CN109374063B - Cluster management-based transformer anomaly detection method, device and equipment - Google Patents
Cluster management-based transformer anomaly detection method, device and equipment Download PDFInfo
- Publication number
- CN109374063B CN109374063B CN201811475724.6A CN201811475724A CN109374063B CN 109374063 B CN109374063 B CN 109374063B CN 201811475724 A CN201811475724 A CN 201811475724A CN 109374063 B CN109374063 B CN 109374063B
- Authority
- CN
- China
- Prior art keywords
- transformer
- clustering
- cluster
- clusters
- analyzed
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a transformer abnormity detection method, device and equipment based on cluster management, a hierarchical clustering algorithm is adopted to divide a first basic parameter, namely a transformer with a standing book parameter and similar working condition data, into the same transformer clustering cluster, each clustering transformer based on the same has a similar state, then the difference of the equipment in the cluster is known through the mutual comparison of a second basic parameter of the transformer in the same clustering cluster, namely state monitoring data, which transformer is in an abnormal state can be rapidly judged, the abnormity of the transformer can be recognized in the early stage of transformer fault occurrence, and the abnormity detection accuracy is high.
Description
Technical Field
The application relates to the technical field of operation fault diagnosis of power transformation equipment, in particular to a transformer abnormity detection method, device and equipment based on cluster management.
Background
The power transformer is one of the most important power transmission and transformation equipment in a power system, and the operation state of the power transformer is directly related to the safety and stability of the whole power system, so that the reliable operation of the transformer is guaranteed to be very important.
At present, a method for detecting a transformer state anomaly is to perform online monitoring on core state quantities of a transformer, and perform threshold value judgment on the core state quantities based on national standards, so as to diagnose whether the state of the transformer is abnormal, and perform threshold value comparison on the transformer state quantities.
Disclosure of Invention
The embodiment of the application provides a transformer abnormity detection method, device and equipment based on cluster management, which can identify the abnormity of a transformer before the transformer breaks down and ensure the safe and stable operation of the transformer.
In view of this, a first aspect of the present application provides a transformer abnormality detection method based on cluster management, including:
taking each transformer to be analyzed in a first number of transformers to be analyzed as an initial transformer cluster, and acquiring a first basic parameter of each initial transformer cluster, wherein the first basic parameter comprises: the transformer comprises a transformer manufacturer, average temperature and humidity of a service place, rated power of a transformer, rated voltage of the transformer and service duration;
calculating first similarity of every two initial transformer clusters according to a similarity calculation formula based on the first basic parameter, performing hierarchical clustering on the initial transformer clusters to obtain a plurality of clustering clusters, and stopping clustering until the ratio of the sum of the number of the clustering clusters and the number of the initial transformer clusters which are not clustered to the first quantity is less than or equal to a preset ratio;
comparing second basic parameters of the transformers to be analyzed in the clustering cluster, and judging whether the transformers to be analyzed are abnormal, wherein the second basic parameters comprise: the transformer oil comprises dissolved gases H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge.
Preferably, the calculating, based on the first basic parameter, a first similarity between every two initial transformer clusters according to a similarity calculation formula, and performing hierarchical clustering on the initial transformer clusters to obtain a plurality of clustered clusters, and stopping clustering until a ratio of a sum of the number of the clustered clusters and the number of the initial transformer clusters that are not clustered to the first number is less than or equal to a preset ratio, specifically includes:
calculating first similarity of every two initial transformer clusters according to a similarity calculation formula based on the first basic parameter, and merging the first initial transformer cluster with the maximum first similarity and the second initial transformer cluster into a cluster;
calculating a first ratio of the total number of the clustering clusters to the initial transformer cluster number which is not clustered to the first number, stopping clustering if the first ratio is less than or equal to a preset ratio, otherwise, continuing clustering the initial transformer clusters to obtain a plurality of clustering clusters, judging a second ratio of the total number of the clustering clusters to the initial transformer cluster number which is not clustered to the first number, and stopping clustering if the second ratio is less than or equal to the preset ratio.
Preferably, the mutual comparison of the second basic parameters is performed on the transformers to be analyzed in the cluster, and whether the transformers to be analyzed are abnormal is determined, where the second basic parameters include: dissolved gases in transformer oil, such as H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge, specifically comprise:
normalizing the second basic parameter;
calculating the distance between every two transformers to be analyzed in the same clustering cluster according to a preset distance calculation formula;
and if the distance between the rest of the transformers to be analyzed and the transformers i to be analyzed in the clustering cluster where the transformers i to be analyzed are located is larger than or equal to the total number of distance thresholds and is larger than or equal to the occupation ratio threshold of each clustering cluster, judging that the transformers i to be analyzed are abnormal.
Preferably, the similarity calculation formula is:
wherein S isijThe coefficient of the levan of transformer i and transformer j, SijkFor transformer i and transformer j at data akA value ofkIs a first basic parameter, WijkAs a weighted variable, if data akIs a binary variable, 1-1 pair time SijkOther pairings S1ijk0; 0-0 pairing time WijkWhen the other is matched, W is equal to 0ijkIf data a is 1kTaking 1 when the data of the two transformers are the same as the sequence variable, and otherwise, taking 0; if the data akIs a numerical variable, Sijk＝1-|aik-ajk|/RkWherein a isikAnd ajkThe variable a is respectively the transformer i and the transformer jkValue of (A), RkIs a variable akThe overall distance of (a).
Preferably, the preset ratio is: 10 percent.
Preferably, the preset distance calculation formula is as follows:
wherein d isijIs Euclidean distance, b 'of transformer i and transformer j'ikThe data is the k-th class online monitoring data of the ith transformer after normalization processing.
Preferably, the duty ratio threshold is: 80 percent.
The second aspect of the present application provides a transformer anomaly detection device based on cluster management, including:
an obtaining module, configured to use each transformer to be analyzed in a first number of transformers to be analyzed as an initial transformer cluster, and obtain a first basic parameter of each initial transformer cluster, where the first basic parameter includes: the transformer comprises a transformer manufacturer, average temperature and humidity of a service place, rated power of a transformer, rated voltage of the transformer and service duration;
the clustering module is used for calculating first similarity of every two initial transformer clusters according to a similarity calculation formula based on the first basic parameter, carrying out hierarchical clustering on the initial transformer clusters to obtain a plurality of clustering clusters, and stopping clustering until the ratio of the number of the clustering clusters to the number of the non-clustered initial transformer clusters to the first number is less than or equal to a preset ratio;
a judging module, configured to perform a second basic parameter comparison on the transformers to be analyzed in the cluster, and judge whether the transformers to be analyzed are abnormal, where the second basic parameter includes: the transformer oil comprises dissolved gases H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge.
Preferably, the clustering module specifically includes: the device comprises a first clustering module and a second clustering module;
the first clustering module is used for calculating first similarity of every two initial transformer clusters according to a similarity calculation formula based on the first basic parameter, and merging the first initial transformer cluster with the maximum first similarity and the second initial transformer cluster into a clustering cluster;
the second clustering module is used for calculating a first ratio of the sum of the number of the clustered clusters and the number of the initial transformer clusters which are not clustered to the first number, stopping clustering if the first ratio is less than or equal to a preset ratio, otherwise, continuing clustering the initial transformer clusters to obtain a plurality of clustered clusters, judging a second ratio of the sum of the number of the clustered clusters and the number of the initial transformer clusters which are not clustered to the first number, and stopping clustering if the second ratio is less than or equal to the preset ratio;
the judging module specifically comprises: the device comprises a normalization module, a distance module and a detection module;
the normalization module is used for performing normalization processing on the second basic parameter;
the distance module is used for calculating the distance between every two transformers to be analyzed in the same clustering cluster according to a preset distance calculation formula;
the detection module is configured to determine that the transformer i to be analyzed is abnormal if distances between the remaining transformers to be analyzed and the transformer i to be analyzed in the cluster where the transformer i to be analyzed is located are greater than or equal to a total number of distance thresholds and account for more than or equal to an occupancy threshold of each cluster.
A third aspect of the present application provides a cluster-managed transformer anomaly detection device, which includes a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the cluster management based transformer anomaly detection method according to the first aspect according to instructions in the program code.
According to the technical scheme, the embodiment of the application has the following advantages:
the application provides a transformer abnormity detection method based on cluster management, which comprises the following steps: taking each transformer to be analyzed in the first number of transformers to be analyzed as an initial transformer cluster, and acquiring a first basic parameter of each initial transformer cluster, wherein the first basic parameter comprises: the transformer comprises a transformer manufacturer, average temperature and humidity of a service place, rated power of a transformer, rated voltage of the transformer and service duration; based on a first basic parameter, calculating first similarity of every two initial transformer clusters according to a similarity calculation formula, carrying out hierarchical clustering on the initial transformer clusters to obtain a plurality of clustering clusters, and stopping clustering until the ratio of the number of the clustering clusters to the sum of the number of the non-clustered initial transformer clusters to the first number is less than or equal to a preset ratio; comparing second basic parameters of the transformers to be analyzed in the clustering cluster, and judging whether the transformers to be analyzed are abnormal, wherein the second basic parameters comprise: the transformer oil comprises dissolved gases H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge. According to the method, the first basic parameters, namely transformers with similar account parameters and working condition data are divided into the same transformer clustering cluster by adopting a hierarchical clustering algorithm, each clustering transformer based on the condition has a similar state, and then the difference of equipment in the clustering clusters is known through the mutual comparison of the second basic parameters of the transformers in the same clustering cluster, namely the state monitoring data, so that which transformer is in an abnormal state can be rapidly judged, the abnormity of the transformers can be recognized in the early stage of the transformer fault occurrence, and the abnormity detection accuracy is high.
Drawings
Fig. 1 is a schematic flowchart of a transformer anomaly detection method based on cluster management in an embodiment of the present application;
fig. 2 is another schematic flow chart of a transformer abnormality detection method based on cluster management in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a transformer abnormality detection apparatus based on cluster management in an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
For convenience of understanding, referring to fig. 1, a transformer abnormality detection method based on cluster management provided in an embodiment of the present application includes:
It should be noted that, in the embodiment of the present application, data of the transformer is divided into the first basic parameter akAnd a second basic parameter bkTwo kinds, the first basic parameter akThe transformer account parameter data comprises six kinds of transformer manufacturers, average temperature and humidity of service places, rated power of a transformer, rated voltage of the transformer and service duration which are respectively marked as a1～a6. Second basic parameter bkDetecting data for a transformer state, comprising: nine kinds of dissolved gases H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge in the transformer oil are respectively b1～b9. Each transformer to be analyzed in the transformers to be analyzed is taken as an initial transformer cluster, i.e. transformer i can be represented as xi＝{ai1,ai2,...,ai6In which xiFirst basic parameter data for the ith transformer, aijJ is not less than 1 and not more than 6 and is the j-th type basic parameter data of the ith transformer.
102, calculating first similarity of every two initial transformer clusters according to a similarity calculation formula based on a first basic parameter, performing hierarchical clustering on the initial transformer clusters to obtain a plurality of clustering clusters, and stopping clustering until the ratio of the number of the clustering clusters to the sum of the number of the non-clustered initial transformer clusters to the first number is less than or equal to a preset ratio.
It should be noted that, in the embodiment of the present application, based on the first basic parameter data of the transformer to be analyzed, the transformer to be analyzed is subjected to cluster analysis, and the transformer to be analyzed is divided into different transformer clusters. For example, the number of transformers to be analyzed is 20, two similarity calculations are performed on the 20 transformers to be analyzed, after the first similarity calculation is performed, the two transformers to be analyzed with the largest similarity, such as the 10 th transformer and the 11 th transformer, are merged into a cluster, at this time, the number of transformer clusters is changed from 20 to 19, whether 19/20 meets the condition that the preset occupation ratio is less than or equal to is judged, if so, clustering is stopped, if not, second clustering is continued, the result of the second clustering may be that the similarity between the 15 th transformer to be analyzed and the 11 th transformer is the largest, the 15 th transformer to be analyzed is merged into the cluster where the 10 th transformer to be analyzed and the 11 th transformer to be analyzed are located in the first clustering, and may also be that the similarity between the 15 th transformer to be analyzed and the 16 th transformer to be analyzed is the largest, combining the 15 th transformer to be analyzed and the 16 th transformer to be analyzed into a cluster, wherein the number of the transformers to be analyzed is changed from 19 to 18, judging whether 18/20 meets the condition that the ratio is less than or equal to the preset ratio, if so, stopping clustering, and if not, continuing clustering.
103, comparing second basic parameters of the transformers to be analyzed in the clustering cluster, and judging whether the transformers to be analyzed are abnormal, wherein the second basic parameters comprise: the transformer oil comprises dissolved gases H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge.
It should be noted that, in this embodiment of the application, based on the plurality of cluster clusters obtained in step 102, abnormality detection is performed on the transformer to be analyzed by comparing transformers to be analyzed in the same cluster with each other. If the transformer to be analyzed in the same cluster is changed beyond the expected change, the corresponding transformer to be analyzed is considered to be abnormal, alarm processing is carried out, transformer abnormity can be recognized in the early stage of transformer fault occurrence, and safe and stable operation of the transformer is guaranteed.
The application provides a transformer abnormity detection method based on cluster management, which comprises the following steps: taking each transformer to be analyzed in the first number of transformers to be analyzed as an initial transformer cluster, and acquiring a first basic parameter of each initial transformer cluster, wherein the first basic parameter comprises: the transformer comprises a transformer manufacturer, average temperature and humidity of a service place, rated power of a transformer, rated voltage of the transformer and service duration; based on a first basic parameter, calculating first similarity of every two initial transformer clusters according to a similarity calculation formula, carrying out hierarchical clustering on the initial transformer clusters to obtain a plurality of clustering clusters, and stopping clustering until the ratio of the number of the clustering clusters to the sum of the number of the non-clustered initial transformer clusters to the first number is less than or equal to a preset ratio; comparing second basic parameters of the transformers to be analyzed in the clustering cluster, and judging whether the transformers to be analyzed are abnormal, wherein the second basic parameters comprise: the transformer oil comprises dissolved gases H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge. According to the method, the first basic parameters, namely transformers with similar account parameters and working condition data are divided into the same transformer clustering cluster by adopting a hierarchical clustering algorithm, each clustering transformer based on the condition has a similar state, and then the difference of equipment in the clustering clusters is known through the mutual comparison of the second basic parameters of the transformers in the same clustering cluster, namely the state monitoring data, so that which transformer is in an abnormal state can be rapidly judged, the abnormity of the transformers can be recognized in the early stage of the transformer fault occurrence, and the abnormity detection accuracy is high.
For convenience of understanding, please refer to fig. 2, in an embodiment of the present application, another transformer abnormality detection method based on cluster management includes:
It should be noted that step 201 is the same as step 101 in the previous embodiment, and detailed description thereof is omitted here.
Further, the similarity calculation formula is:
wherein S isijThe coefficient of the levan of transformer i and transformer j, SijkFor transformer i and transformer j at data akA value ofkIs a first basic parameter, WijkAs a weighted variable, if data akIs a binary variable, 1-1 pair time SijkOther pairings S1ijk0; 0-0 pairing time WijkWhen the other is matched, W is equal to 0ijkIf data a is 1kTaking 1 when the data of the two transformers are the same as the sequence variable, and otherwise, taking 0; if the data akIs a numerical variable, Sijk＝1-|aik-ajk|/RkWherein a isikAnd ajkThe variable a is respectively the transformer i and the transformer jkValue of (A), RkIs a variable akThe overall distance of (a).
Further, the preset ratio is as follows: 10 percent.
It should be noted that, in the embodiment of the present application, based on the first basic parameter data of the transformer to be analyzed, the transformer to be analyzed is subjected to cluster analysis, and the transformer to be analyzed is divided into different transformer clusters. For example, the number of transformers to be analyzed is 20, two similarity calculations are performed on the 20 transformers to be analyzed, after the first similarity calculation is performed, the two transformers to be analyzed with the largest similarity, such as the 10 th transformer and the 11 th transformer, are merged into a cluster, at this time, the number of transformer clusters is changed from 20 to 19, whether 19/20 meets the condition that the preset occupation ratio is less than or equal to is judged, if so, clustering is stopped, if not, second clustering is continued, the result of the second clustering may be that the similarity between the 15 th transformer to be analyzed and the 11 th transformer is the largest, the 15 th transformer to be analyzed is merged into the cluster where the 10 th transformer to be analyzed and the 11 th transformer to be analyzed are located in the first clustering, and may also be that the similarity between the 15 th transformer to be analyzed and the 16 th transformer to be analyzed is the largest, combining the 15 th transformer to be analyzed and the 16 th transformer to be analyzed into a cluster, wherein the number of the transformers to be analyzed is changed from 19 to 18, judging whether 18/20 meets the condition that the ratio is less than or equal to the preset ratio, if so, stopping clustering, and if not, continuing clustering.
And 204, normalizing the second basic parameter.
In the embodiment of the present application, the second basic parameters include: h2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge in the transformer oil are respectively marked as b1～b9In order to eliminate the difference caused by different indexes, the second substrate parameter in each cluster, namely the on-line monitoring data y of the transformer to be analyzedi＝{bi1,bi2,...,bi9Respectively carrying out normalization treatment, wherein the normalization treatment is as follows:
wherein, yiOn-line monitoring data for the ith transformer to be analyzed, bijIs j type online monitoring data of ith transformer, n is the number of transformers in the cluster, b'ijAnd j-th class online monitoring data of the ith transformer to be analyzed after normalization processing is represented.
And step 205, calculating the distance between every two transformers to be analyzed in the same cluster according to a preset distance calculation formula.
Further, the preset distance calculation formula is as follows:
wherein d isijIs Euclidean distance, b 'of transformer i and transformer j'ikThe data is the k-th class online monitoring data of the ith transformer after normalization processing.
And step 206, judging that the transformer i to be analyzed is abnormal if the distance between the transformer i to be analyzed and the rest of the analysis transformers in the cluster in which the transformer i to be analyzed is located is greater than or equal to the total number of distance thresholds and is larger than or equal to the occupation ratio threshold of each cluster.
Further, the duty ratio threshold is: 80 percent.
It should be noted that, in this embodiment of the present application, the occupancy threshold is set to 80%, and for a transformer i to be analyzed in a certain cluster, if the number of transformers to be analyzed in the cluster, whose distance from the transformer i to be analyzed is greater than the distance threshold, exceeds 80% of the number n of transformers in the cluster, the transformer i to be analyzed is considered to be abnormal, otherwise, the transformer i to be analyzed is considered to be normal.
According to the transformer abnormity detection method based on cluster management, transformers with similar account parameters and working condition data are divided into the same transformer cluster by adopting a hierarchical clustering algorithm, each cluster transformer based on the transformer abnormity detection method is in a similar state, the difference of equipment in the cluster is known through mutual comparison of transformer state monitoring data in the same cluster, which transformer is in an abnormal state can be rapidly judged, and the abnormity detection accuracy is high.
According to the cluster management-based transformer abnormity detection method provided by the embodiment of the application, the transformers in the same cluster are used as a reference, the states of the transformers are judged through mutual comparison, the abnormity of the transformers can be recognized in the early stage of transformer fault occurrence, and the cluster management-based transformer abnormity detection method is significant for guaranteeing safe and stable operation of the transformers.
According to the transformer abnormity detection method based on cluster management, the concept of cluster management is introduced into transformer abnormity detection, similar transformers are grouped together to form transformer clusters, and long-term supervision of the transformers is facilitated.
For easy understanding, please refer to fig. 3, an embodiment of the present application provides a transformer abnormality detection apparatus based on cluster management, including:
an obtaining module 301, configured to use each transformer to be analyzed in the first number of transformers to be analyzed as an initial transformer cluster, and obtain a first basic parameter of each initial transformer cluster, where the first basic parameter includes: the transformer comprises a transformer manufacturer, the average temperature and humidity of a service place, the rated power of the transformer, the rated voltage of the transformer and the service duration.
The clustering module 302 is configured to calculate a first similarity between every two transformer clusters according to a similarity calculation formula based on a first basic parameter, perform hierarchical clustering on the initial transformer clusters to obtain a plurality of clustered clusters, and stop clustering until a ratio of a number of the clustered clusters to a total number of the non-clustered initial transformer clusters to the first number is less than or equal to a preset ratio.
The judging module 303 is configured to perform a second basic parameter comparison on the transformers to be analyzed in the cluster, and judge whether the transformers to be analyzed are abnormal, where the second basic parameter includes: the transformer oil comprises dissolved gases H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge.
The clustering module 302 specifically includes: a first clustering module 3021 and a second clustering module 3022.
The first clustering module 3021 is configured to calculate a first similarity between every two initial transformer clusters according to a similarity calculation formula based on the first basic parameter, and merge the first initial transformer cluster with the largest first similarity and the second initial transformer cluster into a cluster.
The second clustering module 3022 is configured to calculate a first ratio of the sum of the number of the clustered clusters and the number of the non-clustered initial transformer clusters to the first number, stop clustering if the first ratio is less than or equal to a preset ratio, otherwise continue clustering the initial transformer clusters to obtain a plurality of clustered clusters, determine a second ratio of the sum of the number of the clustered clusters and the number of the non-clustered initial transformer clusters to the first number, and stop clustering if the second ratio is less than or equal to the preset ratio.
The determining module 303 specifically includes: a normalization module 3031, a distance module 3032 and a detection module 3033;
a normalization module 3031, configured to perform normalization processing on the second basic parameter;
a distance module 3032, configured to calculate a distance between every two transformers to be analyzed in the same cluster according to a preset distance calculation formula;
the detection module 3033 is configured to determine that the transformer i to be analyzed is abnormal if the distance between the transformer i to be analyzed and the remaining transformers in the cluster where the transformer i to be analyzed is located is greater than or equal to the total number of distance thresholds and is greater than or equal to the percentage threshold of each cluster.
Further, the similarity calculation formula is:
wherein S isijThe coefficient of the levan of transformer i and transformer j, SijkFor transformer i and transformer j at data akA value ofkIs a first basic parameter, WijkAs a weighted variable, if data akIs a binary variable, 1-1 pair time SijkOther pairings S1ijk0; 0-0 pairing time WijkWhen the other is matched, W is equal to 0ijkIf data a is 1kTaking 1 when the data of the two transformers are the same as the sequence variable, and otherwise, taking 0; if the data akIs a numerical variable, Sijk＝1-|aik-ajk|/RkWherein a isikAnd ajkThe variable a is respectively the transformer i and the transformer jkValue of (A), RkIs a variable akThe overall distance of (a).
Further, the preset ratio is as follows: 10 percent.
Further, the preset distance calculation formula is as follows:
wherein d isijIs Euclidean distance, b 'of transformer i and transformer j'ikThe data is the k-th class online monitoring data of the ith transformer after normalization processing.
Further, the duty ratio threshold is: 80 percent.
The embodiment of the application provides transformer abnormity detection equipment based on cluster management, and the equipment comprises a processor and a memory:
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is configured to execute the cluster management-based transformer anomaly detection method in the foregoing embodiments according to instructions in the program code.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (6)
1. A transformer abnormity detection method based on cluster management is characterized by comprising the following steps:
taking each transformer to be analyzed in a first number of transformers to be analyzed as an initial transformer cluster, and acquiring a first basic parameter of each initial transformer cluster, wherein the first basic parameter comprises: the transformer comprises a transformer manufacturer, average temperature and humidity of a service place, rated power of a transformer, rated voltage of the transformer and service duration;
based on the first basic parameter, calculating first similarity of every two initial transformer clusters according to a similarity calculation formula, performing hierarchical clustering on the initial transformer clusters to obtain a plurality of clustering clusters, and stopping clustering until the ratio of the number of the clustering clusters to the sum of the number of the non-clustered initial transformer clusters to the first number is less than or equal to a preset ratio, wherein the method specifically comprises the following steps: calculating first similarity of every two initial transformer clusters according to a similarity calculation formula based on the first basic parameter, merging the first initial transformer cluster with the maximum first similarity and the second initial transformer cluster into a cluster, calculating a first ratio of the sum of the number of the cluster clusters and the number of the non-clustered initial transformer clusters to the first number, stopping clustering if the first ratio is smaller than or equal to a preset ratio, otherwise, continuing clustering the initial transformer clusters to obtain a plurality of cluster clusters, judging a second ratio of the sum of the number of the cluster clusters and the number of the non-clustered initial transformer clusters to the first number, and stopping clustering if the second ratio is smaller than or equal to the preset ratio;
comparing second basic parameters of the transformers to be analyzed in the clustering cluster, and judging whether the transformers to be analyzed are abnormal, wherein the second basic parameters comprise: dissolved gases in transformer oil, such as H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge, specifically comprise: normalizing the second basic parameter, calculating the distance between every two transformers to be analyzed in the same clustering group according to a preset distance calculation formula, and judging that the transformer i to be analyzed is abnormal if the distance between the rest transformers to be analyzed and the transformer i to be analyzed in the clustering group in which the transformer i to be analyzed is located is greater than or equal to the total number of distance thresholds and exceeds the ratio threshold of the number of transformers in the clustering group;
the similarity calculation formula is as follows:
wherein S isijThe coefficient of the levan of transformer i and transformer j, SijkFor transformer i and transformer j at data akA value ofkIs a first basic parameter, WijkAs a weighted variable, if data akIs a binary variable, 1-1 pair time SijkOther pairings S1ijk0; 0-0 pairing time WijkWhen the other is matched, W is equal to 0ijkIf data a is 1kAs order variable, two transformer data akSame as Sijk1, otherwise Sijk0; if the data akIs a numerical variable, Sijk＝1-|aik-ajk|/RkWhich isIn (a)ikAnd ajkThe variable a is respectively the transformer i and the transformer jkValue of (A), RkIs a variable akThe overall distance of (a).
2. The cluster management-based transformer abnormality detection method according to claim 1, wherein the preset ratio is: 10 percent.
3. The cluster management-based transformer abnormality detection method according to claim 1, wherein the preset distance calculation formula is:
wherein d isijIs Euclidean distance, b 'of transformer i and transformer j'ikThe data is the k-th class online monitoring data of the ith transformer after normalization processing.
4. The cluster-management-based transformer abnormality detection method according to claim 1, wherein the duty threshold is: 80 percent.
5. A transformer abnormity detection device based on cluster management is characterized by comprising:
an obtaining module, configured to use each transformer to be analyzed in a first number of transformers to be analyzed as an initial transformer cluster, and obtain a first basic parameter of each initial transformer cluster, where the first basic parameter includes: the transformer comprises a transformer manufacturer, average temperature and humidity of a service place, rated power of a transformer, rated voltage of the transformer and service duration;
the clustering module is used for calculating first similarity of every two initial transformer clusters according to a similarity calculation formula based on the first basic parameters, carrying out hierarchical clustering on the initial transformer clusters to obtain a plurality of clustering clusters, and stopping clustering until the ratio of the sum of the number of the clustering clusters and the number of the non-clustered initial transformer clusters to the first quantity is less than or equal to a preset ratio;
the judgment module is used for comparing second basic parameters of the transformers to be analyzed in the clustering cluster, and judging whether the transformers to be analyzed are abnormal or not, wherein the second basic parameters comprise: dissolved gases in transformer oil H2, CH4, C2H2, C2H4, C2H6, CO2, oil temperature and partial discharge;
the clustering module specifically comprises: the device comprises a first clustering module and a second clustering module;
the first clustering module is used for calculating first similarity of every two initial transformer clusters according to a similarity calculation formula based on the first basic parameter, and merging the first initial transformer cluster with the maximum first similarity and the second initial transformer cluster into a clustering cluster;
the second clustering module is used for calculating a first ratio of the sum of the number of the clustering clusters and the number of the initial transformer clusters which are not clustered to the first number, stopping clustering if the first ratio is less than or equal to a preset ratio, otherwise, continuing clustering the initial transformer clusters to obtain a plurality of clustering clusters, judging a second ratio of the sum of the number of the clustering clusters and the number of the initial transformer clusters which are not clustered to the first number, and stopping clustering if the second ratio is less than or equal to the preset ratio;
the judging module specifically comprises: the device comprises a normalization module, a distance module and a detection module;
the normalization module is used for performing normalization processing on the second basic parameter;
the distance module is used for calculating the distance between every two transformers to be analyzed in the same clustering cluster according to a preset distance calculation formula;
the detection module is used for judging that any transformer i to be analyzed in each cluster is abnormal if the distance between the rest transformers to be analyzed and the transformer i to be analyzed in the cluster where the transformer i to be analyzed is located is larger than or equal to the total number of distance thresholds and exceeds the ratio threshold of the number of the clustered transformers;
the similarity calculation formula is as follows:
wherein S isijThe coefficient of the levan of transformer i and transformer j, SijkFor transformer i and transformer j at data akA value ofkIs a first basic parameter, WijkAs a weighted variable, if data akIs a binary variable, 1-1 pair time SijkOther pairings S1ijk0; 0-0 pairing time WijkWhen the other is matched, W is equal to 0ijkIf data a is 1kAs order variable, two transformer data akSame as Sijk1, otherwise Sijk0; if the data akIs a numerical variable, Sijk＝1-|aik-ajk|/RkWherein a isikAnd ajkThe variable a is respectively the transformer i and the transformer jkValue of (A), RkIs a variable akThe overall distance of (a).
6. A cluster management based transformer anomaly detection device, the device comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the cluster management based transformer anomaly detection method according to any one of claims 1-4 according to instructions in the program code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811475724.6A CN109374063B (en) | 2018-12-04 | 2018-12-04 | Cluster management-based transformer anomaly detection method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811475724.6A CN109374063B (en) | 2018-12-04 | 2018-12-04 | Cluster management-based transformer anomaly detection method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109374063A CN109374063A (en) | 2019-02-22 |
| CN109374063B true CN109374063B (en) | 2021-04-23 |
Family
ID=65375738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811475724.6A Active CN109374063B (en) | 2018-12-04 | 2018-12-04 | Cluster management-based transformer anomaly detection method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109374063B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110161382B (en) * | 2019-04-30 | 2022-06-10 | 国网江苏省电力有限公司电力科学研究院 | Method and device for judging whether transformer needs power failure test or not |
| CN113826127A (en) * | 2019-05-23 | 2021-12-21 | 西门子股份公司 | Method and device for evaluating health state of transformer and storage medium |
| CN113077020B (en) * | 2021-06-07 | 2021-08-24 | 广东电网有限责任公司湛江供电局 | Transformer cluster management method and system |
| CN113625058A (en) * | 2021-08-13 | 2021-11-09 | 云南电网有限责任公司电力科学研究院 | Early warning method and system for monitoring transformer bushing based on abnormal point group |
| CN113791300A (en) * | 2021-11-15 | 2021-12-14 | 广东电网有限责任公司东莞供电局 | Charging gun state monitoring method and system for charging station |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2714091B2 (en) * | 1989-01-09 | 1998-02-16 | 株式会社日立製作所 | Field instrument |
| JP3002328B2 (en) * | 1992-05-28 | 2000-01-24 | 株式会社日立製作所 | Ultrasonic wave transmitter |
| CN105871634B (en) * | 2016-06-01 | 2019-02-15 | 北京蓝海讯通科技股份有限公司 | Detect the method for cluster exception and the system of application, management cluster |
| CN106338673A (en) * | 2016-09-29 | 2017-01-18 | 国网山东省电力公司电力科学研究院 | Transformer winding fault characteristic parameter extraction method |
| CN106845728B (en) * | 2017-02-14 | 2020-11-06 | 北京邮电大学 | Method and device for predicting defects of power transformer |
| CN108629528A (en) * | 2018-06-20 | 2018-10-09 | 国网江苏省电力有限公司电力科学研究院 | Quality of Transformer problem analysis method based on Apriori algorithm |
-
2018
- 2018-12-04 CN CN201811475724.6A patent/CN109374063B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109374063A (en) | 2019-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109374063B (en) | Cluster management-based transformer anomaly detection method, device and equipment | |
| CN112162878B (en) | Database fault discovery method and device, electronic equipment and storage medium | |
| Ahmed et al. | Similarity analysis of industrial alarm flood data | |
| CN108173670A (en) | The method and apparatus for detecting network | |
| CN111064614A (en) | Fault root cause positioning method, device, equipment and storage medium | |
| CN111475680A (en) | Method, device, equipment and storage medium for detecting abnormal high-density subgraph | |
| CN111178396A (en) | Method and device for identifying abnormal electricity consumption user | |
| CN111309565B (en) | Alarm processing method and device, electronic equipment and computer readable storage medium | |
| CN106204335A (en) | A kind of electricity price performs abnormality judgment method, Apparatus and system | |
| CN112650200B (en) | Method and device for diagnosing plant station equipment faults | |
| CN115638875B (en) | Power plant equipment fault diagnosis method and system based on map analysis | |
| CN111722952A (en) | Fault analysis method, system, equipment and storage medium of business system | |
| EP2963552B1 (en) | System analysis device and system analysis method | |
| CN115796708B (en) | Big data intelligent quality inspection method, system and medium for engineering construction | |
| CN113125903A (en) | Line loss anomaly detection method, device, equipment and computer-readable storage medium | |
| CN112286771A (en) | Alarm method for monitoring global resources | |
| CN112560940A (en) | Power utilization abnormity detection method, device, equipment and storage medium | |
| CN109784403B (en) | Method for identifying risk equipment and related equipment | |
| KR102150622B1 (en) | System and method for intelligent equipment abnormal symptom proactive detection | |
| CN113255096A (en) | High-loss line abnormal distribution area positioning method and system based on forward stepwise regression | |
| CN117614978A (en) | Information security communication management system for digital workshop | |
| CN117312611A (en) | Rapid positioning and diagnosing method and related device for power faults | |
| CN117170915A (en) | Data center equipment fault prediction method and device and computer equipment | |
| CN116714469A (en) | Charging pile health monitoring method, device, terminal and storage medium | |
| CN116401137A (en) | Core particle health state prediction method and device, electronic equipment and storage medium |
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 |