CN105277818B - A kind of electric power factory equipment method for diagnosing faults based on debate logic - Google Patents
A kind of electric power factory equipment method for diagnosing faults based on debate logic Download PDFInfo
- Publication number
- CN105277818B CN105277818B CN201410359229.4A CN201410359229A CN105277818B CN 105277818 B CN105277818 B CN 105277818B CN 201410359229 A CN201410359229 A CN 201410359229A CN 105277818 B CN105277818 B CN 105277818B
- Authority
- CN
- China
- Prior art keywords
- demonstration
- fault
- electric power
- data
- factory equipment
- 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
Abstract
The present invention provides a kind of electric power factory equipment method for diagnosing faults based on debate logic.Including having the following steps:The data of the DCS on-line monitoring systems of electric power factory equipment state acquisition module acquisition access, and the data of measuring instrument that check offline;The data of acquisition are analyzed by data processing module, determine fault data, and fault data is done standardization processing so that it can be directly becoming the input data of fault diagnosis module;Fault diagnosis module provides for fault determination module according to after, and fault determination module does last judgement according to the diagnostic result of fault diagnosis module, judges guilty culprit.The present invention can solve the problem in inconsistent situation, and when reasoning task encounters predicament, breach can be rapidly found out by debate tree, smoothly completes reasoning task, when staff being made to carry out fault diagnosis, it is easier to find other nonevent Hidden faults.
Description
Technical field
The present invention relates to electric power factory equipment safety monitoring field more particularly to a kind of electric power factory equipment events based on debate logic
Hinder diagnostic method.
Background technology
The method of electric equipment diagnosis failure is generally the method handled based on analytic modell analytical model, based on signal processing at present
Method and Knowledge based engineering method three categories.These method for diagnosing faults can go deep into the behavioral characteristics of device systems this confrontation system
And real-time diagnosis of the realization to system.But failure symptom aspect is obtained without great progress, i.e., current electric power factory equipment
Method for diagnosing faults can not truly react fault signature, and the premise of Precise Diagnosis failure is exactly profoundly to understand failure machine
Reason.But at present to the mechanism of the complex fault of electric power factory equipment understand it is not deep, so it is difficult to theoretically to power plant some
The complex fault of equipment makes appropriate explanation.
The unicity that current diagnostic method is showed in troubleshooting, cannot be complete well at reasoning trouble-shooting source
Face, quickly, neatly trouble-shooting, and it is possible to error in judgement occur when there is inconsistent fault message, there is mistaken diagnosis.
Such as when there are multiple sources of trouble, because the limitation of artificial intelligence may not be able to be judged comprehensively and accurately when reasoning diagnoses
Guilty culprit.Such as in single failure, the current source of trouble can only be searched out, is not checked failure comprehensively, easily lost
Leak other Hidden faults.
For the problems above present invention, using debate logic, this method studies electric power factory equipment failure.Debate
Logic is a kind of more novel inference mechanism, can be good at solving the problem in inconsistent situation, can be preferable
Ground adapts to dialogue inside interaction between multiple agent (reasoning main body) or single agent, and encounters in reasoning task tired
When border, breach can be rapidly found out by debate tree, smoothly completes reasoning task.So the failure based on debate logic
Diagnostic method can combination failure mechanism and diagnostic knowledge comprehensively, the inducement progress that failure is occurred using these available informations
Multilevel iudge, it is progressive, trouble-shooting source procedure is preferably intuitively shown, staff is made to carry out fault diagnosis
When, it is easier to find other nonevent Hidden faults.
Electric power factory equipment can be divided into electrical equipment and rotating machinery, their failure is often complicated, and is likely to be more
A source of trouble causes an a failure either source of trouble to lead to multiple failures.Although and current method for diagnosing faults all belongs to
All it is to use traditional classical inference mechanism, and traditional classics push away in artificial intelligence diagnosis' method, but on inference mechanism
Reason mechanism very well and can not quickly complete the reasoning task of inconsistent situation, this will to encounter failure when troubleshooting
Sign is inconsistent, the concurrent situation of multiple failures and cannot integrate treat problem, where definitely finding out the source of trouble.Namely
It says, in fault diagnosis, the inconsistent situation of generally existing.
In recent years, nonmonotonic logic made great progress, and emerging debate logic is a kind of abstract debate reason
By reasoning problems have general applicability in solving inconsistent situation.And it can well portray in inconsistent situation
Problem, and solved these problems by debate theory.
Invention content
The technical problem to be solved by the present invention is to be directed to above-mentioned technical deficiency, providing one kind can solve not
The problem in consistent situation, can preferably adapt to the interaction between multiple agent (reasoning main body) or single agent
Inside dialogue, and when reasoning task encounters predicament, breach can be rapidly found out by debate tree, smoothly reasoning is appointed
Business is completed, when staff being made to carry out fault diagnosis, it is easier to find being patrolled based on debate for other nonevent Hidden faults
The electric power factory equipment method for diagnosing faults collected.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of electric power factory equipment method for diagnosing faults based on debate logic, which is characterized in that including having the following steps:
The data of the DCS on-line monitoring systems of electric power factory equipment state acquisition module (interface module) acquisition access, Yi Jili
The data of the measuring instrument of ray examination.
The data of acquisition are analyzed by data processing module, determine fault data, and fault data is done at standardization
Reason is so that it can be directly becoming the input data of fault diagnosis module.
For fault diagnosis module using debate logic fault diagnostic model as core, the input data of model comes from data processing mould
The output data of block, fault diagnosis module work in accordance with the following steps:
(1) knowledge hierarchy for fully understanding electric power factory equipment, works and is seen for use in electric power factory equipment status assessment later
Examine information.
(2) electric power factory equipment failure symptom and the initial demonstration of electric power factory equipment relevant knowledge construction are combined.
(3) it is that source builds electric power factory equipment fault diagnosis debate tree-model with initial demonstration:It will each issuable event
Hinder phenomenon list, and be classified as a demonstrations and b demonstrations, for a demonstrations for that can abrogate demonstration, b demonstrations are pros to assume demonstration, wherein a
Demonstration, results from the failure things of reason, and b is that negative side proves, and results from uncertain hypothesis derivation, mutually reciprocal between them
It refutes, according to physical fault presentation, judges the priority between a demonstrations and b demonstrations, derivation knot is obtained by the judgement of priority
Fruit.
(4) it to making inferences judgement to each node (demonstration) in electric power factory equipment fault diagnosis debate tree, derives
Terminate demonstration.
(5) it is verified to terminating demonstration, finds out the source of trouble.
Fault diagnosis module provides for fault determination module according to after, and fault determination module is examined according to fault diagnosis module
Disconnected result does last judgement, judges guilty culprit.
This patent to the effect that builds debate according to the comprehensive knowledge of electric power factory equipment and collected equipment state
Then tree-model carries out demonstration reasoning to model, to draw a conclusion.
We need in conjunction with electric power factory equipment failure symptom in this process and the knowledge in relation to failure is proved to build,
The agent of fault diagnosis is carried out firstly the need of there is certain electric power factory equipment relevant knowledge, in conjunction with knowledge and sight with debate logic with regard to saying
It examines information and obtains electric power factory equipment failure symptom.Following agent needs to confirm how to make inferences judgement to demonstration, although demonstration
Reasoning and judging be all to judge by comparing the state between proving, but for different reasoning tasks, prove reasoning
Judgment method is also different, and the demonstration that electric power factory equipment failure will produce is according to electric power factory equipment failure symptom and related event
Barrier knowledge, which is combined, to be constructed.So to judge demonstration state will failure judgement sign, and the sign of failure is basis
What the verification of electric power factory equipment malfunction was judged, that is to say, that reasoning and judging of proving herein is exactly the shape to electric power factory equipment
State is assessed.Judgement can be made inferences to demonstration, it would be desirable to which understanding, which is likely to require, uses electric power factory equipment shape in order to confirm
State appraisal procedure.At present the method for electric power factory equipment state include winding impedance, no-load voltage ratio measurement, oil chromatogram analysis, absorptance, respectively after
Electrical equipment state checks etc..Then it is combined according to electric power factory equipment failure symptom and electric power factory equipment fault knowledge, constructs initial opinion
By drawing multiple demonstrations to initially carrying out deriving, debate tree is constructed by these demonstrations initially to prove as source for card,
Finally the termination of debate seeds is proved and carries out true and false judgement, finds out source of trouble place.
The beneficial effects of the invention are as follows:We construct transformer fault debate tree-model in the present invention, and by right
Transformer debate tree fault diagnosis model is studied, and where having searched out the source of trouble, this illustrates that debate logic can be to transformation
Logical relation between device fault type and failure symptom carries out good reasoning, is investigated one by one to all kinds of failures, confirms
Guilty culprit both easily and rapidly can carry out an inspection to electric power factory equipment in this way, to find other Hidden faults,
Again can comprehensive trouble-shooting judge failure by accident and generate the maintenance policy of mistake in order to avoid there is under-enumeration failure, it is huge to cause
Big economic loss.
Description of the drawings
Fig. 1 is the module diagram of the embodiment of the present invention;
Fig. 2 is the failure cause and early stage sign of the transformer of the embodiment of the present invention;
Fig. 3 is the Fault Diagnosis Model for Power Transformer of the embodiment of the present invention;
Specific implementation mode
With reference to embodiment, the present invention is further illustrated:
Such as the application example of Fig. 1 Fig. 2 electric power factory equipment method for diagnosing faults shown in Fig. 3 based on debate logic:
The operation outlet of certain power plant is struck by lightning, Power Plant No.1 main transformer biased differential protection action, No. 1 main transformer of tripping
Three side breaker of depressor, at the same time No. 1 main transformer ontology light gas protecting also act.No. 1 main transformer capacity is
40MVA, runs before failure occurs and experiment belongs to normally.
1. the knowledge in terms of transformer fault
The fault type of transformer be it is diversified, it include attachment (such as thermometer, oil level indicator) quality problems it is straight
The insulation breakdown etc. of winding in transformer.
The common transformer fault type of the position classification occurred by failure is shown in Table 1-1.
Table 1-1 transformer fault types
The common transformer fault type classified by the generating process of failure.
(1) catastrophic discontinuityfailure
1) insulation breakdown caused by abnormal voltage (external overvoltage, interior overvoltage).
2) external short circuit accident causes winding deformation, layer short circuit.
3) natural calamity:Earthquake, fire etc..
4) power outage of subsidiary engine.
(2) failure for gradually extending and being formed year in year out
1) defective insulation of iron core, the defective insulation of defective insulation, iron core punching bolt between core-lamination stack.
2) cause the deformation of winding by extraneous short circuit repeatedly.
3) insulation ag(e)ing caused by running overload.
4) since the moisture absorption, free electric discharge cause insulating materials, insulation oil degradation.
2. transformer fault diagnosis debate tree-model is built
According to the comprehensive knowledge of debate logic, by inferenctial knowledge and observed information use based on can abrogate theoretical method and
Based on the assumption that method we can construct some demonstrations.By these demonstration reasoning and judging step by step and to them it
Between attack relationship carry out analysis and can obtain some and have relationship that is direct or indirectly contacting.These relationships are by with tree-shaped
Method drafting will obtain a debate tree.According to this process, according to the knowledge in terms of the above transformer fault, we can be with
Establish following transformer fault diagnosis debate tree-model.As shown in Figure 3.In debate tree, white nodes are pros, grayed-out nodes
For negative side, it is depicted with arrows attack, dotted line indicates attack failure, invalid with "×" demonstration, and indicating square with " √ " proves successfully.
First demonstration is proposed by pros.Pros prove us and are denoted as an, negative side proves us and is denoted as bn。
3. demonstration derives
For Fault Diagnosis Model for Power Transformer, we will be supported by demonstration, are ground based on the attack relationship between demonstration
Study carefully.To find guilty culprit.Pros can be based on some uncertain informations, it is assumed that a failure is to propose to prove, equally
Negative side can also construct a demonstration to achieve the effect that attack is square.
Tranformer protection action situation is first checked for, " differential protection action " and " light watt are sent out by gas main protection
The signal of this action ".By carrying out light gas experiment to Buchholz relay, it is found that the actuating of relay is accurate, contact is good, therefore arranges
Except there is a situation where malfunction.Then carry out the experiment of differential protection simulated failure amount, discovery action is normal, then check electric current,
Voltage circuit is without exception, therefore differential protection does not malfunction.General differential protection and protection all act and can break
It is internal fault to determine transformer fault, so we can be with can abrogate rule construct a1Demonstration.
a1Demonstration:Differential protection and protection all actInternal fault.
b1Demonstration:Characteristic gas component do not sharply increase → without internal fault.
A herein1Demonstration is that can abrogate demonstration, b1Demonstration is assumes to prove, and a1Demonstration and b1Demonstration is mutually refuted, therefore
Judge their priority." internal fault " is that " differential protection and protection all act " is abundant unnecessary reason, and " special
Sign gas component do not sharply increase " be transformer " no internal fault " necessity and sufficiency reason.Because of b1Demonstration is hypothesis opinion
Card, can only attack its argument, we should be to b1Demonstration carries out argument inspection, so We conducted No. 1 main transformer sheets
Body methane gas gas phase analysis, ontology oil chromatogram analysis, are shown in Table 1-2.As can be seen that main transformer breaks down from table 1-2
Afterwards, all kinds of characteristic gas components sharply increase and near or above demand value, this illustrates that body interior breaks down, so b1By
The argument of card is not true, then b1Demonstration is rejected, b1Demonstration loses higher priority, can not attack a1Demonstration, so a1Demonstration is anti-
B is driven1Demonstration attack.So b1It is rejected, and a1Demonstration is acceptable, so terminal block failure is excluded, oily failure,
The external faults such as casing.So by a1Continue to propose following a2、a3、a4Demonstration.
Table 1-2 gases gas-chromatography and ontology oil chromatogram analysis data (μ L/L)
a2Demonstration:Failure is tap switch failure.(due to there is no inspection tap switch, without reliable argument so the demonstration
It is invalid)
a3Demonstration:Failure is iron core failure.(due to there is no inspection iron core, without reliable argument so the demonstration is invalid)
Equilibrium criterion method is analyzed according to gas, it will be seen that wherein 6 characteristic component gas gas and oil theoretical values are much
Higher than each component content in oil sample.And wherein H2、C2H2Content accounts for main ingredient, this illustrate inside transformer there is
More serious Arcing fault.CH4、C2H4It increases sharply, solution theory value significantly larger than exists especially in CO gas gas and oil
Measured value in oil, but CO2Content does not obviously increase but, this shows that arc discharge is related to solid insulation.So we can
Using with based on can abrogate rule method failure as arc fault.
a4Demonstration:Hydrogen, acetylene account for main feature gas componentArcing fault.
b4Demonstration:Three-ratio method does not judge arc discharge → without Arcing fault.
Here a4Demonstration is that can abrogate demonstration, b4Demonstration is mutually refuted to assume demonstration, between them, first determines whether them
Between priority." Arcing fault " is the abundant inessential reason of " hydrogen, acetylene account for main feature gas component " ",
And " three-ratio method does not judge arc discharge " is " no Arcing fault " necessity and sufficiency reason.And b4Demonstration assumes that opinion
Card, therefore its argument can only be attacked, so we should be to b4Demonstration carries out argument inspection.To this, We conducted three-ratio methods
It examines.Coding rule is shown in Table 1-3, and analysis result is " 1,0,2 " in computational chart 1-2, is judged as arc discharge according to fault type,
Meet above-mentioned actual result.So b4The argument of demonstration is not true, then b4Demonstration is rejected, b4Demonstration loses higher priority, nothing
Method attacks a4Demonstration, so a4Demonstration has defendd b4Demonstration attack.Therefore b4Demonstration is rejected, therefore a4Demonstration be it is acceptable, into
And by a4Argument draws new demonstration.
Table 1-3 coding rules
Because arc discharge is a kind of high-energy discharge, is often punctured with transformer winding circle layer insulation and occurred, then
For the wire breaking or over the ground failures such as flashover and tap switch arcing.By fault waveform in main transformer differential protection action report
On see that jump-value of current is present in the sides 110kV B, C phase, respectively DIB, DIC.BC phase difference current opposite in phase, it is equal in magnitude,
This with phase fault characteristic, so it is square can by argument of phase fault with based on the assumption that one conclusion of method construct be
The demonstration of winding failure.
a5Demonstration:Winding phase fault → winding failure.
b5Demonstration:Small → non-winding phase fault of fault current.
A herein5Demonstration, b5Demonstration assumes that demonstration, so a5Demonstration can only argument attacked, therefore b5Demonstration is attempted
Prove a5The argument of demonstration is not really to attack a5Demonstration.Here b5It is more specific to prove argument, compares a5Demonstration has higher preferential
Grade, but b5Demonstration assumes that demonstration, so there is still a need for judge its argument authenticity.Fault current is 0.8Ie, and meeting definite value is
The requirement of 0.3Ie, fault current is small, so excluding winding phase fault, failure is mutually B phases or C phases.So b5Demonstration
Argument is true, and a5The argument of demonstration is not true, therefore b5Demonstration has attacked a5Demonstration, i.e. a5Demonstration is rejected, b5Prove bottom
It is acceptable.But because a5Demonstration assumes that demonstration, argument are not true, and it is true not represent conclusion not.So not representing
Failure is non-winding failure, only eliminates winding phase fault,
To transformer body and thirdly side apparatus checks, No. 1 main transformer differential protection range lead, casing,
The no abnormal situation such as breaker, rheology;There is half gas in ontology Buchholz relay.Winding is carried out to No. 1 main transformer
Deformation, winding D.C. resistance, short-circuit impedance, no-load voltage ratio, insulation resistance, absorptance test, test data are normal.According to chromatography point
The comprehensive analysis of result and protection act situation and electrical test is analysed, therefore thinks that transformer B phases or C phase 110kV windings occur
Slight shorted-turn fault.Then it is square can with it is further proposed that another with the demonstration that B phases or C phases be hypothesis.
a6Demonstration:B phases or C phase faults → winding inter-turn failure.
At this moment, negative side does not reintroduce new demonstration to attack pros, so from a1Prove a6This is proved to prove on branch
All demonstration reasonings finish, dispute terminate, in order to obtain a result, we team a6Demonstration carries out authenticity verification.From us to becoming
Depressor carries out pendant-core examination, hangs out transformer bell jar, finds there is nigrescence phenomenon at the winding leads head end of the sides C phase 110kV;Dismantle C
Phase winding screen, finds between C phase 110kV windings the 13rd and 14 cakes, turn-to-turn has spark tracking, between winding cake, turn-to-turn there is no adhesion
With it is stranded.By checking also no abnormal phenomenon to A, B phase winding.Winding interturn short-circuit event has occurred in transformer of drawing a conclusion
Barrier.
4. obtaining diagnostic result
Diagnostic result:Winding short circuit failure has occurred in the transformer.Abort situation is the sides C phase 110kV winding.Failure cause
Be find between C phase 110kV windings the 13rd and 14 cakes, turn-to-turn has spark tracking, between winding cake, turn-to-turn there is no adhesion and stranded.Together
When make a definite diagnosis A, B phase winding and do not occur abnormal phenomenon.
Protection scope of the present invention is not limited to the above embodiments, it is clear that those skilled in the art can be to this hair
It is bright to carry out various changes and deformation without departing from scope and spirit of the present invention.If these changes and deformation belong to power of the present invention
In the range of profit requirement and its equivalent technologies, then including the intent of the present invention also includes these changes and deforms.
Claims (1)
1. a kind of electric power factory equipment method for diagnosing faults based on debate logic, which is characterized in that including having the following steps:
Electric power factory equipment state acquisition module acquires the data of the DCS on-line monitoring systems of access, and the measuring instrument checked offline
The data of device;
The data of acquisition are analyzed by data processing module, determine fault data, and fault data is done standardization processing, is made
It can be directly becoming the input data of fault diagnosis module;
Fault diagnosis module is using debate logic fault diagnostic model as core, and the input data of model is from data processing module
Output data, fault diagnosis module work in accordance with the following steps:
The knowledge hierarchy for fully understanding electric power factory equipment, for use in the work of electric power factory equipment status assessment later and observed information;
In conjunction with electric power factory equipment failure symptom and the initial demonstration of electric power factory equipment relevant knowledge construction;
It is that source builds electric power factory equipment fault diagnosis debate tree-model with initial demonstration:Each issuable phenomenon of the failure is arranged
Table, and it is classified as a demonstrations and b demonstrations, a demonstrations are that can abrogate demonstration, and b demonstrations is assume that demonstration, wherein a are proved to be square, production
Being born in has the failure things of reason, and b is negative side's demonstration, results from the derivation of uncertain hypothesiss, mutually refutes between them, root
Factually border the surface phenomenon of mal-function judges the priority between a demonstrations and b demonstrations, derivation result is obtained by the judgement of priority;
To making inferences judgement to each node in electric power factory equipment fault diagnosis debate tree, termination demonstration is derived;
It is verified to terminating demonstration, finds out the source of trouble;
Fault diagnosis module provides for fault determination module according to after, and fault determination module is according to the diagnosis knot of fault diagnosis module
Fruit is cooked last judgement, judges guilty culprit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410359229.4A CN105277818B (en) | 2014-07-25 | 2014-07-25 | A kind of electric power factory equipment method for diagnosing faults based on debate logic |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410359229.4A CN105277818B (en) | 2014-07-25 | 2014-07-25 | A kind of electric power factory equipment method for diagnosing faults based on debate logic |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105277818A CN105277818A (en) | 2016-01-27 |
CN105277818B true CN105277818B (en) | 2018-08-07 |
Family
ID=55147178
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410359229.4A Active CN105277818B (en) | 2014-07-25 | 2014-07-25 | A kind of electric power factory equipment method for diagnosing faults based on debate logic |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105277818B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106199241B (en) * | 2016-06-24 | 2019-01-29 | 清华大学 | A kind of electric power station system Multiple faults diagnosis approach based on data harmonization and hypothesis testing |
CN110188087A (en) * | 2019-05-23 | 2019-08-30 | 上海长庚信息技术股份有限公司 | A kind of construction method of power plant equipment knowledge base |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH02221874A (en) * | 1989-02-21 | 1990-09-04 | Toshiba Corp | Fault diagnostic system for electric power transforming equipment |
CN103091589A (en) * | 2013-01-24 | 2013-05-08 | 中国神华能源股份有限公司 | Emergency processing method for electrical device faults |
CN103293421A (en) * | 2013-06-07 | 2013-09-11 | 云南电力调度控制中心 | Power grid fault diagnostic model and diagnostic method thereof |
-
2014
- 2014-07-25 CN CN201410359229.4A patent/CN105277818B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH02221874A (en) * | 1989-02-21 | 1990-09-04 | Toshiba Corp | Fault diagnostic system for electric power transforming equipment |
CN103091589A (en) * | 2013-01-24 | 2013-05-08 | 中国神华能源股份有限公司 | Emergency processing method for electrical device faults |
CN103293421A (en) * | 2013-06-07 | 2013-09-11 | 云南电力调度控制中心 | Power grid fault diagnostic model and diagnostic method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN105277818A (en) | 2016-01-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gouda et al. | Condition assessment of power transformers based on dissolved gas analysis | |
CN102368634B (en) | Unified information platform system for state monitoring of intelligent transformer substation | |
CN104217634B (en) | Distribution true-value simulation test method | |
Li et al. | An integrated method of set pair analysis and association rule for fault diagnosis of power transformers | |
CN102221651A (en) | Fault on-line diagnosis and early warning method of flameproof dry-type transformer for mine | |
Soni et al. | An approach to diagnose incipient faults of power transformer using dissolved gas analysis of mineral oil by ratio methods using fuzzy logic | |
CN105868770A (en) | High-voltage circuit breaker fault diagnosis method based on unsupervised learning model | |
CN108896161B (en) | A kind of assessment method of Wound iron-core transformer winding failure analog platform | |
Khan et al. | ANFIS based identification and location of paper insulation faults of an oil immersed transformer | |
Niţu et al. | Power transformer fault diagnosis using fuzzy logic technique based on dissolved gas analysis and furan analysis | |
Malik et al. | An expert system for incipient fault diagnosis and condition assessment in transformers | |
CN105277818B (en) | A kind of electric power factory equipment method for diagnosing faults based on debate logic | |
CN108037476A (en) | A kind of method of intelligent electric energy meter failure analysis | |
CN109615093A (en) | Repair of Transformer mode determines method and device | |
Rajabimendi et al. | A hybrid algorithm based on neural-fuzzy system for interpretation of dissolved gas analysis in power transformers | |
CN104360194A (en) | Fault diagnosis method for smart power grid | |
Gumilang et al. | Condition assessment method for power transformer as a part of condition based maintenance program in PLN P3B Jawa Bali | |
Taecharoen et al. | Development of dissolved gas analysis analyzing program using visual studio program | |
Rao et al. | Fuzzy logic based system to diagnose internal faults of power transformer | |
Irungu et al. | Comparison of IEC 60599 gas ratios and an integrated fuzzy-evidential reasoning approach in fault identification using dissolved gas analysis | |
Quan et al. | The application of Bayesian network theory in transformer condition assessment | |
CN111707352A (en) | Real-time monitoring method for vibration noise of transformer | |
MAMANE et al. | Artificial Neural Network Based Fault Diagnostic Tools of Power Transformer in Bauchi 132/33 kV Substation | |
Piotrowski | Probability distributions of gases dissolved in oil of failed power transformers | |
KR20190043792A (en) | Restoration system of breakdown in hydroelectric power generation equipment by an application |
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 |