CN115688492B - Digital modeling and intelligent detection method for power secondary equipment - Google Patents
Digital modeling and intelligent detection method for power secondary equipment Download PDFInfo
- Publication number
- CN115688492B CN115688492B CN202310000599.8A CN202310000599A CN115688492B CN 115688492 B CN115688492 B CN 115688492B CN 202310000599 A CN202310000599 A CN 202310000599A CN 115688492 B CN115688492 B CN 115688492B
- Authority
- CN
- China
- Prior art keywords
- digital
- community
- model
- power
- 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.)
- Active
Links
Images
Abstract
The invention discloses a digital modeling and intelligent detection method for secondary power equipment, which comprises the following steps: extracting an electrical signal, a physical position and an information attribute of the power secondary equipment, constructing a digital modeling label of the power secondary equipment based on the electrical signal, the physical position and the information attribute of the power secondary equipment, and constructing a plurality of community digital models of the power secondary equipment based on the identity of the digital modeling label of the power secondary equipment; and sequentially making an optimal community test case of each community digital model in each community digital model through a neural network according to the digital modeling label of the power secondary equipment. According to the method, the test cases are evaluated by using the neural network in the local detection, so that the best test case which ensures that the community test case has the highest test coverage in the community digital model is selected, the community digital model is uniformly detected, the power equipment is uniformly detected by using the relevance of the power system, the detection efficiency is improved, and the accuracy of fault location is improved.
Description
Technical Field
The invention relates to the technical field of power grid modeling, in particular to a digital modeling and intelligent detection method for electric power secondary equipment.
Background
The national smart grid industry base is advanced particularly in the aspects of relay protection and power system automation industry, and 80% of related manufacturing plants in China are gathered. But under the large environment that the population dividend disappears and the labor cost rises, the method has great restriction on the international competitiveness of the manufacturing industry in China. The power system automation industry is the same as most manufacturing industries, and the "industry 4.0" is a necessary way for developing a product which cannot be bypassed, needs to reduce dependence on labor force to a greater extent, and meets personalized requirements of users, so that it is imperative to seek an advanced technology which can replace manpower, improve production efficiency, improve product quality and ensure product consistency.
The prior art CN202111280411.7 discloses a digital modeling and intelligent detection system for electric power secondary equipment, which comprises digital modeling, artificial intelligent software for generating software and hardware configuration of an automatic detection system, and closed-loop intelligent detection, and applies the idea of a digital main line to the intelligent production detection process of electric power system secondary equipment manufacturers, and the digital model of the secondary equipment modeled from the bottom layer by the same syntax semantics has the same data source, so that the digital model has the description of standard development, and is not distorted in step-by-step transmission and traceable. A digital mainline is a method by which unified data access can be created using a single real source. When used throughout an enterprise, this approach may correspond a reliable set of data to different functions, thereby achieving consistency and enhancing collaboration. After the data set is started, the data can be synchronized in real time, so that upstream and downstream information can be available to all users, product innovation is promoted, the process is optimized, and efficiency and worker productivity are improved. Although the prior art has certain advantages in the aspects of equipment modeling and intelligent detection, some defects also exist, for example, each power equipment is subjected to global digital modeling to separate the equipment relevance of a power system, so that the intelligent detection loses integrity, the accuracy is reduced in circuit fault location, meanwhile, the global detection adopts artificial setting by using test cases, the random subjectivity is strong, and the accuracy of fault location is further reduced.
Disclosure of Invention
The invention aims to provide a digital modeling and intelligent detection method for power secondary equipment, which aims to solve the technical problems that in the prior art, each power equipment carries out global digital modeling, the equipment relevance of a power system is cut off, so that the intelligent detection loses integrity, the accuracy is reduced during circuit fault location, meanwhile, the global detection adopts artificial setting by using a test case, the random subjectivity is strong, and the accuracy of fault location is further reduced.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
a digital modeling and intelligent detection method for power secondary equipment comprises the following steps:
the method comprises the following steps of S1, extracting an electrical signal, a physical position and an information attribute of the electric power secondary equipment, constructing a digital modeling label of the electric power secondary equipment based on the electrical signal, the physical position and the information attribute of the electric power secondary equipment, and constructing a plurality of community digital models of the electric power secondary equipment based on the identity of the digital modeling label of the electric power secondary equipment;
s2, sequentially making an optimal community test case of each community digital model in each community digital model through a neural network according to a digital modeling label of power secondary equipment so as to ensure that the community test case has the highest test coverage in the community digital model and realize the uniform detection of the community digital model;
and S3, inputting display data of the power secondary equipment in the community digital model applied with the optimal community test case into a preset detection model to position a power failure point in the community digital model.
As a preferred aspect of the present invention, the constructing a digital modeling tag of the electric power secondary device based on the electric signal, the physical location, and the information attribute of the electric power secondary device includes:
performing principal component analysis on the electrical signals, the physical positions and the information attributes to obtain a plurality of digital characteristics, and performing weighted modeling on each digital characteristic to obtain a characteristic network model;
and performing minimum spanning tree decomposition and evolution on the characteristic network model to obtain a dynamic network model, and performing topological feature extraction on the dynamic network model to obtain a topological feature vector as a digital modeling label of the power secondary equipment.
As a preferable aspect of the present invention, the constructing of the feature network model includes:
taking each digital feature as a network topology node of a feature network model, and setting a topology connecting edge between any two digital features;
and taking the Euclidean distance between any two digital features as the edge weight of the topological connection between the corresponding network topological nodes to obtain the feature network model.
As a preferred scheme of the present invention, the evolution expression of the dynamic network model is:
T i =MST(G cn 0 - G cn i-1 )：
G cn i = G cn i-1 + T i ；
in the formula, T i Is a firstiMinimum spanning tree, G, by secondary evolution cn i-1 Is a firstiDynamic network model obtained by secondary evolution, G cn 0 As a feature network model, G cn 0 - G cn i-1 Is G cn 0 And G cn i-1 MST is the minimum spanning tree generation algorithm,ifor the counting term of the number of evolutions,i∈[2,N]n is the total number of evolutions, G cn N Is a dynamic network model;
wherein, T 1 =MST(G cn 0 )，G cn 1 = T 1 ；
In the formula, T 1 Minimum spanning Tree, G, for evolution 1 cn 1 The dynamic network model obtained for the 1 st evolution.
As a preferable aspect of the present invention, the building of the plurality of community digital models of the electric power secondary device based on the identity of the digital modeling label of the electric power secondary device includes:
clustering operation is carried out on each electric power secondary device based on the digital modeling label so as to classify each electric power secondary device to a plurality of device communities, and digital modeling is carried out on each device community by using the digital modeling label corresponding to the community center point so as to obtain a plurality of community digital models.
As a preferred aspect of the present invention, the sequentially making an optimal community test case for each community digital model in each community digital model according to the digital modeling label of the power secondary device through a neural network includes:
selecting a plurality of groups of test cases and a plurality of electric power secondary devices, and applying each group of test cases to each electric power secondary device in sequence to monitor the test accuracy and the test matching degree;
selecting a test case with the highest test accuracy and test matching degree for each electric power secondary device, extracting topological characteristic vectors of the electric power secondary devices as input items of the neural network, and using the test case as output items of the neural network;
and performing network training on the input items and the output items by utilizing a neural network to obtain a test case matching model, inputting the digital modeling label of each community digital model into the test case matching model to obtain a test case of which each community digital model achieves the highest test accuracy and test matching degree, and taking the test case as the optimal community test case of each community digital model.
As a preferred aspect of the present invention, the inputting display data of the power secondary devices in the community digital model to which the optimal community test case is applied to a preset detection model to locate the power failure point in the community digital model includes:
applying the optimal community test case to the community digital model, and acquiring display data of the power secondary equipment in the community digital model;
and outputting the display data to a preset detection model, judging the operation state of each electric power secondary device by the preset detection model, and calibrating the physical position of the electric power secondary device of which the operation state is judged to be the fault state as an electric power fault point.
As a preferred scheme of the present invention, the preset detection model is constructed by training a classifier model with big data.
As a preferred aspect of the present invention, the topological feature vector includes a maximum degree, an average degree, entropy, energy, an average degree of association, an average shortest path length, and an average class coefficient.
As a preferable aspect of the present invention, the clustering operation is set to be a small community cluster to ensure identity of the digital modeling labels of the power secondary devices in the community digital model.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, local digital modeling is carried out on each electric power secondary device, the device relevance of an electric power system during modeling is guaranteed, the electric power integrity of intelligent detection is further guaranteed, the circuit fault location accuracy is improved, meanwhile, the test cases are evaluated by the aid of the neural network in the local detection, the best test case which guarantees that the community test cases have the highest test coverage in the community digital model is selected, the community digital model is uniformly detected, the electric power devices are uniformly detected by means of the relevance of the electric power system, the detection efficiency is improved, and meanwhile, the fault location accuracy is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary and that other implementation drawings may be derived from the provided drawings by those of ordinary skill in the art without inventive effort.
Fig. 1 is a flowchart of a digital modeling and intelligent detection method for electric power secondary equipment according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the invention provides a digital modeling and intelligent detection method for electric power secondary equipment, which comprises the following steps:
the method comprises the following steps of S1, extracting an electrical signal, a physical position and an information attribute of the electric power secondary equipment, constructing a digital modeling label of the electric power secondary equipment based on the electrical signal, the physical position and the information attribute of the electric power secondary equipment, and constructing a plurality of community digital models of the electric power secondary equipment based on the identity of the digital modeling label of the electric power secondary equipment;
the digital modeling label of the electric power secondary equipment is constructed based on the electric signal, the physical position and the information attribute of the electric power secondary equipment, and comprises the following steps:
performing principal component analysis on the electrical signals, the physical positions and the information attributes to obtain a plurality of digital characteristics, and performing weighted modeling on each digital characteristic to obtain a characteristic network model;
and performing minimum spanning tree decomposition evolution on the characteristic network model to obtain a dynamic network model, and performing topological feature extraction on the dynamic network model to obtain a topological feature vector as a digital modeling label of the power secondary equipment.
Constructing a characteristic network model, comprising the following steps:
taking each digital feature as a network topology node of a feature network model, and setting a topology connecting edge between any two digital features;
and taking the Euclidean distance between any two digital characteristics as the edge weight of the topological connection between the corresponding network topology nodes to obtain a characteristic network model.
The evolution expression of the dynamic network model is as follows:
T i =MST(G cn 0 - G cn i-1 )：
G cn i = G cn i-1 + T i ；
in the formula, T i Is as followsiMinimum spanning tree, G, by secondary evolution cn i-1 Is a firstiDynamic network model obtained by secondary evolution, G cn 0 As a feature network model, G cn 0 - G cn i-1 Is G cn 0 And G cn i-1 MST is the minimum spanning tree generation algorithm,ifor the counting term of the number of evolutions,i∈[2,N]n is the total number of evolutions, G cn N Is a dynamic network model;
wherein, T 1 =MST(G cn 0 )，G cn 1 = T 1 ；
In the formula, T 1 Minimum spanning Tree, G, for evolution 1 cn 1 The dynamic network model obtained for the 1 st evolution.
The method for constructing the plurality of community digital models of the power secondary equipment based on the identity of the digital modeling labels of the power secondary equipment comprises the following steps:
clustering operation is carried out on each electric power secondary device based on the digital modeling label so as to classify each electric power secondary device to a plurality of device communities, and digital modeling is carried out on each device community by using the digital modeling label corresponding to the community center point so as to obtain a plurality of community digital models.
The method comprises the steps of setting a digital modeling label for the secondary power equipment, enabling the secondary power equipment with strong relevance to have the same or similar digital modeling label, enabling the secondary power equipment with the strong relevance to be located in the same community based on polarity clustering operation of the digital modeling label, enabling the secondary power equipment with the strong relevance to be classified in the same community, establishing the same community digital model for the community to perform subsequent fault analysis, achieving unified detection on the secondary power equipment through power system relevance, and improving detection efficiency.
In the embodiment, the digital modeling label performs principal component analysis on the electrical signal, the physical position and the information attribute to obtain a plurality of digital characteristics, and performs weighted modeling on each digital characteristic to obtain a characteristic network model, so that the dimension reduction processing of the digital characteristics is realized and the important characteristics are reserved;
the method comprises the steps of performing minimum spanning tree decomposition evolution on a characteristic network model to obtain a dynamic network model, performing topological feature extraction on the dynamic network model to obtain a topological feature vector as a digital modeling label of the power secondary equipment, performing topological construction on the remaining important features, converting the remaining important features into topological features, and performing feature association on the remaining important features through topological quantization, so that the established digital modeling label performs association characterization on the important features in the electrical signals, the physical positions and the information attributes, namely converting actual data features into topological expressions, and expressing the important features in the discrete electrical signals, the physical positions and the information attributes by using a topological structure, thereby simplifying expression complexity and discrete type.
S2, sequentially making an optimal community test case of each community digital model in each community digital model through a neural network according to the digital modeling label of the power secondary equipment so as to ensure that the community test case has the highest test coverage in the community digital model and realize the uniform detection of the community digital model;
the method comprises the following steps of sequentially making an optimal community test case of each community digital model in each community digital model through a neural network according to a digital modeling label of power secondary equipment, wherein the optimal community test case comprises the following steps:
selecting a plurality of groups of test cases and a plurality of electric secondary devices, and applying each group of test cases to each electric secondary device in sequence to monitor test accuracy and test matching degree;
selecting a test case with the highest test accuracy and test matching degree for each electric power secondary device, extracting topological characteristic vectors of the electric power secondary devices as input items of a neural network, and using the test case as an output item of the neural network;
and performing network training on the input items and the output items by utilizing a neural network to obtain a test case matching model, and inputting the digital modeling label of each community digital model into the test case matching model to obtain a test case, which achieves the highest test accuracy and test matching degree, of each community digital model and is used as the optimal community test case of each community digital model.
Because the electric power relevance of each electric power secondary device in each community digital model is strong, an optimal community test case is selected for each community digital model, the optimal community test case is directly applied to the corresponding community digital model, all the electric power secondary devices in the community digital model can be covered, the community digital model is used as a unit for testing, and compared with the testing method which takes the electric power secondary devices as the unit, the testing efficiency is improved, the electric power relevance of the devices is fully considered, the completeness of electric power detection is guaranteed, the non-discrete testing is realized, the testing effect is closer to the reality, and the testing result is more reliable and accurate.
And S3, inputting display data of the power secondary equipment in the community digital model applied with the optimal community test case into a preset detection model to position a power failure point in the community digital model.
Inputting display data of power secondary equipment in the community digital model applied with the optimal community test case into a preset detection model to position a power failure point in the community digital model, wherein the display data comprises:
applying the optimal community test case to the community digital model, and acquiring display data of the power secondary equipment in the community digital model;
and outputting the display data to a preset detection model, judging the operation state of each power secondary device by the preset detection model, and calibrating the physical position of the power secondary device of which the operation state is judged to be the fault state as a power fault point.
And constructing a preset detection model by training a classifier model through big data.
The topological feature vector comprises maximum degree, average degree, entropy, energy, average joint degree, average shortest path length and average cluster coefficient.
Clustering operation is set as small community clustering to ensure the identity of the digital modeling label of the power secondary equipment in the community digital model.
According to the method, local digital modeling is carried out on each power secondary device, the device relevance of a power system during modeling is guaranteed, the power integrity of intelligent detection is further guaranteed, the circuit fault location accuracy is improved, meanwhile, the test cases are evaluated by the local detection through the neural network so as to select the best test case which guarantees the highest test coverage of the community test case in the community digital model, so that the community digital model is uniformly detected, the power devices are uniformly detected through the power system relevance, the detection efficiency is improved, and meanwhile, the fault location accuracy is further improved.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made to the disclosure by those skilled in the art within the spirit and scope of the disclosure, and such modifications and equivalents should also be considered as falling within the scope of the disclosure.
Claims (6)
1. A digital modeling and intelligent detection method for electric secondary equipment is characterized in that: the method comprises the following steps:
the method comprises the following steps of S1, extracting electrical signals, physical positions and information attributes of the secondary power equipment, constructing a digital modeling label of the secondary power equipment based on the electrical signals, the physical positions and the information attributes of the secondary power equipment, and constructing a plurality of community digital models of the secondary power equipment based on the identity of the digital modeling label of the secondary power equipment;
s2, sequentially making an optimal community test case of each community digital model in each community digital model through a neural network according to the digital modeling label of the power secondary equipment so as to ensure that the community test case has the highest test coverage in the community digital model and realize the uniform detection of the community digital model;
s3, inputting display data of the power secondary equipment in the community digital model applied with the optimal community test case into a preset detection model to position a power failure point in the community digital model;
the digital modeling label of the electric power secondary equipment is constructed based on the electric signal, the physical position and the information attribute of the electric power secondary equipment, and comprises the following steps:
performing principal component analysis on the electrical signal, the physical position and the information attribute to obtain a plurality of digital characteristics, and performing weighted modeling on each digital characteristic to obtain a characteristic network model;
performing minimum spanning tree decomposition evolution on the characteristic network model to obtain a dynamic network model, and performing topological feature extraction on the dynamic network model to obtain a topological feature vector as a digital modeling label of the power secondary equipment;
the method for constructing the plurality of community digital models of the power secondary equipment based on the identity of the digital modeling labels of the power secondary equipment comprises the following steps:
performing clustering operation on each power secondary device based on the digital modeling label to classify each power secondary device into a plurality of device communities, and performing digital modeling on each device community by using the digital modeling label corresponding to the community center point to obtain a plurality of community digital models;
the method comprises the following steps of sequentially making an optimal community test case of each community digital model in each community digital model through a neural network according to a digital modeling label of power secondary equipment, wherein the optimal community test case comprises the following steps:
selecting a plurality of groups of test cases and a plurality of electric secondary devices, and applying each group of test cases to each electric secondary device in sequence to monitor test accuracy and test matching degree;
selecting a test case with the highest test accuracy and test matching degree for each electric power secondary device, extracting topological characteristic vectors of the electric power secondary devices as input items of the neural network, and using the test case as output items of the neural network;
performing network training on input items and output items by utilizing a neural network to obtain a test case matching model, inputting the digital modeling label of each community digital model into the test case matching model to obtain a test case, which is used as an optimal community test case of each community digital model and allows each community digital model to reach the highest test accuracy and test matching degree;
inputting display data of power secondary equipment in the community digital model applied with the optimal community test case into a preset detection model to position a power failure point in the community digital model, wherein the display data comprises:
applying the optimal community test case to the community digital model, and acquiring display data of the power secondary equipment in the community digital model;
and outputting the display data to a preset detection model, judging the operation state of each power secondary device by the preset detection model, and calibrating the physical position of the power secondary device of which the operation state is judged as the fault state as a power fault point.
2. The digital modeling and intelligent detection method for the secondary power equipment according to claim 1, characterized in that: the construction of the characteristic network model comprises the following steps:
taking each digital feature as a network topology node of a feature network model, and arranging a topology connecting edge between any two digital features;
and taking the Euclidean distance between any two digital features as the edge weight of the topological connection between the corresponding network topological nodes to obtain the feature network model.
3. The digital modeling and intelligent detection method for the secondary power equipment according to claim 2, characterized in that: the evolution expression of the dynamic network model is as follows:
T i =MST(G cn 0 -G cn i-1 )：
G cn i = G cn i-1 +T i ；
in the formula, T i Is as followsiMinimum spanning tree, G, by secondary evolution cn i-1 Is a firstiDynamic network model obtained by secondary evolution, G cn 0 As a feature network model, G cn 0 -G cn i-1 Is G cn 0 And G cn i-1 The graph difference operation of (1), MST is a minimum spanning tree generation algorithm,ifor the count term of the number of evolutions,i∈[2,N]n is evolutionTotal number of times, G cn N Is a dynamic network model;
wherein, T 1 =MST(G cn 0 )，G cn 1 = T 1 ；
In the formula, T 1 Minimum spanning Tree, G, for evolution 1 cn 1 The dynamic network model obtained for the 1 st evolution.
4. The digital modeling and intelligent detection method for the electric power secondary equipment according to claim 1, wherein the preset detection model is constructed by training a classifier model through big data.
5. The method according to claim 1, wherein the topological feature vector comprises a maximum degree, an average degree, entropy, energy, an average degree of association, an average shortest path length, and an average class coefficient.
6. The method as claimed in claim 1, wherein the clustering operation is set as small community clustering to ensure identity of digital modeling labels of the secondary power devices in the community digital model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310000599.8A CN115688492B (en) | 2023-01-03 | 2023-01-03 | Digital modeling and intelligent detection method for power secondary equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310000599.8A CN115688492B (en) | 2023-01-03 | 2023-01-03 | Digital modeling and intelligent detection method for power secondary equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115688492A CN115688492A (en) | 2023-02-03 |
| CN115688492B true CN115688492B (en) | 2023-03-10 |
Family
ID=85057473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310000599.8A Active CN115688492B (en) | 2023-01-03 | 2023-01-03 | Digital modeling and intelligent detection method for power secondary equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115688492B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595013B (en) * | 2023-07-17 | 2023-12-01 | 中国水利水电第七工程局有限公司 | Multi-type monitoring information storage and calculation method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657914A (en) * | 2015-03-09 | 2015-05-27 | 云南电网公司昆明供电局 | Method for establishing mathematical model for evaluating operation state of overhead transmission line |
| CN110995475A (en) * | 2019-11-20 | 2020-04-10 | 国网湖北省电力有限公司信息通信公司 | Power communication network fault detection method based on transfer learning |
| CN114880884A (en) * | 2022-07-07 | 2022-08-09 | 北京华源芯电科技有限公司 | Specialized modeling analysis method and system based on digital energy system |
| CN115130254A (en) * | 2022-05-10 | 2022-09-30 | 西华大学 | Power communication fusion network generation method based on improved modularity community division |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120266209A1 (en) * | 2012-06-11 | 2012-10-18 | David Jeffrey Gooding | Method of Secure Electric Power Grid Operations Using Common Cyber Security Services |
| CN116113967A (en) * | 2020-07-16 | 2023-05-12 | 强力交易投资组合2018有限公司 | System and method for controlling digital knowledge dependent rights |
| CN112418451A (en) * | 2020-11-05 | 2021-02-26 | 武汉大学 | Transformer fault diagnosis positioning system based on digital twinning |
| CN113705026B (en) * | 2021-11-01 | 2022-03-08 | 南京亚尔软件测试有限公司 | Digital modeling and intelligent detection system for power secondary equipment |
| CN114036733A (en) * | 2021-11-02 | 2022-02-11 | 南京亚尔软件测试有限公司 | Digital screen cabinet modeling design method for production test and matching test generation method |
-
2023
- 2023-01-03 CN CN202310000599.8A patent/CN115688492B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657914A (en) * | 2015-03-09 | 2015-05-27 | 云南电网公司昆明供电局 | Method for establishing mathematical model for evaluating operation state of overhead transmission line |
| CN110995475A (en) * | 2019-11-20 | 2020-04-10 | 国网湖北省电力有限公司信息通信公司 | Power communication network fault detection method based on transfer learning |
| CN115130254A (en) * | 2022-05-10 | 2022-09-30 | 西华大学 | Power communication fusion network generation method based on improved modularity community division |
| CN114880884A (en) * | 2022-07-07 | 2022-08-09 | 北京华源芯电科技有限公司 | Specialized modeling analysis method and system based on digital energy system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115688492A (en) | 2023-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115688492B (en) | Digital modeling and intelligent detection method for power secondary equipment | |
| CN106681903B (en) | Method and device for generating test case | |
| CN111625991A (en) | Low-voltage distribution network topology verification method | |
| CN110932917A (en) | High-frequency synchronous acquisition and edge calculation-based distribution room topology discovery method | |
| CN111159897B (en) | Target optimization method and device based on system modeling application | |
| CN110556920A (en) | Distribution automation monitoring method, system, terminal and storage medium | |
| CN104698374A (en) | Method for improving testing efficiency and accuracy of automatic relay protecting tester | |
| CN109784393A (en) | A kind of kinsfolk's identification clustering method based on telecommunications big data | |
| CN113705026B (en) | Digital modeling and intelligent detection system for power secondary equipment | |
| CN109901830A (en) | A kind of symbol arranging method and system for scada system development | |
| CN117519951A (en) | Real-time data processing method and system based on message center | |
| CN113660687A (en) | Network difference cell processing method, device, equipment and storage medium | |
| CN115630073B (en) | Electric power Internet of things data processing method and platform based on edge calculation | |
| CN108764750A (en) | Main distribution network model modeling and topology analyzing method and system | |
| CN109710669B (en) | Method for improving accuracy of full power grid model data based on check rule base | |
| CN109165865B (en) | Main distribution integrated model checking method and system based on boundary switch connectivity analysis | |
| CN115174416B (en) | Network planning system, method and device and electronic equipment | |
| CN107357900A (en) | A kind of control method and device of electric power system model versions of data | |
| CN105930295A (en) | Plug and play method and device for secondary equipment of intelligent substation | |
| CN115599657B (en) | Software facility abnormity judgment method | |
| CN110889614A (en) | Power grid system important user power supply risk analysis method based on SCADA big data | |
| CN110955156A (en) | Control method and device of data interface and data interface | |
| CN108563568A (en) | A kind of detection of application performance bottleneck and diagnostic method based on clustering | |
| CN115238423A (en) | S-SCDN dynamic topology analysis and loop detection algorithm based on graph calculation | |
| CN110765655A (en) | Dispatching automation simulation system and construction method and device of SCADA model thereof |
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 |