CN106650191A - Wind power plant power prediction sample screening method based on double confidence intervals - Google Patents
Wind power plant power prediction sample screening method based on double confidence intervals Download PDFInfo
- Publication number
- CN106650191A CN106650191A CN201510729241.4A CN201510729241A CN106650191A CN 106650191 A CN106650191 A CN 106650191A CN 201510729241 A CN201510729241 A CN 201510729241A CN 106650191 A CN106650191 A CN 106650191A
- Authority
- CN
- China
- Prior art keywords
- sample
- confidential interval
- screening
- weight
- interval
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a wind power plant power prediction sample screening method based on double confidence intervals. The method includes the steps that firstly, two linear functions are set to serve as an upper limit and a lower limit of the first confidence interval, and all samples outside the confidence interval are removed according to a set screening coefficient; then according to the wind speed-active power relation of a wind power plant, two non-linear piecewise functions are set to serve as an upper limit and a lower limit of the second confidence interval, all samples outside the confidence interval are removed, upper and lower limit function coefficients of the second confidence interval are continuously adjusted, and it is guaranteed that sample screening is completed after the ratio of the number of samples falling in the confidence interval to the total number of samples is larger than or equal to the set screening coefficient. Wind speed-active power samples capable of best reflecting the operating characteristics of the wind power plant can be screened out, and the defects that in a traditional method, training is not convergent, and wrong wind speed-active power relations are easily introduced are corrected.
Description
Technical field
The present invention relates to be based on dual confidence area in wind farm power prediction field, specifically wind farm power prediction
Between wind farm power prediction screening sample method.
Background technology
At present the construction of wind energy turbine set is more and more, and wind farm power prediction is link important in wind energy turbine set.
Current wind farm power prediction generally uses intelligent algorithm, is input into the actual measurement wind speed number of wind energy turbine set
According to survey active data, the wind speed-active mapping relations of wind energy turbine set are obtained after being trained, then carry out power
Prediction.Wind speed-active data are trained using intelligent algorithm, to wind speed, active this two classes power
Forecast sample has very strong dependence.All actual measurement wind speed and all realities that traditional method passes through collection wind energy turbine set
Active data are surveyed, the data for obtaining filtering out after data quality exception are rejected, then is carried out using intelligent algorithm
Training, has the disadvantage that：
Training does not restrain：The little wind in part and ration the power supply maintenance down when wind speed-active sample cannot reject so that
The sample for filtering out is in divergent state, cannot be restrained using neural metwork training, it is impossible to obtain wind speed-active
Mapping relations, lead to not carry out wind farm power prediction.
Introduce wrong mapping relations：After part abnormal data is introduced, in the case where neural metwork training is restrained,
Wind speed-power the mapping relations of mistake are introduced, causes wind farm power prediction results abnormity.
The content of the invention
The wind for not restraining, introducing mistake is trained in order to overcome traditional wind farm power prediction screening sample method to cause
The defect of speed-active mapping relations, it is proposed that a kind of wind power prediction sample based on dual confidential interval is sieved
Choosing method.
The screening sample of wind farm power prediction of the present invention arranges first two linear functions and resets letter as first
Interval bound, according to the sieveing coeffecient of setting, rejects all samples outside this confidential interval；Secondly
According to the wind speed-active relation of wind energy turbine set, two nonlinear piecewise functions are set used as the second weight confidential interval
Bound, rejects all samples outside this confidential interval, while constantly adjusting the upper of the second weight confidential interval
Lower limit function coefficient, it is ensured that the number of samples in confidential interval that falls accounts for total sample number purpose ratio value more than or equal to setting
After fixed sieveing coeffecient, screening sample is completed.
The purpose of the present invention is reached by following measure：Wind farm power prediction based on dual confidential interval
Screening sample method, comprises the steps：
Step (1), initialization sample selects number of days；
Step (2), it is active to reality to be normalized, set up two dimension so that the reality after wind speed and normalization is active
Coordinate system；
Step (3), the bound function of the weight confidential interval of initialization first, resets as the first of screening sample
The interval bound of letter, it is ensured that the sample number >=total sample number * sieveing coeffecient a fallen in the first weight confidential interval1,
Increase sample number of days if being unsatisfactory for, to obtain enough sample numbers, it is ensured that this part sample is scolded in conduct
In first weight confidential interval of screening sample；
Step (4), carries out the screening sample of the second weight confidential interval, arranges the second heavy confidential interval bound letter
Number is screened, if number of samples is unsatisfactory for expected requirement, is screened again after adjustment bound function；
If now cannot still meet expected requirement beyond adjustment, increase sample number of days, until sample number meets being expected
Require；
Step (5), the sample to filtering out is extracted, and active P is multiplied by by normalizedInstallationCarry out anti-normalizing
Change, complete screening.
Further, in the step (1), initialization sample number of days selects the integral multiple of 15 days or a week.
Further, initialization sample number of days is 2 to 12 all.Initialization sample number of days is rule of thumb typically selected
Select 15 days, usually the integral multiple of i.e. a week 7 days, can need to be set to for 2 to 8 weeks according to scene,
Typically not greater than 3 months.
Further, in the step (3)：The upper limit function of the weight confidential interval of initialization first:ymax=kmax*x
And lower limit function:ymin=kmin* x, as the first of screening sample the bound of confidential interval is weighed, wherein
ymin=kmin* x is the first heavy lower limit of confidence interval function；ymax=kmax* x is the first heavy confidential interval upper limit letter
Number；If the sample number fallen in the first weight confidential interval<Total sample number * sieveing coeffecient a1, increase sample number of days,
Increasing every time after number of days 2 carries out sample collection, then is screened；If the sample fallen in the first weight confidential interval
This number >=total sample number * sieveing coeffecient a1, then first again screening finish；Sieveing coeffecient a1Typically in 0.6-0.9
Between.
Further, in the step (4)：When carrying out the second weight confidential interval screening, the second weight is initialized
The upper limit function of confidential interval：fmaxAnd lower limit function：fmin, using the two functions as the second of screening sample
The bound of weight confidential interval, carries out next step screening sample；fmaxFor the second heavy confidential interval upper limit function,
fminFor the second heavy lower limit of confidence interval function, dynamic adjustment number of times t=0 is initialized afterwards；If dynamic adjustment time
Number t>tmax(dynamic adjustment number of times maximum), increases sample number of days, and to increase carry out sample sieve after number of days 2 every time
Choosing；If dynamic adjustment number of times t≤tmax, tmaxFor dynamic adjustment number of times maximum, judge to fall to reset second
Whether the sample number in letter interval is more than or equal to total sample number * sieveing coeffecient a2, if it is, second resets letter
Interval screening is completed；If it is not, dynamic the second heavy confidential interval upper limit function coefficient k of adjustmentmax=kmax+
△kmax, kmaxFor upper limit function coefficient, △ kmaxFor the second heavy confidential interval upper limit function coefficient amendment step-length,
Adjustment upper limit function parameter cmax=cmax+△cmax, cmaxFor upper limit function parameter, △ cmaxLetter is reset for second
Interval upper limit function parameters revision step-length；Adjust the second heavy lower limit of confidence interval function coefficients kmin=kmin-△
kmin, kminFor the coefficient of lower limit function, △ kminFor the second heavy lower limit of confidence interval function coefficients amendment step-length,
Adjustment lower limit function parameter cmin=cmin-△cmin, cminThe parameter of lower limit function, △ cminLetter area is reset for second
Between lower limit function parameters revision step-length, after often adjusting once, dynamic adjustment number of times t=t+1 then carries out the second weight
Screening sample the, until sample number >=total sample number * sieveing coeffecient a fallen in the second weight confidential interval2, then it is complete
Screening sample in the second weight confidential interval.
Beneficial effect
By obtaining correct wind speed-active mapping relations, forecast model is set up, improve active pre- of wind energy turbine set
Accuracy rate is surveyed, is on the one hand conducive to electrical network reasonable arrangement the whole network planned production, be on the other hand conducive to wind energy turbine set to look forward to
Industry obtains good economic benefit in the performance appraisal of grid company.
Description of the drawings
Fig. 1 is based on the wind farm power prediction screening sample method logic diagram of dual confidential interval.
Specific embodiment
Referring to Fig. 1, this wind farm power prediction screening sample method based on dual confidential interval, including it is as follows
Step：
Step (1), initialization sample selects number of days；
Step (2), it is active to reality to be normalized, set up two dimension so that the reality after wind speed and normalization is active
Coordinate system；
Step (3), the bound function of the weight confidential interval of initialization first, resets as the first of screening sample
The interval bound of letter, it is ensured that the sample number >=total sample number * sieveing coeffecient a fallen in the first weight confidential interval1,
Increase sample number of days if being unsatisfactory for, to obtain enough sample numbers, it is ensured that this part sample is scolded in conduct
In first weight confidential interval of screening sample；
Step (4), carries out the screening sample of the second weight confidential interval, arranges the second heavy confidential interval bound letter
Number is screened, if number of samples is unsatisfactory for expected requirement, is screened again after adjustment bound function；
If now cannot still meet expected requirement beyond adjustment, increase sample number of days, until sample number meets being expected
Require；
Step (5), the sample to filtering out is extracted, and active P is multiplied by by normalizedInstallationCarry out anti-normalizing
Change, complete screening.
Preferably, in the step (1), initialization sample number of days selects 15 days or one week whole
Several times.Initialization sample number of days is 2 to 12 all.Initialization sample number of days is rule of thumb typically chosen 15 days,
Usually the integral multiple of i.e. a week 7 days, can need to be set to for 2 to 8 weeks, typically not greater than according to scene
3 months.In the step (3)：The upper limit function of the weight confidential interval of initialization first:ymax=kmax* x and lower limit
Function:ymin=kmin* x, as the first of screening sample the bound of confidential interval, wherein y are weighedmin=kmin* x is
First heavy lower limit of confidence interval function；ymax=kmax* x is the first heavy confidential interval upper limit function；If fallen
Sample number in one weight confidential interval<Total sample number * sieveing coeffecient a1, increase sample number of days, number of days is increased every time
Sample collection is carried out after 2, then is screened；If sample number >=the sample fallen in the first weight confidential interval is total
Number * sieveing coeffecient a1, then first again screening finish；Sieveing coeffecient a1Typically between 0.6-0.9.The step
Suddenly in (4)：When carrying out the second weight confidential interval screening, the upper limit function of the weight confidential interval of initialization second：
fmaxAnd lower limit function：fmin, using the two functions as the bound of the second of screening sample the weight confidential interval,
Carry out next step screening sample；fmaxFor the second heavy confidential interval upper limit function, fminFor under the second weight confidential interval
Limit function, initializes afterwards dynamic adjustment number of times t=0；If dynamic adjustment number of times t>tmax(dynamic adjustment number of times
Maximum), increase sample number of days, to increase carry out screening sample after number of days 2 every time；If dynamic adjustment number of times
t≤tmax, tmaxFor dynamic adjustment number of times maximum, whether the sample number that judgement falls in the second weight confidential interval
More than or equal to total sample number * sieveing coeffecient a2, if it is, the screening of the second weight confidential interval is completed；If
It is not, dynamic the second heavy confidential interval upper limit function coefficient k of adjustmentmax=kmax+△kmax, kmaxFor upper limit function system
Number, △ kmaxFor the second heavy confidential interval upper limit function coefficient amendment step-length, upper limit function parameter c is adjustedmax=cmax+
△cmax, cmaxFor upper limit function parameter, △ cmaxFor the second heavy confidential interval upper limit function parameters revision step-length；Adjust
Whole second heavy lower limit of confidence interval function coefficients kmin=kmin-△kmin, kminFor the coefficient of lower limit function, △ kminFor
Second heavy lower limit of confidence interval function coefficients amendment step-length, adjusts lower limit function parameter cmin=cmin-△cmin, cmin
The parameter of lower limit function, △ cminFor the second heavy lower limit of confidence interval function parameter amendment step-length, often adjust once
Afterwards, dynamic adjustment number of times t=t+1, then the second heavy screening sample is carried out, until falling in the second weight confidential interval
Sample number >=total sample number * sieveing coeffecient a2, then the screening sample in the second weight confidential interval is completed.
1) wind speed of days=15 days and active sample are chosen in initialization；
2) air speed value keeps constant, active P in sampleIt is real/PInstallationIt is normalized, sets up two-dimensional coordinate system (its
Middle PIt is realBe wind energy turbine set reality it is active, PInstallationIt is the installed capacity of wind energy turbine set)；
3) upper limit function of the weight of initialization first confidential interval:ymax=k1max* x and lower limit function:ymin=k1min* x,
As the bound of the first weight confidential interval of screening sample
(wherein k1maxFor the coefficient of the first heavy confidential interval upper limit function, k1minFor under the first weight confidential interval
The coefficient of limit function)；
If 4) sample number fallen in the first weight confidential interval<Total sample number * sieveing coeffecient a1, increase sample
Number of days, increases after number of days 2 every time, sample collection is carried out, into step 2) continue executing with；
If 5) sample number >=total sample number * sieveing coeffecient a fallen in the first weight confidential interval1, enter second
Screen again；
6) second again screening start, initialization second weight confidential interval upper limit function:fmaxAnd lower limit function:fmin,
Using the two functions as the bound of the second of screening sample the weight confidential interval, next step screening sample is carried out；
7) dynamic adjustment number of times t=0 is initialized；
If 8) dynamic adjustment number of times t>tmax(dynamic adjustment number of times maximum), increases sample number of days, increases every time
Plus sample collection is carried out after number of days 2, and into step 2) continue executing with；
If 9) dynamic adjustment number of times t≤tmax(dynamic adjustment number of times maximum), into step 10) and step
11) screening；
If 10) sample number fallen in the second weight confidential interval<Total sample number * sieveing coeffecient a2, dynamic adjustment
Second heavy confidential interval upper limit function coefficient kmax=kmax+△kmax, adjust upper limit function parameter cmax=cmax+△
cmax；Adjust the second heavy lower limit of confidence interval function coefficients kmin=kmin-△kmin, adjust lower limit function parameter cmin=
cmin-△cmin, after often adjusting once, dynamic adjustment number of times t=t+1；Into step 8)；
(wherein, △ kmaxFor the second heavy confidential interval upper limit function coefficient amendment step-length, △ cmaxLetter is reset for second
Interval upper limit function parameters revision step-length, △ kminFor the second heavy lower limit of confidence interval function coefficients amendment step-length,
△cminFor the second heavy lower limit of confidence interval function parameter amendment step-length)；
If 11) sample number >=total sample number * sieveing coeffecient a fallen in the second weight confidential interval2, filter out
Sample, active P is multiplied by by normalizedInstallationRenormalization is carried out, screening is completed.
Claims (5)
1. based on dual confidential interval wind farm power prediction screening sample method, it is characterised in that include as
Lower step：
Step (1), initialization sample selects number of days；
Step (2), it is active to reality to be normalized, set up two so that the reality after wind speed and normalization is active
Dimension coordinate system；
Step (3), the bound function of the weight confidential interval of initialization first, as the first weight of screening sample
The bound of confidential interval, it is ensured that the sample number >=total sample number * sieveing coeffecient fallen in the first weight confidential interval
A1, increases sample number of days if being unsatisfactory for, to obtain enough sample numbers, it is ensured that this part sample is scolded
As in the first weight confidential interval of screening sample；
Step (4), carries out the screening sample of the second weight confidential interval, arranges the second heavy confidential interval bound
Function is screened, if number of samples is unsatisfactory for expected requirement, is screened again after adjustment bound function；
If now cannot still meet expected requirement beyond adjustment, increase sample number of days, until sample number meets being expected
Require；
Step (5), the sample to filtering out is extracted, by it is normalized it is active be multiplied by P installations carry out it is anti-
Normalization, completes screening.
2. the wind farm power prediction screening sample method of dual confidential interval is based on as claimed in claim 1,
It is characterized in that：In the step (1), initialization sample number of days selects the integral multiple of 15 days or a week.
3. the wind farm power prediction screening sample method of dual confidential interval is based on as claimed in claim 2,
It is characterized in that：Can initialization sample number of days be 2 to 12 all.
4. the wind farm power prediction screening sample method of dual confidential interval is based on as claimed in claim 1,
It is characterized in that：In the step (3), the upper limit function of the weight confidential interval of initialization first:Ymax=kmax*x
And lower limit function:Ymin=kmin*x, as the bound of the first weight confidential interval of screening sample, wherein
Ymin=kmin*x is the first heavy lower limit of confidence interval function；Ymax=kmax*x is the first heavy confidential interval upper limit
Function；If the sample number fallen in the first weight confidential interval<Total sample number * sieveing coeffecient a1, increases sample
Number of days, increasing every time after number of days 2 carries out sample collection, then is screened；If fallen in the first heavy confidential interval
In sample number >=total sample number * sieveing coeffecient a1, then first again screening finish；Sieveing coeffecient a1 typically exists
Between 0.6-0.9.
5. the wind farm power prediction screening sample method of dual confidential interval is based on as claimed in claim 1,
It is characterized in that：In the step (4)：
When carrying out the second weight confidential interval screening, the upper limit function of the weight confidential interval of initialization second：Fmax and
Lower limit function：Fmin, using the two functions as the bound of the second of screening sample the weight confidential interval, is carried out
Next step screening sample；Fmax is the second heavy confidential interval upper limit function, and fmin is under the second weight confidential interval
Limit function, initializes afterwards dynamic adjustment number of times t=0；If dynamic adjustment number of times t>Tmax, tmax are
State adjusts number of times maximum, increases sample number of days, and to increase carry out screening sample after number of days 2 every time；If dynamic
Adjustment number of times t≤tmax, judges whether the sample number fallen in the second weight confidential interval is more than or equal to total sample number
* sieveing coeffecient a2, if it is, the screening of the second weight confidential interval is completed；If it is not, dynamic adjustment the
Double confidential interval upper limit function coefficient k max=kmax+ △ kmax, kmax be upper limit function coefficient, △ kmax
For the second heavy confidential interval upper limit function coefficient amendment step-length, upper limit function parameter cmax=cmax+ △ is adjusted
Cmax, cmax are upper limit function parameter, and △ cmax are the second heavy confidential interval upper limit function parameters revision step-length；
The second heavy lower limit of confidence interval function coefficients kmin=kmin- △ kmin are adjusted, kmin is the coefficient of lower limit function,
△ kmin are the second heavy lower limit of confidence interval function coefficients amendment step-length, adjust lower limit function parameter
Cmin=cmin- △ cmin, the parameter of cmin lower limit functions, △ cmin are the second heavy lower limit of confidence interval function
Parameters revision step-length, after often adjusting once, dynamic adjustment number of times t=t+1, then the second heavy screening sample is carried out,
Until sample number >=total sample number * sieveing coeffecient the a2 fallen in the second weight confidential interval, then complete the second replacement
Screening sample in letter interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510729241.4A CN106650191B (en) | 2015-10-31 | 2015-10-31 | Wind farm power prediction screening sample method based on dual confidence interval |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510729241.4A CN106650191B (en) | 2015-10-31 | 2015-10-31 | Wind farm power prediction screening sample method based on dual confidence interval |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106650191A true CN106650191A (en) | 2017-05-10 |
| CN106650191B CN106650191B (en) | 2018-11-13 |
Family
ID=58810461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510729241.4A Active CN106650191B (en) | 2015-10-31 | 2015-10-31 | Wind farm power prediction screening sample method based on dual confidence interval |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106650191B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184344A (en) * | 2011-06-17 | 2011-09-14 | 上海电机学院 | Method and device for determining confidence probability of power prediction result of wind power station |
| CN103296701A (en) * | 2013-05-09 | 2013-09-11 | 国家电网公司 | Active power control method in wind power plant |
| JP2013253805A (en) * | 2012-06-05 | 2013-12-19 | Fuji Electric Co Ltd | Information processing device, and control method and program for the same |
-
2015
- 2015-10-31 CN CN201510729241.4A patent/CN106650191B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184344A (en) * | 2011-06-17 | 2011-09-14 | 上海电机学院 | Method and device for determining confidence probability of power prediction result of wind power station |
| JP2013253805A (en) * | 2012-06-05 | 2013-12-19 | Fuji Electric Co Ltd | Information processing device, and control method and program for the same |
| CN103296701A (en) * | 2013-05-09 | 2013-09-11 | 国家电网公司 | Active power control method in wind power plant |
Non-Patent Citations (2)
| Title |
|---|
| BRENO MENEZES ET AL.: "Creating Confidence Intervals for Reservoir Computing’s Wind Power Forecast Use of Maximum Likelihood Method and the Distribution-based Method", 《COGNITIVE 2014 : THE SIXTH INTERNATIONAL CONFERENCE ON ADVANCED COGNITIVE TECHNOLOGIES AND APPLICATIONS》 * |
| 王焱 等: "基于OS-ELM和Bootstrap方法的超短期风电功率预测", 《电力系统自动化》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106650191B (en) | 2018-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104915747B (en) | A kind of the power generation performance appraisal procedure and equipment of generating set | |
| US8874276B2 (en) | Event-based control system for wind turbine generators | |
| CN109685257A (en) | A kind of photovoltaic power generation power prediction method based on Support vector regression | |
| CN105825351A (en) | Post evaluation method and risk management and control method of construction cost of power transmission project | |
| CN106251242B (en) | Wind power output interval combination prediction method | |
| CN110443447A (en) | A kind of method and system learning adjustment electric power system tide based on deeply | |
| CN112330050A (en) | Power system load prediction method considering multiple features based on double-layer XGboost | |
| Huang et al. | Analysis of the grain loss in harvest based on logistic regression | |
| CN105204438B (en) | A kind of processing quality control method towards cylinder cap part | |
| CN103750552A (en) | Intelligent sampling method and application of method in cigarette quality control | |
| CN109873428A (en) | A kind of more method for controlling section power and system towards bulk power grid | |
| CN108898249A (en) | A kind of electric network fault prediction technique | |
| CN108009695A (en) | A kind of methods of risk assessment for taking into account index related active distribution network operation | |
| CN116707035A (en) | Active power control method depending on low wind speed dynamic programming | |
| CN112613684B (en) | Special differentiation operation and maintenance method based on distribution network fault prediction | |
| CN106650191A (en) | Wind power plant power prediction sample screening method based on double confidence intervals | |
| CN112686160B (en) | Forest fire spreading prediction method and system based on double-spectrum video image | |
| CN112199805B (en) | Power transmission line hidden danger identification model evaluation method and device | |
| CN110456356B (en) | Data assimilation-oriented weather radar radial speed quality control method | |
| CN116651306B (en) | Intelligent coking coal proportioning system | |
| CN109190845A (en) | A kind of two stages dynamic optimization short-term wind power forecast method | |
| CN106066436B (en) | Consider the operation of power networks state identification method of cascading trip | |
| CN106326982B (en) | A kind of more meteorological wind speed fusion methods optimized based on neural network and pattern search | |
| CN106719284A (en) | A kind of sea-farming wisdom weather forecast service system | |
| CN109978289B (en) | Electric power conversion electric quantity method for safety check before monthly market transaction |
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 |