CN105843210A - Power transformer defect information data mining method - Google Patents
Power transformer defect information data mining method Download PDFInfo
- Publication number
- CN105843210A CN105843210A CN201610166386.2A CN201610166386A CN105843210A CN 105843210 A CN105843210 A CN 105843210A CN 201610166386 A CN201610166386 A CN 201610166386A CN 105843210 A CN105843210 A CN 105843210A
- Authority
- CN
- China
- Prior art keywords
- defect
- attribute
- power transformer
- defective data
- attributes
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000007418 data mining Methods 0.000 title abstract description 4
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000012217 deletion Methods 0.000 claims abstract description 5
- 230000037430 deletion Effects 0.000 claims abstract description 5
- 238000012216 screening Methods 0.000 claims abstract description 4
- 230000002950 deficient Effects 0.000 claims description 58
- 238000013480 data collection Methods 0.000 claims description 38
- 238000012545 processing Methods 0.000 claims description 7
- 230000008034 disappearance Effects 0.000 claims description 5
- 206010061619 Deformity Diseases 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000009412 basement excavation Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 238000012797 qualification Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 8
- 230000003247 decreasing effect Effects 0.000 abstract 1
- 238000013517 stratification Methods 0.000 abstract 1
- 238000012423 maintenance Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0275—Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
- G05B23/0281—Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
Landscapes
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power transformer defect data mining method. The method includes the following steps that: defect attribute screening is performed on the historical defect data set D0 of a power transformer, so that a defect data set D1 can be formed; filling or deletion is performed on defect attributes in the D1, so that noise data can be decreased; new attributes are constructed based on existing attributes of the D1, discretization is performed on continuously-valued attributes, reasonable stratification is performed on categorical attributes, and therefore, a defect data set D2 can be formed; the correlation between input attributes and target attributes is calculated, uncorrelated attributes are deleted, the remaining attributes form a defect data set D3; the association relationships between the attributes of the defect data set are calculated by using an Apriori algorithm; and effective association rules are extracted, the defect factors of the power transformer are analyzed, an association rule knowledge base can be formed. With the power transformer defect data mining method of the invention adopted, the defects of the power transformer can be mined in a multi-dimensional and multi-level manner, the association relationships between the attributes can be extracted conveniently and fast, a basis can be provided for power transformer condition evaluation, and the accuracy of condition evaluation can be improved.
Description
Technical field
The present invention relates to data mining technology field, especially relate to a kind of power transformer defect information data
Method for digging.
Background technology
Reliable and the stable operation of power system, is to ensure economic development, social progress and living standards of the people
Improve premise and the basis of required electric power.Power transformer, as power system visual plant, undertakes electric energy and passes
Defeated with distribution, voltage transformation etc. function, its operation conditions, health level directly affect the safety of power system
Property, stability and reliability.Condition-Based Maintenance Technology based on state evaluation, carries out according to state evaluation result
Actively maintenance, reasonable arrangement repair time and overhauling project, thus reduce equipment failure rate and guarantee sets
The purpose of standby reliability service.
, there is numerous, the attribute in source in the significant data basis that defect information is evaluated as Power Transformer Condition
Enrich, data volume is big, accuracy is low and redundancy high.In the past, power transformer defect information is divided
Analysis relies primarily on statistical analysis, both cannot quickly obtain high value information, can not detecting defects information attribute
Between potential incidence relation, to Operation Condition of Power Transformers evaluation lack enough support.
Summary of the invention
It is contemplated that at least solve one of above-mentioned technical problem.
To this end, it is an object of the invention to propose a kind of power transformer defective data method for digging.
To achieve these goals, embodiment of the invention discloses that a kind of power transformer defective data excavates
Method, comprises the following steps: S1: the historical defect data collection D to power transformer0Screening defect attribute,
Retain and excavate target and there may be the related data of potential association, form defective data collection D1；S2: right
Defective data collection D1In defect attribute by filling up disappearance, righting the wrong, directly delete, delete redundancy
With eliminate in discordance at least one to reduce noise data；S3: to defective data collection D1Redundancy belong to
Property by data integration and the new attribute of data transition structure, continuous attribute is carried out discretization and for point
Type attribute is layered, and forms defective data collection D2；S4: based on defective data collection D2, calculate input
Dependency between attribute and objective attribute target attribute, deletes uncorrelated attribute and constitutes defective data collection D3；S5: based on
Defective data collection D3, minimum support and min confidence are set, use Apriori algorithm to calculate number of defects
According to the incidence relation between set attribute；S6: extract efficient association rule, analyze the defect factors of power transformer,
Form correlation rule knowledge base.
Power transformator defective data method for digging according to embodiments of the present invention, by believing power transformer defect
The association mining method of breath, sets up suitable defective data collection, and the omission eliminating multi-resources Heterogeneous defective data lacks
Lose, the problem such as inconsistent and redundancy, reasonable garbled data attribute, use Apriori algorithm to realize electric power and become
The multidimensional of depressor defective data, multilamellar are excavated, and excavate the incidence relation between defect attribute, carry for state evaluation
For foundation, improve the accuracy rate that Power Transformer Condition is evaluated, it is ensured that power transformer Strategies of Maintenance is more reasonable
Effectively.
It addition, power transformator defective data method for digging according to the above embodiment of the present invention, it is also possible to have
Following additional technical characteristic:
Further, in step sl, defective data collection D1Excavation dimension including but not limited to voltage etc.
Level, manufacturer, unit type, time of putting into operation, disfigurement discovery time, defect type, defect processing are arranged
Execute with transformer station title in interior continuous, classifying type historical data.
Further, step S2 farther includes: redefine power transformer defect based on excavating target
Type, deletes the repeated defects that same equipment occurs, retains defect record first.
Further, in step s3, defective data collection D2Dimension include operation time, operating mechanism
Type, defect processing mode, defect time of origin, manufacturer's qualification, unit type, defect occur former
In cause, equipment operating environment, equipment operational site and transformer station's title at least one.
Further, step S4 farther includes: for defective data collection D2Attribute carry out feature selection,
Calculate each Attribute Significance based on the verification of card side, carry out attribute sequence according to importance value, retain importance degree high
Defect attribute in predetermined threshold value.
Further, the incidence relation using Apriori algorithm to calculate between defective data set attribute wraps further
Include: use Apriori algorithm to carry out the association rule mining between the defect correlative factor of described power transformer,
Wherein, the defect correlative factor of described power transformer includes manufacturer, runs the time limit and defect type.
The additional aspect of the present invention and advantage will part be given in the following description, and part will be retouched from following
Become obvious in stating, or recognized by the practice of the present invention.
Accompanying drawing explanation
Above-mentioned and/or the additional aspect of the present invention and advantage are from combining the accompanying drawings below description to embodiment
Will be apparent from easy to understand, wherein:
Fig. 1 is the flow chart of the power transformer defective data method for digging of one embodiment of the invention.
Detailed description of the invention
Embodiments of the invention are described below in detail, and the example of described embodiment is shown in the drawings, wherein certainly
Begin to same or similar label eventually represent same or similar element or there is the unit of same or like function
Part.The embodiment described below with reference to accompanying drawing is exemplary, is only used for explaining the present invention, and can not
It is interpreted as limitation of the present invention.
In describing the invention, it is to be understood that term " " center ", " longitudinally ", " laterally ", " on ",
D score, "front", "rear", "left", "right", " vertically ", " level ", " top ", " end ", " interior ", " outward " etc.
Orientation or the position relationship of instruction are based on orientation shown in the drawings or position relationship, are for only for ease of description
The present invention and simplification describe rather than indicate or imply that the device of indication or element must have specific side
Position, with specific azimuth configuration and operation, be therefore not considered as limiting the invention.Additionally, term
" first ", " second " are only used for describing purpose, and it is not intended that indicate or hint relative importance.
In describing the invention, it should be noted that unless otherwise clearly defined and limited, term " peace
Dress ", should be interpreted broadly " being connected ", " connection ", for example, it may be fix connection, it is also possible to be removable
Unload connection, or be integrally connected；Can be to be mechanically connected, it is also possible to be electrical connection；Can be to be joined directly together,
Can also be indirectly connected to by intermediary, can be the connection of two element internals.General for this area
For logical technical staff, above-mentioned term concrete meaning in the present invention can be understood with concrete condition.
With reference to explained below and accompanying drawing, it will be clear that these and other aspects of embodiments of the invention.At this
In a little descriptions and accompanying drawing, specifically disclose some particular implementation in embodiments of the invention, represent
Implement some modes of the principle of embodiments of the invention, but it is to be understood that the model of embodiments of the invention
Enclose not limited.On the contrary, embodiments of the invention include falling into the spirit of attached claims and interior
All changes, amendment and equivalent in the range of culvert.
First introduce utilization Apriori algorithm and relate to basic conception: correlation rule and basic conception.
What correlation rule represented is in data base does not have certain between same area and meets and specify the association required to close
The rule of system.If I={i1,i2,…inIt it is the set of item.A given item data storehouse D, the most each things
T is the set of item, meetsIf item collectionAndThen shape is such as
Implications be referred to as correlation rule, X and Y is as the premise of this correlation rule and conclusion；
The basic parameter weighing correlation rule includes support (Support), confidence level (Confidence) and promotes
Degree (Lift).
Support (support): represent the support of item collection X ∪ Y, be i.e. comprise item collection in transaction database D simultaneously
X and the ratio of item collection Y, be designated as:
In formula: | T (X ∨ Y) | represents the number of transactions simultaneously comprising X and Y；| T | represents total number of transactions.
Confidence level (confidence): represent in the affairs that X occurs in transaction database D, wrap again simultaneously
Ratio containing Y, is designated as:
Lifting degree (lift): promote confidence level and the ratio of consequent confidence level that ratio is transaction database D, be designated as:
Promoting and represent under conditions of X occurs than Lift, the conditional probability that Y occurs is that the priori that Y occurs is general
The ratio of rate.When promoting ratio more than 1, showIt is that the appearance of directive association, i.e. X is to Y
Have facilitation；As lift < 1, then show that the appearance of X reduces the probability that Y occurs.
Below in conjunction with accompanying drawing, power transformer defective data method for digging according to embodiments of the present invention is described.
Fig. 1 is the flow chart of the power transformer defective data method for digging of one embodiment of the invention.Please join
Examining Fig. 1, the power transformer defective data method for digging of the embodiment of the present invention comprises the following steps:
S1: the historical defect data collection D to power transformer0Screening defect attribute, retains and excavates target
There may be the related data of potential association, form defective data collection D1。
Specifically, based on expertise by data set D0Uncorrelated attribute delete, including " disfigurement discovery people ",
The dereferenced attribute such as " defect defect elimination people ", " accountability unit " and " entering the maintenance department time ", by preliminary sieve
Retain defect attribute 23 after choosing, constitute defective data collection D1。
S2: to defective data collection D1In defect attribute by fill up disappearance, right the wrong, directly deletion,
In deletion redundancy and elimination discordance, at least one is to reduce noise data.
Specifically, defective data collection D1In exist property value missing errors, peel off, redundancy and inconsistent etc.
Situation.For the problem existed, according to excavating target and the disappearance type of attribute, feature, its processing method
As follows:
S201: owing to different production firms equipment dependability weighed by needs, it is therefore desirable to relatively each equipment deficiency
Time of origin first, and the data having a strong impact on equipment are distributed by same equipment repeated defects so that close online
Calculation result is unreliable, therefore according to " POF ", " transformer station ", " device numbering " and " defect time of origin "
Jointly consider etc. factor, only retain first defect and by remaining redundancy defect delete.
Missing values is there is or peels off in S202: for categorical attribute, such as attribute for " power transformer model "
Value, can jointly be analyzed by the factor such as " transformer station's title ", " electric pressure " and " manufacturer " and fill up disappearance
Value or value of righting the wrong.When jointly analyzing to make up missing data by other attributes, then delete this
Record.
S3: to defective data collection D1Redundant attributes by data integration and the new attribute of data transition structure,
Discretization carried out for continuous attribute and categorical attribute is layered, forming defective data collection D2。
Specifically, defective data collection D1In part Attribute Redundancy, value density low, pass through data integration
Construct new attribute with data mapping mode, both reduced attribute dimensions, the most also promote defective data collection and express energy
Power.Concrete grammar comprises the steps:
S301: based on " defect processing measure " and " defect processing result " this two attribute item, constructs " fault location
Reason mode " defect, defect processing measure is divided into plain mode, substitute mode, comprehensive method and other
Modes etc., are divided to these four mode by multiple different disposal measure, make data be easier to understand.
S302: by " disfigurement discovery time " and " putting equipment in service time ", build " the equipment operation time limit " attribute,
And based on expertise by this continuous attribute quantification, be divided into " running time limit N < 1 year ", " within 1 year, < run
Time limit N < 5 year ", " 5 years < run time limit N < 10 year ", " 10 years < run time limit N < 15 year " " 15
Year<run time limit N<20 year " and 6 property values such as " running time limit N>20 year ".
S303: according to " device type " and " manufacturer " attribute, builds " producer's qualification " attribute and by its point
Become overseas investments " joint " " domestic " three property values.
S304: by defective data collection D1In data carry out quantifying, being layered, set up power transformer defect
Data set D2。
S4: based on defective data collection D2, calculate the dependency between input attribute and objective attribute target attribute, delete not
Association attributes constitutes defective data collection D3.It should be noted that for different excavation targets, its target
Attribute is different.
Specifically, power transformer defective data collection D2Contained attribute is the most more, by investigating between attribute
Importance, reach the purpose of the data set simplified further.The importance of attribute can join in terms of two
Closing and investigate: first, dependence self is investigated；Second, investigate with objective attribute target attribute related angle from input attribute.
Dependence is seen self, and important attribute should be that the information of carrying is many, and namely variance is bigger.According to practical situation
Formulate some standards estimating variance size, when property variance is less than specified value, be then considered as inessential.From
Input attribute is seen with objective attribute target attribute related angle, and the classification prediction of important attribute reply objective attribute target attribute has notable
Meaning.For different types of input attribute and objective attribute target attribute, the measuring method used also differs.Tool
Body situation is as shown in table 1, and table 1 is different variable test method tables.
Table 1 dissimilar variable measuring method
Owing to power transformer defect attribute is grouped as categorical attribute, therefore initially with card side's verification mode
Measure the dependency between attribute.The verification of card side belongs to statistical hypothesis testing category, relates generally to following four
Big step: propose null hypothesis, select and calculate statistic of test, determine significance level, conclusion and decision-making.
Wherein the statistic of test of block-regulations inspection is Peason chi-square statistics amount, and its data are defined as:
In formula: r is the line number of contingency table, c is the columns of contingency table；foFor observed frequency, feFor expectation
Frequency.
The significance level weighed between attribute is to be weighed by " importance degree (Importance) ".Importance
(Importance) not being the size of correlation coefficient, this value is by calculating card side system under specific significance level
The Probability p of metering, by (1-p) value between relatively each variable, thus weighs its importance；Generally this value
This variable of the biggest expression is the most important.
Importance degree I > 0.95 is set, when the importance value reservation more than 0.95, when importance degree is less than 0.9 then
Directly delete；The attribute that importance degree is high, deletes the importance degree attribute less than changed standard, forms power transformer
Device defective data collection D3。
S5: based on defective data collection D3, minimum support and min confidence are set, use Apriori to calculate
Method calculates the incidence relation between defective data set attribute.
Specifically, Apriori algorithm main flow is as follows:
Input: defect database D3；Minimum support minsup
Output: D3In all Strong association rule set R
Algorithm:
F1=find_frequent_1-itemset (D3)
For (k=2；k++)
{Ck=appriori_gen (Fk-1,minsup)；
foreachtransactiont∈D
{Ct=subset (Ck,t)；.
foreachcandidatec∈Ct
c.count++；}
ReturnF=∪kFk；
R=generate_rule (F)；
Rreturn(R)；
procedureapriori_gen(Fk-1:frequent(k-1)-itemsets)；
minsup:minimum supportthreshold)
foreachitemset f1∈Fk-1
foreachitemset f2∈Fk-1
if((f1[1]=f2[1]∧f1[2]=f2[2])∧∧f1[k-2]=f2[k-2]∧f1[k-1]<f2[k-1]))
Then{c=f1[1],f1[2],,f1[k-1],f2[k-1]}；
ifhas_infrequent_subset(c,Fk-1)then
deleteC；
elseaddcto Ck；}
returnCk；
procedurehas_infrequent_subset(c:candidatek-itmeset；Fk-1:frequent(k-1)-itemset)
foreach(k-1)-subsetsofc
returnTRUE；
elsereturnFALSE；
S6: extract efficient association rule, analyze the defect factors of power transformer, form correlation rule knowledge
Storehouse.
In an example of the present invention, using power transformer defect type as consequent, calculate based on apriori
The correlation rule that method is extracted is as shown in table 2, and table 2 is power transformator Strong association rule table.
Table 2 power transformer Strong association rule
By above table, the equipment of vendor A occurs lacking at operation time limit cooling system between 5-10
The probability fallen into is close to 90%, and when equipment state is evaluated, the weight of corresponding manufacturer associated disadvantages, scoring etc. are made
Corresponding adjustment, the O&M strategy proposing this manufacturer's power transformer equipment of being simultaneous for property.Closed by change
The preceding paragraph of connection rule and consequent attribute, cause power transformer from multi-angle, various dimensions, multi-level association analysis
Device produces defect factors.
The power transformer defective data method for digging of the embodiment of the present invention, in conjunction with the particularity of power industry,
Correlation rule is applied in the Analysis on Selecting of power transformer defect information correlation rule, proposes maintenance data
Basic ideas that power transformer defective data is analyzed by the correlation rule in digging technology and concrete
Solution.By to the extraction of Strong association rule and analysis, the state evaluation for power transformer provides ginseng
Examine foundation, state evaluation accuracy rate is higher, power transformer maintenance policy more rationally, more specific aim.
It addition, other of the power transformer defective data method for digging of the embodiment of the present invention is constituted and effect
It is the most all known, in order to reduce redundancy, does not repeats.
In the description of this specification, reference term " embodiment ", " some embodiments ", " example ",
The description of " concrete example " or " some examples " etc. means to combine this embodiment or example describes specific features,
Structure, material or feature are contained at least one embodiment or the example of the present invention.In this manual,
The schematic representation of above-mentioned term is not necessarily referring to identical embodiment or example.And, the tool of description
Body characteristics, structure, material or feature can be with properly in any one or more embodiments or example
Mode combine.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that:
These embodiments can be carried out in the case of without departing from the principle of the present invention and objective multiple change, amendment,
Replacing and modification, the scope of the present invention is limited by claim and equivalent thereof.
Claims (6)
1. a power transformer defective data method for digging, it is characterised in that comprise the following steps:
S1: the historical defect data collection D to power transformer0Screening defect attribute, retains and excavates target
There may be the related data of potential association, form defective data collection D1；
S2: to defective data collection D1In defect attribute by fill up disappearance, right the wrong, directly deletion,
In deletion redundancy and elimination discordance, at least one is to reduce noise data；
S3: to defective data collection D1Redundant attributes by data integration and the new attribute of data transition structure,
Discretization carried out for continuous attribute and categorical attribute is layered, forming defective data collection D2；
S4: based on defective data collection D2, calculate the dependency between input attribute and objective attribute target attribute, delete not
Association attributes constitutes defective data collection D3；
S5: based on defective data collection D3, minimum support and min confidence are set, use Apriori to calculate
Method calculates the incidence relation between defective data set attribute；
S6: extract efficient association rule, analyze the defect factors of power transformer, form correlation rule knowledge
Storehouse.
Power transformer defective data method for digging the most according to claim 1, it is characterised in that
In step sl, defective data collection D1Excavation dimension including but not limited to electric pressure, manufacturer,
Unit type, time of putting into operation, disfigurement discovery time, defect type, defect processing measure and transformer station's title
In interior continuous, classifying type historical data.
Power transformer defective data method for digging the most according to claim 1, it is characterised in that
Step S2 farther includes: redefines power transformer defect type based on excavating target, deletes same
The repeated defects that equipment occurs, retains defect record first.
Power transformer defective data method for digging the most according to claim 1, it is characterised in that
In step s3, defective data collection D2Dimension include operation time, operating mechanism type, defect processing
Mode, defect time of origin, manufacturer's qualification, unit type, defect occurrence cause, equipment run ring
In border, equipment operational site and transformer station's title at least one.
Power transformer defective data method for digging the most according to claim 1, it is characterised in that
Step S4 farther includes: for defective data collection D2Attribute carry out feature selection, based on card side verify
Calculate each Attribute Significance, carry out attribute sequence according to importance value, retain importance degree higher than predetermined threshold value
Defect attribute.
Power transformer defective data method for digging the most according to claim 1, it is characterised in that
The incidence relation using Apriori algorithm to calculate between defective data set attribute farther includes: use Apriori
Algorithm carries out the association rule mining between the defect correlative factor of described power transformer, wherein, described electric power
The defect correlative factor of transformator includes manufacturer, runs the time limit and defect type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610166386.2A CN105843210B (en) | 2016-03-22 | 2016-03-22 | Power transformer defect information data digging method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610166386.2A CN105843210B (en) | 2016-03-22 | 2016-03-22 | Power transformer defect information data digging method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105843210A true CN105843210A (en) | 2016-08-10 |
| CN105843210B CN105843210B (en) | 2018-11-09 |
Family
ID=56582944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610166386.2A Active CN105843210B (en) | 2016-03-22 | 2016-03-22 | Power transformer defect information data digging method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105843210B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106526352A (en) * | 2016-09-30 | 2017-03-22 | 中国电力科学研究院 | Method and system for determining power transformer fault types |
| CN106649479A (en) * | 2016-09-29 | 2017-05-10 | 国网山东省电力公司电力科学研究院 | Probability graph-based transformer state association rule mining method |
| CN107025293A (en) * | 2017-04-13 | 2017-08-08 | 广东电网有限责任公司电力科学研究院 | A kind of second power equipment defective data method for digging and system |
| CN107247995A (en) * | 2016-09-29 | 2017-10-13 | 上海交通大学 | Transmission line of electricity running status association rule mining and Forecasting Methodology based on Bayesian model |
| CN107451416A (en) * | 2017-08-28 | 2017-12-08 | 昆明理工大学 | A kind of sle auxiliary diagnostic equipment and method |
| CN107590621A (en) * | 2017-10-10 | 2018-01-16 | 清华大学 | The defects of based on adaptive Frequent Set mining method compatibility analysis method and device |
| CN109697619A (en) * | 2017-10-20 | 2019-04-30 | 中移(苏州)软件技术有限公司 | A kind of data analysing method and device |
| CN109919338A (en) * | 2019-03-22 | 2019-06-21 | 国网上海市电力公司 | The safety Analysis method of relay protection device |
| CN110442609A (en) * | 2019-08-02 | 2019-11-12 | 云南电网有限责任公司电力科学研究院 | A kind of recognition methods of secondary equipment of intelligent converting station association defect |
| CN111198924A (en) * | 2018-11-19 | 2020-05-26 | 长鑫存储技术有限公司 | Method for establishing product failure knowledge base, failure analysis method, device and medium |
| CN111797146A (en) * | 2020-07-20 | 2020-10-20 | 贵州电网有限责任公司电力科学研究院 | Big data-based equipment defect correlation analysis method |
| CN112085333A (en) * | 2020-08-06 | 2020-12-15 | 国网河南省电力公司经济技术研究院 | Power distribution network construction control index incidence relation research method based on incidence algorithm |
| CN112630645A (en) * | 2020-12-15 | 2021-04-09 | 中国电力科学研究院有限公司 | Method and system for determining defect rate of relay protection equipment |
| CN113516244A (en) * | 2021-07-27 | 2021-10-19 | 盛景智能科技(嘉兴)有限公司 | Intelligent operation and maintenance method and device, electronic equipment and storage medium |
| CN115359307A (en) * | 2022-10-24 | 2022-11-18 | 成都诺比侃科技有限公司 | Contact network loss inspection defect data management method and system based on big data |
| CN117148070A (en) * | 2023-09-08 | 2023-12-01 | 浙江大学 | MCU-Apriori-LoRa based space electromagnetic wave UHF partial discharge directional sensing method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455563A (en) * | 2013-08-15 | 2013-12-18 | 国家电网公司 | Data mining method applicable to integrated monitoring system of intelligent substation |
| CN103488802A (en) * | 2013-10-16 | 2014-01-01 | 国家电网公司 | EHV (Extra-High Voltage) power grid fault rule mining method based on rough set association rule |
| CN104820716A (en) * | 2015-05-21 | 2015-08-05 | 中国人民解放军海军工程大学 | Equipment reliability evaluation method based on data mining |
-
2016
- 2016-03-22 CN CN201610166386.2A patent/CN105843210B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455563A (en) * | 2013-08-15 | 2013-12-18 | 国家电网公司 | Data mining method applicable to integrated monitoring system of intelligent substation |
| CN103488802A (en) * | 2013-10-16 | 2014-01-01 | 国家电网公司 | EHV (Extra-High Voltage) power grid fault rule mining method based on rough set association rule |
| CN104820716A (en) * | 2015-05-21 | 2015-08-05 | 中国人民解放军海军工程大学 | Equipment reliability evaluation method based on data mining |
Non-Patent Citations (2)
| Title |
|---|
| 柴华昕等: "Apriori挖掘频繁项目集算法的改进", 《计算机工程与应用》 * |
| 郑元兵等: "变压器故障特征量可信度的关联规则分析", 《高电压技术》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649479A (en) * | 2016-09-29 | 2017-05-10 | 国网山东省电力公司电力科学研究院 | Probability graph-based transformer state association rule mining method |
| CN107247995A (en) * | 2016-09-29 | 2017-10-13 | 上海交通大学 | Transmission line of electricity running status association rule mining and Forecasting Methodology based on Bayesian model |
| CN106526352A (en) * | 2016-09-30 | 2017-03-22 | 中国电力科学研究院 | Method and system for determining power transformer fault types |
| CN106526352B (en) * | 2016-09-30 | 2020-10-13 | 中国电力科学研究院 | Method and system for determining fault type of power transformer |
| CN107025293A (en) * | 2017-04-13 | 2017-08-08 | 广东电网有限责任公司电力科学研究院 | A kind of second power equipment defective data method for digging and system |
| CN107451416A (en) * | 2017-08-28 | 2017-12-08 | 昆明理工大学 | A kind of sle auxiliary diagnostic equipment and method |
| CN107590621B (en) * | 2017-10-10 | 2020-08-21 | 清华大学 | Defect affinity analysis method and device based on self-adaptive frequent set mining method |
| CN107590621A (en) * | 2017-10-10 | 2018-01-16 | 清华大学 | The defects of based on adaptive Frequent Set mining method compatibility analysis method and device |
| CN109697619A (en) * | 2017-10-20 | 2019-04-30 | 中移(苏州)软件技术有限公司 | A kind of data analysing method and device |
| CN111198924B (en) * | 2018-11-19 | 2022-11-25 | 长鑫存储技术有限公司 | Product failure knowledge base establishing method, failure analysis method, device and medium |
| CN111198924A (en) * | 2018-11-19 | 2020-05-26 | 长鑫存储技术有限公司 | Method for establishing product failure knowledge base, failure analysis method, device and medium |
| CN109919338A (en) * | 2019-03-22 | 2019-06-21 | 国网上海市电力公司 | The safety Analysis method of relay protection device |
| CN110442609B (en) * | 2019-08-02 | 2023-05-16 | 云南电网有限责任公司电力科学研究院 | Identification method for association defects of secondary equipment of intelligent substation |
| CN110442609A (en) * | 2019-08-02 | 2019-11-12 | 云南电网有限责任公司电力科学研究院 | A kind of recognition methods of secondary equipment of intelligent converting station association defect |
| CN111797146A (en) * | 2020-07-20 | 2020-10-20 | 贵州电网有限责任公司电力科学研究院 | Big data-based equipment defect correlation analysis method |
| CN112085333A (en) * | 2020-08-06 | 2020-12-15 | 国网河南省电力公司经济技术研究院 | Power distribution network construction control index incidence relation research method based on incidence algorithm |
| CN112630645A (en) * | 2020-12-15 | 2021-04-09 | 中国电力科学研究院有限公司 | Method and system for determining defect rate of relay protection equipment |
| CN112630645B (en) * | 2020-12-15 | 2024-05-24 | 中国电力科学研究院有限公司 | Method and system for determining defect rate of relay protection equipment |
| CN113516244A (en) * | 2021-07-27 | 2021-10-19 | 盛景智能科技(嘉兴)有限公司 | Intelligent operation and maintenance method and device, electronic equipment and storage medium |
| CN113516244B (en) * | 2021-07-27 | 2023-12-05 | 盛景智能科技(嘉兴)有限公司 | Intelligent operation and maintenance method and device, electronic equipment and storage medium |
| CN115359307A (en) * | 2022-10-24 | 2022-11-18 | 成都诺比侃科技有限公司 | Contact network loss inspection defect data management method and system based on big data |
| CN115359307B (en) * | 2022-10-24 | 2023-01-03 | 成都诺比侃科技有限公司 | Big data-based overhead contact system wear-checking defect data management method and system |
| CN117148070A (en) * | 2023-09-08 | 2023-12-01 | 浙江大学 | MCU-Apriori-LoRa based space electromagnetic wave UHF partial discharge directional sensing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105843210B (en) | 2018-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105843210A (en) | Power transformer defect information data mining method | |
| CN106874582B (en) | A kind of electro spindle life test time design method | |
| CN107301296A (en) | Circuit breaker failure influence factor method for qualitative analysis based on data | |
| CN103793854A (en) | Multiple combination optimization overhead transmission line operation risk informatization assessment method | |
| CN109254219B (en) | A kind of distribution transforming transfer learning method for diagnosing faults considering multiple factors Situation Evolution | |
| CN104299116A (en) | Quantitative evaluation method for security risk of operation of power network | |
| US20210233179A1 (en) | Method for designing composite-index agricultural insurance product and products therefrom | |
| CN106571627A (en) | Secondary device health state evaluation method based on on-line monitoring information | |
| CN105893757A (en) | Voltage sag severity comprehensive evaluation method | |
| Kock | Common structural variation reduction in PLS-SEM: Replacement analytic composites and the one fourth rule | |
| CN103606062A (en) | Relay protection state evaluation and aid decision-making maintenance method | |
| CN104268686A (en) | XML-based space data quality inspection method and system | |
| CN111950850B (en) | Evidence network-based unmanned aerial vehicle system guarantee capability evaluation method | |
| Li et al. | Fuzzy risk prediction of roof fall and rib spalling: based on FFTA–DFCE and risk matrix methods | |
| CN104281525A (en) | Defect data analytical method and method for shortening software testing programs by using same | |
| Hu et al. | Hazard and risk assessment for hydraulic fracturing induced seismicity based on the Entropy-Fuzzy-AHP method in Southern Sichuan Basin, China | |
| Feng et al. | Reliability evaluation of gantry cranes based on fault tree analysis and Bayesian network | |
| CN103942251A (en) | Method and system for inputting high altitude meteorological data into database based on multiple quality control methods | |
| CN117709555A (en) | Carbon emission prediction and evaluation method and system based on transformer carbon accounting model | |
| Chen et al. | A new evaluation method for slope stability based on TOPSIS and MCS | |
| Sheng et al. | Risk assessment of urban gas pipeline based on different unknown measure functions | |
| CN105488270A (en) | Multiattribute comprehensive method for structural fault diagnosis of transformer | |
| CN105184496A (en) | Integrated evaluation method of health index of mine ventilation system | |
| CN107506832A (en) | The hidden danger method for digging aided in is maked an inspection tour to monitoring | |
| Li et al. | Software reliability metrics selecting method based on analytic hierarchy process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231020 Address after: 100084 Tsinghua Yuan, Beijing, Haidian District Patentee after: TSINGHUA University Patentee after: Guangzhou Power Supply Bureau of Guangdong Power Grid Co.,Ltd. Address before: 100084-82 box 100084, Beijing, Haidian District Patentee before: TSINGHUA University Patentee before: GUANGZHOU POWER SUPPLY Co.,Ltd. |