CN104064001A - Intelligent transformer substation alarming inference method - Google Patents
Intelligent transformer substation alarming inference method Download PDFInfo
- Publication number
- CN104064001A CN104064001A CN201410275105.8A CN201410275105A CN104064001A CN 104064001 A CN104064001 A CN 104064001A CN 201410275105 A CN201410275105 A CN 201410275105A CN 104064001 A CN104064001 A CN 104064001A
- Authority
- CN
- China
- Prior art keywords
- testing result
- reasoning
- yes
- alarming
- inference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention discloses an intelligent transformer substation alarming inference method. The method comprises the following steps that (1) weight setting is conducted on a signal stored in a knowledge base of an intelligent alarming system of a transformer substation and a threshold and signal collecting time are set for an inference machine; (2) when the transformer substation generates an alarming signal, the intelligent alarming system judges whether the alarming signal triggers the inference machine or not by comparing the alarming signal with the signal stored in the knowledge base; (3) if the detection result in the step (2) is yes, timing is started and whether the set signal collecting time is up or not is detected; (4) if the detection result in the step (3) is yes, whether a new alarming signal is generated or not is detected, and if the detection result is yes, the step (2) is repeated; (5) if the detection result in the step (4) is not, the weight of the alarming signal is calculated, whether the weight is larger than the set threshold is then detected, if the detection result is no, inferring ends, and if the detection result is yes, a conclusion is obtained through inference. The intelligent transformer substation alarming inference method shows the uncertainty of inference and improves the reliability.
Description
Technical field
The present invention relates to transformer station field, be specifically related to a kind of intelligent substation alarm inference method.
Background technology
State Grid Corporation of China clearly proposed to build " having informationization, robotization, interactive intelligent grid ", and unified intelligent grid was built up in plan comprehensively by 2020.Transformer station is the critical facility of electrical network, a large amount of electrical equipments is installed, and intelligent substation Shi Yi transformer station first and second equipment is digitizing object, take express network communications platform as basis, by digital information is carried out to standardization, realize the inside and outside information sharing in station and interoperability.
The warning information amount of intelligent substation is much larger than conventional substation, when fault occurs, system more can be received a large amount of warning information in a short time, and to system, operation has caused larger burden, screens warning information simultaneously and also has sizable difficulty with analysis, reasoning failure cause.The warning system of intelligent substation merges multi-specialized knowledge at present, a large amount of expertises is solidified in system with expert knowledge library form, by the reasoning from logic based on knowledge base, analyze, relevant many warning information that in operational process, certain primary fault produces are carried out to integrated logic reasoning, draw the rational analysis conclusion of this fault, and scheduling station will be sent in result, but come reasoning transformer station fault to there is certain uncertainty with warning information, confidence level is lower, and main manifestations is the following aspects:
One, the uncertainty of warning information: the warning information that monitor and control facility provides is subject to the impact of the factors such as time, watch-dog performance, not completely credible;
Two, the uncertainty of reasoning: being used for the signal of certain fault of reasoning is not that specific those are several, and fault may only occur part signal while occurring;
, may not there is this fault in three, the uncertainty of conclusion: the fault of the actual generation of transformer station not necessarily conforms to reasoning conclusion, also may occur other fault.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of intelligent substation alarm inference method, the alarm inference system that can solve existing intelligent substation carrys out reasoning transformer station fault with warning information, because the uncertainty of warning information, reasoning and conclusion causes the problem that confidence level is lower.
The present invention is achieved through the following technical solutions:
An intelligent substation alarm inference method, comprises the following steps:
(1) to the signal setting weight of storing in intelligent substation warning system knowledge base, to inference machine setting threshold and signals collecting time;
(2), when transformer station produces alarm signal, intelligent warning system judges by contrast knowledge base whether alarm signal triggers inference machine, if testing result is no, waits for new alarm signal;
(3) if the testing result of step (2) is yes, start timing, detect the signals collecting time that whether reaches setting, if testing result is no, continue timing;
(4) if the testing result of step (3) is yes, detect and whether have the new alarm signal of generation, if testing result is yes, return to step (2);
(5) if the testing result of step (4) is no, calculate the weight of alarm signal, then detect the threshold value whether weight is greater than setting, if testing result is no, finish reasoning, if testing result is yes, reasoning is reached a conclusion.
When the great threshold value in setting of step (5) right to examin, first adopt the method for exhaustion to carry out reasoning, if cannot find the event matching, then adopt fuzzy reasoning method to carry out reasoning.
The present invention's advantage is compared with prior art:
One, by weight, show the uncertainty of warning information, by control signal acquisition time to obtain abundant warning information, passing threshold shows the uncertainty of intelligent alarm reasoning, effectively controls the error rate of false alarm rate and the drawn conclusion of reasoning, improves the confidence level of reasoning conclusion;
Two, the Integrated using method of exhaustion and fuzzy reasoning method carry out reasoning, further improve the confidence level of reasoning conclusion;
Three, reduce maintainer's workload, increase work efficiency.
Accompanying drawing explanation
Fig. 1 is intelligent alarm reasoning process flow diagram.
Embodiment
A kind of intelligent substation alarm inference method as shown in Figure 1, comprises the following steps:
(1) to the signal setting weight of storing in intelligent substation warning system knowledge base, to inference machine setting threshold and signals collecting time, need to adjust in conjunction with field operation experiences the setting of threshold values, threshold values arranged conference and causes reasoning can not well show the uncertainty of intelligent alarm reasoning, threshold values arranges too small, can cause producing more false alarm and false alarm;
(2), when transformer station produces alarm signal, intelligent warning system judges by contrast knowledge base whether alarm signal triggers inference machine, if testing result is no, waits for new alarm signal;
(3) if the testing result of step (2) is yes, start timing, detect the signals collecting time that whether reaches setting, if testing result is no, continue timing;
(4) if the testing result of step (3) is yes, detect and whether have the new alarm signal of generation, if testing result is yes, return to step (2);
(5) if the testing result of step (4) is no, calculate the weight of alarm signal, detect again the threshold value whether weight is greater than setting, if testing result is no, finish reasoning, if testing result is yes, first adopts the method for exhaustion to carry out reasoning and reach a conclusion, if cannot find the event matching, then adopt fuzzy reasoning method to carry out reasoning to reach a conclusion.
The so-called method of exhaustion, infers an anomalous event from the combination of certain event; Fuzzy reasoning method is as long as find certain or a plurality of event on certain unit, no matter have other events or not, just infers an anomalous event.Method of exhaustion reasoning is accurate, can effectively get rid of the impact of mistake remote signalling, but adaptability is slightly poor, because substation equipment model, construct variously, alarm signal can not be in full accord; Fuzzy reasoning method inferential accuracy is not as the method for exhaustion, and occasional is subject to the interference of mistake remote signalling, but adaptability is fine, can tackle the equipment of different model, structure, and inferential accuracy is also enough to meet the needs of on-the-spot operation.During system, two kinds of methods are suitably merged, first according to the listed inference rule of the method for exhaustion, contrast, if cannot find out the event matching, use fuzzy reasoning instead, further improve confidence level.
When reasoning is reached a conclusion, warning system gives the correlation signal that may omit in this reasoning process, and prompting operations staff pays close attention to coherent signal and whether relevant apparatus has extremely, finds as early as possible the hidden danger in transformer station.Further, when reasoning draws generation, warning system also can draw the confidence level of this reasoning conclusion according to the quantity, the inference rule Auto-matching of time order and function sequentially and in the time interval and knowledge base that produce alarm signal, is used for pointing out operations staff.
Claims (2)
1. an intelligent substation alarm inference method, is characterized in that comprising the following steps:
(1) to the signal setting weight of storing in intelligent substation warning system knowledge base, to inference machine setting threshold and signals collecting time;
(2), when transformer station produces alarm signal, intelligent warning system judges by contrast knowledge base whether alarm signal triggers inference machine, if testing result is no, waits for new alarm signal;
(3) if the testing result of step (2) is yes, start timing, detect the signals collecting time that whether reaches setting, if testing result is no, continue timing;
(4) if the testing result of step (3) is yes, detect and whether have the new alarm signal of generation, if testing result is yes, return to step (2);
(5) if the testing result of step (4) is no, calculate the weight of alarm signal, then detect the threshold value whether weight is greater than setting, if testing result is no, finish reasoning, if testing result is yes, reasoning is reached a conclusion.
2. a kind of intelligent substation alarm inference method as claimed in claim 1, it is characterized in that: when the great threshold value in setting of step (5) right to examin, first adopt the method for exhaustion to carry out reasoning, if cannot find the event matching, then adopt fuzzy reasoning method to carry out reasoning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410275105.8A CN104064001B (en) | 2014-06-19 | 2014-06-19 | A kind of intelligent substation alarm inference method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410275105.8A CN104064001B (en) | 2014-06-19 | 2014-06-19 | A kind of intelligent substation alarm inference method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104064001A true CN104064001A (en) | 2014-09-24 |
| CN104064001B CN104064001B (en) | 2016-03-30 |
Family
ID=51551689
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410275105.8A Active CN104064001B (en) | 2014-06-19 | 2014-06-19 | A kind of intelligent substation alarm inference method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104064001B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563681A (en) * | 2017-10-23 | 2018-01-09 | 国网安徽省电力公司 | A kind of hybrid analysis of grid equipment synthesis event |
| CN108074381A (en) * | 2016-11-10 | 2018-05-25 | 杭州海康威视系统技术有限公司 | Alarm method, apparatus and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102035260A (en) * | 2010-12-17 | 2011-04-27 | 国电南瑞科技股份有限公司 | Intelligent warning and fault analysis realizing method for intelligent transformer substation monitoring system |
| CN102393922A (en) * | 2011-06-23 | 2012-03-28 | 山西省电力公司晋中供电分公司 | Fuzzy Petri inference method of intelligent alarm expert system of transformer substation |
| JP2012065466A (en) * | 2010-09-16 | 2012-03-29 | Toshiba Corp | Power monitoring device |
| CN102638100A (en) * | 2012-04-05 | 2012-08-15 | 华北电力大学 | District power network equipment abnormal alarm signal association analysis and diagnosis method |
| CN102663500A (en) * | 2012-03-27 | 2012-09-12 | 许继集团有限公司 | Fuzzy Petri net transformer station fault diagnosis method based on time membership analysis |
| CN103679354A (en) * | 2013-12-02 | 2014-03-26 | 南京磐能电力科技股份有限公司 | Intelligent warning method on basis of multilayer fault inference library and intelligent inference machine |
-
2014
- 2014-06-19 CN CN201410275105.8A patent/CN104064001B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012065466A (en) * | 2010-09-16 | 2012-03-29 | Toshiba Corp | Power monitoring device |
| CN102035260A (en) * | 2010-12-17 | 2011-04-27 | 国电南瑞科技股份有限公司 | Intelligent warning and fault analysis realizing method for intelligent transformer substation monitoring system |
| CN102393922A (en) * | 2011-06-23 | 2012-03-28 | 山西省电力公司晋中供电分公司 | Fuzzy Petri inference method of intelligent alarm expert system of transformer substation |
| CN102663500A (en) * | 2012-03-27 | 2012-09-12 | 许继集团有限公司 | Fuzzy Petri net transformer station fault diagnosis method based on time membership analysis |
| CN102638100A (en) * | 2012-04-05 | 2012-08-15 | 华北电力大学 | District power network equipment abnormal alarm signal association analysis and diagnosis method |
| CN103679354A (en) * | 2013-12-02 | 2014-03-26 | 南京磐能电力科技股份有限公司 | Intelligent warning method on basis of multilayer fault inference library and intelligent inference machine |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108074381A (en) * | 2016-11-10 | 2018-05-25 | 杭州海康威视系统技术有限公司 | Alarm method, apparatus and system |
| CN108074381B (en) * | 2016-11-10 | 2019-09-10 | 杭州海康威视系统技术有限公司 | Alarm method, apparatus and system |
| CN107563681A (en) * | 2017-10-23 | 2018-01-09 | 国网安徽省电力公司 | A kind of hybrid analysis of grid equipment synthesis event |
| CN107563681B (en) * | 2017-10-23 | 2020-07-14 | 国网安徽省电力公司 | Hybrid analysis method for comprehensive events of power grid equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104064001B (en) | 2016-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106655522A (en) | Master station system suitable for operation and maintenance management of secondary equipment of power grid | |
| CN107145959A (en) | A kind of electric power data processing method based on big data platform | |
| CN104063987B (en) | Master control room of nuclear power station back-up disk alarm method and system thereof | |
| CN105373082A (en) | Mine safety management method and mine safety management device based on geographical information system | |
| CN104753178A (en) | Power grid fault handling system | |
| CN103794257B (en) | Nuclear power station head goes out alarm processing method and system | |
| CN105160483A (en) | Secondary apparatus fault diagnosis method based on data excavation | |
| CN104460651B (en) | A kind of ZC based on autonomous learning double is delay machine fault early warning method and device | |
| CN106647695A (en) | Method and system for monitoring running state of on-orbit spacecraft | |
| CN104265616B (en) | Converter valve inner cold water main circulation pump running status on-line monitoring and assessment system | |
| CN105988456A (en) | Vehicle fault remote diagnosis method, vehicle fault remote diagnosis device and vehicle fault remote diagnosis system | |
| CN106532955B (en) | A kind of implementation method of Centralized Monitoring substation telemetering identification function | |
| CN103259686A (en) | CAN bus network fault diagnosis method based on disperse error events | |
| CN111028452A (en) | Transformer substation foreign matter intrusion monitoring system and method | |
| CN105958644A (en) | Pressing plate information management system for intelligent transformer station | |
| CN105571638A (en) | Machinery device fault combination prediction system and method | |
| CN105989427A (en) | Equipment status trend analysis and early warning method based on data mining | |
| CN103063968A (en) | Convertor station electrical equipment status integrated online monitoring system | |
| CN104064001B (en) | A kind of intelligent substation alarm inference method | |
| CN111400114A (en) | Deep recursion network-based big data computer system fault detection method and system | |
| CN107888279A (en) | The fault self-recovery method and system of optical fiber telecommunications system | |
| CN107272050B (en) | Nuclear power plant's seismic monitoring method, apparatus and system | |
| CN102855394B (en) | A kind of abnormal method of detection energy for building based on probability distribution | |
| CN104408665B (en) | Based on the event-oriented noisy data processing system of SCD models | |
| CN108512217B (en) | A kind of safe operation of electric network hidden danger intelligent identification Method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |