CN112198472B - Online remote verification method and system for partial discharge intelligent sensor - Google Patents
Online remote verification method and system for partial discharge intelligent sensor Download PDFInfo
- Publication number
- CN112198472B CN112198472B CN202011069872.5A CN202011069872A CN112198472B CN 112198472 B CN112198472 B CN 112198472B CN 202011069872 A CN202011069872 A CN 202011069872A CN 112198472 B CN112198472 B CN 112198472B
- Authority
- CN
- China
- Prior art keywords
- intelligent
- group
- sensors
- sensor
- cluster
- 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
- 238000012795 verification Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000005259 measurement Methods 0.000 claims abstract description 21
- 239000013598 vector Substances 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/005—Calibrating; Standards or reference devices, e.g. voltage or resistance standards, "golden" references
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention relates to an online remote verification method and system for a partial discharge intelligent sensor, wherein the method comprises the following steps: grouping the intelligent sensors to be checked according to the distance; collecting real-time measurement data of each intelligent sensor in a grouping way; and respectively carrying out clustering operation based on mean shift on the real-time measurement data of each intelligent sensor in each group, and carrying out fault discrimination on each intelligent sensor in each group according to a clustering result. Compared with the prior art, the invention has the advantages of effectively distinguishing faults and the like.
Description
Technical Field
The invention relates to a sensor verification method in the electric power Internet of things, in particular to an online remote verification method and system for a partial discharge intelligent sensor.
Background
The construction of modern electric power internet of things provides more convenient, intelligent, safe and economical electric energy supply for people. However, in order to ensure the intellectualization of the power grid, a large number of sensors run in the electric power internet of things to collect environmental variables in real time, so that the performance of a plurality of intelligent sensing devices which are additionally installed on the site is inevitably uneven. From the acquisition source, the state data of the power equipment acquired by the device is not necessarily completely accurate due to the design principle or quality stability of the sensing device, poor field anti-interference capability and other reasons. From the perspective of signal transmission, it is difficult to ensure that data is not distorted in the upward transmission process due to non-uniform signal transmission modes and interface protocols, non-standard data and the like. After the intelligent sensing devices are operated on site for a long time, the performance of the intelligent sensing devices is affected by various reasons, such as vibration, temperature, humidity, large impact signals inside and outside the equipment and the like, which can damage the characteristics of the sensors, and on-line verification of the sensing devices is difficult to carry out on site. In addition, along with the construction of ubiquitous electric power internet of things, the quantity of sensing devices will rise rapidly, if sensing equipment which does not reach the standard is put into operation, manpower and material resources are consumed to operate and maintain, and the sensing equipment cannot be lost.
The current related technical departments at home and abroad are more traditional in checking the sensor, and the method of carrying out laboratory offline checking by leading to related authorities is adopted for various types of electrified detection and online monitoring sensors, so that the 'gateway' of the device quality can be ensured to a certain extent. But the problem of subsequent temporary and periodic verification of a large number of different types of intelligent sensing devices which have been put into operation on site is a problem which needs to be considered seriously. The performance of the intelligent sensing devices can be affected by various factors on site in the operation process, such as vibration, temperature, humidity, large impact signals inside and outside the equipment and the like, which can affect the characteristics of the sensors, and the traditional laboratory off-line verification method is not suitable for on-site on-line verification. Therefore, how to scientifically and effectively check the performance indexes such as the data loss rate, the sensitivity, the stability and the like of the sensor in operation has a vital effect on ensuring the safe and reliable operation of equipment.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide an online remote verification method and system for a partial discharge intelligent sensor, which can effectively judge faults.
The aim of the invention can be achieved by the following technical scheme:
an online remote verification method for a partial discharge intelligent sensor comprises the following steps:
grouping the intelligent sensors to be checked according to the distance;
collecting real-time measurement data of each intelligent sensor in a grouping way;
and respectively carrying out clustering operation based on mean shift on the real-time measurement data of each intelligent sensor in each group, and carrying out fault discrimination on each intelligent sensor in each group according to a clustering result.
Further, the fault discrimination for each intelligent sensor in each group specifically includes the following steps:
calculating the characteristic value of the sensor data of each intelligent sensor in the group and forming a characteristic vector sample;
performing clustering operation based on mean shift on the feature vector samples;
taking one cluster classification cluster with the largest sample number as a standard cluster, and calculating the distance between the center coordinates of the rest clusters and the center coordinates of the standard cluster;
judging whether the distance is larger than a critical distance, if so, judging that all intelligent sensors in the corresponding cluster have faults.
Further, the mean shift-based clustering operation comprises cluster center searching, similar data cluster merging and small data cluster merging.
Further, the kernel function formula adopted by the cluster center search is as follows:
wherein: g (·) is the negative derivative of the kernel function, x i Gao Weiqiu S h The point included in (a) k is S h The number of the included points, h is the radius of Gao Weiqiu, m k (x) Gao Weiqiu S h An offset mean vector for the set of points involved.
Further, the real-time measurement data is stored in an edge computing platform, and a computer program for executing the step of performing fault discrimination on each intelligent sensor in each group is stored in the edge computing platform.
Further, the edge computing platforms are provided with a plurality of intelligent sensors, and the intelligent sensors to be checked are divided into a plurality of groups according to the distance between each intelligent sensor and each edge computing platform.
The invention also provides an online remote verification system of the partial discharge intelligent sensor, which is used for carrying out online verification on a plurality of intelligent sensors to be verified on the distribution equipment, and comprises a cloud platform server and a plurality of edge computing platforms, wherein,
the cloud platform server divides the intelligent sensors to be checked into a plurality of groups according to the distance between each intelligent sensor and each edge computing platform, and establishes corresponding connection between the intelligent sensors in the groups and the edge computing platform;
and collecting real-time measurement data of each intelligent sensor in the group by each edge computing platform, carrying out clustering operation based on mean shift on the real-time measurement data, and carrying out fault discrimination on each intelligent sensor in the group according to a clustering result.
Further, in the edge computing platform, performing fault discrimination on each intelligent sensor in each group specifically includes:
calculating the characteristic value of the sensor data of each intelligent sensor in the group and forming a characteristic vector sample;
performing clustering operation based on mean shift on the feature vector samples;
taking one cluster classification cluster with the largest sample number as a standard cluster, and calculating the distance between the center coordinates of the rest clusters and the center coordinates of the standard cluster;
judging whether the distance is larger than a critical distance, if so, judging that all intelligent sensors in the corresponding cluster have faults.
Further, the mean shift-based clustering operation comprises cluster center searching, similar data cluster merging and small data cluster merging.
Further, the kernel function formula adopted by the cluster center search is as follows:
wherein: g (·) is the negative derivative of the kernel function, x i Gao Weiqiu S h Middle bagContaining points, k being S h The number of the included points, h is the radius of Gao Weiqiu, m k (x) Gao Weiqiu S h An offset mean vector for the set of points involved.
In order to realize online remote verification of the partial discharge intelligent sensor, the invention provides a local discharge sensor edge calculation verification method based on mean shift clustering.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the intelligent sensors are grouped according to the distance, and the sensors in each group are checked in an online parallel manner in a grouping mode, so that the checking efficiency is effectively improved.
The invention clusters the data characteristic vector measured by the partial discharge sensor by using the density offset vector based on the mean value drift clustering algorithm, and can effectively distinguish the fault sensor.
The method adopted by the invention is compared with other clustering algorithms, and the fault sensor can be effectively judged.
Drawings
FIG. 1 is a diagram of a hardware communication architecture of the present invention;
fig. 2 is a schematic diagram of a verification process according to the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. The present embodiment is implemented on the premise of the technical scheme of the present invention, and a detailed implementation manner and a specific operation process are given, but the protection scope of the present invention is not limited to the following examples.
Example 1
The embodiment provides an online remote verification method for a partial discharge intelligent sensor, which comprises the following steps: grouping the intelligent sensors to be checked according to the distance; collecting real-time measurement data of each intelligent sensor in a grouping way; and respectively carrying out clustering operation based on mean shift on the real-time measurement data of each intelligent sensor in each group, and carrying out fault discrimination on each intelligent sensor in each group according to a clustering result.
As shown in fig. 2, the fault discrimination for each intelligent sensor in each group specifically includes the following steps:
1) And calculating the characteristic value of the sensor data of each intelligent sensor in the group and forming a characteristic vector sample.
Calculating the characteristic value X with certain probability distribution data measured by the partial discharge sensor 1 、X 2 ……X n . And forming the characteristic values into a vector with a dimension of n
2) And carrying out clustering operation based on mean shift on the feature vector samples.
And clustering the characteristic vectors of the partial discharge sensors by using a mean shift clustering model to find out fault sensors with outside dispersion. The model implements clustering through three steps: the cluster center searches, merges similar data clusters and merges small data clusters. First, a center point x is randomly selected from a feature space having N sample points, and Gao Weiqiu S having a radius h centered on the center point is calculated by a kernel function h Offset mean vector m of the contained point set k (x) The formula is as follows:
wherein: g (·) is the negative derivative of the kernel function, x i Gao Weiqiu S h The point included in (a) k is S h The number of points included in the image.
And (3) moving the center point to the place pointed by the mean value vector, and continuously iterating until the condition is met, wherein the center point is the center of the data cluster. The above steps are repeated until all sample points are classified as a certain data cluster. And then combining some data clusters with high similarity into a large data cluster. And finally, merging the small data clusters scattered around the large data cluster into the large data cluster with the highest similarity to the small data cluster, thereby completing the whole clustering process.
3) And taking one cluster classification cluster with the largest sample number as a standard cluster, and calculating the distance l between the center coordinates of the rest clusters and the center coordinates of the standard cluster.
4) Judging whether the distance L is larger than a critical distance L, if so, judging that all intelligent sensors in the corresponding cluster have faults. Wherein the selection of the critical distance L needs to be given by the experience of an expert and a large number of test results in combination with the operating environment of the device.
In this embodiment, the real-time measurement data is stored in an edge computing platform, and the edge computing platform stores a computer program for executing the step of performing the fault discrimination for each intelligent sensor in each group. The edge computing platforms are provided with a plurality of intelligent sensors, and the intelligent sensors to be checked are divided into a plurality of groups according to the distance between each intelligent sensor and each edge computing platform.
The method realizes remote online verification of the partial discharge sensor by using a mean shift clustering algorithm on the edge computing platform, has better robustness and effectiveness, and is suitable for application in a low-power consumption environment of the wireless Internet of things.
Example 2
The embodiment provides an online remote verification system for a partial discharge intelligent sensor, which is used for carrying out online verification on a plurality of intelligent sensors to be verified on power distribution equipment, as shown in fig. 1, and comprises a cloud platform server and a plurality of edge computing platforms, wherein the cloud platform server divides the intelligent sensors to be verified into a plurality of groups according to the distances between the intelligent sensors and the edge computing platforms, and establishes corresponding connection between the intelligent sensors in the groups and the edge computing platforms; and collecting real-time measurement data of each intelligent sensor in the group by each edge computing platform, carrying out clustering operation based on mean shift on the real-time measurement data, and carrying out fault discrimination on each intelligent sensor in the group according to a clustering result. For the intelligent partial discharge sensor installed on the power equipment, the verification system utilizes an edge computing platform to receive data information of a group of partial discharge sensors through an internet of things sink node, then utilizes a mean shift clustering algorithm to cluster partial discharge data measured by a plurality of sensors, and judges the partial discharge sensor with a fault, so that the function of online remote verification of the intelligent partial discharge sensor is achieved. The procedure is as in example 1.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (7)
1. An online remote verification method for a partial discharge intelligent sensor is characterized by comprising the following steps:
grouping the intelligent sensors to be checked according to the distance between the intelligent sensors and each edge computing platform, specifically, dividing the intelligent sensors to be checked into a plurality of groups according to the distance between each intelligent sensor and each edge computing platform, and checking the sensors in each group in an online parallel manner in a grouping mode;
collecting real-time measurement data of each intelligent sensor in groups, receiving the real-time measurement data of a group of adjacent intelligent sensors through the sink node of the Internet of things, and transmitting the real-time measurement data to an edge computing platform;
and respectively carrying out clustering operation based on mean shift on the real-time measurement data of each intelligent sensor in each group, and carrying out fault discrimination on each intelligent sensor in each group according to a clustering result, wherein the clustering operation based on mean shift comprises searching a clustering center, merging similar data clusters and merging small data clusters.
2. The online remote verification method of partial discharge intelligent sensors according to claim 1, wherein the fault discrimination of each intelligent sensor in each group specifically comprises the following steps:
calculating the characteristic value of the sensor data of each intelligent sensor in the group and forming a characteristic vector sample;
performing clustering operation based on mean shift on the feature vector samples;
taking one cluster classification cluster with the largest sample number as a standard cluster, and calculating the distance between the center coordinates of the rest clusters and the center coordinates of the standard cluster;
judging whether the distance is larger than a critical distance, if so, judging that all intelligent sensors in the corresponding cluster have faults.
3. The online remote verification method of the partial discharge intelligent sensor according to claim 1, wherein a kernel function formula adopted by the cluster center search is as follows:
wherein: g (·) is the negative derivative of the kernel function, x i Gao Weiqiu S h The point included in (a) k is S h The number of the included points, h is the radius of Gao Weiqiu, m k (x) Gao Weiqiu S h An offset mean vector for the set of points involved.
4. The online remote verification method of partial discharge intelligent sensors according to claim 2, wherein the real-time measurement data is stored in an edge computing platform having stored therein a computer program for performing the step of performing the fault discrimination for each intelligent sensor in each group.
5. An online remote verification system for a partial discharge intelligent sensor is characterized by being used for carrying out online verification on a plurality of intelligent sensors to be verified on power distribution equipment, comprising a cloud platform server and a plurality of edge computing platforms, wherein,
the cloud platform server divides the intelligent sensors to be verified into a plurality of groups according to the distance between each intelligent sensor and each edge computing platform, online and parallel verifies the sensors in each group in a grouping mode, establishes corresponding connection between the intelligent sensors in the group and the edge computing platform, and receives real-time measurement data of a group of adjacent intelligent sensors through an Internet of things sink node and transmits the real-time measurement data to the edge computing platform;
the edge computing platforms collect real-time measurement data of all intelligent sensors in the group, perform clustering operation based on mean shift on the real-time measurement data, and perform fault discrimination on all the intelligent sensors in the group according to clustering results, wherein the clustering operation based on mean shift comprises searching a clustering center, merging similar data clusters and merging small data clusters.
6. The online remote verification system of partial discharge intelligent sensors according to claim 5, wherein in the edge computing platform, performing fault discrimination on each intelligent sensor in each group specifically comprises:
calculating the characteristic value of the sensor data of each intelligent sensor in the group and forming a characteristic vector sample;
performing clustering operation based on mean shift on the feature vector samples;
taking one cluster classification cluster with the largest sample number as a standard cluster, and calculating the distance between the center coordinates of the rest clusters and the center coordinates of the standard cluster;
judging whether the distance is larger than a critical distance, if so, judging that all intelligent sensors in the corresponding cluster have faults.
7. The online remote verification system of a partial discharge intelligent sensor according to claim 5, wherein the kernel function formula adopted by the cluster center search is as follows:
wherein: g (·) is the negative derivative of the kernel function, x i Gao Weiqiu S h The point included in (a) k is S h The number of the included points, h is the radius of Gao Weiqiu, m k (x) Gao Weiqiu S h An offset mean vector for the set of points involved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011069872.5A CN112198472B (en) | 2020-09-29 | 2020-09-29 | Online remote verification method and system for partial discharge intelligent sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011069872.5A CN112198472B (en) | 2020-09-29 | 2020-09-29 | Online remote verification method and system for partial discharge intelligent sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112198472A CN112198472A (en) | 2021-01-08 |
| CN112198472B true CN112198472B (en) | 2023-11-07 |
Family
ID=74013025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011069872.5A Active CN112198472B (en) | 2020-09-29 | 2020-09-29 | Online remote verification method and system for partial discharge intelligent sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112198472B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113885419A (en) * | 2021-10-30 | 2022-01-04 | 大连腾屹信科技有限公司 | Tower crane safety monitoring system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894027A (en) * | 2016-03-31 | 2016-08-24 | 华北电力科学研究院有限责任公司 | Principal element degree of association sensor fault detection method and apparatus based on density clustering |
| CN107192565A (en) * | 2017-05-25 | 2017-09-22 | 南京康尼机电股份有限公司 | A kind of synchronization detecting method of subway vehicle door system exception operating mode and component degradation |
| CN109772753A (en) * | 2019-03-05 | 2019-05-21 | 中国科学院自动化研究所 | Power battery separation system and method |
| CN110394688A (en) * | 2019-09-02 | 2019-11-01 | 太原科技大学 | Conditions of machine tool monitoring method based on edge calculations |
| CN110889441A (en) * | 2019-11-19 | 2020-03-17 | 海南电网有限责任公司海南输变电检修分公司 | Distance and point density based substation equipment data anomaly identification method |
| CN111505434A (en) * | 2020-04-10 | 2020-08-07 | 国网浙江余姚市供电有限公司 | Method for identifying fault hidden danger of low-voltage distribution meter box line and meter box |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11527891B2 (en) * | 2018-12-20 | 2022-12-13 | The George Washington University | Smart sensor for online situational awareness in power grids |
-
2020
- 2020-09-29 CN CN202011069872.5A patent/CN112198472B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894027A (en) * | 2016-03-31 | 2016-08-24 | 华北电力科学研究院有限责任公司 | Principal element degree of association sensor fault detection method and apparatus based on density clustering |
| CN107192565A (en) * | 2017-05-25 | 2017-09-22 | 南京康尼机电股份有限公司 | A kind of synchronization detecting method of subway vehicle door system exception operating mode and component degradation |
| CN109772753A (en) * | 2019-03-05 | 2019-05-21 | 中国科学院自动化研究所 | Power battery separation system and method |
| CN110394688A (en) * | 2019-09-02 | 2019-11-01 | 太原科技大学 | Conditions of machine tool monitoring method based on edge calculations |
| CN110889441A (en) * | 2019-11-19 | 2020-03-17 | 海南电网有限责任公司海南输变电检修分公司 | Distance and point density based substation equipment data anomaly identification method |
| CN111505434A (en) * | 2020-04-10 | 2020-08-07 | 国网浙江余姚市供电有限公司 | Method for identifying fault hidden danger of low-voltage distribution meter box line and meter box |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112198472A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108601026B (en) | Perception data error attack detection method based on random sampling consistency | |
| CN112560981B (en) | Training method, device, apparatus, program, and storage medium for generating countermeasure model | |
| CN106814320B (en) | A kind of lithium iron phosphate dynamic battery Cycle life prediction system | |
| CN115542099B (en) | Online GIS partial discharge detection method and device | |
| CN115600513B (en) | Karst collapse monitoring early warning and prevention and control integrated informationized simulation research and judgment system | |
| CN110830946A (en) | Mixed type online data anomaly detection method | |
| CN107257351A (en) | One kind is based on grey LOF Traffic anomaly detections system and its detection method | |
| CN113340353B (en) | Monitoring method, equipment and medium for power transmission line | |
| CN113542241A (en) | Intrusion detection method and device based on CNN-BiGRU mixed model | |
| CN110889441A (en) | Distance and point density based substation equipment data anomaly identification method | |
| CN103400308B (en) | GIS equipment operational condition online test method and system | |
| CN114977176B (en) | Power load decomposition method, device, equipment and storage medium | |
| CN112198472B (en) | Online remote verification method and system for partial discharge intelligent sensor | |
| CN116050888A (en) | Method applied to intelligent high-voltage switch cabinet sensor health state assessment | |
| Ma et al. | Measurement error assessment for smart electricity meters under extreme natural environmental stresses | |
| CN113343123B (en) | Training method and detection method for generating confrontation multiple relation graph network | |
| Chen et al. | Insulator recognition method for distribution network overhead transmission lines based on modified yolov3 | |
| CN112949497B (en) | GIS partial discharge pattern recognition method based on improved generalized regression neural network | |
| CN116681186B (en) | Power quality analysis method and device based on intelligent terminal | |
| CN109341650B (en) | Unmanned aerial vehicle elevation error double-threshold correction method based on minimum detection cost | |
| CN114779098B (en) | State evaluation method and system for lithium ion battery | |
| Pan et al. | Study on intelligent anti–electricity stealing early-warning technology based on convolutional neural networks | |
| CN115619013A (en) | Multi-sensor information fusion fire prediction algorithm, system, electronic device and medium | |
| CN112418398A (en) | Safety monitoring method for power information equipment | |
| KR20180120413A (en) | System for processing and analyzing magnetotellurics monitoring data using deep learning algorithm |
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 |