CN105843210B - Power transformer defect information data digging method - Google Patents
Power transformer defect information data digging method Download PDFInfo
- Publication number
- CN105843210B CN105843210B CN201610166386.2A CN201610166386A CN105843210B CN 105843210 B CN105843210 B CN 105843210B CN 201610166386 A CN201610166386 A CN 201610166386A CN 105843210 B CN105843210 B CN 105843210B
- Authority
- CN
- China
- Prior art keywords
- attribute
- defect
- power transformer
- defective data
- data collection
- 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.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000002950 deficient Effects 0.000 claims abstract description 60
- 238000013480 data collection Methods 0.000 claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 206010061619 Deformity Diseases 0.000 claims description 4
- 238000009412 basement excavation Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction 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
- 238000005065 mining Methods 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims description 2
- 230000000717 retained effect Effects 0.000 claims 1
- 238000011156 evaluation Methods 0.000 abstract description 8
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000000605 extraction Methods 0.000 abstract description 3
- 238000010276 construction Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000007418 data mining Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000010998 test method Methods 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 kind of power transformer defective data method for digging, including：To the historical defect data collection D of power transformer0Defect attribute is screened, defective data collection D is formed1；To D1The defects of attribute filled up or deleted to reduce noise data；Based on D1Have the new attribute of attribute construction, discretization is carried out for continuous type attribute and categorical attribute is rationally layered, forms defective data collection D2；Input attribute and the correlation between objective attribute target attribute are calculated, uncorrelated attribute is deleted, remaining attribute constitutes defective data collection D3；The incidence relation between defective data set attribute is calculated using Apriori algorithm；Efficient association rule is extracted, the defect factors of power transformer are analyzed, forms correlation rule knowledge base.The invention has the advantages that：Multidimensional, multilayer excavate power transformer defect, and the incidence relation between convenient and efficient extraction defect attribute provides foundation for Power Transformer Condition evaluation, improves the accuracy rate of state evaluation.
Description
Technical field
The present invention relates to data mining technology fields, more particularly, to a kind of power transformer defect information data mining side
Method.
Background technology
The reliable and stable operation of electric system is to ensure that economic development, social progress and living standards of the people improve institute
Need the premise and basis of electric power.Power transformer undertakes electric energy transmission and distribution, voltage transformation as electric system important equipment
Etc. functions, operation conditions, the general level of the health directly affect safety, stability and the reliability of electric system.It is commented based on state
The Condition-Based Maintenance Technology of valence is carried out according to state evaluation result and is actively overhauled, reasonable arrangement repair time and overhauling project, to
Achieve the purpose that reduce equipment failure rate and ensures equipment reliability service.
The significant data basis that defect information is evaluated as Power Transformer Condition, there are sources, and numerous, attribute is enriched, is counted
According to the features such as amount is big, accuracy is low and redundancy is high.Past, the analysis of power transformer defect information rely primarily on statistical analysis,
Both it can not be quickly obtained high price value information, potential incidence relation that can not be between detecting defects information attribute, to power transformer
Evaluation of running status lacks to be supported enough.
Invention content
The present invention is directed at least solve one of above-mentioned technical problem.
For this purpose, it is an object of the invention to propose a kind of power transformer defective data method for digging.
To achieve the goals above, embodiment of the invention discloses that a kind of power transformer defective data method for digging,
Include the following steps：S1：To the historical defect data collection D of power transformer0Defect attribute is screened, retaining may with excavation target
There are potential associated related datas, form defective data collection D1；S2：To defective data collection D1The defects of attribute by filling up
It lacks, right the wrong, directly deleting, deleting at least one of redundancy and elimination inconsistency to reduce noise data；S3：To lacking
Fall into data set D1Redundant attributes carry out discretization by data integration and the new attribute of data transition structure, for continuous type attribute
It is layered with for categorical attribute, forms defective data collection D2；S4：Based on defective data collection D2, calculate input attribute and mesh
The correlation between attribute is marked, uncorrelated attribute is deleted and constitutes defective data collection D3；S5：Based on defective data collection D3, most ramuscule is set
Degree of holding and min confidence calculate the incidence relation between defective data set attribute using Apriori algorithm；S6：Extraction is effectively closed
Connection rule, analyzes the defect factors of power transformer, forms correlation rule knowledge base.
Power transformer defective data method for digging according to the ... of the embodiment of the present invention, passes through the pass to power transformer defect information
Join method for digging, establish suitable defective data collection, eliminates the omission missing of multi-resources Heterogeneous defective data, inconsistent and redundancy etc.
Problem, reasonable garbled data attribute are realized that the multidimensional of power transformer defective data, multilayer are excavated using Apriori algorithm, are dug
The incidence relation between defect attribute is dug, foundation is provided for state evaluation, improves the accuracy rate of Power Transformer Condition evaluation, ensure
Power transformer Strategies of Maintenance is more rationally effective.
In addition, power transformer defective data method for digging according to the above embodiment of the present invention, can also have following attached
The technical characteristic added：
Further, in step sl, defective data collection D1Excavation dimension including but not limited to voltage class, factory
It is continuous including family, unit type, time of putting into operation, disfigurement discovery time, defect type, defect processing measure and power transformation station name
Type, classifying type historical data.
Further, step S2 further comprises：Power transformer defect type is redefined based on target is excavated, is deleted
The repeated defects that same equipment occurs retain defect record for the first time.
Further, in step s3, defective data collection D2Dimension include run time, operating mechanism type, defect
Processing mode, defect time of origin, manufacturer's qualification, unit type, defect occurrence cause, equipment operating environment, equipment fortune
At least one of row place and power transformation station name.
Further, step S4 further comprises：For defective data collection D2Attribute carry out feature selecting, be based on card side
Verification calculates each Attribute Significance, and attribute sequence is carried out according to importance value, retains the defect category that importance is higher than predetermined threshold value
Property.
Further, the incidence relation between defective data set attribute is calculated using Apriori algorithm to further comprise：Using
Apriori algorithm carries out the association rule mining between the defect correlative factor of the power transformer, wherein the power transformer
The defect correlative factor of device includes manufacturer, the operation time limit and defect type.
The additional aspect and advantage of the present invention will be set forth in part in the description, and will partly become from the following description
Obviously, or practice through the invention is recognized.
Description of the drawings
The above-mentioned and/or additional aspect and advantage of the present invention will become in the description from combination following accompanying drawings to embodiment
Obviously and it is readily appreciated that, wherein：
Fig. 1 is the flow chart of the power transformer defective data method for digging of one embodiment of the invention.
Specific implementation mode
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the present invention, and is not considered as limiting the invention.
In the description of the present invention, it is to be understood that, term "center", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, with specific azimuth configuration and operation, therefore should not be understood as pair
The limitation of the present invention.In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply opposite
Importance.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
Can also be electrical connection to be mechanical connection；It can be directly connected, can also indirectly connected through an intermediary, Ke Yishi
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
With reference to following description and drawings, it will be clear that these and other aspects of the embodiment of the present invention.In these descriptions
In attached drawing, some particular implementations in the embodiment of the present invention are specifically disclosed, to indicate to implement the implementation of the present invention
Some modes of the principle of example, but it is to be understood that the scope of embodiments of the invention is not limited.On the contrary, the present invention
Embodiment includes all changes, modification and the equivalent fallen within the scope of the spirit and intension of attached claims.
It introduces first and is related to basic conception with Apriori algorithm：Correlation rule and basic conception.
What correlation rule indicated is the rule not with the specified desired incidence relation of certain satisfaction between same area in database
Then.If I={ i1,i2,…inBe item set.An item data library D is given, wherein each things T is the set of item, it is full
FootIf item collectionAndThen shaped likeImplications be known as correlation rule, X
Premise and conclusion with Y as the correlation rule；
The basic parameter for weighing correlation rule includes support (Support), confidence level (Confidence) and promotion degree
(Lift)。
Support (support)：It indicates the support of item collection X ∪ Y, is i.e. includes item collection X and item simultaneously in transaction database D
The ratio for collecting Y, is denoted as：
In formula：| T (X ∨ Y) | the number of transactions for indicating while including X and Y；| T | indicate total number of transactions.
Confidence level (confidence)：It indicates in the affairs for occurring X in transaction database D, while including the ratio of Y again,
It is denoted as：
Promotion degree (lift)：It is promoted than the confidence level and the ratio between consequent confidence level for transaction database D, is denoted as：
It is promoted and is indicated under conditions of X occurs than Lift, the conditional probability that Y occurs is the ratio for the prior probability that Y occurs.
When being promoted than being more than 1, showIt is directive association, i.e. the appearance of X has facilitation to Y；Work as lift
<1, then show that the appearance of X reduces the possibility of Y appearance.
Power transformer defective data method for digging according to the ... of the embodiment of the present invention is described below in conjunction with attached drawing.
Fig. 1 is the flow chart of the power transformer defective data method for digging of one embodiment of the invention.Referring to FIG. 1,
The power transformer defective data method for digging of the embodiment of the present invention includes the following steps：
S1：To the historical defect data collection D of power transformer0Screen defect attribute, retain with excavate target there may be
Potential associated related data forms defective data collection D1。
Specifically, expertise is based on by data set D0Uncorrelated attribute delete, including " disfigurement discovery people ", " defect
The dereferenceds attribute such as defect elimination people ", " accountability unit " and " enter maintenance department time ", by retaining defect attribute after preliminary screening
23, constitute defective data collection D1。
S2：To defective data collection D1The defects of attribute lack, right the wrong, directly delete, delete redundancy by filling up
With eliminate at least one of inconsistency to reduce noise data.
Specifically, defective data collection D1In there are attribute value missing errors, peel off, redundancy and it is inconsistent situations such as.For
There are the problem of, according to type, the feature excavated target with lack attribute, processing method is as follows：
S201：Due to needing to weigh different production firm's equipment dependabilities, it is therefore desirable to which more each equipment deficiency is sent out for the first time
The raw time, and same equipment repeated defects will seriously affect the data distribution of equipment so that association result of calculation is unreliable, therefore
Considered jointly according to factors such as " functional locations ", " substation ", " device numbering " and " defect time of origin ", only retains and lack for the first time
It falls into and deletes remaining redundancy defect.
S202：For categorical attribute, such as attribute is that " power transformer model " there are missing values or outliers, can be led to
Crossing factors such as " power transformation station names ", " voltage class " and " manufacturer ", analysis fills up missing values or value of righting the wrong jointly.When
It can not be analyzed jointly to make up missing data by other attributes, then delete this record.
S3：To defective data collection D1Redundant attributes by data integration with the new attribute of data transition structure, for continuous
Type attribute carries out discretization and categorical attribute is layered, and forms defective data collection D2。
Specifically, defective data collection D1In part Attribute Redundancy, value density it is low, pass through data integration and data and convert
Mode constructs new attribute, both reduces attribute dimensions, while also promoting defective data collection ability to express.Specific method includes following step
Suddenly：
S301：Based on " defect processing measure " and " defect processing result " this two attribute item, construct " defect processing mode "
Defect processing measure is divided into plain mode, substitute mode, comprehensive method and other modes etc. by defect, is not existed together a variety of
Reason measure is divided to these four modes, and data is made to be easier to understand.
S302：By " disfigurement discovery time " and " putting equipment in service time ", " the equipment operation time limit " attribute is built, and be based on
The continuous type attribute quantification is divided into " operation time limit N by expertise<1 year ", " 1 year<Run time limit N<5 years ", " 5 years<Operation
Time limit N<10 years ", " 10 years<Run time limit N<15 years " " 15 years<Run time limit N<20 years " and " operation time limit N>20 years " etc. 6
Attribute value.
S303：According to " device type " and " manufacturer " attribute, builds " producer's qualification " attribute and be divided into " outer
Money " " joint " " domestic " three attribute values.
S304：By defective data collection D1In data quantified, be layered, establish power transformer defective data collection D2。
S4：Based on defective data collection D2, input attribute and the correlation between objective attribute target attribute are calculated, uncorrelated attribute structure is deleted
At defective data collection D3.It should be noted that for different excavation targets, objective attribute target attribute is different.
Specifically, power transformer defective data collection D2Contained attribute is still more, by investigating the importance between attribute,
Achieve the purpose that the data set further simplified.The importance of attribute can the combined study in terms of two：First, dependence is certainly
Body is investigated；Second, it is investigated from input attribute and objective attribute target attribute related angle.Dependence itself sees that important attribute should be carried
Information is more, that is, variance is larger.Some standards for estimating variance size are formulated according to actual conditions, are referred to when property variance is less than
Calibration is accurate, then is considered as inessential.From input attribute in terms of objective attribute target attribute related angle, important attribute copes with point of objective attribute target attribute
Class predicts significance.For different types of input attribute and objective attribute target attribute, used measurement method also differs.Tool
Body situation is as shown in table 1, and table 1 is different variable test method tables.
1 different type of table becomes measuring method
It is categorical attribute to be concentrated due to power transformer defect attribute, is measured belong to using card side's verification mode first
Correlation between property.The verification of card side belongs to statistical hypothesis testing scope, relates generally to following four big steps：It is proposed that zero is false
If, select and calculate test statistics, determine significance, conclusion and decision.Wherein block-regulations examine test statistics be
Peason chi-square statistics amounts, data definition are：
In formula：R is the line number of contingency table, and c is the columns of contingency table；foFor observed frequency, feFor expecterd frequency.
The significance level weighed between attribute is weighed by " importance (Importance) ".Importance
(Importance) be not related coefficient size, which is the probability by calculating chi-square statistics amount under specific significance
P, by comparing (1-p) value between each variable, to weigh its importance；The bigger expression variable of the usual value is more important.
Importance I is set>0.95, it is then directly deleted when importance value is more than 0.95 reservation, and importance is less than 0.9
It removes；The high attribute of importance deletes the attribute that importance is less than changed standard, forms power transformer defective data collection D3。
S5：Based on defective data collection D3, minimum support and min confidence are set, is calculated and is lacked using Apriori algorithm
Fall into the incidence relation between 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：Efficient association rule is extracted, the defect factors of power transformer are analyzed, forms correlation rule knowledge base.
In the example of the present invention, using power transformer defect type as consequent, extracted based on apriori algorithms
Correlation rule it is as shown in table 2, table 2 is power transformer Strong association rule table.
2 power transformer Strong association rule of table
By above table it is found that the equipment of vendor A the general of defect occurs in operation time limit cooling system between 5-10
Rate intimate 90%, when equipment state is evaluated weight, the scoring etc. of corresponding manufacturer's associated disadvantages make corresponding adjustment, be directed to simultaneously
Property proposition manufacturer's power transformer equipment O&M strategy.By changing preceding paragraph and the consequent attribute of correlation rule, from more
Angle, various dimensions, multi-level association analysis cause power transformer to generate defect factors.
The power transformer defective data method for digging of the embodiment of the present invention will be associated in conjunction with the particularity of power industry
Rule is applied in the Analysis on Selecting of power transformer defect information correlation rule, proposes the association in maintenance data digging technology
The basic ideas and specific solution that rule analyzes power transformer defective data.By to Strong association rule
Extraction and analysis provide reference frame, state evaluation accuracy rate higher, power transformer dimension for the state evaluation of power transformer
Repair strategy more rationally, more specific aim.
In addition, other compositions of the power transformer defective data method for digging of the embodiment of the present invention and effect are for this
All it is known for the technical staff in field, in order to reduce redundancy, does not repeat.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiments or example in can be combined in any suitable manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that：Not
In the case of being detached from the principle of the present invention and objective a variety of change, modification, replacement and modification can be carried out to these embodiments, this
The range of invention is by claim and its equivalent limits.
Claims (6)
1. a kind of power transformer defective data method for digging, which is characterized in that include the following steps：
S1：To the historical defect data collection D of power transformer0Defect attribute is screened, there may be potential passes with target is excavated for reservation
The related data of connection forms defective data collection D1；
S2：To defective data collection D1The defects of attribute lack, right the wrong, directly delete, delete redundancy and elimination by filling up
At least one of inconsistency is to reduce noise data；
S3：To defective data collection D1Redundant attributes by data integration and the new attribute of data transition structure, for continuous type attribute
It carries out discretization and categorical attribute is layered, form defective data collection D2；
S4：Based on defective data collection D2, input attribute and the correlation between objective attribute target attribute are calculated, uncorrelated attribute composition is deleted and lacks
Fall into data set D3；
S5：Based on defective data collection D3, minimum support and min confidence are set, defective data is calculated using Apriori algorithm
Collect D3Incidence relation between attribute；
S6：Efficient association rule is extracted, the defect factors of power transformer are analyzed, forms correlation rule knowledge base.
2. power transformer defective data method for digging according to claim 1, which is characterized in that in step sl, lack
Fall into data set D1Excavation dimension including but not limited to voltage class, manufacturer, unit type, time of putting into operation, disfigurement discovery
Continuous type, classifying type historical data including time, defect type, defect processing measure and power transformation station name.
3. power transformer defective data method for digging according to claim 1, which is characterized in that step S2 is further wrapped
It includes：Power transformer defect type is redefined based on target is excavated, deletes the repeated defects that same equipment occurs, is retained for the first time
Defect record.
4. power transformer defective data method for digging according to claim 1, which is characterized in that in step s3, lack
Fall into data set D2Dimension include run time, operating mechanism type, defect processing mode, defect time of origin, manufacturer
At least one of qualification, unit type, defect occurrence cause, equipment operating environment, equipment operational site and power transformation station name.
5. power transformer defective data method for digging according to claim 1, which is characterized in that step S4 is further wrapped
It includes：For defective data collection D2Attribute carry out feature selecting, each Attribute Significance of calculating is verified based on card side, according to importance
Value carries out attribute sequence, retains the defect attribute that importance is higher than predetermined threshold value.
6. power transformer defective data method for digging according to claim 1, which is characterized in that calculated using Apriori
The incidence relation that method calculates between defective data set attribute further comprises：The power transformer is carried out using Apriori algorithm
Defect correlative factor between association rule mining, wherein the defect correlative factor of the power transformer include manufacturer,
Run 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 CN105843210A (en) | 2016-08-10 |
| CN105843210B true 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) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649479B (en) * | 2016-09-29 | 2020-05-12 | 国网山东省电力公司电力科学研究院 | Transformer state association rule mining method based on probability graph |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| CN112085333B (en) * | 2020-08-06 | 2023-01-17 | 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 |
| 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 |
| 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 |
| 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 |
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 |
|---|
| Apriori挖掘频繁项目集算法的改进;柴华昕等;《计算机工程与应用》;20071231;第43卷(第24期);第158-161、171页 * |
| 变压器故障特征量可信度的关联规则分析;郑元兵等;《高电压技术》;20120131;第38卷(第1期);第82-88页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105843210A (en) | 2016-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105843210B (en) | Power transformer defect information data digging method | |
| CN104063612B (en) | A kind of Tunnel Engineering risk profiles fuzzy evaluation method and assessment system | |
| Dixit et al. | Identification of parameters for embodied energy measurement: A literature review | |
| CN113900381B (en) | Steel structure remote health monitoring platform based on Internet of things and application method | |
| CN104881003A (en) | Effectiveness evaluation method for metering production facilities | |
| CN105718658A (en) | Large-size bridge online evaluating system | |
| CN113015122B (en) | Assembly type building quality monitoring and analyzing method based on Internet of things and wireless sensor technology | |
| CN112418683A (en) | Construction risk evaluation method for shield underpass existing structure | |
| CN115829322A (en) | Tunnel risk analysis method based on regional geology and construction dual-factor influence | |
| Feng et al. | Reliability evaluation of gantry cranes based on fault tree analysis and Bayesian network | |
| CN110489404A (en) | A kind of comprehensive data method for quality control of the field of distribution network based on three-tier architecture | |
| Qiu et al. | A Comprehensive Assessment Method for Safety Risk of Gas Tunnel Construction Based on Fuzzy Bayesian Network. | |
| CN112488529A (en) | Engineering cost management system based on big data | |
| Teng-teng et al. | Comprehensive appraisal of the safety of hidden frame glass curtain wall based on fuzzy theory | |
| CN111950850B (en) | Evidence network-based unmanned aerial vehicle system guarantee capability evaluation method | |
| CN113269419A (en) | Building engineering project material incoming acceptance management method based on intellectualization and cloud management platform | |
| CN108988347A (en) | A kind of adjusting method and system that power grid Transient Voltage Stability sample set classification is unbalance | |
| CN105184496A (en) | Integrated evaluation method of health index of mine ventilation system | |
| CN109472428A (en) | A kind of power distribution network operation risk assessment method based on loss expectation method | |
| CN103606112A (en) | Power plant operation performance determination method based on multilevel gray evaluation | |
| CN107506832A (en) | The hidden danger method for digging aided in is maked an inspection tour to monitoring | |
| Pierik et al. | European wind turbine standards II (EWTS-II) | |
| CN116805220A (en) | Standard efficiency analysis model and evaluation method based on entropy theory | |
| CN114282423A (en) | Fatigue monitoring method and service life prediction method for shore bridge structure | |
| CN113870383A (en) | Automatic board arranging method and device for construction drawings |
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. |