CN106557607A - A kind of data summarization method of power transmission and transformation fault detection system - Google Patents
A kind of data summarization method of power transmission and transformation fault detection system Download PDFInfo
- Publication number
- CN106557607A CN106557607A CN201610841061.XA CN201610841061A CN106557607A CN 106557607 A CN106557607 A CN 106557607A CN 201610841061 A CN201610841061 A CN 201610841061A CN 106557607 A CN106557607 A CN 106557607A
- Authority
- CN
- China
- Prior art keywords
- information
- breaker
- power transmission
- network
- detection system
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000005540 biological transmission Effects 0.000 title claims abstract description 17
- 230000009466 transformation Effects 0.000 title claims abstract description 17
- 238000003745 diagnosis Methods 0.000 claims abstract description 33
- 230000009471 action Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 7
- 241000272814 Anser sp. Species 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 230000007257 malfunction Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 241001269238 Data Species 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 3
- 230000006855 networking Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a kind of data summarization method of power transmission and transformation fault detection system, comprises the following steps:The SCD model contents that the CIM content with description electrical secondary system information of primary system information are described in transformer station are integrated, the secondary system of intelligent substation topological model and correlation model based on CIM is set up;According to the relaying configuration of each element in power system, the Bayesian network fault diagnosis model of oriented-component is set up, the reliable parameter of protection device and breaker is included into basic input, the trust value between each node of Bayesian network fault diagnosis model is determined.The data summarization method of power transmission and transformation fault detection system of the present invention can collect to the various fault datas of power transmission and transformation fault detection system detection, so as to improve the reliability and data precision of diagnosis.
Description
Technical field
The present invention relates to a kind of method of summary, specifically a kind of data summarization method of power transmission and transformation fault detection system.
Background technology
When breaking down in power system, due to diagnosing the complexity of object, the limitation of means of testing, knowledge not
Accuracy, has substantial amounts of uncertain factor.Especially for huge power system, the contact between each element is tight
Complexity, its failure is probably multiple faults, the complex form such as relevant fault.In the face of the letter with uncertain (including imperfection)
Breath, traditional Fault Diagnosis for Substation are using protection and breaker warning information and Fault Recorder Information, to system mostly
In primary element positioned, in the case where information redundance is inadequate, fault-tolerance is relatively low, and the precision and depth of diagnosis are not yet
It is enough.With the development of network technology, transformer station develops towards intelligentized direction.Adopt compared to traditional transformer station secondary system
Hardwire, intelligent substation primary system adopt intelligent apparatus (IED), electrical secondary system networking.The integrated application of its information makes
The validity of Information Pull is greatly improved, and networking allows each working link of electrical secondary system effectively to be monitored,
Ornamental and controllability are greatly improved.To realize more efficient, comprehensive, deep Fault Diagnosis for Substation and appraisal procedure
There is provided chance and realization rate.At present, in terms of intelligent substation fault diagnosis, neutral net, expert system, Petri network
Deng intelligent method application widely, although there is uncertain factor pair when solving failure to a certain extent in these methods
The impact of fault diagnosis, with certain tolerance, but still can not reasonably be given when there is more complicated situation and examine
Disconnected result even causes wrong diagnosis, traces it to its cause, when being on the one hand system jam, the complexity of failure condition;The opposing party
Face is the unicity of information source used by diagnosis.Thus only go to consider from the angle of algorithm, gone using only fault message complete
Change information has certain limitation, can not fundamentally improve the reliability of diagnosis.
The content of the invention
It is an object of the invention to provide a kind of data summarization method of power transmission and transformation fault detection system, to solve the above-mentioned back of the body
The problem proposed in scape technology.
For achieving the above object, the present invention provides following technical scheme:
A kind of data summarization method of power transmission and transformation fault detection system, comprises the following steps:(1) integrate in transformer station and describe once
The CIM content of system information and the SCD model contents of description electrical secondary system information, set up the intelligent substation based on CIM
Electrical secondary system topological model and correlation model;According to the relaying configuration of each element in power system, the shellfish of oriented-component is set up
The reliable parameter of protection device and breaker is included basic input, determines Bayesian network by leaf this network fault diagnosis model
Trust value between each node of fault diagnosis model;(2) reliable parameter is defined according to secondary network warning information, according to intelligence
The configuration information of transformer station, sets up the relational matrix of device-warning information;(3) pattra leaves is carried out using error backpropagation algorithm
The training of the network parameter of this network fault diagnosis model;(4) the fault warning information obtained when using failure is used as training
Fault diagnosis model network input, calculate destination node value, the probability of malfunction value of computing element.
As further scheme of the invention:In the step (1), concrete grammar includes:(1-1) according in system each
The relaying configuration situation of element, and the internal logical relationship between element fault, protection device action and circuit breaker trip, build
The vertical Bayesian network fault diagnosis model being made up of Noisy-or, Noisy-and node;(1-2) for each protection or
Person's breaker input node, is correspondingly arranged a correct operation reliability parameter;(1-3) with protection and the action message of breaker
And the corresponding reliability parameter information of each device is used as the basic input of Bayesian network model;(1-4) calculate Noisy-or,
Noisy-and nodes take the trust value of true time.
As further scheme of the invention:In the step (1-1), correct operation reliability parameter between [0,1] it
Between, react protection device secondary information.
As further scheme of the invention:In the step (2), concrete grammar includes:(2-1) protection device and open circuit
The reliability parameter of device is defined according to secondary network warning information;(2-2) according to related to each unit protection during failure
Secondary warning information and all possible warning information related to protection device, define the reliability of protection device correct operation
Degree;(2-3) all possible alarm letter related according to secondary warning information related to breaker during failure and with breaker
Breath, defines the reliability of breaker correct operation;(2-4) configuration information according to transformer station, sets up the pass of device-warning information
It is matrix, the device related to warning information in searching matrix, and the reliability of each device of statistical computation.
As further scheme of the invention:In the step (2-1), concrete grammar is:For protection device, with its phase
The secondary network warning information of pass includes:Protection device self-inspection information, SV message communications link-state information and GOOSE tripping operation is logical
Letter link-state information;For breaker, relative secondary network warning information includes:Protection device self-inspection information and
GOOSE tripping operation communication link state information.
As further scheme of the invention:In the step (3), concrete grammar is:For Noisy-or, Noisy-
The Bayesian network fault diagnosis model of and nodes composition, enters the training of line parameter using error backpropagation algorithm, using ladder
Degree descent algorithm causes the mean square deviation between the measured value of target variable and calculated value to reach minimum.
Compared with prior art, the invention has the beneficial effects as follows:The data summarization of power transmission and transformation fault detection system of the present invention
Method can to power transmission and transformation fault detection system detection various fault datas collect, so as to improve diagnosis reliability and
Data precision.
Specific embodiment
Below the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment
Only a part of embodiment of the invention, rather than the embodiment of whole.Based on the embodiment in the present invention, the common skill in this area
The every other embodiment obtained under the premise of creative work is not made by art personnel, belongs to the model of present invention protection
Enclose.
In the embodiment of the present invention, a kind of data summarization method of power transmission and transformation fault detection system is comprised the following steps:(1)
The SCD model contents that the CIM content with description electrical secondary system information of primary system information are described in transformer station are integrated, is set up
Secondary system of intelligent substation topological model and correlation model based on CIM;Matched somebody with somebody according to the protection of each element in power system
Put, set up the Bayesian network fault diagnosis model of oriented-component, the reliable parameter of protection device and breaker is included substantially
Input, determines the trust value between each node of Bayesian network fault diagnosis model;(2) it is fixed according to secondary network warning information
Adopted reliable parameter, according to the configuration information of intelligent substation, sets up the relational matrix of device-warning information;(3) it is anti-using error
The training of the network parameter of Bayesian network fault diagnosis model is carried out to propagation algorithm;(4) failure obtained when by failure is accused
Input of the alarming information as the fault diagnosis model network for having trained, calculates the value of destination node, and the failure of computing element is general
Rate value;In the step (1), concrete grammar includes:(1-1) according to the relaying configuration situation of each element in system, Yi Jiyuan
Internal logical relationship between part failure, protection device action and circuit breaker trip, sets up and is saved by Noisy-or, Noisy-and
The Bayesian network fault diagnosis model of point composition;(1-2) for each protection or breaker input node, it is correspondingly arranged
One correct operation reliability parameter;(1-3) joined with the action message of breaker and the corresponding reliability of each device with protecting
Basic input of the number information as Bayesian network model;(1-4) calculate the letter that Noisy-or, Noisy-and node takes true time
Appoint value;In the step (1-1), correct operation reliability parameter reacts protection device secondary information between [0,1];Institute
State in step (2), concrete grammar includes:(2-1) reliability parameter of protection device and breaker is believed according to secondary network alarm
Breath is defined;(2-2) according to secondary warning information related to each unit protection during failure and the institute related with protection device
Possible warning information, defines the reliability of protection device correct operation;(2-3) according to during failure related to breaker two
Secondary warning information and all possible warning information related to breaker, define the reliability of breaker correct operation;(2-4)
According to the configuration information of transformer station, the relational matrix of device-warning information is set up, the dress related to warning information in searching matrix
Put, and the reliability of each device of statistical computation;In the step (2-1), concrete grammar is:It is for protection device, associated therewith
Secondary network warning information include:Protection device self-inspection information, SV message communications link-state information and GOOSE tripping operation communication
Link-state information;For breaker, relative secondary network warning information includes:Protection device self-inspection information and
GOOSE tripping operation communication link state information;In the step (3), concrete grammar is:For Noisy-or, Noisy-and node
The Bayesian network fault diagnosis model of composition, enters the training of line parameter using error backpropagation algorithm, is declined using gradient
Algorithm causes the mean square deviation between the measured value of target variable and calculated value to reach minimum.
In theory the protection of circuit both sides all should action make its corresponding circuit breaker trip, the protection structure of circuit both sides
Noisy-and nodes.For every side, protection can be divided three classes again:Main protection, back-up protection and adjacent elements it is remote
Back-up protection.Any sort action in this three classes protection makes its correspondence circuit breaker trip, can cut off failure, therefore this three class
Protection composition is Noisy-or nodes.In the case that protection device is operating normally, protection device and breaker actuation should be
Consistent, therefore protect and its correspondence breaker composition Noisy-and node.For each protection or breaker input section
Point, correspondence have a correct operation reliability parameter, and the parameter reacts protection device secondary information between [0,1].When
When breaking down in system, suspected fault element is identified according to outage area first, built for each suspected fault element
Found corresponding fault diagnosis model.
For the Bayesian network fault diagnosis model of described Noisy-or, Noisy-and node composition, using error
Back-propagation algorithm enters the training of line parameter.
For the fault diagnosis model for establishing, the training of network parameter is carried out using error backpropagation algorithm.
For the fault network model of the different type element for having trained, the fault warning information obtained during by failure is made
For the input of network:When the protection or breaker actuation information that obtain are 1 (i.e. protection or breaker actuation), protection or breaking
The input value of device node should be:RP(RB);When obtain protection or breaker actuation information be 0 (i.e. protection or breaker not
Action) when, the input value of protection or breaker node should be:1-RP(RB);When primary system loss of learning, protection or disconnected
The status information on road is indefinite, and the input of the node is defined as RP (RB) also.
The input value of respective nodes is input in network, successively reasoning and calculation goes out the trust value of destination node so as to obtain
The probability of malfunction value of the element.The all fault elements being likely to occur during for failure will be calculated, and the event to them
Barrier probable value is ranked up, by the probability of malfunction threshold value judgment component that set whether failure.It has been generally acknowledged that probability of malfunction
Value is fault element apparently higher than other elements.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of spirit or essential attributes without departing substantially from the present invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit is required rather than described above is limited, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.
Moreover, it will be appreciated that although this specification is been described by according to embodiment, not each embodiment is only wrapped
Containing an independent technical scheme, this narrating mode of specification is only that those skilled in the art should for clarity
Using specification as an entirety, the technical scheme in each embodiment can also Jing it is appropriately combined, form those skilled in the art
Understandable other embodiment.
Claims (6)
1. a kind of data summarization method of power transmission and transformation fault detection system, it is characterised in that comprise the following steps:(1) integrate and become
The CIM content of primary system information and the SCD model contents of description electrical secondary system information are described in power station, foundation is based on
The secondary system of intelligent substation topological model of CIM and correlation model;According to the relaying configuration of each element in power system, build
The reliable parameter of protection device and breaker is included basic input by the Bayesian network fault diagnosis model of vertical oriented-component,
Determine the trust value between each node of Bayesian network fault diagnosis model;(2) can according to the definition of secondary network warning information
By parameter, according to the configuration information of intelligent substation, the relational matrix of device-warning information is set up;(3) reversely passed using error
Broadcasting algorithm carries out the training of network parameter of Bayesian network fault diagnosis model;(4) the fault warning letter obtained when by failure
The input as the fault diagnosis model network for having trained is ceased, the value of destination node, the probability of malfunction value of computing element is calculated.
2. the data summarization method of power transmission and transformation fault detection system according to claim 1, it is characterised in that the step
(1), in, concrete grammar includes:(1-1) according to the relaying configuration situation of each element in system, and element fault, protection dress
The internal logical relationship between action and circuit breaker trip is put, the Bayes being made up of Noisy-or, Noisy-and node is set up
Network fault diagnosis model;(1-2) for each protection or breaker input node, being correspondingly arranged a correct operation can
By spending parameter;(1-3) to protect action message and the corresponding reliability parameter information of each device with breaker as pattra leaves
The basic input of this network model;(1-4) calculate the trust value that Noisy-or, Noisy-and node takes true time.
3. the data summarization method of power transmission and transformation fault detection system according to claim 2, it is characterised in that the step
(1-1), in, correct operation reliability parameter reacts protection device secondary information between [0,1].
4. the data summarization method of power transmission and transformation fault detection system according to claim 1, it is characterised in that the step
(2), in, concrete grammar includes:(2-1) reliability parameter of protection device and breaker is carried out according to secondary network warning information
Definition;(2-2) it is related according to secondary warning information related to each unit protection during failure and with protection device to be possible to
Warning information, define protection device correct operation reliability;(2-3) according to secondary alarm related to breaker during failure
Information and all possible warning information related to breaker, define the reliability of breaker correct operation;(2-4) according to change
The configuration information in power station, sets up the relational matrix of device-warning information, the device related to warning information in searching matrix, and
The reliability of each device of statistical computation.
5. the data summarization method of power transmission and transformation fault detection system according to claim 4, it is characterised in that the step
(2-1), in, concrete grammar is:For protection device, relative secondary network warning information includes:Protection device self-inspection is believed
Breath, SV message communications link-state information and GOOSE tripping operation communication link state information;For breaker, relative two
Secondary network alarm information includes:Protection device self-inspection information and GOOSE tripping operation communication link state information.
6. the data summarization method of power transmission and transformation fault detection system according to claim 1, it is characterised in that the step
(3), in, concrete grammar is:For the Bayesian network fault diagnosis model of Noisy-or, Noisy-and node composition, utilize
Error backpropagation algorithm enters the training of line parameter, using gradient descent algorithm so that the measured value and calculated value of target variable it
Between mean square deviation reach minimum.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610841061.XA CN106557607A (en) | 2016-09-22 | 2016-09-22 | A kind of data summarization method of power transmission and transformation fault detection system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610841061.XA CN106557607A (en) | 2016-09-22 | 2016-09-22 | A kind of data summarization method of power transmission and transformation fault detection system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106557607A true CN106557607A (en) | 2017-04-05 |
Family
ID=58417407
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610841061.XA Pending CN106557607A (en) | 2016-09-22 | 2016-09-22 | A kind of data summarization method of power transmission and transformation fault detection system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106557607A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113691311A (en) * | 2021-08-27 | 2021-11-23 | 中国科学院半导体研究所 | Fault positioning method of optical network, electronic equipment and computer readable storage medium |
CN114241727A (en) * | 2021-11-26 | 2022-03-25 | 国网新疆电力有限公司巴州供电公司 | Intelligent diagnosis early warning system, method and device for power transformation equipment |
CN117495338A (en) * | 2023-09-30 | 2024-02-02 | 国网江苏省电力有限公司信息通信分公司 | System fault diagnosis and repair method based on automatic operation and maintenance |
US11899075B2 (en) * | 2020-08-04 | 2024-02-13 | Maschinenfabrik Reinhausen Gmbh | Device for determining an error probability value for a transformer component and a system having such a device |
-
2016
- 2016-09-22 CN CN201610841061.XA patent/CN106557607A/en active Pending
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11899075B2 (en) * | 2020-08-04 | 2024-02-13 | Maschinenfabrik Reinhausen Gmbh | Device for determining an error probability value for a transformer component and a system having such a device |
CN113691311A (en) * | 2021-08-27 | 2021-11-23 | 中国科学院半导体研究所 | Fault positioning method of optical network, electronic equipment and computer readable storage medium |
CN113691311B (en) * | 2021-08-27 | 2022-12-06 | 中国科学院半导体研究所 | Fault positioning method of optical network, electronic equipment and computer readable storage medium |
CN114241727A (en) * | 2021-11-26 | 2022-03-25 | 国网新疆电力有限公司巴州供电公司 | Intelligent diagnosis early warning system, method and device for power transformation equipment |
CN117495338A (en) * | 2023-09-30 | 2024-02-02 | 国网江苏省电力有限公司信息通信分公司 | System fault diagnosis and repair method based on automatic operation and maintenance |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106557607A (en) | A kind of data summarization method of power transmission and transformation fault detection system | |
CN104297637B (en) | The power system failure diagnostic method of comprehensive utilization electric parameters and time sequence information | |
CN103308824B (en) | Power system fault diagnostic method based on probability Petri net | |
CN107394773B (en) | Distribution network information physical system reliability assessment method considering fault processing overall process | |
CN105678337B (en) | Information fusion method in intelligent substation fault diagnosis | |
CN103336222B (en) | Power system fault diagnosis method based on fuzzy reasoning pulse neurolemma system | |
CN103001328B (en) | Fault diagnosis and assessment method of intelligent substation | |
CN103840967B (en) | A kind of method of fault location in power telecom network | |
CN104901306B (en) | Power grid operation safety margin calculating method taking cascading faults into consideration | |
CN102721901B (en) | Based on the electric network failure diagnosis method of sequential Bayes knowledge base TBKB | |
CN106021666A (en) | Mountain fire disaster early-warning method for overhead power transmission line | |
CN106253270A (en) | Electric system vulnerable line identifying method and system | |
CN106532940A (en) | Alarm signal action and time sequence logic relationship analysis method of intelligent substation | |
CN107870287A (en) | A kind of localization method of distribution network failure | |
CN108039987A (en) | Critical infrastructures fragility assessment method based on multi-layer-coupled relational network | |
CN106226658A (en) | A kind of electric network failure diagnosis method based on multi-data fusion | |
CN105391064A (en) | Accurate hidden failure model-based cascading failure risk evaluation method for power transmission system | |
CN107122878A (en) | A kind of Study of Risk Evaluation Analysis for Power System method based on big data and human factor | |
CN106483425A (en) | The method for diagnosing faults of pulse nerve membranous system based on Triangular Fuzzy Number and device | |
CN102802182A (en) | Fault diagnosis device and method for wireless sensor network | |
CN106771848A (en) | A kind of electric network failure diagnosis method based on the fusion of topological primitive information | |
CN104217120A (en) | Method for evaluating reliability of digital transformer substation relay protection system | |
CN106771853A (en) | A kind of intelligent power network method for diagnosing faults based on event origin | |
CN104600680A (en) | Intelligent alarming method based on data fusion | |
Noorazar et al. | Data‐driven operation of the resilient electric grid: A case of COVID‐19 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170405 |