CN105678337B - Information fusion method in intelligent substation fault diagnosis - Google Patents
Information fusion method in intelligent substation fault diagnosis Download PDFInfo
- Publication number
- CN105678337B CN105678337B CN201610018296.9A CN201610018296A CN105678337B CN 105678337 B CN105678337 B CN 105678337B CN 201610018296 A CN201610018296 A CN 201610018296A CN 105678337 B CN105678337 B CN 105678337B
- Authority
- CN
- China
- Prior art keywords
- fault
- information
- protection
- fault diagnosis
- network
- 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.)
- Expired - Fee Related
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 59
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims abstract description 13
- 230000009471 action Effects 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 6
- 241000272814 Anser sp. Species 0.000 claims description 4
- 230000007547 defect Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 abstract description 3
- 239000008186 active pharmaceutical agent Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses an information fusion method in intelligent substation fault diagnosis, which comprises the steps of establishing an element-oriented Bayesian network fault diagnosis model according to the protection configuration of each element in a system, bringing reliable parameters of a protection device and a breaker into basic input, and determining trust values among nodes of the Bayesian network fault diagnosis model; defining reliable parameters according to secondary network alarm information, and establishing a device-alarm information relation matrix according to configuration information of an intelligent substation; and training network parameters of a Bayesian network fault diagnosis model by using an error back propagation algorithm, taking fault alarm information obtained in fault as the input of a trained fault network, and calculating the value of a target node to obtain the fault probability value of the element. The defect that only protection and circuit breaker information is utilized in the process of primary system diagnosis is overcome, and from the viewpoint of widening information sources, multi-source information is fused, and the accuracy and reliability of diagnosis are improved.
Description
Technical Field
The invention relates to an information fusion method in intelligent substation fault diagnosis.
Background
When a fault occurs in an electric power system, a large number of uncertain factors exist due to the complexity of a diagnosis object, the limitation of a test means, and the inaccuracy of knowledge. Especially for a huge power system, the connection among the elements is close and complicated, and the fault can be in complex forms such as multiple faults, associated faults and the like. In the face of information with uncertainty (including incompleteness), most of the traditional substation fault diagnosis utilizes protection and circuit breaker alarm information and fault recording information to position primary elements in a system, and under the condition of insufficient information redundancy, the fault tolerance is low, and the diagnosis precision and depth are also insufficient. With the development of network technology, the substation develops towards intellectualization. Compared with a traditional transformer substation secondary system, the intelligent transformer substation primary system adopts an intelligent device (IED) and the secondary system is networked. The information integration application greatly improves the effectiveness of information utilization, and the networking effectively monitors each working link of the secondary system, so that the observability and the controllability are greatly improved. Provides opportunities and implementation means for realizing more efficient, comprehensive and deep transformer substation fault diagnosis and evaluation method
At present, in the aspect of intelligent substation fault diagnosis, intelligent methods such as a neural network, an expert system and a Petri network are widely applied, although the method solves the problem of influence of uncertain factors on fault diagnosis to a certain extent and has certain fault tolerance, a diagnosis result can not be reasonably given even a misdiagnosis is caused when a more complex condition occurs, and the reason is determined, namely the complexity of the fault condition when the system fails; another aspect is the uniqueness of the information sources used for diagnosis. Therefore, only from the perspective of algorithm, the use of only fault information to complete information has certain limitations, and the reliability of diagnosis cannot be fundamentally improved.
Disclosure of Invention
The invention provides an information fusion method in intelligent substation fault diagnosis, which comprises the steps of firstly establishing a fault diagnosis model aiming at elements by utilizing a Bayesian network, using multi-source information from a primary system and a secondary system acquired during system fault as input, and calculating and acquiring element fault probability value through Bayesian network reasoning, thereby judging the fault elements.
In order to achieve the purpose, the invention adopts the following technical scheme:
an information fusion method in intelligent substation fault diagnosis comprises the following steps:
(1) establishing an element-oriented Bayesian network fault diagnosis model according to the protection configuration of each element in the power system, bringing reliable parameters of a protection device and a breaker into basic input, and determining trust values among nodes of the Bayesian network fault diagnosis model;
(2) defining reliable parameters according to secondary network alarm information, and establishing a device-alarm information relation matrix according to configuration information of an intelligent substation;
(3) training network parameters of a Bayesian network fault diagnosis model by using an error back propagation algorithm;
(4) and taking the fault alarm information obtained in the fault as the input of the trained fault diagnosis model network, calculating the value of the target node, and calculating the fault probability value of the element.
In the step (1), the specific method comprises:
(1-1) establishing a Bayesian network fault diagnosis model consisting of Noisy-or and Noisy-and nodes according to the protection configuration condition of each element in the system and the internal logic relationship among element faults, protection device actions and breaker tripping;
(1-2) correspondingly setting a correct action reliability parameter for each protection or circuit breaker input node;
(1-3) taking action information of the protection and the breaker and reliability parameter information corresponding to each device as basic input of a Bayesian network model;
(1-4) calculating the trust value when the Noisy-or and Noisy-and nodes take the truth.
Further, in the step (1-1), the reliability parameter of the correct action is between [0,1], and secondary information of the protection device is reflected.
In the step (1-4), the method for calculating the trust value when the Noisy-or and Noisy-and nodes take the truth comprises the following steps:
wherein the parameter cijIs NjSingle precondition NiTaking true value to NjTrue acceptance, i.e. slave node NiTo node NjAnd the conditional probability is obtained by parameter training.
In the step (2), the specific method comprises:
(2-1) defining reliability parameters of the protection device and the breaker according to secondary network alarm information;
(2-2) defining the reliability of the correct action of the protection device according to the secondary alarm information related to the protection of each device during the fault and all possible alarm information related to the protection device;
(2-3) according to secondary alarm information related to the circuit breaker during the fault and all possible alarm information related to the circuit breaker, defining the reliability of the correct action of the circuit breaker;
and (2-4) establishing a device-alarm information relation matrix according to the configuration information of the transformer substation, searching devices related to the alarm information in the matrix, and counting and calculating the reliability of each device.
In the step (2-1), the specific method comprises the following steps: for the protection device, the secondary network alarm information related to the protection device comprises: the method comprises the following steps that self-checking information of a protection device, SV message communication link state information and GOOSE tripping communication link state information are obtained; for the circuit breaker, the secondary network alarm information related to the circuit breaker comprises the following steps: protection device self-checking information and GOOSE trip communication link status information.
Further, in said step (2-2), R is definedPFor the reliability of the protection device action:
wherein SiIs a secondary warning message, S, associated with protection P in the event of a faultnIs all possible alarm information related to protection P.
In the step (2-3), R is definedBReliability of the operation of the circuit breaker device:
wherein SiIs a secondary warning message, S, associated with the circuit breaker B in the event of a faultnIs all possible alarm information associated with circuit breaker B.
In the step (3), the specific method is as follows: aiming at a Bayesian network fault diagnosis model consisting of Noisy-or and Noisy-and nodes, an error back propagation algorithm is utilized to train parameters, and a gradient descent algorithm is utilized to minimize the mean square error between a measured value and a calculated value of a target variable.
In the step (4), the specific method is as follows: for the trained fault network models of different types of elements, the fault alarm information obtained in fault is used as the input of the network: when the obtained protection or breaker is acting, the input values of the protection or breaker node should be: rP(RB) (ii) a When the protection or circuit breaker obtained is not active, the input values of the protection or circuit breaker nodes should be: 1-RP(RB) (ii) a When the system information is lost once, the state information of protection or disconnection is not clear, and the input of the node is defined as RP(RB)。
In the step (4), the input values of the corresponding nodes are input into the network, the trust value of the target node is calculated by layer-by-layer reasoning to obtain the fault probability value of the element, all fault elements which may occur during fault are calculated, the fault probability values are sequenced, and whether the element is in fault is judged according to the set fault probability threshold value.
The invention has the beneficial effects that:
(1) the invention combines the characteristics of the intelligent substation, fully utilizes the secondary network information, and overcomes the defect that only the protection and breaker information is utilized in the primary system diagnosis process by defining the reliability parameters of the correct actions of the protection device and the breaker;
(2) the invention starts from the angle of widening information sources, fuses multi-source information, and simultaneously combines the strong fault-tolerant function of the Bayesian network to improve the accuracy and reliability of diagnosis.
Drawings
FIG. 1(a) is a schematic diagram of a line fault diagnosis model of the present invention;
FIG. 1(b) is a schematic view of a bus fault diagnosis model of the present invention;
FIG. 1(c) is a schematic diagram of a transformer fault diagnosis model according to the present invention;
fig. 2 is a schematic flow chart of the method for training the bayesian network fault diagnosis model according to the present invention.
The specific implementation mode is as follows:
the invention is further described with reference to the accompanying drawings and examples.
By combining the characteristics of the intelligent substation, when a fault occurs in the system, not only can the primary system change in state, but also the networked secondary system can send a lot of alarm information, and the secondary alarm information not only reflects the fault characteristics to a certain extent, but also can reflect the state information of the device. When the fault diagnosis of the intelligent transformer substation is carried out, the fault information of the secondary system of the transformer substation is taken into account, the redundancy of the information can be greatly improved, and the problem of inaccurate fault diagnosis caused by insufficient information is avoided. The secondary alarm information is used for defining the reliability parameters of the correct actions of the protection device and the breaker, the defects existing when only protection and breaker information is used in the primary system diagnosis process are overcome, from the viewpoint of widening information sources, the information of the primary system and the secondary system is combined, more comprehensive information is provided for the diagnosis of the system, and the diagnosis accuracy is improved.
The invention is further explained by taking the fault diagnosis of the intelligent substation integrating the secondary information as a core.
The method comprises the following steps: and establishing a fault diagnosis model.
1) As shown in fig. 1(a), 1(b) and 1(c), a bayesian network fault diagnosis model consisting of noise-or and noise-and nodes is established according to the protection configuration of each element in the system and the internal logic relationship among element faults, protection device actions and breaker tripping.
Taking a line as an example, when a fault occurs in the line L, theoretically, the protection on both sides of the line should act to trip the corresponding circuit breaker, and the protection on both sides of the line constitutes a noise-and node. For each side, protection can be divided into three categories again: primary protection, backup protection, and far backup protection of adjacent elements. Any one of the three types of protection causes the corresponding breaker to trip, and the fault can be removed, so that the three types of protection form a Noisy-or node. In the case of normal operation of the protection device, the protection device and circuit breaker operation should be identical, so that the protection and its corresponding circuit breaker constitute a Noisy-and node.
2) For each protection or circuit breaker input node, a correct action reliability parameter is correspondingly arranged, and the parameter is between 0 and 1]In the meantime, the secondary information of the protection device, such as the protection node MLP in FIG. 1(a), changes the original input of non-0, i.e. 1, by defining a reliability parameter RPThe definition and calculation of (a) are described in detail in the technical solutions.
3) When a fault occurs in the system, firstly, suspicious fault elements are identified according to the outage area, and a corresponding fault diagnosis model is established for each suspicious fault element.
Step two: and calculating a reliability parameter.
1) As detailed in the technical solutions,RPfor the reliability of the protection device action:
wherein SiIs a secondary warning message, S, associated with protection P in the event of a faultnIs all possible alarm information related to protection P.
2)RBReliability of circuit breaker operation:
wherein SiIs a secondary warning message, S, associated with the circuit breaker B in the event of a faultnIs all possible alarm information associated with circuit breaker B.
Because a certain logical relationship exists between the circuit breaker and the protection, namely the circuit breaker is controlled by the protection, when the wrong alarm information of the protection device occurs, the reliability of the correct action of the corresponding circuit breaker is also reduced, and the relationship between the protection and the circuit breaker can be reflected by the following device-alarm information relationship matrix.
3) Establishing a device-alarm information relation matrix DS according to configuration information of the intelligent substationm×n
Wherein each row DiRepresenting a device of a transformer substation, wherein the device comprises various IED intelligent devices such as a protection device, a breaker intelligent terminal and a switch, and has m dimensions; each column SjAnd the possible alarm information in the transformer substation is represented, and the total dimension is n. The elements in the matrix being other than 0, i.e. 1, when device DiAnd alarm information SjIf there is an association relationship, it is 1, otherwise it is 0.
At the same time, element protection matrices EP can be defined according to the network topology of the systema×bProtection-circuit breaker matrix PBb×cThe protection configuration of the element is expressed in a mathematical form. As shown in the following formula, the row element represents element EiThe column element represents the protection PiElement 1 represents element EiProtected PiAnd (4) protecting. A plurality of such matrices may be defined in order to distinguish the categories of protection, e.g., primary protection, backup protection, etc.
When a fault occurs, aiming at a suspicious fault element, the protection corresponding to the element and the related circuit breaker are found out by a matrix search method. At the same time, for the occurrence of a large amount of alarm information in the secondary network, the matrix DS is searchedm×nAnd finding out related alarm information of the corresponding protection and circuit breaker of the element, and counting and calculating the reliability of the correct action of each device.
Step three: and training network parameters.
And (4) aiming at the Bayesian network fault diagnosis model consisting of the Noisy-or and Noisy-and nodes in the step one, training parameters by using an error back propagation algorithm. The basic method of training has been detailed in the technical solution, and the flowchart (as shown in fig. 2) specifically introduces the training step.
And (4) training network parameters by using an error back propagation algorithm for the established fault diagnosis model.
And aiming at the Bayesian network fault diagnosis model consisting of the Noisy-or and Noisy-and nodes in the step one, training parameters by utilizing an error back propagation algorithm. Error back propagation algorithms are commonly used in the training of multi-layer neural networks, using gradient descent algorithms to minimize the mean square error between measured and calculated values of the target variable. The following equation gives the calculation formula of the mean square error:
wherein
Is node NjThe true value of the trust level when the value is true; bel (N)jTrue) is shellfishThe calculated value of the leaf network, and the formula (2) gives the gradient calculation formula of the nodes of Noisy-or and Noisy-and:
where η is the learning factor, δjIs node NjThe error of (2). For the output node:
for hidden nodes, node NjBack-propagating to its parent node NiThe error of (2) is:
each training is based on the error deltajCalculating the gradient DeltaijAnd correcting the parameters by using the gradient, and retraining the calculation until the error meets the requirement.
Each of the different types of elements is trained, as shown in table 1, as a training sample of the line fault model, usually, in order to obtain more optimized network parameters, the training sample may be added according to actual operating conditions.
TABLE 1 line Fault model training
Step four: component failure probability calculation
For the trained fault network models of different types of elements, the fault alarm information obtained in fault is used as the input of the network: when the obtained protection or breaker action information is 1 (i.e., protection or breaker action), the input values of the protection or breaker node should be: rP(RB) (ii) a When the obtained protection or breaker action information is 0 (i.e. protection or breaker does not act), the input values of the protection or breaker node should be: 1-RP(RB) (ii) a When the system information is lost once, the state information of protection or disconnection is not clear, and the input of the node is defined as RP(RB)。
And inputting the input values of the corresponding nodes into the network, and calculating the trust value of the target node layer by layer in an inference manner so as to obtain the fault probability value of the element. All fault elements which may appear during fault are calculated, the fault probability values of all fault elements are ranked, and whether the elements are in fault is judged according to the set fault probability threshold value. It is generally considered that a faulty element has a significantly higher probability value of failure than other elements.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (8)
1. An information fusion method in intelligent substation fault diagnosis is characterized in that: the method comprises the following steps:
(1) establishing a Bayesian network fault diagnosis model facing the elements according to the protection configuration of each element in the power system, taking reliability parameters correspondingly set by a protection device and a circuit breaker as basic input of a Bayesian network, and calculating trust values of each node of the Bayesian network fault diagnosis model;
(2) defining a reliability parameter according to secondary network alarm information, and establishing a device-alarm information relation matrix according to configuration information of an intelligent substation;
(3) training network parameters of a Bayesian network fault diagnosis model by using an error back propagation algorithm;
(4) taking fault alarm information obtained in the fault as the input of a trained fault diagnosis model network, calculating the value of a target node, and calculating the fault probability value of an element;
in the step (2), the specific method comprises:
(2-1) defining the reliability parameters of the correct actions of the protection device and the breaker according to the secondary network alarm information;
(2-2) defining a reliability parameter of the correct action of the protection device according to secondary network alarm information related to the protection of each device during the fault and all possible alarm information related to the protection device;
(2-3) defining a reliability parameter of the correct action of the circuit breaker according to the secondary network alarm information related to the circuit breaker during the fault and all possible alarm information related to the circuit breaker;
and (2-4) establishing a device-alarm information relation matrix according to the configuration information of the transformer substation, searching devices related to the alarm information in the matrix, and counting and calculating reliability parameters of all the devices.
2. The information fusion method in the intelligent substation fault diagnosis as claimed in claim 1, characterized by: in the step (1), the specific method comprises:
(1-1) establishing a Bayesian network fault diagnosis model consisting of Noisy-or and Noisy-and nodes according to the protection configuration condition of each element in the system and the internal logic relationship among element faults, protection device actions and breaker tripping;
(1-2) correspondingly setting a correct action reliability parameter for each protection or circuit breaker input node;
(1-3) calculating reliability parameters corresponding to each device according to the action information of the protection and the breaker, and using the reliability parameters as basic input of a Bayesian network model;
(1-4) calculating the trust value when the Noisy-or and Noisy-and nodes take the truth.
3. The information fusion method in the fault diagnosis of the intelligent substation according to claim 2, characterized in that: in the step (1-1), the reliability parameter of the correct action of the protection device and the breaker is between [0,1], and secondary information of the protection device is reflected.
4. The information fusion method in the fault diagnosis of the intelligent substation according to claim 2, characterized in that: in the step (1-4), the trust value calculation methods when the Noisy-or and Noisy-and nodes take the truths are respectively as follows:
wherein the parameter cijIs NjSingle precondition NiTaking true value to NjTrue acceptance, i.e. slave node NiTo node NjAnd the conditional probability is obtained by parameter training.
5. The information fusion method in the intelligent substation fault diagnosis as claimed in claim 1, characterized by: in the step (2-1), the specific method comprises the following steps: for the protection device, the secondary network alarm information related to the protection device comprises: the method comprises the following steps that self-checking information of a protection device, SV message communication link state information and GOOSE tripping communication link state information are obtained; for the circuit breaker, the secondary network alarm information related to the circuit breaker comprises the following steps: protection device self-checking information and GOOSE trip communication link status information.
6. The information fusion method in the intelligent substation fault diagnosis as claimed in claim 1, characterized by: in the step (3), the specific method is as follows: aiming at a Bayesian network fault diagnosis model consisting of Noisy-or and Noisy-and nodes, an error back propagation algorithm is utilized to train parameters, and a gradient descent algorithm is utilized to minimize the mean square error between a measured value and a calculated value of a target variable.
7. The information fusion method in the intelligent substation fault diagnosis as claimed in claim 1, characterized by: in the step (4), the specific method is as follows: failure for different types of components that have been trainedThe network model takes the fault warning information obtained in the fault as the input of the network: when the obtained protection or breaker is acting, the input values of the protection or breaker node should be: rP(RB) (ii) a When the protection or circuit breaker obtained is not active, the input values of the protection or circuit breaker nodes should be: 1-RP(RB) (ii) a When the system information is lost once, the state information of protection or disconnection is not clear, and the input of the node is defined as RP(RB) (ii) a Wherein R isPThe reliability parameter of the action of the protection device; rBIs a reliability parameter of the action of the breaker device.
8. The information fusion method in the intelligent substation fault diagnosis as claimed in claim 1, characterized by: in the step (4), the input values of the corresponding nodes are input into the network, the trust value of the target node is calculated by layer-by-layer reasoning to obtain the fault probability value of the element, all fault elements which may occur during fault are calculated, the fault probability values are sequenced, and whether the element is in fault is judged according to the set fault probability threshold value.
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 CN105678337A (en) | 2016-06-15 |
| CN105678337B true 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) |
Families Citing this family (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 |
| DE102020120539A1 (en) * | 2020-08-04 | 2022-02-10 | Maschinenfabrik Reinhausen Gmbh | Device for determining an error probability value for a transformer component and a system with such a device |
| 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 |
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 |
|---|
| 基于贝叶斯网络的电网故障诊断方法;霍利民;《华北电力大学学报》;20040625;第31卷(第3期);第30-34页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105678337A (en) | 2016-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105678337B (en) | Information fusion method in intelligent substation fault diagnosis | |
| CN103840967B (en) | A kind of method of fault location in power telecom network | |
| CN103487723B (en) | Fault diagnosis method of electric power system and system | |
| CN103001328B (en) | Fault diagnosis and assessment method of intelligent substation | |
| CN107394773A (en) | Consider the distribution information physical system reliability estimation method of troubleshooting overall process | |
| Di Giorgio et al. | A Bayesian network-based approach to the critical infrastructure interdependencies analysis | |
| Peng et al. | Fault diagnosis of power systems using fuzzy tissue-like P systems | |
| Jenkins et al. | Deterministic and stochastic Petri net models of protection schemes | |
| CN105183952B (en) | A kind of power transmission network method for diagnosing faults based on separation time Fuzzy Petri Net | |
| CN111008454B (en) | Intelligent substation reliability assessment method based on information physical fusion model | |
| CN103308824A (en) | Power system fault diagnostic method based on probability Petri net | |
| CN105067956A (en) | Anti-colony-algorithm-based distribution network fault positioning method | |
| CN106841928A (en) | A kind of Fault Section Location of Distribution Network and system based on Multi-source Information Fusion | |
| CN106226658A (en) | A kind of electric network failure diagnosis method based on multi-data fusion | |
| CN103605787B (en) | Method and system for evaluating and analyzing relay protection | |
| CN110988596A (en) | Novel active power distribution network fault section positioning method | |
| CN109697563B (en) | Electric power information physical system risk guarantee early warning method considering hidden faults | |
| CN106771848A (en) | A kind of electric network failure diagnosis method based on the fusion of topological primitive information | |
| CN113900844A (en) | Service code level-based fault root cause positioning method, system and storage medium | |
| CN110188837A (en) | A kind of MVB network fault diagnosis method based on fuzzy neural | |
| CN104766246A (en) | Power system fault diagnosis method based on timing order fuzzy Petri net | |
| CN109495313B (en) | Wireless sensor network fault detection method based on Poisson distribution fault model | |
| CN114252727A (en) | Power grid fault rapid diagnosis method based on artificial intelligence technology | |
| Klaes et al. | State description of cyber-physical energy systems | |
| CN113740666B (en) | Method for positioning root fault of storm alarm in power system of data center |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200204 |