CN110333414A - The multi-level state evaluating method of power transformer - Google Patents
The multi-level state evaluating method of power transformer Download PDFInfo
- Publication number
- CN110333414A CN110333414A CN201910711762.5A CN201910711762A CN110333414A CN 110333414 A CN110333414 A CN 110333414A CN 201910711762 A CN201910711762 A CN 201910711762A CN 110333414 A CN110333414 A CN 110333414A
- Authority
- CN
- China
- Prior art keywords
- index
- fault type
- transformer
- formula
- membership
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/257—Belief theory, e.g. Dempster-Shafer
Abstract
The invention discloses a kind of multi-level state evaluating methods of power transformer.Construct first can faults type and position transformer multi_tier architecture, after index screening, by seek index impairment grade and carry out Gauss cloud processing reflection criterion boundaries uncertainty；It handles to obtain uncertainty of the comprehensive weight to reflect weight by correlation rule and variable weight；More evidence fusions, which are carried out, with DSmT solves the high conflicting of assessment layer and uncertain problem.Finally obtain the fault type, trouble location and transformer entirety status of the equipment.It solves the uncertain problem that transformer generates in evaluation process, by fault diagnosis in conjunction with health evaluating, can also find the failure that transformer occurs in terms of details from the holistic health for macroscopically seeing transformer.
Description
Technical field
The present invention relates to a kind of Condition Assessment for Power Transformer method more particularly to a kind of power transformer multilayer next states
Appraisal procedure belongs to power supply technique field.
Background technique
Power transformer is the important equipment in power transmission and transformation and power supply-distribution system, safety and stability of the operating status to power grid
Operation has an important influence.In the longtime running of transformer, the exception of operating status is inevitably had, to power transformer
Device carries out accurate operating status assessment, is conducive to going on smoothly for Condition Maintenance Method of Transformer work, makes reasonable maintenance
Strategy.
With the investment to deepen continuously with a large amount of online detection instruments that current state maintenance is carried out, state's net and each province's equipment
Also carrying out the real-time of equipment, dynamic analysis in status assessment, oneself becomes the work of normalization, the repair status of power system device
It has obtained certain improvement, while also having exposed that the equipment state assessment period is long, information analysis is insufficient, real-time is not strong etc. to ask
Topic.Currently with the fast development of power industry, the data in power industry database are in that explosive formula increases, such as account letter
Breath, inspection information, live detection and online monitoring data, off-line testing data etc., have had Develop Data analysis and data are dug
The data basis of work is dug, conventional data processing and statistical analysis technique are awkward, do not adapt to power network development
It is required that.Currently, Transformer State Assessment system lays particular emphasis on the warning of a certain index exceeding standard mostly, it can only reflect the part of transformer
Situation fails combination using multi-source information and realizes that transformer dynamic comprehensive is assessed, transformer station high-voltage side bus and status information is caused to disperse
In multiple information platforms and these platforms are relatively independent, are unfavorable for various dimensions, multidata analysis and the displaying of information, unfavorable
Understand and evaluate in depth of the O&M appraiser to transformer state.
Therefore, it needs to carry out transformer state multi-source information statistical analysis and data mining technology, running state of transformer
Dynamic evaluation and Predicting Technique research, provide reference for Condition Maintenance Method of Transformer, provide for power grid security, reliably with economical operation
It ensures, and there is highly important engineering use value and good application prospect.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of multi-level state evaluating methods of power transformer.
In order to solve the above technical problems, the technical solution adopted by the present invention is that:
A kind of multi-level state evaluating method of power transformer, comprising the following steps:
Step 1: data acquisition: acquisition power transformer ontology, casing, load ratio bridging switch, chiller system, non electrical quantity
The on-line monitoring index of protective device exports same type transformer identical with the power transformer running environment in database
Historical failure data library, on-line monitoring index are as shown in table 1；
Step 2: the fusion of indicator layer degree of membership: comprising the following specific steps
Step 2-1: each index is subjected to degradation treatment:
Increase tendency is presented in numerical value when forward direction deterioration index deteriorates, and numerical value, which is presented, when negative sense cracking index deteriorates reduces
Trend；
Forward direction deterioration index is handled by formula (1):
Negative sense deterioration index is handled by formula (2):
In formula, XrtFor the impairment grade after the t index normalization of r fault type, 0 < r≤n, n is of fault type
Number, 0 < r≤T, T indicate the index number of r fault type；XrtFor the measured value of the t index of r fault type, Xrt0For
The initial value of the t index of r fault type, XrtaFor the warning value of the t index of r fault type；
Step 2-2: calculate membership vector: power transformer health status divides four grades, with index impairment grade pair
It should be related to as shown in table 2；
Gauss cloud is distributed y are as follows:
In formula: xrtFor the impairment grade after the t index normalization of r fault type；EnnIt is grade cloud for a desired value
Entropy En, standard deviation HeNormal random number；Constrain the central value E in sectionxFor Ex=(cmin+cmax)/2；Double constraint spaces
[cmin, cmax] it is the gradational boundary that Gauss cloud is distributed；Grade cloud entropy EnAre as follows:
HeConstant is taken, according to the field experience of transformer state index and uncertain setting；
Step 2-3:
The normal weight coefficient of each index under the fault type is determined according to each index confidence level size, calculation formula is such as
Under:
In formula, wI, jIt is the normal weight coefficient of j-th of single index in i-th of fault type；CI, jIt is i-th of failure classes
The confidence level of j-th of single index in type；miFor the index number in i-th of fault type；
Fault correlation rule AI, j→BiConfidence calculations formula it is as follows:
Transaction database D={ any comprehensive state amount is exceeded }；
Event Ai, j={ j-th of individual event quantity of state in i-th of comprehensive state amount is exceeded }；
Event Bi={ generation of the i-th class failure }；
It include that the number of the affairs of certain specific item collection A is known as the support counting of item collection A in transaction database D,
It is denoted as σ (A), can be expressed as in Probability
Determine the variable weight coefficient of indicator layer:
In formula,For the variable weight coefficient of r kind fault type；xrFor the score value of r-th of fault type；N is failure
The number of type；wrFor the normal weight coefficient of r-th of fault type；
Introduce the variable weight formula that balance function forms variable synthesis mode are as follows:
α is balance function, 0≤α≤1, relative importance of the value size depending on each fault type in formula；When right
When the balance degree of fault type is of less demanding, α > 0.5 is taken；When excluding the major defect of certain comprehensive state amounts, α < is taken
0.5；
Step 2-4: the assessment of indicator layer fault type:
Each index and its each comprehensive weight are weighted fusion, formula is as follows:
Wherein, Flsd(r)For the membership vector of r-th of fault type,For m-th of index in r-th of fault type
Comprehensive weight,For the degree of membership of m-th of index in r-th of fault type.
The distribution situation of corresponding four state grades of degree of membership of indicator layer fault type can be obtained, the table of comparisons 2 judges respectively
Fault type serious conditions；
Step 3: the assessment of component layer fault type: the degree of membership of indicator layer fault type being subjected to DSmT algorithm by component and is melted
It closes, obtains the degree of membership of component layer fault type, the table of comparisons 2 judges the health status of each component；
Step 4: integrality assessment: the degree of membership of component layer fault type being subjected to DSmT algorithm fusion, obtains entirety
The degree of membership of fault type, the table of comparisons 2 judge the health status of each component.
Have the technical effect that solve transformer generates not in evaluation process acquired by by adopting the above technical scheme
Certain problem can also can by fault diagnosis in conjunction with health evaluating from the holistic health for macroscopically seeing transformer
The failure that transformer occurs is found in terms of details.
Detailed description of the invention
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
Fig. 1 is evaluation system figure of the invention,
Fig. 2 is Gauss cloud model figure.
Specific embodiment
Embodiment 1:
A kind of multi-level state evaluating method of power transformer, comprising the following steps:
Step 1: data acquisition: acquisition power transformer ontology, casing, load ratio bridging switch, chiller system, non electrical quantity
The on-line monitoring index of protective device exports same type transformer identical with the power transformer running environment in database
Historical failure data library, on-line monitoring index are as shown in table 1；
Step 2: the fusion of indicator layer degree of membership: comprising the following specific steps
Step 2-1: each index is carried out degradation treatment: the index of transformer is numerous and magnitude is different, using opposite deterioration
Degree is to the processing of being normalized of index.According to it by being normally to increase or reduce into abnormal deterioration process, can be divided into
Forward direction deterioration index deteriorates index with negative sense.Forward direction deterioration index refers to that the index value increases when transformer index deteriorates
Trend, for example, iron core grounding current, furfural content etc.；Negative sense cracking index expression numerical value when the index deteriorates is to present to subtract
Small trend, such as D.C. resistance.
Index is deteriorated for forward direction, is handled by formula (1):
Index is deteriorated for negative sense, is handled by formula (2):
In formula, XrtFor the impairment grade after the t index normalization of r fault type, 0 < r≤n, n is of fault type
Number, 0 < r≤T, T indicate the index number of r fault type；XrtFor the measured value of the t index of r fault type, Xrt0For
The initial value of the t index of r fault type, XrtaFor the warning value of the t index of r fault type.The reference of warning value value
DL/T 596-1996 " power equipment preventive trial regulation ", when only providing demand value in regulation, forward direction deterioration index multiplies 1.3,
Negative sense deteriorates index and is scaled warning value divided by 1.3.
Step 2-2: it calculates membership vector: each index being calculated based on Gauss cloud model and corresponds to being subordinate to for each grade cloud model
Spend vector；According to " oil-immersed transformer (reactor) state evaluation directive/guide ", assessment power transformer health status is divided four
A grade, it is as shown in table 2 with index impairment grade corresponding relationship.
In probability statistics, Gaussian Profile is a kind of extremely important, probability distribution for being most widely used.Gauss is subordinate to letter
Number is subordinating degree function most-often used in fuzzy theory.Gauss cloud model utilizes Gaussian Profile to realize water dust quantitative values twice
Distribution, while random degree of certainty is realized using Gauss subordinating degree function.
If U is the quantitative domain that an exact numerical indicates,It is the qualitativing concept on U.If quantitative values
xrt∈ U, and xrtIt is a Stochastic implementation of qualitativing concept C, xrtObey withFor expectation, EnnFor the Gaussian Profile of variance, i.e.,
xrt~N (Exrt, Enn), wherein EnnIt obeys again with EnFor expectation, HeFor the Gaussian Profile of variance, i.e. Enn~N (En, He), quantitative values
xrtDegree of certainty to qualitativing concept C is
Then xrtDistribution on domain U is known as Gauss cloud.
(3) in formula: xrtFor the impairment grade after the t index normalization of r fault type；En、HeRefer to for the assessment
The mathematical feature value of certain corresponding standard class of mark；EnnIt is grade cloud entropy E for a desired valuen, standard deviation HeNormal state
Random number.
According to the desired definition of cloud, gradational boundary is considered as double constraint space [c by traditional Clouds theorymin, cmax], it is considering
On the basis of the uncertainty of constraint space boundary value, the central value for constraining section can indicate the grade conception, therefore,
Calculation formula beHeConstant is usually taken, it can also be according to the scene of transformer state index
Experience is finely adjusted with uncertainty；For grade cloud entropy EnValue, herein using be based on " 3En" rule cloud entropy calculating side
Method, it is clear that the adjacent rank cloud obtained by this method separates in boundary, embodies the independence of grade classification, calculation method
It is as follows:
Index of correlation can be calculated with above-mentioned Gauss cloud correlation function formula to obtained impairment grade before and correspond to four
The subordinating degree function of state grade.
Step 2-3: it determines the comprehensive weight of each assessment layer: each index of transformer being calculated based on correlation rule and corresponds to each event
The confidence level of barrier type handles to obtain each index comprehensive weight by variable weight according to confidence calculations objective weight；
In Transformer State Assessment, weight setting is of crucial importance, is analyzed based on a large amount of fault cases, passes through association
Rule determines that objective weight meets transformer reality, but the different faults situation of transformer needs to dash forward in assessment result
Out, and the uncertainty study of weight can by weight adjust embody different faults assessment result distinguish so that assessment
As a result it can more correspond to actual needs.
Correlation rule is by finding the correlation between the different indexs that a things occurs, it is based on data mining,
The subset of the index or attribute that frequently occur with the event is found out by statistical law and the association between them is closed
System.According to the definition of correlation rule, transaction database is denoted as D, and D is the set of subset affairs δ, D={ δ1, δ2... δN, N is number
According to the number of subset affairs in library.Certain subset affairs is denoted as δi={ γ1, γ2... γN, γ is known as item.If D={ γ1,
γ2... γjIt is all in D set, any subset A of X is known as item collection, | A | then set A is referred to as K item collection to=K.In affairs
In database D, includes that the number of the affairs of certain specific item collection A is known as the support counting of item collection A, σ (A) is denoted as, general
It can be expressed as in rate
Correlation rule support and confidence calculations between general two events.Support definition assumes that item collectionAndThe support of correlation rule A → B is the percentage in database D comprising A ∪ B,
It is denoted as
Sup (A → B)=P (A ∪ B) (5)
At this point, the relationship that support closer to 1, then shows that A causes B to occur is stronger.
The confidence level of correlation rule A → B is comprising A while also general comprising the percentage of B, that is, condition in database D
Rate P (B | A), it is denoted as
Confidence level characterizes the degree of reliability of correlation rule, i.e. confidence level is higher, shows the credible journey that A also occurs when B occurs
It spends higher.
Therefore, in Transformer State Assessment, such as want the severity for describing failure by the deterioration of index, need to use
Confidence level judges the objective weight of the corresponding index of each fault type, that is to say, that a certain index confidence level is higher, then
Influence when it is deteriorated to failure is bigger.
The calculation method for the confidence level that index each for transformer corresponds to fault type is as follows:
Transaction database D={ any comprehensive state amount is exceeded }；
Event AI, j={ j-th of individual event quantity of state in i-th of comprehensive state amount is exceeded }；
Event Bi={ generation of the i-th class failure }.
In this paper system, when to a certain failure and index analysis, database D, that is, item collection B, therefore can be obtained by formula (7), certain
Fault correlation rule AI, i→BiConfidence calculations formula it is as follows:
The confidence level of single index in each fault type is calculated by above formula, then to each index in same fault type
Confidence level is compared, and the normal weight coefficient of each index under the fault type is determined according to each index confidence level size, meter
It is as follows to calculate formula:
In formula, wI, jIt is the normal weight coefficient of j-th of single index in i-th of fault type；CI, jIt is i-th of failure classes
The confidence level of j-th of single index in type；miFor the index number in i-th of fault type.
The application of correlation rule, the weight for enabling each index to correspond to failure are more bonded reality, avoid excessively
Rely on subjective experience, but often weight coefficient tend not to it is prominent when a certain index variation abnormality is serious it is caused it is serious after
Therefore fruit relies solely on the case where normal weight coefficient can not be suitable for transformer a certain major cycle.
Variable weight theory is that one in theory of factors space is widely used and important modeling principle, in the comprehensive of transformer
It closes in health evaluating and introduces variable weight formula:
In formula,For the variable weight coefficient of r kind fault type；xrFor the score value of r-th of fault type；N is failure
The number of type；wrFor the normal weight coefficient of r-th of fault type；
Balance function is introduced to form variable synthesis mode, variable weight formula is
α is balance function, 0≤α≤1, relative importance of the value size depending on each fault type in formula (10).
When the balance degree to fault type is of less demanding, α > 0.5 is taken；When excluding the major defect of certain comprehensive state amounts, take
α < 0.5；As α=1, it is equal to normal weight pattern.
By introducing variable weight coefficient, so that it may when the deterioration of a certain index is serious, the weight system of this index of adjust automatically
Number, can more characterize the deterioration state of transformer at this time, meet actual demand.
Step 2-4: the assessment of first layer fault type:
Each index and its each comprehensive weight are weighted fusion, formula is as follows:
Wherein, F1sd(r)For the membership vector of r-th of fault type,For m-th of index in r-th of fault type
Comprehensive weight,For the degree of membership of m-th of index in r-th of fault type.
The distribution situation that corresponding four state grades of degree of membership of fault type can be obtained, to judge that each fault type is tight
Weight situation.
Step 3: the assessment of second layer unit status:
It handles to obtain the comprehensive weight of each fault type and component by variable weight on the basis of the power such as each fault type；It will
The fault type degree of membership that first layer is assessed obtains the health status grade of each component of transformer by DSmT algorithm fusion
Degree of membership distribution situation, to judge the health status of each component.
DSmT is a kind of new fuzzy contradiction inference theory proposed by Dezert and Smarandache, be can be regarded as
The natural extension of D-S evidence theory (Dempster-Shafer Theory), but there is important differences between the two.
DSmT can handle insurmountable uncertain, height conflict and inaccurate information source the fusion problem of D-S.When between information source
Conflict it is very big when, DST often occur generating after can not merging or merging antinomy as a result, just to have played its excellent by DSmT at this time
Gesture.
DSmT is defined as follows:
1) broad sense identification framework: Θ={ θ is set0, θ1... θnIdentification frame as fusion problem, it is to be made of n element
Nonempty set.Identification framework element in transformer fault diagnosis corresponds to different fault types.
2) ultrapower integrates: as the set for all combinations of sentences that proposition in Θ is made up of the operation of ∪ and ∩ operator.
3) broad sense brief inference function: in Θ, there are one group of mapping m (): DΘ→ [0,1]
Meet the following conditions
Then m (A) is referred to as brief inference function of the A in broad sense identification framework Θ.
In transformer fault diagnosis, the DSmT model constrained using complete exclusiveness, just for single-element θnIt carries out
Reliability assignment.Decision operation is merged to simplify, the method reallocated using conflicting information according to each single burnt first confidence level, i.e.,
PCR (Proportional Conflict Redistribution) is theoretical.Simultaneously in view of the difference of quantity of state needed for merging
Weight, so the PCR6 rule required using most accurate and satisfaction fusion.Improvement DSmT fusion formula after weight is added is as follows:
Wherein,M ' ()=Wm (), m () are brief inference
Function；W is the weight of evidence source, the comprehensive weight of each quantity of state needed for merging herein, due to changing in fusion process
The weight for having become quantity of state, may result in the sum of reliability not is 1, needs that place is normalized to DSmT output result at this time
Reason；For the classification subset in frame Θ, k is the number of evidence source, σi=1,2 ..., i ..., k, and σiIt is satisfied with
In the polynary complex information source of transformer, each assessment level of transformer can all generate certain ambiguity,
Uncertain and conflicting, especially in assessment of failure level, so can effectively solve high conflicting transformer using DSmT
Fusion problem between the constituted evidence body in multiple information source.
Step 4: the assessment of third layer transformer integrality:
It handles to obtain the comprehensive weight of each fault type and component by variable weight on the basis of the power such as each component of transformer；
The component health status degree of membership that the second layer is assessed obtains the health status of transformer entirety by DSmT algorithm fusion
Membership function distribution situation, to judge health status locating for entirety.
Table 1
The classification of 2 transformer state of table
Claims (1)
1. a kind of multi-level state evaluating method of power transformer, it is characterised in that: the following steps are included:
Step 1: data acquisition: acquisition power transformer ontology, casing, load ratio bridging switch, chiller system, non-ionizing energy loss
The on-line monitoring index of device exports same type transformer history identical with the power transformer running environment in database
Mishap Database, on-line monitoring index are as shown in table 1；
Step 2: the fusion of indicator layer degree of membership: comprising the following specific steps
Step 2-1: each index is subjected to degradation treatment:
Increase tendency is presented in numerical value when forward direction deterioration index deteriorates, and numerical value, which presents to reduce, when negative sense cracking index deteriorates becomes
Gesture；
Forward direction deterioration index is handled by formula (1):
Negative sense deterioration index is handled by formula (2):
In formula, XrtFor the impairment grade after the t index normalization of r fault type, 0 < r≤n, n are the number of fault type, 0
< t≤T, T indicate the index number of r fault type；XrtFor the measured value of the t index of r fault type, Xrt0For r event
Hinder the initial value of the t index of type, XrtaFor the warning value of the t index of r fault type；
Step 2-2: calculate membership vector: power transformer health status divides four grades, corresponding with index impairment grade to close
System is as shown in table 2；
Gauss cloud is distributed y are as follows:
In formula: xrtFor the impairment grade after the t index normalization of r fault type；EnnIt is grade cloud entropy E for a desired valuen、
Standard deviation is HeNormal random number；Constrain the central value E in sectionxFor Ex=(cmtn+cmax)/2；Double constraint space [cmtn,cmax]
For the gradational boundary of Gauss cloud distribution；Grade cloud entropy EnAre as follows:
HeConstant is taken, according to the field experience of transformer state index and uncertain setting；
Step 2-3: determining the normal weight coefficient of each index under the fault type according to each index confidence level size, calculates public
Formula is as follows:
In formula, wt,jIt is the normal weight coefficient of j-th of single index in i-th of fault type；Ct,jIt is in i-th of fault type
J-th of single index confidence level；mtFor the index number in i-th of fault type；
Fault correlation rule Ai,j→BiConfidence calculations formula it is as follows:
Transaction database D={ any comprehensive state amount is exceeded }；
Event Ai, j={ j-th of individual event quantity of state in i-th of comprehensive state amount is exceeded }；
Event Bi={ generation of the i-th class failure }；
In transaction database D, includes that the number of the affairs of certain specific item collection A is known as the support counting of item collection A, be denoted as
σ (A), can be expressed as in Probability
Determine the variable weight coefficient of indicator layer:
In formula,For the variable weight coefficient of r kind fault type；xrFor the score value of r-th of fault type；N is fault type
Number；wrFor the normal weight coefficient of r-th of fault type；
Introduce the variable weight formula that balance function forms variable synthesis mode are as follows:
α is balance function, 0≤α≤1, relative importance of the value size depending on each fault type in formula；When to failure
When the balance degree of type is of less demanding, α > 0.5 is taken；When excluding the major defect of certain comprehensive state amounts, α < 0.5 is taken；
Step 2-4: the assessment of indicator layer fault type:
Each index and its each comprehensive weight are weighted fusion, formula is as follows:
Wherein, Flsd(r)For the membership vector of r-th of fault type,For in r-th of fault type m-th index it is comprehensive
Weight is closed,For the degree of membership of m-th of index in r-th of fault type；
The distribution situation of corresponding four state grades of degree of membership of indicator layer fault type is arrived as available from the above equation, and the table of comparisons 2 judges
Each fault type serious conditions；
Step 3: the assessment of component layer fault type: pressing component for the degree of membership of indicator layer fault type and carry out DSmT algorithm fusion,
The degree of membership of component layer fault type is obtained, the table of comparisons 2 judges the health status of each component；
Step 4: integrality assessment: the degree of membership of component layer fault type being subjected to DSmT algorithm fusion, obtains overall failure
The degree of membership of type, the table of comparisons 2 judge the health status of each component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910711762.5A CN110333414A (en) | 2019-08-02 | 2019-08-02 | The multi-level state evaluating method of power transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910711762.5A CN110333414A (en) | 2019-08-02 | 2019-08-02 | The multi-level state evaluating method of power transformer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110333414A true CN110333414A (en) | 2019-10-15 |
Family
ID=68148345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910711762.5A Pending CN110333414A (en) | 2019-08-02 | 2019-08-02 | The multi-level state evaluating method of power transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110333414A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179576A (en) * | 2019-11-15 | 2020-05-19 | 国网江苏省电力有限公司 | Power utilization information acquisition fault diagnosis method and system with inductive learning function |
| CN111832730A (en) * | 2020-07-09 | 2020-10-27 | 西安交通大学 | Reliability characterization and state identification method for uncertain oil state |
| CN111832731A (en) * | 2020-07-09 | 2020-10-27 | 西安交通大学 | Multi-index monitoring method for representing uncertain state of oil and diagnosing faults |
| CN112486057A (en) * | 2020-11-03 | 2021-03-12 | 江苏核电有限公司 | Dry-type transformer multi-information-quantity online comprehensive monitoring method and system |
| CN113221441A (en) * | 2020-12-24 | 2021-08-06 | 山东鲁能软件技术有限公司 | Method and device for health assessment of power plant equipment |
| CN113449456A (en) * | 2021-07-07 | 2021-09-28 | 国网河北省电力有限公司电力科学研究院 | Health state assessment method for power transformer under incomplete multi-mode information |
| CN113888061A (en) * | 2021-12-07 | 2022-01-04 | 中国南方电网有限责任公司超高压输电公司广州局 | Method and device for evaluating running state of converter transformer |
| CN114779127A (en) * | 2022-06-22 | 2022-07-22 | 湖南科鑫电力设计有限公司 | Power transformer outgoing line short circuit impact management and control system and method thereof |
| CN114859002A (en) * | 2022-07-07 | 2022-08-05 | 山东爱福地生物股份有限公司 | Quality monitoring method and system based on wastewater monitoring data |
| CN115222255A (en) * | 2022-07-20 | 2022-10-21 | 贵州电网有限责任公司 | State evaluation method, device and medium for oil-immersed power transformer |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006126955A (en) * | 2004-10-26 | 2006-05-18 | Tokyo Electric Power Co Inc:The | Agent evaluation supporting device and method |
| CN102621421A (en) * | 2012-03-29 | 2012-08-01 | 贵阳供电局 | Transformer state evaluation method based on correlation analysis and variable weight coefficients |
| CN103605881A (en) * | 2013-10-25 | 2014-02-26 | 南昌大学 | Fault tree and analytic hierarchy process based evaluation method of state of power transformer |
| CN105911407A (en) * | 2016-04-07 | 2016-08-31 | 国网山东省电力公司电力科学研究院 | Transformer state fuzzy set pair assessment method based on matter-element augmentation extensive correlation |
| CN106780108A (en) * | 2016-11-25 | 2017-05-31 | 武汉大学 | A kind of distribution transformer state evaluating method based on improvement evidential reasoning fusion |
| CN107016500A (en) * | 2017-03-27 | 2017-08-04 | 国家电网公司 | Transformer fuzzy synthetic appraisement method based on variable weight |
| CN109816031A (en) * | 2019-01-30 | 2019-05-28 | 南京邮电大学 | A kind of Transformer State Assessment clustering method based on the unbalanced measurement of data |
-
2019
- 2019-08-02 CN CN201910711762.5A patent/CN110333414A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006126955A (en) * | 2004-10-26 | 2006-05-18 | Tokyo Electric Power Co Inc:The | Agent evaluation supporting device and method |
| CN102621421A (en) * | 2012-03-29 | 2012-08-01 | 贵阳供电局 | Transformer state evaluation method based on correlation analysis and variable weight coefficients |
| CN103605881A (en) * | 2013-10-25 | 2014-02-26 | 南昌大学 | Fault tree and analytic hierarchy process based evaluation method of state of power transformer |
| CN105911407A (en) * | 2016-04-07 | 2016-08-31 | 国网山东省电力公司电力科学研究院 | Transformer state fuzzy set pair assessment method based on matter-element augmentation extensive correlation |
| CN106780108A (en) * | 2016-11-25 | 2017-05-31 | 武汉大学 | A kind of distribution transformer state evaluating method based on improvement evidential reasoning fusion |
| CN107016500A (en) * | 2017-03-27 | 2017-08-04 | 国家电网公司 | Transformer fuzzy synthetic appraisement method based on variable weight |
| CN109816031A (en) * | 2019-01-30 | 2019-05-28 | 南京邮电大学 | A kind of Transformer State Assessment clustering method based on the unbalanced measurement of data |
Non-Patent Citations (6)
| Title |
|---|
| SHUGUO GAO: "Research into Power Transformer Health Assessment Technology Based on Uncertainty of Information and Deep Architecture Design", 《MATHEMATICAL PROBLEMS IN ENGINEERING》 * |
| 刘云鹏: "基于AdaBoost-ＲBF 算法与DSmT 的变压器故障诊断技术", 《电力自动化设备》 * |
| 刘云鹏: "采用最优云熵改进可拓云理论的变压器本体绝缘状态评估方法", 《高电压技术》 * |
| 张玉振: "基于时空信息融合的矿用变压器绝缘状态评估方法", 《工况自动化》 * |
| 徐岩: "基于合作博弈和云模型的变压器状态评估方法", 《电力自动化设备》 * |
| 许自强: "数据驱动的电力变压器智能化健康管理关键技术研究", 《中国优秀博士学位论文全文数据库 工程科技辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179576A (en) * | 2019-11-15 | 2020-05-19 | 国网江苏省电力有限公司 | Power utilization information acquisition fault diagnosis method and system with inductive learning function |
| CN111832730B (en) * | 2020-07-09 | 2022-07-26 | 西安交通大学 | Reliability characterization and state identification method for uncertain oil state |
| CN111832730A (en) * | 2020-07-09 | 2020-10-27 | 西安交通大学 | Reliability characterization and state identification method for uncertain oil state |
| CN111832731A (en) * | 2020-07-09 | 2020-10-27 | 西安交通大学 | Multi-index monitoring method for representing uncertain state of oil and diagnosing faults |
| CN112486057A (en) * | 2020-11-03 | 2021-03-12 | 江苏核电有限公司 | Dry-type transformer multi-information-quantity online comprehensive monitoring method and system |
| CN112486057B (en) * | 2020-11-03 | 2021-11-09 | 江苏核电有限公司 | Dry-type transformer multi-information-quantity online comprehensive monitoring method and system |
| CN113221441A (en) * | 2020-12-24 | 2021-08-06 | 山东鲁能软件技术有限公司 | Method and device for health assessment of power plant equipment |
| CN113449456A (en) * | 2021-07-07 | 2021-09-28 | 国网河北省电力有限公司电力科学研究院 | Health state assessment method for power transformer under incomplete multi-mode information |
| CN113449456B (en) * | 2021-07-07 | 2024-03-26 | 国网河北省电力有限公司电力科学研究院 | Health state assessment method for power transformer under incomplete multi-mode information |
| CN113888061A (en) * | 2021-12-07 | 2022-01-04 | 中国南方电网有限责任公司超高压输电公司广州局 | Method and device for evaluating running state of converter transformer |
| CN114779127A (en) * | 2022-06-22 | 2022-07-22 | 湖南科鑫电力设计有限公司 | Power transformer outgoing line short circuit impact management and control system and method thereof |
| CN114859002A (en) * | 2022-07-07 | 2022-08-05 | 山东爱福地生物股份有限公司 | Quality monitoring method and system based on wastewater monitoring data |
| CN115222255A (en) * | 2022-07-20 | 2022-10-21 | 贵州电网有限责任公司 | State evaluation method, device and medium for oil-immersed power transformer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110333414A (en) | The multi-level state evaluating method of power transformer | |
| CN105046402B (en) | A kind of state evaluating method applied to secondary equipment of intelligent converting station | |
| CN105096053B (en) | A kind of health control decision-making technique suitable for complicated technology system | |
| MIRI et al. | Application of fuzzy fault tree analysis on oil and gas offshore pipelines | |
| CN102496069B (en) | Cable multimode safe operation evaluation method based on fuzzy analytic hierarchy process (FAHP) | |
| CN109857835A (en) | A kind of adaptive network security knowledge assessment method based on cognitive diagnosis theory | |
| CN105868912A (en) | Power transformer state evaluate method and apparatus based on data fusion | |
| CN105825271B (en) | Satellite failure diagnosis and prediction method based on evidential reasoning | |
| CN105956779A (en) | Power transformer running state evaluation method and power transformer running state evaluation device | |
| CN108320043A (en) | A kind of distribution network equipment state diagnosis prediction method based on electric power big data | |
| CN105825342A (en) | Pipeline failure possibility evaluation method and system | |
| CN104077493B (en) | Method for constructing state evaluation index system of electric relaying protection system | |
| CN104677997B (en) | A kind of transformer oil chromatographic on-line monitoring differentiation method for early warning | |
| CN105242155A (en) | Transformer fault diagnosis method based on entropy weight method and grey correlation analysis | |
| CN108710756A (en) | The method for diagnosing faults of lower multicharacteristic information Weighted Fusion is analyzed based on spectral clustering | |
| CN107037306A (en) | Transformer fault dynamic early-warning method based on HMM | |
| CN108898311A (en) | A kind of data quality checking method towards intelligent distribution network repairing dispatching platform | |
| CN112906764B (en) | Communication safety equipment intelligent diagnosis method and system based on improved BP neural network | |
| CN108241901A (en) | A kind of transformer Forewarn evaluation method and device based on prediction data | |
| Erginel | Fuzzy rule-based $\tilde p $ and $ n\tilde p $ control charts | |
| CN111178725A (en) | Protective equipment state early warning method based on analytic hierarchy process | |
| CN106647650A (en) | Distributed industrial process monitoring method based variable weighting PCA (Principal Component Analysis) model | |
| CN103440410A (en) | Main variable individual defect probability forecasting method | |
| KR102379472B1 (en) | Multimodal data integration method considering spatiotemporal characteristics of disaster damage | |
| CN105741184A (en) | Transformer state evaluation method and apparatus |
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: 20191015 |
|
| RJ01 | Rejection of invention patent application after publication |