CN103001812B - Intelligent electric power communication failure diagnostic system - Google Patents
Intelligent electric power communication failure diagnostic system Download PDFInfo
- Publication number
- CN103001812B CN103001812B CN201310004309.3A CN201310004309A CN103001812B CN 103001812 B CN103001812 B CN 103001812B CN 201310004309 A CN201310004309 A CN 201310004309A CN 103001812 B CN103001812 B CN 103001812B
- Authority
- CN
- China
- Prior art keywords
- alarm
- unit
- failure
- network
- fault
- 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
- Data Exchanges In Wide-Area Networks (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention belongs to powerline network fault diagnosis field, particularly based on the Intelligent electric power communication failure diagnostic system of neural net.This Intelligent electric power communication failure diagnostic system, comprising: data preprocessing unit, failure location unit, failure diagnosis unit, rearmounted comprehensive analysis of fault unit.The Intelligent electric power communication failure diagnostic system that the embodiment of the present invention provides, the intelligent neural network model framework of overall employing, with the design feature of powerline network and operational mode for foundation, analysis and treament is carried out to alarm, effective location and eliminating network failure, thus improve the operation and maintenance efficiency of powerline network.
Description
Technical field
The invention belongs to powerline network fault diagnosis field, particularly based on the Intelligent electric power communication failure diagnostic system of neural net.
Background technology
Along with the development of powerline network, the scale of network constantly expands, and the business of network equipment quantity and carrying also gets more and more.Define various communication mode and the multi-specialized heterogeneous networks mixed such as collection Optical Fiber Transmission, programme-controlled exchange, communication PCM, data communication, relaying protection.Various network produces a large amount of warning information every day, and these Alerting requirements power communication dispatchers must within the shortest time, the position at the network failure place that correctly judges, type and cause the reason of fault, then takes corresponding solution in time.But in existing powerline network management and utilization, total solution is not had to failure diagnosis, and the artificial treatment of a large amount of warning information can take a large amount of operation maintenance personnel, inefficiency and easily produce Data Consistency, make by manually carry out breakdown judge, analysis, location accuracy rate low, troubleshooting efficiency is not high.Therefore, a kind of intelligentized power communication fault diagnosis system of development and construction and method is needed badly.
Summary of the invention
(1) technical problem that will solve
The technical problem to be solved in the present invention is to provide Intelligent electric power communication failure diagnostic system, process communication failure inefficiency to overcome in prior art and easily produce Data Consistency, make by manually carry out breakdown judge, analysis, location accuracy rate low, the not high defect of troubleshooting efficiency.
(2) technical scheme
In order to solve the problems of the technologies described above, the invention provides a kind of Intelligent electric power communication failure diagnostic system, comprising: data preprocessing unit, failure location unit, failure diagnosis unit, rearmounted comprehensive analysis of fault unit;
Described data preprocessing unit is used for processing warning information;
Described failure location unit for extracting the network location information in alarm, and exports the network topology information associated by fault network element, by analyzing alarm sequence, confirms abort situation;
Described failure diagnosis unit is used for storage failure diagnosis scheme data, carries out failure diagnosis, provide contingent failure cause and processing method to input warning information;
The result that failure location unit and failure diagnosis unit draw by described rearmounted comprehensive analysis of fault unit carries out comprehensive analysis and treament, provides optimum fault solution.
Further, described data preprocessing unit comprises:
Alarm coded representation: according to the feature of electric power communication network structure and alarm, alarm is encoded, described coding uniquely can determine alarm, and comprises whole characteristic informations of alarm, to be applicable to the requirement of the input of neural network failure diagnostic system and each unit alarming processing;
Alarm time window: for carrying out extracting and divide in time window mode to alarm, in the time range determined, obtain a series of warning information;
Sliding step: the sliding step that definition alarm obtains.
Further, described failure location unit comprises Layered multi-subnet neural network module, and alarm time window analysis engine, carries out quick position to fault.
Further, described failure diagnosis unit comprises many hidden layers neural network model, storage failure processing method, tracing trouble reason.
Further, network topology structure, according to the networking mode of power telecom network and operation characteristic, is divided into by described failure location unit: end to end connection, chain connect, star-like connection, to carry out the quick position of fault.
(3) beneficial effect
The Intelligent electric power communication failure diagnostic system that the embodiment of the present invention provides, the intelligent neural network model framework of overall employing, with the design feature of powerline network and operational mode for foundation, analysis and treament is carried out to alarm, effective location and eliminating network failure, thus improve the operation and maintenance efficiency of powerline network.
Accompanying drawing explanation
Fig. 1 is embodiment of the present invention Intelligent electric power communication failure diagnostic system structural representation;
Fig. 2 is embodiment of the present invention Intelligent electric power communication failure diagnostic system general frame figure;
Fig. 3 is alarm coding schematic diagram in embodiment of the present invention Intelligent electric power communication failure diagnostic system;
Fig. 4 is embodiment of the present invention Intelligent electric power communication failure diagnostic system network topology johning knot composition.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples for illustration of the present invention, but are not used for limiting the scope of the invention.
As shown in Figure 1-2, the Intelligent electric power communication failure diagnostic system that the embodiment of the present invention provides comprises: data preprocessing unit 1, failure location unit 2, failure diagnosis unit 3, rearmounted comprehensive analysis of fault unit 4;
Data preprocessing unit 1 is for processing warning information;
Failure location unit 2 for extracting the network location information in alarm, and exports the network topology information associated by fault network element, by analyzing alarm sequence, confirms abort situation;
Failure diagnosis unit 3, for storage failure diagnosis scheme data, is carried out failure diagnosis to input warning information, is provided contingent failure cause and processing method;
Fault Locating Method is combined with method for diagnosing faults, while failure diagnosis, can accurate localizing faults network element position, fast fault is processed.
The result that failure location unit 2 and failure diagnosis unit 3 draw is carried out comprehensive analysis and treament by rearmounted comprehensive analysis of fault unit 4, provides optimum fault solution.
Data preprocessing unit, failure location unit, failure diagnosis unit, each unit inside adopts different neural net model establishings, adopt Layered multi-subnet model to mix structure in parallel with many hidden layers neural network model between each unit, select suitable learning algorithm to carry out learning for different neural network models and optimize.
Wherein: data preprocessing unit 1 comprises:
Alarm coded representation 11: according to the feature of electric power communication network structure and alarm, alarm is carried out 12 coded representations, as shown in Figure 3.Wherein 1,2 bit representations are regional inside the province, 3,4 bit representation site information, 5,6 bit representations specialty webmasters, the 7th bit representation producer, the 8th bit representation unit type, 9,10 bit representation network element models, 11,12 bit representation alarm types, by 12 alarm codings, an alarm can be carried out unique identification, and be convenient to neural network module extraction characteristic information wherein, be applicable to the requirement of neural network failure diagnostic system input.
Alarm time window 12: in order to the needs enabling alarm data be applicable to failure diagnosis, with time window model split alarm data, first the alarm record in database is read in, obtain the alarm time of origin of Article 1 record, as window start time, then add that window size obtains window end time by the time started.Then successively by the record that next reads in, the record that the time is not later than the termination time all preserves.If one the time started of record is later than the termination time, then stop record.Obtain the data of an alarm time window thus.
Sliding step 13: adopt and the above-mentioned time window time started is added that sliding step obtains the NEW BEGINNING time, add window size and obtain the new termination time, then started to read in NEW BEGINNING time immediate record by the pointer movement reading record, time window carries out slip to obtain alarm data according to sliding step size.For the selection principle of sliding step, according to sampling thheorem, sliding step choose the half that should be less than time window, the integrality of correlation rule between selected alarm can be ensured like this.
Failure location unit adopts Layered multi-subnet neural network model, and prime sub-network, by extracting the positional information of the network element in alarm, judges the topology connection structure of network element.Power telecom network is carried out the extraction of topological structure according to the pattern of central station, intermediate station and end stations.Topology connection can be exported with end to end connection, chain connection, star-like connection three kinds of modes.
As shown in Figure 4, rear class sub-network is made up of three sub-networks, stores the related network elements information that three kinds of connected modes comprise respectively, by syndeton and warning information, can export associated network element.According to associated NE information, from alarm time window, inquire corresponding alarm, just can accurate fault location.
Failure diagnosis unit adopts many hidden layers neural network model, for storing a large amount of failure diagnosis schemes.This unit carries out failure diagnosis to input warning information, provides contingent failure cause and processing method.Because failure diagnosis scheme can implicitly disperse to be stored in every connection weights and threshold of neural net by neural net, and parallel processing can be carried out.Therefore, the contradiction between the failed storage capacity occurred in network operation process and the speed of service can effectively be solved.
The result that failure location unit and failure diagnosis unit draw by rearmounted comprehensive analysis of fault unit carries out integrated treatment and analysis, can screen failure cause and processing method, provides optimum fault solution.
Intelligent electric power communication failure diagnostic system adopts mixing Parallel neural networks model and Layered multi-subnet neural network structure, and the parallel input of support information, has very strong information processing capability.
The learning algorithm that each unit selection of Intelligent electric power communication failure diagnostic system is suitable, carries out learning to neural network node parameter and connection weight parameter and optimizes, making network have fast convergence rate, the feature that generalization ability is strong.
As can be seen from the above embodiments, the Intelligent electric power communication failure diagnostic system that the present invention proposes and method entirety adopt intelligent neural network model framework, with the design feature of powerline network and operational mode for foundation, analysis and treament is carried out to alarm, effective location and eliminating network failure, thus improve the operation and maintenance efficiency of powerline network.
The above is only the preferred embodiment of the present invention; it should be pointed out that for those skilled in the art, under the prerequisite not departing from the technology of the present invention principle; can also make some improvement and replacement, these improve and replace and also should be considered as protection scope of the present invention.
Claims (1)
1. an Intelligent electric power communication failure diagnostic system, is characterized in that, comprising: data preprocessing unit, failure location unit, failure diagnosis unit, rearmounted comprehensive analysis of fault unit;
Described data preprocessing unit is used for processing warning information;
Described failure location unit for extracting the network location information in alarm, and exports the network topology information associated by fault network element, by analyzing alarm sequence, confirms abort situation;
Described failure diagnosis unit is used for storage failure diagnosis scheme data, carries out failure diagnosis, provide contingent failure cause and processing method to input warning information;
The result that failure location unit and failure diagnosis unit draw by described rearmounted comprehensive analysis of fault unit carries out comprehensive analysis and treament, provides optimum fault solution;
Wherein, described data preprocessing unit comprises:
Alarm coded representation: according to the feature of electric power communication network structure and alarm, alarm is encoded, described coding uniquely can determine alarm, and comprises whole characteristic informations of alarm, to be applicable to the requirement of the input of neural network failure diagnostic system and each unit alarming processing;
Alarm time window: for carrying out extracting and divide in time window mode to alarm, in the time range determined, obtain a series of warning information;
Sliding step: the sliding step that definition alarm obtains;
Wherein, described failure location unit comprises Layered multi-subnet neural network module, and alarm time window analysis engine, carries out quick position to fault;
Wherein, described failure diagnosis unit comprises many hidden layers neural network model, storage failure processing method, tracing trouble reason;
Wherein, network topology structure, according to the networking mode of power telecom network and operation characteristic, is divided into by described failure location unit: end to end connection, chain connect, star-like connection, to carry out the quick position of fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310004309.3A CN103001812B (en) | 2013-01-06 | 2013-01-06 | Intelligent electric power communication failure diagnostic system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310004309.3A CN103001812B (en) | 2013-01-06 | 2013-01-06 | Intelligent electric power communication failure diagnostic system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103001812A CN103001812A (en) | 2013-03-27 |
| CN103001812B true CN103001812B (en) | 2015-12-02 |
Family
ID=47929971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310004309.3A Active CN103001812B (en) | 2013-01-06 | 2013-01-06 | Intelligent electric power communication failure diagnostic system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103001812B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103607048B (en) * | 2013-11-18 | 2017-02-08 | 国家电网公司 | An electric power network device fault diagnosis method and a system |
| US9880724B2 (en) * | 2014-04-11 | 2018-01-30 | S & C Electric Co. | User interface for viewing event data |
| CN104539047B (en) * | 2014-12-23 | 2016-08-10 | 国家电网公司 | Based on multiple-factor comparison visual intelligent substation fault diagnosis and localization method |
| CN106357458B (en) * | 2016-10-31 | 2019-08-06 | 中国联合网络通信集团有限公司 | Network element method for detecting abnormality and device |
| CN107766879A (en) * | 2017-09-30 | 2018-03-06 | 中国南方电网有限责任公司 | The MLP electric network fault cause diagnosis methods of feature based information extraction |
| CN108092822B (en) * | 2018-01-02 | 2021-08-31 | 华北电力大学（保定） | Method and system for recovering power communication network fault link |
| CN112098889B (en) * | 2020-09-09 | 2022-03-04 | 青岛鼎信通讯股份有限公司 | Single-phase earth fault positioning method based on neural network and feature matrix |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1474542A (en) * | 2002-08-06 | 2004-02-11 | 华为技术有限公司 | Telecommunication equipment fault information managing method |
| CN1479461A (en) * | 2002-08-29 | 2004-03-03 | 华为技术有限公司 | Communication system fault diagnosis method and system |
| CN102083116A (en) * | 2011-01-10 | 2011-06-01 | 浪潮通信信息系统有限公司 | Method for constructing intelligent communication alarm fault positioning expert system based on meta-knowledge |
| CN102130783A (en) * | 2011-01-24 | 2011-07-20 | 浪潮通信信息系统有限公司 | Intelligent alarm monitoring method of neural network |
| CN102637019A (en) * | 2011-02-10 | 2012-08-15 | 武汉科技大学 | Intelligent integrated fault diagnosis method and device in industrial production process |
-
2013
- 2013-01-06 CN CN201310004309.3A patent/CN103001812B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1474542A (en) * | 2002-08-06 | 2004-02-11 | 华为技术有限公司 | Telecommunication equipment fault information managing method |
| CN1479461A (en) * | 2002-08-29 | 2004-03-03 | 华为技术有限公司 | Communication system fault diagnosis method and system |
| CN102083116A (en) * | 2011-01-10 | 2011-06-01 | 浪潮通信信息系统有限公司 | Method for constructing intelligent communication alarm fault positioning expert system based on meta-knowledge |
| CN102130783A (en) * | 2011-01-24 | 2011-07-20 | 浪潮通信信息系统有限公司 | Intelligent alarm monitoring method of neural network |
| CN102637019A (en) * | 2011-02-10 | 2012-08-15 | 武汉科技大学 | Intelligent integrated fault diagnosis method and device in industrial production process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103001812A (en) | 2013-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103001812B (en) | Intelligent electric power communication failure diagnostic system | |
| CN104935489B (en) | A kind of information collection networking method and power information acquire network | |
| CN102123045A (en) | Modeling method for high-voltage equipment on-line monitoring systems based on international electro-technical commission (IEC) 61850 | |
| CN107730394A (en) | The polynary isomeric data fusion method of panorama power network based on big data | |
| CN103167526B (en) | Communication base station realizes the method and system of Global Informationization management | |
| CN103779799B (en) | The empty terminal graphic software platform method of intelligent substation field adjustable | |
| CN102841293B (en) | Fault positioning system for 10kV power distribution network circuit | |
| CN103926896A (en) | Underground explosive-proof power source monitoring system and method based on network | |
| CN106603274B (en) | Power distribution network fault positioning method based on multidimensional communication data | |
| CN107918273A (en) | A kind of application system of mobile technology of Internet of things on halved belt sorter | |
| CN205596111U (en) | Online identification system of platform district's circuit | |
| CN103686641A (en) | Method for sending and receiving short message in power monitoring field | |
| CN111369777A (en) | Maintenance method and maintenance system for low-voltage user electricity consumption information acquisition system | |
| CN103532233B (en) | Based on the power information acquisition abnormity Precise Position System of GPRS technology | |
| CN107611940A (en) | A kind of power distribution network method for monitoring abnormality and system based on historical data analysis | |
| CN103268353B (en) | Grid alarm auto response system and grid alarm automatic response method | |
| CN115514089A (en) | Power equipment data monitoring system for transformer substation | |
| CN104599197B (en) | Intelligent substation protection system reliability layering equivalence method | |
| CN105954580A (en) | Remote electric energy metering monitoring system | |
| CN202068232U (en) | Intelligent network recording and analyzing device | |
| CN212541567U (en) | Maintenance system of low-voltage user electricity consumption information acquisition system | |
| CN109507468A (en) | A kind of header box branch current detection method and system based on linked character | |
| CN103679562A (en) | Power grid measurement data monitoring method and system | |
| CN203057173U (en) | Intelligent carrier communication network management device | |
| CN107819625A (en) | A kind of performance diagnogtics method based on electric power radio communication access device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent for invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 030001 East Street, Taiyuan, Shanxi, No. 169 Applicant after: INFORMATION COMMUNICATION BRANCH, STATE GRID SHANXI ELECTRIC POWER CO., LTD. Address before: 030001 East Street, Taiyuan, Shanxi, No. 169 Applicant before: Information and Communication Branch Company, Shanxi Electric Power Company |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: APPLICANT; FROM: INFORMATION COMMUNICATION BRANCH SHANXI ELECTRIC POWER CO., LTD. TO: INFORMATION COMMUNICATION BRANCH COMPANY, STATE GRID SHANXI ELECTRIC POWER COMPANY |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |