CN112381130A - Cluster analysis-based power distribution room multivariate data anomaly detection method - Google Patents
Cluster analysis-based power distribution room multivariate data anomaly detection method Download PDFInfo
- Publication number
- CN112381130A CN112381130A CN202011246416.3A CN202011246416A CN112381130A CN 112381130 A CN112381130 A CN 112381130A CN 202011246416 A CN202011246416 A CN 202011246416A CN 112381130 A CN112381130 A CN 112381130A
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- power distribution
- distribution room
- judging
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 14
- 238000007621 cluster analysis Methods 0.000 title claims description 9
- 230000002159 abnormal effect Effects 0.000 claims abstract description 37
- 238000012544 monitoring process Methods 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims 1
- 238000007689 inspection Methods 0.000 description 10
- 238000012423 maintenance Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a clustering analysis-based power distribution room multivariate data anomaly detection method, which comprises the following steps of: step 1, collecting normal monitoring data samples of a power distribution room, and standardizing the data samples; step 2, generating a normal clustering cluster for the standardized data by adopting a clustering algorithm; step 3, collecting monitoring data of the power distribution room in real time, and applying a time sliding window model to the real-time monitoring data; step 4, obtaining a candidate abnormal data set D corresponding to each time sliding window model; step 5, judging a data point D in the candidate abnormal data set D to judge whether the data point D belongs to a normal cluster; step 6.1, if the data belongs to the data, judging the next data point d + 1; step 6.21, if the data does not belong to the abnormal data set, obtaining an abnormal data point a, and adding the data point a into an abnormal data set Q; and 6.22, judging the abnormal mode of the abnormal data point a. The invention can monitor the abnormal state of the power equipment according to the multivariate data collected on line.
Description
Technical Field
The invention relates to a clustering analysis-based power distribution room multivariate data anomaly detection method used in the field of automatic monitoring of smart power grids.
Background
Monitoring of the operating state of the electrical equipment is critical to ensure safe operation of the power grid. At present, a power grid company mainly adopts a manual inspection and live detection mode to inspect power equipment. However, this approach has two problems: 1) the manual inspection has large workload, low efficiency and high cost, which leads to heavy workload of inspection personnel and large inspection pressure, and the contradiction between the rapid increase of the power grid scale and the configuration of equipment operation and maintenance personnel is increasingly prominent 2) the manual inspection has inspection blind areas, and the operation and maintenance personnel can not realize all-weather, all-time and all-round inspection. In recent years, in order to solve the problems of operation inspection of a power distribution room, an online monitoring system and an inspection robot are researched and applied more, but multivariate data obtained by online monitoring and collection are difficult to be effectively utilized, only unrelated data sets can be formed, and the online monitoring system and the inspection robot cannot be practically applied to state monitoring and state prediction of power equipment.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a clustering analysis-based power distribution room multivariate data anomaly detection method which can monitor the state anomaly of power equipment according to online collected multivariate data.
One technical scheme for achieving the above purpose is as follows: a power distribution room multivariate data anomaly detection method based on cluster analysis comprises the following steps:
step 1, collecting normal monitoring data samples of a power distribution room, and standardizing the data samples;
step 2, generating a normal clustering cluster for the standardized data by adopting a clustering algorithm;
step 3, collecting monitoring data of the power distribution room in real time, and applying a time sliding window model to the real-time monitoring data;
step 4, obtaining a candidate abnormal data set D corresponding to each time sliding window model;
step 5, judging a data point D in the candidate abnormal data set D to judge whether the data point D belongs to a normal cluster;
step 6.1, if the data belongs to the data, judging the next data point d + 1;
step 6.21, if the data does not belong to the abnormal data set, obtaining an abnormal data point a, and adding the data point a into an abnormal data set Q;
and 6.22, judging the abnormal mode of the abnormal data point a.
Furthermore, the data types of the power distribution room normal monitoring data samples are partial discharge signals, infrared signals, temperature data and humidity data respectively.
Further, the method for judging the abnormal pattern of the abnormal data point a in step 6.22 is manual judgment or machine learning judgment by introducing an expert database.
The invention relates to a power distribution room multivariate data anomaly detection method based on cluster analysis, which mainly utilizes a time sequence sliding window to establish a data set for multidimensional online monitoring data flow, establishes an anomaly detection model of multivariate characteristic quantity data points based on an unsupervised k-means clustering method to judge whether anomaly occurs or not, realizes anomaly detection of multidimensional state quantity, and identifies an anomaly mode and occurrence time of the multidimensional state quantity. The integrated sensing terminal is implanted into the algorithm, so that not only can the abnormal changes of the level transition and trend of the state parameters such as the temperature, the partial discharge and the sound of the equipment be detected, but also the abnormal changes of the correlation among the state quantities such as the ambient temperature, the humidity, the temperature, the sound and the partial discharge of the equipment can be detected.
Drawings
Fig. 1 is a flowchart of a power distribution room multivariate data anomaly detection method based on cluster analysis according to the present invention.
Detailed Description
In order to better understand the technical solution of the present invention, the following detailed description is made by specific examples:
referring to fig. 1, a power distribution room multivariate data anomaly detection method based on cluster analysis is characterized by comprising the following steps:
step 1, collecting normal monitoring data samples of a power distribution room, and standardizing the data samples;
step 2, generating a normal clustering cluster for the standardized data by adopting a clustering algorithm;
step 3, collecting monitoring data of the power distribution room in real time, and applying a time sliding window model to the real-time monitoring data;
step 4, obtaining a candidate abnormal data set D corresponding to each time sliding window model;
step 5, judging a data point D in the candidate abnormal data set D to judge whether the data point D belongs to a normal cluster;
step 6.1, if the data belongs to the data, judging the next data point d + 1;
step 6.21, if the data does not belong to the abnormal data set, obtaining an abnormal data point a, and adding the data point a into an abnormal data set Q;
and 6.22, judging the abnormal mode of the abnormal data point a. The method for judging the abnormal mode of the abnormal data point a is manual judgment or machine learning judgment by introducing an expert database.
The data types of the normal monitoring data samples of the power distribution room are partial discharge signals, infrared signals, temperature data and humidity data.
It should be understood by those skilled in the art that the above embodiments are only for illustrating the present invention and are not to be used as a limitation of the present invention, and that changes and modifications to the above described embodiments are within the scope of the claims of the present invention as long as they are within the spirit and scope of the present invention.
Claims (3)
1. A power distribution room multivariate data anomaly detection method based on cluster analysis is characterized by comprising the following steps:
step 1, collecting normal monitoring data samples of a power distribution room, and standardizing the data samples;
step 2, generating a normal clustering cluster for the standardized data by adopting a clustering algorithm;
step 3, collecting monitoring data of the power distribution room in real time, and applying a time sliding window model to the real-time monitoring data;
step 4, obtaining a candidate abnormal data set D corresponding to each time sliding window model;
step 5, judging a data point D in the candidate abnormal data set D to judge whether the data point D belongs to a normal cluster;
step 6.1, if the data belongs to the data, judging the next data point d + 1;
step 6.21, if the data does not belong to the abnormal data set, obtaining an abnormal data point a, and adding the data point a into an abnormal data set Q;
and 6.22, judging the abnormal mode of the abnormal data point a.
2. The cluster analysis-based power distribution room multivariate data anomaly detection method according to claim 1, wherein the data types of the power distribution room normal monitoring data samples are partial discharge signals, infrared signals, temperature data and humidity data respectively.
3. The method for detecting the multivariate data abnormality of the power distribution room based on the cluster analysis as claimed in claim 1, wherein the method for judging the abnormal pattern of the abnormal data points a in step 6.22 is manual judgment or machine learning judgment with an expert database.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011246416.3A CN112381130A (en) | 2020-11-10 | 2020-11-10 | Cluster analysis-based power distribution room multivariate data anomaly detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011246416.3A CN112381130A (en) | 2020-11-10 | 2020-11-10 | Cluster analysis-based power distribution room multivariate data anomaly detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112381130A true CN112381130A (en) | 2021-02-19 |
Family
ID=74578946
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011246416.3A Pending CN112381130A (en) | 2020-11-10 | 2020-11-10 | Cluster analysis-based power distribution room multivariate data anomaly detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112381130A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112990329A (en) * | 2021-03-26 | 2021-06-18 | 清华大学 | System abnormity diagnosis method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101908065A (en) * | 2010-07-27 | 2010-12-08 | 浙江大学 | On-line attribute abnormal point detecting method for supporting dynamic update |
CN105512474A (en) * | 2015-12-02 | 2016-04-20 | 国网山东省电力公司电力科学研究院 | Transformer state monitoring data anomaly detection method |
CN108491861A (en) * | 2018-02-24 | 2018-09-04 | 全球能源互联网研究院有限公司 | Power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion and device |
CN111582406A (en) * | 2020-05-31 | 2020-08-25 | 重庆大学 | Power equipment state monitoring data clustering method and system |
-
2020
- 2020-11-10 CN CN202011246416.3A patent/CN112381130A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101908065A (en) * | 2010-07-27 | 2010-12-08 | 浙江大学 | On-line attribute abnormal point detecting method for supporting dynamic update |
CN105512474A (en) * | 2015-12-02 | 2016-04-20 | 国网山东省电力公司电力科学研究院 | Transformer state monitoring data anomaly detection method |
CN108491861A (en) * | 2018-02-24 | 2018-09-04 | 全球能源互联网研究院有限公司 | Power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion and device |
CN111582406A (en) * | 2020-05-31 | 2020-08-25 | 重庆大学 | Power equipment state monitoring data clustering method and system |
Non-Patent Citations (1)
Title |
---|
严英杰 等: "基于滑动窗口和聚类算法的变压器状态异常检测", 《高电压技术》, pages 262 - 263 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112990329A (en) * | 2021-03-26 | 2021-06-18 | 清华大学 | System abnormity diagnosis method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112179691B (en) | Mechanical equipment running state abnormity detection system and method based on counterstudy strategy | |
CN108197817A (en) | A kind of method of the non-intrusion type load transient state monitoring based on big data | |
CN112462736B (en) | Wind turbine generator fault diagnosis method based on data analysis | |
CN104330675A (en) | Multivariate time series based power transformation equipment online monitoring and analysis system and method thereof | |
CN116028887B (en) | Analysis method of continuous industrial production data | |
CN113177646A (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
CN113884837B (en) | Cable partial discharge online monitoring and analyzing system and analyzing method | |
CN103529337B (en) | The recognition methods of nonlinear correlation relation between equipment failure and electric quantity information | |
CN112381130A (en) | Cluster analysis-based power distribution room multivariate data anomaly detection method | |
CN117743794A (en) | Distributed photovoltaic power station fault diagnosis and efficiency loss evaluation system | |
CN117235617A (en) | ML-RFKNN-based photovoltaic array fault diagnosis method in sand and dust weather | |
CN113671287B (en) | Intelligent detection method, system and readable storage medium for power grid automation terminal | |
CN115146727A (en) | Intelligent power utilization system fault detection method and system | |
CN113591909A (en) | Abnormality detection method, abnormality detection device, and storage medium for power system | |
CN112560889A (en) | Power load identification method | |
CN115711206B (en) | Wind driven generator blade icing state monitoring system based on clustering weight | |
CN117951633B (en) | Photovoltaic power generation equipment fault diagnosis method and system | |
CN111157812A (en) | Power equipment fault monitoring method based on electromagnetic induction | |
CN117111661B (en) | Centralized control system and method for production workshops | |
CN118069470B (en) | Equipment state real-time sensing and on-line monitoring system for comprehensive energy device | |
CN116819158B (en) | Intelligent monitoring system and method for current of isolating switch motor | |
CN117932358A (en) | Intelligent remote electric field fault diagnosis method and system | |
CN118169500A (en) | Power grid fault recognition system based on big data | |
CN116454839A (en) | Insulation detection grounding control method | |
ZHOU et al. | ABNORMAL ENERGY CONSUMPTION MODE DETECTION OF OFFICE BUILDING AIR CONDITIONING SYSTEM BASED ON INFORMATION ENTROPY |
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 |