so
Classify afterwards to test sample.
In conclusion the application uses integrated learning approach, strong classification can be obtained after integrating using multiple Weak Classifiers
The result of multiple models and classifier Shared Decision Making is replaced single model or classifier, so that lithium ion by this advantage of device
Complex nonlinear classification problem when battery failures occur obtains more stable classification results and better nicety of grading.In addition,
Using flexible support vector machines as single classifier, can be formed in different distributed areas according to data distribution feature
Different parameter, to improve classification accuracy.
Embodiments of the present invention can use for one or more processors or processing unit so that step executed
Instruction encodes in one or more non-transitory computer-readable mediums.It should be noted that one or more non-transient computers are readable
Medium should include volatile memory and nonvolatile memory.It should be noted that substitution be achieved in that it is possible comprising it is hard
Part implementation or software/hardware implementation.ASIC, programmable array, digital signal can be used in the function that hardware is implemented
Processing circuit etc. is realized.Therefore, the term " means " in any claim is intended to cover software realization mode and hardware is real
Both existing modes.Similarly, term " computer readable medium or medium " as used herein includes having to implement on it
The software and/or hardware or their combination of instruction repertorie.Utilize these substitution implementations conceived, it should be understood that attached
Figure and accompanying description provide those skilled in the art and write program code (that is, software) and/or manufacture circuit (that is, hardware)
To execute the required functional information of required processing.
It should be noted that embodiments of the present invention may also refer to thereon with various computer-implemented for executing
The computer product of the non-transient visible computer readable medium of the computer code of operation.Medium and computer code can be for out
In the purpose of the present invention medium and computer code that specially design and construct or they can be the technology in related fields
Personnel are known or available.The example of visible computer readable medium includes but is not limited to: such as magnetic of hard disk, floppy disk and tape
Property medium；The optical medium of such as CD-ROM and hologram device；Magnet-optical medium；And it is specifically configured to store or stores and execute
The hardware device of program code, for example, specific integrated circuit (ASIC), programmable logic device (PLD), flash memory device and
ROM and RAM device.The example of computer code includes machine code (for example, compiler generate code) and comprising can be by
Computer is performed the file of more advanced code using interpreter.Embodiments of the present invention can wholly or partly be implemented
For can be in the machine-executable instruction in the program module executed by processing equipment.The example of program module includes library, program, example
Journey, object, component and data structure.In the calculating environment of distribution, program module can be physically located locally, remotely or two
In the setting of person.
Those skilled in the art will recognize that computing system or programming language do not weigh for practice of the invention
It wants.Those skilled in the art will will also be appreciated that multiple said elements can physically and/or functionally be divided into submodule
Or it combines.
It will be understood that example, embodiment and experiment above is exemplary, and for purposes of clarity and understanding,
And it does not limit the scope of the invention.It is intended that after those skilled in the art reads this specification and studies attached drawing
All substitutions of the invention that will be apparent to those skilled in the science, displacement, enhancing, equivalent, combination improve and include
Within the scope of the invention.Accordingly, it is intended to explanation, claims include falling in the true spirit and scope of the present invention
All such substitutions, displacement, enhancing, equivalent, combination or improve, unless in addition appended claim is defined with its language
Explanation.It should be noted that the element of appended claim can be arranged differently, including with multiple subordinates, configuration and combination.Example
Such as, in embodiments, each claimed subject matter can be with other claim combinations.
Claims (7)
1. a kind of diagnostic method of lithium battery failure characterized by comprising
S1, based on single classifier, construct integrated classifier, establish lithium battery failure modes prediction model；
S2, feature, and the input as lithium battery failure modes prediction model are extracted from battery BMS system.
2. the diagnostic method of lithium battery failure according to claim 1, which is characterized in that integrated classifier uses
Boosting class or bagging class.
3. the diagnostic method of lithium battery failure according to claim 2, which is characterized in that integrated classifier uses
Bagging algorithm, comprising:
Assuming that lithium ion battery data set D,
D={ (S1,S2,...,Sn)}k (1)
M data is randomly choosed in data set D, forms new sample set D1,
D={ (S1,S2,...,Sn)}m (2)
On new data set, classification results are provided using single classifier, finally further according to the fault compression after parameter prediction,
T random sampling procedure is repeated, the mean value of T model will be obtained as last output result.
4. the diagnostic method of lithium battery failure according to claim 2, which is characterized in that integrated classifier uses
Adaboost algorithm, comprising:
(1), data-oriented collection D, it is assumed that n data of selection
D={ (S1,S2,...,Sn)}k
(2), initial weight w={ 1/n } is set；
(3), For i=1:T
N data are generated by weight w in D, form new data set Di；
In new data set DiThe middle parameter using principle of least square method estimation model obtains optimal function Fi；Calculate FiModel
In data set DiOn RMSE error and update weight Fwi；
(4), it exports
5. the diagnostic method of lithium battery failure according to claim 1, which is characterized in that single classifier is selected from decision tree point
Class device, neural network classifier, support vector machine classifier, Bayes classifier and logistic regression classifier.
6. the diagnostic method of lithium battery failure according to claim 5, which is characterized in that single classifier uses supporting vector
Machine classifier.
7. the diagnostic method of lithium battery failure according to claim 6, which is characterized in that support vector machine classifier algorithm
Include:
1) supporting vector for describing each section is chosen:
Training sample is divided into k section, and each section has different complexity CP, according to different CP values,
The specific regression parameter p for generating different sections, returns the section of division according to different regression parameter p, obtains every
The supporting vector SVs of a demarcation interval；
2) new training sample set generates:
If TSiFor supporting vector selected in ith zone, then all supporting vectors are extracted, construct completely new instruction
Practice sample set SVs={ TS1, TS2..., TSk}={ SVi}I=1 m；
3) function approximation:
Enabling SVs is training sample, regression parameter is arranged according to new training sample complexity, then to the sample of each division
This section carries out Function Fitting；
4) classify:
Classified according to the function of fitting to input data, wherein preset parameter the p:{ ε, σ, C in SVM be rewritten into one group
It can be with the parameter vector of self-control:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393300.3A CN110146817A (en) | 2019-05-13 | 2019-05-13 | The diagnostic method of lithium battery failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393300.3A CN110146817A (en) | 2019-05-13 | 2019-05-13 | The diagnostic method of lithium battery failure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110146817A true CN110146817A (en) | 2019-08-20 |
Family
ID=67595202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910393300.3A Pending CN110146817A (en) | 2019-05-13 | 2019-05-13 | The diagnostic method of lithium battery failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110146817A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826645A (en) * | 2019-11-22 | 2020-02-21 | 四川长虹电器股份有限公司 | Adaboost algorithm-based lithium battery retirement detection method and system |
| CN111157898A (en) * | 2020-01-07 | 2020-05-15 | 清华大学深圳国际研究生院 | New energy vehicle online battery fault detection and analysis method and device |
| CN111208436A (en) * | 2020-02-21 | 2020-05-29 | 河海大学 | Energy storage battery overcharge diagnosis method based on IMF energy moment and genetic algorithm optimization SVM |
| CN112067997A (en) * | 2020-08-14 | 2020-12-11 | 杭州小电科技股份有限公司 | Diagnosis method and system for mobile power supply leasing equipment, electronic equipment and storage medium |
| CN112710956A (en) * | 2020-12-17 | 2021-04-27 | 四川虹微技术有限公司 | Battery management system fault detection system and method based on expert system |
| CN115453369A (en) * | 2022-09-20 | 2022-12-09 | 中国汽车工程研究院股份有限公司 | Method for fuel cell consistency prediction and fault diagnosis |
| CN116429339A (en) * | 2023-06-07 | 2023-07-14 | 海斯坦普汽车组件(北京)有限公司 | Leakage detection method and system for new energy battery box |
| CN116760150A (en) * | 2023-08-14 | 2023-09-15 | 安徽博诺思信息科技有限公司 | Fault-tolerant operation method and device for single storage battery fault |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102749585A (en) * | 2011-04-21 | 2012-10-24 | 李昌 | Multi-layer SVM (support vector machine) based storage battery on-line monitoring method |
| CN103293487A (en) * | 2013-06-28 | 2013-09-11 | 哈尔滨工业大学 | Lithium ion battery service life forecasting method based on integrated model |
| CN107582037A (en) * | 2017-09-30 | 2018-01-16 | 深圳前海全民健康科技有限公司 | Method based on pulse wave design medical product |
| CN107992895A (en) * | 2017-10-19 | 2018-05-04 | 电子科技大学 | A kind of Boosting support vector machines learning method |
| CN108344947A (en) * | 2018-01-11 | 2018-07-31 | 西南交通大学 | A kind of fuel cell diagnostic method of non-intrusion type |
| CN109061495A (en) * | 2018-08-07 | 2018-12-21 | 中国电建集团福建省电力勘测设计院有限公司 | A kind of hybrid energy-storing battery failure diagnostic method |
| CN109143091A (en) * | 2018-10-15 | 2019-01-04 | 四川长虹电器股份有限公司 | Battery management system failure FDIR system and method based on dual redundant |
| CN109726452A (en) * | 2018-12-12 | 2019-05-07 | 浙江大学 | A kind of online Proton Exchange Membrane Fuel Cells method for diagnosing faults based on impedance spectrum |
-
2019
- 2019-05-13 CN CN201910393300.3A patent/CN110146817A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102749585A (en) * | 2011-04-21 | 2012-10-24 | 李昌 | Multi-layer SVM (support vector machine) based storage battery on-line monitoring method |
| CN103293487A (en) * | 2013-06-28 | 2013-09-11 | 哈尔滨工业大学 | Lithium ion battery service life forecasting method based on integrated model |
| CN107582037A (en) * | 2017-09-30 | 2018-01-16 | 深圳前海全民健康科技有限公司 | Method based on pulse wave design medical product |
| CN107992895A (en) * | 2017-10-19 | 2018-05-04 | 电子科技大学 | A kind of Boosting support vector machines learning method |
| CN108344947A (en) * | 2018-01-11 | 2018-07-31 | 西南交通大学 | A kind of fuel cell diagnostic method of non-intrusion type |
| CN109061495A (en) * | 2018-08-07 | 2018-12-21 | 中国电建集团福建省电力勘测设计院有限公司 | A kind of hybrid energy-storing battery failure diagnostic method |
| CN109143091A (en) * | 2018-10-15 | 2019-01-04 | 四川长虹电器股份有限公司 | Battery management system failure FDIR system and method based on dual redundant |
| CN109726452A (en) * | 2018-12-12 | 2019-05-07 | 浙江大学 | A kind of online Proton Exchange Membrane Fuel Cells method for diagnosing faults based on impedance spectrum |
Non-Patent Citations (1)
| Title |
|---|
| 易辉: "基于支持向量机的故障诊断及应用研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826645A (en) * | 2019-11-22 | 2020-02-21 | 四川长虹电器股份有限公司 | Adaboost algorithm-based lithium battery retirement detection method and system |
| CN111157898A (en) * | 2020-01-07 | 2020-05-15 | 清华大学深圳国际研究生院 | New energy vehicle online battery fault detection and analysis method and device |
| CN111208436A (en) * | 2020-02-21 | 2020-05-29 | 河海大学 | Energy storage battery overcharge diagnosis method based on IMF energy moment and genetic algorithm optimization SVM |
| CN112067997A (en) * | 2020-08-14 | 2020-12-11 | 杭州小电科技股份有限公司 | Diagnosis method and system for mobile power supply leasing equipment, electronic equipment and storage medium |
| CN112067997B (en) * | 2020-08-14 | 2023-11-14 | 杭州小电科技股份有限公司 | Diagnosis method and system for portable power source leasing equipment, electronic equipment and storage medium |
| CN112710956A (en) * | 2020-12-17 | 2021-04-27 | 四川虹微技术有限公司 | Battery management system fault detection system and method based on expert system |
| CN112710956B (en) * | 2020-12-17 | 2023-08-04 | 四川虹微技术有限公司 | Expert system-based battery management system fault detection system and method |
| CN115453369A (en) * | 2022-09-20 | 2022-12-09 | 中国汽车工程研究院股份有限公司 | Method for fuel cell consistency prediction and fault diagnosis |
| CN116429339A (en) * | 2023-06-07 | 2023-07-14 | 海斯坦普汽车组件(北京)有限公司 | Leakage detection method and system for new energy battery box |
| CN116429339B (en) * | 2023-06-07 | 2023-09-01 | 海斯坦普汽车组件(北京)有限公司 | Leakage detection method and system for new energy battery box |
| CN116760150A (en) * | 2023-08-14 | 2023-09-15 | 安徽博诺思信息科技有限公司 | Fault-tolerant operation method and device for single storage battery fault |
| CN116760150B (en) * | 2023-08-14 | 2023-11-14 | 安徽博诺思信息科技有限公司 | Fault-tolerant operation method and device for single storage battery fault |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110146817A (en) | The diagnostic method of lithium battery failure | |
| Hong et al. | Fault prognosis of battery system based on accurate voltage abnormity prognosis using long short-term memory neural networks | |
| Liu et al. | Towards long lifetime battery: AI-based manufacturing and management | |
| CN110133508A (en) | The safe early warning method of electric automobile power battery | |
| Zhang et al. | Research on electric vehicle charging safety warning model based on back propagation neural network optimized by improved gray wolf algorithm | |
| Hashemi et al. | Machine learning‐based model for lithium‐ion batteries in BMS of electric/hybrid electric aircraft | |
| CN111007401A (en) | Electric vehicle battery fault diagnosis method and device based on artificial intelligence | |
| CN107329088A (en) | The health status diagnostic device and method of battery | |
| Wang et al. | A fault diagnosis method for lithium-ion battery packs using improved RBF neural network | |
| CN109283469A (en) | Battery management system failure prediction method, device and readable storage medium storing program for executing | |
| Wang et al. | A comprehensive working state monitoring method for power battery packs considering state of balance and aging correction | |
| Xu et al. | A vehicle-cloud collaborative method for multi-type fault diagnosis of lithium-ion batteries | |
| Zhang et al. | Intelligent state of charge estimation of battery pack based on particle swarm optimization algorithm improved radical basis function neural network | |
| Qiu et al. | A novel entropy-based fault diagnosis and inconsistency evaluation approach for lithium-ion battery energy storage systems | |
| Zhang et al. | State of health estimation of lithium-ion batteries based on modified flower pollination algorithm-temporal convolutional network | |
| He et al. | Voltage abnormality-based fault diagnosis for batteries in electric buses with a self-adapting update model | |
| Sun et al. | Anomaly detection of power battery pack using gated recurrent units based variational autoencoder | |
| Li et al. | Timely thermal runaway prognosis for battery systems in real-world electric vehicles based on temperature abnormality | |
| CN115061058A (en) | Method and system for measuring and calculating gradient utilization residual life of retired power battery | |
| Jeng et al. | Evaluation of cell inconsistency in lithium-ion battery pack using the autoencoder network model | |
| Sun et al. | A novel fault prediction method based on convolutional neural network and long short-term memory with correlation coefficient for lithium-ion battery | |
| Garg et al. | Reconfigurable battery systems: Challenges and safety solutions using intelligent system framework based on digital twins | |
| Yao et al. | An intelligent fault diagnosis method for lithium-ion battery pack based on empirical mode decomposition and convolutional neural network | |
| Wen et al. | Lithium battery health state assessment based on vehicle-to-grid (V2G) real-world data and natural gradient boosting model | |
| CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190820 |
|
| RJ01 | Rejection of invention patent application after publication |