CN109738970A - The method, apparatus and storage medium for realizing Lightning Warning are excavated based on lightning data - Google Patents
The method, apparatus and storage medium for realizing Lightning Warning are excavated based on lightning data Download PDFInfo
- Publication number
- CN109738970A CN109738970A CN201811494090.9A CN201811494090A CN109738970A CN 109738970 A CN109738970 A CN 109738970A CN 201811494090 A CN201811494090 A CN 201811494090A CN 109738970 A CN109738970 A CN 109738970A
- Authority
- CN
- China
- Prior art keywords
- lightning
- data
- thunder
- thunderstorm
- warning
- 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
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses a kind of method, apparatus and storage medium that realization Lightning Warning is excavated based on lightning data, method includes the following steps: S10, analysis atmospheric electric field intensity and radar return start Lightning Warning process when meeting preset condition；S20, acquisition satellite cloud picture data and lighting location data, in conjunction with satellite cloud picture and lighting location data and carry out differentiation amendment, then carry out clustering to lightning data, obtain thunderstorm group mobile speed and direction；S30, distribution is rolled into a ball according to currently available thunderstorm, the mobile speed and direction of thunderstorm group is found out using linear regression method, position and quantity occur for prediction subsequent time thunder and lightning；S40, by region division it is different grids, the Lightning Warning of appropriate level is carried out according to the radar site of prediction and quantity.Lightning Warning method of the invention has pre-warning time short, the high advantage of accuracy rate, reduces the whole false alarm rate of thunder and lightning detection net, promotes its Lightning Warning accuracy rate, reduce Lightning Warning space error.
Description
Technical field
The invention belongs to Lightning Warning technical fields, and in particular to a kind of Lightning Warning method, apparatus and storage medium.
Background technique
Thunder and lightning is with the physics such as its powerful electric current, hot high temperature, fierce shock wave and strong electromagnetic radiation effect
It answers, so that it is generated huge destruction in moment, to cause property and casualties.In recent years, China gradually increases spy
The construction dynamics of ultra-high-tension power transmission line implements the strong smart grid developed using extra-high voltage grid as core, electric network coordination at different levels
Strategy, with the raising of voltage class, transmission line of electricity is also bigger by the risk of thunderbolt, cannot if line failure
Restore electricity demand in time, and huge loss can be brought to national economy.
The current still not yet complete explanation mechanism of the mankind of atmospheric electrical phenomena, a kind of natural phenomena for grasping rule, with function
Rate is big, quantity is more, randomness is strong, is unevenly distributed, the features such as occurrence and development process is fast.The mankind are not stopping to visit always for a long time
The various technological means of Suo Caiyong realize that measurement and monitoring to thunder and lightning, including Doppler weather radar, meteorological satellite, very high frequency(VHF) are done
Relate to method, very low frequency direction time difference combined method, High-speed Photography Technology etc..Worldwide application at present is more widely adopted
With the lightning monitoring system of very low frequency direction time difference combined method, can to coverage area each time thunder and lightning twinkle SM cease it is real-time
Monitoring.China has put into a large amount of resource in lightning protection, and with the foundation of Lightning business platform and perfect, data are abundant
Shared, lightning data library increasingly will accumulate and expand.Lightning data saves in the database in a variety of forms, and for these
The use of data rests on always the stage of access and statistics, and traditional data query and analysis can not effectively excavate thunder and lightning prison
The database of survey.
Past can not unite to the observation of thunder and lightning mainly using estimating to the important physicals parameter such as intensity of lightning, steepness
Meter analysis, the frequent degree that thunder and lightning occurs also can only be for statistical analysis according to thunderstorm day.Nowadays electric system lighting location
Increase increasingly with early warning system information monitoring ability, the data information of large amount of complex is collected system database, is formed huge
Information considerably beyond the processing capacity of staff, accurately these failures cannot be judged, analyzed.Contemporary Information
Society has stepped into big data period, and big data, which rapidly develops, grows up and obtained a large amount of utilization.Big data analysis is thunder
Hiding mode and rule therein are found out in electric data mining, can be provided corresponding strategy for workers such as maintenance, maintenance and be helped.
Lightning data based on big data, which excavates, realizes Lightning Warning, and early warning result will create high value for lightning protection mitigation, can be
Dispatcher handles event and provides synergism, can effectively play the when consumption for reducing accident treatment, and prevent accident from further expanding
The effect opened.Currently, the method for the Lightning Warning that many units are carried out be the atmospheric electric field data detected by ground electric field instrument,
The Lighting Position Data of Lighting position machine monitoring, the related data of radar detection and the data obtained from data center, weather bureau
Information intuitively reflects, but its early warning effect is not ideal enough.
Summary of the invention
Goal of the invention: in view of the deficiencies of the prior art, the present invention proposes that a kind of excavate based on lightning data realizes that thunder and lightning is pre-
Alert method, apparatus and storage medium, can quickly, accurately to in region in short-term thunder and lightning carry out early warning.
Technical solution: according to the first aspect of the invention, a kind of excavated based on lightning data is provided and realizes Lightning Warning
Method, comprising the following steps:
S10, analysis atmospheric electric field intensity and radar return start Lightning Warning process when meeting preset condition；
S20, acquisition satellite cloud picture data and lighting location data, in conjunction with satellite cloud picture and lighting location data and are sentenced
It does not correct, then clustering is carried out to lightning data, obtain thunderstorm group mobile speed and direction；
S30, distribution is rolled into a ball according to currently available thunderstorm, the mobile speed and side of thunderstorm group is found out using linear regression method
To position and quantity occur for prediction subsequent time thunder and lightning；
S40, by region division it is different grids, the thunder and lightning of appropriate level is carried out according to the radar site of prediction and quantity
Early warning.
Preferably, it in the step S10, dashes forward when the atmospheric electric field of region reaches 4kV/m and 40dBz echo high degree
When breaking and maintaining on 0 DEG C of echo top height, prealarming process is initially entered.
It preferably, include: to be carried out smoothly using mean filter method to cloud atlas to the processing of satellite cloud picture in the step S20
Then processing clusters cloud atlas using FCM fuzzy clustering algorithm, then carry out clustering to the RGB channel of cloud atlas, obtains multi-pass
The cluster cloud cluster region of road intersection, the cloud cluster image after finally synthesizing segmentation, then makees outside forecast in short-term to cloud atlas.
It preferably, include: to be collected into using clustering method to lightening detection station to the processing of lighting location data
Site location data, thunder and lightning Wave data, arrival time data are analyzed, by the way that discrete single thunder and lightning is focused into difference
Thunderstorm group reject undesirable thunderstorm group in conjunction with satellite cloud picture thunderstorm cloud cluster region contour.
Preferably, lightning data is clustered using improved k- central point cluster algorithm in the step S20
Analysis, process are as follows: the number for other samples for including within the scope of radius of neighbourhood ε will be specified to be defined as this around a sample point
Sample is divided into high density and two groups of low-density based on the density of sample, selects density from high density group by the density of sample point
Distinctiveness ratio square is determined by calculating the distance in data set between sample point greatly and apart from remote sample point as initial center point
Battle array calculates and chooses high density sample into high density sample set, so that discrete thunder and lightning is automatically separated into different thunderstorm groups,
Same color, closely located point form a thunderstorm group.
Preferably, the step S40 divides region-of-interest with square net, counts each grid forecasting thunder and lightning quantity, will
Meet the grid of setting thunder and lightning quantity as prewarning area, lightening activity is predicted to open up with transmission line of electricity spatial geographical locations
Analysis is flutterred, and early warning intensity grade is divided according to thunder and lightning quantity.
According to the second aspect of the invention, a kind of computer readable storage medium is provided, is stored with computer on the medium
Program can realize above-mentioned method when processor executes the computer program.
According to the third aspect of the invention we, a kind of device for being excavated based on lightning data and realizing Lightning Warning is provided, it is described
Device includes analysis module, data processing module, prediction module and warning module, wherein the analysis module is big for analyzing
Pneumoelectric field intensity and radar return send enabling signal to data processing module, start Lightning when meeting preset condition
Prealarming process；The data processing module combination satellite cloud picture data and lighting location data simultaneously carry out differentiation amendment, then to thunder
Electric data carry out clustering, obtain thunderstorm group mobile speed and direction；The prediction module is according to currently available thunderstorm
Using linear regression method prediction subsequent time thunder and lightning position and quantity occur for group's distribution；Region division is by the warning module
Different grids carries out the Lightning Warning of appropriate level according to the radar site of prediction and quantity.
The utility model has the advantages that the present invention uses the big data analysis method such as statistical analysis, data mining, thunder and lightning detection data incorporates
Atmospheric electric field, satellite cloud picture, weather radar data for communication are transported using data mining technology prediction thunderstorm group movement tendency, thunder cloud
Dynamic path, realizes Lightning Warning.Pre-warning time of the present invention is short, and accuracy rate is high, reduces the whole false alarm rate of thunder and lightning detection net, mentions
Lightning Warning accuracy rate is risen, Lightning Warning space error is reduced.
Detailed description of the invention
Fig. 1 is the Lightning Warning method flow diagram according to the embodiment of the present invention；
Fig. 2 is the improvement k- central point cluster algorithm flow chart according to the embodiment of the present invention；
Fig. 3 is the lightning warning device structural block diagram according to the embodiment of the present invention.
Specific embodiment
Technical solution of the present invention is described further with reference to the accompanying drawing.
Referring to Fig.1, based on lightning data excavate realize Lightning Warning method the following steps are included:
Whether S10, analysis atmospheric electric field intensity and radar return, the atmospheric electric field for monitoring region reach predetermined threshold
Whether value, radar 40dBz echo high degree are broken through and are maintained on 0 DEG C of echo top height.
When thundercloud comes temporarily, atmospheric electric field intensity can change, and pass through the electric field pole between monitoring thundercloud and the earth
Property, intensity, development evolvement, using the Lightning Warning method based on atmospheric electric field dynamic adaptive threshold, it can be achieved that thunderstorm send out
Exhibition initial stage shifts to an earlier date 15~30min and issues Lightning Warning.In specific implementation process, set when interest region atmospheric electric field reaches
When originating threshold value of warning (such as 4kV/m) surely, it is believed that be the preliminary Rule of judgment for reaching thunder and lightning generation.
The Lightning Warning method of dynamic adaptive threshold described here, refer to using historical data with actually occur
The process that lighting location data compare and analyze, it is by Lightning Warning parametric statistics calculation procedure first by the model of variation value
It encloses and calculates, then equal difference is divided into 100 value ranges, then chooses inverting Lightning Warning process by different range threshold value
And these values are assessed, the rate of failing to report (1- early warning accuracy rate) and early warning rate of false alarm of Lightning Warning are calculated, and define and comment
Estimating objective function, f (x, y)=μ x+ (1- μ) y, wherein x is rate of failing to report (rate of failing to report=1- accuracy rate), and y is false alert rate, μ ∈ (0,
1) it is balance factor, is the value according to the adjustment of early warning efficiency judgment criteria, with rate of failing to report for main judgment criteria if, otherwise
Using false alert rate as main standard.Corresponding threshold value is exactly optimal Lightning Warning threshold value, which will be updated to history threshold data
Library, so that Lightning Warning procedure extraction uses in real time in the future.
In order to further increase precision of prediction, present invention further contemplates that the prediction of fusion radar echo signal.Weather radar
Spatial resolution is usually 1km, has an ability for differentiating thunder cloud, and radar twice body sweep between time interval only 5-
6min, observation interval is short, can provide for the early-warning and predicting of thunder and lightning intensive enough on the relatively complete, time on space structure
Data.Observation monomer 40dBz echo high changes with time, and P value generation refers to that 40dBz or more echo accounts in this height
The percent by volume of 25dBz or more echo.It is single if 40dBz echo high degree is broken through and maintained on 0 DEG C of echo top height
Body has very big probability that lightning will occur.
(1) if 40dBz echo high breaches -10 DEG C of echo top heights, judge to sweep in the radar body for meeting the condition
First lightning will occur after time within the about 15min time.
(2) if 40dBz echo high fails to break through -10 DEG C of echo top heights.If P value break through and be able to maintain that 5% with
The first lightning of monomer will then occur in about 15min after the radar body flyback time for meeting the condition for the preceding paragraph time.
(3) if above-mentioned condition is not able to satisfy, and monomer 40dBz echo high is able to maintain that always in 0 DEG C of layer knot degree
More than height, it may be considered that lightning will not occur for monomer in a short time.
When meeting above-mentioned atmospheric electric field and radar signal condition, start Lightning prealarming process.
S20, acquisition satellite cloud picture data and lighting location data, in conjunction with satellite cloud picture and lighting location data and are sentenced
It does not correct, then clustering is carried out to lightning data, obtain thunderstorm group mobile speed and direction.
Since satellite sounding range is big, radar detection precision is high, cloud atlas can see that cloud top is distributed, and lighting location figure can be seen
The vertical distribution of cloud base and cloud layer, therefore cooperated using these data, learn from other's strong points to offset one's weaknesses, it can be to the analysis of medium and small scale weather
More comprehensive information is provided with forecast.The present invention is obtained by carrying out mean filter, fuzzy clustering processing to satellite cloud picture image
The cloud cluster territorial classification of RGB channel intersection obtains lightning distribution, then again by carrying out clustering to lighting location data
Discrete cloud cluster and thunder and lightning are divided into different thunderstorm groups by clustering.Specifically, comprising the following steps:
S21, data prediction
Choose a certain range of a large amount of lightening activities, thunder and lightning Wave data, GPS time data, site location data, signal
The data such as characteristic, thunder and lightning coordinate data, thunder and lightning time data, intensity of lightning data and database format, GIS format,
The data such as the formats such as picture JPG, PNG, document format carry out nondimensionalization processing to data first, and image data is 0-255
UNIT type data, need to normalize, be transformed between 0-1, and the numerical value in database is directed to different types of data, and selection is corresponding
Dimensionless method.Purpose is that all data can be used in computer programming.And differentiation amendment is carried out to data, it rejects
Undesirable setting value.
S22, satellite cloud picture data processing
Cloud atlas is smoothed first with mean filter method, it is then poly- to cloud atlas using FCM fuzzy clustering algorithm
Class finally carries out clustering to the RGB channel of cloud atlas, obtains the cluster cloud cluster region of multichannel intersection, finally synthesizes point
Cloud cluster image after cutting.Then outside forecast in short-term is made to cloud atlas.
It handles for cloud cluster area image in satellite cloud picture, cloud atlas is smoothed first with mean filter method,
Taken mean value smoothing formula are as follows:
Wherein (m, n) indicates the pixel coordinate of pixel, and k determines (m, n) Size of Neighborhood, with the child window of k × k size
Interior median replaces the value f (m, n) of (m, n)；Then cloud atlas is clustered using fuzzy clustering algorithm, constructs objective function
Make J (U, c1, cc) value reaches minimum value, wherein uijCodomain is 0~1, uijIndicate degree of membership, λj(j=
1,2, n) be formula (2) n constraint formula Lagrange multiplier, ciFor the cluster centre of blur level i, dij=| | ci-
xj| | the Euclidean distance between ith cluster center and j-th of data point；M ∈ [1, ∞) it is a Weighted Index；To cloud
The RGB channel of figure carries out clustering, is that the cluster numbers of cloud atlas are set as v class according to the signature analysis of cloud atlas, passes through cloud atlas
Matrix A={ ai| i=1,2,3 } search maximum membership degree matrix value Max (Udata), obtain the cluster cloud cluster area of multichannel intersection
Domain.Identification condition by satellite deep convection index and the bright temperature difference of infrared multichannel as infrared cloud image thunderstorm cloud cluster, to region
Contour line is smoothed, to realize the identification to satellite cloud picture thunderstorm cloud cluster.
S23, lightning location system data processing
Site location data, thunder and lightning Wave data, arrival time data that lightening detection station is collected into etc. utilize data
Digging technology, using correlation rule, analysis of the methods of classifying, birds of the same feather flock together, by the way that discrete single thunder and lightning is focused into different thunders
Undesirable thunderstorm group, the displacement of discovery thunderstorm group and hair are rejected in conjunction with satellite cloud picture thunderstorm cloud cluster region contour by sudden and violent group
Exhibition changes over time the rule having.
S24, clustering
Clustering is carried out to lightning data using the improvement k- central point cluster algorithm based on density.Pass through cluster
After analysis obtains different time sections thunder cloud thunderbolt point, each cluster cloud cluster mass center of each period is calculated, calculation formula is shown in
According to t1Discrete thunder and lightning is automatically separated into different thunderstorm groups by thunder and lightning spatial position in moment selection area, identical
Color, closely located point form a thunderstorm group, and so on solve different time tnThe coordinate sequence of same thunderstorm group mass center
The point of column, same color indicates t1-tnThe motion profile of its thunderstorm represented group mass center in period.
Fig. 2 shows the processes of the improvement k- central point cluster algorithm of the invention used, and principle is a sample
The number for other samples for including within the scope of radius of neighbourhood ε is specified to be defined as the density of the sample point around point, based on sample
Sample can be divided into high density and two groups of low-density by density, select density larger from high density group and apart from farther away sample
Point is used as initial center point, by calculating the distance in data set between sample point, determines dissimilarity matrix, calculates and choose high density
Discrete thunder and lightning can be automatically separated into different thunderstorm groups, identical face at high density sample set, by the method by sample
Color, closely located point form a thunderstorm group.
S30, position and quantity are occurred according to currently available thunderstorm group forecast of distribution thunder and lightning.
Thunderstorm group is found out using linear regression method based on the data that acquisition station monitors are digitized in Shock Web system
Mobile speed and direction, obtains t using extrapolationn+1The thunderstorm cumularsharolith at moment set with thunder and lightning quantity, using linear regression analysis one
The practical mass center of period thunder cloud can acquire equation of linear regression, outside according to the situation of change of mass center transit square degree in the period
It pushes away to obtain tn+1The mobile speed of the thunderstorm mass center at moment and direction.To realize according to the history thunder and lightning before current time
Monitoring data subsequent time thunder and lightning occur the prediction of position and quantity.
Predict tn+1It moment and actually occurs position and has a deviation, carry out real time correction.The tn+1 moment and actually occur position
Have deviation, prediction result relative error is more than 15%, and the replacement tn+1 moment predict coordinate, and returned data is handled, not under the influence of one
The position that the thunderstorm group mass center at moment occurs.
S40, by region division be different grids, carry out the Lightning Warning of appropriate level.
Region-of-interest is divided with square net, counts each grid forecasting thunder and lightning quantity, setting thunder and lightning quantity will be met
Grid carries out topological analysis with transmission line of electricity spatial geographical locations as prewarning area, by lightening activity prediction, and according to thunder and lightning
Quantity divides early warning intensity grade.Lightning Warning intensity grade is as shown in the table:
When interest region atmospheric electric field, which reaches setting, terminates threshold value of warning, Lightning prealarming process terminates.
The embodiment of the present invention also provides a kind of computer readable storage medium, is stored with computer program on the medium,
Processor can realize method described above when executing the computer program.The computer-readable medium may be considered that
It is tangible and non-transitory.The non-limiting example of non-transitory visible computer readable medium includes non-volatile memories
Device circuit (such as flash memory circuit, Erasable Programmable Read Only Memory EPROM circuit or mask ROM circuit), volatibility are deposited
Memory circuit (such as static random access memorizer circuit or dynamic RAM circuit), magnetic storage medium (such as
Analog or digital tape or hard disk drive) and optical storage media (such as CD, DVD or Blu-ray Disc) etc..Computer program packet
Include the processor-executable instruction being stored at least one non-transitory visible computer readable medium.Computer program may be used also
With include or dependent on storage data.Computer program may include interacted with the hardware of special purpose computer it is basic input/
Output system (BIOS), one or more operating systems, is used the device driver interacted with the particular device of special purpose computer
Family application program, background service, background application etc..
Referring to Fig. 3, the lightning warning device excavated based on lightning data includes analysis module, data processing module, prediction
Module and warning module, wherein analysis module is for analyzing atmospheric electric field intensity and radar return, when meeting preset condition,
For example, when region atmospheric electric field reach 4kV/m and 40dBz echo high degree break through and maintain 0 DEG C of echo top height it
When upper, enabling signal was sent to data processing module, starts Lightning prealarming process；Data processing module combination satellite cloud picture
Data and radar data simultaneously carry out differentiation amendment, then carry out clustering to lightning data, obtain the mobile speed of thunderstorm group and
Direction；Using linear regression method prediction subsequent time thunder and lightning position occurs for prediction module according to currently available thunderstorm group distribution
And quantity；Region division is different grids by warning module, carries out appropriate level according to the radar site of prediction and quantity
Lightning Warning.
In the specific implementation, the data processing module may include pretreatment unit, satellite cloud picture processing unit, Lei Dian
Location data processing unit, taxon, wherein the pretreatment unit carries out at nondimensionalization the mass data of selection
Reason, and differentiation amendment is carried out to data, reject undesirable setting value；The satellite cloud picture processing unit is filtered using mean value
Wave method is smoothed cloud atlas, is then clustered using FCM fuzzy clustering algorithm to cloud atlas, then to the RGB channel of cloud atlas into
Row clustering obtains the cluster cloud cluster region of multichannel intersection, the cloud cluster image after finally synthesizing segmentation, then to cloud atlas
Make outside forecast in short-term；Site location data that the lighting location data processing unit is collected into lightening detection station, thunder and lightning
Wave data, arrival time data are analyzed, by the way that discrete single thunder and lightning to be focused into different thunderstorm groups, in conjunction with satellite
Cloud atlas thunderstorm cloud cluster region contour, rejects undesirable thunderstorm group；The taxon is poly- by improved k- central point
Discrete cloud cluster and thunder and lightning are divided into different thunderstorm groups by alanysis algorithm, obtain thunderstorm group mobile speed and direction.It is described
Cloud Picture specific method and k- central point cluster algorithm are identical as during the above method, and details are not described herein.
Claims (9)
1. a kind of excavate the method for realizing Lightning Warning based on lightning data, which comprises the following steps:
S10, analysis atmospheric electric field intensity and radar return start Lightning Warning process when meeting preset condition；
S20, acquisition satellite cloud picture data and lighting location data in conjunction with satellite cloud picture and lighting location data and differentiate and are repaired
Just, then to lightning data clustering is carried out, obtains thunderstorm group mobile speed and direction；
S30, distribution is rolled into a ball according to currently available thunderstorm, the mobile speed and direction of thunderstorm group is found out using linear regression method,
Predict that position and quantity occur for subsequent time thunder and lightning；
It S40, is different grids by region division, the thunder and lightning for carrying out appropriate level according to the radar site of prediction and quantity is pre-
It is alert.
2. according to claim 1 excavate the method for realizing Lightning Warning based on lightning data, it is characterised in that: the step
In rapid S10, breaks through when the atmospheric electric field of region reaches 4kV/m and 40dBz echo high degree and maintain 0 DEG C of echo top height
On when, initially enter prealarming process.
3. according to claim 1 excavate the method for realizing Lightning Warning based on lightning data, it is characterised in that: the step
It is as follows to the processing of satellite cloud picture in rapid S20: cloud atlas is smoothed using mean filter method, it is then fuzzy using FCM
Clustering algorithm clusters cloud atlas, then carries out clustering to the RGB channel of cloud atlas, obtains the cluster cloud cluster area of multichannel intersection
Domain, the cloud cluster image after finally synthesizing segmentation, then makees outside forecast in short-term to cloud atlas.
4. according to claim 1 excavate the method for realizing Lightning Warning based on lightning data, it is characterised in that: the step
It include: the site location being collected into using clustering method to lightening detection station to the processing of lighting location data in rapid S20
Data, thunder and lightning Wave data, arrival time data are analyzed, by the way that discrete single thunder and lightning is focused into different thunderstorms
Group, in conjunction with satellite cloud picture thunderstorm cloud cluster region contour, rejects undesirable thunderstorm group.
5. according to claim 1 excavate the method for realizing Lightning Warning based on lightning data, it is characterised in that: the step
Clustering, process are as follows: by a sample are carried out to lightning data using improved k- central point cluster algorithm in rapid S20
It specifies the number for other samples for including within the scope of radius of neighbourhood ε to be defined as the density of the sample point around this point, is based on sample
Density sample is divided into high density and two groups of low-density, select density big from high density group and apart from remote sample point as
Initial center point determines dissimilarity matrix, calculates and choose high density sample point by calculating the distance in data set between sample point
High density sample set is formed, so that discrete thunder and lightning is automatically separated into different thunderstorm groups, same color, closely located point group
At a thunderstorm group.
6. according to claim 1 excavate the method for realizing Lightning Warning based on lightning data, it is characterised in that: the step
Rapid S40 divides region-of-interest with square net, counts each grid forecasting thunder and lightning quantity, will meet the grid of setting thunder and lightning quantity
As prewarning area, lightening activity prediction is subjected to topological analysis with transmission line of electricity spatial geographical locations, and according to thunder and lightning quantity
Divide early warning intensity grade.
7. it is a kind of based on lightning data excavate realize Lightning Warning device, which is characterized in that described device include analysis module,
Data processing module, prediction module and warning module, wherein the analysis module is returned for analyzing atmospheric electric field intensity and radar
Wave sends enabling signal to data processing module, starts Lightning prealarming process when meeting preset condition；The data
Processing module combination satellite cloud picture data and lighting location data simultaneously carry out differentiation amendment, then carry out cluster point to lightning data
Analysis obtains thunderstorm group mobile speed and direction；The prediction module is returned according to currently available thunderstorm group distribution using linear
Return method prediction subsequent time thunder and lightning that position and quantity occurs；Region division is different grids by the warning module, according to
The radar site and quantity of prediction carry out the Lightning Warning of appropriate level.
8. according to claim 7 excavate the device for realizing Lightning Warning based on lightning data, which is characterized in that the number
It include pretreatment unit, satellite cloud picture processing unit, thunder point location data processing unit, taxon according to processing module, wherein
The pretreatment unit carries out nondimensionalization processing to the mass data of selection, and carries out differentiation amendment to data, and rejecting is not inconsistent
Close desired setting value；The satellite cloud picture processing unit is smoothed cloud atlas using mean filter method, then uses
FCM fuzzy clustering algorithm clusters cloud atlas, then carries out clustering to the RGB channel of cloud atlas, obtains the cluster of multichannel intersection
Cloud cluster region, the cloud cluster image after finally synthesizing segmentation, then makees outside forecast in short-term to cloud atlas；The lighting location data
Site location data that processing unit is collected into lightening detection station, thunder and lightning Wave data, arrival time data are analyzed, and are led to
It crosses and discrete single thunder and lightning is focused into different thunderstorm groups, in conjunction with satellite cloud picture thunderstorm cloud cluster region contour, rejecting is not met
It is required that thunderstorm group；Discrete cloud cluster and thunder and lightning are divided by the taxon by improved k- central point cluster algorithm
Different thunderstorm groups obtains thunderstorm group mobile speed and direction.
9. a kind of computer readable storage medium, computer program is stored on the medium, which is characterized in that is executed in processor
Claim 1~6 any method can be realized when the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811494090.9A CN109738970B (en) | 2018-12-07 | 2018-12-07 | Method, device and storage medium for realizing lightning early warning based on lightning data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811494090.9A CN109738970B (en) | 2018-12-07 | 2018-12-07 | Method, device and storage medium for realizing lightning early warning based on lightning data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109738970A true CN109738970A (en) | 2019-05-10 |
| CN109738970B CN109738970B (en) | 2021-02-02 |
Family
ID=66359282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811494090.9A Active CN109738970B (en) | 2018-12-07 | 2018-12-07 | Method, device and storage medium for realizing lightning early warning based on lightning data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109738970B (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110806509A (en) * | 2019-11-29 | 2020-02-18 | 广州供电局有限公司 | Lightning activity spatial feature detection method and device |
| CN110879828A (en) * | 2019-11-20 | 2020-03-13 | 上海眼控科技股份有限公司 | Processing method and device of radar echo map, computer equipment and storage medium |
| CN110907708A (en) * | 2019-12-09 | 2020-03-24 | 国网江苏省电力有限公司电力科学研究院 | Lightning early warning method |
| CN111583586A (en) * | 2020-04-03 | 2020-08-25 | 武汉天宏防雷检测中心发展有限公司 | Lightning monitoring and early warning method and device |
| CN111666903A (en) * | 2020-06-10 | 2020-09-15 | 中国电子科技集团公司第二十八研究所 | Method for identifying thunderstorm cloud cluster in satellite cloud picture |
| CN111987691A (en) * | 2020-08-06 | 2020-11-24 | 珠海格力电器股份有限公司 | Equipment power-off protection method based on thunderstorm early warning, storage medium and electronic equipment |
| CN112017090A (en) * | 2020-08-14 | 2020-12-01 | 广东电网有限责任公司广州供电局 | Lightning activity intensity characterization method and device, computer equipment and storage medium |
| CN112578232A (en) * | 2019-09-30 | 2021-03-30 | 北京金风慧能技术有限公司 | Lightning early warning method and lightning early warning device of wind generating set |
| CN112630597A (en) * | 2020-12-25 | 2021-04-09 | 广东电网有限责任公司 | Fault determination method, device, equipment and storage medium |
| CN112668790A (en) * | 2020-12-30 | 2021-04-16 | 南京信息工程大学 | Thunder and lightning prediction method based on space-time sequence clustering algorithm and LSTM neural network |
| CN113011098A (en) * | 2021-03-26 | 2021-06-22 | 云南电网有限责任公司电力科学研究院 | Power transmission corridor area lightning activity rule analysis display model and system |
| CN113204903A (en) * | 2021-04-29 | 2021-08-03 | 国网电力科学研究院武汉南瑞有限责任公司 | Method for predicting thunder and lightning |
| CN113203896A (en) * | 2021-05-19 | 2021-08-03 | 贵州省气象灾害防御技术中心 | Threshold method inspection and improvement algorithm for lightning early warning of single-station atmospheric electric field instrument |
| CN113219259A (en) * | 2021-04-26 | 2021-08-06 | 吉林省气候中心 | Lightning early warning method, device, equipment and storage medium |
| CN113406726A (en) * | 2021-06-01 | 2021-09-17 | 中国石油大学(北京) | Oil and gas station lightning accident early warning method, device, equipment and storage medium |
| CN113466570A (en) * | 2021-07-26 | 2021-10-01 | 厦门大恒科技有限公司 | Lightning early warning method and lightning early warning device |
| CN113484619A (en) * | 2021-06-08 | 2021-10-08 | 广东电网有限责任公司广州供电局 | Lightning activity spatial feature analysis method |
| CN113985145A (en) * | 2021-09-13 | 2022-01-28 | 广东电网有限责任公司广州供电局 | Thunder and lightning early warning method, early warning device and computer readable storage medium |
| CN114518612A (en) * | 2022-02-14 | 2022-05-20 | 广东省气象公共安全技术支持中心 | Thunderstorm risk early warning method and system and electronic equipment |
| CN114792392A (en) * | 2022-05-18 | 2022-07-26 | 西南交通大学 | Method for simulating lightning precursor development path based on Markov chain |
| CN114994801A (en) * | 2022-08-05 | 2022-09-02 | 中国气象局公共气象服务中心(国家预警信息发布中心) | Lightning monitoring and early warning method and device |
| US20230161073A1 (en) * | 2021-11-25 | 2023-05-25 | Zhejiang Meteorological Observatory | Thunderstorm gale early-warning method, system, equipment, and terminal |
| CN116910491A (en) * | 2023-09-11 | 2023-10-20 | 四川弘和数智集团有限公司 | Lightning monitoring and early warning system and method, electronic equipment and storage medium |
| CN117349692A (en) * | 2023-12-04 | 2024-01-05 | 国网江西省电力有限公司南昌供电分公司 | Distribution line lightning early warning method integrating multiple lightning early warning factors |
| CN117725523A (en) * | 2024-01-31 | 2024-03-19 | 中科技术物理苏州研究院 | Thunderstorm weather early warning method and early warning system based on physical constraint |
| CN117725523B (en) * | 2024-01-31 | 2024-04-12 | 中科技术物理苏州研究院 | Thunderstorm weather early warning method and early warning system based on physical constraint |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000065953A (en) * | 1998-08-20 | 2000-03-03 | Toko Electric Corp | Lightning-forecasting system |
| JP2004061416A (en) * | 2002-07-31 | 2004-02-26 | Kansai Electric Power Co Inc:The | Method and device for predicting generation of winter thunder |
| CN104200281A (en) * | 2014-08-25 | 2014-12-10 | 清华大学 | Method and system for predicting thunder cloud moving path based on lightning location system |
| CN106526708A (en) * | 2016-09-21 | 2017-03-22 | 广东奥博信息产业有限公司 | Intelligent early-warning analysis method for meteorological severe convection weather based on machine learning |
| CN106707371A (en) * | 2016-11-21 | 2017-05-24 | 深圳市气象服务中心 | Lightning monitoring early-warning and alert service system and early warning method thereof |
-
2018
- 2018-12-07 CN CN201811494090.9A patent/CN109738970B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000065953A (en) * | 1998-08-20 | 2000-03-03 | Toko Electric Corp | Lightning-forecasting system |
| JP2004061416A (en) * | 2002-07-31 | 2004-02-26 | Kansai Electric Power Co Inc:The | Method and device for predicting generation of winter thunder |
| CN104200281A (en) * | 2014-08-25 | 2014-12-10 | 清华大学 | Method and system for predicting thunder cloud moving path based on lightning location system |
| CN106526708A (en) * | 2016-09-21 | 2017-03-22 | 广东奥博信息产业有限公司 | Intelligent early-warning analysis method for meteorological severe convection weather based on machine learning |
| CN106707371A (en) * | 2016-11-21 | 2017-05-24 | 深圳市气象服务中心 | Lightning monitoring early-warning and alert service system and early warning method thereof |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112578232A (en) * | 2019-09-30 | 2021-03-30 | 北京金风慧能技术有限公司 | Lightning early warning method and lightning early warning device of wind generating set |
| CN112578232B (en) * | 2019-09-30 | 2023-10-27 | 北京金风慧能技术有限公司 | Lightning early warning method and lightning early warning equipment of wind generating set |
| CN110879828A (en) * | 2019-11-20 | 2020-03-13 | 上海眼控科技股份有限公司 | Processing method and device of radar echo map, computer equipment and storage medium |
| CN110879828B (en) * | 2019-11-20 | 2020-11-24 | 上海眼控科技股份有限公司 | Processing method and device of radar echo map, computer equipment and storage medium |
| CN110806509B (en) * | 2019-11-29 | 2021-12-17 | 广东电网有限责任公司广州供电局 | Lightning activity spatial feature detection method and device |
| CN110806509A (en) * | 2019-11-29 | 2020-02-18 | 广州供电局有限公司 | Lightning activity spatial feature detection method and device |
| CN110907708A (en) * | 2019-12-09 | 2020-03-24 | 国网江苏省电力有限公司电力科学研究院 | Lightning early warning method |
| CN111583586A (en) * | 2020-04-03 | 2020-08-25 | 武汉天宏防雷检测中心发展有限公司 | Lightning monitoring and early warning method and device |
| CN111666903A (en) * | 2020-06-10 | 2020-09-15 | 中国电子科技集团公司第二十八研究所 | Method for identifying thunderstorm cloud cluster in satellite cloud picture |
| CN111666903B (en) * | 2020-06-10 | 2022-10-04 | 中国电子科技集团公司第二十八研究所 | Method for identifying thunderstorm cloud cluster in satellite cloud picture |
| CN111987691A (en) * | 2020-08-06 | 2020-11-24 | 珠海格力电器股份有限公司 | Equipment power-off protection method based on thunderstorm early warning, storage medium and electronic equipment |
| CN111987691B (en) * | 2020-08-06 | 2022-11-22 | 珠海格力电器股份有限公司 | Equipment power-off protection method based on thunderstorm early warning, storage medium and electronic equipment |
| CN112017090A (en) * | 2020-08-14 | 2020-12-01 | 广东电网有限责任公司广州供电局 | Lightning activity intensity characterization method and device, computer equipment and storage medium |
| CN112630597A (en) * | 2020-12-25 | 2021-04-09 | 广东电网有限责任公司 | Fault determination method, device, equipment and storage medium |
| CN112668790A (en) * | 2020-12-30 | 2021-04-16 | 南京信息工程大学 | Thunder and lightning prediction method based on space-time sequence clustering algorithm and LSTM neural network |
| CN112668790B (en) * | 2020-12-30 | 2023-07-25 | 南京信息工程大学 | Lightning prediction method based on space-time sequence clustering algorithm and LSTM neural network |
| CN113011098B (en) * | 2021-03-26 | 2023-09-01 | 云南电网有限责任公司电力科学研究院 | Lightning activity rule analysis display model and system for power transmission corridor area |
| CN113011098A (en) * | 2021-03-26 | 2021-06-22 | 云南电网有限责任公司电力科学研究院 | Power transmission corridor area lightning activity rule analysis display model and system |
| CN113219259A (en) * | 2021-04-26 | 2021-08-06 | 吉林省气候中心 | Lightning early warning method, device, equipment and storage medium |
| CN113204903B (en) * | 2021-04-29 | 2022-04-29 | 国网电力科学研究院武汉南瑞有限责任公司 | Method for predicting thunder and lightning |
| CN113204903A (en) * | 2021-04-29 | 2021-08-03 | 国网电力科学研究院武汉南瑞有限责任公司 | Method for predicting thunder and lightning |
| CN113203896B (en) * | 2021-05-19 | 2023-10-03 | 贵州省气象灾害防御技术中心 | Threshold method inspection and improvement method for lightning early warning by single-station atmospheric electric field instrument |
| CN113203896A (en) * | 2021-05-19 | 2021-08-03 | 贵州省气象灾害防御技术中心 | Threshold method inspection and improvement algorithm for lightning early warning of single-station atmospheric electric field instrument |
| CN113406726A (en) * | 2021-06-01 | 2021-09-17 | 中国石油大学(北京) | Oil and gas station lightning accident early warning method, device, equipment and storage medium |
| CN113484619A (en) * | 2021-06-08 | 2021-10-08 | 广东电网有限责任公司广州供电局 | Lightning activity spatial feature analysis method |
| CN113466570A (en) * | 2021-07-26 | 2021-10-01 | 厦门大恒科技有限公司 | Lightning early warning method and lightning early warning device |
| WO2023005542A1 (en) * | 2021-07-26 | 2023-02-02 | 厦门大恒科技有限公司 | Lightning early warning method and lightning early warning device |
| CN113985145A (en) * | 2021-09-13 | 2022-01-28 | 广东电网有限责任公司广州供电局 | Thunder and lightning early warning method, early warning device and computer readable storage medium |
| US20230161073A1 (en) * | 2021-11-25 | 2023-05-25 | Zhejiang Meteorological Observatory | Thunderstorm gale early-warning method, system, equipment, and terminal |
| US11802992B2 (en) * | 2021-11-25 | 2023-10-31 | Zhejiang Meteorological Observatory | Thunderstorm gale early-warning method, system, equipment, and terminal |
| CN114518612A (en) * | 2022-02-14 | 2022-05-20 | 广东省气象公共安全技术支持中心 | Thunderstorm risk early warning method and system and electronic equipment |
| CN114792392A (en) * | 2022-05-18 | 2022-07-26 | 西南交通大学 | Method for simulating lightning precursor development path based on Markov chain |
| CN114994801B (en) * | 2022-08-05 | 2022-10-25 | 中国气象局公共气象服务中心(国家预警信息发布中心) | Lightning monitoring and early warning method and device |
| CN114994801A (en) * | 2022-08-05 | 2022-09-02 | 中国气象局公共气象服务中心(国家预警信息发布中心) | Lightning monitoring and early warning method and device |
| CN116910491A (en) * | 2023-09-11 | 2023-10-20 | 四川弘和数智集团有限公司 | Lightning monitoring and early warning system and method, electronic equipment and storage medium |
| CN116910491B (en) * | 2023-09-11 | 2024-01-23 | 四川弘和数智集团有限公司 | Lightning monitoring and early warning system and method, electronic equipment and storage medium |
| CN117349692A (en) * | 2023-12-04 | 2024-01-05 | 国网江西省电力有限公司南昌供电分公司 | Distribution line lightning early warning method integrating multiple lightning early warning factors |
| CN117725523A (en) * | 2024-01-31 | 2024-03-19 | 中科技术物理苏州研究院 | Thunderstorm weather early warning method and early warning system based on physical constraint |
| CN117725523B (en) * | 2024-01-31 | 2024-04-12 | 中科技术物理苏州研究院 | Thunderstorm weather early warning method and early warning system based on physical constraint |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109738970B (en) | 2021-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109738970A (en) | The method, apparatus and storage medium for realizing Lightning Warning are excavated based on lightning data | |
| Mwangi et al. | Forecasting droughts in East Africa | |
| CN112070286B (en) | Precipitation forecast and early warning system for complex terrain river basin | |
| CN113762090B (en) | Disaster monitoring and early warning method for ultra-high voltage dense transmission channel | |
| CN107193060B (en) | A kind of multipath Typhoon Storm Surge Over method for quick predicting and system | |
| KR101937940B1 (en) | Method of deciding cpted cctv position by big data | |
| CN110019595A (en) | A kind of integrated method and system of multi-source meteorological data | |
| CN116363601B (en) | Data acquisition and analysis method and system for pollution monitoring equipment | |
| CN113327022B (en) | Lightning protection safety risk management system and method | |
| CN114493052B (en) | Multi-model fusion self-adaptive new energy power prediction method and system | |
| Bao et al. | Lightning performance evaluation of transmission line based on data-driven lightning identification, tracking, and analysis | |
| CN106980874B (en) | A kind of multi-time Scales dimension data fusion method towards distribution big data | |
| CN103942251A (en) | Method and system for inputting high altitude meteorological data into database based on multiple quality control methods | |
| CN114897329A (en) | Power transmission line inspection method, device and system and storage medium | |
| CN110334127A (en) | A kind of distribution network line fault law mining method, system and storage medium | |
| CN112233381A (en) | Debris flow early warning method and system based on mechanism and machine learning coupling | |
| CN115688032A (en) | Power grid risk early warning method and system under typhoon disaster based on multi-source data fusion | |
| CN114664041B (en) | Multi-sensor fusion early warning prediction method based on deep learning | |
| CN113344735B (en) | Disaster prevention and reduction monitoring and early warning system of power grid equipment | |
| CN111222662A (en) | Power grid typhoon flood disaster early warning method and device | |
| CN115457211A (en) | Transformer substation management method and system based on digital twins | |
| CN114661700A (en) | Artificial influence weather operation effect inspection method based on AI | |
| Alves et al. | Lightning Warning Prediction with Multi-source Data | |
| CN117556197B (en) | Typhoon vortex initialization method based on artificial intelligence | |
| CN110070199A (en) | A kind of power grid typhoon disaster method for early warning and system |
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 |