CN107092983A - Transmission pressure ice covering thickness Forecasting Methodology and device - Google Patents
Transmission pressure ice covering thickness Forecasting Methodology and device Download PDFInfo
- Publication number
- CN107092983A CN107092983A CN201710234538.2A CN201710234538A CN107092983A CN 107092983 A CN107092983 A CN 107092983A CN 201710234538 A CN201710234538 A CN 201710234538A CN 107092983 A CN107092983 A CN 107092983A
- Authority
- CN
- China
- Prior art keywords
- ice
- thickness
- mrow
- ice thickness
- standard
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The invention provides a kind of transmission pressure ice covering thickness Forecasting Methodology and device, methods described is included:Ice thickness radius and the icing radius containing wire are obtained, according to Ice thickness radius and the icing radius calculation containing wire obtains the standard ice thickness of the first Ice;Mesoscale numerical weather forecast meteorological element data are obtained, the standard ice thickness for obtaining the second Ice is calculated according to mesoscale numerical weather forecast meteorological element data;According to the standard ice thickness of the first Ice and the standard ice thickness of the second Ice, calculate and obtain ice thickness coefficient;The Weather Elements of predetermined classification and quantity are obtained according to mesoscale numerical weather forecast meteorological element data;Ice thickness coefficient and Weather Elements are brought into SVM machine learning models and are fitted, fitting function model is obtained;Bring the mesoscale numerical weather forecast meteorological element data corresponding to testing data into fitting function model, obtain prediction ice thickness coefficient and prediction Ice thickness information.
Description
Technical field
The present invention relates to power grid security field, espespecially a kind of transmission pressure ice covering thickness Forecasting Methodology and device.
Background technology
Harm of the icing to power network, triggers reason to divide five classes according to it:(1) line passing load.Under cold sleety weather,
Icing constantly increases on wire, causes the quality and volume of transmission pressure constantly to increase, and makes conducting wire sag increase, over the ground spacing
Reduce, when accumulating to a certain extent, it is possible to occur flashover fault.Meanwhile, conducting wire sag and volume increase, in wind-force effect
Under, it is possible to cause two wires or wire to be collided with ground, occur the accident that wire is even blown in short circuit tripping operation, burn.When covering
Ice quality further increases, more than wire, metal, insulator and tower bar mechanical strength when, wire may be made from aluminium hydraulic pressed connecting pipe
It is interior to extract out, or the fracture of outer layer aluminium stock, steel core extraction.And icing quality exceed shaft tower nominal load when, shaft tower column foot may be caused
Sink, tilt or burst.Shaft tower fractures or even collapsed.(2) the uneven icing of adjacent shelves or the same period does not deice.Tension force can be produced
Official post wire is slided in wire clamp, and the online clamp mouth part complete rupture of wire external layer aluminium stock, steel core are twitched when serious, wire clamp opposite side
Aluminium stock by crowded near wire clamp.(3) ice insulator is dodged.Ice sudden strain of a muscle is a kind of special shape of pollution flashover, the feelings of serious icing
Under condition, there is ice slush bridge joint in a large amount of umbrella shapes of insulator, make insulator dielectric intensity decreases, reveal Distance Shortened.In deicing processes,
The surface moisture film of ice body or ice crystal can dissolve the electrolyte in filth quickly, improve the conductance of ice-melt water or ice face moisture film
Rate, the distortion for causing insulator chain voltage's distribiuting and monolithic insulator surface voltage to be distributed, so as to reduce -- icing insulator string
Flashover voltage.(4) Galloping of Overhead Transmission Line damages power equipment.Wind-force effect is lower to occur low frequency (usual 0.1~3Hz) significantly
The vibrations of (amplitude is 5~300 times of diameter of wire) are waved.During conductor galloping, shaft tower, wire, gold utensil and part will be damaged,
Cause Frequent trip even power outage.(5) substation equipment icing density.In transformer station, many outdoor high-voltage isolating switch
Guillotine type structure is employed, this structure is under the conditions of high and cold icy jelly, or even can not normally divide and greatly interfere with power network
System is normally run.
At the beginning of 2008, low temperature sleet and snow ice weather covering south China, Central China, East China cause Guizhou, Hunan, extensively
East, Yunnan, Guangxi and Jiangxi etc. save transmission line of electricity large area, stopped transport for a long time, cause nationwide power network stoppage in transit power circuit
36740, totally 2018, stoppage in transit transformer station, 110~500kV circuits, which have 8381 base shaft towers, topples over and damages.Totally 170, the whole nation
The situation of power failure occurs for county (city).The Guizhou most area of south electric network power supply area, northern Guangxi area, Guangdong Guangdong
Backlands area and Yunnan Northeastern Yunnan facility are by heavy damage.Current ice damage causes huge to national economy and people's lives
Loss, only the direct economic loss of south electric network is just up to more than 150 hundred million yuan, based on this, how to provide a kind of accurately and effectively icing
Forecasting Methodology, a problem as urgent need to resolve in the industry.The technology of current icing forecast is mainly by meteorological element and icing
Model is set up in observation directly training.This method heavy dependence icing observes the quality and quantity of data.Herein in conjunction with mesoscale
Numerical weather prediction model and machine learning algorithm, forecast that Ice is thick indirectly by forecasting nondimensional ice thickness coefficient
Degree.
The content of the invention
It is unified into present invention aims at the error for reducing observation data quality problem introducing there is provided one kind to standard ice thickness
Forecast help to compare the transmission pressure ice covering thickness Forecasting Methodology and device of different regions ice thickness situation.
For up to above-mentioned purpose, transmission pressure ice covering thickness Forecasting Methodology provided by the present invention is specifically included:Obtain electric wire
Ice covering thickness radius and the icing radius containing wire, according to the Ice thickness radius and the icing radius containing wire
Calculate the standard ice thickness for obtaining the first Ice;Mesoscale numerical weather forecast meteorological element data are obtained, in described
Yardstick numerical weather forecast meteorological element data calculate the standard ice thickness for obtaining the second Ice;Covered according to first electric wire
The standard ice thickness of the standard ice thickness of ice and second Ice, calculates and obtains ice thickness coefficient;According to the mesoscale numerical value
Weather forecast meteorological element data obtain the Weather Elements of predetermined classification and quantity;By the ice thickness coefficient and the Weather Elements
Bring into SVM machine learning models i.e. SVMs and be fitted, obtain fitting function model;By corresponding to testing data
Mesoscale numerical weather forecast meteorological element data bring the fitting function model into, prediction ice thickness coefficient are obtained, according to described
Predict that ice thickness coefficient obtains prediction Ice thickness information.
In above-mentioned transmission pressure ice covering thickness Forecasting Methodology, it is preferred that according to the Ice thickness radius and institute
The standard ice thickness for stating the first Ice of acquisition of the icing radius calculation containing wire is included:According to being obtained following normalized form
The standard ice thickness of first Ice;
In above-mentioned formula:robsFor the standard ice thickness of the first Ice;R is Ice thickness radius;ρ is icing
Density;R is the icing radius comprising wire;K represents icing form factor, is 0.8 for glaze, rime, the loose mixture of misty rain
~0.9, snow slush is 0.9~0.95, and small icing k values limit choosing, the big top limit choosing of icing k values on the lower.
In above-mentioned transmission pressure ice covering thickness Forecasting Methodology, it is preferred that according to the mesoscale numerical weather forecast gas
As the standard ice thickness that factor data calculates the second Ice of acquisition is included:Second electric wire is obtained according to following empirical equation
The standard ice thickness of icing;
In above-mentioned formula:rsmFor the standard ice thickness of two Ices;ρiFor iced insulator;I is corresponding with observation each
The individual time;ρ0For the density of water;P is precipitation;V is wind speed;W is Liquid water content.
In above-mentioned transmission pressure ice covering thickness Forecasting Methodology, it is preferred that according to the standard ice of first Ice
The standard ice thickness of thick and described second Ice, calculates acquisition ice thickness coefficient and includes:Obtained according to following ice thickness coefficient formula
The ice thickness coefficient;
In above-mentioned formula:robsFor the standard ice thickness of the first Ice;rsmFor the standard ice thickness of two Ices;T is
Training data, i is the training data corresponding time;For the training data at i moment.
In above-mentioned transmission pressure ice covering thickness Forecasting Methodology, it is preferred that predicted according to the prediction ice thickness coefficient
Ice thickness information is included:Obtained according to the ice thickness coefficient formula, the empirical equation and the prediction ice thickness coefficient
Predict Ice thickness information.
In above-mentioned transmission pressure ice covering thickness Forecasting Methodology, it is preferred that according to the mesoscale numerical weather forecast gas
As the Weather Elements that factor data obtains predetermined classification and quantity are included:According to the mesoscale numerical weather forecast meteorological element
Data obtain dew-point temperature, temperature, four Weather Elements corresponding to four classification each division of day and night of precipitation and sleet percentage.
In above-mentioned transmission pressure ice covering thickness Forecasting Methodology, it is preferred that by the ice thickness coefficient and the Weather Elements
Bring into be fitted in SVM machine learning models and include:Will to the ice thickness coefficient and the weather by Gaussian kernel function
Element is fitted.
In above-mentioned transmission pressure ice covering thickness Forecasting Methodology, it is preferred that by Gaussian kernel function to the ice thickness system
Number is fitted with the Weather Elements to be included:According to below equation by Gaussian kernel function to the ice thickness coefficient with it is described
Weather Elements are fitted;
In above formula:X represents to observe the vector of data, xpSupporting vector is represented, σ represents variance.
The present invention also provides a kind of transmission pressure ice covering thickness prediction meanss, and described device calculates mould comprising standard ice thickness
Block, ice thickness coefficients statistics module, Weather Elements acquisition module, study module and prediction module;The standard ice thickness computing module
For obtaining Ice thickness radius and icing radius containing wire, according to Ice thickness radius and described containing leading
The icing radius calculation of line obtains the standard ice thickness of the first Ice;And obtain mesoscale numerical weather forecast meteorological element
Data, the standard ice thickness for obtaining the second Ice is calculated according to the mesoscale numerical weather forecast meteorological element data;Institute
Stating ice thickness coefficients statistics module is used for the standard ice thickness and the standard of second Ice according to first Ice
Ice thickness, calculates and obtains ice thickness coefficient;The Weather Elements acquisition module is used for meteorological according to the mesoscale numerical weather forecast
Factor data obtains the Weather Elements of predetermined classification and quantity;The study module is used for the ice thickness coefficient and the weather
Key element is brought into SVM machine learning models and is fitted, and obtains fitting function model;The prediction module is used for testing data
Corresponding mesoscale numerical weather forecast meteorological element data bring the fitting function model into, obtain prediction ice thickness coefficient,
Prediction Ice thickness information is obtained according to the prediction ice thickness coefficient.
In above-mentioned transmission pressure ice covering thickness prediction meanss, it is preferred that the standard ice thickness computing module includes first
Ice computing unit and the second Ice computing unit;The first Ice computing unit covers for obtaining electric wire
Ice thickness radius and the icing radius containing wire, according to the Ice thickness radius and the icing radiuscope containing wire
Calculate the standard ice thickness for obtaining the first Ice;The second Ice computing unit is pre- for obtaining mesoscale Numerical Weather
Meteorological element data are reported, the mark for obtaining the second Ice is calculated according to the mesoscale numerical weather forecast meteorological element data
Quasi- ice thickness.
Transmission pressure ice covering thickness Forecasting Methodology provided by the present invention and device combination mesoscale numerical weather forecast mould
Formula and machine learning algorithm, forecast Ice thickness, according to dimensionless number indirectly by forecasting nondimensional ice thickness coefficient
Utilization when can reduce observation data quality problem introduce error advantage, be unified into standard ice thickness, effectively forecast ratio
Compared with different regions ice thickness situation.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, not
Constitute limitation of the invention.In the accompanying drawings:
Fig. 1 is the schematic flow sheet of transmission pressure ice covering thickness Forecasting Methodology provided by the present invention;
Fig. 2 is the structural representation of transmission pressure ice covering thickness prediction meanss provided by the present invention.
Embodiment
For the purpose, technical scheme and advantage of the embodiment of the present invention are more clearly understood, with reference to embodiment and attached
Figure, is described in further details to the present invention.Here, the schematic description and description of the present invention is used to explain the present invention,
But it is not as a limitation of the invention.
It is main by below scheme in transmission pressure ice covering thickness Forecasting Methodology principle provided by the present invention:First, obtain
Ice thickness data, standard ice thickness data are converted into by Ice thickness data;Then, it is pre- with mesoscale Numerical Weather
The weather of pattern simulation storm yardstick is reported, the forecast result of mesoscale numerical weather forecast pattern is obtained, by forecast result generation
Enter Ice thickness empirical model and obtain standard ice thickness data;Again, determine ice thickness coefficient, it is comprehensive by observation data conversion into
Standard ice thickness data, calculate by mesoscale numerical weather forecast pattern simulation and empirical equation obtained standard ice thickness data and
Come;Forecast target using ice thickness coefficient as machine learning;Finally, according to chi in the dynamics of icing and physics principle selection
The Weather Elements of numerical weather forecast pattern simulation are spent, these key elements are regard as the characterization factor of machine learning, ice thickness coefficient work
For the target of machine learning, substitute into machine learning model, carry out Ice thickness prediction model training;By constantly debugging
The parameter of Ice thickness prediction model obtains optimal models scheme and carries out Ice thickness prediction.
According to above-mentioned principle, it refer to shown in Fig. 1, transmission pressure ice covering thickness Forecasting Methodology provided by the present invention is specific
Comprising:S101 obtains Ice thickness radius and the icing radius containing wire, according to the Ice thickness radius and institute
State the standard ice thickness that the icing radius calculation containing wire obtains the first Ice;S102 obtains mesoscale numerical weather forecast gas
As factor data, the standard ice for obtaining the second Ice is calculated according to the mesoscale numerical weather forecast meteorological element data
It is thick;S103 is calculated according to the standard ice thickness of first Ice and the standard ice thickness of second Ice and is obtained ice
Thick coefficient;The weather that S104 obtains predetermined classification and quantity according to the mesoscale numerical weather forecast meteorological element data will
Element;The ice thickness coefficient is brought into SVM machine learning models and is fitted by S105 with the Weather Elements, obtains fitting function
Model;S106 brings the mesoscale numerical weather forecast meteorological element data corresponding to testing data into the fitting function mould
Type, obtains prediction ice thickness coefficient, and prediction Ice thickness information is obtained according to the prediction ice thickness coefficient.
For each flow and step of the above-mentioned transmission pressure ice covering thickness Forecasting Methodology of clearer explanation, below with specific real
Example is described further to it:
In above-mentioned steps S101, obtained according to the Ice thickness radius and the icing radius calculation containing wire
The standard ice thickness for obtaining the first Ice is included:Ice thickness radius data are obtained from power network microclimate scope,
With wire radius data;The standard ice thickness of first Ice is obtained by following normalized form;
In above-mentioned formula:Wherein, robsFor standard ice thickness, unit mm.R is Ice thickness radius.ρ is that icing is close
Degree, g/cm3, R is the icing radius (wire radius adds icing radius) comprising wire, and k represents icing form factor, for rain
The loose mixture of rime, rime, misty rain is 0.8~0.9, and snow slush is 0.9~0.95, and small icing k values limit choosing on the lower, and big icing k values are leaned on
The upper limit is selected;So it will be observed that ice thickness all change into density for 0.9g/cm3Standard ice thickness, facilitate numerical computations and compare.
In above-mentioned steps S102, calculated according to the mesoscale numerical weather forecast meteorological element data and obtain the second electricity
The standard ice thickness of line icing is included:Mesoscale numerical weather forecast meteorological element data are obtained, according to the icing region observed
With region, time and the physical parameter of set of time mesoscale numerical weather forecast pattern, resolution ratio is designed to observation data institute
The yardstick of corresponding stormy weather, with each stormy Power evelopment process of accurate simulation, makes mesoscale numerical weather forecast
The forecast result of pattern is closer actual;The analog result of mesoscale numerical weather forecast pattern is included by half an hour precipitation, wind
Speed, Liquid water content, dew-point temperature, temperature, precipitation, sleet percentage;Taken out from obtained WRF results by half an hour drop
Water, wind speed and Liquid water content data, and substitute into following empirical equation and acquire second electric wire corresponding to each moment
The standard ice thickness of icing;
In above-mentioned formula:rsmFor the standard ice thickness of two Ices;ρiFor iced insulator;I is corresponding with observation each
The individual time;ρ0For the density of water;P is precipitation;V is wind speed;W is Liquid water content;The temporal resolution meter of wherein each variable
The calculation cycle can be alternatively other times for half an hour, and the present invention is not limited herein.
In real work, above-mentioned weather forecast data come from Study of Meso Scale Weather Forecast Mode WRF (Weather Research
And Forecasting), it is developed based on U.S. environment center (NCEP) and American National Center for Atmospheric Research (NCAR)
Mesoscale NWP;It by exploitation and upgrading for many years, can run on parallel computing platform, can simulate
Several meters of air motion processes to thousands of km yardsticks;It is at present with one of widest weather forecast pattern;In operation
During yardstick Forecast Mode, it is necessary to design simulation region, simulated time, need to provide Parameterization Scheme;Wherein Parameterization Scheme is again
The parameter of physical parameter, including boundary layer processes, microphysical processes, land surface emissivity etc. is made to select;Due to different simulation areas
Atmospheric conditions, geographical feature, weather characteristics etc. are all different, and the Parameterization Scheme of selection also can be different;Two kinds of choosings are only provided below
The method of Parameterization Scheme is selected for illustrating:1st, set according to artificial experience, it is special by the history air in analysis mode region
Climate characteristic of seeking peace provides empirical parameter scheme;2nd, by simulating many kinds of parameters scheme comparison of weather history process, screen
Go out optimal case.Above two scheme is only to readily appreciate, when actual use can feelings select suitable scheme to be used,
Invention is not limited herein.
In above-mentioned steps S103, according to the standard ice thickness of first Ice and the mark of second Ice
Quasi- ice thickness, calculates acquisition ice thickness coefficient and includes:The standard ice thickness data r that data reduction is obtained will be observed by power network microclimateoBsWith
The standard ice thickness data r obtained by mesoscale numerical weather forecast pattern and empirical equation of correspondence timesmSubstitute into following ice thickness
Coefficient formula obtains the ice thickness coefficient;
In above-mentioned formula:Y is ice thickness coefficient;robsFor the standard ice thickness of the first Ice;rsmFor two Ices
Standard ice thickness;T is training data, and i is the training data corresponding time;For the training data at i moment.
In above-mentioned steps S104, mainly according to the dynamics and physics principle of icing, in above-mentioned yardstick Numerical Weather
Selection and the meteorological element of icing formation strong correlation in the result of Forecast Mode, be respectively:Dew-point temperature, temperature, precipitation, jelly
Rain percentage, four Weather Elements of correspondence when each time, this four Weather Elements as machine learning characterization factor;Thus,
In a preferred embodiment of the invention, according to the mesoscale numerical weather forecast meteorological element data obtain predetermined classification and
The Weather Elements of quantity are included:Dew-point temperature, temperature, drop are obtained according to the mesoscale numerical weather forecast meteorological element data
Four Weather Elements corresponding to four classification each division of day and night of water and sleet percentage.Correlation of the aforementioned four key element with icing
Property is most close, and other key elements are all much the derivative key elements of this four elements, and selection has little significance;Certainly the present invention is not herein
Restriction element particular number and classification, can select to add according to actual needs or delete in real work.
In above-mentioned steps S105, electric wire ice thickness coefficient obtained above and meteorological element are mainly substituted into machine learning mould
In type, characterization factor was the observation standard ice thickness in four meteorological elements and upper a period of time time, and forecast target is an ice thickness coefficient, is indulged
It is classified as the observation time that corresponding icing observes data;By repeatedly training and parameter testing, optimal fitting function mould is obtained
Type, icing forecast is carried out with the model, and input data is four meteorological element fields that mesoscale numerical weather forecast pattern is exported,
Output data is prediction ice thickness coefficient;Wherein the ice thickness coefficient and the Weather Elements are brought into SVM machine learning models
It is fitted and includes:The ice thickness coefficient and the Weather Elements are intended by Gaussian kernel function according to below equation
Close;
In above formula:X represents to observe the vector of data, xpSupporting vector is represented, σ represents variance.
Fitting function model is obtained by above-described embodiment, and according to corresponding to the fitting function model and testing data
Mesoscale numerical weather forecast meteorological element data are obtained after prediction ice thickness coefficient, in addition it is also necessary at the prediction ice thickness coefficient
Reason is calculated, and is that this can bring the prediction ice thickness coefficient into above-mentioned ice thickness empirical equation (1) and/or ice thickness coefficient formula respectively
(2) in, the experience ice thickness and ice thickness coefficient formula (2) obtained with this by ice thickness empirical equation (1) is calculated and obtains ice covering thickness,
Obtain prediction ice covering thickness.
To improve the accuracy of the fitting function model, in real work, when there is new ice covering thickness to observe data,
Previous moment can be observed to data and current weather Element field and be put into the model simultaneously, model debugging is constantly carried out and optimize the mould
Shape parameter, the enhancing forecast degree of accuracy;The present invention does not just do excessive limitation herein, and staff can compare tune according to actual conditions
Examination.
It refer to shown in Fig. 2, the present invention also provides a kind of transmission pressure ice covering thickness prediction meanss, described device includes mark
Quasi- ice thickness computing module 201, ice thickness coefficients statistics module 202, Weather Elements acquisition module 203, study module 204 and prediction mould
Block 205;The standard ice thickness computing module 201 is used to obtain Ice thickness radius and the icing radius containing wire, according to
The Ice thickness radius and the icing radius calculation containing wire obtain the standard ice thickness of the first Ice;And
Mesoscale numerical weather forecast meteorological element data are obtained, are calculated according to the mesoscale numerical weather forecast meteorological element data
Obtain the standard ice thickness of the second Ice;The ice thickness coefficients statistics module 202 is used for according to first Ice
The standard ice thickness of standard ice thickness and second Ice, calculates and obtains ice thickness coefficient;The Weather Elements acquisition module 203
Weather Elements for obtaining predetermined classification and quantity according to the mesoscale numerical weather forecast meteorological element data;It is described to learn
Practising module 204 is used to the Weather Elements bring the ice thickness coefficient in SVM machine learning models into be fitted, and is intended
Close function model;The prediction module 205 is used for the mesoscale numerical weather forecast meteorological element number corresponding to testing data
According to the fitting function model is brought into, prediction ice thickness coefficient is obtained, prediction Ice is obtained according to the prediction ice thickness coefficient
Thickness information.
In the above-described embodiments, the standard ice thickness computing module includes the first Ice computing unit and the second electric wire
Icing computing unit;The first Ice computing unit is used to obtain Ice thickness radius and the icing half containing wire
Footpath, the standard ice of the first Ice is obtained according to the Ice thickness radius and the icing radius calculation containing wire
It is thick;The second Ice computing unit is used to obtain mesoscale numerical weather forecast meteorological element data, in described
Yardstick numerical weather forecast meteorological element data calculate the standard ice thickness for obtaining the second Ice.
Particular embodiments described above, has been carried out further in detail to the purpose of the present invention, technical scheme and beneficial effect
Describe in detail it is bright, should be understood that the foregoing is only the present invention specific embodiment, the guarantor being not intended to limit the present invention
Scope is protected, within the spirit and principles of the invention, any modification, equivalent substitution and improvements done etc. should be included in this
Within the protection domain of invention.
Claims (10)
1. a kind of transmission pressure ice covering thickness Forecasting Methodology, it is characterised in that methods described is included:
Ice thickness radius and the icing radius containing wire are obtained, according to Ice thickness radius and described containing leading
The icing radius calculation of line obtains the standard ice thickness of the first Ice;
Mesoscale numerical weather forecast meteorological element data are obtained, according to the mesoscale numerical weather forecast meteorological element data
Calculate the standard ice thickness for obtaining the second Ice;
According to the standard ice thickness of first Ice and the standard ice thickness of second Ice, calculate and obtain ice thickness system
Number;
The Weather Elements of predetermined classification and quantity are obtained according to the mesoscale numerical weather forecast meteorological element data;
The ice thickness coefficient is brought into SVM machine learning models with the Weather Elements and is fitted, fitting function mould is obtained
Type;
Bring the mesoscale numerical weather forecast meteorological element data corresponding to testing data into the fitting function model, obtain
Ice thickness coefficient is predicted, prediction Ice thickness information is obtained according to the prediction ice thickness coefficient.
2. transmission pressure ice covering thickness Forecasting Methodology according to claim 1, it is characterised in that according to the Ice
The standard ice thickness that thickness radius and the icing radius calculation containing wire obtain the first Ice is included:According to following standard
Formula obtains the standard ice thickness of first Ice;
<mrow>
<msub>
<mi>r</mi>
<mrow>
<mi>o</mi>
<mi>b</mi>
<mi>s</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mi>&rho;</mi>
<mrow>
<mn>0.9</mn>
<mrow>
<mo>(</mo>
<mo>(</mo>
<mrow>
<mi>k</mi>
<mo>*</mo>
<msup>
<mi>R</mi>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mi>r</mi>
<mn>2</mn>
</msup>
</mrow>
<mo>)</mo>
<mo>+</mo>
<msup>
<mi>r</mi>
<mn>2</mn>
</msup>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>-</mo>
<mi>r</mi>
<mo>;</mo>
</mrow>
In above-mentioned formula:robsFor the standard ice thickness of the first Ice;R is Ice thickness radius;ρ is iced insulator;
R is the icing radius comprising wire;K represents icing form factor.
3. transmission pressure ice covering thickness Forecasting Methodology according to claim 2, it is characterised in that according to the mesoscale number
The standard ice thickness that value weather forecast meteorological element data calculate the second Ice of acquisition is included:Obtained according to following empirical equation
The standard ice thickness of second Ice;
<mrow>
<msub>
<mi>r</mi>
<mrow>
<mi>s</mi>
<mi>m</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<msub>
<mi>&rho;</mi>
<mi>i</mi>
</msub>
<mi>&pi;</mi>
</mrow>
</mfrac>
<msup>
<mrow>
<mo>&lsqb;</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>P&rho;</mi>
<mn>0</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<mn>3.6</mn>
<mi>V</mi>
<mi>W</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>&rsqb;</mo>
</mrow>
<mrow>
<mn>1</mn>
<mo>/</mo>
<mn>2</mn>
</mrow>
</msup>
<mo>;</mo>
</mrow>
In above-mentioned formula:rsmFor the standard ice thickness of two Ices;ρiFor iced insulator;I for it is corresponding with observation each when
Between;ρ0For the density of water;P is precipitation;V is wind speed;W is Liquid water content.
4. transmission pressure ice covering thickness Forecasting Methodology according to claim 3, it is characterised in that according to first electric wire
The standard ice thickness of the standard ice thickness of icing and second Ice, calculates acquisition ice thickness coefficient and includes:According to following ice thickness
Coefficient formula obtains the ice thickness coefficient;
<mrow>
<msubsup>
<mi>y</mi>
<mi>i</mi>
<mi>t</mi>
</msubsup>
<mo>=</mo>
<mfrac>
<msubsup>
<mi>r</mi>
<mrow>
<mi>s</mi>
<mi>m</mi>
</mrow>
<mi>i</mi>
</msubsup>
<msubsup>
<mi>r</mi>
<mrow>
<mi>o</mi>
<mi>b</mi>
<mi>s</mi>
</mrow>
<mi>i</mi>
</msubsup>
</mfrac>
<mo>;</mo>
</mrow>
In above-mentioned formula:Y is ice thickness coefficient;robsFor the standard ice thickness of the first Ice;rsmFor the standard of two Ices
Ice thickness;T is training data, and i is the training data corresponding time;For the training data at i moment.
5. transmission pressure ice covering thickness Forecasting Methodology according to claim 4, it is characterised in that according to the prediction ice thickness
Coefficient obtains prediction Ice thickness information and included:According to the ice thickness coefficient formula, the empirical equation and the prediction
Ice thickness coefficient obtains prediction Ice thickness information.
6. transmission pressure ice covering thickness Forecasting Methodology according to claim 1, it is characterised in that according to the mesoscale number
Value weather forecast meteorological element data obtain predetermined classification and the Weather Elements of quantity are included:According to the mesoscale Numerical Weather
Forecast that meteorological element data obtain dew-point temperature, temperature, corresponding to four classification each division of day and night of precipitation and sleet percentage
Four Weather Elements.
7. transmission pressure ice covering thickness Forecasting Methodology according to claim 1, it is characterised in that by the ice thickness coefficient with
The Weather Elements are brought into be fitted in SVM machine learning models and included:By Gaussian kernel function to the ice thickness coefficient
It is fitted with the Weather Elements.
8. transmission pressure ice covering thickness Forecasting Methodology according to claim 7, it is characterised in that pass through Gaussian kernel function
The ice thickness coefficient is fitted with the Weather Elements and included:According to below equation by Gaussian kernel function to the ice
Thick coefficient is fitted with the Weather Elements;
<mrow>
<mi>k</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<msup>
<mi>x</mi>
<mi>p</mi>
</msup>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<msup>
<mrow>
<mo>|</mo>
<mrow>
<mi>x</mi>
<mo>-</mo>
<msup>
<mi>x</mi>
<mi>p</mi>
</msup>
</mrow>
<mo>|</mo>
</mrow>
<mn>2</mn>
</msup>
<mrow>
<mn>2</mn>
<msup>
<mi>&sigma;</mi>
<mn>2</mn>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mo>;</mo>
</mrow>
In above formula:X represents to observe the vector of data, xpSupporting vector is represented, σ represents variance.
9. a kind of transmission pressure ice covering thickness prediction meanss, it is characterised in that described device includes standard ice thickness computing module, ice
Thick coefficients statistics module, Weather Elements acquisition module, study module and prediction module;
The standard ice thickness computing module is used to obtain Ice thickness radius and the icing radius containing wire, according to the electricity
Line ice covering thickness radius and the icing radius calculation containing wire obtain the standard ice thickness of the first Ice;And in obtaining
Yardstick numerical weather forecast meteorological element data, calculate according to the mesoscale numerical weather forecast meteorological element data and obtain the
The standard ice thickness of two Ices;
The ice thickness coefficients statistics module is used for standard ice thickness and second Ice according to first Ice
Standard ice thickness, calculate obtain ice thickness coefficient;
The Weather Elements acquisition module is used to obtain predetermined class according to the mesoscale numerical weather forecast meteorological element data
The Weather Elements of other and quantity;
The study module is used to the Weather Elements bring the ice thickness coefficient in SVM machine learning models into be intended
Close, obtain fitting function model;
The prediction module is described for the mesoscale numerical weather forecast meteorological element data corresponding to testing data to be brought into
Fitting function model, obtains prediction ice thickness coefficient, and prediction Ice thickness information is obtained according to the prediction ice thickness coefficient.
10. transmission pressure ice covering thickness prediction meanss according to claim 9, it is characterised in that the standard ice thickness meter
Calculate module and include the first Ice computing unit and the second Ice computing unit;
The first Ice computing unit is used to obtain Ice thickness radius and the icing radius containing wire, according to institute
State Ice thickness radius and the icing radius calculation containing wire obtains the standard ice thickness of the first Ice;
The second Ice computing unit is used to obtain mesoscale numerical weather forecast meteorological element data, in described
Yardstick numerical weather forecast meteorological element data calculate the standard ice thickness for obtaining the second Ice.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710234538.2A CN107092983A (en) | 2017-04-11 | 2017-04-11 | Transmission pressure ice covering thickness Forecasting Methodology and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710234538.2A CN107092983A (en) | 2017-04-11 | 2017-04-11 | Transmission pressure ice covering thickness Forecasting Methodology and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107092983A true CN107092983A (en) | 2017-08-25 |
Family
ID=59637632
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710234538.2A Pending CN107092983A (en) | 2017-04-11 | 2017-04-11 | Transmission pressure ice covering thickness Forecasting Methodology and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107092983A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109492823A (en) * | 2018-11-26 | 2019-03-19 | 南京大学 | A kind of prediction technique of pair of electric power line ice-covering thickness |
CN109543295A (en) * | 2018-11-21 | 2019-03-29 | 国网青海省电力公司 | The meteorological element data processing method and device of numerical weather forecast |
CN110853089A (en) * | 2019-09-30 | 2020-02-28 | 安徽南瑞继远电网技术有限公司 | Multi-factor-based simulation wire icing thickness algorithm |
CN111539842A (en) * | 2020-04-08 | 2020-08-14 | 成都思晗科技股份有限公司 | Overhead transmission line icing prediction method based on meteorological and geographical environments |
CN112949920A (en) * | 2021-02-26 | 2021-06-11 | 中国电力工程顾问集团西南电力设计院有限公司 | Regional icing prediction and early warning method based on ice observation representative station data |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102297674A (en) * | 2011-04-27 | 2011-12-28 | 中国电力工程顾问集团西南电力设计院 | Method for utilizing visibility model to predict icing thickness of transmission line |
CN103453867A (en) * | 2013-09-09 | 2013-12-18 | 国家电网公司 | Electric transmission line ice coating thickness monitoring method |
CN104462660A (en) * | 2014-11-14 | 2015-03-25 | 贵州电力试验研究院 | Drawing method for winter icing thickness distribution of field electric transmission line |
CN104578061A (en) * | 2015-01-26 | 2015-04-29 | 国家电网公司 | Method for pre-estimating overhead power transmission line wire designed ice thickness |
CN104699889A (en) * | 2014-12-26 | 2015-06-10 | 国家电网公司 | Drawing method and device for ice region distribution diagram |
US9097649B2 (en) * | 2013-02-20 | 2015-08-04 | Halliburton Energy Services, Inc. | Optical design techniques for providing favorable fabrication characteristics |
CN105631115A (en) * | 2015-12-25 | 2016-06-01 | 国网浙江省电力公司丽水供电公司 | Refined covering ice model establishment method for power transmission line |
CN105184407B (en) * | 2015-09-11 | 2017-03-01 | 国家电网公司 | Powerline ice-covering forecast of growth method based on Atmospheric Numerical Model |
-
2017
- 2017-04-11 CN CN201710234538.2A patent/CN107092983A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102297674A (en) * | 2011-04-27 | 2011-12-28 | 中国电力工程顾问集团西南电力设计院 | Method for utilizing visibility model to predict icing thickness of transmission line |
US9097649B2 (en) * | 2013-02-20 | 2015-08-04 | Halliburton Energy Services, Inc. | Optical design techniques for providing favorable fabrication characteristics |
CN103453867A (en) * | 2013-09-09 | 2013-12-18 | 国家电网公司 | Electric transmission line ice coating thickness monitoring method |
CN104462660A (en) * | 2014-11-14 | 2015-03-25 | 贵州电力试验研究院 | Drawing method for winter icing thickness distribution of field electric transmission line |
CN104699889A (en) * | 2014-12-26 | 2015-06-10 | 国家电网公司 | Drawing method and device for ice region distribution diagram |
CN104578061A (en) * | 2015-01-26 | 2015-04-29 | 国家电网公司 | Method for pre-estimating overhead power transmission line wire designed ice thickness |
CN105184407B (en) * | 2015-09-11 | 2017-03-01 | 国家电网公司 | Powerline ice-covering forecast of growth method based on Atmospheric Numerical Model |
CN105631115A (en) * | 2015-12-25 | 2016-06-01 | 国网浙江省电力公司丽水供电公司 | Refined covering ice model establishment method for power transmission line |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109543295A (en) * | 2018-11-21 | 2019-03-29 | 国网青海省电力公司 | The meteorological element data processing method and device of numerical weather forecast |
CN109543295B (en) * | 2018-11-21 | 2023-08-25 | 国网青海省电力公司 | Meteorological element data processing method and device for numerical weather forecast |
CN109492823A (en) * | 2018-11-26 | 2019-03-19 | 南京大学 | A kind of prediction technique of pair of electric power line ice-covering thickness |
CN109492823B (en) * | 2018-11-26 | 2021-04-30 | 南京大学 | Method for predicting icing thickness of power transmission line |
CN110853089A (en) * | 2019-09-30 | 2020-02-28 | 安徽南瑞继远电网技术有限公司 | Multi-factor-based simulation wire icing thickness algorithm |
CN111539842A (en) * | 2020-04-08 | 2020-08-14 | 成都思晗科技股份有限公司 | Overhead transmission line icing prediction method based on meteorological and geographical environments |
CN111539842B (en) * | 2020-04-08 | 2023-05-23 | 成都思晗科技股份有限公司 | Overhead power transmission line icing prediction method based on meteorological and geographic environments |
CN112949920A (en) * | 2021-02-26 | 2021-06-11 | 中国电力工程顾问集团西南电力设计院有限公司 | Regional icing prediction and early warning method based on ice observation representative station data |
CN112949920B (en) * | 2021-02-26 | 2023-04-07 | 中国电力工程顾问集团西南电力设计院有限公司 | Regional icing prediction and early warning method based on ice observation representative station data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107092983A (en) | Transmission pressure ice covering thickness Forecasting Methodology and device | |
Bonelli et al. | Wet snow hazard for power lines: a forecast and alert system applied in Italy | |
CN102938021B (en) | A kind of powerline ice-covering load quantitative is estimated and Forecasting Methodology | |
CN104063750A (en) | Method for predicting influence of disasters to power system based on improved AHP-anti-entropy weight | |
CN103678865A (en) | Fault probability online evaluation method of power transmission line faults caused by freezing rain | |
CN105279612A (en) | Poisson distribution-based power transmission line tripping risk assessment method | |
CN112001070B (en) | Modeling method for outage probability of power transmission line affected by external environment | |
CN102928751B (en) | Traveling wave principle-based high-tension overhead line insulator online monitoring method | |
CN105278004B (en) | A kind of weather condition analysis method of grid power transmission circuit section | |
CN106570780A (en) | Power transmission line dancing warning method based on gray relation theory | |
CN102968554A (en) | Tower pole icing disaster risk prediction method based on safety margin | |
CN102903018A (en) | Air speed early warning information processing method of transmission line based on geographic information system (GIS) | |
CN106408859B (en) | Power transmission line column wire body system ice-coating pre-warning system and method | |
Lacavalla et al. | Forecasting and monitoring wet-snow sleeve on overhead power lines in Italy | |
CN103940397A (en) | Online monitoring method of overhead line equivalent icing thickness | |
CN107092982A (en) | A kind of method for forecasting ice coating of power grid and device | |
CN117009731A (en) | Power failure early warning method based on meteorological factors | |
CN105158821A (en) | Meteorological early warning method of power transmission line icing gallop disasters | |
CN109884420A (en) | A kind of simulation experiment method of overhead transmission line birds droppings flashover fault | |
Xie et al. | Extensions of power system early-warning defense schemes by integrating wide area meteorological information | |
Lu et al. | An analysis of the reliability of a new dataset of transmission line icing thickness in southern China | |
Freddo et al. | Wet–snow accretion on conductors: the Italian approach to reduce risks on existing OHL | |
Huang et al. | Data mining evaluation of reliability of overhead line iced tension tensor | |
Amicarelli et al. | Impact of snow storms on distribution grids: e-distribuzione and RSE experimental stations | |
Nygaard et al. | Development of ice load maps for structural design |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170825 |
|
RJ01 | Rejection of invention patent application after publication |