CN107733089A - A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM - Google Patents
A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM Download PDFInfo
- Publication number
- CN107733089A CN107733089A CN201711103650.9A CN201711103650A CN107733089A CN 107733089 A CN107733089 A CN 107733089A CN 201711103650 A CN201711103650 A CN 201711103650A CN 107733089 A CN107733089 A CN 107733089A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- data
- svm
- disconnecting link
- 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 12
- 230000007257 malfunction Effects 0.000 claims abstract description 7
- 230000008030 elimination Effects 0.000 claims abstract description 5
- 238000003379 elimination reaction Methods 0.000 claims abstract description 5
- 238000009434 installation Methods 0.000 claims description 18
- 230000036541 health Effects 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 241000196324 Embryophyta Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000006870 function Effects 0.000 description 12
- 238000012423 maintenance Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 229910052573 porcelain Inorganic materials 0.000 description 1
Classifications
-
- H02J13/0003—
-
- H02J13/0006—
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
-
- 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
- Y04S10/16—Electric power substations
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM, comprise the following steps：Step 1：Arrange data source；Step 2：Pretreatment is carried out to above-mentioned data source and obtains consistent monotonicity, and normalizing makes number range be in [0,1]；Step 3：After obtaining normalized numerical value by step 2, with reference to the training sample (x of historical data compositioni,yi), training sample (xi,yi) pass through the calculating of function train svm in SVM tool boxes, you can deviation b and Lagrange coefficient α are obtained, draws forecast model：Step 5：The forecast model trained with historical data carries out disconnecting link secondary circuit failure prediction, exports and thinks normal operation for 1, if output thinks failure be present for+1, you can carry out malfunction elimination in advance with reference to power failure plan.
Description
Technical field
The present invention relates to automation mechanized operation field, more particularly to spreader bar automation paper feeding.
Background technology
Disconnecting switch in power system is disconnecting link, is the important electrical equipment of power system.Once generation transformer station knife
Lock secondary circuit failure, it will there is disconnecting link and refuse to close, refuse phenomenon of grading, produce critical defect, not only influence to stop power transmission efficiency,
The security risk of work is also add, porcelain vase may be caused to produce crack, or even fracture what is more, cause equipment fault to be tripped
Serious consequence, influence power network normal operation.
However, because each component deterioration process of different disconnecting links is different, periodic inspection, periodic maintenance except increase safeguard into
This, can not fundamentally solve outside maintenance workload and predict disconnecting link secondary circuit whether failure.At present, for becoming
The disconnecting link secondary circuit failure that power station is widely used lacks a kind of effective Forecasting Methodology.
The content of the invention
It is a primary object of the present invention to overcome drawbacks described above of the prior art, a kind of transformer station based on SVM is proposed
Disconnecting link secondary circuit failure Forecasting Methodology, its method is simply clear, is easy to calculate, it is easy to accomplish.
In order to solve above-mentioned technical problem, the invention provides a kind of transformer station's disconnecting link secondary circuit event based on SVM
Hinder Forecasting Methodology, comprise the following steps：
Step 1：Arrange the 1. installation producer of disconnecting link account in export PMS account systems, 2. run the time limit, 3. maintenance time
Number, 4. running environment, 5. power distribution equipment pattern, six big major influence factors of load condition are 6. undertaken as data source；
Step 2：To 1. installed in above-mentioned data source producer, 4. running environment, 5. power distribution equipment pattern pre-processes
Consistent monotonicity is obtained, and normalizing makes number range be in [0,1]；
Installation producer is pre-processed and normalization refers to：The actual event in this area under one's jurisdiction power network according to the installation producer
Hinder quantity gi, with reference to related installation plant equipment sum C in PMS account systemsi, define producer health degree ηi
I=1 in formula, 2 ..., m, m be that equipment the installation producer quantity of failure occurred, and provide not occurring temporarily therefore
The installation producer health degree of barrier is 0；
Pretreatment is carried out to running environment to refer to：The situation that equipment operates in outdoor environment is 1, operates in indoor environment
Situation be 0；
Pretreatment is carried out to power distribution equipment pattern to refer to：It is 1 to provide AIS equipment, GIS device 0；
1. installation producer, 4. running environment, 5. power distribution equipment pattern obtains consistent dullness after above-mentioned pretreatment
Property, numerical value is bigger, and fault rate is higher, and each data, which are normalized, further according to formula (2) makes number range be in [0,1]；
I=1 in formula, 2 ..., n, i-th group of data is represented, j=1,2 ..., 6, represents jth dimension data, Iij、Ii'jRespectively
Represent each influence factor numerical value and the numerical value after normalization after pretreatment；
Step 3：Selection uses radial direction base RBF functionsAs kernel function；
Step 4：After obtaining normalized numerical value by step 2, with reference to the training sample (x of historical data compositioni,
yi), i=1,2 ..., n, represent i-th group of data, wherein yi∈ {+1, -1 }；Training sample (xi,yi) by SVM tool boxes
Function train-svm calculating, you can deviation b and Lagrange coefficient α are obtained, so as to draw the forecast model such as following formula：
X in formulaiFor training data, i=1,2 ..., n, n be training data group number, x is data to be predicted, and K is core letter
Number,And training data and prediction data are 6 dimension data types；Adjusting parameter σ in formula
It is set to 64.290；
Step 5：The forecast model trained with historical data carries out disconnecting link secondary circuit failure prediction, exports and recognizes for -1
For normal operation, think failure be present if exporting for+1, you can carry out malfunction elimination in advance with reference to power failure plan.
In a preferred embodiment：In step 4,
, will by hyperplane equation wx+b=0：Training sample (xi,yi) it is divided into two classes：
In above formula, w is vector, and the optimal hyperlane of SVMs is one and causes the maximum hyperplane of classifying edge,
I.e. so thatMaximum, so solving optimal hyperlane, i.e. object function is
Above formula should meet constraints：yi(w·xi+ b) -1 >=0, i=1,2 ..., n.
According to Lagrange duality principle, above-mentioned object function equivalency transform is
α is Lagrange multiplier in formula, and T is matrix rotor, and it has following relation with w：
It is trained using above-mentioned training sample data.
Compared to prior art, technical scheme possesses following beneficial effect
A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM proposed by the present invention, can predict knife in advance
Whether is lock secondary circuit health, and malfunction elimination is carried out in advance with reference to power failure plan, reduces disconnecting link catastrophic discontinuityfailure to grid switching operation
Influence and the potential safety hazard come to the person, power network, equipment belt, greatly improve the safety operation level of power supply enterprise, improve and supply
Electric reliability, there is huge Social benefit and economic benefit.
Embodiment
Below by way of embodiment, the invention will be further described.Specifically comprise the following steps：
1) the 1. installation producer of export disconnecting link account first, is arranged from PMS account systems, the time limit is 2. run, 3. overhauls
Number, 4. running environment, 5. power distribution equipment pattern, six big major influence factors of load condition are 6. undertaken as training and test
Data；
2) due to 1. install producer, 4. running environment, 5. there is particularity in the data of power distribution equipment pattern, need to carry out such as
Lower pretreatment：
(1) producer is installed：According to the installation producer in this area under one's jurisdiction power network physical fault quantity gi, with reference to PMS accounts system
Related installation plant equipment sum C in systemi, define producer health degree ηi：
I=1 in formula, 2 ..., m, m be that equipment the installation producer quantity of failure occurred, and provide not occurring temporarily therefore
The installation producer health degree of barrier is 0.It is apparent that health degree more levels off to 1, illustrate that fault rate is higher.
(2) running environment：Present invention provide that the situation of equipment operation out of doors is 1, situation indoors is 0, through endless
Full statistics, the equipment failure rate run out of doors are relatively high；
(3) power distribution equipment pattern：Present invention provide that AIS equipment is 1, GIS device 0, through incomplete statistics, AIS equipment
Fault rate is relatively high；
Consistent monotonicity is obtained after above-mentioned pretreatment, numerical value is bigger, and fault rate is higher, further according to formula (2)
Each data, which are normalized, makes number range be in [0,1]；
I=1 in formula, 2 ..., n, i-th group of data is represented, j=1,2 ..., 6, represents jth dimension data, Iij、Ii'jRespectively
Represent each influence factor numerical value and the numerical value after normalization after pretreatment.
3) radial direction base RBF functions are used by experience and repeatedly test, selection for the selected of model parameter, the present invention
As kernel function,
Adjusting parameter σ is set to 64.290 in formula；
4) it is understood that, SVMs be based on Statistical Learning Theory structure typical neutral net, it is by building
Found an optimal separating hyper plane so that the distance between two class samples of the plane both sides maximize, so as to classification problem
Good generalization ability is provided.After obtaining normalized numerical value by step 2), with reference to the training sample of historical data composition
(xi,yi), i=1,2 ..., n, represent i-th group of data, wherein yi∈ {+1, -1 }.Then, hyperplane equation wx+b is passed through
=0, sample is divided into two classes：
W is vector, and the optimal hyperlane of SVMs is one and causes the maximum hyperplane of classifying edge, that is, causesMaximum, so solving optimal hyperlane, i.e. object function is
Above formula should meet constraints：yi(w·xi+ b) -1 >=0, i=1,2 ..., n.
According to Lagrange duality principle, above-mentioned object function equivalency transform is
T is matrix rotor in formula, and α is Lagrange multiplier, and it has following relation with w：
It is trained using above-mentioned training sample data, passes through the calculating of function train-svm in SVM tool boxes, you can
Deviation b and Lagrange coefficient α are obtained, and according to formula (7), w is obtained, so as to draw the forecast model such as following formula：
X in formulaiFor training data, i=1,2 ..., n, x be data to be predicted, K is kernel function, the present inventionAnd training data and prediction data are 6 dimension data types.
5) the forecast model formula (8) trained according to historical data, by letter in forecast sample data input SVM tool boxes
Number predict-svm is calculated, and is completed the failure predication to disconnecting link secondary circuit, is exported and think normal operation for -1, if defeated
It has and thinks failure be present for+1, you can carries out malfunction elimination in advance with reference to power failure plan.
Applicating example
According to certain districts and cities' corporate history running situation, 300 groups of training samples of export, 30 groups of test samples are arranged.Train sample
260 groups of normal condition in this, 40 groups of malfunction；25 groups of normal condition in test sample, 5 groups of malfunction.
The present invention is first according to step 1) -4) by above-mentioned training sample composing training collection it is { (x1,y1),(x2,
y2),...,(x300,y300), wherein, xi∈R6,yi={ 1, -1 }, works as yiWhen=1, it is secondary to represent that i-th of sample has disconnecting link
Loop fault, work as yiWhen=- 1, represent that i-th of sample disconnecting link secondary circuit is normal.Then, function in SVM tool boxes is passed through
Forecast model traindata.model is calculated in train-svm, finally, combines forecast model according to step 5), will predict
Function predict-svm calculates prediction result in sample data input SVM tool boxes, as shown in table 1 below.
The disconnecting link secondary circuit failure prediction result of table 1
Overall accuracy is the correct sample number of prediction and the ratio of total forecast sample number in upper table.And as shown in Table 1, should
The accuracy that invention is predicted disconnecting link secondary circuit failure up to more than 90%, therefore to disconnecting link secondary circuit failure prediction be
It is feasible, efficient.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited to
This, any one skilled in the art the invention discloses technical scope in, the change that can readily occur in or replace
Change, should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with the protection of claim
Scope is defined.
Claims (2)
1. a kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM, it is characterised in that comprise the following steps：
Step 1：The 1. installation producer of disconnecting link account in export PMS account systems is arranged, the time limit is 2. run, 3. overhauls number, 4.
Running environment, 5. power distribution equipment pattern, six big major influence factors of load condition are 6. undertaken as data source；
Step 2：To 1. installed in above-mentioned data source producer, 4. running environment, 5. power distribution equipment pattern carry out pretreatment obtain one
The monotonicity of cause, and normalizing makes number range be in [0,1]；
Installation producer is pre-processed and normalization refers to：According to the installation producer in this area under one's jurisdiction power network physical fault quantity
gi, with reference to related installation plant equipment sum C in PMS account systemsi, define producer health degree ηi
<mrow>
<msub>
<mi>&eta;</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mfrac>
<msub>
<mi>g</mi>
<mi>i</mi>
</msub>
<msub>
<mi>C</mi>
<mi>i</mi>
</msub>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
I=1 in formula, 2 ..., m, m be that equipment the installation producer quantity of failure occurred, and provide temporarily do not occurred the peace of failure
It is 0 to fill producer's health degree；
Pretreatment is carried out to running environment to refer to：The situation that equipment operates in outdoor environment is 1, operates in the situation of indoor environment
For 0；
Pretreatment is carried out to power distribution equipment pattern to refer to：It is 1 to provide AIS equipment, GIS device 0；
1. installation producer, 4. running environment, 5. power distribution equipment pattern obtains consistent monotonicity after above-mentioned pretreatment, number
Value is bigger, and fault rate is higher, and each data, which are normalized, further according to formula (2) makes number range be in [0,1]；
<mrow>
<msubsup>
<mi>I</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
<mo>&prime;</mo>
</msubsup>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>I</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>-</mo>
<mi>min</mi>
<mi> </mi>
<msub>
<mi>I</mi>
<mi>j</mi>
</msub>
</mrow>
<mrow>
<mi>max</mi>
<mi> </mi>
<msub>
<mi>I</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<mi>min</mi>
<mi> </mi>
<msub>
<mi>I</mi>
<mi>j</mi>
</msub>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
I=1 in formula, 2 ..., n, i-th group of data is represented, j=1,2 ..., 6, represents jth dimension data, Iij、I′ijRepresent respectively
Each influence factor numerical value and the numerical value after normalization after pretreatment；
Step 3：Selection uses radial direction base RBF functionsAs kernel function, wherein adjustment ginseng
Number σ is set to 64.290；
Step 4：After obtaining normalized numerical value by step 2, with reference to the training sample (x of historical data compositioni,yi), i=
1,2 ..., n, represent i-th group of data, wherein yi∈ {+1, -1 }；Training sample (xi,yi) pass through function in SVM tool boxes
Train-svm calculating, you can deviation b and Lagrange coefficient α are obtained, so as to draw the forecast model such as following formula：
<mrow>
<mi>y</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mi>K</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>b</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
X in formulaiFor training data, i=1,2 ..., n, n be training data group number, x is data to be predicted, and K is kernel function,And training data and prediction data are 6 dimension data types；
Step 5：The forecast model trained with historical data carries out disconnecting link secondary circuit failure prediction, exports and thinks just for -1
Often operation, if output thinks failure be present for+1, you can carry out malfunction elimination in advance with reference to power failure plan.
2. a kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM according to claim 1, its feature exist
In：In step 4,
, will by hyperplane equation wx+b=0：Training sample (xi,yi) it is divided into two classes：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>w</mi>
<mo>&CenterDot;</mo>
<mi>x</mi>
<mo>+</mo>
<mi>b</mi>
<mo>&GreaterEqual;</mo>
<mn>0</mn>
<mo>,</mo>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>=</mo>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>w</mi>
<mo>&CenterDot;</mo>
<mi>x</mi>
<mo>+</mo>
<mi>b</mi>
<mo>&le;</mo>
<mn>0</mn>
<mo>,</mo>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>=</mo>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
In above formula, w is vector；The optimal hyperlane of SVMs is a hyperplane for causing classifying edge maximum, even if
Maximum, so solving optimal hyperlane, i.e. object function is
<mrow>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
<mi>&phi;</mi>
<mrow>
<mo>(</mo>
<mi>w</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<mo>|</mo>
<mo>|</mo>
<mi>w</mi>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>5</mn>
<mo>)</mo>
</mrow>
</mrow>
Above formula should meet constraints：yi(w·xi+ b) -1 >=0, i=1,2 ..., n.
According to Lagrange duality principle, above-mentioned object function equivalency transform is
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
<mi>&Gamma;</mi>
<mrow>
<mo>(</mo>
<mi>w</mi>
<mo>,</mo>
<mi>b</mi>
<mo>,</mo>
<mi>&alpha;</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<mo>|</mo>
<mo>|</mo>
<mi>w</mi>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
<mo>-</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<mo>(</mo>
<mrow>
<msup>
<mi>w</mi>
<mi>T</mi>
</msup>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>+</mo>
<mi>b</mi>
</mrow>
<mo>)</mo>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>6</mn>
<mo>)</mo>
</mrow>
</mrow>
α is Lagrange multiplier in formula, and T refers to matrix rotor, and it has following relation with w：
<mrow>
<mi>w</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>y</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>7</mn>
<mo>)</mo>
</mrow>
</mrow>
It is trained using above-mentioned training sample data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711103650.9A CN107733089A (en) | 2017-11-10 | 2017-11-10 | A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711103650.9A CN107733089A (en) | 2017-11-10 | 2017-11-10 | A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107733089A true CN107733089A (en) | 2018-02-23 |
Family
ID=61214326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711103650.9A Pending CN107733089A (en) | 2017-11-10 | 2017-11-10 | A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107733089A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108923413A (en) * | 2018-05-23 | 2018-11-30 | 国网福建省电力有限公司莆田供电公司 | Quality of voltage prediction technique based on support vector machines |
| CN109035066A (en) * | 2018-09-30 | 2018-12-18 | 国网山西省电力公司阳泉供电公司 | The high breaking route genetic analysis of 10 kilovolts of distributions and administering method based on SVM |
| CN109061453A (en) * | 2018-08-02 | 2018-12-21 | 国网福建省电力有限公司 | Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient |
| CN110649597A (en) * | 2019-09-06 | 2020-01-03 | 国网山东省电力公司寿光市供电公司 | RBF neural network-based power distribution network feeder automation control method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160444A (en) * | 2015-10-22 | 2015-12-16 | 广东电网有限责任公司电力调度控制中心 | Electrical equipment failure rate determining method and system |
| CN105932774A (en) * | 2016-05-11 | 2016-09-07 | 国网冀北电力有限公司张家口供电公司 | Device state early warning method in smart transformer substation based on ICA algorithm |
| US20170015339A1 (en) * | 2014-12-12 | 2017-01-19 | Beijing Jiaotong University | Complex network-based high speed train system safety evaluation method |
| CN106844826A (en) * | 2016-12-02 | 2017-06-13 | 上海电机学院 | A kind of method for the diagnosis of gearbox of wind turbine failure predication |
| CN107257161A (en) * | 2017-06-20 | 2017-10-17 | 安徽南瑞继远电网技术有限公司 | A kind of transformer station's disconnecting link remote control auxiliary check method and system based on state recognition algorithm |
-
2017
- 2017-11-10 CN CN201711103650.9A patent/CN107733089A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170015339A1 (en) * | 2014-12-12 | 2017-01-19 | Beijing Jiaotong University | Complex network-based high speed train system safety evaluation method |
| CN105160444A (en) * | 2015-10-22 | 2015-12-16 | 广东电网有限责任公司电力调度控制中心 | Electrical equipment failure rate determining method and system |
| CN105932774A (en) * | 2016-05-11 | 2016-09-07 | 国网冀北电力有限公司张家口供电公司 | Device state early warning method in smart transformer substation based on ICA algorithm |
| CN106844826A (en) * | 2016-12-02 | 2017-06-13 | 上海电机学院 | A kind of method for the diagnosis of gearbox of wind turbine failure predication |
| CN107257161A (en) * | 2017-06-20 | 2017-10-17 | 安徽南瑞继远电网技术有限公司 | A kind of transformer station's disconnecting link remote control auxiliary check method and system based on state recognition algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 余彬 等: "基于支持向量机的变电站过热故障的在线监测", 《浙江电力》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108923413A (en) * | 2018-05-23 | 2018-11-30 | 国网福建省电力有限公司莆田供电公司 | Quality of voltage prediction technique based on support vector machines |
| CN109061453A (en) * | 2018-08-02 | 2018-12-21 | 国网福建省电力有限公司 | Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient |
| CN109035066A (en) * | 2018-09-30 | 2018-12-18 | 国网山西省电力公司阳泉供电公司 | The high breaking route genetic analysis of 10 kilovolts of distributions and administering method based on SVM |
| CN110649597A (en) * | 2019-09-06 | 2020-01-03 | 国网山东省电力公司寿光市供电公司 | RBF neural network-based power distribution network feeder automation control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107733089A (en) | A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM | |
| Liu et al. | A systematic approach for dynamic security assessment and the corresponding preventive control scheme based on decision trees | |
| US9239816B2 (en) | Method of power system preventive control candidate measures identification self-adaptive to external environment | |
| CN103700025B (en) | A kind of assessment sort method of power system device importance degree based on risk analysis | |
| CN103545832B (en) | A kind of photovoltaic system energy accumulation capacity configuration based on generating predicated error | |
| CN107194574B (en) | Power grid security risk assessment method based on load loss | |
| CN104392391A (en) | Power grid running safety risk quantification method | |
| CN102934312B (en) | Energy production system and control thereof | |
| CN103337043B (en) | The method for early warning of electric power communication device running status and system | |
| CN104299116A (en) | Quantitative evaluation method for security risk of operation of power network | |
| CN103279900B (en) | A kind of appraisal procedure for weak domain of area transmission network | |
| CN106447227A (en) | Urban power grid abnormal state analyzing method and system | |
| CN109359896B (en) | SVM-based power grid line fault risk early warning method | |
| CN109061453A (en) | Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient | |
| CN103150635B (en) | Power equipment O&M method | |
| CN106058865A (en) | Power grid node voltage dip risk evaluation method | |
| CN104021304A (en) | Installation priority level evaluation method for on-line monitoring devices of transformers | |
| CN107239652A (en) | A kind of charging station running status methods of risk assessment | |
| CN103500283A (en) | Power transformer risk assessment method based on fault tree | |
| CN105184490B (en) | Forming Electrical Dispatching Command Tickets process risk assists Pre-control System | |
| CN109214717A (en) | Power distribution network power grid evaluation method and its evaluation system | |
| CN106600458A (en) | Power grid risk comprehensive assessment method based on improved power betweenness | |
| CN106571627A (en) | Secondary device health state evaluation method based on on-line monitoring information | |
| CN108448721A (en) | The method of electric system main station monitoring signal and standard signal Auto-matching | |
| CN107230160A (en) | A kind of 10kV line trippings wrong report is intelligent to judge implementation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180705 Address after: 351100 No. 999, South Garden Road, Xia Lin Street, Chengxiang District, Putian, Fujian Applicant after: PUTIAN POWER SUPPLY COMPANY, STATE GRID FUJIAN ELECTRIC POWER CO., LTD. Applicant after: State Grid Fujian Electric Power Co., Ltd. Address before: No. 54, No. 257, Drum Tower District, Fuzhou, Fujian Applicant before: State Grid Fujian Electric Power Co., Ltd. Applicant before: State Grid Corporation of China Applicant before: PUTIAN POWER SUPPLY COMPANY, STATE GRID FUJIAN ELECTRIC POWER CO., LTD. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180223 |
|
| RJ01 | Rejection of invention patent application after publication |