CN107621594B - A kind of electric network failure diagnosis method based on fault recorder data and Bayesian network - Google Patents
A kind of electric network failure diagnosis method based on fault recorder data and Bayesian network Download PDFInfo
- Publication number
- CN107621594B CN107621594B CN201711115714.7A CN201711115714A CN107621594B CN 107621594 B CN107621594 B CN 107621594B CN 201711115714 A CN201711115714 A CN 201711115714A CN 107621594 B CN107621594 B CN 107621594B
- Authority
- CN
- China
- Prior art keywords
- failure
- probability
- fault
- electronic component
- node
- 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.)
- Active
Links
Landscapes
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Emergency Protection Circuit Devices (AREA)
Abstract
The electric network failure diagnosis method based on fault recorder data and Bayesian network that the invention discloses a kind of, includes the following steps: S1: determining fault zone by protective device action message, breaker information and the fault recorder data in SCADA system information；S2: establishing Bayesian network diagnostic model according to fault zone, obtains the probability of malfunction G1 of each element；S3: the probability of malfunction G2 of each element is obtained by fault diagnosis principle using fault recorder data；S4: the different weight of G1 and G2 is assigned according to expert method, the probability of malfunction G3 of each element is obtained by weighted average method.Compared with prior art, the present invention the diagnosis to failure is more accurate, and can adjust the weight of two methods according to the actual situation, there is very high practicability.
Description
Technical field
The present invention relates to electric network failure diagnosis fields, are based on fault recorder data and Bayes more particularly, to one kind
The electric network failure diagnosis method of network.
Background technique
SCADA (operation supervisory control and data aquisition system) system is equipment indispensable in control centre, it can be
Auxiliary dispatching person's electric power monitoring system when Power System Steady-state is run, also can provide fault message in failure for dispatcher.Work as hair
When raw failure, SCADA system can provide the outlet action message of switching information and protection for staff, but this is not able to satisfy
Demand of the fault diagnosis to information.Also, existing dispatch automated system can only acquire data in the system failure, not to letter
Breath, which is screened and processed, is just supplied directly to dispatcher, and dispatcher is caused to have little time to judge and handle.When generation complex fault
When, if only using the data that SCADA system reports, diagnostic system can not provide satisfactory result.In order to guarantee
What is diagnosed is accurate, needs to find new diagnostic message source and diagnostic method.
Summary of the invention
The present invention overcomes the technological deficiencies of above-mentioned existing method for diagnosing faults, provide a kind of based on fault recorder
According to the electric network failure diagnosis method with Bayesian network.The present invention passes through fault recorder data, breaker actuation information and electronics
Each element current direction matrix when element fault acquisition of information failure, forms suspicious element collection；Pass through Bayesian network simultaneously,
Electric network failure diagnosis is carried out, forms suspicious element collection, the weight distribution provided using expert method is carried out using weighted average model
Diagnosis.
In order to solve the above technical problems, technical scheme is as follows:
A kind of electric network failure diagnosis method based on fault recorder data and Bayesian network, includes the following steps:
S1: it is determined by protective device action message, breaker information and the fault recorder data in SCADA system information
Fault zone；
S2: establishing Bayesian network diagnostic model according to fault zone, obtains the probability of malfunction G1 of each element；
S3: the probability of malfunction G2 of each element is obtained by fault diagnosis principle using fault recorder data；
S4: the different weight of G1 and G2 is assigned according to expert method, the failure of each element is obtained by weighted average method
Probability G3.
In a preferred solution, the S2 includes following below scheme:
S2.1: corresponding Bayesian network diagnostic model is established to the node in fault zone；The node includes mother
Line, route, electronic component, breaker and protective device；
S2.2: for the Bayesian network diagnostic model of each electronic component, the failure prior probability of each node is solved；
S2.3: failure prior probability is associated with posterior probability, obtains the probability of malfunction G1 of element.
In a preferred solution, the failure prior probability of each node in the S2.2 includes following calculating stream
Journey:
S2.2.1: it for the failure prior probability of electronic component, is calculated by the year failure-frequency of equipment, i.e. equipment
Continuous operation for a period of time after, the probability that breaks down；The failure prior probability P of electronic component1It is asked by following formula
It takes:
P1=P { 0 < t }=1-ewt
In formula, w is element year failure rate, and t is that element overhauls number.
S2.2.2: for the failure prior probability P of breaker and protective device linkage2, P2It is asked by following formula
It takes:
In formula, parent (Xi) indicate electronic component node.
In a preferred solution, the probability of malfunction G1 of the element is sought by following formula:
In formula, P (Y) indicates the failure prior probability of electronic component, i.e. P (Y)=P1；P (X) indicates breaker node and protects
The failure prior probability of protection unit linkage, i.e. P (X)=P2；P (Y | X) indicate the item acted in known breaker and protective device
Under part, the probability of electronic component failure；P (X | Y) indicate breaker and protective device under conditions of known electronic element fault
The probability of the failure of linkage.
In a preferred solution, the S3 includes following below scheme:
S3.1: for the node x in fault recorder data1, x2..., xn-1, xn, adopted by Lagrange's interpolation insertion
Sampling point is handled, and the polynomial equation y=f (x) across n node is obtained；
S3.2: failure is carried out using mutation quantity algorithm for the sampled point of the Lagrange's interpolation in fault recorder data
Differentiate；
S3.3: fault component extraction is carried out to malfunctioning node, obtains positive negative voltage and current component phase；
S3.4: by positive negative voltage and current component phase, differentiate current direction, form element current directional correlation square
Battle array, obtains the probability of malfunction G2 of each element according to current direction matrix.
In a preferred solution, secondary Lagrange's interpolation is used in the S3.1 to be handled, specifically
Content is as follows:
For the node x in fault recorder data1, x2..., xn-1, xn, interpolation point x and corresponding three points are set
xi-1,xi,xi+1, the i sought by following formula:
According to x, xi-1,xi,xi+1Obtain secondary Lagrange interpolation polynomial y=f (x), the y=f (x) by with
Lower formula is sought:
In a preferred solution, four sampled values are used in the S3.2 be mutated quantity algorithm, four samplings
Value mutation quantity algorithm content is as follows:
Δ i (k)=[i (k)-i (k-N)]-[i (k-N)+i (k-2N)]
In formula, Δ i (k) is current change quantity, and i (k) is the current sampling data of this week interim k-th of sampled point, i (k-N)
For the current sampling data of k-th of sampled point in a upper period, i (k-2N) is the current sample of k-th of sampled point in upper two cycles
Value；
Fault initiating discrimination formula:
Δ i (k) > Iset
In formula, IsetIt is preset value.If Δ i (k) > Iset, then judge node for malfunctioning node.
In a preferred solution, the IsetIt is sought by following formula:
Iset=k1Δi(k)+k2IN
In formula, k1And k2It is preset value, INIt is the load current value before corresponding electronic component failure.
In a preferred solution, the S3.3 includes following calculation process:
S3.3.1: fault component i is extractedg(t), the ig(t) it is sought by following formula:
ig(t)=i (t)-i (t-nN)
In formula, i (t) be failure when current sampling data, i (t-nN) be failure before current sampling data, and i (t-nN) with
I (t) is separated by n period, and N is each cycle sampling number；
S3.3.2: in fault component ig(t) corresponding positive negative voltage and current component phase is obtained on.
Compared with prior art, the beneficial effect of technical solution of the present invention is:
It is each when the present invention is by fault recorder data, breaker actuation information and electronic component failure acquisition of information failure
Element current direction matrix forms suspicious element collection；Simultaneously by Bayesian network, electric network failure diagnosis is carried out, is formed suspicious
Element collection, the weight distribution provided using expert method, is diagnosed using weighted average model.The present invention and prior art phase
Than, it is more accurate to the diagnosis of failure, and the weight of two methods can be adjusted according to the actual situation, have very high practical
Property.
Detailed description of the invention
Fig. 1 is the present embodiment flow chart.
Specific embodiment
The attached figures are only used for illustrative purposes and cannot be understood as limitating the patent；
To those skilled in the art, it is to be understood that certain known features and its explanation, which may be omitted, in attached drawing
's.
The following further describes the technical solution of the present invention with reference to the accompanying drawings and examples.
As shown in Figure 1, a kind of electric network failure diagnosis method based on fault recorder data and Bayesian network, including it is as follows
Step:
S1. fault zone is determined by SCADA system information；
Event is determined by protective device action message, breaker information and the fault recorder data in SCADA system information
Hinder region.
S2. corresponding Bayesian network diagnostic model is established to the node in fault zone；
Node includes bus, route, electronic component, breaker and protective device.
S3. the failure prior probability of each node is solved；
For the failure prior probability of electronic component, calculated by the year failure-frequency of equipment, i.e., equipment is continuously transported
After row a period of time, the probability that breaks down；The failure prior probability P of electronic component1It is sought by following formula:
P1=P { 0 < t }=1-ewt
In formula, w is element year failure rate, and t is that element overhauls number, takes t=2 in the present embodiment；
For the failure prior probability P of breaker and protective device linkage2, P2It is sought by following formula:
In formula, parent (Xi) indicate electronic component node.
S4. failure prior probability is associated with posterior probability, obtains the probability of malfunction G1 of element；
The probability of malfunction G1 of element is sought by following formula:
In formula, P (Y) indicates the failure prior probability of electronic component, i.e. P (Y)=P1；P (X) indicates breaker node and protects
The failure prior probability of protection unit linkage, i.e. P (X)=P2；P (Y | X) indicate the item acted in known breaker and protective device
Under part, the probability of electronic component failure；P (X | Y) indicate breaker and protective device under conditions of known electronic element fault
The probability of the failure of linkage.
S5. Lagrange's interpolation is used to the node in fault recorder data；
For the node x in fault recorder data1, x2..., xn-1, xn, interpolation point x and corresponding three points are set
xi-1,xi,xi+1, the i sought by following formula:
According to x, xi-1,xi,xi+1Obtain secondary Lagrange interpolation polynomial y=f (x), the y=f (x) by with
Lower formula is sought:
S6. fault distinguishing is carried out using four sampled values mutation quantity algorithm for the sampled point in fault recorder data；
It is as follows that four sampled values are mutated quantity algorithm content:
Δ i (k)=[i (k)-i (k-N)]-[i (k-N)+i (k-2N)]
In formula, Δ i (k) is current change quantity, and i (k) is the current sampling data of this week interim k-th of sampled point, i (k-N)
For the current sampling data of k-th of sampled point in a upper period, i (k-2N) is the current sample of k-th of sampled point in upper two cycles
Value；
Fault initiating discrimination formula:
Δ i (k) > Iset
Iset=k1Δi(k)+k2IN
In formula, k1And k2It is preset value, INIt is the load current value before corresponding electronic component failure.If Δ i (k) >
Iset, then judge node for malfunctioning node.
S7. fault component extraction is carried out to malfunctioning node, obtains positive negative voltage and current component phase；
Fault component i is extracted to malfunctioning nodeg(t), ig(t) it is sought by following formula:
ig(t)=i (t)-i (t-nN)
In formula, i (t) be failure when current sampling data, i (t-nN) be failure before current sampling data, and i (t-nN) with
I (t) is separated by n period, and N is each cycle sampling number；
In fault component ig(t) corresponding positive negative voltage and current component phase is obtained on.
S8. by positive negative voltage and current component phase, the probability of malfunction G2 of each element is obtained；
By positive negative voltage and current component phase, current direction is differentiated, form element current directional correlation matrix, root
The probability of malfunction G2 of each element is obtained according to current direction matrix.
S9. the different weight of G1 and G2 is assigned according to expert method, the failure of each element is obtained by weighted average method
Probability G3；
In the present embodiment, 40% weight is assigned to G1, assigns 60% weight to G2.
The same or similar label correspond to the same or similar components；
The terms describing the positional relationship in the drawings are only for illustration, should not be understood as the limitation to this patent；
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
Made any modifications, equivalent replacements, and improvements etc., should be included in the claims in the present invention within the spirit and principle of invention
Protection scope within.
Claims (5)
1. a kind of electric network failure diagnosis method based on fault recorder data and Bayesian network, which is characterized in that including as follows
Step:
S1: failure is determined by protective device action message, breaker information and the fault recorder data in SCADA system information
Region；
S2: establishing Bayesian network diagnostic model according to fault zone, obtains the probability of malfunction G1 of each electronic component；
S3: the probability of malfunction G2 of each electronic component is obtained by fault diagnosis principle using fault recorder data；
S4: the different weight of G1 and G2 is assigned according to expert method, the failure of each electronic component is obtained by weighted average method
Probability G3；
The S2 includes following below scheme:
S2.1: corresponding Bayesian network diagnostic model is established to the node in fault zone；The node includes bus, line
Road, electronic component, breaker and protective device；
S2.2: for the Bayesian network diagnostic model of each electronic component, the failure prior probability of each node is solved；
S2.3: failure prior probability is associated with posterior probability, obtains the probability of malfunction G1 of electronic component；
The failure prior probability of each node in the S2.2 includes following calculation process:
S2.2.1: it for the failure prior probability of electronic component, is calculated by the year failure-frequency of equipment, i.e., equipment is continuous
After running a period of time, the probability that breaks down；The failure prior probability P of electronic component1It is sought by following formula:
P1=P { 0 < t }=1-ewt
In formula, w is electronic component year failure rate, and t is that electronic component overhauls number；
S2.2.2: for the failure prior probability P of breaker and protective device linkage2, failure prior probability P2Pass through following formula
It is sought:
In formula, parent (Xi) indicate electronic component node；
The probability of malfunction G1 of the electronic component is sought by following formula:
In formula, P (Y) indicates the failure prior probability of electronic component, i.e. P (Y)=P1；P (X) indicates that breaker node and protection fill
Set the failure prior probability of linkage, i.e. P (X)=P2；P (Y | X) it indicates under conditions of known breaker and protective device act,
The probability of electronic component failure；P (X | Y) it indicates under conditions of known electronic element fault, breaker and protective device link
Failure probability；
The S3 includes following below scheme:
S3.1: for the node x in fault recorder data1, x2..., xn-1, xn, sampled point is inserted by Lagrange's interpolation
It is handled, obtains the polynomial equation y=f (x) across n node；
S3.2: failure is carried out using mutation quantity algorithm for the sampled point of the Lagrange's interpolation in fault recorder data and is sentenced
Not；
S3.3: fault component extraction is carried out to malfunctioning node, obtains positive negative voltage and current component phase；
S3.4: by positive negative voltage and current component phase, differentiating current direction, forms electronic component current direction and is associated with square
Battle array, obtains the probability of malfunction G2 of each electronic component according to current direction matrix.
2. electric network failure diagnosis method according to claim 1, which is characterized in that use secondary drawing in the S3.1
Ge Lang interpolation method is handled, and particular content is as follows:
For the node x in fault recorder data1, x2..., xn-1, xn, interpolation point x and corresponding three points x is seti-1,xi,
xi+1, the i sought by following formula:
According to x, xi-1,xi,xi+1Secondary Lagrange interpolation polynomial y=f (x) is obtained, the y=f (x) passes through following public affairs
Formula is sought:
3. electric network failure diagnosis method according to claim 2, which is characterized in that use four samplings in the S3.2
Value mutation quantity algorithm, the four sampled values mutation quantity algorithm content are as follows:
Δ i (k)=[i (k)-i (k-N)]-[i (k-N)+i (k-2N)]
In formula, Δ i (k) is current change quantity, and i (k) is the current sampling data of this week interim k-th of sampled point, and i (k-N) is upper
The current sampling data of k-th of sampled point in one period, i (k-2N) are the current sampling data of k-th of sampled point in upper two cycles；
Fault initiating discrimination formula:
Δ i (k) > Iset
In formula, IsetIt is preset value, if Δ i (k) > Iset, then judge node for malfunctioning node.
4. electric network failure diagnosis method according to claim 3, which is characterized in that the IsetBy following formula into
Row is sought:
Iset=k1Δi(k)+k2IN
In formula, k1And k2It is preset value, INIt is the load current value before corresponding electronic component failure.
5. electric network failure diagnosis method according to claim 3 or 4, which is characterized in that the S3.3 includes following meter
Calculate process:
S3.3.1: fault component i is extractedg(t), the ig(t) it is sought by following formula:
ig(t)=i (t)-i (t-nN)
In formula, current sampling data when i (t) is failure, i (t-nN) is the current sampling data before failure, and i (t-nN) and i (t)
It is separated by n period, N is each cycle sampling number；
S3.3.2: in fault component ig(t) corresponding positive negative voltage and current component phase is obtained on.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711115714.7A CN107621594B (en) | 2017-11-13 | 2017-11-13 | A kind of electric network failure diagnosis method based on fault recorder data and Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711115714.7A CN107621594B (en) | 2017-11-13 | 2017-11-13 | A kind of electric network failure diagnosis method based on fault recorder data and Bayesian network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107621594A CN107621594A (en) | 2018-01-23 |
| CN107621594B true CN107621594B (en) | 2019-10-22 |
Family
ID=61098886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711115714.7A Active CN107621594B (en) | 2017-11-13 | 2017-11-13 | A kind of electric network failure diagnosis method based on fault recorder data and Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107621594B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108768748B (en) * | 2018-06-20 | 2021-05-11 | 广东电网有限责任公司 | Fault diagnosis method and device for power communication service and storage medium |
| CN109001596B (en) * | 2018-10-17 | 2021-06-29 | 广东电网有限责任公司 | Power grid fault diagnosis and power transmission line parameter identification system |
| CN110108981B (en) * | 2019-04-30 | 2024-05-31 | 中国电力科学研究院有限公司 | Fault diagnosis method and system for lines in active power distribution network |
| CN110414552B (en) * | 2019-06-14 | 2021-07-16 | 中国人民解放军海军工程大学 | Bayesian evaluation method and system for spare part reliability based on multi-source fusion |
| CN110488156A (en) * | 2019-08-30 | 2019-11-22 | 西南交通大学 | A kind of high-speed railway distribution substation fault component diagnosis method |
| CN112147459B (en) * | 2020-08-12 | 2024-08-16 | 国电南瑞科技股份有限公司 | SCADA system-based power grid fault analysis device and method |
| CN111985708B (en) * | 2020-08-17 | 2023-09-22 | 云南电网有限责任公司电力科学研究院 | Bayesian algorithm-based high-voltage circuit breaker refusal operation probability prediction method and device |
| CN113283603B (en) * | 2021-06-08 | 2023-06-20 | 华能(浙江)能源开发有限公司清洁能源分公司 | Fine closed-loop fan fault diagnosis method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101661075A (en) * | 2009-06-08 | 2010-03-03 | 浙江大学 | Power system failure diagnostic method based on neural network and fuzzy integral |
| CN101726688A (en) * | 2009-09-17 | 2010-06-09 | 浙江大学 | Method for diagnosing multi-data-source information fusion-based power system fault |
| CN103293421A (en) * | 2013-06-07 | 2013-09-11 | 云南电力调度控制中心 | Power grid fault diagnostic model and diagnostic method thereof |
| CN103995215A (en) * | 2014-05-08 | 2014-08-20 | 国家电网公司 | Intelligent electrical-network fault diagnosis method based on multilevel feedback adjustment |
| CN105044562A (en) * | 2015-08-26 | 2015-11-11 | 云南电网有限责任公司电力科学研究院 | Distribution network fault positioning method based on Bayes formula algorithm |
| CN105093033A (en) * | 2015-09-01 | 2015-11-25 | 华中电网有限公司 | Power grid multi-source information-based fault integrated analysis system and analysis method |
| CN104698343B (en) * | 2015-03-26 | 2016-06-08 | 广东电网有限责任公司电力调度控制中心 | Power grid fault judgment method and system based on history recorder data |
| CN105974232A (en) * | 2016-05-10 | 2016-09-28 | 国网山东省电力公司德州供电公司 | Power grid fault diagnosis method suitable for high tension transmission network |
| CN106226658A (en) * | 2016-09-07 | 2016-12-14 | 上海市政工程设计研究总院（集团）有限公司 | A kind of electric network failure diagnosis method based on multi-data fusion |
| CN106841909A (en) * | 2016-12-20 | 2017-06-13 | 国网辽宁省电力有限公司沈阳供电公司 | Multi-source Information Fusion distribution network failure analysis based on direction hierarchical fuzzy Petri network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8593769B2 (en) * | 2008-09-19 | 2013-11-26 | Schweitzer Engineering Laboratories Inc | Secure arc flash detection |
-
2017
- 2017-11-13 CN CN201711115714.7A patent/CN107621594B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101661075A (en) * | 2009-06-08 | 2010-03-03 | 浙江大学 | Power system failure diagnostic method based on neural network and fuzzy integral |
| CN101726688A (en) * | 2009-09-17 | 2010-06-09 | 浙江大学 | Method for diagnosing multi-data-source information fusion-based power system fault |
| CN103293421A (en) * | 2013-06-07 | 2013-09-11 | 云南电力调度控制中心 | Power grid fault diagnostic model and diagnostic method thereof |
| CN103995215A (en) * | 2014-05-08 | 2014-08-20 | 国家电网公司 | Intelligent electrical-network fault diagnosis method based on multilevel feedback adjustment |
| CN104698343B (en) * | 2015-03-26 | 2016-06-08 | 广东电网有限责任公司电力调度控制中心 | Power grid fault judgment method and system based on history recorder data |
| CN105044562A (en) * | 2015-08-26 | 2015-11-11 | 云南电网有限责任公司电力科学研究院 | Distribution network fault positioning method based on Bayes formula algorithm |
| CN105093033A (en) * | 2015-09-01 | 2015-11-25 | 华中电网有限公司 | Power grid multi-source information-based fault integrated analysis system and analysis method |
| CN105974232A (en) * | 2016-05-10 | 2016-09-28 | 国网山东省电力公司德州供电公司 | Power grid fault diagnosis method suitable for high tension transmission network |
| CN106226658A (en) * | 2016-09-07 | 2016-12-14 | 上海市政工程设计研究总院（集团）有限公司 | A kind of electric network failure diagnosis method based on multi-data fusion |
| CN106841909A (en) * | 2016-12-20 | 2017-06-13 | 国网辽宁省电力有限公司沈阳供电公司 | Multi-source Information Fusion distribution network failure analysis based on direction hierarchical fuzzy Petri network |
Non-Patent Citations (6)
| Title |
|---|
| 基于多源信息融合的电网故障诊断方法研究;高振兴 等;《电力系统保护与控制》;20110316;第39卷(第6期);第17-23页 * |
| 基于改进贝叶斯网络和Hibert-Huang变换的多源信息融合电网故障诊断方法;罗孝辉;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20160115(第01期);第C042-351页 * |
| 基于故障录波数据的分析软件设计与电网故障诊断方法;方志宏;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20160115(第01期);第C042-394页 * |
| 基于概率盒理论的电网故障信息融合算法研究;刘彦君;《中国优秀硕士学位论文全文数据库 信息科技辑》;20170215(第02期);第I140-149页 * |
| 基于贝叶斯网络和故障录波数据的电网故障综合诊断方法;王海港 等;《电力系统及其自动化》;20161231;第38卷(第4期);第93-96页 * |
| 融合信息理论的电力系统故障诊断解析模型;张岩 等;《电力自动化设备》;20140228;第34卷(第2期);第158-174页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107621594A (en) | 2018-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107621594B (en) | A kind of electric network failure diagnosis method based on fault recorder data and Bayesian network | |
| CN111443259A (en) | Active power distribution network fault diagnosis method and system based on local abnormal factor detection | |
| CN108083044A (en) | A kind of elevator based on big data analysis maintenance system and method on demand | |
| CN107798395A (en) | A kind of power grid accident signal automatic diagnosis method and system | |
| CN106405475A (en) | Electric energy meter abnormity diagnosis method | |
| CN114065875B (en) | Power grid fault identification system based on big data | |
| CN104537271B (en) | A kind of power distribution network bad data recognition method based on quality tab | |
| Hor et al. | Building knowledge for substation-based decision support using rough sets | |
| CN109521348A (en) | A kind of reliability test of dc circuit breaker IGBT module and lifetime estimation method | |
| CN106646130B (en) | A kind of active distribution network Fault Locating Method compared based on current polarity and system | |
| CN103995172B (en) | Method for on-line monitoring of load current of GIS bus of substation | |
| CN104615122B (en) | A kind of industry control signal detection system and detection method | |
| Wang et al. | A minimum hitting set algorithm with prejudging mechanism for model-based fault diagnosis in distribution networks | |
| CN105022021A (en) | State discrimination method for gateway electrical energy metering device based on the multiple agents | |
| CN107846472A (en) | The fleet anomaly detection method of extensive power transmission and transforming equipment Monitoring data flow | |
| CN108919044A (en) | A kind of unit style distribution network failure active identification method based on mutual verification scheme | |
| CN104215879B (en) | A kind of short circuit fault of power distribution network localization method and system | |
| CN108287327A (en) | Metering automation terminal fault diagnostic method based on Bayes's classification | |
| CN117612345A (en) | Power equipment state monitoring and alarming system and method | |
| CN113376476A (en) | PHM-based operation and maintenance system and method for medium and low voltage power distribution network | |
| CN111144549A (en) | Microgrid attack identification method based on convolutional neural network and microgrid coordination controller | |
| CN108399579B (en) | Intelligent analysis system for monitoring data signals of substation equipment | |
| CN115470850A (en) | Water quality abnormal event recognition early warning method based on pipe network water quality time-space data | |
| CN109884469A (en) | The determination method of distribution network failure section and fault moment | |
| CN112924813B (en) | Power distribution network short-circuit fault monitoring method and device based on electrical data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |