CN107730079A - A kind of power transmission and transforming equipment defect portrait method based on data mining - Google Patents
A kind of power transmission and transforming equipment defect portrait method based on data mining Download PDFInfo
- Publication number
- CN107730079A CN107730079A CN201710832029.XA CN201710832029A CN107730079A CN 107730079 A CN107730079 A CN 107730079A CN 201710832029 A CN201710832029 A CN 201710832029A CN 107730079 A CN107730079 A CN 107730079A
- Authority
- CN
- China
- Prior art keywords
- defect
- equipment
- data
- correlation
- degree
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 204
- 230000005540 biological transmission Effects 0.000 title claims abstract description 31
- 230000001131 transforming effect Effects 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000007418 data mining Methods 0.000 title claims abstract description 17
- 230000007812 deficiency Effects 0.000 claims abstract description 37
- 238000004458 analytical method Methods 0.000 claims abstract description 33
- 230000008439 repair process Effects 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 5
- 230000005611 electricity Effects 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims description 2
- 238000007670 refining Methods 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 description 16
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 5
- 239000012141 concentrate Substances 0.000 description 4
- 230000006378 damage Effects 0.000 description 4
- 239000002994 raw material Substances 0.000 description 4
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007257 malfunction Effects 0.000 description 2
- 238000011056 performance test Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 239000000741 silica gel Substances 0.000 description 2
- 229910002027 silica gel Inorganic materials 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000002845 discoloration Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
A kind of power transmission and transforming equipment defect portrait method based on data mining, comprises the following steps:(1)Extract sample data;(2)Frequency analysis is carried out to sample data;(3)The degree of correlation quantizating index of every kind of equipment deficiency type and relation factor is assessed successively;(4)Drawn a portrait according to degree of correlation quantizating index.Use the method for the present invention, it can quickly, intuitively understand and grasp power transmission and transforming equipment major defect distribution characteristics and its internal association factor and correlation degree, foundation is provided to reduce the decision-making of equipment deficiency rate, meanwhile, enhance science and preciseness that equipment deficiency is analyzed.
Description
Technical field
The present invention relates to data mining technology and electric power equipment management technical field, more particularly to one kind to be based on data mining
Power transmission and transforming equipment defect portrait method.
Background technology
The safety decision-making of power transmission and transforming equipment the stability of Operation of Electric Systems, but due to the basic structure of power transmission and transforming equipment
Into difference, and many power transmission and transforming equipments come from different manufacturers, in the process of power transmission and transforming equipment operation and maintenance
In there is also more factor effect, resulting in power transmission and transforming equipment, operationally there is some defect problems.Due to defeated change
Become electric fault meeting strong influence caused by electric equipment defect and the safe for operation of power system, cause the supply appearance of electric power poor
Mistake, life and production to people bring strong influence.
At present to the analysis of power transmission and transforming equipment defect, often only using empiric observation method and simple count method to equipment deficiency
Analyzed.Empiric observation method, it is so as to the analysis method intuitively drawn a conclusion based on a large amount of operating experiences and maintenance experience.Should
Method is simple and clear, and the overall condition that defect occurs has the reflection of relative straightforward, but is easily influenceed by Subjective,
There is no the believable data of science as analysis foundation, it is difficult to accomplish the analytical conclusions of scientific and precise.And simple count analytic approach, it is
The simple data for automating defect sample is analyzed, the different characteristics of each sample can not be reflected, tie analysis
There is systematic error to a certain degree in fruit, it is impossible to scientifically reflect the extent of injury that the defects of different runs to equipment.
The content of the invention
The main object of the present invention is to provide a kind of portrait method of power transmission and transforming equipment defect, right in the prior art to solve
The analysis of equipment deficiency lacks the problem of scientific and preciseness.
To achieve these goals, the technical solution adopted by the present invention is:
A kind of power transmission and transforming equipment defect portrait method based on data mining, comprises the following steps:
S1:Extract sample data;
S2:Frequency analysis is carried out to the defects of sample data record data;
S3:The degree of correlation quantizating index of every kind of equipment deficiency type and relation factor is assessed successively;
S4:Drawn a portrait according to the degree of correlation quantizating index.
Preferably, the power transmission and transforming equipment includes main transformer, breaker and transmission line of electricity.
Preferably, the sample data in the step S1 is from equipment account, defect record and defect analysis report, institute
State defect analysis and be reported in Structure of need before input.
Preferably, the sample data in the step S1 includes device type and supplier data, device location and O&M
Team's data, equipment life and overhaul data, defect time and weather environment data, unit exception operating condition data and defect
Situation describes data.
Preferably, the device type and supplier data be used for reflect equipment whether there is with particular device type or
The defects of closely related design of supplier, familial problem;Device location and O&M the team data are set for reflection
It is standby to whether there is and problem the defects of specific geographic position or closely related O&M team;The equipment life and overhaul data
For reflecting the degree of correlation between equipment deficiency problem and life-span, repair history;The defect time and weather environment data
For reflecting the degree of correlation between equipment deficiency problem and season, weather environment;The unit exception operating condition data are used
Degree of correlation between reflection equipment deficiency problem and misoperation operating mode;The defect situation describes data and is used as defect number
According to tag along sort.
Preferably, the analysis in the step S2 includes rejected region analysis, defect type analysis and Causes Analysis.
Preferably, the degree of correlation quantizating index in the step S3 includes:
(1)Device type and supplier's degree of correlation:Reflect between equipment deficiency problem and particular device type or supplier
Degree of correlation.
(2)Device location and O&M team degree of correlation:Reflect equipment deficiency problem and specific geographic position or O&M
Degree of correlation between team.
(3)Equipment life and maintenance degree of correlation:Reflect equipment deficiency problem and the phase between life-span, repair history factor
Pass degree.
(4)Defect time and weather environment degree of correlation:Reflect between equipment deficiency problem and season, weather element
Degree of correlation.
(5)Unit exception operating condition degree of correlation:Reflect between equipment deficiency problem and misoperation operating mode factor
Degree of correlation.
Preferably, the assessment in the step S3 includes the defects of different defect type correlations reason and different defect causes
The caused aspect of defect type two.
Preferably, the assessment in the step S3 includes refining the details of each degree of correlation quantizating index.
Preferably, the portrait in the step S4 is presented using radar map.
Benefit of the invention is that:
(1)Visualized and presented based on big data various dimensions, it is special quickly, intuitively to understand and grasp the distribution of power transmission and transforming equipment major defect
Sign and its internal association factor and correlation degree;
(2)Indexing based on equipment deficiency relation factor and correlation degree, the portrait of equipment deficiency relation factor is realized, for drop
The decision-making of low equipment deficiency rate provides foundation.
(3)Enhance the science and preciseness of equipment deficiency analysis.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the present invention.
Fig. 2 associates distribution map between oil-filled transformer body defect defect type and defect cause.
Fig. 3 associates distribution map between oil-filled transformer body defect defect cause and defect type.
Fig. 4 a and Fig. 4 b are the statistical Butut between oil-filled transformer defect type and defect generation month.
Fig. 5 a and Fig. 5 b are the statistical Butut between oil-filled transformer defect type and defect generation position.
Statistical Bututs of Fig. 6 a and Fig. 6 b between oil-filled transformer defect type and defect equipment manufacturer.
Statistical Bututs of Fig. 7 a and Fig. 7 b between oil-filled transformer defect type and equipment lifespan.
Statistical Bututs of Fig. 8 a and Fig. 8 b between oil-filled transformer defect type and equipment operating environment.
Fig. 9 a ~ Fig. 9 u are inherent law portrait figure of the oil-filled transformer by defect type.
Figure 10 a ~ Figure 10 j are inherent law portrait figure of the oil-filled transformer by defect cause.
Embodiment
A kind of power transmission and transforming equipment defect portrait method based on data mining, as shown in figure 1, comprising the following steps:
S1:Extract sample data;
The applicable power transmission and transforming equipment of the method for the present invention includes main transformer, breaker and transmission line of electricity.Wrap in sample data source
Equipment account, defect record and defect analysis report are included, and defect analysis needs to carry out structuring before being reported in input.
The demand drawn a portrait according to equipment deficiency relation factor, main input data parameter is classified by following label:
Device type and supplier data, device location and O&M team data, equipment life and overhaul data, defect time and meteorology
Environmental data, unit exception operating condition data and defect situation describe data.Wherein:
(1)Device type and supplier data are mainly derived from equipment account, and its data target is used to reflect that equipment whether there is
Problem the defects of closely related design, familial with particular device type or supplier.Key data parameter has equipment
Title(Numbering), voltage class, device type, unit type, production firm, the date of production, Type of equipment, etc..
(2)Device location and O&M team data are mainly derived from equipment account and defect record, and its data target is used for
Reflect that equipment whether there is and problem the defects of specific geographic position or closely related O&M team.Key data parameter has list
Position title/power supply administration's title(Code), affiliated power transformation station name(Numbering), administrative department/discovery department name(Numbering)/ make a report on
Department name(Numbering), safeguard teams and groups/discovery teams and groups title(Numbering), finder/reporter, etc..
(3)Equipment life and overhaul data are mainly derived from equipment account, defect record, defect analysis report, its data
Index is used for the degree of correlation reflected between the factor such as equipment deficiency problem and life-span, repair history.Main data field has throwing
Fortune date, discovery time, equipment add up that defect number occurs, same defects number, the number that breaks down occur, disappeared apart from last time
Lack the time, test repair time, etc. apart from last time fault correction time, apart from last time.
(4)Defect time and weather environment data are mainly derived from defect record and defect analysis report, its data target
For reflecting the degree of correlation between the factor such as equipment deficiency problem and season, weather environment.When main data field is found
Between(During the date), filling time, at that time weather circumstance condition(Temperature, humidity, precipitation, wind speed, thunder and lightning etc.), etc..
(5)Unit exception operating condition data are mainly derived from defect analysis report, and its data target is used to reflect equipment
Degree of correlation between the factor such as defect problem and misoperation operating mode.Main data field has protection recording, overvoltage, short
Road, overload, etc..
(6)Defect situation describes data and is mainly derived from defect record, and its data target is used for defective data tag along sort.
Main data field has actual defects toponym, functional location title(ID), defect content, defect numbering, rejected region name
Claim(Coding), defect standard code, defect rank, defect item name(Coding), defect presentation title(Coding), defect cause
Title(Coding), etc..
S2:Frequency analysis is carried out to the defects of sample data record data, lacking for certain kind equipment is provided by the frequency
The situation of falling into general view.When carrying out defect frequency analysis, including rejected region analysis, defect type analysis and defect cause point
Analysis.
S3:The degree of correlation quantizating index of every kind of equipment deficiency type and relation factor is assessed successively.Wherein, phase
Pass degree quantizating index includes:
(1)Device type and supplier's degree of correlation:Reflect between equipment deficiency problem and particular device type or supplier
Degree of correlation.
(2)Device location and O&M team degree of correlation:Reflect equipment deficiency problem and specific geographic position or O&M
Degree of correlation between team.
(3)Equipment life and maintenance degree of correlation:Reflect equipment deficiency problem and the phase between life-span, repair history factor
Pass degree.
(4)Defect time and weather environment degree of correlation:Reflect between equipment deficiency problem and season, weather element
Degree of correlation.
(5)Unit exception operating condition degree of correlation:Reflect between equipment deficiency problem and misoperation operating mode factor
Degree of correlation.
When assessing degree of correlation quantizating index, the defects of being divided into different defect type correlations reason and different defect causes
Caused two kinds of situations of defect type are assessed.During assessment, every kind of equipment deficiency type and primary association can be not only analyzed
Relation between the degree of correlation quantizating index of factor, and for the degree of correlation quantizating index of each relation factor, may be used also
Further to refine the details of each single item relation factor degree of correlation quantizating index.
S4:Drawn a portrait according to above-mentioned quantizating index.In portrait, every kind of equipment deficiency type and master can not only be presented
The relation between the degree of correlation quantizating index of relation factor is wanted, and quantifies to refer to for the degree of correlation of each relation factor
Mark, it can also further refine the details that each single item relation factor degree of correlation quantizating index is presented.It can not only press respectively
Equipment deficiency type and defect cause are drawn a portrait, can also be by different defect types and different defect causes respectively in the not same month
The factors such as part, position, producer, lifespan and running environment are drawn a portrait.
Embodiment one
The present embodiment is drawn a portrait as case with oil-filled transformer defect, and its step is as follows:
1st, data sample is extracted
Oil-filled transformer defect record data over the years totally 4948 are extracted from system, at the same be associated with equipment account,
Other data such as transformer station's dirt area grade residing for equipment, for subsequent analysis.
2nd, defect record data frequency analysis
(1)Analytic statistics is carried out by rejected region, its result is as shown in table 1:
Table 1
Rejected region | The frequency of occurrences |
Body | 1858 |
1048 | |
It is other | 893 |
Rejected region | 418 |
Oil line pipe | 97 |
Valve | 78 |
Respirator | 69 |
(2)Analytic statistics is carried out by defect type, its result is as shown in table 2:
Table 2
Defect type | The frequency of occurrences |
It is other | 1390 |
Seepage | 631 |
Blocking device is abnormal | 577 |
Color exception | 489 |
Tripping/malfunction | 326 |
Instruction is abnormal | 177 |
Oil level is abnormal | 171 |
Infrared test is abnormal | 99 |
Meter/oil level instruction is abnormal | 81 |
Component damage | 54 |
Component failure | 52 |
Water-level gauge instruction is abnormal | 45 |
Mechanical damage | 39 |
Performance test is abnormal | 38 |
Silica gel deliquescence changes colour | 36 |
Electrical test data exception | 28 |
Leak(Oil) | 26 |
Device is abnormal | 26 |
Poor sealing | 24 |
Power failure | 23 |
Cooling system | 23 |
Distribution transforming leakage of oil | 23 |
Cacophonia | 21 |
(3)Analytic statistics is carried out by defect cause, its result is as shown in table 3:
Table 3
Defect cause | The frequency of occurrences |
Natural environment-high temperature, high humidity, high salt | 752 |
Outgoing control is not in place | 222 |
Extended active duty | 190 |
Production raw material(Parts)It is off quality | 148 |
Loose contact | 98 |
It is other | 97 |
Product design is unreasonable | 48 |
Maintaining is not carried out in accordance with regulations | 41 |
Production raw material(Parts)It is off quality; | 38 |
Overload | 23 |
3rd, the association analysis between defect type and defect cause
(1)By taking oil-filled transformer body defect as an example, distribution is associated as shown in Figure 2 between defect type and defect cause.
(2)By taking oil-filled transformer body defect as an example, distribution is associated such as Fig. 3 institutes between defect cause and defect type
Show.
4th, drawn a portrait by the inherent law of defect type
(1)By taking oil-filled transformer as an example, statistical distribution such as Fig. 4 a between month and Fig. 4 b institutes occur for defect type and defect
Show.
(2)By taking oil-filled transformer as an example, statistical distribution such as Fig. 5 a and figure between defect type and defect generation position
Shown in 5b.
(3)By taking oil-filled transformer as an example, statistical distribution such as Fig. 6 a and figure between defect type and defect equipment manufacturer
Shown in 6b.
(4)By taking oil-filled transformer as an example, statistical distribution such as Fig. 7 a and figure between defect type and equipment lifespan
Shown in 7b.
(5)By taking oil-filled transformer as an example, statistical distribution such as Fig. 8 a and figure between defect type and equipment operating environment
Shown in 8b.
(6)According to the result of above-mentioned statistics, carried out by the inherent law of oil-filled transformer defect type using radar map
Portrait, its result as shown in Fig. 9 a ~ Fig. 9 u, wherein:
Fig. 9 a represent that defect type is " other ", and the defect type data draw a portrait result without clear and definite directive significance;
Fig. 9 b represent that defect type is " seepage ", and the defect type is more easy to send out with finding there is obvious extraordinary correlation month
It is raw in colder month, it is related to material characteristic of expanding with heat and contract with cold;
Fig. 9 c represent defect type as " blocking device abnormal ", and the defect type and manufacturer have substantially extraordinary related
Property, the plant equipment such as Jiangsu China roc is more easy to that the defect occurs;
Fig. 9 d represent that defect type is " color exception ", and the defect type surpasses with finding that month, manufacturer, dirty area's grade have
Normal correlation, but rule directive property is not very prominent;
Fig. 9 e represent that defect type is " tripping/malfunction ", and the defect type is with finding that month, manufacturer, dirty area's grade have
Extraordinary correlation, but rule directive property is not very prominent;
Fig. 9 f represent defect type as " instruction is abnormal ", and the defect type is with finding that it is obvious extraordinary that month, dirty area's grade have
Correlation, it is more easy to appear in the month in time of the year when autumn changes into winter, and dirty area's grade C regions;
Fig. 9 g represent defect type as " oil level is abnormal ", and the defect type has bright with discovery month, manufacturer, dirty area's grade
Aobvious extraordinary correlation, is more easy to appear in hotter month, and the equipment of Jiangsu Hua Pengdeng producers;
Fig. 9 h represent defect type as " infrared test is abnormal ", and the defect type has extraordinary correlation month with discovery, but
Rule directive property is not very prominent;
Fig. 9 i represent defect type as " meter/oil level instruction abnormal ", and the defect type and discovery have extraordinary related in month
Property, it is more easy to appear in hotter month;
Fig. 9 j represent that defect type is " component failure ", and the defect type is advised with finding there is extraordinary correlation month
It is not very prominent to restrain directive property;
Fig. 9 k represent defect type as " water-level gauge instruction is abnormal ", and the defect type is with finding month, manufacturer, dirty area's grade
With obvious extraordinary correlation;
Fig. 9 l represent that defect type is " mechanical damage ", and the defect type has bright with discovery month, manufacturer, dirty area's grade
Aobvious extraordinary correlation, concentration are appeared in Jiangsu Hua Peng equipment;
Fig. 9 m represent defect type as " performance test is abnormal ", and the defect type is with finding that it is extraordinary that month, manufacturer have
Correlation, but rule directive property is not very prominent;
Fig. 9 n represent that defect type is " discoloration of silica gel deliquescence ", and the defect type is with finding that it is extraordinary that month, dirty area's grade have
Correlation, visible according to correlation thermodynamic chart, the defect is more easy to appear in the month in spring of low temperature and moisture;
Fig. 9 o represent that defect type is " electrical test data exception ", and the defect type is with finding that it is super that month, manufacturer have
Normal correlation, but rule directive property is not very prominent;
Fig. 9 p represent that defect type is " leak(Oil)", the defect type is with finding that it is obvious extraordinary that month, manufacturer have
Correlation, concentrate and appear in special become in the equipment of electrician Hengyang factory;
Fig. 9 q represent defect type as " device is abnormal ", and the defect type has obvious extraordinary correlation with dirty area's grade;
Fig. 9 r represent that defect type is " poor sealing ", and the defect type has bright with discovery month, manufacturer, dirty area's grade
Aobvious extraordinary correlation, concentrate appear in it is special become electrician Xinjiang, Hengyang factory equipment in;
Fig. 9 s represent that defect type is " power failure ", and the defect type has bright with discovery month, manufacturer, dirty area's grade
Aobvious extraordinary correlation, concentrate appear in Jiangsu Hua Peng, Hefei transformer factory equipment in;
Fig. 9 t represent that defect type is " cooling system failure ", and the defect type rule directive property is not very prominent;
Fig. 9 u represent that defect type is " distribution transforming leakage of oil ", and the defect type is with finding that it is obvious extraordinary that month, dirty area's grade have
Correlation, be more easy to occur in colder month.
5th, drawn a portrait by the inherent law of defect cause
Same principle, according to above-mentioned same method and steps, you can obtain inherence of the oil-filled transformer by defect cause
Rule is drawn a portrait, as shown in Figure 10 a ~ Figure 10 j, wherein:
Figure 10 a represent that defect cause is " natural environment-high temperature, high humidity, high salt ", and the defect cause rule directive property is not very
It is prominent, but frequency of occurrence is high, the doubtful factor that multifactor mutual interference be present or fill out by mistake;
Figure 10 b represent defect cause as " outgoing control is not in place ", and the defect cause rule directive property is not very prominent;
Figure 10 c represent that defect cause is " extended active duty ", and the defect cause mainly appears on operation 30 years or so equipment of year, with
And the equipment of Jiangsu Hua Pengdeng producers;
Figure 10 d represent that defect cause is " production raw material(Parts)It is off quality ", the defect cause rule is pointed to
Property is not very prominent;
Figure 10 e represent that defect cause is " loose contact ", and the defect cause rule directive property is not very prominent;
Figure 10 f represent that defect cause is " other ", and the defect cause rule directive property is not very prominent;
Figure 10 g represent that defect cause is " product design is unreasonable ", and the defect cause is with finding that it is obvious that month, manufacturer have
Extraordinary correlation, concentrate the equipment for appearing in Nanjing power transformer Chang Deng producers;
Figure 10 h represent that defect cause be " maintaining is not carried out in accordance with regulations ", the defect cause and discovery month, dirty area's grade,
Place transformer station has obvious extraordinary correlation, and concentration appears in a few regions such as anti-city station;
Figure 10 i represent that defect cause is " production raw material(Parts)It is off quality;", the defect cause rule is pointed to
Property is not very prominent;
Figure 10 j represent that defect cause is " overload ", and the defect cause is concentrated with finding there is obvious extraordinary correlation month
Appear in summer high temperature month, and the equipment of the producer such as Siemens.
Claims (10)
- A kind of 1. power transmission and transforming equipment defect portrait method based on data mining, it is characterised in that comprise the following steps:S1:Extract sample data;S2:Frequency analysis is carried out to the defects of sample data record data;S3:The degree of correlation quantizating index of every kind of equipment deficiency type and relation factor is assessed successively;S4:Drawn a portrait according to the degree of correlation quantizating index.
- A kind of 2. power transmission and transforming equipment defect portrait method based on data mining according to claim 1, it is characterised in that The power transmission and transforming equipment includes main transformer, breaker and transmission line of electricity.
- A kind of 3. power transmission and transforming equipment defect portrait method based on data mining according to claim 1, it is characterised in that Sample data in the step S1 is from equipment account, defect record and defect analysis report, the defect analysis report The Structure of need before input.
- A kind of 4. power transmission and transforming equipment defect portrait method based on data mining according to claim 1, it is characterised in that Sample data in the step S1 includes device type and supplier data, device location and O&M team data, equipment longevity Life and overhaul data, defect time and weather environment data, unit exception operating condition data and defect situation describe data.
- A kind of 5. power transmission and transforming equipment defect portrait method based on data mining according to claim 4, it is characterised in that The device type and supplier data are used to reflect equipment with the presence or absence of closely related with particular device type or supplier Design, familial the defects of problem;Device location and O&M the team data are used to reflect that equipment whether there is and spy The defects of determining geographical position or closely related O&M team problem;The equipment life and overhaul data are used to reflect that equipment lacks The degree of correlation fallen between problem and life-span, repair history;The defect time and weather environment data are used to reflect that equipment lacks The degree of correlation fallen between problem and season, weather environment;The unit exception operating condition data are used to reflect equipment deficiency Degree of correlation between problem and misoperation operating mode;The defect situation describes data and is used as defective data tag along sort.
- A kind of 6. power transmission and transforming equipment defect portrait method based on data mining according to claim 1, it is characterised in that Analysis in the step S2 includes rejected region analysis, defect type analysis and Causes Analysis.
- A kind of 7. power transmission and transforming equipment defect portrait method based on data mining according to claim 1, it is characterised in that Degree of correlation quantizating index in the step S3 includes:(1)Device type and supplier's degree of correlation:Reflect between equipment deficiency problem and particular device type or supplier Degree of correlation;(2)Device location and O&M team degree of correlation:Reflect equipment deficiency problem and specific geographic position or O&M team Between degree of correlation;(3)Equipment life and maintenance degree of correlation:Reflect equipment deficiency problem journey related between life-span, repair history factor Degree;(4)Defect time and weather environment degree of correlation:Reflect equipment deficiency problem and the phase between season, weather element Pass degree;(5)Unit exception operating condition degree of correlation:Reflect related between equipment deficiency problem and misoperation operating mode factor Degree.
- A kind of 8. power transmission and transforming equipment defect portrait method based on data mining according to claim 1, it is characterised in that The defects of assessment in the step S3 includes different defect type correlations reason and different defect causes caused by defect type Two aspects.
- A kind of 9. power transmission and transforming equipment defect portrait method based on data mining according to claim 1, it is characterised in that Assessment in the step S3 includes refining the details of each degree of correlation quantizating index.
- 10. a kind of power transmission and transforming equipment defect portrait method based on data mining according to claim 1, its feature exist In the portrait in the step S4 is presented using radar map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710832029.XA CN107730079A (en) | 2017-09-15 | 2017-09-15 | A kind of power transmission and transforming equipment defect portrait method based on data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710832029.XA CN107730079A (en) | 2017-09-15 | 2017-09-15 | A kind of power transmission and transforming equipment defect portrait method based on data mining |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107730079A true CN107730079A (en) | 2018-02-23 |
Family
ID=61206292
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710832029.XA Pending CN107730079A (en) | 2017-09-15 | 2017-09-15 | A kind of power transmission and transforming equipment defect portrait method based on data mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107730079A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110378586A (en) * | 2019-07-08 | 2019-10-25 | 国网山东省电力公司菏泽供电公司 | Defect of transformer equipment method for early warning and system based on Dynamic Closed Loop information management |
CN110866150A (en) * | 2019-10-31 | 2020-03-06 | 南方电网调峰调频发电有限公司 | Method for rapidly generating ledger data map and overhauling defects of pre-control equipment family |
CN110866617A (en) * | 2019-11-15 | 2020-03-06 | 国网天津市电力公司 | Maintenance aid decision-making method associated with equipment life cycle |
CN112269779A (en) * | 2020-10-30 | 2021-01-26 | 国网上海市电力公司 | Big data analysis system and method for defects of power equipment |
CN113656390A (en) * | 2021-08-13 | 2021-11-16 | 国网辽宁省电力有限公司信息通信分公司 | Power equipment defect label portrait method based on defect equipment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102081765A (en) * | 2011-01-19 | 2011-06-01 | 西安交通大学 | Systematic control method for repair based on condition of electricity transmission equipment |
CN102193555A (en) * | 2011-03-11 | 2011-09-21 | 凯里供电局 | Panoramic-state monitoring system for centralized control centers |
CN102663537A (en) * | 2012-03-13 | 2012-09-12 | 凯里供电局 | Maintenance system of power equipment based on risk assessment |
CN105913185A (en) * | 2016-04-12 | 2016-08-31 | 大唐东北电力试验研究所有限公司 | Thermal power plant environment protection equipment online risk evaluation method and thermal power plant environment protection equipment online risk evaluation system |
CN106125714A (en) * | 2016-06-20 | 2016-11-16 | 南京工业大学 | Failure Rate Forecasting Method in conjunction with BP neutral net Yu two parameters of Weibull |
US20170028282A1 (en) * | 2015-07-28 | 2017-02-02 | Seiko Epson Corporation | Swing diagnosis method, recording medium, swing diagnosis apparatus, and swing diagnosis system |
CN106447531A (en) * | 2016-09-09 | 2017-02-22 | 国家电网公司 | Communication operation method |
CN106570644A (en) * | 2016-11-04 | 2017-04-19 | 国网山东省电力公司电力科学研究院 | Power transmission and transformation equipment quantization evaluation method based on statistical tool |
-
2017
- 2017-09-15 CN CN201710832029.XA patent/CN107730079A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102081765A (en) * | 2011-01-19 | 2011-06-01 | 西安交通大学 | Systematic control method for repair based on condition of electricity transmission equipment |
CN102193555A (en) * | 2011-03-11 | 2011-09-21 | 凯里供电局 | Panoramic-state monitoring system for centralized control centers |
CN102663537A (en) * | 2012-03-13 | 2012-09-12 | 凯里供电局 | Maintenance system of power equipment based on risk assessment |
US20170028282A1 (en) * | 2015-07-28 | 2017-02-02 | Seiko Epson Corporation | Swing diagnosis method, recording medium, swing diagnosis apparatus, and swing diagnosis system |
CN105913185A (en) * | 2016-04-12 | 2016-08-31 | 大唐东北电力试验研究所有限公司 | Thermal power plant environment protection equipment online risk evaluation method and thermal power plant environment protection equipment online risk evaluation system |
CN106125714A (en) * | 2016-06-20 | 2016-11-16 | 南京工业大学 | Failure Rate Forecasting Method in conjunction with BP neutral net Yu two parameters of Weibull |
CN106447531A (en) * | 2016-09-09 | 2017-02-22 | 国家电网公司 | Communication operation method |
CN106570644A (en) * | 2016-11-04 | 2017-04-19 | 国网山东省电力公司电力科学研究院 | Power transmission and transformation equipment quantization evaluation method based on statistical tool |
Non-Patent Citations (1)
Title |
---|
严英杰 等: ""基于高维随机矩阵大数据分析模型的输变电设备关键性能评估方法"", 《中国电机工程学报》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110378586A (en) * | 2019-07-08 | 2019-10-25 | 国网山东省电力公司菏泽供电公司 | Defect of transformer equipment method for early warning and system based on Dynamic Closed Loop information management |
CN110378586B (en) * | 2019-07-08 | 2021-11-09 | 国网山东省电力公司菏泽供电公司 | Power transformation equipment defect early warning method and system based on dynamic closed-loop knowledge management |
CN110866150A (en) * | 2019-10-31 | 2020-03-06 | 南方电网调峰调频发电有限公司 | Method for rapidly generating ledger data map and overhauling defects of pre-control equipment family |
CN110866150B (en) * | 2019-10-31 | 2022-09-30 | 南方电网调峰调频发电有限公司 | Method for rapidly generating ledger data map and overhauling defects of pre-control equipment family |
CN110866617A (en) * | 2019-11-15 | 2020-03-06 | 国网天津市电力公司 | Maintenance aid decision-making method associated with equipment life cycle |
CN112269779A (en) * | 2020-10-30 | 2021-01-26 | 国网上海市电力公司 | Big data analysis system and method for defects of power equipment |
CN113656390A (en) * | 2021-08-13 | 2021-11-16 | 国网辽宁省电力有限公司信息通信分公司 | Power equipment defect label portrait method based on defect equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107730079A (en) | A kind of power transmission and transforming equipment defect portrait method based on data mining | |
EP3023851B1 (en) | System and method for determining the current and future state of health of a power transformer | |
CN103218695B (en) | Secondary equipment intelligence state evaluation diagnostic system and method thereof | |
CN112104083B (en) | Power grid production command system based on situation awareness | |
CN103914791A (en) | Electrical equipment state maintenance system | |
CN104392288B (en) | A kind of primary cut-out component inspection method | |
CN104732058B (en) | A kind of appraisal procedure of various dimensions transmission facility state | |
CN105678469A (en) | Risk assessment method for relay protection equipment in intelligent substation | |
Plieva et al. | Analysis of technological damage at 110 kV substations in JSC IDGC of the North Caucasus-«Sevkavkazenergo» | |
Mirzai et al. | Regular paper Failures Analysis and Reliability Calculation for Power Transformers | |
CN104992377A (en) | Method for analyzing reliability of transformer based on service year and load level | |
CN104993594A (en) | Generator set smart grid system and realization method | |
CN106501641B (en) | A kind of transformer quality state appraisal procedure | |
CN113779005A (en) | Defect evaluation method and device for primary equipment and storage medium | |
CN116012189A (en) | Electric power facility flood disaster-stricken space heterogeneity analysis method and system | |
JP2017167708A (en) | Maintenance system and maintenance method | |
Carneiro | Substation power transformer risk management: Predictive methodology based on reliability centered maintenance data | |
Krieg et al. | Techniques and experience in on-line transformer condition monitoring and fault diagnosis in ElectraNet SA | |
Tariku et al. | Distribution transformer failure study and solution proposal in Ethiopia | |
CN106022556A (en) | Method of assessing new and old SF6 porcelain knob type breaker important component states from multiple dimensions | |
Dolezilek et al. | Remote data monitoring and data analysis for substations: A case study in implementation | |
Lappi | Asset performance management application for power system condition monitoring in an Internet of Things platform | |
CN112991092B (en) | Power-saving early warning information analysis method based on knowledge graph technology | |
CN111413955A (en) | Generator-transformer unit remote fault diagnosis system | |
Khan | Improving the reliability performance of medium voltage networks |
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: 20180223 |
|
RJ01 | Rejection of invention patent application after publication |