CN107944716A - Based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome - Google Patents
Based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome Download PDFInfo
- Publication number
- CN107944716A CN107944716A CN201711224872.6A CN201711224872A CN107944716A CN 107944716 A CN107944716 A CN 107944716A CN 201711224872 A CN201711224872 A CN 201711224872A CN 107944716 A CN107944716 A CN 107944716A
- Authority
- CN
- China
- Prior art keywords
- electrical energy
- learning
- abnormity diagnosis
- basic reason
- substation
- 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
- 238000005259 measurement Methods 0.000 title claims abstract description 16
- 230000005856 abnormality Effects 0.000 title claims abstract description 8
- 238000002405 diagnostic procedure Methods 0.000 title claims abstract description 8
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 238000003745 diagnosis Methods 0.000 claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000013135 deep learning Methods 0.000 claims abstract description 9
- 238000012937 correction Methods 0.000 claims abstract description 3
- 238000000034 method Methods 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 18
- 238000012098 association analyses Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 5
- 238000013398 bayesian method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 4
- 230000005611 electricity Effects 0.000 description 4
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000002547 anomalous effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 101000679358 Brassica oleracea var. botrytis Triose phosphate/phosphate translocator, non-green plastid, chloroplastic Proteins 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005303 weighing Methods 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses one kind based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome, comprise the following steps：Step S1, establishes substation's electrical energy metering cycle balance abnormity diagnosis rule base；Step S2, carries out electrical energy metering result data Source Tracing with clear and definite abnormal conditions；Abnormal conditions are carried out basic reason analysis by step S3 according to abnormity diagnosis rule base；Step S4, analysis corrections are carried out based on deep learning to basic reason.The present invention realizes that abnormal basic reason diagnoses by the amendment of supervised learning, unsupervised learning.
Description
Technical field
The present invention relates to power scheduling to control applied technical field, and in particular to one kind is based on the modified power transformation of learning outcome
Stand the electrical energy measurement cycle balance abnormality diagnostic method.
Background technology
Substation's balance monitoring is the integrated application to substation's gathered data result, forms complexity, causes unbalanced
Reason is numerous, O＆M inefficiency.Manually investigation mode orientation problem main at present, fault restoration poor in timeliness.Cure uneven
The search procedure for the reason that weighs, judges that involved all links diagnose automatically, intelligent decision causes unbalanced to balance automatically
Position, can be greatly improved the efficiency of substation's balance monitoring O＆M, electricity error of omission loss caused by reducing metering fault.
The content of the invention
It is an object of the invention to overcome deficiency of the prior art, there is provided one kind is based on the modified power transformation of learning outcome
Stand electrical energy measurement cycle balance abnormality diagnostic method, by supervised learning, unsupervised learning it is mutual correct realize it is abnormal
Basic reason diagnoses.
In order to solve the above technical problems, the present invention provides one kind based on learning outcome modified substation's electrical energy measurement week
Phase balances abnormality diagnostic method, it is characterized in that, comprise the following steps：
Step S1, establishes substation's electrical energy metering cycle balance abnormity diagnosis rule base；
Step S2, carries out electrical energy metering result data Source Tracing with clear and definite abnormal conditions；
Abnormal conditions are carried out basic reason analysis by step S3 according to abnormity diagnosis rule base；
Step S4, analysis corrections are carried out based on deep learning to basic reason.
Further, in step S3, if can not determine basic reason according to abnormity diagnosis rule base, with reference to history not
Equilibrium reasons carry out the correlation that current uneven reason is searched in association analysis, and association analysis result is passed through abnormity diagnosis rule
Basic reason is searched again in storehouse.
Further, association analysis uses Apriori algorithm.
Further, deep learning detailed process is in step S4：Using history case and abnormity diagnosis rule base to root
This reason carries out supervised learning training, and whether analysis basic reason is correct；Abnormal phenomenon to supervised learning can not be carried out
Whether the training of progress unsupervised learning, analysis basic reason are correct, so as to be modified to supervised learning.
Further, supervised learning uses k nearest neighbor algorithms or Nae Bayesianmethod.
Further, unsupervised learning uses clustering algorithm.
Compared with prior art, the beneficial effect that is reached of the present invention is：Accuracy rate of diagnosis is improved, reduces invalid repetition
Searching work, lifts operation management efficiency.
Brief description of the drawings
Fig. 1 is the factor for influencing substation's electrical energy metering cycle balance.
Embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiments are only used for clearly illustrating the present invention
Technical solution, and be not intended to limit the protection scope of the present invention and limit the scope of the invention.
The present invention's balances abnormality diagnostic method based on learning outcome modified substation's electrical energy measurement cycle, including following
Step：
Step S1, substation's electrical energy metering cycle balance abnormity diagnosis rule base is established according to history abnormal data record.
Electric quantity balancing normally means that power grid active loss is normal, the electric network model and actual motion of EQUILIBRIUM CALCULATION FOR PROCESS institute foundation
Wiring is consistent, electric energy meter metric results are normal, collection is normal, electricity calculates or EQUILIBRIUM CALCULATION FOR PROCESS result is accurate, almost relate to electricity
Network loss consumption, the every aspect of acquisition system operation and maintenance, realize an index operation of power networks and acquisition system are run it is comprehensive
Monitoring is closed, can be as one of the main means of collection O＆M and level of control.
Substation's electrical energy measurement cycle balance is made of dozens of or hundreds of equipment metering points of electric energy, therefore influences power transformation
The factor for electrical energy metering cycle balance of standing is numerous, specific as shown in Figure 1, being transported including such as electric energy meter operating status, acquisition channel
Row state, stoichiometric point configuration, electric network model information, EQUILIBRIUM CALCULATION FOR PROCESS method and these higher major class factors of active loss, every
A major class factor includes specific influence factor type further below, for example the influence factor included under electric energy meter operating status is set
Standby failure（The abnormal time collected judges）, wiring error, metric results mistake, clock jitter and communication module failure etc.；
The influence factor included under acquisition channel operating status have acquisition terminal failure, exchange fault, isolating device failure, circuit or
Wiring faults and network congestion etc.；The influence factor included under stoichiometric point configuration has PT configuration errors, CT configuration errors, equipment class
Type configuration error and state switching identification are wrong etc.；The influence factor included under electric network model information is with electric network model with showing
The inconsistent, electric network model in field and D5000 synchronization time differences and kainogenesis interval switching etc.；The influence that EQUILIBRIUM CALCULATION FOR PROCESS method includes because
The no-load voltage ratio that is known as big, the indivedual stoichiometric point configuration of clock jitter between main table is bigger than normal, the regular unreasonable, computational methods of Smaller load are not sent out
The defects of now arriving etc.；The influence factor included under active loss is higher have line loss is higher, loss on transmission is higher, equipment fault and circuit or
Ageing equipment etc..
According to balance monitoring calculating logic, main balance abnormal phenomenon deterministic process is as follows：
A) not calculated case is set by hand
Really belong to not satisfying the requirements and install electric energy meter progress electric quantity acquisition at the same time in circuit and high voltage side of transformer, corresponding busbar is put down
Weighing apparatus directly puts number 0%, and the corresponding stoichiometric point of remaining busbar still carries out whole station EQUILIBRIUM CALCULATION FOR PROCESS.
B) basis is calculated to judge：Classify, point situation
According to electric energy meter operating status, acquisition channel operation shape, stoichiometric point configuration, electric network model letter in electric quantity balancing influence factor
Cease four aspect influence factors and carry out following study and judge：
Electric network model：According to integration collection system grid model data structure, electric network data model is associated out, and identifies calculating
The model modification informations such as CT, PT, electric energy meter are replaced in period.
Archives integrality judges：Archives integrality is judged.Check, judge to calculate the meter for the state that puts into operation in the period
Amount point whether equipment, CTPT, electric energy meter information completely.It is typical such as electric energy meter not to be installed.
Collection situation judges：Time point association is calculated electric energy meter less than the situation of ins and outs to judge.Such as calculate the time
Newly put into operation in section, retired, acquisition abnormity, electric energy meter set and do not gather.
Ins and outs situation judges：Whether the ins and outs collected is effectively judged.As ins and outs is mutually kept to bear, abnormal ins and outs,
Ins and outs upset etc..
C) unbalance factor calculates：Further classify, point situation
Following study and judge is carried out according to EQUILIBRIUM CALCULATION FOR PROCESS method aspect influence factor in electric quantity balancing influence factor：
Smaller load：In view of electricity it is smaller in the case of the significant factor of measurement error, when busbar unbalance factor（Or whole station is uneven
Rate）The active total value of active summation output is inputted in calculation formula and is below limit value（It is tentative：Day statistical value≤24MWh, the moon count
Value≤200MWh）, directly put number 0%.
Rule calculates：（It is active total to input active total-output）/ input active total * 100%.
Acquisition abnormity calculates：Exception is judged as if there is some metering, corresponding unbalance factor is directly disposed as 100%,
But still can pair can be with calculated equilibrium part calculated equilibrium, for monitoring analysis.
In order to analyze the influence factor of field balancing abnormal phenomenon, recorded, combed according to history abnormal data in the present invention
Abnormal threshold values or abnormal judgment rule are established, establishes abnormity diagnosis rule base, description abnormal phenomenon, anomalous effects result, exception
Processing method etc., facilitates operation maintenance personnel lean operation management.
Step S2, carries out Electric energy measurement data Source Tracing with clear and definite abnormal conditions.
Source Tracing is exactly to refer to data to trace to the source herein, is progressively analyzed.When there is uneven alarm in balance monitoring system, pin
Trace to the source all data being related to, reacquire most basic data from each source, progressively investigate the quality of data and calculating
Process, passes through the clear and definite abnormal conditions of course replay.
Abnormal conditions are carried out basic reason analysis by step S3 according to abnormity diagnosis rule base.
In the several or dozens of exception found every time, there are the possibility situation of numerous kinds：A, individual event does not influence extremely
EQUILIBRIUM CALCULATION FOR PROCESS is as a result, belong to the normal variation in tolerance interval；B, individual event does not influence EQUILIBRIUM CALCULATION FOR PROCESS as a result, and meaning extremely
Power grid, metering system or acquisition system and operation exception occur；C, individual event does not influence EQUILIBRIUM CALCULATION FOR PROCESS as a result, being other extremely
Abnormal necessity or indicative information；D, individual event anomalous effects EQUILIBRIUM CALCULATION FOR PROCESS is as a result, and be main cause；E, individual event exception shadow
EQUILIBRIUM CALCULATION FOR PROCESS is rung as a result, still other are abnormal caused, can not directly be eliminated.
The present situation of a basic reason is usually present in numerous phenomenons for causing uneven reason.For the above situation,
To clear and definite abnormal conditions by abnormity diagnosis rule base, basic reason is searched.If basic reason cannot be determined, with reference to history
Uneven reason carries out association analysis lookup and the correlation of current uneven reason（The historical statistics occurred according to association,
Find out the abnormal phenomenon that can occur at the same time）, use in the embodiment of the present invention Apriori algorithm in association analysis to find out and can go out at the same time
Association analysis result, is searched basic reason by existing abnormal phenomenon again by abnormity diagnosis rule base, while supplements abnormal examine
Disconnected rule base, realizes unsupervised learning.
Step S4, basic reason diagnostic analysis result is provided based on deep learning.
The abnormal basic reason provided using step S3 modes is accurate, then can instruct to carry out failure defect elimination processing immediately.But
Situation about not analyzing in history is possible in the presence of there is new unusual combination situation, according to abnormity diagnosis rule base just not
It can be identified, so as to not give opinion or the situation to error score analysis result.
For the above situation, deep learning process is established, i.e., using history it is determined that case and the abnormity diagnosis rule crossed
Then storehouse is trained, and supervised learning, analysis basic reason knot are carried out using k nearest neighbor algorithms and Nae Bayesianmethod scheduling algorithm
Whether fruit is correct, and this analysis result is improved abnormity diagnosis rule base, while can not carry out the different of supervised learning to all
Often occur as the abnormal phenomenon with None- identified in step S3 is using clustering algorithm progress unsupervised learning, analysis basic reason result
It is whether correct, and this analysis result is improved into abnormity diagnosis rule base, so as to effectively be corrected to supervised learning.
The analysis result directly drawn using deep learning process instructs defect elimination to work.There is mistake in defect elimination work feedback
Or during unreasonable situation, invite expert to participate in, generating new training data according to expertise is used to participate in calculating, and analyzes depth
The reason for degree learning process provides error result, is modified deep learning analysis result, i.e., error result is examined by expert
Disconnected to reclassify basic reason or establish new basic reason, perfect, supplement abnormity diagnosis rule base, plays to there is supervision to learn
Practise, unsupervised learning and conventional expert judgments result are modified.
The present invention is corrected by supervised learning, unsupervised learning, the mutual of expert judgments result, with reference to every kind of method
Advantage, lifts the accuracy of diagnostic result, reduces invalid repetition searching work, lifts operation management efficiency.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, some improvement and modification, these improvements and modifications can also be made
Also it should be regarded as protection scope of the present invention.
Claims (6)
1. based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome, it is characterized in that, including it is following
Step：
Step S1, establishes substation's electrical energy metering cycle balance abnormity diagnosis rule base；
Step S2, carries out electrical energy metering result data Source Tracing with clear and definite abnormal conditions；
Abnormal conditions are carried out basic reason analysis by step S3 according to abnormity diagnosis rule base；
Step S4, analysis corrections are carried out based on deep learning to basic reason.
It is 2. according to claim 1 based on the modified substation's electrical energy measurement cycle balance abnormity diagnosis side of learning outcome
Method, it is characterized in that, it is uneven with reference to history if can not determine basic reason according to abnormity diagnosis rule base in step S3
Reason carries out the correlation that current uneven reason is searched in association analysis, association analysis result by abnormity diagnosis rule base again
Secondary lookup basic reason.
It is 3. according to claim 2 based on the modified substation's electrical energy measurement cycle balance abnormity diagnosis side of learning outcome
Method, it is characterized in that, association analysis uses Apriori algorithm.
It is 4. according to claim 1 based on the modified substation's electrical energy measurement cycle balance abnormity diagnosis side of learning outcome
Method, it is characterized in that, deep learning detailed process is in step S4：Using history case and abnormity diagnosis rule base to basic reason
Supervised learning training is carried out, whether analysis basic reason is correct；Nothing is carried out to the abnormal phenomenon that can not carry out supervised learning
Whether supervised learning training, analysis basic reason are correct, so as to be modified to supervised learning.
It is 5. according to claim 4 based on the modified substation's electrical energy measurement cycle balance abnormity diagnosis side of learning outcome
Method, it is characterized in that, supervised learning uses k nearest neighbor algorithms or Nae Bayesianmethod.
It is 6. according to claim 4 based on the modified substation's electrical energy measurement cycle balance abnormity diagnosis side of learning outcome
Method, it is characterized in that, unsupervised learning uses clustering algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711224872.6A CN107944716A (en) | 2017-11-29 | 2017-11-29 | Based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711224872.6A CN107944716A (en) | 2017-11-29 | 2017-11-29 | Based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107944716A true CN107944716A (en) | 2018-04-20 |
Family
ID=61946660
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711224872.6A Pending CN107944716A (en) | 2017-11-29 | 2017-11-29 | Based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107944716A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108710948A (en) * | 2018-04-25 | 2018-10-26 | 佛山科学技术学院 | A kind of transfer learning method based on cluster equilibrium and weight matrix optimization |
| CN108986913A (en) * | 2018-07-13 | 2018-12-11 | 希蓝科技（北京）有限公司 | A kind of optimization artificial intelligence cardiac diagnosis method and system |
| CN109710734A (en) * | 2018-12-11 | 2019-05-03 | 中国联合网络通信集团有限公司 | Automatic auditing method, device, system and the storage medium of structural knowledge |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102621411A (en) * | 2012-03-02 | 2012-08-01 | 中国电力科学研究院 | Remote diagnosis method for distributed quality of electric energy |
| US20130282314A1 (en) * | 2003-08-08 | 2013-10-24 | Electric Power Group, Llc | Wide-area, real-time monitoring and visualization system |
| 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 |
| CN103605103A (en) * | 2013-06-26 | 2014-02-26 | 广东电网公司东莞供电局 | Electric energy measurement fault intelligent diagnostic method based on S-shaped curve function |
| CN105652232A (en) * | 2015-12-30 | 2016-06-08 | 国家电网公司 | Stream processing-based electric energy metering device online abnormality diagnosis method and system |
| CN106199276A (en) * | 2016-07-25 | 2016-12-07 | 国电南瑞科技股份有限公司 | The intelligent diagnosis system of abnormal information and method in a kind of power information acquisition system |
-
2017
- 2017-11-29 CN CN201711224872.6A patent/CN107944716A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130282314A1 (en) * | 2003-08-08 | 2013-10-24 | Electric Power Group, Llc | Wide-area, real-time monitoring and visualization system |
| CN102621411A (en) * | 2012-03-02 | 2012-08-01 | 中国电力科学研究院 | Remote diagnosis method for distributed quality of electric energy |
| CN103605103A (en) * | 2013-06-26 | 2014-02-26 | 广东电网公司东莞供电局 | Electric energy measurement fault intelligent diagnostic method based on S-shaped curve function |
| 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 |
| CN105652232A (en) * | 2015-12-30 | 2016-06-08 | 国家电网公司 | Stream processing-based electric energy metering device online abnormality diagnosis method and system |
| CN106199276A (en) * | 2016-07-25 | 2016-12-07 | 国电南瑞科技股份有限公司 | The intelligent diagnosis system of abnormal information and method in a kind of power information acquisition system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108710948A (en) * | 2018-04-25 | 2018-10-26 | 佛山科学技术学院 | A kind of transfer learning method based on cluster equilibrium and weight matrix optimization |
| CN108710948B (en) * | 2018-04-25 | 2021-08-31 | 佛山科学技术学院 | Transfer learning method based on cluster balance and weight matrix optimization |
| CN108986913A (en) * | 2018-07-13 | 2018-12-11 | 希蓝科技（北京）有限公司 | A kind of optimization artificial intelligence cardiac diagnosis method and system |
| CN109710734A (en) * | 2018-12-11 | 2019-05-03 | 中国联合网络通信集团有限公司 | Automatic auditing method, device, system and the storage medium of structural knowledge |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107358366B (en) | Distribution transformer fault risk monitoring method and system | |
| CN107680368A (en) | A kind of metering device on-line monitoring and intelligent diagnosing method based on gathered data | |
| CN103337043B (en) | The method for early warning of electric power communication device running status and system | |
| CN114994441B (en) | Intelligent electric power efficiency monitoring device | |
| CN106204330A (en) | A kind of power distribution network intelligent diagnosis system | |
| CN107944716A (en) | Based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome | |
| CN105467971B (en) | A kind of second power equipment monitoring system and method | |
| CN109501834A (en) | A kind of point machine failure prediction method and device | |
| CN102289731A (en) | Method for maintaining state of power transmission equipment based on system risk | |
| CN113762604B (en) | Industrial Internet big data service system | |
| CN109949178B (en) | Method for judging and complementing power failure event of medium-voltage distribution network based on support vector machine | |
| CN108304931A (en) | A kind of Condition-based Maintenance of Substation Equipment method for diagnosing faults | |
| CN110311709A (en) | Power information acquisition system fault distinguishing method | |
| CN108879654A (en) | Based on telemetering unusual fluctuation unit exception remote diagnostic method | |
| CN108646684B (en) | Multi-product production line production period prediction method based on variability measurement | |
| CN104834305B (en) | Distribution automation terminal remote measurement exception analysis system and method based on DMS systems | |
| CN108510147A (en) | A kind of Comprehensive assessment of power quality method based on residual error volatility model | |
| CN110443481B (en) | Power distribution automation terminal state evaluation system and method based on hybrid K-nearest neighbor algorithm | |
| CN109284886A (en) | Electrical Safety management method and device based on artificial intelligence | |
| CN110096723B (en) | High-voltage switch cabinet insulation state analysis method based on operation and maintenance detection big data | |
| CN112905670A (en) | Electric energy meter system for indoor power failure fault study and judgment and indoor power failure fault study and judgment method | |
| CN109298228A (en) | A kind of Intelligence Diagnosis method and system based on photovoltaic group string current anomaly | |
| CN116050716A (en) | Intelligent park management control platform based on Internet | |
| CN113052473B (en) | Power grid risk analysis method based on fault rate and static safety analysis | |
| CN115169596A (en) | Transformer area line loss analysis method based on integrated electric quantity and line loss management system |
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: 20180420 |
|
| RJ01 | Rejection of invention patent application after publication |