CN105678337A - Information fusion method in intelligent transformer station fault diagnosis - Google Patents
Information fusion method in intelligent transformer station fault diagnosis Download PDFInfo
- Publication number
- CN105678337A CN105678337A CN201610018296.9A CN201610018296A CN105678337A CN 105678337 A CN105678337 A CN 105678337A CN 201610018296 A CN201610018296 A CN 201610018296A CN 105678337 A CN105678337 A CN 105678337A
- Authority
- CN
- China
- Prior art keywords
- fault
- information
- protection
- warning information
- chopper
- 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.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 58
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000009471 action Effects 0.000 claims description 14
- 230000007257 malfunction Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 5
- 241000272814 Anser sp. Species 0.000 claims description 4
- 230000007547 defect Effects 0.000 abstract description 3
- 230000001012 protector Effects 0.000 abstract 1
- 230000006855 networking Effects 0.000 description 3
- 239000008186 active pharmaceutical agent Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007935 neutral effect Effects 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
Abstract
The invention discloses an information fusion method in intelligent transformer station fault diagnosis. According to a protection configuration of each component in a system, a component-oriented Bayes network fault diagnosis model is built. Reliable parameters of a protector and a breaker are used as basic inputs of the model, and the model decides trust values among nodes of the model. The reliable parameters are defined on the basis of secondary network warning information. According to configuration information of an intelligent transformer station, a device - warning information relation matrix is set up. An error back propagation algorithm is used for training network parameters of the model. Fault warning information obtained during fault is used as input of a trained fault network. The value of a target node is calculated so that a fault probability of the component is obtained. The method solves the defect of using protection and breaker information only during primary system diagnosis. The method widens information sources and integrates information from multiple sources, so that the precision and reliability of diagnosis are improved.
Description
Technical field
The present invention relates to the information fusion method in a kind of intelligent substation fault diagnosis.
Background technology
Power system when breaking down, owing to diagnosing the inexactness of the complexity of object, the limitation of means of testing, knowledge, also exist substantial amounts of uncertain factor. Especially for huge power system, the contact between each element is closely complicated, and its fault is probably the complex forms such as multiple faults, relevant fault. In the face of having the information of uncertainty (including imperfection); traditional Fault Diagnosis for Substation is utilize protection and chopper warning information and Fault Recorder Information mostly; primary element in system is positioned; when information redundance is inadequate; fault-tolerance is relatively low, and the precision of diagnosis and the degree of depth are also inadequate. Along with the development of network technology, transformer station develops towards intelligentized direction. Adopting hardwire compared to tradition transformer station secondary system, intelligent substation primary system adopts intelligent apparatus (IED), electrical secondary system networking. The integrated application of its information makes the effectiveness of Information Pull be greatly improved, and networking makes each working link of electrical secondary system effectively to be monitored, ornamental and controllability are greatly improved. Chance and realization rate is provided for realizing more efficient, comprehensive, deep Fault Diagnosis for Substation and appraisal procedure
At present, in intelligent substation fault diagnosis, neutral net, specialist system, the application of the intelligent methods such as Petri network is widely, These methods, while there is the uncertain factor impact on fault diagnosis when to some extent solving fault, there is certain tolerance, but still can not reasonably provide diagnostic result when more complicated situation occurs and even cause wrong diagnosis, trace it to its cause, when being system jam on the one hand, the complexity of failure condition; It is the unicity of diagnosis information source used on the other hand. Thus only go to consider from the angle of algorithm, utilize only fault message to go completion information to have certain limitation, can not fundamentally improve the reliability of diagnosis.
Summary of the invention
The present invention is to solve the problems referred to above, propose the information fusion method in a kind of intelligent substation fault diagnosis, this method sets up the fault diagnosis model for element first with Bayesian network, the multi-source information from primary system and electrical secondary system obtained during with the system failure is input, calculated by Bayesian Network Inference and obtain element fault probit, thus determining fault element, it is possible to be effectively applicable to the location of fault element during Intelligent transformer station fault and the diagnosis of transformer station secondary system device and analysis.
To achieve these goals, the present invention adopts the following technical scheme that
Information fusion method in a kind of intelligent substation fault diagnosis, comprises the following steps:
(1) according to the relaying configuration of each element in power system, set up the Bayesian network fault diagnosis model of oriented-component, include the reliable parameter of protection device and chopper in basic input, it is determined that the trust value between each node of Bayesian network fault diagnosis model;
(2) define reliable parameter, the configuration information according to intelligent substation according to secondary network warning information, set up the relational matrix of device-warning information;
(3) error backpropagation algorithm is utilized to carry out the training of network parameter of Bayesian network fault diagnosis model;
(4) the fault warning information obtained time using fault, as the input of the fault diagnosis model network trained, calculates the value of destination node, the probability of malfunction value of computing element.
In described step (1), concrete grammar includes:
(1-1) according to the relaying configuration situation of each element in system, and element fault, internal logical relationship between protection device action and circuit breaker trip, set up the Bayesian network fault diagnosis model being made up of Noisy-or, Noisy-and node;
(1-2) for each protection or chopper input node, it is correspondingly arranged a correct operation reliability parameter;
(1-3) input using the reliability parameter information that protection is corresponding with the action message of chopper and each device as the basic of Bayesian network model;
(1-4) calculate Noisy-or, Noisy-and node and take the trust value of true time.
Further, in described step (1-1), correct operation reliability parameter is between [0,1], and device secondary information is protected in reaction.
In described step (1-4), Noisy-or, Noisy-and node takes the trust value computing method of true time and is:
Wherein parameter cijIt is NjSingle premise NiTo N when taking true valuejThe genuine degree of recognition, namely from node NiTo node NjConditional probability, conditional probability is obtained by parameter training.
In described step (2), concrete grammar includes:
(2-1) reliability parameter protecting device and chopper is defined according to secondary network warning information;
(2-2) secondary warning information relevant to each unit protection time according to fault and all possible warning information relevant with protection device, the reliability of definition protection device correct operation;
(2-3) secondary warning information relevant to chopper time according to fault and all possible warning information relevant with chopper, the reliability of definition chopper correct operation;
(2-4) configuration information according to transformer station, sets up the relational matrix of device-warning information, finds device relevant to warning information in matrix the reliability of each device of statistical computation.
In described step (2-1), method particularly includes: for protection device, relative secondary network warning information includes: protection self-check of device information, SV message communication link-state information and GOOSE tripping operation communication link state information; For chopper, relative secondary network warning information includes: protection self-check of device information and GOOSE tripping operation communication link state information.
Further, in described step (2-2), define RPFor protecting the reliability of device action:
Wherein SiSecondary warning information relevant to protection P when being fault, SnIt is all possible warning information relevant to protection P.
In described step (2-3), define RBReliability for release unit action:
Wherein SiSecondary warning information relevant to chopper B when being fault, SnIt is all possible warning information relevant to chopper B.
In described step (3), method particularly includes: for the Bayesian network fault diagnosis model of Noisy-or, Noisy-and node composition, utilize error backpropagation algorithm to carry out the training of parameter, utilize gradient descent algorithm that the mean square deviation between the measured value of target variable and value of calculation is reached minimum.
In described step (4); method particularly includes: the fault network model of the dissimilar element for having trained; the fault warning information obtained during using fault is as the input of network: when the protection obtained or breaker actuation, the input value of protection or chopper node should be: RP(RB); When the protection obtained or chopper do not have action, the input value of protection or chopper node should be: 1-RP(RB); When primary system loss of learning, the status information of protection or open circuit is indefinite, also the input of this node is defined as RP(RB)。
In described step (4), the input value of respective nodes is input in network, successively reasoning and calculation goes out the trust value of destination node thus obtaining the probability of malfunction value of this element, the all fault elements being likely to occur during for fault are all calculated, and its probability of malfunction value is ranked up, by the probability of malfunction threshold value judgment component that set whether fault.
The invention have the benefit that
(1) feature of combined with intelligent transformer station of the present invention, make full use of secondary network information, by defining the reliability parameter of protection device and chopper correct operation, solve and primary system diagnosis process only utilizes the defect existed when protection and chopper information;
(2) present invention is from the angle widening information source, merges multi-source information, in combination with the powerful fault tolerance of Bayesian network, improves degree of accuracy and the reliability of diagnosis.
Accompanying drawing explanation
The Circuit fault diagnosis model schematic that Fig. 1 (a) is the present invention;
The bus-bar fault diagnostic cast schematic diagram that Fig. 1 (b) is the present invention;
The Fault Diagnosis Model for Power Transformer schematic diagram that Fig. 1 (c) is the present invention;
Fig. 2 is the schematic flow sheet of the training Bayesian network fault diagnosis model of the present invention.
Detailed description of the invention:
Below in conjunction with accompanying drawing, the invention will be further described with enforcement.
The feature of combined with intelligent transformer station, when system breaks down, not only primary system can change in generation state, the electrical secondary system of networking also can send a lot of warning information, secondary warning information not only reflects fault signature to a certain extent, it is also possible to reflect the status information of device itself. When carrying out intelligent substation fault diagnosis, transformer station secondary system fault message is taken into account, it is possible to greatly improve the redundancy of information, it is to avoid occur owing to information deficiency causes the coarse problem of fault diagnosis. Utilize the reliability parameter of secondary warning information definition protection device and chopper correct operation; solve and primary system diagnosis process only utilizes the defect existed when protection and chopper information; from the angle widening information source; information in conjunction with first and second system; there is provided more comprehensively information to the diagnosis of system, improve the degree of accuracy of diagnosis.
With merge secondary information intelligent substation fault diagnosis for core, existing summary of the invention is described further.
Step one: the foundation of fault diagnosis model.
1) as shown in Fig. 1 (a), Fig. 1 (b) and Fig. 1 (c); according to the relaying configuration situation of each element in system; and element fault, internal logical relationship between protection device action and circuit breaker trip, set up the Bayesian network fault diagnosis model being made up of Noisy-or, Noisy-and node.
For circuit, when circuit L breaks down, the protection of circuit both sides all action should make its corresponding circuit breaker trip in theory, the protection structure Noisy-and node of circuit both sides. For every side, protection can be divided three classes again: the remote back-up protection of main protection, back-up protection and adjacent elements. Any sort action in the protection of this three class makes its corresponding circuit breaker trip, can excise fault, and therefore this three class protection composition is Noisy-or node. When protection device regular event, protection device should be consistent with breaker actuation, therefore protection and its corresponding chopper composition Noisy-and node.
2) for each protection or chopper input node; correspondence has a correct operation reliability parameter; this parameter is between [0; 1] between; reaction protection device secondary information; protection node M LP in Fig. 1 (a), by define reliability parameter change original non-zero namely 1 input, its reliability parameter RPDefinition and calculate be described in detail in technical scheme.
3) when system breaks down, first identify suspected fault element according to outage area, set up corresponding fault diagnosis model for each suspected fault element.
Step 2: reliability parameter calculates.
1) describe in detail in technical scheme, RPFor protecting the reliability of device action:
Wherein SiSecondary warning information relevant to protection P when being fault, SnIt is all possible warning information relevant to protection P.
2)RBReliability for breaker actuation:
Wherein SiSecondary warning information relevant to chopper B when being fault, SnIt is all possible warning information relevant to chopper B.
Owing to there is certain logical relation and the shielded control of chopper between chopper and protection; thus when the warning information of protection device mistake occurs; the reliability of corresponding chopper correct operation also reduces, and the relation of protection and chopper can be reflected by the relational matrix of following apparatus-warning information.
3) configuration information according to intelligent substation, sets up the relational matrix DS of device-warning informationm×n
Each of which row DiRepresent a device of transformer station, including various IED intelligent apparatus such as protection, chopper intelligent terminal, switches, m dimension altogether; Every string SjRepresent warning information possible in transformer station, altogether n dimension. Element in matrix non-zero namely 1, as device DiWith warning information SjBetween be 1 when there is incidence relation, be otherwise 0.
Network topology structure according to system can define element-protection matrix EP simultaneouslya×b, protection-chopper matrix PBb×c, the relaying configuration situation of element is expressed by the form of mathematics. Being shown below, row element represents element Ei, column element represents protection Pi, element 1 represents element EiProtected PiProtection. Classification for distinguishing protection, for instance main protection, back-up protection etc., it is possible to define multiple such matrix.
When breaking down, for suspected fault element, the method searched for by matrix finds the protection and relevant chopper thereof that element is corresponding. Simultaneously for secondary network occurs a large amount of warning information, search matrix D Sm×nFind the relevant warning information of the protection of element correspondence and chopper, add up and calculate the reliability of each device correct operation.
Step 3: the training of network parameter.
For the Bayesian network fault diagnosis model that Noisy-or, Noisy-and node described in step one forms, error backpropagation algorithm is utilized to carry out the training of parameter. The basic skills of training describes in detail in technical scheme, and flow chart (such as Fig. 2) specifically introduces training step.
For the fault diagnosis model established, error backpropagation algorithm is utilized to carry out the training of network parameter.
For the Bayesian network fault diagnosis model of a kind of described Noisy-or, Noisy-and node composition of step, error backpropagation algorithm is utilized to carry out the training of parameter. Error backpropagation algorithm is generally used for the training of multilayer neural network, utilizes gradient descent algorithm that the mean square deviation between the measured value of target variable and value of calculation is reached minimum. The computing formula of mean square deviation given below:
WhereinFor node NjActual value for its degree of belief of true time; Bel (Nj=True) it is Bayesian network value of calculation, (2) formula gives the gradient calculation formula of Noisy-or, Noisy-and node:
Wherein η is Studying factors, δjIt is node NjError. For output node:
To hiding node, node NjPropagate back to its father node NiError be:
Train each time according to error deltajCalculate gradient deltaij, remove corrected parameter by gradient, then re-training calculate, until error meets requirement.
Will be trained for each different types of element, as shown in table 1, for the training sample of line fault model, generally for obtaining more optimal network parameter, it is possible to increase training sample according to practical operation situation.
Table 1. line fault model training
Step 4: element fault probability calculation
The fault network model of the dissimilar element for having trained; the fault warning information obtained during using fault is as the input of network: when the protection obtained or breaker actuation information are 1 (protection or breaker actuation), the input value of protection or chopper node should be: RP(RB); When the protection obtained or breaker actuation information are 0 (namely protection or chopper are failure to actuate), the input value of protection or chopper node should be: 1-RP(RB); When primary system loss of learning, the status information of protection or open circuit is indefinite, also the input of this node is defined as RP(RB)。
Being input in network by the input value of respective nodes, successively reasoning and calculation goes out the trust value of destination node thus obtaining the probability of malfunction value of this element. The all fault elements being likely to occur during for fault will be calculated, and their probability of malfunction value is ranked up, by the probability of malfunction threshold value judgment component that set whether fault. It has been generally acknowledged that probability of malfunction value apparently higher than other elements for fault element.
The specific embodiment of the present invention is described in conjunction with accompanying drawing although above-mentioned; but not limiting the scope of the invention; one of ordinary skill in the art should be understood that; on the basis of technical scheme, those skilled in the art need not pay various amendments or deformation that creative work can make still within protection scope of the present invention.
Claims (10)
1. the information fusion method in intelligent substation fault diagnosis, is characterized in that: comprise the following steps:
(1) according to the relaying configuration of each element in power system, set up the Bayesian network fault diagnosis model of oriented-component, include the reliable parameter of protection device and chopper in basic input, it is determined that the trust value between each node of Bayesian network fault diagnosis model;
(2) define reliable parameter, the configuration information according to intelligent substation according to secondary network warning information, set up the relational matrix of device-warning information;
(3) error backpropagation algorithm is utilized to carry out the training of network parameter of Bayesian network fault diagnosis model;
(4) the fault warning information obtained time using fault, as the input of the fault diagnosis model network trained, calculates the value of destination node, the probability of malfunction value of computing element.
2. the information fusion method in a kind of intelligent substation fault diagnosis as claimed in claim 1, is characterized in that: in described step (1), concrete grammar includes:
(1-1) according to the relaying configuration situation of each element in system, and element fault, internal logical relationship between protection device action and circuit breaker trip, set up the Bayesian network fault diagnosis model being made up of Noisy-or, Noisy-and node;
(1-2) for each protection or chopper input node, it is correspondingly arranged a correct operation reliability parameter;
(1-3) input using the reliability parameter information that protection is corresponding with the action message of chopper and each device as the basic of Bayesian network model;
(1-4) calculate Noisy-or, Noisy-and node and take the trust value of true time.
3. the information fusion method in a kind of intelligent substation fault diagnosis as claimed in claim 2, is characterized in that: in described step (1-1), and correct operation reliability parameter is between [0,1], and device secondary information is protected in reaction.
4. the information fusion method in a kind of intelligent substation fault diagnosis as claimed in claim 2, is characterized in that: in described step (1-4), and Noisy-or, Noisy-and node takes the trust value computing method of true time and is respectively as follows:
Wherein parameter cijIt is NjSingle premise NiTo N when taking true valuejThe genuine degree of recognition, namely from node NiTo node NjConditional probability, conditional probability is obtained by parameter training.
5. the information fusion method in a kind of intelligent substation fault diagnosis as claimed in claim 1, is characterized in that: in described step (2), concrete grammar includes:
(2-1) reliability parameter protecting device and chopper is defined according to secondary network warning information;
(2-2) secondary warning information relevant to each unit protection time according to fault and all possible warning information relevant with protection device, the reliability of definition protection device correct operation;
(2-3) secondary warning information relevant to chopper time according to fault and all possible warning information relevant with chopper, the reliability of definition chopper correct operation;
(2-4) configuration information according to transformer station, sets up the relational matrix of device-warning information, finds device relevant to warning information in matrix the reliability of each device of statistical computation.
6. the information fusion method in a kind of intelligent substation fault diagnosis as claimed in claim 5, it is characterized in that: in described step (2-1), method particularly includes: for protection device, relative secondary network warning information includes: protection self-check of device information, SV message communication link-state information and GOOSE tripping operation communication link state information; For chopper, relative secondary network warning information includes: protection self-check of device information and GOOSE tripping operation communication link state information.
7. the information fusion method in a kind of intelligent substation fault diagnosis as claimed in claim 5, is characterized in that: in described step (2-2), defines RPFor protecting the reliability of device action:
Wherein SiSecondary warning information relevant to protection P when being fault, SnIt is all possible warning information relevant to protection P;
In described step (2-3), define RBReliability for release unit action:
Wherein SiSecondary warning information relevant to chopper B when being fault, SnIt is all possible warning information relevant to chopper B.
8. the information fusion method in a kind of intelligent substation fault diagnosis as claimed in claim 1, it is characterized in that: in described step (3), method particularly includes: for the Bayesian network fault diagnosis model of Noisy-or, Noisy-and node composition, utilize error backpropagation algorithm to carry out the training of parameter, utilize gradient descent algorithm that the mean square deviation between the measured value of target variable and value of calculation is reached minimum.
9. the information fusion method in a kind of intelligent substation fault diagnosis as claimed in claim 1; it is characterized in that: in described step (4); method particularly includes: the fault network model of the dissimilar element for having trained; the fault warning information obtained during using fault is as the input of network: when the protection obtained or breaker actuation, the input value of protection or chopper node should be: RP(RB); When the protection obtained or chopper do not have action, the input value of protection or chopper node should be: 1-RP(RB); When primary system loss of learning, the status information of protection or open circuit is indefinite, also the input of this node is defined as RP(RB)。
10. the information fusion method in a kind of intelligent substation fault diagnosis as claimed in claim 1, it is characterized in that: in described step (4), the input value of respective nodes is input in network, successively reasoning and calculation goes out the trust value of destination node thus obtaining the probability of malfunction value of this element, the all fault elements being likely to occur during for fault are all calculated, and its probability of malfunction value is ranked up, by the probability of malfunction threshold value judgment component that set whether fault.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610018296.9A CN105678337B (en) | 2016-01-12 | 2016-01-12 | Information fusion method in intelligent substation fault diagnosis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610018296.9A CN105678337B (en) | 2016-01-12 | 2016-01-12 | Information fusion method in intelligent substation fault diagnosis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105678337A true CN105678337A (en) | 2016-06-15 |
CN105678337B CN105678337B (en) | 2020-02-04 |
Family
ID=56300189
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610018296.9A Expired - Fee Related CN105678337B (en) | 2016-01-12 | 2016-01-12 | Information fusion method in intelligent substation fault diagnosis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105678337B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106446393A (en) * | 2016-09-18 | 2017-02-22 | 广东电网有限责任公司电力科学研究院 | Power transmission network component failure diagnosis method |
CN106646068A (en) * | 2017-01-22 | 2017-05-10 | 国网湖北省电力公司检修公司 | Method for diagnosing defects of intelligent substation secondary system based on multi-parameter information fusion |
CN110298409A (en) * | 2019-07-03 | 2019-10-01 | 广东电网有限责任公司 | Multi-source data fusion method towards electric power wearable device |
CN112415331A (en) * | 2020-10-27 | 2021-02-26 | 中国南方电网有限责任公司 | Power grid secondary system fault diagnosis method based on multi-source fault information |
CN113807461A (en) * | 2021-09-27 | 2021-12-17 | 国网四川省电力公司电力科学研究院 | Transformer fault diagnosis method based on Bayesian network |
CN117169717A (en) * | 2023-09-11 | 2023-12-05 | 江苏微之润智能技术有限公司 | Motor health assessment method and device based on single chip microcomputer and storage medium |
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 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102255764A (en) * | 2011-09-02 | 2011-11-23 | 广东省电力调度中心 | Method and device for diagnosing transmission network failure |
CN102497024A (en) * | 2011-12-16 | 2012-06-13 | 广东电网公司茂名供电局 | Intelligent warning system based on integer programming |
CN103986238A (en) * | 2014-05-28 | 2014-08-13 | 山东大学 | Intelligent substation fault diagnosis method based on probability weighting bipartite graph method |
-
2016
- 2016-01-12 CN CN201610018296.9A patent/CN105678337B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102255764A (en) * | 2011-09-02 | 2011-11-23 | 广东省电力调度中心 | Method and device for diagnosing transmission network failure |
CN102497024A (en) * | 2011-12-16 | 2012-06-13 | 广东电网公司茂名供电局 | Intelligent warning system based on integer programming |
CN103986238A (en) * | 2014-05-28 | 2014-08-13 | 山东大学 | Intelligent substation fault diagnosis method based on probability weighting bipartite graph method |
Non-Patent Citations (1)
Title |
---|
霍利民: "基于贝叶斯网络的电网故障诊断方法", 《华北电力大学学报》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106446393A (en) * | 2016-09-18 | 2017-02-22 | 广东电网有限责任公司电力科学研究院 | Power transmission network component failure diagnosis method |
CN106646068A (en) * | 2017-01-22 | 2017-05-10 | 国网湖北省电力公司检修公司 | Method for diagnosing defects of intelligent substation secondary system based on multi-parameter information fusion |
CN110298409A (en) * | 2019-07-03 | 2019-10-01 | 广东电网有限责任公司 | Multi-source data fusion method towards electric power wearable device |
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 |
CN112415331A (en) * | 2020-10-27 | 2021-02-26 | 中国南方电网有限责任公司 | Power grid secondary system fault diagnosis method based on multi-source fault information |
CN112415331B (en) * | 2020-10-27 | 2024-04-09 | 中国南方电网有限责任公司 | Power grid secondary system fault diagnosis method based on multi-source fault information |
CN113807461A (en) * | 2021-09-27 | 2021-12-17 | 国网四川省电力公司电力科学研究院 | Transformer fault diagnosis method based on Bayesian network |
CN117169717A (en) * | 2023-09-11 | 2023-12-05 | 江苏微之润智能技术有限公司 | Motor health assessment method and device based on single chip microcomputer and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN105678337B (en) | 2020-02-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105678337A (en) | Information fusion method in intelligent transformer station fault diagnosis | |
CN103336222B (en) | Power system fault diagnosis method based on fuzzy reasoning pulse neurolemma system | |
CN104063586B (en) | Bayesian network failure prediction method based on polymorphic fault tree | |
Mo et al. | A dynamic neural network aggregation model for transient diagnosis in nuclear power plants | |
CN104765965A (en) | GIS fault diagnosis and reliability analysis method based on fuzzy Petri | |
CN103293421A (en) | Power grid fault diagnostic model and diagnostic method thereof | |
CN105183952B (en) | A kind of power transmission network method for diagnosing faults based on separation time Fuzzy Petri Net | |
CN106226658A (en) | A kind of electric network failure diagnosis method based on multi-data fusion | |
CN103840967A (en) | Method for locating faults in power communication network | |
CN103901320A (en) | Method for diagnosing power system fault considering multi-source data | |
CN102570451A (en) | Static reliability assessment method for power transmission network | |
EP3968479A1 (en) | Systems and methods for automatic power topology discovery | |
CN105005644B (en) | A method of detection threephase asynchronous failure | |
CN110188837A (en) | A kind of MVB network fault diagnosis method based on fuzzy neural | |
CN106483425A (en) | The method for diagnosing faults of pulse nerve membranous system based on Triangular Fuzzy Number and device | |
CN106296440A (en) | Based on transformer station's warning information analysis and decision system integrated for ANN and ES and method | |
CN109697563B (en) | Electric power information physical system risk guarantee early warning method considering hidden faults | |
CN104597375A (en) | Power grid fault diagnosis method | |
CN104346627A (en) | Big data analysis-based SF6 (sulfur hexafluoride) gas leakage online early warning platform | |
CN106557607A (en) | A kind of data summarization method of power transmission and transformation fault detection system | |
Xu et al. | Fault diagnosis and identification of malfunctioning protection devices in a power system via time series similarity matching | |
Cai et al. | Bayesian networks in fault diagnosis: Practice and application | |
CN105225167A (en) | A kind of cascading failure recognition sequence system and method | |
Kumar et al. | Deep Learning based Fault Detection in Power Transmission Lines | |
CN106569095A (en) | Power grid fault diagnosis system based on weighted average dependence classifier |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200204 |
|
CF01 | Termination of patent right due to non-payment of annual fee |