CN107464060B - Intelligent monitoring expert system based on active probability statistical algorithm - Google Patents
Intelligent monitoring expert system based on active probability statistical algorithm Download PDFInfo
- Publication number
- CN107464060B CN107464060B CN201710669553.XA CN201710669553A CN107464060B CN 107464060 B CN107464060 B CN 107464060B CN 201710669553 A CN201710669553 A CN 201710669553A CN 107464060 B CN107464060 B CN 107464060B
- Authority
- CN
- China
- Prior art keywords
- probability
- information
- fault
- remote signaling
- faults
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 31
- 238000012896 Statistical algorithm Methods 0.000 title claims abstract description 12
- 230000011664 signaling Effects 0.000 claims abstract description 53
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000000034 method Methods 0.000 claims description 6
- 230000001960 triggered effect Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 101100070529 Xenopus laevis hesx1-b gene Proteins 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention relates to the technical field of power grid equipment monitoring, in particular to an intelligent monitoring expert system based on an active probability statistical algorithm. The remote signaling information collection system comprises a server, an information collection module and a display module, wherein the information collection module and the display module are respectively connected with the server, remote signaling sent by power grid equipment is summarized into the server through the information collection module, and a remote signaling fault corresponding probability table, other information and a fault corresponding probability table are prestored in the server; the remote signaling fault corresponding probability table is used for storing and reflecting the corresponding probability between each remote signaling and each possible fault, and the other information and fault corresponding probability table is used for storing and reflecting the corresponding probability between other information and faults collected by each trigger.
Description
Technical Field
The invention relates to the technical field of power grid equipment monitoring, in particular to an intelligent monitoring expert system based on an active probability statistical algorithm.
Background
With the continuous development of the power grid scale and the continuous improvement of the complexity of the power grid, the power grid equipment monitoring technology also meets more challenges. At present, most substations are unattended substations, the power grid equipment monitoring mainly depends on an SCADA system to transmit alarm information from a plant station end to a master station end, and monitoring personnel at the master station end comprehensively analyze the alarm information so as to judge the fault condition of the equipment. However, due to the problems of discrete alarm information, complex types, multiple signals and the like of the SCADA system, certain trouble is caused to the equipment monitoring and fault analysis of monitoring personnel at the master station end. Therefore, the intelligent monitoring expert system capable of integrating various alarm information and automatically performing intelligent research and judgment on equipment conditions can effectively improve the working efficiency of monitoring personnel.
For the intelligent monitoring expert system of the power grid aiming at realizing intelligent analysis of the power grid equipment faults, a plurality of patents at present propose corresponding solutions, all the solutions are realized by searching a pre-established alarm combination rule base, namely, a corresponding relation rule base of various alarm signal combinations and field actual equipment faults in the transformer substation is pre-established, and when in alarm, the nearest alarm combination in the rule base is automatically matched according to the alarm signals, so that the fault condition is judged.
Under this scheme, if an unmatched alarm condition is encountered in the actual alarm, the decision cannot be made. In addition, if the decision is wrong, no alternative other options can be provided. In addition, the judging method of the alarm combination rule base cannot fully utilize other types of criteria such as telemetry, channel state and the like, so that the accuracy of system judgment is affected. Therefore, in order to improve the reliability and accuracy of equipment monitoring, there is a need for an intelligent monitoring expert system that is adaptable to any combination of alarms, that can fully utilize the useful information provided by the SCADA system, and that can provide several alternatives.
Disclosure of Invention
Aiming at the problem that the alarm combination rule base mode can not be matched, the invention provides an intelligent monitoring expert system based on an active probability statistical algorithm, which can conduct intelligent research and judgment in any event and any alarm combination, actively collect all information provided by the system, calculate the probability of various faults possibly existing, give out corresponding research and judgment results and corresponding alternative schemes according to the probability, and improve the reliability and accuracy of the intelligent monitoring expert system.
The invention is realized by adopting the following technical scheme:
the intelligent monitoring expert system based on the active probability statistical algorithm comprises a server, an information collection module and a display module, wherein the information collection module and the display module are respectively connected with the server, remote signaling sent by power grid equipment is summarized into the server through the information collection module, and a remote signaling fault corresponding probability table, other information and a fault corresponding probability table are prestored in the server; the remote signaling fault corresponding probability table is used for storing and reflecting the corresponding probability between each remote signaling and each possible fault, and the other information and fault corresponding probability table is used for storing and reflecting the corresponding probability between other information and faults collected by each trigger.
The monitoring method of the intelligent monitoring expert system based on the active probability statistical algorithm comprises the following steps:
1) When an event occurs to the power grid equipment, the information collection module collects remote signaling alarm information sent by the power grid equipment to a server;
2) The server searches other pre-stored information and fault corresponding probability tables based on the pre-stored remote signaling fault corresponding probability tables in the server according to the remote signaling alarm information obtained in the step 1), and actively triggers and collects other information with the corresponding probability not equal to 0, and actively performs active statistical calculation on the occurrence probability of various faults under the alarm signal combination, so that probability ordering of various faults is obtained and is used as an intelligent analysis result of the intelligent monitoring expert system.
The remote signaling fault corresponding probability table records all faults possibly occurring corresponding to each remote signaling of the power grid equipment and the probabilities corresponding to the faults; the probability is calculated through statistics of the historical signaling conditions of the remote signaling, and dynamic change is carried out along with the increase of the signaling times, so that the accuracy of the probability is maintained.
The server triggers the collection of other related category information according to other information and the fault corresponding probability table in the step 2), so that the fault criterion is extended from the only remote signaling information to the multi-category comprehensive information; if some faults need to trigger various types of information collection, once other types of information collection are triggered, final probability calculation is carried out according to the remote signaling fault corresponding probability table and other information and the corresponding probability in the fault corresponding probability table; and the other types of information collection is not required to be triggered by some faults, and the final probability calculation can be completed only through a probability table corresponding to the remote signaling faults.
The active probability statistical calculation refers to that after triggering and collecting all information, the system calculates the occurrence probability of all faults corresponding to remote signaling according to the collected information; the calculation result of each fault probability contains the inferred contribution of all remote signaling and other types of information to the fault; finally, the system obtains probability calculation results of all faults corresponding to remote signaling, and sorts the probability calculation results according to the probability.
The intelligent monitoring expert system based on the active probability statistical algorithm can calculate the probability of each possible fault from the probability statistical angle, so that a fault judgment list ordered according to the probability is obtained, and the problem of unmatched faults is solved. And the information trigger collection mechanism is used for carrying out active probability statistics, so that the accuracy of research and judgment is improved through more comprehensive information. Meanwhile, as the studying and judging are carried out through probability calculation, the system can give out a plurality of alternative other studying and judging results at the same time, and the system has wider adaptability to fault judgment.
Drawings
The invention will be further described with reference to the accompanying drawings in which:
FIG. 1 is a schematic diagram of an active probability statistical algorithm used in the present invention;
in fig. 1: a1 and A2 … An are n alarming remote signaling sent when equipment fails, and F1 and F2 … Fm are m possible failures corresponding to the n alarming remote signaling; b1, B2 … Bi represent i class B information which may be collected by m kinds of fault triggers, C1, C2 … Cj represent j class C information which may be collected by m kinds of fault triggers; the possible faults corresponding to the remote signaling A1 are F1 and Fm, the possible faults corresponding to the A2 are F2 and Fm, and the possible faults corresponding to the An are F1 and F2 … Fm; meanwhile, B-type information triggered and collected by F1 is B1 and B2, and C-type information triggered and collected is C1; f2 triggers the B type information collected to be B2, and triggers the C type information collected to be C2; fm triggers B1 and B2 … Bi and C1 and C2 … Cj.
Detailed Description
The monitoring method of the intelligent monitoring expert system based on the active probability statistical algorithm comprises the following steps:
1) When an event occurs to the power grid equipment, the information collection module collects remote signaling alarm information sent by the power grid equipment to a server;
2) The server searches other pre-stored information and fault corresponding probability tables based on the pre-stored remote signaling fault corresponding probability tables in the server according to the remote signaling alarm information obtained in the step 1), and actively triggers and collects other information with the corresponding probability not equal to 0, and actively performs active statistical calculation on the occurrence probability of various faults under the alarm signal combination, so that probability ordering of various faults is obtained and is used as an intelligent analysis result of the intelligent monitoring expert system.
In order to facilitate calculation, the system reflects whether other information is required to assist calculation or not through other information and a fault corresponding probability table; if the probability of the fault in the fault corresponding probability table is 0, indicating that the fault does not need to collect other information; if the probability of correspondence between the fault and some other information is not 0, the system needs to actively collect the other information to assist calculation; this determination is the trigger. Triggering is realized by inquiring other information and fault corresponding probability tables, and collecting is realized by inquiring other information of needed power grid equipment through an information collecting module and then collecting the information into a server.
Referring to the correspondence in fig. 1, the probability of the remote signaling An corresponding to the fault Fm is represented by PAnFm, the probability of the B-class information Bi collected by the fault Fm triggering corresponding to the fault is represented by PFmBi, and the probability of the C-class information Cj collected by the fault Fm triggering corresponding to the fault is represented by PFmCj. According to the above description, all the corresponding relations and the related probability values should be established and maintained in the system in advance.
When a fault occurs, m possible faults can be calculated according to the relevant n remote signals. For the fault F1, corresponding to the remote signaling A1 and An, triggering and collecting B-type information as B1 and B2, and triggering and collecting C-type information as C2, the probability of occurrence of the fault F1 can be calculated as follows:
P F1 =1-（1-P A1F1 ）（1-P AnF1 ）（1-P F1B1 ）（1-P F1B2 ）（1-P F1C1 ）
for the fault F2, corresponding to the remote signaling A2 and An, triggering and collecting B-type information as B2 and C-type information as C2, the probability of occurrence of the fault F2 can be calculated as follows:
P F2 =1-（1-P A2F2 ）（1-P AnF2 ）（1-P F2B2 ）（1-P F2C2 ）
thus, the calculation formula for the fault Fm for A1, A2 … An, B1, B2 … Bi, C1, C2 … Cj can be given here:
P Fm =1-∑（1-P AnFm ）（1-P FmBi ）（1-P FmCj ）
wherein n, i, j are natural numbers other than 0,
n=1,2,3……
i=1,2,3……
j=1,2,3……。
through the series of algorithms, the occurrence probability of each fault can be calculated. And finally, the system orders the probability so as to obtain a series of studying and judging results, and takes the fault with the highest probability as the studying and judging conclusion of the intelligent expert system, and the two faults arranged in the second and third positions are taken as the standby studying and judging conclusion.
Claims (2)
1. The intelligent monitoring expert system based on the active probability statistical algorithm comprises a server, an information collection module and a display module, wherein the information collection module and the display module are respectively connected with the server, remote signaling sent by power grid equipment is summarized into the server through the information collection module, and a remote signaling fault corresponding probability table, other information and a fault corresponding probability table are prestored in the server; the remote signaling fault corresponding probability table is used for storing and reflecting the corresponding probability between each remote signaling and each possible fault, and the other information and fault corresponding probability table is used for storing and reflecting the corresponding probability between other information and faults collected by each trigger, wherein the corresponding probability between other information and faults is 0 or not 0; the method is characterized by comprising the following steps:
1) When an event occurs to the power grid equipment, the information collection module collects remote signaling alarm information sent by the power grid equipment to a server;
2) The server searches other pre-stored information and fault corresponding probability tables based on the pre-stored remote signaling fault corresponding probability tables in the server according to the remote signaling alarm information obtained in the step 1), and actively triggers and collects other information with the corresponding probability not equal to 0, and actively performs active statistical calculation on the occurrence probability of various faults under the alarm signal combination, so that probability ordering of various faults is obtained and is used as an intelligent analysis result of an intelligent monitoring expert system;
the remote signaling fault corresponding probability table records all faults possibly occurring corresponding to each remote signaling of the power grid equipment and the probabilities corresponding to the faults; the probability is calculated through statistics of the historical signaling conditions of the remote signaling and dynamically changes along with the increase of the signaling times, so that the accuracy of the probability is maintained;
the statistical calculation refers to that after the system triggers and collects all information, the occurrence probability of all faults corresponding to remote signaling is calculated according to the collected information; the calculation result of each fault probability contains the inferred contribution of all remote signaling and other types of information to the fault; finally, the system obtains probability calculation results of all faults corresponding to remote signaling, and sorts the probability calculation results according to the probability;
probability P for fault Fm corresponding to remote signaling An AnFm Representing the probability P for the failure Fm triggering the collected B-type information Bi to correspond to the failure FmBi Representing the probability P for the failure Fm triggering the collected C-type information Cj to correspond to the failure FmCj A representation;
for the fault F1, corresponding to the remote signaling A1 and An, triggering and collecting B-type information as B1 and B2, and triggering and collecting C-type information as C1 and C2, the probability of the fault F1 can be calculated as follows:
P F1 =1-（1-P A1F1 ）（1-P AnF1 ）（1-P F1B1 ）（1-P F1B2 ）（1-P F1C1 ）
for the fault F2, corresponding to the remote signaling A2 and An, triggering and collecting B-type information as B2 and C-type information as C2, and calculating the occurrence probability of the fault F2 as follows:
P F2 =1-（1-P A2F2 ）（1-P AnF2 ）（1-P F2B2 ）（1-P F2C2 ）
the calculation formula of the fault Fm corresponding to A1, A2 … An, B1, B2 … Bi, C1, C2 … Cj is given:
P Fm =1-∑（1-P AnFm ）（1-P FmBi ）（1-P FmCj ）
wherein n, i, j are natural numbers other than 0,
n=1,2,3……
i=1,2,3……
j=1,2,3……。
2. the monitoring method of the intelligent monitoring expert system based on the active probability statistical algorithm as claimed in claim 1, wherein the monitoring method is characterized by comprising the following steps: the server triggers the collection of other related category information according to other information and the fault corresponding probability table in the step 2), so that the fault criterion is extended from the only remote signaling information to the multi-category comprehensive information; if some faults need to trigger various types of information collection, once other types of information collection are triggered, final probability calculation is carried out according to the remote signaling fault corresponding probability table and other information and the corresponding probability in the fault corresponding probability table; and the other types of information collection is not required to be triggered by some faults, and the final probability calculation can be completed only through a probability table corresponding to the remote signaling faults.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710669553.XA CN107464060B (en) | 2017-08-08 | 2017-08-08 | Intelligent monitoring expert system based on active probability statistical algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710669553.XA CN107464060B (en) | 2017-08-08 | 2017-08-08 | Intelligent monitoring expert system based on active probability statistical algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107464060A CN107464060A (en) | 2017-12-12 |
| CN107464060B true CN107464060B (en) | 2024-03-22 |
Family
ID=60548521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710669553.XA Active CN107464060B (en) | 2017-08-08 | 2017-08-08 | Intelligent monitoring expert system based on active probability statistical algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107464060B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104348667A (en) * | 2014-11-11 | 2015-02-11 | 上海新炬网络技术有限公司 | Fault positioning method based on warning information |
| CN105528679A (en) * | 2015-12-11 | 2016-04-27 | 谭焕玲 | Power system fault diagnosis method |
| CN106096732A (en) * | 2016-06-20 | 2016-11-09 | 广东电网有限责任公司肇庆供电局 | A kind of SCADA, intelligent warning system based on SCADA and method |
| CN106941423A (en) * | 2017-04-13 | 2017-07-11 | 腾讯科技（深圳）有限公司 | Failure cause localization method and device |
-
2017
- 2017-08-08 CN CN201710669553.XA patent/CN107464060B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104348667A (en) * | 2014-11-11 | 2015-02-11 | 上海新炬网络技术有限公司 | Fault positioning method based on warning information |
| CN105528679A (en) * | 2015-12-11 | 2016-04-27 | 谭焕玲 | Power system fault diagnosis method |
| CN106096732A (en) * | 2016-06-20 | 2016-11-09 | 广东电网有限责任公司肇庆供电局 | A kind of SCADA, intelligent warning system based on SCADA and method |
| CN106941423A (en) * | 2017-04-13 | 2017-07-11 | 腾讯科技（深圳）有限公司 | Failure cause localization method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107464060A (en) | 2017-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609569B (en) | Power distribution network ground fault positioning method based on multi-dimensional feature vectors | |
| CN105305444B (en) | The alarm of distribution comprehensive intelligent and processing method based on allotment integration | |
| CN109828182B (en) | Power grid system fault analysis and early warning method based on fault classification processing | |
| CN102819239B (en) | Intelligent fault diagnosis method of numerical control machine tool | |
| CN106199276A (en) | The intelligent diagnosis system of abnormal information and method in a kind of power information acquisition system | |
| CN110941918B (en) | Intelligent substation fault analysis system | |
| CN104483601A (en) | Power distribution network fault location method based on fault indicators | |
| CN106787169A (en) | A kind of method of multi-data source comparison techniques diagnosis transformer station remote measurement failure | |
| CN114280414A (en) | Low-voltage distribution network fault positioning system and method based on topology dynamic identification | |
| CN103376348A (en) | Method of controlling fault current in system for monitoring and controlling power system | |
| CN110838821B (en) | Photovoltaic power station fault control method and system | |
| CN109245305A (en) | A kind of photovoltaic plant automatic early-warning cloud platform and system | |
| CN110723166A (en) | Turnout monitoring method and system | |
| CN108732444A (en) | Intelligent substation protects equipment running status apparatus for evaluating and maintenance decision method | |
| CN107294205B (en) | Substation state monitoring method based on information protection master station data | |
| CN110164102A (en) | A kind of photovoltaic plant group string abnormal alarm method and warning device | |
| CN107464060B (en) | Intelligent monitoring expert system based on active probability statistical algorithm | |
| CN109778195A (en) | Pipeline transportation cathodic protection and anti-corrosion intelligent management system | |
| CN112600309B (en) | Low-voltage power distribution intelligent diagnosis system with wave recording function | |
| CN105184657A (en) | Power supply risk assessment method and system for power system | |
| CN112101422B (en) | Typical case self-learning method for power system fault case | |
| CN109507468B (en) | Header box branch current detection method and system based on correlation characteristics | |
| CN113590368A (en) | Abnormal equipment diagnosis method and system based on edge-edge coordination | |
| CN114997561A (en) | Ground wire geographical position positioning system and method adopting artificial intelligence | |
| KR20210033625A (en) | Apparatus and method for collecting history data of solar power system |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wang Lin Inventor after: Han Shaohua Inventor before: Wang Lin Inventor before: Han Shaohua Inventor before: Xu Jing Inventor before: Zhang Yida Inventor before: Hu Danlin |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |