CN109061453A - Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient - Google Patents
Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient Download PDFInfo
- Publication number
- CN109061453A CN109061453A CN201810870505.1A CN201810870505A CN109061453A CN 109061453 A CN109061453 A CN 109061453A CN 201810870505 A CN201810870505 A CN 201810870505A CN 109061453 A CN109061453 A CN 109061453A
- Authority
- CN
- China
- Prior art keywords
- sample
- disconnecting link
- training sample
- evaluated
- coefficient
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
- G01R31/3271—Testing of circuit interrupters, switches or circuit-breakers of high voltage or medium voltage devices
- G01R31/3272—Apparatus, systems or circuits therefor
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient, include the following steps: 1) from PMS account system export installation producer, the operation time limit, maintenance number, running environment, power distribution equipment pattern, undertake load condition as historical data, and to partially being pre-processed, normalized as training sample;2) training sample and sample to be evaluated are subjected to related coefficient and calculate simultaneously given threshold, the training sample that will be less than threshold value is rejected, and is filtered out and the higher sample of the sample degree of association to be evaluated;3) for the training sample filtered out, the optimized parameter for determining support vector machines is searched for using Gridregression;3) it is calculated using function train-svm in the tool box LIBSVM, obtains deviation b and Lagrange coefficient α, α*, to obtain prediction model:
Description
Technical field
The invention belongs to substation's disconnecting link secondary circuit failure predict field, be related to it is a kind of meter and related coefficient substation
Disconnecting link secondary circuit failure prediction technique.
Background technique
Disconnecting link, that is, disconnecting switch is primary equipment important in electric system, and secondary circuit failure will affect point of disconnecting link
It closes, not only influences substation's operation maintenance personnel and stop power transmission, increase the work of service personnel, be also possible to damage primary equipment when serious
It is bad, it extends and stops electric power feeding time, increase attricist, influence operation of power networks.
However, leading to since disconnecting link secondary circuit can judge whether break down from appearance unlike primary equipment
It crosses and regularly overhauls, safeguards not reaching look-ahead and have disconnecting link secondary circuit there are problems that failure.Currently, for power transformation
Disconnecting link secondary circuit failure lacks a kind of efficient, feasible prediction technique in standing.
Summary of the invention
It is a primary object of the present invention to overcome drawbacks described above in the prior art, propose it is a kind of meter and related coefficient change
Power station disconnecting link secondary circuit failure prediction technique, method is simply clear, convenient for calculating, it is easy to accomplish.
The present invention adopts the following technical scheme:
Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient, which comprises the steps of:
1) installation producer, the operation time limit, maintenance number, operation ring of export disconnecting link account are arranged from PMS account system
Border, power distribution equipment pattern undertake the big major influence factors data of load condition six as historical data, and to installation producer, fortune
Row environment, power distribution equipment pattern carry out pretreatment and obtain consistent monotonicity, and normalizing is in numberical range [0,1], then
Installation producer, running environment and power distribution equipment pattern after running the time limit, overhauling number, undertake load condition and normalization is made
For training sample;
2) training sample and sample to be evaluated are carried out related coefficient calculating will be less than according to related coefficient given threshold
The training sample of threshold value is rejected, and is filtered out and the higher sample of the sample degree of association to be evaluated;
3) it for the training sample filtered out, is determined and is supported using the Gridregression program search of matlab tool
Fault-tolerant penalty coefficient C, the insensitive coefficient ε and core width system σ optimized parameter of vector machine;
4) calculated using function train-svm in the tool box LIBSVM, obtain deviation b and Lagrange coefficient α,
α*, to obtain the prediction model such as following formula:
X in formulaiFor the training sample filtered out, i=1,2 ..., n, n are the number of the training sample filtered out, x be to
Sample is evaluated, K is kernel function,
And training sample and sample to be evaluated are 6 dimension data types;
5) sample to be evaluated is predicted using prediction model, exports and think disconnecting link normal operation for -1, if output for+
1 is thought disconnecting link there are failure, i.e., carries out malfunction elimination in advance in combination with power failure plan.
Preferably, as follows to the pretreatment of the installation producer in step 1):
According to the installation producer in this area under one's jurisdiction power grid physical fault quantity gi, in conjunction with installation related in PMS account system
Plant equipment sum Ci, define producer health degree ηi
I=1 in formula, 2 ..., m, m are that the installation producer quantity of failure occurred in equipment, and provided do not occurred failure temporarily
Installation producer health degree be 0.
Preferably, as follows to the pretreatment of the running environment in step 1): the case where specified devices are run outdoors
Be 1, indoors the case where be 0.
Preferably, as follows to the pretreatment of the power distribution equipment pattern in step 1): regulation AIS equipment is that 1, GIS is set
Standby is 0.
Preferably, in step 1), the normalization makes numberical range be in [0,1], referring to as follows:
I=1 in formula, 2 ..., k indicate i-th group of data, and k is the sum of training sample, and j=1,2 ..., 6 indicates jth
Dimension data, min Ij、max IjRespectively indicate the minimum value and maximum value of all training sample jth dimension datas, Iij、I′ijRespectively
The jth dimension data of i-th group of sample indicates each influence factor numerical value and the numerical value after normalizing after pretreatment.
Preferably, the correlation coefficient ρ range described in step 2) be [- 1 ,+1], the threshold value P=| ρ |, related coefficient
ρ calculation formula is as follows:
In formula, XiFor i-th of index in sample to be evaluated, YiFor i-th of index in training sample,It is to be evaluated
The average value of all indexs in sample,For the average value of indexs all in training sample, N is sample middle finger target number, N=
6。
By the above-mentioned description of this invention it is found that compared with prior art, the invention has the following beneficial effects:
Method of the invention, substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient can be pre- in advance
Disconnecting link secondary circuit failure is surveyed, the accuracy rate of prediction is improved.Troubleshooting is carried out in advance according to prediction result combination power failure plan,
Disconnecting link secondary circuit catastrophic discontinuityfailure is reduced to the person, power grid, equipment bring security risk, greatly improves the peace of power supply enterprise
Full operation level improves power supply reliability, has huge Social benefit and economic benefit.
Specific embodiment
Below by way of specific embodiment, the invention will be further described.
Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient of the invention includes the following:
1) from PMS account system arrange export disconnecting link account 1. installation producer, 2. run the time limit, 3. overhaul number,
4. 6. running environment, 5. power distribution equipment pattern undertake the big major influence factors of load condition six as trained and test data.
Due to 1. installing, producer, 4. running environment, the data of 5. power distribution equipment pattern need to carry out following pre- there are particularity
Processing:
(1) install producer: according to the installation producer in this area under one's jurisdiction power grid physical fault quantity gi, in conjunction with PMS account system
Related installation plant equipment sum C in systemi, define producer health degree ηi
I=1 in formula, 2 ..., m, m are that the installation producer quantity of failure occurred in equipment, and provided do not occurred failure temporarily
Installation producer health degree be 0.It is apparent that health degree more levels off to 1, illustrate that failure rate is higher;
(2) running environment: present invention provide that equipment operation outdoors the case where be 1, indoors the case where be 0, through endless
Full statistics, the equipment failure rate run outdoors are relatively high;
(3) power distribution equipment pattern: present invention provide that AIS equipment is 1, GIS device 0, through incomplete statistics, AIS equipment
Failure rate is relatively high;
Consistent monotonicity is obtained after above-mentioned pretreatment, numerical value is bigger, and failure rate is higher, further according to formula (2)
Each data, which are normalized, makes numberical range be in [0,1];
I=1 in formula, 2 ..., k, indicate i-th group of data, and k is the number of total training sample, j=1,2 ..., 6, table
Show jth dimension data, min Ij、max IjRespectively indicate the minimum value and maximum value of all training sample jth dimension datas, Iij、I′ij
Respectively indicate the jth dimension data of i-th group of sample each influence factor numerical value and the numerical value after normalizing after pretreatment.
2) with historical data as relative value standardization sample Y, with the standardized index amount of disconnecting link to be evaluated formed to
Sample X is evaluated, evaluates the correlation between sample to be evaluated and historical sample with Spearman rank correlation coefficient ρ (formula 3),
Related coefficient is bigger, that is, indicates that the degree of correlation between sample to be evaluated and historical sample is bigger or more similar.When variation becomes
When gesture is identical, correlation coefficient ρ range between two variables be [- 1 ,+1] or.
In formula, XiFor i-th of index in sample to be evaluated, YiFor i-th of index in training sample,It is to be evaluated
The average value of all indexs in sample,For the average value of indexs all in training sample, N is sample middle finger target number, N=
6。
Take P=| ρ |, if the threshold value of P is that 0.5, P >=0.5 indicates that sample is significant correlation to the degree of correlation of prediction result,
P < 0.5 indicates that sample is low correlation to the degree of correlation of prediction result.The mark of quality using related coefficient P value as judgement sample
Standard, the sample that will be less than threshold value are rejected, are filtered out and the higher n group training sample of the sample degree of association to be evaluated.
3) using the fault-tolerant penalty coefficient C of Gridregression program search support vector machines, unwise of matlab tool
Feel coefficient ε and core width system σ optimized parameter, determines model parameter.
4) support vector machines is based on the typical neural network of Statistical Learning Theory building, it is by establishing a most optimal sorting
Class hyperplane, so that the distance between two class samples of the plane two sides maximize, to provide classification problem general well
Change ability.It is obtained and the higher training sample composing training collection (x of the sample degree of association to be evaluated by step 3)i,yi), i=1,
2 ..., n indicates i-th group of data, and n is the number of the training sample screened, wherein xiIndicate i-th group of training sample;Its
Middle yi∈ {+1, -1 }, yi∈ {+1, -1 }, yi=+1 to represent i-th group of sample be that there are the sample of disconnecting link secondary circuit failure, yi
=-1 represents i-th group of sample as the normal sample of disconnecting link secondary circuit.It then, is normal by hyperplane equation wx+b=0, b
Number, x is the x in training sample, and w is coefficient, and sample is divided into two classes:
The optimal hyperlane of support vector machines is one and makes the maximum hyperplane of classifying edge, i.e., so thatMaximum,
So solving optimal hyperlane, i.e. objective function is
It is a function of definition, in order to askMaximum value, its inverse is defined asAbove formula should expire
Sufficient constraint condition: yi(w·xi+ b) -1 >=0, i=1,2 ..., n.
It but is frequently not that all training samples can free from errors carry out linear function fit, therefore, formula at precision ε
(5) it is converted into following formula, i.e.,
Non-negative slack variable ξ is introduced in formulaiAnd ξi *To measure the departure degree ε of training sample, fault-tolerant punishment system is constructed
Number C exceeds the sample punishment degree of error, above formula constraint condition to control
Majorized function above is a typical quadratic programming problem, introduces Lagrange multiplier αi,ηi (glug
Constant used in bright daily process) it obtains
In order to seek the solution of above equation, by Γ to each variable derivation, extreme point is found out, that is, asks optimal solution to have
According to Lagrange duality principle, above-mentioned objective function equivalency transform is
Above formula meets condition
For nonlinear situation, generallys use kernel function K appropriate and achieved that instead of the inner product of vectors in higher dimensional space
Linear fit after a certain linear transformation, the present invention have determined the fault-tolerant penalty coefficient of support vector machines by Gridregression
C and core width system σ optimized parameter, and then using the calculating of function train-svm in the tool box LIBSVM, deviation can be obtained
B and Lagrange coefficient α, α*, to obtain the prediction model such as following formula:
X in formulaiFor training sample, i=1,2 ..., n, x are sample to be evaluated, and K is kernel function, the present inventionAnd training sample and sample to be evaluated are 6 dimension data types.
5) according to trained prediction model formula (12), sample data to be evaluated is inputted into function in the tool box SVM
Predict-svm is calculated, and is completed prediction to sample to be evaluated, is exported and think disconnecting link normal operation for -1, if output for+
1 is thought disconnecting link there are failure, i.e., carries out malfunction elimination in advance in combination with power failure plan.
Applicating example
According to certain districts and cities' corporate history operating condition, 300 groups of training samples of export, 60 groups of samples to be evaluated are arranged.Training
260 groups of normal condition in sample, 40 groups of malfunction;45 groups of normal condition in sample to be evaluated, 15 groups of malfunction.
The present invention is first according to step 1)~3) by above-mentioned training sample composing training collection be { (x1,y1),(x2,
y2),...,(x300,y300), wherein xi∈R6,yi={ 1, -1 }, works as yiWhen=1, indicate that there are disconnecting link secondary returnings for i-th of sample
Road failure, works as yiWhen=- 1, indicate that i-th of sample disconnecting link secondary circuit is normal.Then, it is used by step 4)
Gridregression has determined the fault-tolerant penalty coefficient C of support vector machines, insensitive coefficient ε and core width system σ optimized parameter,
Respectively 65,0.032,7.Then according to step 5), prediction model is calculated by function train-svm in the tool box SVM
Sample data to be evaluated is inputted function in the tool box SVM finally, combining prediction model according to step 6) by cctrain.model
Predict-svm calculates prediction result, as shown in table 1 below.
1 disconnecting link secondary circuit failure prediction result of table
Whole accuracy is to predict the ratio of correct sample number and total forecast sample number in upper table.As shown in Table 1, the invention
To the accuracy of disconnecting link secondary circuit failure prediction than directly predict accurately with all samples after meter and related coefficient
Rate wants high, shows to predict to be feasible, efficient to disconnecting link secondary circuit failure.
The above is only a specific embodiment of the present invention, but the design concept of the present invention is not limited to this, all to utilize this
Design makes a non-material change to the present invention, and should all belong to behavior that violates the scope of protection of the present invention.
Claims (6)
1. substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient, which comprises the steps of:
1) the installation producer of export disconnecting link account is arranged from PMS account system, the operation time limit, maintenance number, running environment, is matched
Electric installation pattern undertakes the big major influence factors data of load condition six as historical data, and to installation producer, operation ring
Border, power distribution equipment pattern carry out pretreatment and obtain consistent monotonicity, and normalizing is in numberical range [0,1], then will fortune
The row time limit, overhaul number, undertake load condition and normalization after installation producer, running environment and power distribution equipment pattern be as instruction
Practice sample;
2) training sample and sample to be evaluated are carried out related coefficient calculating will be less than threshold value according to related coefficient given threshold
Training sample reject, filter out and the higher sample of the sample degree of association to be evaluated;
3) for the training sample filtered out, supporting vector is determined using the Gridregression program search of matlab tool
Fault-tolerant penalty coefficient C, the insensitive coefficient ε and core width system σ optimized parameter of machine;
4) it is calculated using function train-svm in the tool box LIBSVM, obtains deviation b and Lagrange coefficient α, α*, thus
Obtain the prediction model such as following formula:
X in formulaiFor the training sample filtered out, i=1,2 ..., n, n are the number of the training sample filtered out, and x is to be evaluated
Sample, K are kernel function,
And training sample and sample to be evaluated are 6 dimension data types;
5) sample to be evaluated is predicted using prediction model, exports and thinks disconnecting link normal operation for -1, if output is+1
Thinking disconnecting link, there are failures, i.e., carry out malfunction elimination in advance in combination with power failure plan.
2. substation's disconnecting link secondary circuit failure prediction technique of meter as described in claim 1 and related coefficient, feature exist
In as follows to the pretreatment of the installation producer in step 1):
According to the installation producer in this area under one's jurisdiction power grid physical fault quantity gi, in conjunction with installation related in PMS account system, producer is set
Standby sum Ci, define producer health degree ηi
I=1 in formula, 2 ..., m, m are that the installation producer quantity of failure occurred in equipment, and provided do not occurred the peace of failure temporarily
Filling producer's health degree is 0.
3. substation's disconnecting link secondary circuit failure prediction technique of meter as described in claim 1 and related coefficient, feature exist
In as follows to the pretreatment of the running environment in step 1): the case where specified devices are run outdoors is 1, indoors
Situation is 0.
4. substation's disconnecting link secondary circuit failure prediction technique of meter as described in claim 1 and related coefficient, feature exist
In as follows to the pretreatment of the power distribution equipment pattern in step 1): regulation AIS equipment is 1, GIS device 0.
5. substation's disconnecting link secondary circuit failure prediction technique of meter as described in claim 1 and related coefficient, feature exist
In in step 1), the normalization makes numberical range be in [0,1], referring to as follows:
I=1 in formula, 2 ..., k indicate i-th group of data, and k is the sum of training sample, and j=1,2 ..., 6 indicates jth dimension
According to minIj、maxIjRespectively indicate the minimum value and maximum value of all training sample jth dimension datas, Iij、I′ijI-th group of sample respectively
This jth dimension data indicates each influence factor numerical value and the numerical value after normalizing after pretreatment.
6. substation's disconnecting link secondary circuit failure prediction technique of meter as described in claim 1 and related coefficient, feature exist
In, correlation coefficient ρ range described in step 2) be [- 1 ,+1], the threshold value P=| ρ |, correlation coefficient ρ calculation formula is such as
Under:
In formula, XiFor i-th of index in sample to be evaluated, YiFor i-th of index in training sample,For sample to be evaluated
In all indexs average value,For the average value of indexs all in training sample, N is sample middle finger target number, N=6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810870505.1A CN109061453A (en) | 2018-08-02 | 2018-08-02 | Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810870505.1A CN109061453A (en) | 2018-08-02 | 2018-08-02 | Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109061453A true CN109061453A (en) | 2018-12-21 |
Family
ID=64832867
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810870505.1A Pending CN109061453A (en) | 2018-08-02 | 2018-08-02 | Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109061453A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110048430A (en) * | 2019-05-08 | 2019-07-23 | 国网福建省电力有限公司莆田供电公司 | A kind of voltage-sensitive consumer networks weak spot recognition methods |
CN110287640A (en) * | 2019-07-03 | 2019-09-27 | 辽宁艾特斯智能交通技术有限公司 | Life prediction method, apparatus, storage medium and the electronic equipment of lighting apparatus |
CN111398865A (en) * | 2020-04-17 | 2020-07-10 | 国网福建省电力有限公司 | Transient current-based transformer secondary circuit inspection method |
CN112114214A (en) * | 2020-09-08 | 2020-12-22 | 贵州电网有限责任公司 | Transformer fault diagnosis method |
CN113408441A (en) * | 2021-06-24 | 2021-09-17 | 武汉理工大学 | Track bed fault early warning method based on DRSN and person correlation coefficient |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103955759A (en) * | 2014-04-18 | 2014-07-30 | 国家电网公司 | Photovoltaic power generation power short-term prediction method by adopting composite data source based on radial basis kernel function support vector machine |
CN105203876A (en) * | 2015-09-15 | 2015-12-30 | 云南电网有限责任公司电力科学研究院 | Transformer on-line monitoring state assessment method utilizing support vector machine and correlation analysis |
CN106646165A (en) * | 2016-12-23 | 2017-05-10 | 西安交通大学 | Method and system for classifying and positioning internal insulation defects of GIS |
CN106650037A (en) * | 2016-11-30 | 2017-05-10 | 国网江苏省电力公司盐城供电公司 | State diagnosis method of lightning arrester based on support vector machine regression |
CN107733089A (en) * | 2017-11-10 | 2018-02-23 | 国网福建省电力有限公司 | A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM |
-
2018
- 2018-08-02 CN CN201810870505.1A patent/CN109061453A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103955759A (en) * | 2014-04-18 | 2014-07-30 | 国家电网公司 | Photovoltaic power generation power short-term prediction method by adopting composite data source based on radial basis kernel function support vector machine |
CN105203876A (en) * | 2015-09-15 | 2015-12-30 | 云南电网有限责任公司电力科学研究院 | Transformer on-line monitoring state assessment method utilizing support vector machine and correlation analysis |
CN106650037A (en) * | 2016-11-30 | 2017-05-10 | 国网江苏省电力公司盐城供电公司 | State diagnosis method of lightning arrester based on support vector machine regression |
CN106646165A (en) * | 2016-12-23 | 2017-05-10 | 西安交通大学 | Method and system for classifying and positioning internal insulation defects of GIS |
CN107733089A (en) * | 2017-11-10 | 2018-02-23 | 国网福建省电力有限公司 | A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM |
Non-Patent Citations (2)
Title |
---|
刘菊艳: "基于数据挖掘技术的短期风速预测", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
神显豪: "基于支持向量回归机的传感器故障诊断方法研究", 《机床与液压》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110048430A (en) * | 2019-05-08 | 2019-07-23 | 国网福建省电力有限公司莆田供电公司 | A kind of voltage-sensitive consumer networks weak spot recognition methods |
CN110287640A (en) * | 2019-07-03 | 2019-09-27 | 辽宁艾特斯智能交通技术有限公司 | Life prediction method, apparatus, storage medium and the electronic equipment of lighting apparatus |
CN110287640B (en) * | 2019-07-03 | 2023-10-13 | 辽宁艾特斯智能交通技术有限公司 | Lighting equipment service life prediction method and device, storage medium and electronic equipment |
CN111398865A (en) * | 2020-04-17 | 2020-07-10 | 国网福建省电力有限公司 | Transient current-based transformer secondary circuit inspection method |
CN111398865B (en) * | 2020-04-17 | 2022-07-05 | 国网福建省电力有限公司 | Transient current-based transformer secondary circuit inspection method |
CN112114214A (en) * | 2020-09-08 | 2020-12-22 | 贵州电网有限责任公司 | Transformer fault diagnosis method |
CN113408441A (en) * | 2021-06-24 | 2021-09-17 | 武汉理工大学 | Track bed fault early warning method based on DRSN and person correlation coefficient |
CN113408441B (en) * | 2021-06-24 | 2022-06-10 | 武汉理工大学 | Track bed fault early warning method based on DRSN and person correlation coefficient |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109061453A (en) | Substation's disconnecting link secondary circuit failure prediction technique of meter and related coefficient | |
Liu et al. | A systematic approach for dynamic security assessment and the corresponding preventive control scheme based on decision trees | |
CN103337043B (en) | The method for early warning of electric power communication device running status and system | |
CN108320043A (en) | A kind of distribution network equipment state diagnosis prediction method based on electric power big data | |
CN110322135A (en) | A kind of method for real-time monitoring and system of grid equipment safe operation state | |
CN102496069A (en) | Cable multimode safe operation evaluation method based on fuzzy analytic hierarchy process (FAHP) | |
CN104200288A (en) | Equipment fault prediction method based on factor-event correlation recognition | |
CN107256449A (en) | A kind of relay protection device of intelligent substation state evaluation and appraisal procedure | |
CN104408562A (en) | Photovoltaic system generating efficiency comprehensive evaluation method based on BP (back propagation) neural network | |
CN111369168B (en) | Associated feature selection method suitable for multiple regulation and control operation scenes of power grid | |
CN206312210U (en) | A kind of status assessing system of Distribution Network Equipment | |
CN105447657A (en) | Risk-based operation and maintenance management system of 750KV power equipment | |
CN103699668A (en) | Power distribution network electric equipment combination state evaluation method based on data section consistency | |
CN104036434A (en) | Evaluation method for load supply capacity of power distribution network | |
CN104680254A (en) | Method for optimizing power grid planning scheme based on comprehensive cost model | |
CN106056218B (en) | The monthly Maintenance Schedule Optimization method of equipment of meter and overload and Transient Stability Constraints | |
CN107733089A (en) | A kind of transformer station's disconnecting link secondary circuit failure Forecasting Methodology based on SVM | |
CN114386753A (en) | Equipment risk comprehensive analysis early warning method based on main transformer load condition | |
CN110783913B (en) | Group-based optimal power grid topology online optimization method considering expected accident set | |
CN104484828B (en) | High-voltage electrical appliance operation quality evaluation method and system based on logistic regression | |
CN104598969B (en) | High-voltage electrical appliance operation quality evaluation method and system based on neural network | |
CN104077231B (en) | Transformer maintenance optimization method based on symbol dynamics and LS-SVM | |
CN107292759A (en) | Distribution network planning based on power supply reliability calculates analysis system | |
CN108921438A (en) | A kind of power distribution network regulation and administration weak link identification method based on cascade weight | |
CN108830434A (en) | A kind of needing forecasting method of transformer equipment defect elimination goods and materials |
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: 20181221 |
|
RJ01 | Rejection of invention patent application after publication |