CN110932881A - Equipment portrait method based on monitoring alarm signal - Google Patents
Equipment portrait method based on monitoring alarm signal Download PDFInfo
- Publication number
- CN110932881A CN110932881A CN201910981737.9A CN201910981737A CN110932881A CN 110932881 A CN110932881 A CN 110932881A CN 201910981737 A CN201910981737 A CN 201910981737A CN 110932881 A CN110932881 A CN 110932881A
- Authority
- CN
- China
- Prior art keywords
- equipment
- monitoring
- signals
- power grid
- alarm
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0604—Management of faults, events, alarms or notifications using filtering, e.g. reduction of information by using priority, element types, position or time
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention provides a method for accurately and dynamically portraying power grid equipment from the perspective of monitoring alarm signals and further knowing the operation condition and the health degree of the equipment. The invention cleans and filters public equipment signals and power grid event signals based on monitoring alarm information. Through the deep research and analysis of the first and second devices, a device feature point knowledge base is established according to different device principles. By utilizing natural language analysis and deep learning technology, the remote signaling alarm signal is standardized, so that a computer can prepare and effectively understand the meaning of the alarm signal, the dynamic portrait of equipment is realized, and the operation evaluation of a transformer substation is fully covered. The method has the advantages that the utilization rate of the existing information resources is improved, meanwhile, the manual productivity is liberated, the control capacity of the substation equipment is enhanced, and effective data support is provided for discovering weak links of the power grid.
Description
Technical Field
The method belongs to the technical field of electric power, and particularly relates to a method for realizing dynamic portrayal of power grid equipment based on monitoring alarm signals.
Background
The power grid monitoring is an important measure for guaranteeing the safe and stable operation of the power grid. With the continuous promotion and deepening of a large operation mode, a centralized monitoring mode is generally adopted by a transformer substation, the monitoring task of a power grid is heavier and heavier, primary equipment monitoring signals and secondary equipment monitoring signals are monitored in a centralized mode in a main station, the magnitude of single-day monitoring alarm signals is huge, and the description is not standard. The monitoring signals in the current system are only listed in a time sequence, and the logic relation between the signals cannot be reflected, so that the monitoring and analyzing work task is heavy. In the face of massive alarm signals, the judgment is completely carried out by means of manual experience, corresponding technical means are lacked, the problem that effective monitoring and management cannot be carried out exists, and hidden dangers and risks are brought to power grid monitoring operation.
The alarm signal has the characteristics of real-time, objective and no human intervention, and the like, and the mining and analysis of massive alarm information are realized by adopting an effective monitoring data mining and analyzing means, so that useful information and knowledge are converted. After the alarm signals generated by the power grid events are filtered, the remaining alarm signals can objectively reflect the health condition of the power grid operation equipment.
In conclusion, through the deep research on the alarm signal, the method has great significance on the safe and stable operation of the power grid. The invention realizes accurate dynamic portrait of the power grid equipment from the angle of the alarm signal and further knows the operation condition and the health degree of the equipment.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a method for realizing dynamic portrayal of power grid equipment based on an alarm signal, and promotes effective evaluation of the operation condition and the health degree of the operation equipment.
In order to solve the technical problems, the invention is realized by the following technical scheme: a method of device portrayal based on monitoring alert signals, comprising the steps of:
step 1, filtering and cleaning alarm signals sent by a power grid event;
step 2, associating the monitoring information table with the standard signals one by one;
step 3, establishing a primary equipment feature point knowledge base and a secondary equipment feature point knowledge base;
and 4, classifying the alarm signals according to the fault or alarm characteristics.
Preferably, in the step 1, the EMS system is used to interface the monitoring alarm signal, and the image of the device is displayed only after the EMS system is cleaned by the computer.
Preferably, in step 1, the content of the washing and filtering is as follows: firstly, classifying signals into tripping, equipment abnormity, maintenance and debugging, equipment operation and other events based on a primary and secondary wiring mode, a protection configuration and action principle of a power grid and signals sent by equipment, and labeling the signals; secondly, public equipment and public signals of the existing transformer substation are relatively different and do not have analysis conditions, so that public information is synchronously filtered; after the monitoring alarm signals are cleaned and filtered, the rest alarm signals are used as basic data support of the dynamic portrait of the equipment.
Preferably, in the step 2, a natural language parsing technology is adopted, and according to the language specification and the regulation and control working habit of the power system, basic constituent elements and structural relationships among the elements are extracted and identified, each monitoring signal is segmented and reconstructed, invalid information is screened and filtered, grammatical inference and syntactic analysis are performed, and accurate monitoring signal meanings and equipment to which the monitoring signal belongs are obtained.
Preferably, in the step 2, in order to adapt to the conditions of change of the monitoring information table, modification perfection of power grid regulations and the like, a machine self-learning concept is added, the new regulations of the power grid are adapted, and meanwhile, the monitoring information is learned and trained, an optimal model is established, and signal meanings are automatically identified.
Preferably, in the step 3, through deep analysis of the monitoring information table, the equipment such as the circuit breaker, the main transformer and the line protection is analyzed one by one, and an equipment characteristic point knowledge base is established to cover all the primary and secondary equipment of the power grid except the public equipment.
Preferably, in the step 4, after the cleaning, filtering and analyzing based on the quasi-real-time monitoring alarm signal, the characteristic points in the step 3 are associated one by one to realize dynamic updating of the equipment portrait data, and through state evaluation of the whole network equipment, alarm conditions of various kinds of equipment within a period of time and conditions of key attention signals are automatically summarized and summarized, so that dynamic portrait of the equipment and full coverage of operation evaluation of the transformer substation are realized.
The invention has the advantages and positive effects that:
the invention has reasonable design, correlates the collected remote signaling alarm signals to the corresponding equipment interval units, analyzes and judges the correctness and the effectiveness of the information by utilizing the correlation between the signals and the events, realizes the evaluation of the power grid equipment, dynamically summarizes and summarizes the alarm conditions of various equipment and the conditions of key attention signals, realizes the integrated analysis of the existing information resources, improves the utilization rate of the existing information, realizes the dynamic portrait of the equipment and fully covers the operation evaluation of the transformer substation.
Drawings
FIG. 1 is a process flow diagram of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
FIG. 1 shows an embodiment of a method for monitoring a device representation based on an alarm signal, comprising the following steps:
step 1, filtering and cleaning alarm signals sent by the power grid event.
In this step, the EMS system is used to interface the monitoring alarm signal, and the equipment portrait work can be performed only after the computer cleaning process is performed. The contents of the main cleaning filters are as follows: firstly, based on a primary and secondary wiring mode, a protection configuration and action principle of a power grid and a signal sent by equipment, the signal is classified into tripping, equipment abnormity, maintenance and debugging, equipment operation and other events, and labeling processing is carried out on the signals. Secondly, public equipment and public signals of the conventional transformer substation have large relative difference and do not have analysis conditions, so that public information is synchronously filtered.
By the method, after the monitoring alarm signals are cleaned and filtered, the rest alarm signals are used as basic data support of the dynamic portrait of the equipment.
And 2, associating the monitoring information table with the standard signals one by one.
In the step, firstly, a natural language analysis technology is adopted, and according to the language specification and the regulation and control working habit of the power system, basic constituent elements and the structural relationship among the elements are extracted and identified, each monitoring signal is segmented and reconstructed, invalid information is screened and filtered, grammar inference and syntactic analysis are carried out, and the accurate meaning of the monitoring signal and the equipment to which the monitoring signal belongs are obtained. For example, "the switch energy storage motor runs overtime", "the energy storage motor power supply is disconnected during idle running", "the energy storage power supply disappears", and the like, the monitoring signals are uniformly identified, and the standardized management of the monitoring information is facilitated.
Meanwhile, a machine self-learning concept is added. Because the monitoring information changes along with the transformation or production of the transformer substation, the current monitoring information management cannot ensure 100% standardization due to the influence of the professional degree of the compiling personnel and the special conditions of the site. In addition, with the continuous improvement and development of the power grid, the related management regulations and regulations of the power are also continuously changed. In order to adapt to the situation, a machine self-learning concept is added, the monitoring information is learned and trained while the new regulation of the power grid is adapted, an optimal model is established, and the meaning of signals, the generation reason and the like are automatically identified.
And 3, establishing a primary equipment feature point knowledge base and a secondary equipment feature point knowledge base.
In the step, the equipment alarm information is classified according to the fault or alarm characteristics, and the characteristic rule of the alarm of each equipment in the interval is analyzed and summarized by combining with the historical alarm information.
Through the deep analysis to the monitoring information table, carry out analysis one by one to circuit breaker, main transformer, line protection etc. primary, secondary equipment, establish equipment characteristic point knowledge base (except public equipment), for example according to different principles such as the spring of circuit breaker, pneumatics, surge, establish the characteristic point of circuit breaker: SF6 air pressure abnormity, mechanism pressing overtime, energy storage motor abnormity, air pressure abnormity, oil pressure abnormity, three-phase inconsistency, N2 leakage, heater fault and the like. In total, 300-dimensional accurate images are performed, and all primary and secondary equipment except public equipment of a power grid are covered.
And 4, classifying the alarm signals according to the fault or alarm characteristics.
In the step, after the cleaning, filtering and analyzing based on the quasi-real-time monitoring alarm signal, the characteristic points in the step 3 are associated one by one, so that the dynamic updating of the equipment portrait data is realized. Through the state evaluation of the equipment in the whole network, the alarm conditions of various equipment in a period of time and the conditions of key attention signals are automatically summarized and summarized, so that the dynamic portrait of the equipment is realized, and the operation evaluation of the transformer substation is fully covered.
It should be emphasized that the embodiments described herein are illustrative rather than restrictive, and thus the present invention is not limited to the embodiments described in the detailed description, but also includes other embodiments that can be derived from the technical solutions of the present invention by those skilled in the art.
The above description is only an embodiment of the present invention, but the technical features of the present invention are not limited thereto, and any changes or modifications within the technical field of the present invention by those skilled in the art are covered by the claims of the present invention.
Claims (7)
1. A method for device portrayal based monitoring of alert signals comprising the steps of:
step 1, filtering and cleaning alarm signals sent by a power grid event;
step 2, associating the monitoring information table with the standard signals one by one;
step 3, establishing a primary equipment feature point knowledge base and a secondary equipment feature point knowledge base;
and 4, classifying the alarm signals according to the fault or alarm characteristics.
2. A method for monitoring a representation of an apparatus as claimed in claim 1, wherein: in the step 1, the monitoring alarm signal is connected with the EMS system, and the equipment portrait work can be performed only after the computer cleaning treatment is performed.
3. A method for monitoring a representation of an apparatus as claimed in claim 2, wherein: in the step 1, the content of the cleaning and filtering is as follows: firstly, classifying signals into tripping, equipment abnormity, maintenance and debugging, equipment operation and other events based on a primary and secondary wiring mode, a protection configuration and action principle of a power grid and signals sent by equipment, and labeling the signals; secondly, public equipment and public signals of the existing transformer substation are relatively different and do not have analysis conditions, so that public information is synchronously filtered; after the monitoring alarm signals are cleaned and filtered, the rest alarm signals are used as basic data support of the dynamic portrait of the equipment.
4. A method for monitoring a representation of an apparatus as claimed in claim 1, wherein: in the step 2, a natural language analysis technology is adopted, and according to the language specification and the regulation and control working habit of the power system, basic constituent elements and the structural relationship among the elements are extracted and identified, each monitoring signal is segmented and reconstructed, invalid information is screened and filtered, grammar inference and syntactic analysis are carried out, and accurate monitoring signal meanings and equipment to which the monitoring signal belongs are obtained.
5. A method for monitoring a representation of an apparatus as claimed in claim 1, wherein: in the step 2, in order to adapt to the conditions of the change of the monitoring information table, the modification and perfection of the power grid regulation and the like, a machine self-learning concept is added, the new regulation of the power grid is adapted, meanwhile, the monitoring information is learned and trained, an optimal model is established, and the signal meaning is automatically identified.
6. A method for monitoring a representation of an apparatus as claimed in claim 1, wherein: in the step 3, through deep analysis of the monitoring information table, equipment such as a circuit breaker, a main transformer and line protection is analyzed one by one, and an equipment characteristic point knowledge base is established to cover all primary and secondary equipment of the power grid except public equipment.
7. A method of monitoring a representation of an apparatus as claimed in claim 1 or 4, wherein: in the step 4, after cleaning, filtering and analyzing based on the quasi-real-time monitoring alarm signals, the characteristic points in the step 3 are associated one by one to realize dynamic updating of the equipment portrait data, and alarm conditions and key attention signal conditions of various equipment within a period of time are automatically summarized and summarized through state evaluation of the whole network equipment, so that dynamic portrait of the equipment and full coverage of operation evaluation of the transformer substation are realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910981737.9A CN110932881B (en) | 2019-10-16 | 2019-10-16 | Equipment portrait method based on monitoring alarm signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910981737.9A CN110932881B (en) | 2019-10-16 | 2019-10-16 | Equipment portrait method based on monitoring alarm signal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110932881A true CN110932881A (en) | 2020-03-27 |
| CN110932881B CN110932881B (en) | 2022-07-26 |
Family
ID=69848953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910981737.9A Active CN110932881B (en) | 2019-10-16 | 2019-10-16 | Equipment portrait method based on monitoring alarm signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110932881B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598023A (en) * | 2020-12-02 | 2021-04-02 | 国网青海省电力公司海东供电公司 | Intelligent identification and automatic mapping method and device for power grid monitoring alarm information |
| CN113268590A (en) * | 2021-04-06 | 2021-08-17 | 云南电网有限责任公司昆明供电局 | Power grid equipment running state evaluation method based on equipment portrait and integrated learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160483A (en) * | 2015-09-10 | 2015-12-16 | 国家电网公司 | Secondary apparatus fault diagnosis method based on data excavation |
| WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
| CN109886487A (en) * | 2019-02-20 | 2019-06-14 | 云南电网有限责任公司信息中心 | A method of based on power equipment portrait power network monitoring early warning |
| CN110321411A (en) * | 2019-06-26 | 2019-10-11 | 国网江苏省电力有限公司 | A kind of power system monitor warning information classification method, system and readable storage medium storing program for executing |
-
2019
- 2019-10-16 CN CN201910981737.9A patent/CN110932881B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
| CN105160483A (en) * | 2015-09-10 | 2015-12-16 | 国家电网公司 | Secondary apparatus fault diagnosis method based on data excavation |
| CN109886487A (en) * | 2019-02-20 | 2019-06-14 | 云南电网有限责任公司信息中心 | A method of based on power equipment portrait power network monitoring early warning |
| CN110321411A (en) * | 2019-06-26 | 2019-10-11 | 国网江苏省电力有限公司 | A kind of power system monitor warning information classification method, system and readable storage medium storing program for executing |
Non-Patent Citations (2)
| Title |
|---|
| 汪崔洋 等: "基于告警信号文本挖掘的电力调度故障诊断", 《电力自动化设备》 * |
| 王烨 等: "基于大数据技术的专家知识库设备画像推荐算法研究", 《计算机测量与控制》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598023A (en) * | 2020-12-02 | 2021-04-02 | 国网青海省电力公司海东供电公司 | Intelligent identification and automatic mapping method and device for power grid monitoring alarm information |
| CN112598023B (en) * | 2020-12-02 | 2024-01-26 | 国网青海省电力公司海东供电公司 | Intelligent identification and automatic mapping method and device for power grid monitoring alarm information |
| CN113268590A (en) * | 2021-04-06 | 2021-08-17 | 云南电网有限责任公司昆明供电局 | Power grid equipment running state evaluation method based on equipment portrait and integrated learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110932881B (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110401262B (en) | GIS equipment state intelligent monitoring system and method based on edge computing technology | |
| CN112788142B (en) | Intelligent edge Internet of things gateway supporting multi-sensor access | |
| CN101551440B (en) | Generator transformer unit faults recorder analysis device | |
| CN103823433B (en) | Method for realizing relay protection equipment on-line monitoring by use of communication process analysis | |
| CN104753178A (en) | Power grid fault handling system | |
| CN110336379B (en) | Transformer substation online monitoring system based on Internet of things and terminal equipment | |
| CN107834523B (en) | Extra-high voltage direct-current fault diagnosis system and working method based on model and rule base | |
| CN111591778A (en) | Remote monitoring management system and method for stacker-reclaimer based on Internet technology | |
| CN110932881B (en) | Equipment portrait method based on monitoring alarm signal | |
| CN111581196A (en) | Supply and distribution power grid intelligent data acquisition and arrangement system based on intelligent factory framework | |
| CN110739770B (en) | Relay protection tube control system based on information fusion | |
| CN105978140A (en) | Information integrating method of power device | |
| CN111864902A (en) | Intelligent substation secondary equipment fault comprehensive analysis system based on big data | |
| CN109633345B (en) | Secondary equipment on-line monitoring and analyzing device | |
| CN109581115B (en) | Power distribution network low-voltage diagnosis system and diagnosis method | |
| CN110837027A (en) | Auxiliary decision method and system based on scheduling end key information extraction under power grid fault condition | |
| CN113471864A (en) | Transformer substation secondary equipment field maintenance device and method | |
| CN206470391U (en) | Electrical energy meter fault diagnostic system structure | |
| CN101847865A (en) | Electric network relay protection and fault analysis system | |
| CN109217311B (en) | Power distribution network operation state control and evaluation method | |
| CN111652500A (en) | Automatic duty-on auxiliary system and equipment based on scheduling and report generation method thereof | |
| CN207149078U (en) | A kind of low-voltage collecting meter reading system fault locator | |
| CN115267616A (en) | Transformer running state monitoring system and method based on enterprise data middling station | |
| CN116169778A (en) | Processing method and system based on power distribution network anomaly analysis | |
| CN201682276U (en) | Relay protection and fault analysis system for power grid |
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 |