CN109299552A - A kind of appraisal procedure and its assessment system of battery power status - Google Patents
A kind of appraisal procedure and its assessment system of battery power status Download PDFInfo
- Publication number
- CN109299552A CN109299552A CN201811155381.5A CN201811155381A CN109299552A CN 109299552 A CN109299552 A CN 109299552A CN 201811155381 A CN201811155381 A CN 201811155381A CN 109299552 A CN109299552 A CN 109299552A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- battery
- power status
- valid data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000004445 quantitative analysis Methods 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims 1
- 238000011158 quantitative evaluation Methods 0.000 abstract description 7
- 238000004146 energy storage Methods 0.000 description 14
- 230000005540 biological transmission Effects 0.000 description 6
- 239000000463 material Substances 0.000 description 5
- 230000006399 behavior Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000010291 electrical method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000006317 isomerization reaction Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of appraisal procedure of battery power status and its assessment system, the appraisal procedure of battery power status specifically includes the following steps: acquisition battery initial data, initial data is pre-processed to obtain valid data;Valid data are stored, while valid data are sent to Spark big data platform;Analysis is carried out to valid data and operation forms five elements set, building and/or more new knowledge base;According to the energy state of the output assessment battery in five elements set and shown.Battery power status appraisal procedure and its assessment system provided by the present application can acquire a variety of data of battery, and pass through the energy state of more impact factor quantitative evaluation batteries.
Description
Technical field
This application involves battery technology fields, and in particular, to a kind of appraisal procedure and its assessment of battery power status
System.
Background technique
Battery energy storage is an important branch of current energy storage technology development, and battery energy storage application technology is just towards distribution
Formula, movable type, isomerization, intelligence, informationization direction develop, energy state (SOE) quantitative evaluation of battery energy storage system
It plays an important role in the more scene safeties in production of movement/isomery battery energy storage system.Energy state (SOE) table of battery
The ratio for showing releasable energy and battery maximum available energy under battery conditions present is reflection energy content of battery service condition
Important indicator plays an important role in distributed/extensive battery energy storage system.
The estimation method of battery SOE is different from the lotus dotted state (SOC) of battery, not only by the shadow of battery load current
It rings, it is also related to voltage end voltage.In the use process of lithium battery, when battery temperature and the variation of battery charging and discharging multiplying power,
The discharging efficiency of battery can change correspondingly and influence the SOE of battery.In order to estimate the SOE of battery, common mode is to battery
Specific external electrical characteristic states estimated, establish the relational model between battery SOC and SOE, a kind of common battery benefit
It is charge and discharge electrical method with the estimation method of potentiality: firstly, carrying out charge and discharge to battery, obtains the initial SOE of battery;Then, for
Battery in use carries out charge and discharge, obtains the real surplus SOE of battery;Returned with the remaining SOE of battery divided by initial SOE
The one battery SOE estimated value changed, but existing technical solution can only disclose the SOE estimation rule of battery under single factors,
Can not system comprehensively accurately disclose battery SOE state, and mostly research be based on battery SOC state measure battery
SOE, using the external behavior SOC of the single battery of same battery material system as measurement index for, particular battery material
External electrical method of evaluating characteristic can not accurately measure the external electrical characteristic parameter of isomery battery or battery pack, can not also determine.
In addition, after battery group, since the inconsistency difference between battery causes battery life to be substantially reduced, the characteristic of battery pack
To will lead to when larger with battery cell property difference hot-spot occur nonlinear change, and traditional battery energy storage system without
Method accomplishes the battery SOE quantization and assessment that battery pack is combined with battery cell, therefore to the SOE amount of battery cell and battery pack
Change assessment and equally brings important challenge.In conclusion the quantitative evaluation technological deficiency of existing battery energy storage SOE, becomes limit
System distribution, mobile, isomery formula battery energy storage system utilization and extention significant obstacle.
Summary of the invention
This application provides a kind of appraisal procedures of battery power status, specifically includes the following steps: the original of acquisition battery
Beginning data pre-process initial data to obtain valid data;Valid data are stored, while valid data being sent
Give Spark big data platform;Analysis is carried out to valid data and operation forms five elements set, building and/or more new knowledge base;
According to the energy state of the output assessment battery in five elements set and shown.
As above, wherein building and more new knowledge base are the following steps are included: choose relational model S (t);According to relationship mould
Type forms five elements set, building and/or more new knowledge base;Wherein relational model S (t)={ (ω, ρ): Ω, ω, ρ }, wherein
ω is valid data, and Ω is the track set of input, and ρ is the output of relational model.
It is as above, wherein the selection of relational model determines system the following steps are included: establish assessment system model R (t)
Input X, obtain the input X for enriching assessment system priori knowledge and system and input to obtain ideally according to system
Export Y1;The evaluation scheme of selecting system, determines whether assessment models R (t) can satisfy the evaluation condition of system structure, and obtains
The true output Y2 for the assessment models that can be used for assessing out;It regard output Y2 and valid data ω as input, it is true according to input
Fixed or calibration relation model S (t).
As above, wherein the input X of system and valid data ω are put into relational model, pass through online or offline point
Analysis, is classified, is returned, clustering algorithm obtains the output Y of system, obtains five elements set, five elements collection table by exporting Y
It is shown as P=(T, X, Ω, Y, S), wherein T indicates state trajectory set, and X indicates the input of assessment system, and Ω indicates the rail of input
Trace set, Y indicate the output of system, and S indicates relational model, and the update of knowledge base is completed by the update of five elements set.
As above, wherein if collecting the first valid data ω, X is inputted according to ω and system first and chooses the first relationship
ω and X are put into the first relational model by model, obtain the first output Y, are formed five elements set P1=(T, X, Ω, Y1, S);
If collecting the second valid data ω ', X ' is inputted according to ω ' and system second and chooses the second relational model, is obtained ω ' and X '
It is put into the second relational model, obtains the second output Y ', form five elements set P2=(T ', X ', Ω ', Y ', S ');By system
Second input X ' and the second valid data ω ' be put into the first relational model, obtained third export Y ", form five elements
Set P3=(T ", X ", Ω ", Y ", S "), P3 and P2 are compared, if the difference of P3 and P2 in threshold value, without more
New knowledge base.
As above, wherein if the difference of five elements set P3 P2 in conjunction with five elements is more than threshold value, five elements set P3
Five elements set P1 is replaced, P3 is added to the update for carrying out knowledge base in knowledge base.
As above, wherein the difference of five elements set P2 and five elements set P3 are carried out by least square method or KNN algorithm
Value calculates.
As above, wherein initial data includes running state information, environmental data and the battery information of battery system.
A kind of assessment system, including acquisition module, data memory module and quantitative analysis module;Acquisition module is for adopting
Initial data inside set battery, and initial data is transferred to data collection data memory module by series of preprocessing;
Data memory module is connect with acquisition module, initial data that treated for receiving acquisition module, will be original by pretreatment
Data become valid data, are stored valid data by way of elasticity distribution formula data set or distributed file system
Come, and sends and give quantization analysis module;Quantitative analysis module is connect with data memory module, for receiving treated significant figure
According to, to data carry out analysis and operation, carry out constructing/more new knowledge base.
As above, wherein quantitative analysis module is including being that model chooses module, construction of knowledge base/update module, battery energy
Measure state computation module and display module;It wherein include Spark real time data processing Core API mould in knowledge base update module
Block and Spark machine learning library module;Relational model chooses module and carries out relational model for valid data based on the received
It chooses;Construction of knowledge base/update module is connect with relationship module, for importing valid data in relational model, and is passed through
Spark real time data processing Core API module carries out online or off-line analysis, is divided by Spark machine learning library module
Class, recurrence, clustering algorithm finally obtain the set building/more new knowledge base of five elements;Battery power status computing module with know
Know library building/update module connection, for calculating the energy state of battery according to obtained five elements set, and is sent to display
Module;Display module is connect with battery power status computing module, for receiving calculated battery power status and being shown
Show.
The application has the advantages that
(1) battery power status appraisal procedure and its assessment system provided by the present application can acquire a variety of numbers of battery
According to, and pass through the energy state of more impact factors (temperature, load, operating condition) quantitative evaluation battery.
(2) battery power status appraisal procedure and its assessment system provided by the present application by online or off-line analysis and
Various operations enrich constantly or more new knowledge base, can sufficiently excavate the value in movement/isomery battery system data, carry out real
When assessment battery energy state.
(3) battery power status appraisal procedure and its assessment system provided by the present application are based on spark big data platform
It is assessed, the distributed structure/architecture of big data platform, is easy to extend and reduce, the change that can cope with distributed energy storage scale comes
Reach the effective use of resource, also solves the prior art and be difficult to the drawbacks of handling massive logs.
(4) battery power status appraisal procedure and its assessment system provided by the present application can acquire effective data, quasi-
The wrong report of information really is removed, and provides detailed quantitative evaluation as a result, for instructing distribution/movable type/isomery energy storage system
Distributing rationally for system is run with combined optimization.
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 can also be obtained according to these attached drawings other for those of ordinary skill in the art
Attached drawing.
Fig. 1 is the appraisal procedure flow chart according to battery power status provided by the embodiments of the present application;
Fig. 2 is the assessment system schematic diagram of internal structure according to battery power status provided by the embodiments of the present application;
Fig. 3 is the schematic diagram of internal structure of the quantitative analysis module of battery power status provided by the embodiments of the present application.
Specific embodiment
Below with reference to the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Ground description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on the application
In embodiment, those skilled in the art's every other embodiment obtained without making creative work, all
Belong to the range of the application protection.
The application provides the appraisal procedure and its assessment system of a kind of battery power status, can be according to multiple battery outside
Characteristic parameter realizes more impact factors, more application scenarios association analysis as measurement index, finally carries out to battery power status
Potential Evaluation.
As shown in Figure 1, be battery power status appraisal procedure provided by the present application, wherein specifically includes the following steps:
Step S110: acquiring the initial data of battery, is pre-processed to obtain valid data to initial data.
Illustratively, acquisition is battery initial data under different battery materials, different operating condition and different scenes, electricity
Pond initial data includes the running state information (such as output electric current, output voltage, battery capacity etc.) of battery system, environment number
According to (such as temperature, humidity and bearing power etc.) and battery information (such as battery material, date of manufacture, cycle-index
Deng).Valid data are the more impact factors for measuring battery power status.
Specifically, pretreatment includes being filtered, merging and standardized format to the data of acquisition, further, is led to
Log transmission system (Flume) is crossed, initial data is integrated in distributed information system (Kafka), is realized in initial data
Log collection, log integrity and the real-time Transmission of log.
Illustratively, log collection can collect system log, monitoring file log and TCP (Transmission
Control Protocol, transmission control protocol)/UDP (User Datagram Protoco, User Datagram Protocol) interface
Log etc..
Step S120: valid data are stored, while being sent to Spark big data platform.
Specifically, Spark is the computing engines for the Universal-purpose quick for aiming at large-scale data processing and designing.
Specifically, initial data is become into valid data by data filtering operation and map operation by initial data, led to
The form for crossing elasticity distribution formula data set (RDD) or distributed file system (HDFS) stores.
Illustratively, different from initial data, valid data are required data when assessment system is assessed, such as
Export a part of data in the initial data such as electric current, bearing power and cycle-index.
Step S130:Spark big data platform carries out analysis and operation to valid data, passes through the result after analytic operation
Building and/or more new knowledge base.
Specifically, building and more new knowledge base include following sub-step:
Step D1: the relational model S (t) of assessment system is chosen.Specifically includes the following steps:
Step F1: establishing assessment system model R (t), and determining the input X of system, (system constants, system performance, noise are big
Small, variable time delay and system mode component etc.), obtain the input X for enriching assessment system priori knowledge and system and according to
System inputs to obtain output Y1 ideally.
Step F2: the evaluation scheme of selecting system determines whether assessment models R (t) can satisfy the assessment of system structure
Condition, and obtain the output Y2 that can be used for the assessment models assessed.
Illustratively, Y1 is the output ideally envisioned, and Y2 is the true vector obtained according to input X.
Specifically, the selected of evaluation scheme need to consider following problems: 1, open loop and closed loop characteristic;2, offline with comment online
Estimate;3, precision, complexity and the period assessed;4, the selection of signal type;5, the error etc. of systematic survey.
Illustratively, common system evaluation Scheme algorithm has: particle swarm algorithm, genetic algorithm, linear regression algorithm, shellfish
Leaf this algorithm, k nearest neighbor algorithm, categorised decision tree algorithm, algorithm of support vector machine etc..
Step F3: using output Y2 and valid data ω as the input of assessment system model, relationship is determined according to input
Model S (t) improves calibration relation model S (t) using experimental data test.
Specifically, relational model S (t)={ (ω, ρ): Ω, ω, ρ }, wherein ω is valid data, and Ω is the track of input
Set, ρ are the output of relational model.
As another embodiment, assessment system is decomposed into numerous subsystem, there are a passes in each subsystem
It is model, the input of each subsystem is one or more parameters in valid data, illustratively, if valid data include fortune
Row status data, environmental data, battery information, then using running state data as the input of subsystem 1, environmental data is as son
The input of system 2, input of the battery information as subsystem 3 obtain the relational model of subsystem 1 according to the input of subsystem 1
S1(t), the relational model S of subsystem 2 is obtained according to the input of subsystem 22(t), subsystem 3 is obtained according to the input of subsystem 3
Relational model S3(t), by the relational model S of subsystem 1,2,31(t)、S2(t)、S3(t) relational model of system can be obtained
S(t)。
The selection principle of relational model of selection and system of the relational model of each subsystem is identical.
The application is to be assessed the energy state (SOE) of battery, but the energy state of battery is in different works
It is continually changing under condition or environment, it is therefore desirable to be acquired in real time to the parameter information of battery, and by collected battery
Initial data be converted into valid data, assessment system chooses different relational models according to the difference of valid data, that is,
It says, initial data of every acquisition, all chooses a relational model again.
Step D2: according to relational model building/more new knowledge base;
Since there are formula S (t)={ (ω, ρ): Ω, ω, ρ } for relational model, by the input X of system and valid data ω
Be put into relational model, by online or off-line analysis, classified, returned, clustering algorithm can obtain output ρ, at this time ρ be
The output Y of system can obtain the set of five elements by exporting Y, be expressed as P=(T, X, Ω, Y, S), wherein T indicates state
Track set, X indicate the input of assessment system, and Ω indicates the track set of input, and Y indicates the output of assessment system, and S indicates to close
It is model.Five elements set enrich constantly and/or update be exactly knowledge base building and/or update.
As another embodiment, if existence function relationship (ρ=f (ω)) above formula can indicate between ω, ρ are as follows: S=
(T, X, Ω, Y, F), wherein F is relation function.
Specifically, the set expression of five elements can express the external behavior of assessment system.
Illustratively, if assessing the battery under a scene, first according to the input X of system (the first input X)
The first relational model S is chosen with valid data ω (the first valid data ω)1(t), X and the first valid data ω is inputted by first
It is put into the first relational model S1(t) in, the first output Y is finally then obtained by analysis and operation, forms five elements set P1
=(T, X, Ω, Y, S), is put into knowledge base and is stored;If again to the battery under another work condition state under a scene
Secondary to be assessed, then valid data ω, which changes, becomes ω ', and system input becomes X ', and chooses the second relational model again
S2(t), the second input X ' and the second valid data ω ' of system is put into the second relational model S2(t) in, second is finally obtained
Y ' is exported, is formd five elements set P2=(T ', X ', Ω ', Y ', S '), meanwhile, the second input X ' and second of system is had
Effect data ω ' is put into the first relational model S1(t) in, obtained third output Y ", form five elements set P3=(T ", X ",
Ω ", Y ", S "), five elements set P3 and five elements set P2 are compared, if the difference of P3 and P2 is smaller, in threshold value,
Five elements set is not updated then, that is, without more new knowledge base.
Specifically, P3 and P2 are calculated by least square method or KNN algorithm, if P3 is being specified with differing for P2
Threshold value in, then without the update of knowledge base, if the difference of P3 and P2 has been more than specified threshold range, P3 substitutes P2 collection
It closes, P3 is added to the update for carrying out knowledge base in knowledge base.
Preferably, specified threshold can be technical staff and be configured according to the actual situation, herein without limiting.
If valid data are changed again, step D1 is executed again, carries out the selection of relational model S (t), warp again
The continuous selection of relational model is crossed, output Y is also constantly changed, and five elements set also constantly changes, to five elements collection
Conjunction constantly compared, when assessment system stop assessment or five elements be integrated into when not updated in the duration, then must
The output determining to one, output Y of the output ρ of relational model as system, that is, battery is released under current state
The energy put.
As another embodiment, the assessment models of system are determined according to the input X of system, valid data ω is put into pass
It is by online or off-line analysis, to be classified, returned, clustering algorithm can obtain the first output Y, ultimately formed in model
Five elements set P=(T, X, Ω, Y, S).
It further include the accuracy for measuring five elements set, by the way that assessment system is decomposed into nothing as another embodiment
Several subsystems include a relational model in each subsystem, illustratively, if the logical relation between subsystem is string
Join, then the output ρ of subsystem 11In conjunction with the valid data ω of 2 script of subsystem2As the entirety input of subsystem 2, subsystem 2
Output ρ2In conjunction with the valid data ω of subsystem 33As the entirety input of subsystem 3, the output ρ of subsystem 33For system
Export Y.
Further, the relational model of each subsystem equally exists formula S ' (t)={ (ω, ρ): Ω, ω, ρ }, simultaneously
There is formula S ' (t)={ Q, λ, σ } in the relational model of subsystem, the first input X and the first valid data ω of system is put again
Enter the relational model S of subsystem 11(t) it in, is analyzed by online/line, classification, recurrence, aggregating algorithm are finally then exported
ρ1, by exporting ρ1Form seven element set P '=(T, X, Ω, ρ1, Q, λ, σ), wherein T, the T in X, Ω and five elements set,
X, Ω meaning are identical, and Q indicates the state variable of system, and λ indicates that output function, σ indicate the state component of system.If system is quiet
State, then seven elements can be expressed as P '=(X, Y, Q, λ), and seven element sets are able to reflect external behavior and the inside spy of system
Property.
Seven element sets can measure the accuracy of five elements set, illustratively, if having finally obtained five elements set
System decomposition can be then numerous subsystem, by finally obtained seven element set and five elements set by most by P3
Small square law/KNN algorithm carries out operation, obtains five elements set and whether the difference of seven element sets is excessive, if difference is smaller
Then five elements set the result is that accurate, the operation again of five elements set is carried out if difference is larger.
Step S140: it assesses the energy state of battery and is shown.
The releasable energy for having obtained battery by step S130 and battery maximum available energy are subjected to ratio calculation, obtained
To percentage be exactly battery energy state.
It is illustrated in figure 2 the schematic diagram of internal structure of the assessment system of battery power status provided by the present application.
Assessment system includes acquisition module 210, data memory module 220, quantitative analysis module 230.
Acquisition module 210 is used to acquire the initial data of inside battery, and initial data is passed by series of preprocessing
It is defeated by data collection data memory module 220.
Specifically, initial data include battery energy storage system running state data (such as output electric current, output voltage,
Battery capacity etc.), environmental data (such as temperature, humidity and bearing power etc.) and battery information (such as battery material, life
Produce date, cycle-index etc.).
Further, acquisition module 110 is by log transmission system (Flume), and the initial data of acquisition is integrated point
In cloth message system (Kafka), log collection, log integrity and the real-time Transmission of log in initial data are realized.
Data memory module 220 is connect with acquisition module 210, treated for receiving acquisition module initial data, warp
Crossing data filtering operation and map operation becomes valid data for initial data, on the one hand passes through elasticity distribution formula data set
(RDD) or the form of distributed file system (HDFS) stores, and is on the other hand sent to quantitative analysis module 230.
Quantitative analysis module 230 is connect with data memory module 220, for receiving treated valid data, to data
Analysis and operation are carried out, carries out constructing/more new knowledge base.
Specifically, include Spark big data platform in quantitative analysis module 230, counted based on Spark big data platform
According to analysis and operation, as shown in figure 3, wherein quantitative analysis module 230 specifically include relational model choose module 310, knowledge
Library building/update module 320, battery power status computing module 330 and display module 340, wherein construction of knowledge base/update
It include Spark real time data processing Core API module 350 and Spark machine learning library module 360 in module 320.
Specifically, relational model chooses the selection that module 310 carries out relational model for valid data based on the received.
Construction of knowledge base/update module 320 is connect with relationship module 310, for valid data to be imported in relational model,
And online or off-line analysis is carried out by Spark real time data processing Core API module 350, pass through Spark machine learning library mould
Block 360 classified, returned, clustering algorithm, finally obtains the set building/more new knowledge base of five elements.
Battery power status computing module 330 is connect with construction of knowledge base/update module 320, for according to five obtained
Element set calculates the energy state of battery, and is sent to display module 340.
Display module 340 is connect with battery power status computing module 330, for receiving calculated battery power status
And it is shown.
The application has the advantages that
(1) battery power status appraisal procedure and its assessment system provided by the present application can acquire a variety of numbers of battery
According to, and pass through the energy state of more impact factors (temperature, load, operating condition) quantitative evaluation battery.
(2) battery power status appraisal procedure and its assessment system provided by the present application by online or off-line analysis and
Various operations enrich constantly or more new knowledge base, can sufficiently excavate the value in movement/isomery battery system data, carry out real
When assessment battery energy state.
(3) battery power status appraisal procedure and its assessment system provided by the present application are based on spark big data platform
It is assessed, the distributed structure/architecture of big data platform, is easy to extend and reduce, the change that can cope with distributed energy storage scale comes
Reach the effective use of resource, also solves the prior art and be difficult to the drawbacks of handling massive logs.
(4) battery power status appraisal procedure and its assessment system provided by the present application can acquire effective data, quasi-
The wrong report of information really is removed, and provides detailed quantitative evaluation as a result, for instructing distribution/movable type/isomery energy storage system
Distributing rationally for system is run with combined optimization.
Although the example of present application reference is described, it is intended merely to the purpose explained rather than the limit to the application
System, the change to embodiment, increase and/or deletion can be made without departing from scope of the present application.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain
Lid is within the scope of protection of this application.Therefore, the protection scope of the application should be based on the protection scope of the described claims.
Claims (10)
1. a kind of appraisal procedure of battery power status, which is characterized in that specifically includes the following steps:
The initial data for acquiring battery, pre-processes initial data to obtain valid data;
Valid data are stored, while valid data are sent to Spark big data platform;
Analysis is carried out to valid data and operation forms five elements set, building and/or more new knowledge base;
According to the energy state of the output assessment battery in five elements set and shown.
2. the appraisal procedure of battery power status as described in claim 1, which is characterized in that building and more new knowledge base include
Following steps:
It chooses relational model S (t);
Five elements set, building and/or more new knowledge base are formed according to relational model;
Wherein relational model S (t)={ (ω, ρ): Ω, ω, ρ }, wherein ω is valid data, and Ω is the track set of input, ρ
For the output of relational model.
3. the appraisal procedure of battery power status as claimed in claim 2, which is characterized in that the selection of relational model include with
Lower step:
Assessment system model R (t) is established, determines the input X of system, obtains the input for enriching assessment system priori knowledge and system
X and input to obtain output Y1 ideally according to system;
The evaluation scheme of selecting system, determines whether assessment models R (t) can satisfy the evaluation condition of system structure, and obtains
The true output Y2 for the assessment models that can be used for assessing;
By output Y2 and valid data ω as input, according to input determination or calibration relation model S (t).
4. the appraisal procedure of battery power status as claimed in claim 2, which is characterized in that by the input X of system and effectively
Data ω is put into relational model, by online or off-line analysis, is classified, is returned, clustering algorithm obtains the output of system
Y obtains five elements set by exporting Y, and five elements set expression is P=(T, X, Ω, Y, S), and wherein T indicates state trajectory collection
It closes, X indicates the input of assessment system, and Ω indicates the track set of input, and Y indicates the output of system, and S indicates relational model, leads to
The update of knowledge base is completed in the update for crossing five elements set.
5. the appraisal procedure of battery power status as claimed in claim 4, which is characterized in that if collecting the first valid data
ω inputs X according to ω and system first and chooses the first relational model, ω and X are put into the first relational model, it is defeated to obtain first
Y out is formed five elements set P1=(T, X, Ω, Y1, S);If the second valid data ω ' is collected, according to ω ' and system second
Input X ' and choose the second relational model, obtain ω ' and X ' it is put into the second relational model, the second output Y ' is obtained, forms five
Element set P2=(T ', X ', Ω ', Y ', S ');Second input X ' and the second valid data ω ' of system is put into the first relationship
In model, third output Y " is obtained, five elements set P3=(T ", X ", Ω ", Y ", S ") is formd, P3 and P2 have been carried out pair
Than, if the difference of P3 and P2 in threshold value, without more new knowledge base.
6. the appraisal procedure of battery power status as claimed in claim 4, which is characterized in that if five elements set P3 and five yuan
Element in conjunction with P2 difference be more than threshold value, then five elements set P3 by five elements set P1 replace, by P3 be added in knowledge base into
The update of row knowledge base.
7. such as the appraisal procedure of battery power status described in claim 5 or 6, which is characterized in that by least square method or
The difference that KNN algorithm carries out five elements set P2 and five elements set P3 calculates.
8. the appraisal procedure of battery power status as described in claim 1, which is characterized in that initial data includes battery system
Running state information, environmental data and battery information.
9. a kind of assessment system, which is characterized in that including acquisition module, data memory module and quantitative analysis module;
Acquisition module is used to acquire the initial data of inside battery, and initial data is transferred to data by series of preprocessing
Acquired data storage module;
Data memory module is connect with acquisition module, initial data that treated for receiving acquisition module, will by pretreatment
Initial data becomes valid data, is stored valid data by way of elasticity distribution formula data set or distributed file system
Get up, and sends and give quantization analysis module;
Quantitative analysis module is connect with data memory module, for receiving treated valid data, to data analyzed with
And operation, it carries out constructing/more new knowledge base.
10. assessment system as claimed in claim 9, which is characterized in that quantitative analysis module is including being model selection module, knowing
Know library building/update module, battery power status computing module and display module;Wherein include in knowledge base update module
Spark real time data processing Core API module and Spark machine learning library module;
Relational model chooses the selection that module carries out relational model for valid data based on the received;
Construction of knowledge base/update module is connect with relationship module, for importing valid data in relational model, and is passed through
Spark real time data processing Core API module carries out online or off-line analysis, is divided by Spark machine learning library module
Class, recurrence, clustering algorithm finally obtain the set building/more new knowledge base of five elements;
Battery power status computing module is connect with construction of knowledge base/update module, for total according to obtained five elements collection
The energy state of battery is calculated, and is sent to display module;
Display module is connect with battery power status computing module, for receiving calculated battery power status and being shown
Show.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811155381.5A CN109299552A (en) | 2018-09-29 | 2018-09-29 | A kind of appraisal procedure and its assessment system of battery power status |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811155381.5A CN109299552A (en) | 2018-09-29 | 2018-09-29 | A kind of appraisal procedure and its assessment system of battery power status |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109299552A true CN109299552A (en) | 2019-02-01 |
Family
ID=65161270
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811155381.5A Pending CN109299552A (en) | 2018-09-29 | 2018-09-29 | A kind of appraisal procedure and its assessment system of battery power status |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109299552A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110416636A (en) * | 2019-06-26 | 2019-11-05 | 北京航空航天大学 | A kind of power battery management system and method based on cloud data management |
CN111222584A (en) * | 2020-01-15 | 2020-06-02 | 北京辉腾格勒石墨烯科技有限公司 | Lithium battery real-time evaluation method based on big data and deep neural network |
CN114139706A (en) * | 2021-08-31 | 2022-03-04 | 国网北京市电力公司 | Evaluation system of energy storage resource |
CN114579659A (en) * | 2022-03-07 | 2022-06-03 | 山东云储新能源科技有限公司 | System and method for estimating and sorting utilization potential of power battery by gradient utilization |
CN115098737A (en) * | 2022-06-14 | 2022-09-23 | 上海玫克生储能科技有限公司 | Energy storage power station data processing method and system, storage medium and terminal |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6271648B1 (en) * | 2000-09-27 | 2001-08-07 | Ford Global Tech., Inc. | Method of preconditioning a battery to improve cold temperature starting of a vehicle |
CN103257323A (en) * | 2013-06-03 | 2013-08-21 | 清华大学 | Method for estimating lithium ion battery remaining available capacity |
CN104951662A (en) * | 2015-07-16 | 2015-09-30 | 中国科学院广州能源研究所 | Method for estimating SOE (State of Energy) of lithium iron phosphate battery |
CN105068007A (en) * | 2015-07-01 | 2015-11-18 | 清华大学 | Method and system for predicting changes of parameters of lithium ion battery model |
CN106033113A (en) * | 2015-03-19 | 2016-10-19 | 国家电网公司 | Health state evaluation method for energy-storage battery pack |
CN107092733A (en) * | 2017-04-06 | 2017-08-25 | 汕头大学 | The lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks |
CN107656216A (en) * | 2017-11-15 | 2018-02-02 | 国网辽宁省电力有限公司鞍山供电公司 | A kind of lead-acid accumulator on-line monitoring is safeguarded and early warning system and performance estimating method |
CN108279383A (en) * | 2017-11-30 | 2018-07-13 | 深圳市科列技术股份有限公司 | battery life predicting method, battery data server and battery data processing system |
-
2018
- 2018-09-29 CN CN201811155381.5A patent/CN109299552A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6271648B1 (en) * | 2000-09-27 | 2001-08-07 | Ford Global Tech., Inc. | Method of preconditioning a battery to improve cold temperature starting of a vehicle |
CN103257323A (en) * | 2013-06-03 | 2013-08-21 | 清华大学 | Method for estimating lithium ion battery remaining available capacity |
CN106033113A (en) * | 2015-03-19 | 2016-10-19 | 国家电网公司 | Health state evaluation method for energy-storage battery pack |
CN105068007A (en) * | 2015-07-01 | 2015-11-18 | 清华大学 | Method and system for predicting changes of parameters of lithium ion battery model |
CN104951662A (en) * | 2015-07-16 | 2015-09-30 | 中国科学院广州能源研究所 | Method for estimating SOE (State of Energy) of lithium iron phosphate battery |
CN107092733A (en) * | 2017-04-06 | 2017-08-25 | 汕头大学 | The lithium ion battery mechanical strength Forecasting Methodology searched for based on Automatic Neural Networks |
CN107656216A (en) * | 2017-11-15 | 2018-02-02 | 国网辽宁省电力有限公司鞍山供电公司 | A kind of lead-acid accumulator on-line monitoring is safeguarded and early warning system and performance estimating method |
CN108279383A (en) * | 2017-11-30 | 2018-07-13 | 深圳市科列技术股份有限公司 | battery life predicting method, battery data server and battery data processing system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110416636A (en) * | 2019-06-26 | 2019-11-05 | 北京航空航天大学 | A kind of power battery management system and method based on cloud data management |
CN111222584A (en) * | 2020-01-15 | 2020-06-02 | 北京辉腾格勒石墨烯科技有限公司 | Lithium battery real-time evaluation method based on big data and deep neural network |
CN114139706A (en) * | 2021-08-31 | 2022-03-04 | 国网北京市电力公司 | Evaluation system of energy storage resource |
CN114579659A (en) * | 2022-03-07 | 2022-06-03 | 山东云储新能源科技有限公司 | System and method for estimating and sorting utilization potential of power battery by gradient utilization |
CN115098737A (en) * | 2022-06-14 | 2022-09-23 | 上海玫克生储能科技有限公司 | Energy storage power station data processing method and system, storage medium and terminal |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109299552A (en) | A kind of appraisal procedure and its assessment system of battery power status | |
Zhao et al. | Lithium-ion batteries state of charge prediction of electric vehicles using RNNs-CNNs neural networks | |
Liu et al. | Future ageing trajectory prediction for lithium-ion battery considering the knee point effect | |
CN112731159A (en) | Method for pre-judging and positioning battery fault of battery compartment of energy storage power station | |
CN111812536A (en) | Rapid evaluation method for retired power battery residual value | |
Zhang et al. | Intelligent state of charge estimation of battery pack based on particle swarm optimization algorithm improved radical basis function neural network | |
AU2021101964A4 (en) | Artificial intelligence based smart electric vehicle battery management system | |
CN115267555A (en) | Battery SOH (State of health) evaluation system of energy storage system based on battery multipoint temperature measurement | |
Zheng et al. | Real-time estimation of battery state of charge with metabolic grey model and LabVIEW platform | |
Zou et al. | Advancements in Artificial Neural Networks for health management of energy storage lithium-ion batteries: A comprehensive review | |
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 | |
CN111537888A (en) | Data-driven echelon battery SOC prediction method | |
Liu et al. | Data science-based full-lifespan management of lithium-ion battery: manufacturing, operation and reutilization | |
Long et al. | Multi-parameter optimization method for remaining useful life prediction of lithium-ion batteries | |
CN115586444A (en) | Lithium battery residual life prediction method based on VMD and BP neural network | |
CN115097312A (en) | Lithium ion battery fusion life prediction model combining data driving model and empirical model | |
Jafari et al. | Optimizing battery RUL prediction of lithium-ion batteries based on Harris hawk optimization approach using random forest and LightGBM | |
Chen et al. | State of health estimation of lithium-ion batteries based on equivalent circuit model and data-driven method | |
CN114879070A (en) | Battery state evaluation method and related equipment | |
CN110232432B (en) | Lithium battery pack SOC prediction method based on artificial life model | |
CN116609686B (en) | Battery cell consistency assessment method based on cloud platform big data | |
CN117054892A (en) | Evaluation method, device and management method for battery state of energy storage power station | |
Pozzato et al. | Combining physics-based and machine learning methods to accelerate innovation in sustainable transportation and beyond: a control perspective | |
Mehta et al. | A Comprehensive study of Machine Learning Techniques used for estimating State of Charge for Li-ion Battery | |
Huang et al. | SOC prediction of Lithium battery based on fuzzy information granulation and support vector regression |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190201 |