CN113884803A - Distribution network fault studying and judging method - Google Patents
Distribution network fault studying and judging method Download PDFInfo
- Publication number
- CN113884803A CN113884803A CN202110994163.6A CN202110994163A CN113884803A CN 113884803 A CN113884803 A CN 113884803A CN 202110994163 A CN202110994163 A CN 202110994163A CN 113884803 A CN113884803 A CN 113884803A
- Authority
- CN
- China
- Prior art keywords
- fault
- accident
- distribution network
- analysis
- equipment
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000004458 analytical method Methods 0.000 claims abstract description 73
- 238000010276 construction Methods 0.000 claims abstract description 22
- 238000003745 diagnosis Methods 0.000 claims abstract description 18
- 238000010801 machine learning Methods 0.000 claims abstract description 12
- 238000009411 base construction Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 24
- 238000010586 diagram Methods 0.000 claims description 14
- 238000012423 maintenance Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000011161 development Methods 0.000 claims description 9
- 230000018109 developmental process Effects 0.000 claims description 9
- 238000011835 investigation Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 4
- 230000003111 delayed effect Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000010365 information processing Effects 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000001052 transient effect Effects 0.000 claims description 3
- 238000009472 formulation Methods 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims description 2
- 238000009960 carding Methods 0.000 claims 1
- 206010063385 Intellectualisation Diseases 0.000 abstract 1
- 230000033228 biological regulation Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000012098 association analyses Methods 0.000 description 3
- 230000006698 induction Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to a distribution network fault studying and judging method which comprises the steps of difference analysis and scheme making, distribution network alarm information machine learning sample customization, fault analysis unit deduction model graph construction, fault diagnosis knowledge base construction and a networked fault information closed-loop management module, wherein the fault analysis unit deduction model graph construction comprises physical unit construction, combined physical unit construction and analysis unit construction. The invention greatly improves the intellectualization level of accident analysis.
Description
Technical Field
The invention belongs to the technical field of power grid systems, and particularly relates to a distribution network fault studying and judging method.
Background
With the development of distribution networks, the pressure of regulators for carrying out regulation and control operation of the distribution networks is higher and higher, the operation of the distribution networks and the fault and exception handling of the distribution networks mainly depend on manual experience, and the traditional empirical dispatching control process is difficult to meet the requirement of complex distribution networks on the regulation and control operation.
When a fault occurs, a regulation and control person mainly finds out the fault type, fault equipment, fault phase, protection action condition and coincidence condition through manual one-by-one analysis of DMS alarm information. The fault handling process mainly depends on the experience of a regulating and controlling person, an accumulative knowledge base cannot be formed at present, a fault assistant decision cannot be effectively pushed intelligently, the regulating and controlling person needs to master various safety operation rules and specifications to accurately deal with the fault and abnormal handling, and a specification file cannot be intelligently applied to a business process.
With the improvement of the operation complexity of the distribution network and the rapid development of the dispatching automation technology and the artificial intelligence technology, the current fault analysis and judgment in a manual mode and the fault handling decision are difficult to adapt to the daily work of dispatching personnel, and the current automation technology needs to be fully excavated and utilized to carry out rapid fault diagnosis and decision assistance.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a distribution network fault studying and judging method, which has the following specific technical scheme:
the distribution network fault studying and judging method comprises the steps of difference analysis and scheme making, distribution network alarm information machine learning sample customization, fault analysis unit deduction model diagram construction, fault diagnosis knowledge base construction and networked fault information closed-loop management module construction.
The specific method for the difference analysis and the scheme formulation is as follows:
respectively carrying out investigation and investigation on the distribution network fault occurrence and fault disposal conditions, collecting user data and main application scene collection, combing the line fault event, main transformer fault, bus fault event, capacitive reactance device fault, grounding transformer/station transformer fault and switch body fault which occur in the distribution network, forming a fault condition layout report, and formulating an integral implementation scheme of a dispatching safety command and fault disposal system.
The specific method for customizing the machine learning sample of the distribution network alarm information comprises the following steps:
by means of extracting and labeling samples, analysis conditions are provided for an analysis algorithm, distribution network alarm information is combed, word segmentation and labeling are sequentially performed on the alarm information according to four priority levels of accidents, abnormity, displacement and informing, and distribution network alarm information machine learning samples are customized.
The method for constructing the fault analysis unit deduction model diagram comprises physical unit construction, combined physical unit construction and analysis unit construction.
The method for constructing the fault diagnosis knowledge base comprises the following steps:
when the accident tripping occurs, a large number of signals can occur in a short time, the evolution process of the whole accident is obtained by adopting an accident analysis model according to the equipment to which the signals belong, the signal type, the occurrence time and the sequence, an accident analysis set is obtained, the fault property is quickly analyzed and the fault equipment is positioned, an event chain which visually reflects the accident occurrence development process is formed, the problem that unrelated signals are crossed with each other is effectively solved, the complexity degree of accident handling is reduced, and all accident chains formed by the accident tripping occur are integrated to form a fault diagnosis knowledge base.
The method for constructing the networked fault information closed-loop management module comprises the following steps:
the networked fault information closed-loop management module realizes a closed-loop processing process of fault information, after a distribution personnel monitors a distribution automation system, when the distribution network equipment is abnormal, a fault information processing flow can be initiated, the networked fault information closed-loop management module automatically dials an intelligent voice telephone to remind an operation and maintenance unit of the fault equipment and carry out patrol, meanwhile, characters, pictures or video information of the fault recorded by the distribution personnel can be sent to the operation and maintenance unit through a networked platform, after the operation and maintenance unit personnel carry out patrol and processing on site, information recovery is carried out on the reason, the process and the result of fault processing, and finally, the fault processing process is automatically filed to form networked fault information closed-loop management.
Further: in the method for difference analysis and scheme making, the line fault event comprises line fault tripping and line fault switch refusing.
The main transformer faults comprise main transformer body faults, main transformer high/medium/low voltage side fault tripping and main transformer fault switch failure.
The bus fault event comprises bus fault and bus fault line switch failure.
The capacitive reactance fault comprises a capacitive/reactive fault trip event.
The grounding transformer/station fault comprises grounding transformer/station fault tripping.
The switch body faults comprise line switches, bus-coupled/sectional switches and bypass switch fault tripping.
Further: in the method for constructing the fault analysis unit deduction model diagram, the physical unit construction adopts a physical unit mode, signals can be classified again, the signals are divided into specific physical units, primary equipment is positioned through the physical units, certain accident equipment can be quickly positioned when an accident happens, and the intelligent level of accident analysis is greatly improved.
Further: in the constructed fault analysis unit deduction model diagram, the combined physical units can be divided into equipment combined physical units, combined physical units under a voltage class and extension units formed according to the protection range of the protection device according to the type of the primary and secondary equipment.
Further: the equipment combined physical unit is as follows: the physical units on both sides of the line or the basic physical units of each side terminal of the main transformer are combined to form the basic units of the line or the main transformer.
Further: the combined physical units under the voltage class are as follows: bus differential protection under different voltage levels combines basic units formed by buses and switches thereof under different voltage levels.
Further: the extension unit formed according to the protection range of the protection device is formed by combining equipment of the range related to protection, and is composed of basic units which are searched outwards by stages by a main basic unit, and the stages can be limited.
Further: in the method for constructing the fault analysis unit deduction model diagram, the method for constructing the analysis unit comprises the following steps: and constructing the analysis unit by taking the primary equipment to which the signal belongs as a basic physical unit, taking the event-related equipment as a combination unit and taking the signal uploading time window as a time unit for the objectified signal.
Further: in the method for constructing the fault diagnosis knowledge base, the accident trip is divided into the following steps according to the accident time: transient faults, delayed faults, permanent faults.
Further: when the accident is analyzed, fault equipment, a trip switch, a phase, a coincidence condition and protection action information contained in an accident signal are extracted, and an integral description of accident diagnosis is formed to be used as the accident analysis set.
The distribution network fault studying and judging method provided by the invention has the following beneficial effects: when an accident occurs, the invention can quickly position certain accident equipment, thereby greatly improving the intelligent level of accident analysis.
And constructing an analysis unit by taking the primary equipment to which the signal belongs as a basic physical unit, taking the event-related equipment as a combination unit and taking the signal uploading time window as a time unit. The signals are combined according to the association relationship to form a matter which can comprehensively reflect the happening of the transformer substation or the equipment, the judgment of one equipment matter is formed by performing association analysis and induction on the signals, and the scattered signals in the monitoring system are displayed in a form of an information analysis unit set only by time sequence arrangement.
By constructing a fault diagnosis knowledge base, when an accident trip occurs, a large number of signals occur in a short time, and according to equipment to which the signals belong, signal types, occurrence time and sequence, an accident analysis model can acquire the evolution process of the whole accident to obtain an accident analysis set, quickly analyze the fault property and position fault equipment to form an event chain which visually reflects the accident occurrence and development process, effectively solve the problem of cross of unrelated signals and reduce the complexity of accident handling. The fault assistant decision is effectively pushed intelligently, and the regulation and control personnel can accurately deal with the fault and the abnormal handling without skillfully mastering various safety operation regulations and specifications. Along with the improvement of the operation complexity of the distribution network and the rapid development of the dispatching automation technology and the artificial intelligence technology, the dispatching personnel can conveniently process the daily work along with the fault analysis and judgment and the fault handling decision of the current manual mode.
Due to the fact that the number of secondary signals is large, configuration levels are large, descriptions and expression modes are different in different manufacturers and different maintenance periods, and modeling is difficult, the method for customizing the distribution network alarm information machine learning sample can enable an analysis algorithm to obtain a better analysis result.
Drawings
Fig. 1 is a schematic block diagram of a distribution network fault studying and judging method according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic block diagram illustrating a distribution network fault investigation method according to the present invention.
The distribution network fault studying and judging method comprises the steps of difference analysis and scheme making, distribution network alarm information machine learning sample customization, fault analysis unit deduction model diagram construction, fault diagnosis knowledge base construction and networked fault information closed-loop management module construction.
Difference analysis and scheme making:
the method comprises the following steps of (1) performing investigation and investigation on the fault occurrence and fault handling conditions of a distribution network in a certain area, collecting user data and collecting main application scenes, and combing line fault events which occur in the last 5 years of the distribution network in the certain area, wherein the line fault events comprise line fault tripping and line fault switch refusing; the main transformer faults comprise main transformer body faults, main transformer high/medium/low voltage side fault tripping and main transformer fault switch failure; bus fault events including bus fault, bus fault line switch failure; capacitive reactance faults, including capacitive/reactor fault trip events; the fault handling method comprises the steps of grounding transformer/station fault tripping, switch body fault, 17 types of distribution network faults and fault handling records of 6 equipment types including line switches, bus-tie/section switches, bypass switch fault tripping and the like, wherein each type of fault is not less than 2, and fault condition touch report is formed.
And formulating an overall implementation scheme of the dispatching safety command and fault disposal system based on artificial intelligence.
Customizing a distribution network alarm information machine learning sample:
because the number of secondary signals is huge, the number of related configuration layers is large, descriptions and expression modes are different in different manufacturers and different maintenance periods, and modeling is difficult, a semantic analysis method is needed to solve the problem of secondary modeling, so that a better analysis result can be obtained by an analysis algorithm, and analysis conditions are provided for the analysis algorithm by extracting samples and labeling the samples. And combing the alarm information of the distribution network, and sequentially carrying out word segmentation and labeling on the alarm information according to four priority levels of accidents, abnormity, displacement and informing to customize a machine learning sample of the alarm information of the distribution network.
Constructing a fault analysis unit deduction model diagram:
A. physical unit construction:
the mode of adopting the physical unit can classify the signal once more, divides the signal to specific physical unit in, through the primary equipment of physical unit location, when the accident takes place, can fix a position certain accident equipment rapidly, has improved the intelligent level of accident analysis greatly.
B. Combined physical unit:
the combined physical unit can be divided into an equipment combined physical unit, a combined physical unit under a voltage class and an extension unit formed according to the protection range of the protection device according to the type of the primary and secondary equipment.
1. Equipment combined physical unit: the physical units on both sides of the line or the basic physical units of each side terminal of the main transformer are combined to form the basic units of the line or the main transformer.
2. Combined physical unit at voltage level: bus protection under different voltage levels can combine the buses and the basic units formed by the switches thereof under different voltage levels.
3. An extension unit formed according to a protection range of the protection device: is composed of devices protecting the range concerned, noting that the basic units to be searched step by step with the main basic unit out can define the number of steps, for example: three or four stages.
C. Construction of an analysis unit:
and constructing an analysis unit by taking the primary equipment to which the signal belongs as a basic physical unit, taking the event-related equipment as a combination unit and taking the signal uploading time window as a time unit. The signals are combined according to the association relationship to form a matter which can comprehensively reflect the happening of the transformer substation or the equipment, the judgment of one equipment matter is formed by performing association analysis and induction on the signals, and the scattered signals in the monitoring system are displayed in a form of an information analysis unit set only by time sequence arrangement.
Constructing a fault diagnosis knowledge base:
accidents can be classified into accident tripping and general accidents according to severity level.
When the accident tripping occurs, a large number of signals occur in a short time, the accident analysis model can acquire the evolution process of the whole accident according to the equipment to which the signals belong, the signal type, the occurrence time and the sequence, an accident analysis set is obtained, the fault property is quickly analyzed, the fault equipment is positioned, an event chain which visually reflects the accident occurrence and development process is formed, the problem that uncorrelated signals are crossed is effectively solved, and the complexity of accident handling is reduced.
The accident trip can be divided into the following according to the accident time: transient faults, delayed faults, permanent faults. When the accident diagnosis and analysis are carried out, information such as fault equipment, a trip switch, phase, coincidence condition, protection action and the like contained in the signals are mainly extracted to form the overall description of the accident diagnosis.
A networked fault information closed-loop management module:
the networked fault information closed-loop management module realizes a closed-loop processing process of fault information, a distribution personnel can initiate a fault information processing flow if the distribution network equipment is found to be abnormal after monitoring the distribution automation system, the system automatically dials an intelligent voice telephone to remind an operation and maintenance unit of fault equipment and requires patrol, meanwhile, the system can send character, picture or video information of faults recorded by the distribution personnel to the operation and maintenance unit through a networked platform, the operation and maintenance unit personnel carry out patrol and processing on site and then carry out information recovery on reasons, processes and results of fault processing, and finally, the system automatically files the fault processing process to form networked fault information closed-loop management.
The distribution network fault studying and judging method provided by the invention has the following beneficial effects: when an accident occurs, the invention can quickly position certain accident equipment, thereby greatly improving the intelligent level of accident analysis.
And constructing an analysis unit by taking the primary equipment to which the signal belongs as a basic physical unit, taking the event-related equipment as a combination unit and taking the signal uploading time window as a time unit. The signals are combined according to the association relationship to form a matter which can comprehensively reflect the happening of the transformer substation or the equipment, the judgment of one equipment matter is formed by performing association analysis and induction on the signals, and the scattered signals in the monitoring system are displayed in a form of an information analysis unit set only by time sequence arrangement.
By constructing a fault diagnosis knowledge base, when an accident trip occurs, a large number of signals occur in a short time, and according to equipment to which the signals belong, signal types, occurrence time and sequence, an accident analysis model can acquire the evolution process of the whole accident to obtain an accident analysis set, quickly analyze the fault property and position fault equipment to form an event chain which visually reflects the accident occurrence and development process, effectively solve the problem of cross of unrelated signals and reduce the complexity of accident handling. The fault assistant decision is effectively pushed intelligently, and the regulation and control personnel can accurately deal with the fault and the abnormal handling without skillfully mastering various safety operation regulations and specifications. Along with the improvement of the operation complexity of the distribution network and the rapid development of the dispatching automation technology and the artificial intelligence technology, the dispatching personnel can conveniently process the daily work along with the fault analysis and judgment and the fault handling decision of the current manual mode.
Due to the fact that the number of secondary signals is large, configuration levels are large, descriptions and expression modes are different in different manufacturers and different maintenance periods, and modeling is difficult, the method for customizing the distribution network alarm information machine learning sample can enable an analysis algorithm to obtain a better analysis result.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. The distribution network fault studying and judging method is characterized by comprising the following steps: the method comprises the steps of difference analysis and scheme making, distribution network alarm information machine learning sample customization, fault analysis unit deduction model graph construction, fault diagnosis knowledge base construction and networked fault information closed-loop management module construction;
the specific method for the difference analysis and the scheme formulation is as follows:
respectively carrying out investigation and investigation on distribution network fault occurrence and fault disposal conditions, collecting user data and collecting main application scenes, combing line fault events, main transformer faults, bus fault events, capacitive reactance faults, grounding transformer/station transformer faults and switch body faults which occur in a distribution network, forming fault condition layout reports, and formulating an integral implementation scheme of a dispatching safety command and fault disposal system;
the specific method for customizing the machine learning sample of the distribution network alarm information comprises the following steps:
providing analysis conditions for an analysis algorithm by means of extracting and labeling samples, carding distribution network alarm information, performing word segmentation and labeling on the alarm information in sequence according to four priority levels of accidents, abnormity, displacement and informing, and customizing a distribution network alarm information machine learning sample;
the method comprises the following steps that a model diagram is deduced by the fault analysis unit construction, and the model diagram comprises physical unit construction, combined physical unit construction and analysis unit construction;
the method for constructing the fault diagnosis knowledge base comprises the following steps:
when the accident tripping occurs, a large number of signals can occur in a short time, the evolution process of the whole accident is obtained by adopting an accident analysis model according to the equipment to which the signals belong, the signal type, the occurrence time and the sequence, an accident analysis set is obtained, the fault property is quickly analyzed and the fault equipment is positioned, an event chain which visually reflects the accident occurrence development process is formed, the problem that unrelated signals are crossed with each other is effectively solved, the complexity degree of accident handling is reduced, and all accident chains formed by the accident tripping occur are integrated to form a fault diagnosis knowledge base;
the method for constructing the networked fault information closed-loop management module comprises the following steps:
the networked fault information closed-loop management module realizes a closed-loop processing process of fault information, after a distribution personnel monitors a distribution automation system, when the distribution network equipment is abnormal, a fault information processing flow can be initiated, the networked fault information closed-loop management module automatically dials an intelligent voice telephone to remind an operation and maintenance unit of the fault equipment and carry out patrol, meanwhile, characters, pictures or video information of the fault recorded by the distribution personnel can be sent to the operation and maintenance unit through a networked platform, after the operation and maintenance unit personnel carry out patrol and processing on site, information recovery is carried out on the reason, the process and the result of fault processing, and finally, the fault processing process is automatically filed to form networked fault information closed-loop management.
2. The distribution network fault studying and judging method according to claim 1, characterized in that: in the method for difference analysis and scheme making, the line fault event comprises line fault tripping and line fault switch refusing;
the main transformer faults comprise main transformer body faults, main transformer high/medium/low voltage side fault tripping and main transformer fault switch failure;
the bus fault event comprises bus fault and bus fault line switch failure;
the capacitive reactance fault comprises a capacitive/reactance fault trip event;
the fault changing for the grounding transformer/station comprises fault changing tripping for the grounding transformer/station;
the switch body faults comprise line switches, bus-coupled/sectional switches and bypass switch fault tripping.
3. The distribution network fault studying and judging method according to claim 1, characterized in that: in the method for constructing the fault analysis unit deduction model diagram, the physical unit construction adopts a physical unit mode, signals can be classified again, the signals are divided into specific physical units, primary equipment is positioned through the physical units, certain accident equipment can be quickly positioned when an accident happens, and the intelligent level of accident analysis is greatly improved.
4. The distribution network fault studying and judging method according to claim 1, characterized in that: in the constructed fault analysis unit deduction model diagram, the combined physical units can be divided into equipment combined physical units, combined physical units under a voltage class and extension units formed according to the protection range of the protection device according to the type of the primary and secondary equipment.
5. The distribution network fault studying and judging method according to claim 4, characterized in that: the equipment combined physical unit is as follows: the physical units on both sides of the line or the basic physical units of each side terminal of the main transformer are combined to form the basic units of the line or the main transformer.
6. The distribution network fault studying and judging method according to claim 4, characterized in that: the combined physical units under the voltage class are as follows: bus differential protection under different voltage levels combines basic units formed by buses and switches thereof under different voltage levels.
7. The distribution network fault studying and judging method according to claim 4, characterized in that: the extension unit formed according to the protection range of the protection device is formed by combining equipment of the range related to protection, and is composed of basic units which are searched outwards by stages by a main basic unit, and the stages can be limited.
8. The distribution network fault studying and judging method according to claim 1, characterized in that: in the method for constructing the fault analysis unit deduction model diagram, the method for constructing the analysis unit comprises the following steps:
and constructing the analysis unit by taking the primary equipment to which the signal belongs as a basic physical unit, taking the event-related equipment as a combination unit and taking the signal uploading time window as a time unit for the objectified signal.
9. The distribution network fault studying and judging method according to claim 1, characterized in that: in the method for constructing the fault diagnosis knowledge base, the accident trip is divided into the following steps according to the accident time: transient faults, delayed faults, permanent faults.
10. The distribution network fault studying and judging method according to claim 9, characterized in that: when the accident is analyzed, fault equipment, a trip switch, a phase, a coincidence condition and protection action information contained in an accident signal are extracted, and an integral description of accident diagnosis is formed to be used as the accident analysis set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110994163.6A CN113884803A (en) | 2021-08-27 | 2021-08-27 | Distribution network fault studying and judging method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110994163.6A CN113884803A (en) | 2021-08-27 | 2021-08-27 | Distribution network fault studying and judging method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113884803A true CN113884803A (en) | 2022-01-04 |
Family
ID=79011230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110994163.6A Pending CN113884803A (en) | 2021-08-27 | 2021-08-27 | Distribution network fault studying and judging method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113884803A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140036375A (en) * | 2012-09-12 | 2014-03-26 | 현대로템 주식회사 | Intelligent failure asset management system for railway car |
| CN104155581A (en) * | 2014-08-20 | 2014-11-19 | 国家电网公司 | Distribution network power fault judgment method |
| CN105449862A (en) * | 2015-12-09 | 2016-03-30 | 国网安徽省电力公司蚌埠供电公司 | Intelligent processing system for power grid monitoring alarm information on basis of physical units as containers |
| CN109086889A (en) * | 2018-09-30 | 2018-12-25 | 广东电网有限责任公司 | Terminal fault diagnostic method neural network based, device and system |
| CN109242118A (en) * | 2018-10-30 | 2019-01-18 | 重庆旺山实业有限公司 | A kind of visual integrated management system of intelligence O&M |
| CN109557414A (en) * | 2018-11-30 | 2019-04-02 | 国家电网有限公司技术学院分公司 | Integrated power system fault diagnosis alarming processing system and method |
| CN109782126A (en) * | 2018-12-27 | 2019-05-21 | 上海交通大学 | Power distribution network incipient fault detection method based on class people's concept learning |
| US20210174973A1 (en) * | 2017-11-30 | 2021-06-10 | Michael Munoz | INTERNET OF THINGS (IoT) ENABLED WIRELESS SENSOR SYSTEM ENABLING PROCESS CONTROL, PREDICTIVE MAINTENANCE OF ELECTRICAL DISTRIBUTION NETWORKS, LIQUID AND GAS PIPELINES AND MONITORING OF AIR POLLUTANTS INCLUDING NUCLEAR, CHEMICAL, AND BIOLOGICAL AGENTS USING ATTACHED AND/OR EMBEDDED PASSIVE ELECTROMAGNETIC SENSORS |
| CN113625082A (en) * | 2021-08-06 | 2021-11-09 | 国网宁夏电力有限公司 | Power distribution network equipment fault studying and judging method based on machine learning algorithm model |
-
2021
- 2021-08-27 CN CN202110994163.6A patent/CN113884803A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140036375A (en) * | 2012-09-12 | 2014-03-26 | 현대로템 주식회사 | Intelligent failure asset management system for railway car |
| CN104155581A (en) * | 2014-08-20 | 2014-11-19 | 国家电网公司 | Distribution network power fault judgment method |
| CN105449862A (en) * | 2015-12-09 | 2016-03-30 | 国网安徽省电力公司蚌埠供电公司 | Intelligent processing system for power grid monitoring alarm information on basis of physical units as containers |
| US20210174973A1 (en) * | 2017-11-30 | 2021-06-10 | Michael Munoz | INTERNET OF THINGS (IoT) ENABLED WIRELESS SENSOR SYSTEM ENABLING PROCESS CONTROL, PREDICTIVE MAINTENANCE OF ELECTRICAL DISTRIBUTION NETWORKS, LIQUID AND GAS PIPELINES AND MONITORING OF AIR POLLUTANTS INCLUDING NUCLEAR, CHEMICAL, AND BIOLOGICAL AGENTS USING ATTACHED AND/OR EMBEDDED PASSIVE ELECTROMAGNETIC SENSORS |
| CN109086889A (en) * | 2018-09-30 | 2018-12-25 | 广东电网有限责任公司 | Terminal fault diagnostic method neural network based, device and system |
| CN109242118A (en) * | 2018-10-30 | 2019-01-18 | 重庆旺山实业有限公司 | A kind of visual integrated management system of intelligence O&M |
| CN109557414A (en) * | 2018-11-30 | 2019-04-02 | 国家电网有限公司技术学院分公司 | Integrated power system fault diagnosis alarming processing system and method |
| CN109782126A (en) * | 2018-12-27 | 2019-05-21 | 上海交通大学 | Power distribution network incipient fault detection method based on class people's concept learning |
| CN113625082A (en) * | 2021-08-06 | 2021-11-09 | 国网宁夏电力有限公司 | Power distribution network equipment fault studying and judging method based on machine learning algorithm model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110336375B (en) | Processing method and system for power grid monitoring alarm information | |
| WO2015043441A1 (en) | Smart alarm inference method based on multi-scenario analysis | |
| CN111768076B (en) | Monitoring alarm signal clustering method taking power grid event as center | |
| CN106908690A (en) | Distributed intelligence warning system and its method for diagnosing faults between boss station | |
| CN108988487B (en) | Power grid power failure event identification method based on multidimensional data | |
| CN107492952A (en) | A kind of regulation and control center alarm signal analysis method and the intelligent warning system based on it | |
| CN104218676A (en) | Intelligent warning system and method for power dispatching automation master station | |
| CN109001596B (en) | Power grid fault diagnosis and power transmission line parameter identification system | |
| CN110321411A (en) | A kind of power system monitor warning information classification method, system and readable storage medium storing program for executing | |
| CN112269812A (en) | Intelligent power distribution network safety monitoring management system based on big data | |
| CN110349048B (en) | Substation multidimensional data operation interactive control platform and fault handling method | |
| CN110458535A (en) | A kind of computer room O&M method based on AR glasses | |
| CN107834523A (en) | Extra-high voltage direct-current fault diagnosis system and method for work based on model and rule base | |
| CN103324128A (en) | Primary equipment fault warning comprehensive compression method in power dispatching automation system | |
| CN109361260A (en) | A kind of electric power system fault intelligent monitoring and judgment method | |
| CN115208059A (en) | Transformer substation power and environment monitoring alarm processing system and method | |
| CN110046782A (en) | A kind of automatic identifying method of power grid accident tripping monitoring information problem | |
| CN111044845A (en) | Power distribution network accident identification method and system based on Apriori algorithm | |
| CN114398947A (en) | Expert system-based power grid fault automatic classification method and system | |
| CN113449044A (en) | Intelligent station equipment maintenance safety measure automatic generation method and device based on learning inference machine | |
| CN117272571A (en) | Visual checking method and system for power grid new equipment starting scheme | |
| CN113884803A (en) | Distribution network fault studying and judging method | |
| CN110750500A (en) | Method and system for checking CCD (Charge coupled device) file and SCD (substation configuration description) file of intelligent substation | |
| CN114626440A (en) | Monitoring signal objectification analysis method and device | |
| CN112434955B (en) | Distribution network line operation risk sensing method based on multi-data fusion |
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 |