CN107247450A - Circuit breaker failure diagnostic method based on Bayesian network - Google Patents
Circuit breaker failure diagnostic method based on Bayesian network Download PDFInfo
- Publication number
- CN107247450A CN107247450A CN201710312354.3A CN201710312354A CN107247450A CN 107247450 A CN107247450 A CN 107247450A CN 201710312354 A CN201710312354 A CN 201710312354A CN 107247450 A CN107247450 A CN 107247450A
- Authority
- CN
- China
- Prior art keywords
- bayesian network
- circuit breaker
- data
- breaker failure
- diagnostic
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
- G05B23/0254—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses the circuit breaker failure diagnostic method based on Bayesian network, it is the structure and fault characteristic according to breaker, Bayesian network diagnostic model is built on data mining KNIME platforms increasing income, for the fault diagnosis to breaker, and by the emulation experiment of bulk items True Data, verify the convergence, high efficiency and accuracy of the diagnostic model method.The application uses Bayes net algorithm, when having taken into full account that breaker breaks down, the causality and uncertainty of the variable data such as voltage, electric current, insulaion resistance, substantially increases the convergence and accuracy of fault diagnosis result.
Description
Technical field
The present invention relates to a kind of circuit breaker failure diagnostic method, and in particular to a kind of breaker event based on Bayesian network
Hinder diagnostic method, belong to power equipment safety monitoring field.
Background technology
In the last few years, various mining algorithms were widely used in the fault diagnosis of equipment, and achieve it is good into
Achievement.Such as various types of expert diagnostic systems, Neural Network Diagnosis System and the diagnostic system based on fuzzy theory.Existing rank
Section, the circuit breaker failure diagnostic method based on neural network algorithm is very commonly and effectively.But it there is also many defects:
One is when training sample number is more and when complicated input/output relation, it is slow that its convergence rate just becomes, and does not receive even
Hold back;Two be with input feature value dimension it is more when, its network performance performance it is poor.
Bayesian network has very big advantage for solving failure caused by complication system uncertain factor, shows as receiving
Hold back the characteristic that speed is fast, classification capacity is strong, the degree of accuracy is high;It is considered as that current uncertain knowledge expression and reasoning field are most effective
Theoretical model;It cleverly combines the prior probability of event with posterior probability using Bayes' theorem as theoretical foundation,
The posterior probability of event is determined using sample data and prior probability;Bayesian network describes number using the weight of probability measure
Correlation between, solves the inconsistency between data, can the easily incomplete problem of processing information.
There are many experts and scholars to study circuit breaker failure diagnosis problem both at home and abroad at present, be broadly divided into god
Through four kinds of methods such as network, fuzzy reasoning, genetic algorithm and expert system.These diagnostic methods show it is good it is adaptive should be able to
Power, self-learning capability, fault-tolerant ability and diagnosis capability.But when training sample number is more and input/output relation is very complicated
When, its convergence rate is very slow, does not restrain even;And its carry out fault diagnosis when, or the accuracy of diagnostic result compared with
It is low, otherwise Diagnostic Time is longer.
The content of the invention
The present invention in view of the shortcomings of the prior art and difficult point, designs a kind of circuit breaker failure diagnosis based on Bayesian network
Method, so as to realize the convergence, high efficiency and accuracy of diagnostic result.
The present invention is that Integral Thought is achieved in that:
Circuit breaker failure diagnostic method based on Bayesian network, is the structure and fault characteristic according to breaker, is opening
Source data, which is excavated, builds Bayesian network diagnostic model on KNIME platforms, for the fault diagnosis to breaker, and by a large amount of
The emulation experiment of project True Data, verifies the convergence, high efficiency and accuracy of the diagnostic model method.Needed in this method
There are the knowledge base of circuit breaker failure, Bayesian network diagnostic model, circuit breaker failure diagnosis, emphasis is that diagnostic model is set
Meter.Wherein, the knowledge base composition of circuit breaker failure includes sample set and test set, and sample set is trained for diagnostic model, test
Collect the accuracy for verifying diagnostic model;The structure of Bayesian network diagnostic model is divided into three links, i.e. data acquisition, number
Data are read in Data preprocess and data mining, the first diagnostic model from Mysql databases, are then become by row filtering, row
Change, the pretreatment of the volume of data such as random subregion, final diagnosis model employs the Bayesian network section in being extended outside Weka
Point carries out data mining, by the training to great amount of samples data, forms a kind of based on Bayesian network conditional probability distribution
Circuit breaker failure diagnostic model;In actual applications, by calling the Bayesian network fault diagnosis model method after training,
The fault diagnosis to breaker is realized, and diagnostic result is shown.
In summary, we can draw the circuit breaker failure diagnostic method based on Bayesian network, comprise the following steps:
Step 1: the construction of knowledge base of circuit breaker failure
The structure of knowledge base includes failure mode analysis and database designs two steps:
1.1:The fault type of breaker is various, according to physical fault analysis of cases, by the most common failure of breaker
It is divided into three major types, eight groups, specific fault type is as shown in table 1-1.
Table 1-1 circuit breaker failure types
1.2:Database design mainly includes the design of circuit breaker failure diagnostic rule table, circuit breaker failure diagnostic rule table
Design mainly include data ID, index and judge the specific field such as item, fault type and Diagnostic Time, its literary name section detailed design
As shown in table 1-2.
Table 1-2 circuit breaker failure diagnostic rule literary name sections
Step 2: Bayesian network fault diagnosis model is designed
The modeling and simulation platform diagnosed using KNIME 3.3.1 data mining platforms as circuit breaker failure, based on shellfish
The fault diagnosis model design of this network of leaf is as shown in Figure 2.In actual circuit breaker failure diagnosis, by calling this model,
Realize the diagnosis to circuit breaker failure type.
Fault diagnosis model based on Bayesian network includes data acquisition, three rings of data prediction and data mining
Section.
2.1:Data acquisition
The step accesses MySQL database by database connecting node, reads sample set data, and data content includes 8
Item Judging index and 1 failure determination result.Wherein, the 10 groups of sample metadata randomly selected are as shown in table 1-3.
Table 1-3 sample set metadatas
2.2:Data prediction
For the sample metadata read from database, the data prediction of progress is included into row filtering, row and exchanges sum
According to subregion.
2.2.1:The distracter trained for Bayesian network, such as sequence number, fault time are removed using row filter node;
2.2.2:Upset the case order of circuit breaker failure using row switching node, be that the random subregion of sample data does standard
It is standby;
2.2.3:Use data partition node by sample data by random point of certain ratio (this model set for 70%)
Into two parts, a part is used for the training of Bayesian network sample set, and another part is tested for sample set.Pass through test result and reality
The comparison of border result, verifies the accuracy of Bayesian network model.
By pretreated metadata as shown in table 1-4 and table 1-5.Not only put in order and changed, for instructing
Practice and the sample size of test also changes therewith.
The pretreated training datas of table 1-4
The pretreated test datas of table 1-5
2.3:Data mining
2.3.1:On the basis of data prediction, diagnostic model employs the Bayesian network section in being extended outside Weka
Point carries out data mining, by the training to great amount of samples data, forms one and is based on Bayesian network conditional probability distribution
Fault diagnosis model.
2.3.2:It is that user need not write program using the advantage of KNIME platform modelings, only needs simple node connection
And parameter setting, it just can construct the system model of complexity.Input, output and the parameter of Bayesian network node in this diagnostic model
Set as follows:
A) input of Bayesian network node is 8 Judging index:Closing coil insulaion resistance, no-voltage trip coil shape
State, closing coil voltage, on off state, overload protection, overcurrent protection, under-voltage protection, inverse work(protection;
B) target of Bayesian network node is output as circuit breaker failure type (Fault_type);
C) parameter setting of Bayesian network node is illustrated in fig. 3 shown below.
Step 3: circuit breaker failure is diagnosed
In actual circuit breaker failure diagnostic application, by calling the Bayesian network fault diagnosis model, realization pair
The diagnosis of circuit breaker failure type
3.1:Circuit breaker failure test result is made comparisons with actual result (Fault_type Prediction_Fault_
Type), the convergence, high efficiency and accuracy to Bayesian network fault diagnosis model are verified, its result such as Fig. 4
It is shown.
In 259 test datas of sample set, predicting the outcome consistent with actual result has 250 groups, only 9 groups data
Predict the outcome and error occur, the accuracy of its fault diagnosis result is 96.525%, and error rate is 3.475%, uniformity inspection
It is 0.957 to test (kappa) result, and Diagnostic Time is 6.334s.It is possible thereby to prove, the fault diagnosis mould based on Bayesian network
Type is efficient, accurate.
The circuit breaker failure diagnostic method based on Bayesian network of the present invention is diagnosed relative to traditional circuit breaker failure
Method, mainly there is three innovative points:1. Bayes net algorithm, when having taken into full account that breaker breaks down, voltage, electricity are used
The causality and uncertainty of the variable datas such as stream, insulaion resistance, substantially increase the convergence and standard of fault diagnosis result
True property;2. traditional artificial detection is replaced using data mining and analytical technology, has not only saved the costs such as manpower and materials, and
Shorten failure diagnosis time;3. fault diagnosis is carried out to breaker by the method for far call fault diagnosis model, can be real
An existing server disposition, the function that multiple host is called greatlys save system memory resource.
Brief description of the drawings
Fig. 1 is the circuit breaker failure diagnostic method schematic diagram of the invention based on Bayesian network;
Fault diagnosis model schematic diagrames of the Fig. 2 based on Bayesian network;
Fig. 3 is the parameter setting figure of Bayesian network node;
Fig. 4 Bayesian network fault diagnosis model simulation result figures;
Fig. 5 is circuit breaker failure tree graph;
Fig. 6 is that algorithms of different accuracy simulation result compares figure.
Fig. 7 circuit breaker failure diagnostic flow charts.
Embodiment
The present invention is described further below in conjunction with the accompanying drawings.
As shown in Figure 1, a kind of circuit breaker failure diagnostic method based on Bayesian network, is the structure according to breaker
And fault characteristic, Bayesian network diagnostic model is built on data mining KNIME platforms increasing income, for the failure to breaker
Diagnosis, and by the emulation experiment of bulk items True Data, verifies the convergence of the diagnostic model method, high efficiency and accurate
Property.The knowledge base of circuit breaker failure, Bayesian network diagnostic model, circuit breaker failure diagnosis are needed in this method, emphasis is
Design to diagnostic model.Wherein, the knowledge base composition of circuit breaker failure includes sample set and test set, and sample set is used to diagnose
Model training, test set is used for the accuracy for verifying diagnostic model;The structure of Bayesian network diagnostic model is divided into three links,
That is data, Ran Houjing are read in data acquisition, data prediction and data mining, the first diagnostic model from Mysql databases
The volume of data pretreatment such as row filtering, line translation, random subregion is crossed, final diagnosis model is employed outside Weka in extension
Bayesian network node carries out data mining, by the training to great amount of samples data, forms a kind of based on Bayesian network
The circuit breaker failure diagnostic model of conditional probability distribution;In actual applications, by calling the Bayesian network failure after training
Diagnostic model method, realizes the fault diagnosis to breaker, and diagnostic result is shown.
In summary, we can draw the circuit breaker failure diagnostic method based on Bayesian network, as shown in Figure 7,
Comprise the following steps:
Step 1: the construction of knowledge base of circuit breaker failure
The structure of knowledge base includes failure mode analysis and database designs two steps:
1.1:The fault type of breaker is various, and accompanying drawing 5 and subordinate list almost list the common all events of breaker
Barrier.
Subordinate list fault tree Event Description table
According to physical fault analysis of cases, the most common failure of breaker is divided into three major types, eight groups, specific fault type
As shown in table 1-1.
Table 1-1 circuit breaker failure types
1.2:Database design mainly includes the design of circuit breaker failure diagnostic rule table, circuit breaker failure diagnostic rule table
Design mainly include data ID, index and judge the specific field such as item, fault type and Diagnostic Time, its literary name section detailed design
As shown in table 1-2.
Table 1-2 circuit breaker failure diagnostic rule literary name sections
Step 2: Bayesian network fault diagnosis model is designed
The modeling and simulation platform diagnosed using KNIME 3.3.1 data mining platforms as circuit breaker failure, based on shellfish
The fault diagnosis model design of this network of leaf is as shown in Figure 2.In actual circuit breaker failure diagnosis, by calling this mould
Type, realizes the diagnosis to circuit breaker failure type.
Fault diagnosis model based on Bayesian network includes data acquisition, three rings of data prediction and data mining
Section.
2.1:Data acquisition
The step accesses MySQL database by database connecting node, reads sample set data, and data content includes 8
Item Judging index and 1 failure determination result.Wherein, the 10 groups of sample metadata randomly selected are as shown in table 1-3.
Table 1-3 sample set metadatas
2.2:Data prediction
For the sample metadata read from database, the data prediction of progress is included into row filtering, row and exchanges sum
According to subregion.
2.2.1:The distracter trained for Bayesian network, such as sequence number, fault time are removed using row filter node;
2.2.2:Upset the case order of circuit breaker failure using row switching node, be that the random subregion of sample data does standard
It is standby;
2.2.3:Use data partition node by sample data by random point of certain ratio (this model set for 70%)
Into two parts, a part is used for the training of Bayesian network sample set, and another part is tested for sample set.Pass through test result and reality
The comparison of border result, verifies the accuracy of Bayesian network model.
By pretreated metadata as shown in table 1-4 and table 1-5.Not only put in order and changed, for instructing
Practice and the sample size of test also changes therewith.
The pretreated training datas of table 1-4
The pretreated test datas of table 1-5
2.3:Data mining
2.3.1:On the basis of data prediction, diagnostic model employs the Bayesian network section in being extended outside Weka
Point carries out data mining, by the training to great amount of samples data, forms one and is based on Bayesian network conditional probability distribution
Fault diagnosis model.
2.3.2:It is that user need not write program using the advantage of KNIME platform modelings, only needs simple node connection
And parameter setting, it just can construct the system model of complexity.Input, output and the parameter of Bayesian network node in this diagnostic model
Set as follows:
A) input of Bayesian network node is 8 Judging index:Closing coil insulaion resistance, no-voltage trip coil shape
State, closing coil voltage, on off state, overload protection, overcurrent protection, under-voltage protection, inverse work(protection;
B) target of Bayesian network node is output as circuit breaker failure type (Fault_type);
C) parameter setting of Bayesian network node is as shown in Figure 3.
Step 3: circuit breaker failure is diagnosed
In actual circuit breaker failure diagnostic application, by calling the Bayesian network fault diagnosis model, realization pair
The diagnosis of circuit breaker failure type
3.1:Circuit breaker failure test result is made comparisons with actual result (Fault_type Prediction_Fault_
Type), the convergence, high efficiency and accuracy to Bayesian network fault diagnosis model verify that its result is for example attached
Shown in Fig. 4.
In 259 test datas of sample set, predicting the outcome consistent with actual result has 250 groups, only 9 groups data
Predict the outcome and error occur, the accuracy of its fault diagnosis result is 96.525%, and error rate is 3.475%, uniformity inspection
It is 0.957 to test (kappa) result, and Diagnostic Time is 6.334s.It is possible thereby to prove, the fault diagnosis mould based on Bayesian network
Type is efficient, accurate.
Accompanying drawing 6 is that algorithms of different accuracy simulation result compares figure, by accompanying drawing 6 as can be seen that the application is based on pattra leaves
The circuit breaker failure diagnostic method of this network, result is accurate, than BP neural network and Nae Bayesianmethod, either from
In accuracy or uniformity, all it is significantly increased.
Accompanying drawing 7 shows the flow that circuit breaker failure diagnosis is carried out using circuit breaker failure diagnostic system, is expressed as follows:
1) circuit breaker failure diagnostic system, and initialization data storehouse are started;
2) enter fault detection module, the automatic detection time is set, and according to detected rule, the current data to each circuit is entered
Row automatic detection, continues to detect if not breaking down, if there is failure, then generates examining report and notify to repair people
Member carries out fault location;
3) enter positioning failure source module, import the circuit breaker voltage data for producing failure, system is by matching positioning rule
Then, failure judgement position, finds the source of trouble;
4) enter fault diagnosis module, the diagnostic model based on Bayesian network is built first, then sample set is carried out
Training, the network model of the conditional probability distribution formed after training;Then system is real by way of calling fault diagnosis model
Now to the fault diagnosis of breaker.
Claims (4)
1. the circuit breaker failure diagnostic method based on Bayesian network, it is characterised in that:It is special according to the structure of breaker and failure
Property, Bayesian network diagnostic model is built on data mining KNIME platforms increasing income, for the fault diagnosis to breaker, and
By the emulation experiment of bulk items True Data, convergence, high efficiency and the accuracy of Bayesian network diagnostic model are verified,
Specifically include:
The structure of the knowledge base of circuit breaker failure, the structure of Bayesian network diagnostic model, circuit breaker failure diagnosis:
Wherein
In the structure of the knowledge base of circuit breaker failure, the composition of the knowledge base of circuit breaker failure includes sample set and test set, sample
This collects for diagnostic model training, and test set is used for the accuracy for verifying diagnostic model;
The structure of Bayesian network diagnostic model is divided into three links, i.e. data acquisition, data prediction and data mining, first
Bayesian network diagnostic model reads data from Mysql databases, is then pre-processed by volume of data, final diagnosis mould
The Bayesian network node that type is employed in being extended outside Weka carries out data mining, by the training to great amount of samples data,
Form a kind of circuit breaker failure diagnostic model based on Bayesian network conditional probability distribution;
Circuit breaker failure diagnosis is in actual applications by calling the Bayesian network fault diagnosis model after training, realization pair
The fault diagnosis of breaker, and diagnostic result is shown.
2. the circuit breaker failure diagnostic method based on Bayesian network according to claim 1, it is characterised in that:
In the construction of knowledge base of circuit breaker failure, the structure of knowledge base includes failure mode analysis and database designs two steps
Suddenly:
1.1:The fault type of breaker is various, and according to physical fault analysis of cases, the most common failure of breaker is divided into
Three major types, eight groups, specific fault type is as shown in table 1-1;
Table 1-1 circuit breaker failure types
1.2:Database design mainly includes the design of circuit breaker failure diagnostic rule table, circuit breaker failure diagnostic rule literary name section
Detailed design is as shown in table 1-2:
Table 1-2 circuit breaker failure diagnostic rule literary name sections
3. the circuit breaker failure diagnostic method based on Bayesian network according to claim 2, it is characterised in that:
Bayesian network fault diagnosis model design in, the fault diagnosis model based on Bayesian network include data acquisition,
Three links of data prediction and data mining;
2.1:Data acquisition
The step accesses MySQL database by database connecting node, reads sample set data, and data content is sentenced including 8
Determine index and 1 failure determination result;Wherein, the 10 groups of sample metadata randomly selected are as shown in table 1-3;
Table 1-3 sample set metadatas
2.2:Data prediction
For the sample metadata read from database, the data prediction of progress is included into row filtering, row and exchanged and data point
Area;
2.2.1:The distracter trained for Bayesian network is removed using row filter node;
2.2.2:Upset the case order of circuit breaker failure using row switching node, be that the random subregion of sample data is prepared;
2.2.3:Sample data is randomly divided into two parts by 70% using data partition node, a part is used for Bayesian network sample
This collection is trained, and another part is tested for sample set;By the comparison of test result and actual result, Bayesian network mould is verified
The accuracy of type;
By pretreated metadata as shown in table 1-4 and table 1-5;Not only put in order and changed, for train and
The sample size of test also changes therewith;
The pretreated training datas of table 1-4
The pretreated test datas of table 1-5
2.3:Data mining
2.3.1:On the basis of data prediction, the Bayesian network node that diagnostic model is employed in being extended outside Weka enters
Row data mining, by the training to great amount of samples data, forms an event based on Bayesian network conditional probability distribution
Hinder diagnostic model;
2.3.2:It is that user need not write program using the advantage of KNIME platform modelings, only needs simple node connection and join
Number is set, and just can construct the system model of complexity;Input, output and the parameter setting of Bayesian network node in this diagnostic model
It is as follows:
A) input of Bayesian network node is 8 Judging index:Closing coil insulaion resistance, no-voltage trip coil state, conjunction
Lock coil voltage, on off state, overload protection, overcurrent protection, under-voltage protection, inverse work(protection;
B) target of Bayesian network node is output as circuit breaker failure type;
C) parameter of Bayesian network node is set.
4. the circuit breaker failure diagnostic method based on Bayesian network according to claim 3, it is characterised in that:
In circuit breaker failure diagnosis, by calling the Bayesian network fault diagnosis model, realize to circuit breaker failure type
Diagnosis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710312354.3A CN107247450A (en) | 2017-05-05 | 2017-05-05 | Circuit breaker failure diagnostic method based on Bayesian network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710312354.3A CN107247450A (en) | 2017-05-05 | 2017-05-05 | Circuit breaker failure diagnostic method based on Bayesian network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107247450A true CN107247450A (en) | 2017-10-13 |
Family
ID=60016914
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710312354.3A Pending CN107247450A (en) | 2017-05-05 | 2017-05-05 | Circuit breaker failure diagnostic method based on Bayesian network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107247450A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108020781A (en) * | 2017-12-19 | 2018-05-11 | 上海电机学院 | A kind of circuit breaker failure diagnostic method |
CN109032872A (en) * | 2018-08-13 | 2018-12-18 | 广州供电局有限公司 | Equipment fault diagnosis method and system based on bayesian network |
CN109062189A (en) * | 2018-08-30 | 2018-12-21 | 华中科技大学 | A kind of industrial process method for diagnosing faults for complex fault |
CN109100646A (en) * | 2018-08-17 | 2018-12-28 | 国网江苏省电力有限公司检修分公司 | A kind of Fault Diagnosis for HV Circuit Breakers method |
CN110649980A (en) * | 2019-09-04 | 2020-01-03 | 北京百分点信息科技有限公司 | Fault diagnosis method and device and electronic equipment |
CN117114226A (en) * | 2023-10-20 | 2023-11-24 | 无锡宇拓物联信息科技有限公司 | Intelligent dynamic optimization and process scheduling system of automation equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103245911A (en) * | 2013-05-03 | 2013-08-14 | 云南电力试验研究院(集团)有限公司电力研究院 | Breaker fault diagnosis method based on Bayesian network |
CN103616635A (en) * | 2013-12-05 | 2014-03-05 | 国家电网公司 | Method and device for diagnosing mechanical characteristic failures of high-voltage circuit-breaker |
CN104297589A (en) * | 2014-09-29 | 2015-01-21 | 国家电网公司 | Method for diagnosing fault of oil-immersed transformer on basis of rough set and bayesian network |
CN106130986A (en) * | 2016-06-30 | 2016-11-16 | 湘潭大学 | A kind of wind energy turbine set active safety defence method based on automated decision-making |
CN106250934A (en) * | 2016-08-12 | 2016-12-21 | 南方电网科学研究院有限责任公司 | The sorting technique of a kind of defective data and device |
-
2017
- 2017-05-05 CN CN201710312354.3A patent/CN107247450A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103245911A (en) * | 2013-05-03 | 2013-08-14 | 云南电力试验研究院(集团)有限公司电力研究院 | Breaker fault diagnosis method based on Bayesian network |
CN103616635A (en) * | 2013-12-05 | 2014-03-05 | 国家电网公司 | Method and device for diagnosing mechanical characteristic failures of high-voltage circuit-breaker |
CN104297589A (en) * | 2014-09-29 | 2015-01-21 | 国家电网公司 | Method for diagnosing fault of oil-immersed transformer on basis of rough set and bayesian network |
CN106130986A (en) * | 2016-06-30 | 2016-11-16 | 湘潭大学 | A kind of wind energy turbine set active safety defence method based on automated decision-making |
CN106250934A (en) * | 2016-08-12 | 2016-12-21 | 南方电网科学研究院有限责任公司 | The sorting technique of a kind of defective data and device |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108020781A (en) * | 2017-12-19 | 2018-05-11 | 上海电机学院 | A kind of circuit breaker failure diagnostic method |
CN109032872A (en) * | 2018-08-13 | 2018-12-18 | 广州供电局有限公司 | Equipment fault diagnosis method and system based on bayesian network |
CN109032872B (en) * | 2018-08-13 | 2021-08-10 | 广东电网有限责任公司广州供电局 | Bayesian network-based equipment fault diagnosis method and system |
CN109100646A (en) * | 2018-08-17 | 2018-12-28 | 国网江苏省电力有限公司检修分公司 | A kind of Fault Diagnosis for HV Circuit Breakers method |
CN109062189A (en) * | 2018-08-30 | 2018-12-21 | 华中科技大学 | A kind of industrial process method for diagnosing faults for complex fault |
CN109062189B (en) * | 2018-08-30 | 2020-06-30 | 华中科技大学 | Industrial process fault diagnosis method for complex fault |
CN110649980A (en) * | 2019-09-04 | 2020-01-03 | 北京百分点信息科技有限公司 | Fault diagnosis method and device and electronic equipment |
CN110649980B (en) * | 2019-09-04 | 2021-09-28 | 北京百分点科技集团股份有限公司 | Fault diagnosis method and device and electronic equipment |
CN117114226A (en) * | 2023-10-20 | 2023-11-24 | 无锡宇拓物联信息科技有限公司 | Intelligent dynamic optimization and process scheduling system of automation equipment |
CN117114226B (en) * | 2023-10-20 | 2024-01-30 | 无锡宇拓物联信息科技有限公司 | Intelligent dynamic optimization and process scheduling system of automation equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107247450A (en) | Circuit breaker failure diagnostic method based on Bayesian network | |
CN107482626B (en) | Method for identifying key nodes of regional power grid | |
CN107527114B (en) | A kind of route platform area exception analysis method based on big data | |
CN105512448B (en) | A kind of appraisal procedure of power distribution network health index | |
CN110458230A (en) | A kind of distribution transforming based on the fusion of more criterions is with adopting data exception discriminating method | |
CN110298601A (en) | A kind of real time business air control system of rule-based engine | |
Deka et al. | Learning topology of the power distribution grid with and without missing data | |
CN104299115B (en) | Secondary system of intelligent substation state analysis method based on Fuzzy C-Means Cluster Algorithm | |
CN108414896B (en) | Power grid fault diagnosis method | |
CN106569030B (en) | Alarm threshold optimization method and device in a kind of electrical energy measurement abnormity diagnosis | |
CN107632590B (en) | A kind of bottom event sort method priority-based | |
CN105721228A (en) | Method for importance evaluation of nodes of power telecommunication network based on fast density clustering | |
CN110059714A (en) | Diagnosis Method of Transformer Faults based on multi-category support vector machines | |
CN109800995A (en) | A kind of grid equipment fault recognition method and system | |
CN109033513A (en) | Method for diagnosing fault of power transformer and diagnosing fault of power transformer device | |
CN109670611A (en) | A kind of power information system method for diagnosing faults and device | |
CN110232405A (en) | Method and device for personal credit file | |
CN104217088B (en) | The optimization method and system of operator's mobile service resource | |
CN113222036A (en) | Automatic defect identification method and device for high-voltage cable grounding system | |
CN105301602B (en) | One kind is based on grey relational grade aeronautical satellite integrity key point integrated recognition method | |
CN105406461A (en) | Adaptive dynamic load monitoring method for power distribution network power failure events | |
CN109587145B (en) | False data intrusion detection method, device and equipment in power network | |
CN114154766A (en) | Method and system for early warning vulnerability of power grid under dynamic prediction of thunder and lightning | |
CN110348676A (en) | A kind of automation of transformation substations equipment state evaluation method and system | |
CN106100870A (en) | A kind of community network event detecting method based on link prediction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171013 |
|
RJ01 | Rejection of invention patent application after publication |