CN109307852A - A kind of method and system of the measurement error of determining electric automobile charging pile electric energy metering device - Google Patents
A kind of method and system of the measurement error of determining electric automobile charging pile electric energy metering device Download PDFInfo
- Publication number
- CN109307852A CN109307852A CN201811037730.3A CN201811037730A CN109307852A CN 109307852 A CN109307852 A CN 109307852A CN 201811037730 A CN201811037730 A CN 201811037730A CN 109307852 A CN109307852 A CN 109307852A
- Authority
- CN
- China
- Prior art keywords
- data
- electric energy
- layer
- error
- input
- 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
- 238000005259 measurement Methods 0.000 title claims abstract description 136
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 230000006870 function Effects 0.000 claims description 50
- 238000004364 calculation method Methods 0.000 claims description 30
- 238000003062 neural network model Methods 0.000 claims description 29
- 238000005192 partition Methods 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 12
- 238000007689 inspection Methods 0.000 claims description 11
- 210000004027 cell Anatomy 0.000 claims description 9
- 230000005611 electricity Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000007418 data mining Methods 0.000 abstract description 2
- 238000013210 evaluation model Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/16—Information or communication technologies improving the operation of electric vehicles
- Y02T90/167—Systems integrating technologies related to power network operation and communication or information technologies for supporting the interoperability of electric or hybrid vehicles, i.e. smartgrids as interface for battery charging of electric vehicles [EV] or hybrid vehicles [HEV]
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S30/00—Systems supporting specific end-user applications in the sector of transportation
- Y04S30/10—Systems supporting the interoperability of electric or hybrid vehicles
- Y04S30/12—Remote or cooperative charging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Fuzzy Systems (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Secondary Cells (AREA)
Abstract
The present invention provides a kind of method and system of the measurement error of the electric energy metering device of determining electric automobile charging pile, described method and system comprehensively utilizes a variety of factors for influencing electric energy metering error, data mining, which is carried out, by the method for clustering generates sample, the fuzzy-neural network method to be formed is combined using fuzzy system and artificial neural network, take full advantage of the advantages of two methods handle multiple coupled system, build an Intelligent electric-energy metering error evaluation model, substantially increase the accuracy that the electric energy metering error of electric automobile charging pile electric energy metering device calculates.
Description
Technical field
The present invention relates to electric energy metering error analysis fields, and charge more particularly, to a kind of determining electric car
The method and system of the measurement error of stake electric energy metering device.
Background technique
In the prior art, electric automobile charging pile electric energy metering error mainly utilizes the obtained mark under laboratory environment
Quasi- error obtained by Comparison Method, but in fact, the installation of electric automobile charging pile and working environment be it is complicated and diversified,
Can not be consistent always with laboratory environment, so the error information obtained by Comparison Method can not accurately react its reality
Situation, it is therefore desirable to the influence of many factors such as operation of power networks operating condition, environmental factor is comprehensively considered, further, since electric car
Power battery can be with the increase for using the time so that cell degradation, total capacity reduces, and the battery data of electric car also can
Influence the accuracy of electric energy metering error.
Summary of the invention
In order to solve to determine that charging pile electric energy metering error does not consider its actual working environment and battery in the prior art
The technical problem of calculated result inaccuracy caused by itself, the present invention provide a kind of determining electric automobile charging pile electrical energy measurement
The method of the measurement error of device, which comprises
It acquires the electric energy measurement data of electric automobile charging pile electric energy metering device and influences the factor of electric energy metering error
Data and establish database jointly with theoretical electric energy measurement data, in the database to actual power continuous data and reason
Primary Calculation is carried out by electric energy measurement data and obtains electrical energy measurement initial error, wherein the electric energy meter of the electric energy metering device
Measuring data includes first inspection data and week inspection data；
Using cluster algorithm on the factor of the electrical energy measurement initial error data and influence electric energy metering error
Data are screened, and the fuzzy neural network model for determining the measurement error of electric automobile charging pile electric energy metering device is formed
Input data；
Using the fuzzy neural network model for the measurement error for determining electric automobile charging pile electric energy metering device to described
Input data is trained, and determines the mapping relations of the input data Yu final electric energy metering error, and average using center
Anti-fuzzy method determines the final electric energy metering error of electric energy metering device.
Further, the data of the factor for influencing electric energy metering error include: grid operation data, electric car electricity
Pond data, environmental information data, mutual inductor data and analog/digital A/D converter precision.
Further, the calculation formula of the electrical energy measurement initial error are as follows:
Electrical energy measurement initial error=(actual power continuous data-theory electric energy measurement data)/theory electrical energy measurement number
According to.
Further, the algorithm using clustering on the electrical energy measurement initial error data and influences electric energy meter
The data for measuring the factor of error are screened, and the fuzzy of the measurement error for determining electric automobile charging pile electric energy metering device is formed
The input data of neural network model includes:
If determining the index set X={ x of the measurement error of electric automobile charging pile electric energy metering devicei, the index set
In index xiData set xi={ xik, wherein the index set X includes electrical energy measurement initial error data and influence electric energy
The factor of measurement error, 1≤i≤n, 1≤k≤m, m, n are natural number；
The data of each index in the index set X are standardized, and calculate that normalized treated
Index xiWith index xjSimilarity factor rij, wherein 1≤i, j≤n, n are natural number；
According to the similarity factor rijGenerate similarity relation matrixAnd by the method for transitive closure,
Work as R2k=RkWhen, determine the equivalent matrice R*=R of the similarity relation matrix Rk；
Based on the equivalent matrice R*Using different partition value λ to the equivalent matrice R*It is clustered, is determined optimal poly-
Class is as a result, and determine the input data of fuzzy neural network model according to the optimum cluster result.
Further, the data of each index in the index set X are standardized, and parameter xiWith
Index xjSimilarity factor rijInclude:
To the index x in index set XiData set { xikIn data xikIt carries out nondimensionalization processing and generates normal data
x'ik, its calculation formula is:
Wherein,
By standardized data x'ikThe achievement data x after generating normalization is normalized* ik, its calculation formula is:
Wherein, x'ikminAnd x'ikmaxIt is the minimum value and maximum value in standardized data respectively；
To the index x generated after the normalizationiWith index xjIts similarity factor is calculated, its calculation formula is:
Wherein,1≤i, j≤n.
Further, when partition value λ takes 0.7, to the equivalent matrice R*It carries out cluster and obtains optimum cluster result.
Further, electric energy measurement data and influence of the method in acquisition electric automobile charging pile electric energy metering device
Data of the factor of electric energy metering error and to establish before database further include establishing determining electric automobile charging pile electrical energy measurement
The fuzzy neural network model of the measurement error of device, the fuzzy neural network model are divided into 5 layers, enable xi(t) input is indicated,
Y indicates output, Ii (k)Indicate i-th of input of kth layer, wi (k)Indicate i-th of connection weight of kth layer, Oi (k)Indicate kth layer
I-th of output signal, O(5)Indicate the 5th layer of output, the i.e. final error of electric energy measurement, F () indicates activation primitive, often
The net input of a node is indicated by function f, in which:
For first layer as input layer, node is input node, number of nodes 6, respectively electrical energy measurement initial error number
According to, grid operation data, batteries of electric automobile situation, environmental information, mutual inductor data, A/D converter accuracy data 6 input
Value, i.e. f=Ii (1)(i=1,2,3,4,5,6), F ()=f, wi (1)=1, Oik (1)=xik(i=1,2 ..., 6；J=1,2 ...,
mi), wherein miFor xiFuzzy partition number；
The second layer is blurring layer, and each node indicates a linguistic variable value, and number of nodes is each node mould of first layer
The summation of paste segmentation artIt is used to calculate the degree of membership letter that each input component belongs to each linguistic variable value fuzzy set
Number, the blurring layer neuron use Gaussian function as excitation function, i.e., membership function uses Gaussian function in blurring layer
Number, then:
F ()=ef
Wherein ζikAnd δikCenter and the width for respectively indicating the Gauss type function of the kth item of the i-th input language variable, when
When input layer input signal, the blurring layer obtains corresponding degree of membership under the action of Gaussian function；
The node of third layer is fuzzy rule node, indicates that fuzzy logic ordination, number of nodes areThe third
Layer obtains out every rule using the self-study habit of neural network for generating fuzzy logic ordination and condition or former piece matching
Relevance grade, regular node executes fuzzy and operation: f=min (I1 (3),I2 (3),I3 (3),…,In (3)) and F ()=f, wi (3)=
1；
4th layer is then normalized operation, generates every rule and corresponds to the output that input generates, interstitial content and the
Three layers identical, i.e.,F ()=min (1, f), wi (4)=1；
Layer 5 is output layer, generates total output of control rule, final electric energy metering error is obtained, by second layer institute
The ζ of narrationikAnd δikThe respectively center of membership function and width are averaged Anti-fuzzy device f=∑ (w according to centerik (5)·Ii (5))
=∑ (ζikδik)·Ii (5),It seeks, wherein the connection weight w of layer 5ik (5)=ζikδik。
According to another aspect of the present invention, the present invention provides a kind of meter of determining electric automobile charging pile electric energy metering device
The system for measuring error, the system comprises:
Data acquisition unit is used to acquire electric energy measurement data and the influence of electric automobile charging pile electric energy metering device
The data of the factor of electric energy metering error simultaneously establish database with theoretical electric energy measurement data jointly, in the database to reality
Border electric energy measurement data and theoretical electric energy measurement data carry out primary Calculation and obtain electrical energy measurement initial error, wherein the electricity
The electric energy measurement data of energy metering device includes first inspection data and all inspection data；
Data clusters unit is used for the algorithm using clustering to the electrical energy measurement initial error data and influence
The data of the factor of electric energy metering error are screened, and the measurement error for determining electric automobile charging pile electric energy metering device is formed
Fuzzy neural network model input data；
Data training unit is used to utilize the fuzzy of the measurement error for determining electric automobile charging pile electric energy metering device
Neural network model is trained the input data, determines that the mapping of the input data and final electric energy metering error is closed
System, and the final electric energy metering error of electric energy metering device is determined using the center Anti-fuzzy method that is averaged.
Further, the data of the factor of the influence electric energy metering error of the data acquisition unit acquisition include: power grid
Operation data, batteries of electric automobile data, environmental information data, mutual inductor data and analog/digital A/D converter precision.
Further, the data acquisition unit calculates the calculation formula of electrical energy measurement initial error are as follows:
Electrical energy measurement initial error=(actual power continuous data-theory electric energy measurement data)/theory electrical energy measurement number
According to.
Further, the data clusters unit includes:
Index set unit is used to establish the index of the measurement error of determining electric automobile charging pile electric energy metering device
Collect X={ xi, the index x in the index setiData set xi={ xik, wherein at the beginning of the index set X includes electrical energy measurement
Beginning error information and the factor for influencing electric energy metering error, 1≤i≤n, 1≤k≤m, m, n is natural number；
Standardisation Cell is used to be standardized the data of each index in the index set X, and calculates
Normalized treated index xiWith index xjSimilarity factor rij, wherein 1≤i, j≤n, n are natural number；
Equivalent matrice unit is used for according to the similarity factor rijGenerate similarity relation matrixAnd
By the method for transitive closure, work as R2k=RkWhen, determine the equivalent matrice R of the similarity relation matrix R*=Rk；
Cluster result unit is used for based on the equivalent matrice R*Using different partition value λ to the equivalent matrice R*
It is clustered, determines optimum cluster as a result, and determining the input number of fuzzy neural network model according to the optimum cluster result
According to.
Further, the Standardisation Cell is standardized the data of each index in the index set X,
And parameter xiWith index xjSimilarity factor rijInclude:
To the index x in index set XiData set { xikIn data xikIt carries out nondimensionalization processing and generates normal data
x'ik, its calculation formula is:
Wherein,
By standardized data x'ikThe achievement data x after generating normalization is normalized* ik, its calculation formula is:
Wherein, x'ikminAnd x'ikmaxIt is the minimum value and maximum value in standardized data respectively；
To the index x generated after the normalizationiWith index xjIts similarity factor is calculated, its calculation formula is:
Wherein,1≤i, j≤n.
Further, the cluster result unit take partition value λ be 0.7 when, to the equivalent matrice R*Cluster is carried out to obtain
Obtain optimum cluster result.
Further, the system also includes model foundation unit, it is used to establish determining electric automobile charging pile electric energy
The fuzzy neural network model of the measurement error of metering device, the fuzzy neural network model are divided into 5 layers, enable xi(t) it indicates
Input, y indicate output, Ii (k)Indicate i-th of input of kth layer, wi (k)Indicate i-th of connection weight of kth layer, Oi (k)It indicates
I-th of output signal of kth layer, O(5)Indicate the 5th layer of output, the i.e. final error of electric energy measurement, F () indicates activation letter
The net input of number, each node is indicated by function f, in which:
For first layer as input layer, node is input node, number of nodes 6, respectively electrical energy measurement initial error number
According to, grid operation data, batteries of electric automobile situation, environmental information, mutual inductor data, A/D converter accuracy data 6 input
Value, i.e. f=Ii (1)(i=1,2,3,4,5,6), F ()=f, wi (1)=1, Oik (1)=xik(i=1,2 ..., 6；J=1,2 ...,
mi), wherein miFor xiFuzzy partition number；
The second layer is blurring layer, and each node indicates a linguistic variable value, and number of nodes is each node mould of first layer
The summation of paste segmentation artIt is used to calculate the degree of membership letter that each input component belongs to each linguistic variable value fuzzy set
Number, the blurring layer neuron use Gaussian function as excitation function, i.e., membership function uses Gaussian function in blurring layer
Number, then:
F ()=ef
Wherein ζikAnd δikCenter and the width for respectively indicating the Gauss type function of the kth item of the i-th input language variable, when
When input layer input signal, the blurring layer obtains corresponding degree of membership under the action of Gaussian function；
The node of third layer is fuzzy rule node, indicates that fuzzy logic ordination, number of nodes areThe third
Layer obtains out every rule using the self-study habit of neural network for generating fuzzy logic ordination and condition or former piece matching
Relevance grade, regular node executes fuzzy and operation: f=min (I1 (3),I2 (3),I3 (3),…,In (3)) and F ()=f, wi (3)=
1；
4th layer is then normalized operation, generates every rule and corresponds to the output that input generates, interstitial content and the
Three layers identical, i.e.,F ()=min (1, f), wi (4)=1；
Layer 5 is output layer, generates total output of control rule, final electric energy metering error is obtained, by second layer institute
The ζ of narrationikAnd δikThe respectively center of membership function and width are averaged Anti-fuzzy device f=∑ (w according to centerik (5)·Ii (5))
=∑ (ζikδik)·Ii (5),It seeks, wherein the connection weight w of layer 5ik (5)=ζikδik。
Technical solution of the present invention provide determination electric automobile charging pile electric energy metering device measurement error method and
System comprehensively utilizes a variety of factors for influencing electric energy metering error, carries out data mining by the method for clustering and generates sample
This, combines the fuzzy-neural network method to be formed using fuzzy system and artificial neural network, takes full advantage of two methods
The advantages of handling multiple coupled system builds an Intelligent electric-energy metering error evaluation model, greatly improves electric energy metering error
The accuracy of calculating.
Detailed description of the invention
By reference to the following drawings, exemplary embodiments of the present invention can be more fully understood by:
Fig. 1 is the measurement error according to the determination electric automobile charging pile electric energy metering device of the preferred embodiment for the present invention
Method flow chart；
Fig. 2 is the measurement error according to the determination electric automobile charging pile electric energy metering device of the preferred embodiment for the present invention
Fuzzy neural network model topological diagram；
Fig. 3 is the measurement error according to the determination electric automobile charging pile electric energy metering device of the preferred embodiment for the present invention
System structural schematic diagram.
Specific embodiment
Exemplary embodiments of the present invention are introduced referring now to the drawings, however, the present invention can use many different shapes
Formula is implemented, and is not limited to the embodiment described herein, and to provide these embodiments be at large and fully disclose
The present invention, and the scope of the present invention is sufficiently conveyed to person of ordinary skill in the field.Show for what is be illustrated in the accompanying drawings
Term in example property embodiment is not limitation of the invention.In the accompanying drawings, identical cells/elements use identical attached
Icon note.
Unless otherwise indicated, term (including scientific and technical terminology) used herein has person of ordinary skill in the field
It is common to understand meaning.Further it will be understood that with the term that usually used dictionary limits, should be understood as and its
The context of related fields has consistent meaning, and is not construed as Utopian or too formal meaning.
Fig. 1 is the measurement error according to the determination electric automobile charging pile electric energy metering device of the preferred embodiment for the present invention
Method flow chart.As shown in Figure 1, determination electric automobile charging pile electric energy metering device described in this preferred embodiment
The method 100 of measurement error is since step 101.
In step 101, the fuzzy neural network for determining the measurement error of electric automobile charging pile electric energy metering device is established
Model.
Fig. 2 is the measurement error according to the determination electric automobile charging pile electric energy metering device of the preferred embodiment for the present invention
Fuzzy neural network model topological diagram.As shown in Fig. 2, the fuzzy neural network model is divided into 5 layers, xi(t) indicate defeated
Enter, y indicates output, Ii (k)Indicate i-th of input of kth layer, wi (k)Indicate i-th of connection weight of kth layer, Oi (k)Indicate kth
I-th of output signal of layer, O(5)Indicating the 5th layer of output, the i.e. final error of electric energy measurement, F () indicates activation primitive,
The net input of each node is indicated by function f, in which:
For first layer as input layer, node is input node, number of nodes 6, respectively electrical energy measurement initial error number
According to, grid operation data, batteries of electric automobile situation, environmental information, mutual inductor data, A/D converter accuracy data 6 input
Value, i.e. f=Ii (1)(i=1,2,3,4,5,6), F ()=f, wi (1)=1, Oik (1)=xik(i=1,2 ..., 6；J=1,2 ...,
mi), wherein miFor xiFuzzy partition number；
The second layer is blurring layer, and each node indicates a linguistic variable value, and number of nodes is each node mould of first layer
The summation of paste segmentation artIt is used to calculate the degree of membership letter that each input component belongs to each linguistic variable value fuzzy set
Number, the blurring layer neuron use Gaussian function as excitation function, i.e., membership function uses Gaussian function in blurring layer
Number, then:
F ()=ef
Wherein ζikAnd δikCenter and the width for respectively indicating the Gauss type function of the kth item of the i-th input language variable, when
When input layer input signal, the blurring layer obtains corresponding degree of membership under the action of Gaussian function；
The node of third layer is fuzzy rule node, indicates that fuzzy logic ordination, number of nodes areThe third
Layer obtains out every rule using the self-study habit of neural network for generating fuzzy logic ordination and condition or former piece matching
Relevance grade, regular node executes fuzzy and operation: f=min (I1 (3),I2 (3),I3 (3),…,In (3)) and F ()=f, wi (3)=
1；
4th layer is then normalized operation, generates every rule and corresponds to the output that input generates, interstitial content and the
Three layers identical, i.e.,F ()=min (1, f), wi (4)=1；
Layer 5 is output layer, generates total output of control rule, final electric energy metering error is obtained, by second layer institute
The ζ of narrationikAnd δikThe respectively center of membership function and width are averaged Anti-fuzzy device f=∑ (w according to centerik(5)·Ii
(5))=∑ (ζikδik)·Ii(5),It seeks, wherein the connection weight w of layer 5ik(5)=ζik
δik。
In step 102, acquires the electric energy measurement data of electric automobile charging pile electric energy metering device and influence electrical energy measurement
The data of the factor of error simultaneously establish database with theoretical electric energy measurement data jointly, in the database to actual power meter
Amount data and theoretical electric energy measurement data carry out primary Calculation and obtain electrical energy measurement initial error, wherein the electrical energy measurement dress
The electric energy measurement data set includes first inspection data and week inspection data；
In step 103, electrical energy measurement mistake on the electrical energy measurement initial error data and is influenced using cluster algorithm
The data of the factor of difference are screened, and the fuzzy neural for determining the measurement error of electric automobile charging pile electric energy metering device is formed
The input data of network model；
In step 104, the fuzzy neural network for the measurement error for determining electric automobile charging pile electric energy metering device is utilized
Model is trained the input data, determines the mapping relations of the input data Yu final electric energy metering error, and makes
The final electric energy metering error of electric energy metering device is determined with the center Anti-fuzzy method that is averaged.
Preferably, the data of the factor for influencing electric energy metering error include: grid operation data, batteries of electric automobile
Data, environmental information data, mutual inductor data and analog/digital A/D converter precision.The grid operation data includes trend
And harmonic wave, the environmental information data include temperature and temperature, the batteries of electric automobile data include battery charge state SOC
With cell health state SOH, mutual inductor data include voltage transformer and current transformer data.Wherein, the electric car
Battery data is instant data, needs to carry out real-time communication with the battery management system of electric car.
Preferably, the calculation formula of the electrical energy measurement initial error are as follows:
Electrical energy measurement initial error=(actual power continuous data-theory electric energy measurement data)/theory electrical energy measurement number
According to.
Preferably, the algorithm using clustering on the electrical energy measurement initial error data and influences electrical energy measurement
The data of the factor of error are screened, and the fuzzy mind for determining the measurement error of electric automobile charging pile electric energy metering device is formed
Input data through network model includes:
If determining the index set X={ x of the measurement error of electric automobile charging pile electric energy metering devicei, the index set
In index xiData set xi={ xik, wherein the index set X includes electrical energy measurement initial error data and influence electric energy
The factor of measurement error, 1≤i≤n, 1≤k≤m, m, n are natural number；
The data of each index in the index set X are standardized, and calculate that normalized treated
Index xiWith index xjSimilarity factor rij, wherein 1≤i, j≤n, n are natural number；
According to the similarity factor rijGenerate similarity relation matrixAnd by the method for transitive closure,
Work as R2k=RkWhen, determine the equivalent matrice R of the similarity relation matrix R*=Rk；
Based on the equivalent matrice R*Using different partition value λ to the equivalent matrice R*It is clustered, is determined optimal poly-
Class is as a result, and determine the input data of fuzzy neural network model according to the optimum cluster result.
Preferably, the data of each index in the index set X are standardized, and parameter xiAnd finger
Mark xjSimilarity factor rijInclude:
To the index x in index set XiData set { xikIn data xikIt carries out nondimensionalization processing and generates normal data
x'ik, its calculation formula is:
Wherein,
By standardized data x'ikThe achievement data x after generating normalization is normalized* ik, its calculation formula is:
Wherein, x'ikminAnd x'ikmaxIt is the minimum value and maximum value in standardized data respectively；
To the index x generated after the normalizationiWith index xjIts similarity factor is calculated, its calculation formula is:
Wherein,1≤i, j≤n.
Preferably, when partition value λ takes 0.7, to the equivalent matrice R*It carries out cluster and obtains optimum cluster result.
Fig. 3 is the measurement error according to the determination electric automobile charging pile electric energy metering device of the preferred embodiment for the present invention
System structural schematic diagram.As shown in figure 3, determination electric automobile charging pile electrical energy measurement described in this preferred embodiment fills
The system 300 for the measurement error set includes:
Model foundation unit 301 is used to establish the measurement error of determining electric automobile charging pile electric energy metering device
Fuzzy neural network model.
Preferably, the fuzzy neural network model is divided into 5 layers, enables xi(t) input is indicated, y indicates output, Ii (k)It indicates
I-th of input of kth layer, wi (k)Indicate i-th of connection weight of kth layer, Oi (k)Indicate i-th of output signal of kth layer, O
(5) indicate the 5th layer of output, the i.e. final error of electric energy measurement, F () indicates activation primitive, each node it is net input by
Function f is indicated, in which:
For first layer as input layer, node is input node, number of nodes 6, respectively electrical energy measurement initial error number
According to, grid operation data, batteries of electric automobile situation, environmental information, mutual inductor data, A/D converter accuracy data 6 input
Value, i.e. f=Ii (1)(i=1,2,3,4,5,6), F ()=f, wi (1)=1, Oik (1)=xik(i=1,2 ..., 6；J=1,2 ...,
mi), wherein miFor xiFuzzy partition number；
The second layer is blurring layer, and each node indicates a linguistic variable value, and number of nodes is each node mould of first layer
The summation of paste segmentation artIt is used to calculate the degree of membership letter that each input component belongs to each linguistic variable value fuzzy set
Number, the blurring layer neuron use Gaussian function as excitation function, i.e., membership function uses Gaussian function in blurring layer
Number, then:
F ()=ef
Wherein ζikAnd δikCenter and the width for respectively indicating the Gauss type function of the kth item of the i-th input language variable, when
When input layer input signal, the blurring layer obtains corresponding degree of membership under the action of Gaussian function；
The node of third layer is fuzzy rule node, indicates that fuzzy logic ordination, number of nodes areThe third
Layer obtains out every rule using the self-study habit of neural network for generating fuzzy logic ordination and condition or former piece matching
Relevance grade, regular node executes fuzzy and operation: f=min (I1 (3),I2 (3),I3(3),…,In(3)) and F ()=f, wi
(3)=1；
4th layer is then normalized operation, generates every rule and corresponds to the output that input generates, interstitial content and the
Three layers identical, i.e.,F ()=min (1, f), wi (4)=1；
Layer 5 is output layer, generates total output of control rule, final electric energy metering error is obtained, by second layer institute
The ζ of narrationikAnd δikThe respectively center of membership function and width are averaged Anti-fuzzy device f=∑ (w according to centerik (5)·Ii (5))
=∑ (ζikδik)·Ii (5),It seeks, wherein the connection weight w of layer 5ik (5)=ζikδik。
Data acquisition unit 302, be used to acquire electric automobile charging pile electric energy metering device electric energy measurement data and
It influences the data of the factor of electric energy metering error and establishes database jointly with theoretical electric energy measurement data, in the database
Primary Calculation is carried out to actual power continuous data and theoretical electric energy measurement data and obtains electrical energy measurement initial error, wherein institute
The electric energy measurement data for stating electric energy metering device includes first inspection data and week inspection data；
Data clusters unit 303, be used for algorithm using clustering to the electrical energy measurement initial error data and
The data for influencing the factor of electric energy metering error are screened, and the metering for determining electric automobile charging pile electric energy metering device is formed
The input data of the fuzzy neural network model of error；
Data training unit 304 is used to utilize the measurement error for determining electric automobile charging pile electric energy metering device
Fuzzy neural network model is trained the input data, determines reflecting for the input data and final electric energy metering error
It penetrates relationship, and determines the final electric energy metering error of electric energy metering device using the center Anti-fuzzy method that is averaged.
Preferably, the data of the factor for the influence electric energy metering error that the data acquisition unit 302 acquires include: power grid
Operation data, batteries of electric automobile data, environmental information data, mutual inductor data and analog/digital A/D converter precision.
Preferably, the data acquisition unit 302 calculates the calculation formula of electrical energy measurement initial error are as follows:
Electrical energy measurement initial error=(actual power continuous data-theory electric energy measurement data)/theory electrical energy measurement number
According to.
Preferably, the data clusters unit 303 includes:
Index set unit 331 is used to establish the measurement error of determining electric automobile charging pile electric energy metering device
Index set X={ xi, the index x in the index setiData set xi={ xik, wherein the index set X includes electric energy meter
It measures initial error data and influences the factor of electric energy metering error, 1≤i≤n, 1≤k≤m, m, n is natural number；
Standardisation Cell 332 is used to be standardized the data of each index in the index set X, and
Calculate normalized treated index xiWith index xjSimilarity factor rij, wherein 1≤i, j≤n, n are natural number；
Equivalent matrice unit 333 is used for according to the similarity factor rijGenerate similarity relation matrix
And by the method for transitive closure, work as R2k=RkWhen, determine the equivalent matrice R of the similarity relation matrix R*=Rk；
Cluster result unit 334 is used for based on the equivalent matrice R*Using different partition value λ to the square of equal value
Battle array R*It is clustered, determines optimum cluster as a result, and determining the defeated of fuzzy neural network model according to the optimum cluster result
Enter data.
Preferably, the Standardisation Cell 332 is standardized place to the data of each index in the index set X
Reason, and parameter xiWith index xjSimilarity factor rijInclude:
To the index x in index set XiData set { xikIn data xikIt carries out nondimensionalization processing and generates normal data
x'ik, its calculation formula is:
Wherein,
By standardized data x'ikThe achievement data x after generating normalization is normalized* ik, its calculation formula is:
Wherein, x'ikminAnd x'ikmaxIt is the minimum value and maximum value in standardized data respectively；To raw after the normalization
At index xiWith index xjIts similarity factor is calculated, its calculation formula is:
Wherein,1≤i, j≤n.
Preferably, the cluster result unit 334 take partition value λ be 0.7 when, to the equivalent matrice R*Cluster is carried out to obtain
Obtain optimum cluster result.
The present invention is described by reference to a small amount of embodiment.However, it is known in those skilled in the art, as
Defined by subsidiary Patent right requirement, in addition to the present invention other embodiments disclosed above equally fall in it is of the invention
In range.
Normally, all terms used in the claims are all solved according to them in the common meaning of technical field
It releases, unless in addition clearly being defined wherein.All references " one/described/be somebody's turn to do [device, component etc.] " are all opened ground
At least one example being construed in described device, component etc., unless otherwise expressly specified.Any method disclosed herein
Step need not all be run with disclosed accurate sequence, unless explicitly stated otherwise.
Claims (14)
1. a kind of method of the measurement error of determining electric automobile charging pile electric energy metering device, which is characterized in that the method
Include:
It acquires the electric energy measurement data of electric automobile charging pile electric energy metering device and influences the number of the factor of electric energy metering error
Database is established jointly according to and with theoretical electric energy measurement data, in the database to actual power continuous data and theory electricity
Energy continuous data carries out primary Calculation and obtains electrical energy measurement initial error, wherein the electrical energy measurement number of the electric energy metering device
Data are examined according to including first inspection data and week；
Using cluster algorithm on the data of the electrical energy measurement initial error data and the factor for influencing electric energy metering error
It is screened, forms the input for determining the fuzzy neural network model of measurement error of electric automobile charging pile electric energy metering device
Data；
Using the fuzzy neural network model for the measurement error for determining electric automobile charging pile electric energy metering device to the input
Data are trained, and determine the mapping relations of the input data Yu final electric energy metering error, and are averaged reverse using center
Paste method determines the final electric energy metering error of electric energy metering device.
2. the method according to claim 1, wherein the data packet of the factor for influencing electric energy metering error
It includes: grid operation data, batteries of electric automobile data, environmental information data, mutual inductor data and analog/digital A/D converter
Precision.
3. according to the method described in claim 2, it is characterized in that, the calculation formula of the electrical energy measurement initial error are as follows:
Electrical energy measurement initial error=(actual power continuous data-theory electric energy measurement data)/theory electric energy measurement data.
4. according to the method described in claim 2, it is characterized in that, the algorithm using clustering is to the electrical energy measurement
The data of initial error data and the factor of influence electric energy metering error are screened, and are formed and are determined electric automobile charging pile electric energy
The input data of the fuzzy neural network model of the measurement error of metering device includes:
If determining the index set X={ x of the measurement error of electric automobile charging pile electric energy metering devicei, the finger in the index set
Mark xiData set xi={ xik, wherein the index set X includes that electrical energy measurement initial error data and influence electrical energy measurement miss
The factor of difference, 1≤i≤n, 1≤k≤m, m, n is natural number；
The data of each index in the index set X are standardized, and calculate normalized treated index xi
With index xjSimilarity factor rij, wherein 1≤i, j≤n, n are natural number；
According to the similarity factor rijGenerate similarity relation matrix R=(rij)n×n, and by the method for transitive closure, work as R2k=
RkWhen, determine the equivalent matrice R of the similarity relation matrix R*=Rk；
Based on the equivalent matrice R*Using different partition value λ to the equivalent matrice R*It is clustered, determines optimum cluster knot
Fruit, and determine according to the optimum cluster result input data of fuzzy neural network model.
5. according to the method described in claim 4, it is characterized in that, the data to each index in the index set X carry out
Standardization, and parameter xiWith index xjSimilarity factor rijInclude:
To the index x in index set XiData set { xikIn data xikIt carries out nondimensionalization processing and generates normal data x'ik,
Its calculation formula is:
Wherein,
By standardized data x'ikThe achievement data x after generating normalization is normalized* ik, its calculation formula is:
Wherein, x'ikminAnd x'ikmaxIt is the minimum value and maximum value in standardized data respectively；
To the index x generated after the normalizationiWith index xjIts similarity factor is calculated, its calculation formula is:
Wherein,
6. according to the method described in claim 4, it is characterized in that, when partition value λ takes 0.7, to the equivalent matrice R*It carries out
Cluster obtains optimum cluster result.
7. according to method described in claim 2 or 4, which is characterized in that the method is in acquisition electric automobile charging pile electricity
Can metering device electric energy measurement data and influence electric energy metering error factor data and establish before database and further include
Establish the fuzzy neural network model for determining the measurement error of electric automobile charging pile electric energy metering device, the fuzznet
Network model is divided into 5 layers, enables xi(t) input is indicated, y indicates output, Ii (k)Indicate i-th of input of kth layer, wi (k)Indicate kth layer
I-th of connection weight, Oi (k)Indicate i-th of output signal of kth layer, O(5)Indicate the 5th layer of output, i.e. electric energy measurement
Final error, F () indicate activation primitive, and the net input of each node is indicated by function f, in which:
For first layer as input layer, node is input node, number of nodes 6, respectively electrical energy measurement initial error data, electricity
6 net operation data, batteries of electric automobile situation, environmental information, mutual inductor data, A/D converter accuracy data input values, i.e.,
F=Ii (1)(i=1,2,3,4,5,6), F ()=f, wi (1)=1, Oik (1)=xik(i=1,2 ..., 6；J=1,2 ..., mi),
Wherein miFor xiFuzzy partition number；
The second layer is blurring layer, and each node indicates a linguistic variable value, and number of nodes is fuzzy point of each node of first layer
Cut the summation of artIt is used to calculate the subordinating degree function that each input component belongs to each linguistic variable value fuzzy set,
The blurring layer neuron uses Gaussian function as excitation function, i.e., membership function uses Gaussian function in blurring layer,
Then:
F ()=ef
Wherein ζikAnd δikCenter and the width for respectively indicating the Gauss type function of the kth item of the i-th input language variable, work as input layer
When input signal, the blurring layer obtains corresponding degree of membership under the action of Gaussian function；
The node of third layer is fuzzy rule node, indicates that fuzzy logic ordination, number of nodes areThe third layer is used
In generating fuzzy logic ordination and condition or former piece matching, i.e., the suitable of every rule is obtained out using the self-study habit of neural network
Expenditure, regular node execute fuzzy and operation: f=min (I1 (3),I2 (3),I3 (3),…,In (3)) and F ()=f, wi (3)=1；
4th layer is then normalized operation, generates every rule and corresponds to the output that input generates, interstitial content and third layer
It is identical, i.e.,F ()=min (1, f), wi (4)=1；
Layer 5 is output layer, generates total output of control rule, obtains final electric energy metering error, described by the second layer
ζikAnd δikThe respectively center of membership function and width are averaged Anti-fuzzy device f=∑ (w according to centerik (5)·Ii (5))=∑
(ζikδik)·Ii (5),It seeks, wherein the connection weight w of layer 5ik (5)=ζikδik。
8. a kind of system of the measurement error of determining electric automobile charging pile electric energy metering device, which is characterized in that the system
Include:
Data acquisition unit is used to acquire the electric energy measurement data of electric automobile charging pile electric energy metering device and influences electric energy
The data of the factor of measurement error simultaneously establish database with theoretical electric energy measurement data jointly, in the database to practical electricity
Energy continuous data and theoretical electric energy measurement data carry out primary Calculation and obtain electrical energy measurement initial error, wherein the electric energy meter
The electric energy measurement data for measuring device includes first inspection data and week inspection data；
Data clusters unit is used for the algorithm using clustering to the electrical energy measurement initial error data and influence electric energy
The data of the factor of measurement error are screened, and the mould for determining the measurement error of electric automobile charging pile electric energy metering device is formed
Paste the input data of neural network model；
Data training unit is used for the fuzzy neural using the measurement error for determining electric automobile charging pile electric energy metering device
Network model is trained the input data, determines the mapping relations of the input data Yu final electric energy metering error,
And the final electric energy metering error of electric energy metering device is determined using the center Anti-fuzzy method that is averaged.
9. system according to claim 8, which is characterized in that the influence electrical energy measurement of the data acquisition unit acquisition misses
The data of the factor of difference include: grid operation data, batteries of electric automobile data, environmental information data, mutual inductor data and mould
Quasi-/digital A/D converter precision.
10. system according to claim 9, which is characterized in that the data acquisition unit calculates electrical energy measurement and initially misses
The calculation formula of difference are as follows:
Electrical energy measurement initial error=(actual power continuous data-theory electric energy measurement data)/theory electric energy measurement data.
11. system according to claim 9, which is characterized in that the data clusters unit includes:
Index set unit is used to establish the index set X of the measurement error of determining electric automobile charging pile electric energy metering device
={ xi, the index x in the index setiData set xi={ xik, wherein the index set X includes that electrical energy measurement initially misses
Difference data and the factor for influencing electric energy metering error, 1≤i≤n, 1≤k≤m, m, n is natural number；
Standardisation Cell is used to be standardized the data of each index in the index set X, and calculates through marking
Standardization treated index xiWith index xjSimilarity factor rij, wherein 1≤i, j≤n, n are natural number；
Equivalent matrice unit is used for according to the similarity factor rijGenerate similarity relation matrix R=(rij)n×n, and pass through biography
The method for passing closure, works as R2k=RkWhen, determine the equivalent matrice R of the similarity relation matrix R*=Rk；
Cluster result unit is used for based on the equivalent matrice R*Using different partition value λ to the equivalent matrice R*It carries out
Cluster determines optimum cluster as a result, and determining the input data of fuzzy neural network model according to the optimum cluster result.
12. system according to claim 11, which is characterized in that the Standardisation Cell is to every in the index set X
The data of a index are standardized, and parameter xiWith index xjSimilarity factor rijInclude:
To the index x in index set XiData set { xikIn data xikIt carries out nondimensionalization processing and generates normal data x'ik,
Its calculation formula is:
Wherein,
By standardized data x'ikThe achievement data x after generating normalization is normalized* ik, its calculation formula is:
Wherein, x'ikminAnd x'ikmaxIt is the minimum value and maximum value in standardized data respectively；
To the index x generated after the normalizationiWith index xjIts similarity factor is calculated, its calculation formula is:
Wherein,
13. system according to claim 11, which is characterized in that the cluster result unit take partition value λ be 0.7 when,
To the equivalent matrice R*It carries out cluster and obtains optimum cluster result.
14. system described in 0 or 11 according to claim 1, which is characterized in that the system also includes model foundation unit,
The fuzzy neural network model of its measurement error for being used to establish determining electric automobile charging pile electric energy metering device is described fuzzy
Neural network model is divided into 5 layers, enables xi(t) input is indicated, y indicates output, Ii (k)Indicate i-th of input of kth layer, wi (k)Table
Show i-th of connection weight of kth layer, Oi (k)Indicate i-th of output signal of kth layer, O(5)Indicate the 5th layer of output, i.e. electric energy
The final error of measurement, F () indicate activation primitive, and the net input of each node is indicated by function f, in which:
For first layer as input layer, node is input node, number of nodes 6, respectively electrical energy measurement initial error data, electricity
6 net operation data, batteries of electric automobile situation, environmental information, mutual inductor data, A/D converter accuracy data input values, i.e.,
F=Ii (1)(i=1,2,3,4,5,6), F ()=f, wi (1)=1, Oik (1)=xik(i=1,2 ..., 6；J=1,2 ..., mi),
Wherein miFor xiFuzzy partition number；
The second layer is blurring layer, and each node indicates a linguistic variable value, and number of nodes is fuzzy point of each node of first layer
Cut the summation of artIt is used to calculate the subordinating degree function that each input component belongs to each linguistic variable value fuzzy set,
The blurring layer neuron uses Gaussian function as excitation function, i.e., membership function uses Gaussian function in blurring layer,
Then:
F ()=ef
Wherein ζikAnd δikCenter and the width for respectively indicating the Gauss type function of the kth item of the i-th input language variable, work as input layer
When input signal, the blurring layer obtains corresponding degree of membership under the action of Gaussian function；
The node of third layer is fuzzy rule node, indicates that fuzzy logic ordination, number of nodes areThe third layer is used
In generating fuzzy logic ordination and condition or former piece matching, i.e., the suitable of every rule is obtained out using the self-study habit of neural network
Expenditure, regular node execute fuzzy and operation: f=min (I1 (3),I2 (3),I3 (3),…,In (3)) and F ()=f, wi (3)=1；
4th layer is then normalized operation, generates every rule and corresponds to the output that input generates, interstitial content and third layer
It is identical, i.e.,F ()=min (1, f), wi (4)=1；
Layer 5 is output layer, generates total output of control rule, obtains final electric energy metering error, described by the second layer
ζikAnd δikThe respectively center of membership function and width are averaged Anti-fuzzy device f=∑ (w according to centerik (5)·Ii (5))=∑
(ζikδik)·Ii (5),It seeks, wherein the connection weight w of layer 5ik (5)=ζikδik。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811037730.3A CN109307852A (en) | 2018-09-06 | 2018-09-06 | A kind of method and system of the measurement error of determining electric automobile charging pile electric energy metering device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811037730.3A CN109307852A (en) | 2018-09-06 | 2018-09-06 | A kind of method and system of the measurement error of determining electric automobile charging pile electric energy metering device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109307852A true CN109307852A (en) | 2019-02-05 |
Family
ID=65224649
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811037730.3A Pending CN109307852A (en) | 2018-09-06 | 2018-09-06 | A kind of method and system of the measurement error of determining electric automobile charging pile electric energy metering device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109307852A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110095744A (en) * | 2019-04-04 | 2019-08-06 | 国网江苏省电力有限公司电力科学研究院 | A kind of electronic mutual inductor error prediction method |
| CN110717422A (en) * | 2019-09-25 | 2020-01-21 | 北京影谱科技股份有限公司 | Method and system for identifying interactive action based on convolutional neural network |
| CN114594318A (en) * | 2021-06-08 | 2022-06-07 | 浙江科律检测技术有限公司 | Metering error monitoring method for alternating current charging pile and storage medium |
| CN118011308A (en) * | 2024-04-08 | 2024-05-10 | 国网冀北电力有限公司 | Charging pile metering misalignment detection method, system, terminal and medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR970071027A (en) * | 1996-04-01 | 1997-11-07 | 김영귀 | How to measure battery charge of electric vehicle using neural network |
| CN105158725A (en) * | 2015-08-24 | 2015-12-16 | 中国电力科学研究院 | Multi-dimensional influence quantity-based electric energy meter metering accuracy evaluation method |
| CN105825290A (en) * | 2016-01-29 | 2016-08-03 | 江苏省电力公司电力经济技术研究院 | Electric quantity prediction method based on industrial chain product output |
| CN106249193A (en) * | 2016-09-06 | 2016-12-21 | 武汉尤瑞卡节能科技有限公司 | A kind of method and system of the charging pile electric energy metering error verification of charging station |
| CN106338708A (en) * | 2016-08-30 | 2017-01-18 | 中国电力科学研究院 | Electric energy metering error analysis method by combining deep learning and recursive neural network |
| CN106427589A (en) * | 2016-10-17 | 2017-02-22 | 江苏大学 | Electric car driving range estimation method based on prediction of working condition and fuzzy energy consumption |
| CN106712065A (en) * | 2017-02-23 | 2017-05-24 | 沈阳工业大学 | Prediction method of indexes of influence of electric card charging on power distribution network active loss |
| CN107085139A (en) * | 2017-05-16 | 2017-08-22 | 国网江苏省电力公司电力科学研究院 | The efficiency metering system and metering method of a kind of electric automobile direct-current charging post |
| CN107422272A (en) * | 2017-07-07 | 2017-12-01 | 淮阴工学院 | A kind of electric automobile power battery SOC intellectualized detection devices |
| CN107878244A (en) * | 2017-11-27 | 2018-04-06 | 深圳市菊水皇家科技有限公司 | A kind of data cleansing and Forecasting Methodology and electric automobile mobile charging treasured system |
| US20180188346A1 (en) * | 2017-01-03 | 2018-07-05 | San Diego Gas & Electric Company | Systems and Methods for Verifying Sub Metering Accuracy for Electric Vehicle Charging Stations |
-
2018
- 2018-09-06 CN CN201811037730.3A patent/CN109307852A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR970071027A (en) * | 1996-04-01 | 1997-11-07 | 김영귀 | How to measure battery charge of electric vehicle using neural network |
| CN105158725A (en) * | 2015-08-24 | 2015-12-16 | 中国电力科学研究院 | Multi-dimensional influence quantity-based electric energy meter metering accuracy evaluation method |
| CN105825290A (en) * | 2016-01-29 | 2016-08-03 | 江苏省电力公司电力经济技术研究院 | Electric quantity prediction method based on industrial chain product output |
| CN106338708A (en) * | 2016-08-30 | 2017-01-18 | 中国电力科学研究院 | Electric energy metering error analysis method by combining deep learning and recursive neural network |
| CN106249193A (en) * | 2016-09-06 | 2016-12-21 | 武汉尤瑞卡节能科技有限公司 | A kind of method and system of the charging pile electric energy metering error verification of charging station |
| CN106427589A (en) * | 2016-10-17 | 2017-02-22 | 江苏大学 | Electric car driving range estimation method based on prediction of working condition and fuzzy energy consumption |
| US20180188346A1 (en) * | 2017-01-03 | 2018-07-05 | San Diego Gas & Electric Company | Systems and Methods for Verifying Sub Metering Accuracy for Electric Vehicle Charging Stations |
| CN106712065A (en) * | 2017-02-23 | 2017-05-24 | 沈阳工业大学 | Prediction method of indexes of influence of electric card charging on power distribution network active loss |
| CN107085139A (en) * | 2017-05-16 | 2017-08-22 | 国网江苏省电力公司电力科学研究院 | The efficiency metering system and metering method of a kind of electric automobile direct-current charging post |
| CN107422272A (en) * | 2017-07-07 | 2017-12-01 | 淮阴工学院 | A kind of electric automobile power battery SOC intellectualized detection devices |
| CN107878244A (en) * | 2017-11-27 | 2018-04-06 | 深圳市菊水皇家科技有限公司 | A kind of data cleansing and Forecasting Methodology and electric automobile mobile charging treasured system |
Non-Patent Citations (3)
| Title |
|---|
| 王熙照等: "传递闭包聚类中的模糊性分析", 《计算机工程与应用》 * |
| 薛善良等: "基于模糊神经网络的WSN无线数据收发单元故障诊断", 《计算机科学》 * |
| 高琴妹: "《模糊集合基础理论及应用》", 31 December 2000, 东南大学出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110095744A (en) * | 2019-04-04 | 2019-08-06 | 国网江苏省电力有限公司电力科学研究院 | A kind of electronic mutual inductor error prediction method |
| CN110717422A (en) * | 2019-09-25 | 2020-01-21 | 北京影谱科技股份有限公司 | Method and system for identifying interactive action based on convolutional neural network |
| CN114594318A (en) * | 2021-06-08 | 2022-06-07 | 浙江科律检测技术有限公司 | Metering error monitoring method for alternating current charging pile and storage medium |
| CN118011308A (en) * | 2024-04-08 | 2024-05-10 | 国网冀北电力有限公司 | Charging pile metering misalignment detection method, system, terminal and medium |
| CN118011308B (en) * | 2024-04-08 | 2024-06-11 | 国网冀北电力有限公司 | Charging pile metering misalignment detection method, system, terminal and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109307852A (en) | A kind of method and system of the measurement error of determining electric automobile charging pile electric energy metering device | |
| CN109145949A (en) | Non-intrusive electrical load monitoring and decomposition method and system based on integrated study | |
| CN113064093B (en) | Method and system for jointly estimating state of charge and state of health of energy storage battery | |
| CN111368904B (en) | Electrical equipment identification method based on electric power fingerprint | |
| WO2022021726A1 (en) | Pmu-based power system state estimation performance evaluation method | |
| CN103514566A (en) | Risk control system and method | |
| Morsalin et al. | Electric vehicle charge scheduling using an artificial neural network | |
| CN106338708A (en) | Electric energy metering error analysis method by combining deep learning and recursive neural network | |
| CN105572572B (en) | Analog-circuit fault diagnosis method based on WKNN-LSSVM | |
| CN104280612B (en) | Distributed harmonic source identification method based on single-frequency current transmission characteristics | |
| CN106777786A (en) | A kind of lithium ion battery SOC estimation method | |
| CN109613440A (en) | Stage division, device, equipment and the storage medium of battery | |
| CN105807231A (en) | Method and system for storage battery residual capacity detection | |
| CN108804800A (en) | Lithium ion battery SOC on-line prediction methods based on echo state network | |
| CN110738429A (en) | electric energy meter state evaluation method and device | |
| CN107527131A (en) | A kind of cluster electric system energy consumption level evaluation method and device | |
| CN105406461A (en) | Adaptive dynamic load monitoring method for power distribution network power failure events | |
| CN107008671A (en) | The sorting technique and device of a kind of electrokinetic cell | |
| Cetinkaya | Long-term electrical load forecasting based on economic and demographic data for Turkey | |
| Mohammad et al. | Short term load forecasting using deep neural networks | |
| CN116842459B (en) | Electric energy metering fault diagnosis method and diagnosis terminal based on small sample learning | |
| CN113093014A (en) | Online collaborative estimation method and system for SOH and SOC based on impedance parameters | |
| Song et al. | Capacity estimation method of lithium-ion batteries based on deep convolution neural network | |
| CN111965442A (en) | Energy internet fault diagnosis method and device under digital twin environment | |
| CN105896547A (en) | Large power network graded voltage control method under wind power access |
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: 20190205 |
|
| RJ01 | Rejection of invention patent application after publication |