CN115828132A - Spectral clustering transformer cooling device operation state identification method, terminal and medium - Google Patents
Spectral clustering transformer cooling device operation state identification method, terminal and medium Download PDFInfo
- Publication number
- CN115828132A CN115828132A CN202211454780.8A CN202211454780A CN115828132A CN 115828132 A CN115828132 A CN 115828132A CN 202211454780 A CN202211454780 A CN 202211454780A CN 115828132 A CN115828132 A CN 115828132A
- Authority
- CN
- China
- Prior art keywords
- objects
- object set
- transformer
- cooling device
- graph
- 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
Images
Landscapes
- Housings And Mounting Of Transformers (AREA)
Abstract
The invention discloses a spectral clustering running state identification method, a terminal and a medium for a transformer cooling device, relates to the technical field of monitoring of a power system cooling device, and solves the problem that the running state of the transformer cooling device cannot be accurately judged by utilizing monitoring data information in the conventional online monitoring method for the temperature of a transformer, wherein the technical scheme is as follows: constructing an undirected weighted graph related to the similarity between the objects in the first object set and the objects in the first object set according to the similarity between the objects in the first object set, and performing cluster division on the undirected weighted graph to enable the objects in the first object set to be clustered into a plurality of second object sets; acquiring an oil temperature difference value between objects in a second object set, and constructing a connected graph of the second object set based on the oil temperature difference value between the objects; and identifying the second object concentrated object based on the target sub-connected graph in the connected graph to obtain a first identification result, so as to achieve the purposes of analyzing the oil temperature state of the transformer in real time and grasping the running state of the transformer cooling device in time.
Description
Technical Field
The invention relates to the technical field of monitoring of cooling devices of power systems, in particular to a method, a terminal and a medium for identifying the operating state of a spectral clustering transformer cooling device.
Background
The transformer is used as electrical equipment widely applied to power systems and enterprise users, and plays a key role in the processes of power transmission, distribution and use. In order to ensure that the heat generated by the transformer during operation does not affect the normal operation of the transformer, a cooling system needs to be added on the transformer, thereby playing a role in reducing the oil temperature of the transformer. When the cooling device is abnormally operated, the most direct change is that the temperature of the transformer oil is abnormally increased, the service life of the transformer is shortened, and the transformer is in failure and is stopped operating when the temperature is serious.
In order to ensure the safe operation of the transformer, it is urgently needed to be able to timely and accurately judge the operation state of the transformer, monitor the oil temperature change of the transformer in real time, and take appropriate measures in real time to ensure the safe, stable and economic operation of the transformer. At present, various online monitoring methods for transformer temperature have been proposed, including wireless and wired monitoring networks, but both lack analysis and application of monitoring data, and cannot accurately determine the operating state of the transformer cooling device by using the monitoring data information.
Disclosure of Invention
The invention aims to provide a spectral clustering transformer cooling device operation state identification method, a terminal and a medium, and achieves the purposes of analyzing the oil temperature state of a transformer in real time and grasping the operation state of the transformer cooling device in time.
The technical purpose of the invention is realized by the following technical scheme:
the method for identifying the operating state of the spectral clustering transformer cooling device comprises the following steps:
acquiring similarity among objects in a first object set;
constructing an undirected weighted graph about the similarity between the objects in the first object set and the objects in the first object set;
performing cluster division processing on the undirected weighted graph to enable objects in the first object set to be clustered into a plurality of second object sets;
acquiring an oil temperature difference value between objects in any second object set, and constructing a connected graph of any second object set based on the oil temperature difference value between the objects;
and identifying any object in the second object set based on the target sub-connected graph in the connected graph to obtain a first identification result.
Further, the method for acquiring the similarity between the objects in the first object set specifically comprises:
acquiring characteristic data of each object in a first object set;
and calculating the characteristic data of each object in the first object set by using Euclidean measurement to obtain the similarity between the objects in the first object set.
Further, the characteristic data comprises measurement data and standing book data;
wherein the measurement data comprises an ambient temperature and a transformer load factor;
the ledger data includes manufacturer and equipment model.
Further, the process of obtaining the similarity between the objects in the first object set specifically includes:
identifying the ledger data among the objects, and if the manufacturer and the equipment model in the ledger data among the objects are the same, obtaining a first identification result; otherwise, obtaining a second identification result;
and respectively carrying out Euclidean metric calculation on the measured data of the objects in the first identification result and the second identification result to obtain the similarity between the objects in the first object set.
Further, the process of performing cluster partitioning on the undirected weighted graph specifically includes:
constructing an adjacency matrix and a degree matrix of the undirected weighted graph;
constructing a laplacian matrix for the undirected weighted graph based on the adjacency matrix and the degree matrix of the undirected weighted graph;
standardizing the Laplace matrix to obtain a standardized Laplace matrix;
selecting eigenvalues of the standardized Laplace matrix and eigenvectors corresponding to the eigenvalues to construct an eigenvector matrix;
and carrying out Ncut graph cutting on the undirected weighted graph based on the feature matrix, and then dividing the objects in the first object set into a plurality of second object sets by clusters.
Further, the method for constructing the connectivity graph of any second object set specifically includes:
presetting an oil temperature target value;
if the oil temperature difference value between any two objects in any second object set is not more than the oil temperature target value, communicating the any two objects;
and traversing all objects in any second object set to obtain a connected graph of any second object set.
Further, the target oil temperature value is a difference between the abnormal oil temperature value and the normal oil temperature value of the object.
Further, the target sub-connected graph is the largest connected graph in the connected graph.
An electronic terminal, comprising: a memory for storing a computer program; and the processor is used for executing the computer program stored in the memory so as to enable the electronic terminal to execute the spectral clustering transformer cooling device operation state identification method.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, implements the spectral clustering transformer cooling device operating state identification method.
Compared with the prior art, the invention has the following beneficial effects:
constructing an undirected weighted graph related to the similarity between the objects in the first object set and the objects in the first object set according to the similarity between the objects in the first object set, and performing cluster division on the undirected weighted graph to enable the objects in the first object set to be clustered into a plurality of second object sets; acquiring an oil temperature difference value between objects in any second object set, and constructing a connected graph of any second object set based on the oil temperature difference value between the objects; and identifying any second object concentrated object based on the target sub-connected graph in the connected graph to obtain a first identification result, so that the aims of analyzing the oil temperature state of the transformer in real time, grasping the running state of the transformer cooling device in time, improving the running state monitoring and early warning capability of the transformer cooling device and ensuring the safe and stable running of the transformer are fulfilled.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
fig. 1 is a schematic flow chart of a method for identifying an operation state of a spectral clustering transformer cooling device in this embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The embodiment is as follows: as shown in fig. 1, the method, terminal and medium for identifying the operating state of the spectral clustering transformer cooling device,
the method for identifying the operating state of the spectral clustering transformer cooling device comprises the following steps: acquiring similarity among objects in a first object set; constructing an undirected weighted graph about the similarity between the objects in the first object set and the objects in the first object set; performing cluster division processing on the undirected weighted graph to enable objects in the first object set to be clustered into a plurality of second object sets; acquiring an oil temperature difference value between objects in any second object set, and constructing a connected graph of any second object set based on the oil temperature difference value between the objects; and identifying any object in the second object set based on the target sub-connected graph in the connected graph to obtain a first identification result.
The method for acquiring the similarity between the objects in the first object set specifically comprises the following steps: acquiring characteristic data of each object in a first object set; the characteristic data comprises measurement data and standing book data; wherein the measurement data comprises an ambient temperature and a transformer load factor; the ledger data includes manufacturer and equipment model.
Specifically, the method comprises the following steps: at a certain data acquisition moment, acquiring characteristic data of n transformers in a monitoring range in real time, and constructing a first object set U comprising the n transformers and the characteristic data corresponding to the transformers n ＝{u 1 、u 2 ……u n-1 、u n ,u 1 Characteristic data u 2 Characteristic data of 823060, 8230u n-1 Characteristic data u n Profile }. The characteristic data of the transformer comprise measurement data and standing book data of the transformer, wherein the measurement data of the transformer specifically comprise: the ambient temperature of the transformer, the load factor of the transformer. The transformer ledger data specifically includes: the manufacturer of the transformer and the type of the transformer.
And calculating the characteristic data of each object in the first object set by using Euclidean measurement to obtain the similarity between the objects in the first object set. The process for obtaining the similarity between the objects in the first object set specifically comprises the following steps: identifying the ledger data among the objects, and if the manufacturer and the equipment model in the ledger data among the objects are the same, obtaining a first identification result; otherwise, obtaining a second identification result; and respectively carrying out Euclidean metric calculation on the measured data of the objects in the first identification result and the second identification result to obtain the similarity between the objects in the first object set.
Specifically, the method comprises the following steps: according to transformer u i 、u j Calculating the environmental temperature, the load factor, the manufacturer and the type of the transformer u i 、u j Similarity sim (u) between i ，u j )。
In the calculation of transformer u i 、u j Similarity sim (u) between i ，u j ) Before, judge transformer u i 、u j If the manufacturer and the equipment model (standing book data) of the transformer u are the same or not i 、u j The types of the manufacturers and the equipment are the same, then the transformer u i 、u j Objects belonging to the first recognition result; if transformer u i 、u j Is not identical in manufacturer and equipment model (including transformer u) i 、u j The same manufacturer, different equipment types and the transformer u i 、u j Different manufacturers, the same equipment model, and a transformer u i 、u j Different manufacturers and equipment models, etc.), the transformer u i 、u j Belonging to the object in the second recognition result.
First calculating transformer u i 、u j Euclidean distance (Euclidean distance) between the transformer units, and then the transformer u is obtained by using the Euclidean distance i 、u j The similarity between them.
Wherein u is i Is the ith transformer, u j Is the jth transformer, η i The load factor of the ith transformer; eta j The load factor of the jth transformer is shown; t is t Ring i The ambient temperature of the ith transformer; t is t Ring j Is the ambient temperature of the jth transformer; z is the type of the transformer-to-transformer ledger data identification result; when z takes a value of 1, it represents the transformer u i 、u j The manufacturer and the equipment model of the device are completely the same and belong to a first identification result; when z takes a value of 0, it represents the transformer u i 、u j The manufacturer and the equipment model of (2) are not completely the same and belong to a second identification result.
The process of performing cluster division on the undirected weighted graph specifically comprises the following steps: constructing an adjacency matrix and a degree matrix of the undirected weighted graph; constructing a laplacian matrix for the undirected weighted graph based on the adjacency matrix and the degree matrix of the undirected weighted graph; standardizing the Laplace matrix to obtain a standardized Laplace matrix; selecting eigenvalues of the standardized Laplace matrix and eigenvectors corresponding to the eigenvalues to construct an eigenvector matrix; and carrying out Ncut graph cutting on the undirected weighted graph based on the feature matrix, and then dividing the objects in the first object set into a plurality of second object sets by clusters.
Specifically, the method comprises the following steps: constructing an undirected weighted graph G (V, E) with a vertex V as a first set of objects U n Set of transformers, E is a first set of objects U n The set of similarities between the transformers.
And constructing an adjacency matrix W and a degree matrix D of the undirected weighted graph G (V, E) according to the undirected weighted graph G (V, E).
Calculating an adjacency matrix W:
w ij ＝w ji ＝sim(u i ,u j ),w ij ≥0,w ii ＝0
wherein, w ij 、w ji For a transformer u i 、u j I is an element of (1, n), j is an element of (1, n)
A calculation degree matrix D:
a laplacian matrix L is calculated.
After the Laplace matrix L is subjected to standardization processing, a standardized Laplace matrix D is obtained -1/2 LD -1/2 Calculating D -1/2 LD -1/2 And the respective corresponding feature vectors f.
Will normalize the Laplace matrix D -1/2 LD -1/2 After n eigenvalues in the system are sorted from large to small, the smallest k eigenvalues and eigenvectors f corresponding to the k eigenvalues are taken, wherein k belongs to (1, n).
And forming a matrix by the k eigenvalues and eigenvectors F corresponding to the k eigenvalues, and standardizing the matrix formed by the k eigenvalues and eigenvectors F corresponding to the k eigenvalues according to rows to finally form an n x k dimensional eigenvector matrix F.
On the basis of the n multiplied by k dimension characteristic matrix F, carrying out Ncut mapping on the undirected weighted graph to obtain cluster division A (a) of the transformer in the first object set under different operating conditions 1 ,a 2 ,...a k ) Wherein a is k Representing the kth second set (kth cluster).
The method for constructing the connected graph of any second object set specifically comprises the following steps: presetting an oil temperature target value; if the oil temperature difference value between any two objects in any second object set is not more than the oil temperature target value, communicating the any two objects; and traversing all the objects in any second object set to obtain a connected graph of any second object set. And the target oil temperature value is the difference value between the abnormal oil temperature value and the normal oil temperature value of the object. And the target sub-connected graph is the maximum connected graph in the connected graph.
Specifically, the method comprises the following steps: selecting the normal oil temperature value of the transformer when the transformer cooling device operates normally, wherein the oil temperature value of the transformer is the normal oil temperature value of the transformer, selecting the abnormal oil temperature value of the transformer when the transformer cooling device operates abnormally, and taking the difference value between the normal oil temperature value and the abnormal oil temperature value of the transformer as the target oil temperature value omega. Selecting any one of the second sets, where the ith second set a is selected i If the second set a i The difference between the oil temperatures of any two transformers is smallAt the target oil temperature value omega, the two transformers are communicated, and the second set a is traversed i All transformers are arranged inside to form a communication graph G 1 Selecting a connectivity graph G 1 Maximum connectivity sub-graph G 1 ' as a target connectivity graph. By judging whether the transformer is in the maximum connected subgraph G 1 ' (target communication diagram) indicates the operation state of the cooling device of the transformer. If the transformer is not in the maximum connected sub-graph G 1 ' (target connection diagram), it represents that the transformer is an abnormal point, indicating that the cooling device of the transformer is not operating normally; if the transformer is in maximum connected sub-graph G 1 ' (target connection diagram) indicates that the transformer is a normal point, indicating that the cooling device of the transformer is operating normally. The second set a i When any two transformers are communicated, the oil temperature difference of the two transformers satisfies the following relation:
t oil ＝x i -x j ≤ω
Wherein, t Oil For a transformer x i 、x j Difference of oil temperatures of (1), x i Is a second set a i Oil temperature value, x, of the ith transformer j Is a second set a i The oil temperature value of the jth transformer.
In summary, the method for identifying the operating state of the transformer cooling device based on spectral clustering provided by this embodiment solves the problems that various online monitoring methods for the temperature of the transformer are provided, analysis and application of monitoring data are lacked, and the operating state of the transformer cooling device cannot be accurately judged by using the information of the monitoring data. The monitoring and early warning capability of the running state of the transformer cooling device is improved, the safe and stable running of the transformer is guaranteed, the oil temperature state of the transformer is analyzed in real time, and the running state of the transformer cooling device is mastered in time.
The present embodiment further provides an electronic terminal, including: a memory for storing a computer program; and the processor is used for executing the computer program stored in the memory so as to enable the electronic terminal to execute the spectral clustering transformer cooling device operation state identification method.
The present embodiment also provides a computer-readable storage medium, which stores a computer program, and when the program is executed by a processor, the computer program implements the spectral clustering transformer cooling device operation state identification method.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only examples of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. The method for identifying the operating state of the spectral clustering transformer cooling device is characterized by comprising the following steps of:
acquiring similarity among objects in a first object set;
constructing an undirected weighted graph about the similarity between the objects in the first object set and the objects in the first object set;
performing cluster division processing on the undirected weighted graph to enable objects in the first object set to be clustered into a plurality of second object sets;
acquiring an oil temperature difference value between objects in any second object set, and constructing a connected graph of any second object set based on the oil temperature difference value between the objects;
and identifying any one second object centralized object based on the target sub-connected graph in the connected graph to obtain a first identification result.
2. The spectral clustering transformer cooling device operation state identification method according to claim 1, wherein the method for obtaining the similarity between the first object concentration objects specifically comprises:
acquiring characteristic data of each object in a first object set;
and calculating the characteristic data of each object in the first object set by using Euclidean measurement to obtain the similarity between the objects in the first object set.
3. The spectral clustering transformer cooling device operation state identification method according to claim 2, characterized in that:
the characteristic data comprises measurement data and standing book data;
wherein the measurement data comprises an ambient temperature and a transformer load factor;
the ledger data includes manufacturer and equipment model.
4. The spectral clustering transformer cooling device operation state identification method according to claim 3, wherein the process of obtaining the similarity between the objects in the first object set specifically comprises:
identifying the ledger data among the objects, and if the manufacturer and the equipment model in the ledger data among the objects are the same, obtaining a first identification result; otherwise, obtaining a second identification result;
and respectively carrying out Euclidean metric calculation on the measured data of the objects in the first identification result and the second identification result to obtain the similarity between the objects in the first object set.
5. The spectral clustering transformer cooling device operation state identification method according to claim 1, wherein the process of performing cluster division processing on the undirected weighted graph specifically comprises:
constructing an adjacency matrix and a degree matrix of the undirected weighted graph;
constructing a laplacian matrix for the undirected weighted graph based on the adjacency matrix and the degree matrix of the undirected weighted graph;
standardizing the Laplace matrix to obtain a standardized Laplace matrix;
selecting eigenvalues of the standardized Laplace matrix and eigenvectors corresponding to the eigenvalues to construct an eigenvector matrix;
and carrying out Ncut graph cutting on the undirected weighted graph based on the feature matrix, and then dividing the objects in the first object set into a plurality of second object sets by clusters.
6. The spectral clustering transformer cooling device operation state identification method according to claim 1, wherein the construction method of the connectivity graph of any one of the second object sets specifically is:
presetting an oil temperature target value;
if the oil temperature difference value between any two objects in any second object set is not more than the oil temperature target value, communicating the any two objects;
and traversing all the objects in any second object set to obtain a connected graph of any second object set.
7. The spectral clustering transformer cooling device operating state identification method according to claim 6, wherein:
and the target oil temperature value is the difference value between the abnormal oil temperature value and the normal oil temperature value of the object.
8. The spectral clustering transformer cooling device operation state identification method according to claim 1, characterized in that:
and the target sub-connected graph is the maximum connected graph in the connected graph.
9. An electronic terminal, comprising:
a memory for storing a computer program;
a processor for executing the memory-stored computer program to cause an electronic terminal to perform the spectral-clustered transformer cooling apparatus operation state identification method of any one of claims 1 to 8.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: the program, when executed by a processor, implements the spectral clustering transformer cooling device operating state identification method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211454780.8A CN115828132A (en) | 2022-11-21 | 2022-11-21 | Spectral clustering transformer cooling device operation state identification method, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211454780.8A CN115828132A (en) | 2022-11-21 | 2022-11-21 | Spectral clustering transformer cooling device operation state identification method, terminal and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115828132A true CN115828132A (en) | 2023-03-21 |
Family
ID=85529621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211454780.8A Pending CN115828132A (en) | 2022-11-21 | 2022-11-21 | Spectral clustering transformer cooling device operation state identification method, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115828132A (en) |
-
2022
- 2022-11-21 CN CN202211454780.8A patent/CN115828132A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699913B (en) | Method and device for diagnosing abnormal relationship of household transformer in transformer area | |
| CN111475680A (en) | Method, device, equipment and storage medium for detecting abnormal high-density subgraph | |
| CN116148679B (en) | Battery health state prediction method and related device | |
| CN110795690A (en) | Wind power plant operation abnormal data detection method | |
| CN114114039B (en) | Method and device for evaluating consistency of single battery cells of battery system | |
| CN113570200A (en) | Power grid operation state monitoring method and system based on multidimensional information | |
| CN107942994A (en) | A kind of satellite temperature control system method for diagnosing faults based on temperature curve feature | |
| CN113554526A (en) | Fault early warning method and device for power equipment, storage medium and processor | |
| CN113125903A (en) | Line loss anomaly detection method, device, equipment and computer-readable storage medium | |
| CN111027841A (en) | Low-voltage transformer area line loss calculation method based on gradient lifting decision tree | |
| Li et al. | A novel method for lithium-ion battery fault diagnosis of electric vehicle based on real-time voltage | |
| CN114610553A (en) | Intelligent equipment detection system and detection method thereof | |
| CN112163595B (en) | Method and device for acquiring typical electricity utilization mode of user and electronic equipment | |
| CN108537249B (en) | Industrial process data clustering method for density peak clustering | |
| CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
| CN115828132A (en) | Spectral clustering transformer cooling device operation state identification method, terminal and medium | |
| CN117170915A (en) | Data center equipment fault prediction method and device and computer equipment | |
| CN115795389A (en) | Method and system for monitoring operation condition of transformer cooling device | |
| CN111988192A (en) | Train communication network fault diagnosis method based on machine learning | |
| Chen et al. | A data mining method for extracting key factors of distribution network reliability | |
| CN115828118B (en) | Air conditioner abnormality identification method based on machine learning | |
| CN115829543B (en) | Method for determining validity of preventive test of power equipment based on fault detection interval | |
| CN114580108B (en) | Oxygen top-blown converter small sample fault diagnosis method based on graph neural network | |
| CN112884167B (en) | Multi-index anomaly detection method based on machine learning and application system thereof | |
| CN111553565B (en) | Performance evaluation method and system for online monitoring device of transformer substation |
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 |