CN110095744A - A kind of electronic mutual inductor error prediction method - Google Patents
A kind of electronic mutual inductor error prediction method Download PDFInfo
- Publication number
- CN110095744A CN110095744A CN201910270880.7A CN201910270880A CN110095744A CN 110095744 A CN110095744 A CN 110095744A CN 201910270880 A CN201910270880 A CN 201910270880A CN 110095744 A CN110095744 A CN 110095744A
- Authority
- CN
- China
- Prior art keywords
- mutual inductor
- electronic mutual
- data
- sample data
- environment parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G01R35/02—Testing or calibrating of apparatus covered by the other groups of this subclass of auxiliary devices, e.g. of instrument transformers according to prescribed transformation ratio, phase angle, or wattage rating
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of electronic mutual inductor error prediction method, include the following steps: that the error information for acquiring electronic mutual inductor and environment parameter data generate sample data, and reject wherein abnormal data；Sample data is standardized based on Z-score standardized method；Clustering processing is carried out to the historical data of environment parameter, electronic mutual inductor error prediction model is established by training study；According to environment parameter value, predicted based on ratio difference and angular difference of the prediction model to electronic mutual inductor.Advantage: the present invention does not need to establish any physical model, method based on multidimensional data driving, according to the error information of electronic mutual inductor and environment parameter data, the On-line Estimation of electronic mutual inductor error may be implemented, it solves the problems, such as that electronic mutual inductor error and environment parameter are not present and determines functional relation, be conducive to the accuracy for improving electronic mutual inductor error prediction.
Description
Technical field
The invention belongs to equipment for power transmission and distribution status assessment and fault diagnosis fields, more particularly, to one kind based on cluster
The electronic mutual inductor error prediction method of neural network.
Background technique
Electronic mutual inductor be undertake intelligent substation digitlization, automation, information-based, interactive key equipment it
One.After electronic mutual inductor, signal light transmission fibrillation fundamentally solves electromagnetic transformer and is transferred to secondary device
Additive error problem, substantially increase the accuracy of measurement and metering system.But from the point of view of live operation problem, electronics
The accuracy problems of formula mutual inductor still occupy biggish ratio.Although all passed through type in fortune electronic mutual inductor
Formula test and delivery test, but its error qualification rate is generally relatively low when to in-site installation, most mutual inductors require at the scene into
Row error transfer factor.Since the change of external environment parameter is so that the error of electronic mutual inductor changes, in laboratory, now
The error of electronic mutual inductor is inconsistent when field off-line operation and on-line operation, and the stability of transformer error state is poor,
The metering confidence level of electronic mutual inductor is seriously affected.
The error of electronic mutual inductor examines the method for generalling use periodic inspection or interruption maintenance, utilizes standard electric
Magnetic-type mutual inductor verifies electronic mutual inductor, including offline method of calibration and on-line testing method.These methods of calibration
Can not assessment electronics formula mutual inductor longtime running error, and field conduct is difficult, and onerous toil is needed to operate.
The prior art includes the electronic mutual inductor error prediction method based on temporal model, by determining historic state
The correlation of data in time predicts future trends.But this method is not counted and the effect of extraneous factor,
When external environment varies widely, there may be large errors for prediction result.
The prior art further includes the electronic mutual inductor error prediction method based on error backward propagation method, will
The system that hollow coil current transformer is equivalent to a multiple input single output approaches mutual inductor based on feedforward neural network
The degradation characteristics of error are predicted according to ratio difference of the neural network model to mutual inductor.But this method does not account for sample
Influence of the exceptional value to the structure and parameter of model in notebook data, and there is also be easily trapped into local minimum, receive for the model
Hold back the disadvantages of speed is slow.
In conclusion the prior art can not assessment electronics formula mutual inductor longtime running error, field conduct is difficult, needs
It wants onerous toil to operate, is affected by the external environment big, there may be large errors for live prediction result, unreliable etc..
Summary of the invention
The technical problem to be solved by the present invention is to overcome the deficiencies of existing technologies, a kind of electronic mutual inductor mistake is provided
Poor prediction technique.
In order to solve the above technical problems, the present invention provides
A kind of electronic mutual inductor error prediction method, which is characterized in that include the following steps:
S1: acquisition electronic mutual inductor error amount and environment parameter value generate sample data；
S2: being standardized the sample data of electronic mutual inductor error amount, unified electronic formula transformer error
The unit and the order of magnitude of value and environment parameter value；
Clustering processing is carried out to the historical data of environment parameter, environment parameter data are divided into what several differed greatly
Space obtains the cluster centre of different classifications；
S3: by after cluster electronic mutual inductor error information and environment parameter data be trained study, establish and correspond to
Neural network, obtain electronic mutual inductor than poor prediction model and angular difference prediction model；
S4: based on training obtain than difference prediction model and angular difference prediction model, according to environment parameter value, to electronic type
The ratio difference and angular difference of mutual inductor are predicted.
Further, in the step S1, the sample data that electronic mutual inductor error and environment parameter value generate is distributed
Rule is distributed using β (g, h) come unified representation, x~β (g, h), x ∈ [a, b], and wherein x indicates sample data, and a and b indicate sample
The minimum value and maximum value of notebook data, g and h are expressed as distribution parameter.
Further, in the step S2, sample data is standardized based on Z-score standardized method,
Calculation formula are as follows:The wherein value of x ' expression standardization, x indicate sample data,Indicate sample data
Average value, σ indicate the standard deviation of sample data.
Further, in the step S2, K object is as cluster centre in selection sample data；Calculate sample data
Euclidean distance between cluster centre:Wherein, n indicates the number of sample data, xiIndicate sample
Notebook data value, UKIndicate cluster centre, according to apart from nearest principle by sample data distribute to away from nearest center to
Amount, constitutes disjoint cluster by these data；Using the mean value of sample datas all in different clusters as in new cluster
The heart；The Euclidean distance of sample data and new cluster centre is iterated to calculate, until new cluster centre is equal with former cluster centre
Or reach maximum number of iterations.
Further, in the step S3, using the ratio difference or angular difference of electronic mutual inductor as output variable, with environment
For parametric data as input variable, the input neuron number of the network is p, and output neuron number is q, hidden neuron
Number and object number it is equal be K；I-th of input vector of neural network is Xi=(x1,x2,…,xp), wherein x1,
x2... xpFor input vector XiElement, i-th output vector is Yi=(y1,y2,…,yq), wherein y1, y2... yqIt is defeated
Outgoing vector YiElement, output layer weight be W=[ω1, ω2,…,ωK]T, wherein ω1, ω2... ωKFor initial output layer
The element of weight vectors W, Basis Function Center value are cluster centre [U1,U2,…,UK]T, wherein U1,U2,…,UKFor cluster centre
Element, the transposition of T representing matrix.
Further, the mapping function of the hidden neuron is Gaussian function:
Wherein, j=1,2 ..., K, UjFor the element of cluster centre, σ2For cluster centre
The standard deviation of element；
According to output layer weight and mapping function, the output of neural network is acquired are as follows:ωj
For the element of initial output layer weight vectors W, the final weight W of neural network output layer is obtained according to least square methodn=
[w1, w2..., wk]T, wherein w1,w2,…,wKIndicate final output layer weight vectors WnElement.
Further, by environment parameter value Ci=(c1,c2,…,cp) substitute into the defeated of the neural network that step S3 is established
Enter, electronic mutual inductor is than difference or the predicted value of angular difference are as follows:With electronic mutual inductor error
Actual value fiOn the basis of, calculate prediction error:Wherein, c1,c2,…, cpIndicate environment parameter
Element, wjFor the element of final output layer weight vectors, N is to calculate points.
A kind of electronic mutual inductor Error prediction system, which is characterized in that including sequentially connected data acquisition module,
Standardization and clustering processing module, prediction model establish module and prediction module；
The data acquisition module generates sample data for acquiring electronic mutual inductor error amount and environment parameter value；
The standardization and clustering processing module are for marking the sample data of electronic mutual inductor error amount
Quasi-ization processing, the unit and the order of magnitude of unified electronic formula transformer error value and environment parameter value, and environment parameter is gone through
History data carry out clustering processing, and environment parameter data are divided into several spaces to differ greatly, obtain the cluster of different classifications
Center；
The prediction model establishes module for the electronic mutual inductor error information and environment parameter data after clustering
It is trained study, establishes corresponding neural network, obtains electronic mutual inductor than poor prediction model and angular difference prediction model；
The prediction module based on training obtain than difference prediction model and angular difference prediction model, according to environment parameter value,
The ratio difference and angular difference of electronic mutual inductor are predicted.
Further, the sample data regularity of distribution that the electronic mutual inductor error and environment parameter value generate uses β
(g, h) distribution carrys out unified representation, and x~β (g, h), x ∈ [a, b], wherein x indicates sample data, and a and b indicate sample data
Minimum value and maximum value, g and h are expressed as distribution parameter.
Further, the standardization and clustering processing module are used based on Z-score standardized method to sample
Data are standardized, calculation formula are as follows:The wherein value of x ' expression standardization, x indicate sample number
According to,Indicate that the average value of sample data, σ indicate the standard deviation of sample data；
K object is as cluster centre in the standardization and clustering processing module selection sample data；Calculate sample
Euclidean distance between notebook data and cluster centre:Wherein, n indicates the number of sample data, xi
Indicate sampled data values, UKIt indicates cluster centre, distributes to sample data away from nearest according to apart from nearest principle
Center vector constitutes disjoint cluster by these data；Gather the mean value of sample datas all in different clusters as new
Class center；The Euclidean distance of sample data and new cluster centre is iterated to calculate, until new cluster centre and former cluster centre
It is equal or reach maximum number of iterations.
Further, the prediction model establish module for using the ratio of electronic mutual inductor difference or angular difference as exporting
Variable, using environment parameter data as input variable, the input neuron number of the network is p, and output neuron number is q,
Hidden neuron number and object number it is equal be K；I-th input vector of neural network is Xi=(x1,x2,…,
xp), wherein x1, x2... xpFor input vector XiElement, i-th output vector is Yi=(y1,y2,…,yq), wherein y1,
y2... yqFor output vector YiElement, output layer weight be W=[ω1,ω2,…,ωK]T, wherein ω1, ω2... ωK
For the element of initial output layer weight vectors W, Basis Function Center value is cluster centre [U1,U2,…,UK]T, wherein U1,U2,…,
UKFor the element of cluster centre, the transposition of T representing matrix；
The mapping function of the hidden neuron is Gaussian function:
Wherein, j=1,2 ..., K, UjFor the element of cluster centre, σ2For cluster centre
The standard deviation of element,
According to output layer weight and mapping function, the output of neural network is acquired are as follows:
ωjFor the element of initial output layer weight vectors W, the final weight W of neural network output layer is obtained according to least square methodn=
[w1, w2..., wk]T, wherein w1,w2,…,wKIndicate final output layer weight vectors WnElement.
Further, the prediction module is by environment parameter value Ci=(c1,c2,…,cp) substitute into what step S4 was established
The input of neural network, electronic mutual inductor is than difference or the predicted value of angular difference are as follows:With electronics
Formula transformer error actual value fiOn the basis of, calculate prediction error:Wherein, c1,c2,…,cpTable
Show the element of environment parameter, wjFor the element of final output layer weight vectors, N is to calculate points.
Advantageous effects of the invention:
The present invention does not need to establish any physical model, based on the method for multidimensional data driving, according to electronic mutual inductor
Error information and environment parameter data, the On-line Estimation of electronic mutual inductor error may be implemented, solve electronic type mutual inductance
The problem of determining functional relation is not present in device error and environment parameter, is conducive to the standard for improving electronic mutual inductor error prediction
True property.
Detailed description of the invention
Fig. 1 is implementation process diagram of the invention；
Fig. 2 is electronic mutual inductor error state monitoring platform schematic diagram；
Fig. 3 (a), (b), (c), (d) and (f) be respectively temperature, humidity, vibration, magnetic field and load parameter cluster calculation
As a result；
Fig. 4 (a) and (b) are the neural network iteration result than poor prediction model and angular difference prediction model respectively；
Fig. 5 (a) and (b) are based on electronic mutual inductor of the invention respectively than difference prediction result and angular difference prediction knot
Fruit；
Wherein, 1 is hollow coil current transformer, and 2 be electromagnetic current transducer, and 3 be environmental monitoring unit, and 4 be light
Fine remote transmission unit, 5 be signal acquisition unit, and 6 be data processing unit, and 7 be time synchronization unit, and 8 be interchanger, and 9 be service
Device.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating this hair
Bright technical solution, and not intended to limit the protection scope of the present invention.
A kind of electronic mutual inductor error prediction method based on clustering neural network, comprising the following steps:
Step 1: acquisition electronic mutual inductor error amount and environment parameter value generate sample, are rejected based on β (g, h) distribution
Abnormal data in sample；
The value range of sample data capacity is in 10000~∞, it is preferable that sample size can be chosen for 15000.
The sample data regularity of distribution that electronic mutual inductor error and environment parameter value generate is distributed to unite using β (g, h)
One indicates, i.e. x~β (g, h), x ∈ [a, b], and wherein x indicates sample data, and a and b indicate the minimum value and maximum of sample data
Value, g and h are expressed as distribution parameter.
Enable u=(x-a)/(x-b), the estimated value of distribution parameter g and h are as follows:
Wherein,Indicate the mean value of u,Indicate the variance of u.
The estimated value of sample data distributionAre as follows:Wherein,For the mean value of sample data, σ is the standard deviation of sample data.If sampled data values existWithBetween, then judge the number
According to for normal data, otherwise judging that the data for abnormal data, and are rejected.
Step 2: the sample data after rejecting abnormalities data is standardized based on Z-score standardized method,
The unit and the order of magnitude of unified electronic formula transformer error value and environment parameter value；
For the sample data after rejecting abnormalities data, standard is carried out to sample data based on Z-score standardized method
Change processing is the difference of a score and average again divided by the process of standard deviation, calculation formula are as follows:
Step 3: clustering processing being carried out to the historical data of environment parameter, environment parameter data are divided into several differences
Biggish space obtains the cluster centre of different classifications；
K object is 1~4 as cluster centre, the value range of K in selection sample data, it is preferable that K is taken as 4；Meter
Calculate the Euclidean distance between sample data and cluster centre:Wherein, n indicates sample
The number of data, xiIndicate sampled data values, UjIt indicates cluster centre, distributes to sample data according to apart from nearest principle
Away from nearest center vector, disjoint cluster is constituted by these data；By the equal of sample datas all in K classification
Value is as new cluster centre；The Euclidean distance of sample data and new cluster centre is iterated to calculate, until new cluster centre
It is equal with former cluster centre or reach maximum number of iterations.
Step 4: by after cluster electronic mutual inductor error information and environment parameter data be trained study, establish
Corresponding neural network obtains electronic mutual inductor than poor prediction model and angular difference prediction model；
Using the ratio difference or angular difference of electronic mutual inductor as output variable, using environment parameter data as input variable, lead to
It crosses training study and establishes radial base neural net.The input neuron number of the network is p, and output neuron number is q, hidden
It is K containing neuron number, the value range of p is 2~5, it is preferable that p is taken as 5, q and is taken as 1；I-th of neural network input to
Amount is Xi=(x1,x2,…,xp), i-th of output vector is Yi=(y1, y2,…,yq), output layer weight is W=[ω1,
ω2,…,ωK]T, Basis Function Center value is cluster centre [U1, U2,…Uj...,UK]T；The mapping function of hidden neuron is height
This function:Wherein,According to output layer weight and reflect
Function is penetrated, it can be in the hope of the output of neural network are as follows:
The final weight W of neural network output layer is obtained according to least square methodn=[w1, w2..., wk]T……(7)。
Step 5: the prediction model obtained based on training, according to environment parameter value, to the ratio difference of electronic mutual inductor and angle
Difference is predicted.
It will be according to environment parameter value Ci=(c1,c2,…,cp) input of neural network that step S4 is established is substituted into, electricity
Minor mutual inductor is than difference or the predicted value of angular difference are as follows:With electronic mutual inductor
Error actual value fiOn the basis of, calculate prediction error:Wherein N is to calculate points.
The present invention will be further explained below with reference to the attached drawings and specific examples.Embodiment is exemplary, it is intended to be used
It is of the invention in explaining, and be not considered as limiting the invention.
As shown in Figure 1, the present invention according to the following steps predicts the error of electronic mutual inductor:
(1) electronic mutual inductor error state monitoring platform as shown in Figure 2 is built, electronic mutual inductor error is acquired
Data and environment parameter data.Platform include: environmental monitoring unit 3, optical fiber remote transmission unit 4, signal acquisition unit 5, at data
Manage unit 6, time synchronization unit 7.Be equipped in platform one 0.2 grade hollow coil current transformer 1 and one 0.2 grade
Electromagnetic current transducer 2.It is exported with electromagnetic current transducer 2 as standard signal, available hollow coil current is mutual
The comparison result of 1 error of sensor.Environmental monitoring unit 3 can be acquired the environment parameter of mutual inductor installation place, including temperature
The parameters such as degree, humidity, vibration, magnetic field；Optical fiber remote transmission unit 4 then by the data normalization of environmental monitoring unit, is sent to one
Data processing unit 6；Data are transferred to server 9 by interchanger 8 by data processing unit 6, and monitoring data are in server 9
In stored；The output data of the acquisition digitlization electromagnetic current transducer 2 of signal acquisition unit 5；Data processing unit 6
The output data of signal acquisition unit 5 and the sampling value message data of hollow coil current transformer 1 are received simultaneously.According to ring
The error information of border parameter and hollow coil current transformer 1 constructs original random matrix D；Clock synchronization unit 7 constructs whole
The synchronized clock system of a system is responsible for synchronization optical fiber remote transmission unit 4, data processing unit 6 and signal acquisition unit 5.Benefit
2 groups of abnormal datas in data sample are rejected with formula (1) and formula (2).
(2) sample data after rejecting abnormalities data is standardized using formula (3), unified electronic formula is mutual
The unit and the order of magnitude of sensor error amount and environment parameter value.
(3) it is iterated using formula (4), obtains the cluster centre of environment parameter, cluster result is as shown in Figure 3.
(4) using the ratio of electronic mutual inductor difference or angular difference as output variable, with temperature, humidity, vibration, magnetic field and
Load parameter calculates the weight of neural network output layer using formula (5)~formula (7) as input variable, establishes cluster mind
Through network, neural network iteration result is as shown in Figure 4.
(5) environment parameter is substituted into neural network, the ratio difference or angular difference of electronic mutual inductor is predicted using formula (8),
Prediction result is as shown in Figure 5, it can be seen that the maximum value than difference prediction error is 0.05%, and angular difference predicts error most
Big absolute value is 9.5 '.On the basis of electronic mutual inductor error true value, prediction error is calculated using formula (9), can be obtained
Reach 7.4% to than difference prediction error, angular difference prediction error reaches 9.5%, shows that prediction result and actual value are coincide.Ability
Technical staff in domain is it should be appreciated that embodiments herein can provide as method, system or computer program product.Therefore,
The shape of complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Formula.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions each in flowchart and/or the block diagram
The combination of process and/or box in process and/or box and flowchart and/or the block diagram.It can provide these computers
Processor of the program instruction to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices
To generate a machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute
For realizing the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram
Device.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that instruction stored in the computer readable memory generation includes
The manufacture of command device, the command device are realized in one box of one or more flows of the flowchart and/or block diagram
Or the function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that
Series of operation steps are executed on computer or other programmable devices to generate computer implemented processing, thus calculating
The instruction executed on machine or other programmable devices is provided for realizing in one or more flows of the flowchart and/or side
The step of function of being specified in block diagram one box or multiple boxes.The above is only a preferred embodiment of the present invention, it answers
When pointing out, for those skilled in the art, without departing from the technical principles of the invention, may be used also
To make several improvement and deformations, those modifications and variations should also be regarded as the protection scope of the present invention.
Claims (12)
1. a kind of electronic mutual inductor error prediction method, which is characterized in that include the following steps:
S1: acquisition electronic mutual inductor error amount and environment parameter value generate sample data；
S2: being standardized the sample data of electronic mutual inductor error amount, unified electronic formula transformer error value and
The unit and the order of magnitude of environment parameter value；
Clustering processing is carried out to the historical data of environment parameter, environment parameter data are divided into several spaces to differ greatly,
Obtain the cluster centre of different classifications；
S3: by after cluster electronic mutual inductor error information and environment parameter data be trained study, establish corresponding mind
Through network, electronic mutual inductor is obtained than poor prediction model and angular difference prediction model；
S4: based on training obtain than difference prediction model and angular difference prediction model, according to environment parameter value, to electronic mutual inductor
Ratio difference and angular difference predicted.
2. electronic mutual inductor error prediction method according to claim 1, which is characterized in that in the step S1, electricity
The sample data regularity of distribution that minor transformer error and environment parameter value generate is distributed using β (g, h) come unified representation, x~β
(g, h), x ∈ [a, b], wherein x indicates sample data, and a and b indicate the minimum value and maximum value of sample data, and g and h are expressed as
Distribution parameter.
3. electronic mutual inductor error prediction method according to claim 1, which is characterized in that in the step S2, base
Sample data is standardized in Z-score standardized method, calculation formula are as follows:Wherein x ' expression mark
The value of standardization processing, x indicate sample data,Indicate that the average value of sample data, σ indicate the standard deviation of sample data.
4. electronic mutual inductor error prediction method according to claim 1, which is characterized in that in the step S2, choosing
K object is as cluster centre in sampling notebook data；Calculate the Euclidean distance between sample data and cluster centre:Wherein, n indicates the number of sample data, xiIndicate sampled data values, UKIt indicates cluster centre, presses
Range distributes to sample data away from nearest center vector from nearest principle, is made of these data disjoint poly-
Class；Using the mean value of sample datas all in different clusters as new cluster centre；Iterate to calculate sample data and new cluster
The Euclidean distance at center, until new cluster centre is equal with former cluster centre or reaches maximum number of iterations.
5. electronic mutual inductor error prediction method according to claim 1, which is characterized in that in the step S3, with
The ratio difference or angular difference of electronic mutual inductor are as output variable, using environment parameter data as input variable, the input of the network
Neuron number is p, and output neuron number is q, hidden neuron number and object number it is equal be K；Neural network
I-th of input vector be Xi=(x1,x2,…,xp), wherein x1, x2... xpFor input vector XiElement, export for i-th to
Amount is Yi=(y1,y2,…,yq), wherein y1, y2... yqFor output vector YiElement, output layer weight be W=[ω1,
ω2,…,ωK]T, wherein ω1, ω2... ωKFor the element of initial output layer weight vectors W, Basis Function Center value is in cluster
The heart [U1,U2,…,UK]T, wherein U1,U2,…,UKFor the element of cluster centre, the transposition of T representing matrix.
6. electronic mutual inductor error prediction method according to claim 5, which is characterized in that the hidden neuron
Mapping function is Gaussian function:
Wherein, j=1,2 ..., K, UjFor the element of cluster centre, σ2For cluster centre element
Standard deviation；
According to output layer weight and mapping function, the output of neural network is acquired are as follows:ωjIt is first
The element of beginning output layer weight vectors W obtains the final weight W of neural network output layer according to least square methodn=[w1,
w2,…,wk]T, wherein w1,w2,…,wKIndicate final output layer weight vectors WnElement.
7. electronic mutual inductor error prediction method according to claim 6, which is characterized in that by environment parameter value Ci=
(c1,c2,…,cp) input of neural network that step S3 is established is substituted into, electronic mutual inductor is than difference or the predicted value of angular difference
Are as follows:With electronic mutual inductor error actual value fiOn the basis of, calculate prediction error:Wherein, c1,c2,…,cpIndicate the element of environment parameter, wjFor final output layer weight vectors
Element, N are to calculate points.
8. a kind of electronic mutual inductor Error prediction system, which is characterized in that including sequentially connected data acquisition module, standard
Change processing and clustering processing module, prediction model establish module and prediction module；
The data acquisition module generates sample data for acquiring electronic mutual inductor error amount and environment parameter value；
The standardization and clustering processing module are for being standardized the sample data of electronic mutual inductor error amount
Processing, the unit and the order of magnitude of unified electronic formula transformer error value and environment parameter value, and the history number to environment parameter
According to clustering processing is carried out, environment parameter data are divided into several spaces to differ greatly, obtain the cluster centre of different classifications；
The prediction model establishes module for the electronic mutual inductor error information and the progress of environment parameter data after clustering
Training study, establishes corresponding neural network, obtains electronic mutual inductor than poor prediction model and angular difference prediction model；
The prediction module based on training obtain than difference prediction model and angular difference prediction model, according to environment parameter value, to electricity
The ratio difference and angular difference of minor mutual inductor are predicted.
9. electronic mutual inductor Error prediction system according to claim 8, which is characterized in that the electronic mutual inductor
The sample data regularity of distribution that error and environment parameter value generate is distributed using β (g, h) come unified representation, x~β (g, h), x ∈
[a, b], wherein x indicates sample data, and a and b indicate the minimum value and maximum value of sample data, and g and h are expressed as distribution parameter.
10. electronic mutual inductor Error prediction system according to claim 8, which is characterized in that the standardization
It uses with clustering processing module and sample data is standardized based on Z-score standardized method, calculation formula are as follows:The wherein value of x ' expression standardization, x indicate sample data,Indicate that the average value of sample data, σ indicate
The standard deviation of sample data；
K object is as cluster centre in the standardization and clustering processing module selection sample data；Calculate sample number
According to the Euclidean distance between cluster centre:Wherein, n indicates the number of sample data, xiIndicate sample
Notebook data value, UKIndicate cluster centre, according to apart from nearest principle by sample data distribute to away from nearest center to
Amount, constitutes disjoint cluster by these data；Using the mean value of sample datas all in different clusters as new cluster centre；
Iterate to calculate the Euclidean distance of sample data and new cluster centre, until new cluster centre it is equal with original cluster centre or
Reach maximum number of iterations.
11. electronic mutual inductor Error prediction system according to claim 8, which is characterized in that the prediction model is built
Formwork erection block is used for using the ratio of electronic mutual inductor difference or angular difference as output variable, using environment parameter data as input variable,
The input neuron number of the network be p, output neuron number be q, hidden neuron number and object number it is equal be K
It is a；I-th of input vector of neural network is Xi=(x1,x2,…,xp), wherein x1, x2... xpFor input vector XiElement,
I-th of output vector is Yi=(y1,y2,…,yq), wherein y1, y2... yqFor output vector YiElement, output layer weight be W
=[ω1,ω2,…,ωK]T, wherein ω1, ω2... ωKFor the element of initial output layer weight vectors W, Basis Function Center value
For cluster centre [U1,U2,…,UK]T, wherein U1,U2,…,UKFor the element of cluster centre, the transposition of T representing matrix；
The mapping function of the hidden neuron is Gaussian function:
Wherein, j=1,2 ..., K, UjFor the element of cluster centre, σ2For cluster centre element
Standard deviation acquires the output of neural network according to output layer weight and mapping function are as follows:ωj
For the element of initial output layer weight vectors W, the final weight W of neural network output layer is obtained according to least square methodn=[w1,
w2,…,wk]T, wherein w1,w2,…,wKIndicate final output layer weight vectors WnElement.
12. electronic mutual inductor Error prediction system according to claim 8, which is characterized in that the prediction module will
Environment parameter value Ci=(c1,c2,…,cp) substitute into the input of neural network that step S4 is established, electronic mutual inductor than difference or
The predicted value of person's angular difference are as follows:With electronic mutual inductor error actual value fiOn the basis of, calculate prediction
Error:Wherein, c1,c2,…,cpIndicate the element of environment parameter, wjFor final output layer weight to
The element of amount, N are to calculate points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910270880.7A CN110095744B (en) | 2019-04-04 | 2019-04-04 | Error prediction method for electronic transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910270880.7A CN110095744B (en) | 2019-04-04 | 2019-04-04 | Error prediction method for electronic transformer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110095744A true CN110095744A (en) | 2019-08-06 |
| CN110095744B CN110095744B (en) | 2021-05-11 |
Family
ID=67444305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910270880.7A Active CN110095744B (en) | 2019-04-04 | 2019-04-04 | Error prediction method for electronic transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110095744B (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110542879A (en) * | 2019-09-30 | 2019-12-06 | 国网四川省电力公司电力科学研究院 | Method and system for predicting operation performance variation trend of capacitor voltage transformer |
| CN110632546A (en) * | 2019-09-25 | 2019-12-31 | 国网江苏省电力有限公司电力科学研究院 | Electronic transformer credibility evaluation method and device based on whole-network-domain evidence set |
| CN110632545A (en) * | 2019-09-25 | 2019-12-31 | 国网江苏省电力有限公司电力科学研究院 | Regression neural network-based error risk assessment method and device for electronic transformer |
| CN111160419A (en) * | 2019-12-13 | 2020-05-15 | 中国电力科学研究院有限公司 | Electronic transformer data classification prediction method and device based on deep learning |
| CN111537938A (en) * | 2020-03-31 | 2020-08-14 | 国网江西省电力有限公司电力科学研究院 | Error short-time prediction method for electronic transformer based on intelligent algorithm |
| CN111814390A (en) * | 2020-06-18 | 2020-10-23 | 三峡大学 | Voltage transformer error prediction method based on transfer entropy and wavelet neural network |
| CN111896905A (en) * | 2020-06-18 | 2020-11-06 | 中国电力科学研究院有限公司 | Power transformer operation error state identification method and device |
| CN112379322A (en) * | 2020-11-05 | 2021-02-19 | 广东电网有限责任公司佛山供电局 | On-line monitoring method for capacitor voltage transformer |
| CN112816754A (en) * | 2020-12-22 | 2021-05-18 | 深圳供电局有限公司 | Current compensation method and equipment for current transformer |
| CN112990598A (en) * | 2021-03-31 | 2021-06-18 | 浙江禹贡信息科技有限公司 | Reservoir water level time sequence prediction method and system |
| CN112989587A (en) * | 2021-03-04 | 2021-06-18 | 国网湖南省电力有限公司 | Online analysis method and system for degradation cause of capacitive voltage transformer |
| CN113156359A (en) * | 2021-04-16 | 2021-07-23 | 中国电力科学研究院有限公司 | Method and system for determining metering error of capacitor voltage transformer |
| CN113218444A (en) * | 2021-03-31 | 2021-08-06 | 中国电力科学研究院有限公司 | Intelligent sensing method and device for operating environment of electric energy metering device |
| CN113325357A (en) * | 2021-08-04 | 2021-08-31 | 华中科技大学 | Voltage transformer error evaluation method and system based on output time series difference |
| CN113376562A (en) * | 2021-06-08 | 2021-09-10 | 国网重庆市电力公司营销服务中心 | CVT (continuously variable transmission) verification method, device and medium based on rolling time window-FCM (fuzzy c-means) clustering |
| CN113447879A (en) * | 2021-05-27 | 2021-09-28 | 国网山东省电力公司营销服务中心(计量中心) | Electric energy meter metering error prediction method, system and device based on multi-stress influence |
| CN113567904A (en) * | 2021-07-02 | 2021-10-29 | 中国电力科学研究院有限公司 | Method and system suitable for metering error of capacitive mutual inductor |
| CN113702895A (en) * | 2021-10-28 | 2021-11-26 | 华中科技大学 | Online quantitative evaluation method for error state of voltage transformer |
| CN113743651A (en) * | 2021-08-04 | 2021-12-03 | 三峡大学 | Electronic voltage transformer error state prediction method based on machine learning and SVM algorithm |
| CN113777552A (en) * | 2021-11-09 | 2021-12-10 | 武汉格蓝若智能技术有限公司 | Method and system for predicting metering error of capacitive voltage transformer |
| CN113821938A (en) * | 2021-11-18 | 2021-12-21 | 武汉格蓝若智能技术有限公司 | Short-term prediction method and device for metering error state of mutual inductor |
| CN115480204A (en) * | 2022-09-29 | 2022-12-16 | 武汉格蓝若智能技术有限公司 | Current transformer operation error online evaluation optimization method based on big data deduction |
| CN115542230A (en) * | 2022-11-24 | 2022-12-30 | 武汉格蓝若智能技术股份有限公司 | Current transformer error estimation method and device based on diffusion model |
| CN115616470A (en) * | 2022-12-20 | 2023-01-17 | 国网福建省电力有限公司 | Current transformer metering error state prediction method, system, equipment and medium |
| CN115878963A (en) * | 2023-01-05 | 2023-03-31 | 国网江苏省电力有限公司营销服务中心 | Capacitance voltage transformer metering error prediction method, system, terminal and medium |
| CN116125361A (en) * | 2023-02-03 | 2023-05-16 | 华中科技大学 | Voltage transformer error evaluation method, system, electronic equipment and storage medium |
| CN118091527A (en) * | 2024-04-24 | 2024-05-28 | 威胜集团有限公司 | Voltage transformer error assessment method based on interpretive deep learning |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103412948A (en) * | 2013-08-27 | 2013-11-27 | 北京交通大学 | Cluster-based collaborative filtering commodity recommendation method and system |
| CN103837770A (en) * | 2014-02-26 | 2014-06-04 | 广东电网公司电力科学研究院 | Electrical equipment defect detection and maintenance method |
| CN104850859A (en) * | 2015-05-25 | 2015-08-19 | 电子科技大学 | Multi-scale analysis based image feature bag constructing method |
| EP2914068A1 (en) * | 2014-02-28 | 2015-09-02 | Zhejiang Sungiant arts and crafts Co., Ltd. | Electronic transformer-controlled two-wire two-way LED (light-emitting diode) lamp string |
| US20150268290A1 (en) * | 2012-10-24 | 2015-09-24 | State Grid Corporation Of China (Sgcc) | Method for On-Line Diagnosing Gradually-Changing Fault of Electronic Current Transformers |
| JP5858519B2 (en) * | 2011-08-31 | 2016-02-10 | 国立研究開発法人産業技術総合研究所 | Error evaluation system for electronic current transformers |
| CN106548021A (en) * | 2016-11-03 | 2017-03-29 | 华中科技大学 | A kind of electronic mutual inductor error state appraisal procedure based on higher-dimension random matrix |
| CN107817395A (en) * | 2017-09-05 | 2018-03-20 | 天津市电力科技发展有限公司 | A kind of stealing investigation method based on power network line kinematic error remote calibration |
| CN107972508A (en) * | 2017-11-27 | 2018-05-01 | 南京晓庄学院 | A kind of electric automobile charge power control method and control device |
| CN108801448A (en) * | 2018-07-09 | 2018-11-13 | 滨州职业学院 | A kind of urban traffic noise monitoring system of intelligent terminal monitoring |
| CN109307852A (en) * | 2018-09-06 | 2019-02-05 | 中国电力科学研究院有限公司 | A kind of method and system of the measurement error of determining electric automobile charging pile electric energy metering device |
-
2019
- 2019-04-04 CN CN201910270880.7A patent/CN110095744B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5858519B2 (en) * | 2011-08-31 | 2016-02-10 | 国立研究開発法人産業技術総合研究所 | Error evaluation system for electronic current transformers |
| US20150268290A1 (en) * | 2012-10-24 | 2015-09-24 | State Grid Corporation Of China (Sgcc) | Method for On-Line Diagnosing Gradually-Changing Fault of Electronic Current Transformers |
| CN103412948A (en) * | 2013-08-27 | 2013-11-27 | 北京交通大学 | Cluster-based collaborative filtering commodity recommendation method and system |
| CN103837770A (en) * | 2014-02-26 | 2014-06-04 | 广东电网公司电力科学研究院 | Electrical equipment defect detection and maintenance method |
| EP2914068A1 (en) * | 2014-02-28 | 2015-09-02 | Zhejiang Sungiant arts and crafts Co., Ltd. | Electronic transformer-controlled two-wire two-way LED (light-emitting diode) lamp string |
| CN104850859A (en) * | 2015-05-25 | 2015-08-19 | 电子科技大学 | Multi-scale analysis based image feature bag constructing method |
| CN106548021A (en) * | 2016-11-03 | 2017-03-29 | 华中科技大学 | A kind of electronic mutual inductor error state appraisal procedure based on higher-dimension random matrix |
| CN107817395A (en) * | 2017-09-05 | 2018-03-20 | 天津市电力科技发展有限公司 | A kind of stealing investigation method based on power network line kinematic error remote calibration |
| CN107972508A (en) * | 2017-11-27 | 2018-05-01 | 南京晓庄学院 | A kind of electric automobile charge power control method and control device |
| CN108801448A (en) * | 2018-07-09 | 2018-11-13 | 滨州职业学院 | A kind of urban traffic noise monitoring system of intelligent terminal monitoring |
| CN109307852A (en) * | 2018-09-06 | 2019-02-05 | 中国电力科学研究院有限公司 | A kind of method and system of the measurement error of determining electric automobile charging pile electric energy metering device |
Non-Patent Citations (2)
| Title |
|---|
| WU QIAO 等: "Error prediction method of electronic transformers based on RBF neural network", 《 2017 13TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONIC MEASUREMENT & INSTRUMENTS (ICEMI)》 * |
| 胡琛 等: "基于随机矩阵理论的电子式互感器误差状态相关性分析方法", 《电力自动化设备》 * |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110632545B (en) * | 2019-09-25 | 2021-09-21 | 国网江苏省电力有限公司电力科学研究院 | Regression neural network-based error risk assessment method and device for electronic transformer |
| CN110632546A (en) * | 2019-09-25 | 2019-12-31 | 国网江苏省电力有限公司电力科学研究院 | Electronic transformer credibility evaluation method and device based on whole-network-domain evidence set |
| CN110632545A (en) * | 2019-09-25 | 2019-12-31 | 国网江苏省电力有限公司电力科学研究院 | Regression neural network-based error risk assessment method and device for electronic transformer |
| CN110632546B (en) * | 2019-09-25 | 2021-07-02 | 国网江苏省电力有限公司电力科学研究院 | Electronic transformer credibility evaluation method and device based on whole-network-domain evidence set |
| CN110542879A (en) * | 2019-09-30 | 2019-12-06 | 国网四川省电力公司电力科学研究院 | Method and system for predicting operation performance variation trend of capacitor voltage transformer |
| CN110542879B (en) * | 2019-09-30 | 2022-02-11 | 国网四川省电力公司电力科学研究院 | Method and system for predicting operation performance variation trend of capacitor voltage transformer |
| CN111160419A (en) * | 2019-12-13 | 2020-05-15 | 中国电力科学研究院有限公司 | Electronic transformer data classification prediction method and device based on deep learning |
| CN111160419B (en) * | 2019-12-13 | 2023-04-18 | 中国电力科学研究院有限公司 | Deep learning-based electronic transformer data classification prediction method and device |
| CN111537938B (en) * | 2020-03-31 | 2022-12-09 | 国网江西省电力有限公司电力科学研究院 | Error short-time prediction method for electronic transformer based on intelligent algorithm |
| CN111537938A (en) * | 2020-03-31 | 2020-08-14 | 国网江西省电力有限公司电力科学研究院 | Error short-time prediction method for electronic transformer based on intelligent algorithm |
| CN111896905A (en) * | 2020-06-18 | 2020-11-06 | 中国电力科学研究院有限公司 | Power transformer operation error state identification method and device |
| CN111814390A (en) * | 2020-06-18 | 2020-10-23 | 三峡大学 | Voltage transformer error prediction method based on transfer entropy and wavelet neural network |
| CN111814390B (en) * | 2020-06-18 | 2023-07-28 | 三峡大学 | Voltage transformer error prediction method based on transfer entropy and wavelet neural network |
| CN112379322A (en) * | 2020-11-05 | 2021-02-19 | 广东电网有限责任公司佛山供电局 | On-line monitoring method for capacitor voltage transformer |
| CN112816754A (en) * | 2020-12-22 | 2021-05-18 | 深圳供电局有限公司 | Current compensation method and equipment for current transformer |
| CN112989587A (en) * | 2021-03-04 | 2021-06-18 | 国网湖南省电力有限公司 | Online analysis method and system for degradation cause of capacitive voltage transformer |
| CN113218444A (en) * | 2021-03-31 | 2021-08-06 | 中国电力科学研究院有限公司 | Intelligent sensing method and device for operating environment of electric energy metering device |
| CN112990598A (en) * | 2021-03-31 | 2021-06-18 | 浙江禹贡信息科技有限公司 | Reservoir water level time sequence prediction method and system |
| CN113156359B (en) * | 2021-04-16 | 2024-01-26 | 中国电力科学研究院有限公司 | Method and system for determining metering error of capacitive voltage transformer |
| CN113156359A (en) * | 2021-04-16 | 2021-07-23 | 中国电力科学研究院有限公司 | Method and system for determining metering error of capacitor voltage transformer |
| CN113447879A (en) * | 2021-05-27 | 2021-09-28 | 国网山东省电力公司营销服务中心(计量中心) | Electric energy meter metering error prediction method, system and device based on multi-stress influence |
| CN113376562A (en) * | 2021-06-08 | 2021-09-10 | 国网重庆市电力公司营销服务中心 | CVT (continuously variable transmission) verification method, device and medium based on rolling time window-FCM (fuzzy c-means) clustering |
| CN113567904A (en) * | 2021-07-02 | 2021-10-29 | 中国电力科学研究院有限公司 | Method and system suitable for metering error of capacitive mutual inductor |
| CN113743651A (en) * | 2021-08-04 | 2021-12-03 | 三峡大学 | Electronic voltage transformer error state prediction method based on machine learning and SVM algorithm |
| CN113325357A (en) * | 2021-08-04 | 2021-08-31 | 华中科技大学 | Voltage transformer error evaluation method and system based on output time series difference |
| CN113702895B (en) * | 2021-10-28 | 2022-02-08 | 华中科技大学 | Online quantitative evaluation method for error state of voltage transformer |
| CN113702895A (en) * | 2021-10-28 | 2021-11-26 | 华中科技大学 | Online quantitative evaluation method for error state of voltage transformer |
| CN113777552A (en) * | 2021-11-09 | 2021-12-10 | 武汉格蓝若智能技术有限公司 | Method and system for predicting metering error of capacitive voltage transformer |
| CN113821938A (en) * | 2021-11-18 | 2021-12-21 | 武汉格蓝若智能技术有限公司 | Short-term prediction method and device for metering error state of mutual inductor |
| CN113821938B (en) * | 2021-11-18 | 2022-02-18 | 武汉格蓝若智能技术有限公司 | Short-term prediction method and device for metering error state of mutual inductor |
| CN115480204A (en) * | 2022-09-29 | 2022-12-16 | 武汉格蓝若智能技术有限公司 | Current transformer operation error online evaluation optimization method based on big data deduction |
| CN115542230B (en) * | 2022-11-24 | 2023-03-24 | 武汉格蓝若智能技术股份有限公司 | Current transformer error estimation method and device based on diffusion model |
| CN115542230A (en) * | 2022-11-24 | 2022-12-30 | 武汉格蓝若智能技术股份有限公司 | Current transformer error estimation method and device based on diffusion model |
| CN115616470A (en) * | 2022-12-20 | 2023-01-17 | 国网福建省电力有限公司 | Current transformer metering error state prediction method, system, equipment and medium |
| CN115616470B (en) * | 2022-12-20 | 2023-09-22 | 国网福建省电力有限公司 | Method, system, equipment and medium for predicting metering error state of current transformer |
| CN115878963A (en) * | 2023-01-05 | 2023-03-31 | 国网江苏省电力有限公司营销服务中心 | Capacitance voltage transformer metering error prediction method, system, terminal and medium |
| CN115878963B (en) * | 2023-01-05 | 2023-06-23 | 国网江苏省电力有限公司营销服务中心 | Method, system, terminal and medium for predicting metering error of capacitive voltage transformer |
| CN116125361B (en) * | 2023-02-03 | 2023-07-18 | 华中科技大学 | Voltage transformer error evaluation method, system, electronic equipment and storage medium |
| CN116125361A (en) * | 2023-02-03 | 2023-05-16 | 华中科技大学 | Voltage transformer error evaluation method, system, electronic equipment and storage medium |
| CN118091527A (en) * | 2024-04-24 | 2024-05-28 | 威胜集团有限公司 | Voltage transformer error assessment method based on interpretive deep learning |
| CN118091527B (en) * | 2024-04-24 | 2024-07-09 | 威胜集团有限公司 | Voltage transformer error assessment method based on interpretive deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110095744B (en) | 2021-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110095744A (en) | A kind of electronic mutual inductor error prediction method | |
| CN110082579A (en) | A kind of area's Intelligent power-stealing prevention monitoring method, system, equipment and medium | |
| CN104200288B (en) | A kind of equipment fault Forecasting Methodology based on dependency relation identification between factor and event | |
| CN109491289A (en) | A kind of dynamic early-warning method and device for data center's dynamic environment monitoring | |
| CN106647650B (en) | Distributing Industrial Process Monitoring method based on variable weighting pca model | |
| CN109103991B (en) | Big data analysis method for intelligent power distribution network | |
| CN110826228B (en) | Regional power grid operation quality limit evaluation method | |
| CN109818349A (en) | A kind of power grid robust state prediction technique based on multi-dimensional state matrix shiding matching | |
| CN110348665A (en) | A kind of low-voltage platform area electric power system data quality evaluating method and device | |
| CN109298225B (en) | Automatic identification model system and method for abnormal state of voltage measurement data | |
| CN110019098A (en) | Electrical energy measurement big data analysis system based on Hadoop frame | |
| CN114297947B (en) | Data-driven wind power system twinning method and system based on deep learning network | |
| CN113659565B (en) | Online prediction method for frequency situation of new energy power system | |
| CN111476427A (en) | Low-voltage distribution area topology identification method and identification device | |
| CN108132423B (en) | A kind of method for rapidly positioning based on state transition probability power system monitoring data distortion | |
| CN109687426A (en) | Fault rate parameter modeling method, device, equipment and storage medium | |
| CN111598165A (en) | Density clustering outlier detection method based on extreme learning machine | |
| CN115204698A (en) | Real-time analysis method for power supply stability of low-voltage transformer area | |
| CN116956189A (en) | Current abnormality detection system, method, electronic equipment and medium | |
| CN116308883A (en) | Regional power grid data overall management system based on big data | |
| CN116467648A (en) | Early monitoring method for nonlinear platform power failure based on Internet of things table | |
| CN110378358A (en) | A kind of power distribution network isomeric data integration method and system | |
| CN115169719A (en) | Platform area state prediction model based on fuzzy clustering and BP neural network | |
| Ullah et al. | Adaptive data balancing method using stacking ensemble model and its application to non-technical loss detection in smart grids | |
| CN110133417A (en) | Grid line loss detection system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |