CN107292448A - A kind of power energy microstructure Prediction method of power network typhoon salvaging - Google Patents
A kind of power energy microstructure Prediction method of power network typhoon salvaging Download PDFInfo
- Publication number
- CN107292448A CN107292448A CN201710580793.2A CN201710580793A CN107292448A CN 107292448 A CN107292448 A CN 107292448A CN 201710580793 A CN201710580793 A CN 201710580793A CN 107292448 A CN107292448 A CN 107292448A
- Authority
- CN
- China
- Prior art keywords
- typhoon
- power
- loss late
- salvaging
- model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 239000002245 particle Substances 0.000 claims abstract description 28
- 238000010219 correlation analysis Methods 0.000 claims abstract description 8
- 239000000463 material Substances 0.000 claims description 16
- 230000005611 electricity Effects 0.000 claims description 9
- 230000001419 dependent effect Effects 0.000 claims description 3
- 230000001771 impaired effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000003455 independent Effects 0.000 claims 1
- 230000008439 repair process Effects 0.000 abstract description 13
- 238000011160 research Methods 0.000 abstract description 6
- 238000012706 support-vector machine Methods 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract description 3
- 229910000831 Steel Inorganic materials 0.000 description 7
- 230000006378 damage Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 239000010959 steel Substances 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 238000005303 weighing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 229920000742 Cotton Polymers 0.000 description 1
- 235000018783 Dacrycarpus dacrydioides Nutrition 0.000 description 1
- 244000288671 Dacrycarpus dacrydioides Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 239000000853 adhesive Substances 0.000 description 1
- HSFWRNGVRCDJHI-UHFFFAOYSA-N alpha-acetylene Natural products C#C HSFWRNGVRCDJHI-UHFFFAOYSA-N 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000002320 enamel (paints) Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000004519 grease Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000010902 straw Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
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
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The power energy microstructure Prediction method for the power network typhoon salvaging that the present invention is provided is sought using the grey relational grade Weighted Support Vector model based on particle cluster algorithm to typhoon failure law, and implements prediction to repairing after power network typhoon calamity.Grey correlation analysis is applied in combination with SVMs, then it optimized by particle cluster algorithm, a kind of research method of science can not only be provided for first-aid repair construction power energy microstructure Prediction after power network typhoon calamity, while can also put forward the precision of high force-energy microstructure Prediction.
Description
Technical field
The present invention relates to Electric Power Project Management field, SVMs, grey correlation point are utilized more particularly, to one kind
The method that analysis and particle cluster algorithm carry out power network typhoon salvaging power energy microstructure Prediction.
Background technology
Under the climate change background using global warming as principal character, extreme weather climate damage showed increased, to society
The influence of meeting economic development increasingly sharpens.In Extreme Weather-climate Events, the casualty loss that tropical cyclone is caused is very serious.
Guangdong Province is located at Pacific Ocean west bank, is on the verge of the South Sea, is the major area of Tropical Cyclone Landing China.Annual summer and autumn rainy season Guangdong
Province is all attacked by tropical cyclone, is the province of China's Tropical Cyclone Disaster most serious.Storm wind, typhoon easily make supply line,
Power equipment is damaged, and is caused the broken string and tower, and first-aid repair construction is more difficult of mass-sending property, is seriously threatened power grid security.Mesh
Before, the research both at home and abroad in this field is relatively fewer, and the field also has many problems demands to solve, and in particular how concentrates tune
Spend related personnel and implement repairing.
Power network rushes to repair the important task for bearing fast recovery of power supply, lacks rational tissue during power network is rushed to repair at present
Man-machine unreasonable distribution in prediction, work progress, easily causes the work holdup phenomenon of large area, significantly reduces the work of salvaging
Make efficiency.Based on such a situation, carry out salvaging power energy microstructure Prediction work after power network typhoon calamity, for rationally carrying out typhoon
Work is rushed to repair after calamity has preferable directive function.
The content of the invention
The technology that the present invention lacks rational microstructure Prediction to solve above prior art during power network is rushed to repair lacks
It is sunken that there is provided a kind of power energy microstructure Prediction method of power network typhoon salvaging.
To realize above goal of the invention, the technical scheme of use is:
A kind of power energy microstructure Prediction method of power network typhoon salvaging, comprises the following steps:
S1. grid equipment loss amount regional along each typhoon in sample, and electric power facility total amount are collected, each is tried to achieve
Area power grid equipment loss late along wind;
S2. supporting vector machine model is set up, supporting vector machine model is combined with grey correlation analysis, is calculated using population
Method is optimized to supporting vector machine model with grey correlation analysis, sets up the grey relational grade weighting branch based on particle cluster algorithm
Hold vector machine model;
S3. using two parameters of mileage along grade during Landed Typhoon, regional longitudinal direction as independent variable, regional power equipment
Loss late is dependent variable, and the damage under grade typhoon is logged in all previous difference according to the grid equipment in mileage area along different longitudinal directions
Mistake rate sets up loss late forecast model, and uses the grey relational grade Weighted Support Vector model pair based on particle cluster algorithm
Loss late forecast model is fitted;
S4. the precision of loss late forecast model is verified;
S5. input Landed Typhoon when grade and area longitudinal direction along mileage, obtain the loss late of area power grid equipment,
The total amount of grid equipment based on area calculates the quantity of impaired grid equipment, then carries out manpower, material that repairing need to expend
The calculating that material, auxiliary equipment and repairing are spent, realizes the power energy microstructure Prediction to salvaging.
Compared with prior art, the beneficial effects of the invention are as follows:
The present invention is using the grey relational grade Weighted Support Vector model based on particle cluster algorithm to typhoon failure law
Sought, and prediction is implemented to repairing after power network typhoon calamity.Grey correlation analysis is applied in combination with SVMs, then borrowed
Help particle cluster algorithm to optimize it, a kind of science can not only be provided for first-aid repair construction power energy microstructure Prediction after power network typhoon calamity
Research method, while can also put forward the precision of high force-energy microstructure Prediction.
Brief description of the drawings
Fig. 1:The method of the invention flow chart;
Fig. 2:Characteristic gray degree of association weighted support vector regression machine model realization figure based on PSO;
Fig. 3:The typhoon salvaging unit region repairing artificial work day prognostic chart of common laborer;
Fig. 4:φ steel wire rope prognostic charts below 15 needed for the region repairing of typhoon salvaging unit;
Fig. 5:Electric engineering car machine-team prognostic chart needed for typhoon salvaging unit region.
Embodiment
Accompanying drawing being given for example only property explanation, it is impossible to be interpreted as the limitation to this patent;
Below in conjunction with drawings and examples, the present invention is further elaborated.
Embodiment 1
As shown in figure 1, the Forecasting Methodology that the present invention is provided specifically includes following steps:
S1. collect grid power power transformating and supplying facility loss amount regional along each typhoon in historical sample and electric power is set along the line
Total amount is applied, area power grid equipment loss late along each typhoon is tried to achieve;
S2. supporting vector machine model is set up, supporting vector machine model is combined with grey correlation analysis, is calculated using population
Method is optimized to supporting vector machine model with grey correlation analysis, sets up the grey relational grade weighting branch based on particle cluster algorithm
Hold vector machine model;
S3. using two parameters of mileage along grade during Landed Typhoon, regional longitudinal direction as independent variable, regional power equipment
Loss late is dependent variable, and the damage under grade typhoon is logged in all previous difference according to the grid equipment in mileage area along different longitudinal directions
Mistake rate sets up loss late forecast model, and uses the grey relational grade Weighted Support Vector model pair based on particle cluster algorithm
Loss late forecast model is fitted;
S4. the precision of loss late forecast model is verified;
S5. input Landed Typhoon when grade and area longitudinal direction along mileage, obtain the loss late of area power grid equipment,
The total amount of grid equipment based on area calculates the quantity of impaired grid equipment, then carries out manpower, material that repairing need to expend
The calculating that material, auxiliary equipment and repairing are spent, realizes the power energy microstructure Prediction to salvaging.
Wherein, support vector regression by input sample space by using Nonlinear Mapping φ:X → φ (x), is transformed to
Another feature space, using ε-insensitive loss function, constructs regression estimates function in this feature space, leads to simultaneously
Cross minimum | | ω | |2To reduce the complexity of model, wherein ω is a vector in regression problem.In order to measure ε-no
The departure degree of training sample outside sensitive strip, introduces the slack variable of non-negativeWith punishment parameter C
(penalty coefficient is the tolerance to error, and the value is higher, illustrate more to can't stand error occur), obtains ε-supporting vector and returns
Return the original optimization problem of machine:
s.t.((ω·φ(xi))+b)-yi≤ε+ξi, i=1,2 ..., l
yi-((ω·φ(xi))+b)≤ε+ξi, i=1,2 ..., l
ξi (*)>=0, i=1,2 ..., l
Its dual problem is:
0≤αi *≤ C, i=1,2 ..., l
Finally, the regression estimates formula for obtaining SVMs is
And the detailed process for setting up grey relation model is as follows:
If X={ x0,x1,...,xmIt is gray relative factor set, xoFor reference sequences, xiFor comparative sequences, i=1,
2,...,m},x0(k),xi(k) it is respectively xoWith xiK-th point of number, i.e.,
xo=(x0(1),x2(2),...,x0(n))
xi=(xi(1),xi(2),...,xi), (n) i=1,2 ..., m
Claim r (x0,xi) it is xoWith xiGrey relational grade, r (x0(k),xi(k)) it is xoWith xiIn the grey relational grade system of k points
Number.
For ρ ∈ (0,1), order
Wherein ρ is referred to as resolution ratio.
On the basis of more than, the support vector regression model of feature based grey relational grade weighting is set up:
If known training set T={ (x1,y1),(x2,y2),...(xl,yl)}∈(Rn×R)l, it is prediction letter in training set T
Effective sample in number relation, it exports sample X=[x1,x2,...,xl] there is m feature:X1,X2,...,Xm, exporting sample is
Y=[y1,y2,...,yl], feature XiWeight with respect to Y is ωi, i=1 ..., m.Value difference means in the input space
Axle will be according to ωiSize and stretch or shrink, make W=diag (ω1,ω2,...,ωm) it is characterized weighting matrix.
Make K (ui,uj) kernel function on U × U is defined in,W is dimension of m m of the luv space to output space
The matrix of a linear transformation, wherein m are the dimension of luv space, characteristic weighing kernel function KfIt is defined as follows Kf(ui,uj)=K (ui TW,
uj TW)
After being weighted to feature, optimization problem is converted into
s.t.((ω·φ(Wxi))+b)-yi≤ε+ξi, i=1,2 ..., l
yi-((ω·φ(Wxi))+b)≤ε+ξi, i=1,2 ..., l
ξi (*)>=0, i=1,2 ..., l
Its dual problem is:
0≤αi *≤ C, i=1,2 ..., l
Therefore regression equation be converted into for
F (x) is previously stored a functional relation in Matlab softwares, x is inputted, with regard to that can draw corresponding y values.In formula
Kf(x,xi) it is the kernel function chosen according to actual conditions, amount of calculation can be simplified.αiAnd α *iFor Lagrange multiplier, b is
Regression parameter.
Specific algorithm is as follows:
Step 1:Reference sequences x is determined on the basis of training set T0=Y and comparative sequences Xi;
Step 2:Initial data is subjected to nondimensionalization processing, to eliminate the influence that size order is different;
Step 3:1 calculate X by definitioniWeights omega with respect to Yi, obtain feature weighting matrix W;
Step 4:It is determined that appropriate parameter ε, C and kernel function, determine characteristic weighing kernel function Kf;
Step 5:The support vector regression algorithm weighted with gray characteristics carries out regression forecasting.
On the basis of more than, the characteristic gray degree of association weighted support vector regression machine model based on PSO is set up:
PSO is that particle cluster algorithm is a kind of optimized algorithm with global optimizing ability based on colony and fitness.
In PSO, optimization problem is possible to the position that solution is considered as in search space, is referred to as " particle ", all particles are all
It is given two features in position and speed and has an adaptive value determined by optimised function.PSO be initialized as a group with
Machine particle (RANDOM SOLUTION), then finds optimal solution by iteration.In each iteration, particle is by tracking two extreme values come more
It is new oneself;First is exactly optimal solution that particle is found in itself, and this solution is referred to as individual extreme value PbestValue is that whole population is looked for
The optimal solution arrived, this solution is global extremum GbestDuring two optimal solutions, each particle according to following formula update the speed of oneself and
Position:
νi(t+1)=ω νi(t)+c1R1[R1 b(t)-xi(t)]+c2R2[Rg b(t)-xi(t)] (1)
xi(t+1)=xi(t)+φνi(t+1) (2)
In formula:T is iterations;νt(t) it is speed of i-th of particle in t iteration;ω is inertia weight;c1,c2For
Cognitive coefficient;R1,R2For uniform random number;Ri b(t) it is the individual history optimal locations of particle i;Rg b(t) for colony's history most
Excellent position;xt(t) for particle in the position of t iteration;φ is a contraction factor, for keeping speed within the specific limits.
Characteristic gray degree of association weighted support vector regression machine optimization process based on PSO is as follows:
Step 1:Particle populations are initialized, setting iterations, particle dimension, population size randomly generate 1 group of parameter work
For particle initial solution locus and initial velocity, characteristic weighing kernel function K is determinedf;
Step 2:The support vector regression algorithm weighted with gray characteristics carries out regression forecasting.Using relevance grade functionFitness analysis is carried out, wherein n is training sample number;yiFor actual value;For predicted value.
Step 3:To each particle, compare its best P lived throughbestFitness value and colony live through most
Good position GbestFitness value, if comparing Pbest、GbestIt is good, then update Pbest、Gbest, otherwise keep original data.
Step 4:After whole colony particle is calculated, judge whether to meet end condition, particle is according to formula if being unsatisfactory for
(1) (2) update, and produce new population, return to step (2).If meeting maximum iteration or termination condition, calculating terminates
And export result of calculation.
Embodiment 2
To verify the precision of Forecasting Methodology proposed by the present invention, it is most representational that the present embodiment chooses typhoon salvaging
Tower engineering is research object, and money table is received by being sent to grid company, and different regions shaft tower total amount is (specific along statistics typhoon
Data are as shown in table 1) and the shaft tower quantity lost during by typhoon, the basic data finally according to collection obtains different regions
Shaft tower loss late under different typhoon grades, as shown in table 2.
The shaft tower total amount summary sheet of table 1
Area | Shaft tower total amount (unit:Base) |
Yangxi | 21000 |
Leizhou | 77378 |
Dianbai | 44866 |
Huaiji | 34211 |
Xuwen | 58927 |
Suixi | 55024 |
Foshan | 7232 |
Jiangmen | 178800 |
Slope head | 82502 |
Xia Shan | 116858 |
Numb chapter | 40244 |
Wenchang | 24924 |
The regional typhoon shaft tower loss late summary sheet of table 2
Analytical table 2 understands that typhoon is based on Landed Typhoon intensity (x for the destruction of electric power facility1), mileage along longitudinal direction
(x2) two parameters, electric power facility can express as the sign of destruction object with destruction amount, due to electric power facility be distributed it is close
The area differentiation of degree, that is to say, that can cause a number of loss in the typhoon of a region some strength grade, but due to
The otherness of area distribution general layout, the typhoon of equality strength may not cause same amount of loss in another region.Therefore it is of the invention
The loss late (y) for choosing area is research object, is used as the function y=f (x for being destroyed feature1,x2).Pass through loss late (y)
And area electric power facility total amount α tries to achieve destruction quantity (y*) to predict emergency repair cost and rush to repair the amount that required power can be supplied
(Y) relation that the grade that, thus detects a typhoon can be supplied with repairing power, i.e. Y=g (y)=g (f (x1,x2))。
Before the present invention is used in the gray characteristics Weighted Support Vector two-dimensional function approximating method based on PSO, selection table 2
20 groups of data of four typhoons are used as test sample as training sample, 5 groups of data of last typhoon.Selection of kernel function is high
This Radial basis kernel function K (x, x')=exp (- γ | | x-x'| |2), with root-mean-square errorAs
Verify the standard of model quality.Feature elects x as1, x2, take resolution ratio ρ=0.5, ωkIt is related to parameter setting in=1/n, PSO:
Population scale L=60, c1=c2=1.31, ω=1.08, greatest iteration t=50.All calculating use MATLAB software programmings
Realize, the situation of implementing is shown in Fig. 2.Wherein x1Axle represents typhoon grade, x2Axle represents mileage along longitudinal direction, and y-axis represents regional bar
Tower loss late.
PSO optimizing results are ε=0.064, C=1.50, γ=0.25;The number of supporting vector is 15, weight difference
For:ω1=0.6387, ω2=0.6311;Root-mean-square error RMSE=0.0001595.Prove that model error is small, can be accurately pre-
Survey.Using the model of above-mentioned foundation, 5 groups of test samples to 17 grades of typhoons are predicted experiment, predict the outcome as shown in table 3:
The model prediction contrast table of table 3
The root-mean-square error RMSE=0.001963 being predicted with grey weighed SVM model of the present invention based on PSO.From
Above analysis result can be seen that the generalization ability of the grey weighed SVM model based on PSO preferably, and prediction is accurate.Therefore, exist
Under actual conditions based on this research small sample, area along typhoon is carried out from the gray characteristics weighed SVM model based on PSO
The prediction of electric power facility loss late, precision is of a relatively high.
Further, introduce and power network typhoon salvaging people, material, the consumption of machine how are predicted by this model.From
Receive money data to understand, lose the base of concurrent 13873 in the nearly 3 years sample all-works in In Guangdong Province altogether, wherein righting is mixed
The solidifying soil base of electric pole 4764, righting concurrent accounting is 34.34%;The base of concurrent 9109 of replacing, changes concrete
Electric pole accounting is 65.66%.The present invention defines tower engineering to change concurrent and righting concurrent.According to engineering
Quota understands that changing 1 base concrete electric pole needs unskilled labor artificial 36.14 (work day), (work of technology of transmission of electricity workman work 14.22
Day);The base concrete electric pole of righting 1 needs common laborer artificial 6.856 (work day), it is necessary to (work of technology of transmission of electricity workman work 3.146
Day).Common laborer's artificial work day needed for 1 base electric pole:D1=36.14*65.66%+6.856*34.34%=26.084;It is required
Technology of transmission of electricity workman's work work day:D2=14.215*65.66%+3.146*34.34%=10.414.
Further, provide according to receiving, the nearly 3 years samples in In Guangdong Province always rush to repair expense for 144287614 yuan, wherein change and
Righting concurrent spends 83620704 yuan altogether, because people, material, the amount of machine and expense have direct positive correlation, according to
This can be obtained, and the ratio beta that tower engineering consumes people, material, the amount of machine and total cost is 0.57954.Then Landed Typhoon intensity, longitudinal edge
Line mileage is shown in accompanying drawing 3, technology of transmission of electricity workman's work work day=common artificial with the unit region repairing artificial work day model of common laborer
Work day * 0.3992.Pass through analysis chart 3:X1 axles represent typhoon grade, and x2 axles represent mileage along longitudinal direction, and the amount of Y1 axles multiplies
With αiRepresent common laborer's artificial work day, wherein α needed for repairingiRepresent each department shaft tower total amount, typhoon repairing technology of transmission of electricity workman
Work work day can be obtained by repairing common artificial work day * 0.3992.
Further, according to project quota, the amount and tower engineering mechanical stage of the valuation material of tower engineering consumption can be obtained
Class collects, specifically respectively as shown in table 4 below, table 5.
The tower engineering of table 4 valuation material consumption summary sheet
Valuation material category | Change concrete | Righting concrete electric |
Steel wire rope φ (kg) below 15 | 0.473175 | -- |
Second-class (the m of the red kahikatea of square bar3) | 0.00465 | 0.0084 |
Welding rod J422 integrates (kg) | 1.9150 | -- |
Galvanized wire integrates (kg) | 0.59375 | 0.5 |
Oxygen (m3) | 1.74 | -- |
Acetylene gas (m3) | 0.575 | -- |
Antirust paint (kg) | 0.29 | 0.0075 |
Common enamel paint (kg) | 0.08525 | 0.0222 |
Transport protection steel bracket (kg) | 2.4396 | -- |
Straw bag (individual) | 0.1094 | -- |
Copper wiring 2mm | -- | 0.75 |
Self-adhesive rubber band | -- | 2.4 |
Gasoline (kg) | -- | 0.006 |
Electric force compounded grease (kg) | -- | 0.003 |
Hacksaw blade (root) | -- | 0.15 |
Cotton waste (kg) | -- | 0.006 |
The tower engineering mechanical one-shift summary sheet of table 5
Mechanical type | Change concrete | Righting concrete electric |
A.C. welder 21kVA | 0.1272 | -- |
Within motor-driven grinding mill 5t | 0.1958 | 0.3456 |
Transmission of electricity special purpose vehicle formula lifting | 0.21005 | -- |
Transmit electricity special truck 5t | 1.18005 | 0.0309 |
Electric engineering car | 0.4176 | 0.558 |
Engine-driven hydraulic press-connection machine 100t | -- | 0.0185 |
Typhoon is combined by table 4 and rushes to repair artificial work day prediction algorithm flow, typhoon grade and sample in salvaging can be obtained
Our unit's region valuation consumption of materials model.By taking tower engineering valuation material steel wire rope as an example, with side proposed by the present invention
Method, fits Landed Typhoon intensity, φ models of steel wire rope below 15 needed for mileage and the repairing of unit region are shown in figure along longitudinal direction
4.Pass through analysis chart 4:x1Axle represents typhoon grade, x2Axle represents mileage along longitudinal direction, Y2The amount of axle is multiplied by αiRepresent repairing
The amount of required φ steel wire ropes below 15, wherein αiRepresent each department shaft tower total amount.Remaining tower engineering valuation material with reference to table 4 with
The ratio of steel wire rope quantity is tried to achieve needed for unit.
Similarly, typhoon is combined by table 5 and rushes to repair artificial work day prediction algorithm flow, typhoon grade and salvaging can be obtained
Middle sample unit region valuation consumption of materials model.By taking tower engineering mechanical-electric engineering truck machine-team as an example, with the present invention
The method of proposition, fits Landed Typhoon intensity, electric engineering car machine-team mould needed for mileage and the repairing of unit region along longitudinal direction
Type is shown in Fig. 5.Pass through analysis chart 5:x1Axle represents typhoon grade, x2Axle represents mileage along longitudinal direction, Y3The amount of axle is multiplied by αiGeneration
The amount of electric engineering car mechanical one-shift, wherein α needed for table repairingiRepresent each department shaft tower total amount.Other kinds of mechanical one-shift
Ratiometric conversion according to table 5 and unit of power engineering truck machine-team can be obtained.
Meaning of the present invention is:By set forth herein method, rationally can accurately predict that power network typhoon was rushed to repair
People, material, the consumption of machine in journey, compensate for blank of the power network typhoon salvaging in power energy microstructure Prediction field.Science is reliable
Power energy microstructure Prediction be carry out power network typhoon salvaging basis, be power network typhoon salvaging efficiently complete, reduction electricity
Net typhoon salvaging cost and the important leverage for recovering typhoon disaster regional power supply in time.
Obviously, the above embodiment of the present invention is only intended to clearly illustrate example of the present invention, and is not pair
The restriction of embodiments of the present invention.For those of ordinary skill in the field, may be used also on the basis of the above description
To make other changes in different forms.There is no necessity and possibility to exhaust all the enbodiments.It is all this
Any modifications, equivalent substitutions and improvements made within the spirit and principle of invention etc., should be included in the claims in the present invention
Protection domain within.
Claims (3)
1. a kind of power energy microstructure Prediction method of power network typhoon salvaging, it is characterised in that:Comprise the following steps:
S1. grid equipment loss amount regional along each typhoon in sample, and electric power facility total amount are collected, each typhoon edge is tried to achieve
Line area power grid equipment loss late;
S2. supporting vector machine model is set up, supporting vector machine model is combined with grey correlation analysis, particle cluster algorithm pair is used
Supporting vector machine model is optimized with grey correlation analysis, set up based on particle cluster algorithm grey relational grade weighting support to
Amount machine model;
S3. so that two parameters of mileage is independents variable along grade during Landed Typhoon, regional longitudinal direction, the loss of regional power equipment
Rate is dependent variable, and the loss late under grade typhoon is logged in all previous difference according to the grid equipment in mileage area along different longitudinal directions
Loss late forecast model is set up, and using the grey relational grade Weighted Support Vector model based on particle cluster algorithm to loss
Rate forecast model is fitted;
S4. the precision of loss late forecast model is verified;
S5. input Landed Typhoon when grade and area longitudinal direction along mileage, obtain the loss late of area power grid equipment, be based on
The total amount of the grid equipment in area calculates the quantity of impaired grid equipment, then carries out manpower, material that repairing need to expend, auxiliary
The calculating for helping equipment and repairing to spend, realizes the power energy microstructure Prediction to salvaging.
2. the power energy microstructure Prediction method of power network typhoon salvaging according to claim 1, it is characterised in that:The electricity
Net equipment is shaft tower.
3. the power energy microstructure Prediction method of power network typhoon salvaging according to claim 1, it is characterised in that:The step
The detailed process of rapid S4 checkings loss late precision of forecasting model is as follows:
Grade when inputting from a certain history Landed Typhoon to loss late forecast model and mileage, loss late along the longitudinal direction in somewhere
Forecast model is calculated according to the data of input to be obtained loss late and is exported, by the loss late of output and somewhere in the history
The true loss late of grid equipment under typhoon is compared, and then utilizes the precision of root-mean-square error RMSE method computation models.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710580793.2A CN107292448A (en) | 2017-07-17 | 2017-07-17 | A kind of power energy microstructure Prediction method of power network typhoon salvaging |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710580793.2A CN107292448A (en) | 2017-07-17 | 2017-07-17 | A kind of power energy microstructure Prediction method of power network typhoon salvaging |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107292448A true CN107292448A (en) | 2017-10-24 |
Family
ID=60100866
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710580793.2A Pending CN107292448A (en) | 2017-07-17 | 2017-07-17 | A kind of power energy microstructure Prediction method of power network typhoon salvaging |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107292448A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112579580A (en) * | 2020-11-26 | 2021-03-30 | 广东工业大学 | Pre-alarm method based on industrial big data prediction |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102269124A (en) * | 2011-06-30 | 2011-12-07 | 内蒙古电力勘测设计院 | Ultra-short term wind power station generated power forecasting system |
CN102663513A (en) * | 2012-03-13 | 2012-09-12 | 华北电力大学 | Combination forecast modeling method of wind farm power by using gray correlation analysis |
-
2017
- 2017-07-17 CN CN201710580793.2A patent/CN107292448A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102269124A (en) * | 2011-06-30 | 2011-12-07 | 内蒙古电力勘测设计院 | Ultra-short term wind power station generated power forecasting system |
CN102663513A (en) * | 2012-03-13 | 2012-09-12 | 华北电力大学 | Combination forecast modeling method of wind farm power by using gray correlation analysis |
Non-Patent Citations (4)
Title |
---|
张树团等: "基于粒子群算法和支持向量机的故障诊断研究", 《计算机测量与控制》 * |
朱清清等: "输电线路运行可靠性预测", 《电力系统自动化》 * |
范亚洲: "沿海架空输电线路防风防雷的综合治理", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
饶刚等: "基于灰色特征加权支持向量机的二维函数拟合", 《计算机工程与设计》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112579580A (en) * | 2020-11-26 | 2021-03-30 | 广东工业大学 | Pre-alarm method based on industrial big data prediction |
CN112579580B (en) * | 2020-11-26 | 2022-07-05 | 广东工业大学 | Pre-alarm method based on industrial big data prediction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Negnevitsky et al. | Short term wind power forecasting using hybrid intelligent systems | |
CN110880789B (en) | Economic dispatching method for wind power and photovoltaic combined power generation system | |
CN101592673B (en) | Method for forecasting wind speed along railway | |
CN110729764B (en) | Optimal scheduling method for photovoltaic power generation system | |
CN105787600A (en) | Electric taxi charging station planning method based on adaptive quantum genetic algorithm | |
CN103488869A (en) | Wind power generation short-term load forecast method of least squares support vector machine | |
CN106295899B (en) | Wind power probability density Forecasting Methodology based on genetic algorithm Yu supporting vector quantile estimate | |
CN104933627A (en) | Energy efficiency combination evaluation method of machine tool product manufacture system | |
CN109117486A (en) | A kind of electric automobile charging station optimum programming method | |
CN112613554B (en) | Wind driven generator variable pitch system fault prediction method and system | |
CN104376371B (en) | A kind of distribution based on topology is layered load forecasting method | |
CN107122856A (en) | Space saturation load forecasting method under new situation | |
CN102930343A (en) | Method for energy optimization of distributed power generation and energy supply system | |
CN105787588A (en) | Dynamic state peak-valley time-of-use tariff method for improving new energy absorption capability | |
CN106156895A (en) | A kind of charging electric vehicle load forecasting method based on fuzzy C-means clustering with substep grid search support vector regression | |
CN106886833A (en) | A kind of wind-driven generator addressing Lectotype Optimization method suitable for Complex Constraints condition | |
CN106600136A (en) | Electric power section off-limit control efficiency evaluation method | |
CN112215428A (en) | Photovoltaic power generation power prediction method and system based on error correction and fuzzy logic | |
CN105205326A (en) | Method for on-line prediction of real-time load of power plant | |
CN109190786A (en) | A kind of combination forecasting method of photovoltaic efficiency | |
CN107292448A (en) | A kind of power energy microstructure Prediction method of power network typhoon salvaging | |
He et al. | A lyapunov drift-plus-penalty-based multi-objective optimization of energy consumption, construction period and benefit | |
CN105976099A (en) | Fuzzy information-based aerospace model scientific research and production management level evaluation method | |
CN113393156A (en) | Life cycle evaluation-based offshore wind farm environmental impact assessment method | |
CN112836876A (en) | Power distribution network line load prediction method based on deep learning |
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: 20171024 |
|
RJ01 | Rejection of invention patent application after publication |