CN114024370A - Ring main unit meter map identification method based on machine vision and edge calculation - Google Patents
Ring main unit meter map identification method based on machine vision and edge calculation Download PDFInfo
- Publication number
- CN114024370A CN114024370A CN202111422489.8A CN202111422489A CN114024370A CN 114024370 A CN114024370 A CN 114024370A CN 202111422489 A CN202111422489 A CN 202111422489A CN 114024370 A CN114024370 A CN 114024370A
- Authority
- CN
- China
- Prior art keywords
- module
- meter
- visible light
- main unit
- ring main
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Abstract
The utility model relates to the technical field of power industry ring main unit equipment, in particular to a ring main unit meter map identification method based on machine vision and edge calculation, which realizes the collection and identification of a meter map and the update and storage of sample data through a ring main unit meter identification device and a system cloud computing server background two-layer framework; the meter recognition device is provided with an AI acceleration module for local map recognition, communicates with the system background through the 5G module, continuously updates a system background sample database and improves map recognition efficiency. According to the method and the device, the system integration level and the interaction efficiency of the system are improved through visible light collection, image local intelligent recognition and 5G communication.
Description
Technical Field
The application relates to the technical field of power industry ring main unit equipment, in particular to a ring main unit meter map identification method based on machine vision and edge calculation.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Distribution fortune inspector need come the prejudgement equipment through the tour and the multidimension degree analysis to the looped netowrk cabinet and whether have the fault risk, nevertheless tour personnel and observe the vision of table meter, the angle is different, leads to the operation error ubiquitous, has influenced data analysis's the degree of accuracy greatly. Meanwhile, the inspection workload is huge and complex, a large amount of time is consumed for copying data and subsequently analyzing and processing the data, and the efficiency is greatly reduced.
Along with the application of mobile devices such as power inspection robots and unmanned aerial vehicles, the system can carry out inspection detection such as infrared temperature measurement on distribution network lines. And for the place of joining in marriage net looped netowrk cabinet multilayer arrangement, robot, unmanned aerial vehicle can't reach, and corresponding instrument reading can't automatic acquisition.
In the traditional meter map identification method, a map is uploaded to a system background server for identification and analysis through wireless communication, a large number of maps need to be uploaded in a short time, so that a large number of maps are transmitted back to the server, the pressure of the server and network bandwidth is increased, and the communication cost is greatly increased. The current meter recognition device is limited by a hardware platform to have limited capability of processing images, and has limited space for improving the analysis accuracy rate by only depending on a software algorithm, so that the current recognition accuracy rate cannot achieve the effect of reliable application.
Disclosure of Invention
The technical problem that this application will solve is: the method for identifying the looped network cabinet meter map overcomes the defects of the prior art, and based on machine vision and edge calculation, the problems that a traditional meter map identification method in the background art occupies a server and network bandwidth is large are solved, and meanwhile, the accuracy rate can be improved.
The technical scheme that this application solved the problem that prior art exists adopted is:
the application provides a looped netowrk cabinet table meter atlas recognition device based on machine vision and edge calculation, including looped netowrk cabinet table meter, platform, its characterized in that: the device also comprises a pointer identification device and a system cloud computing server background;
the pointer identification device comprises a visible light camera module, an AI acceleration module, a switch, a main processor module, a 5G module, a power management module and a storage module, wherein the visible light camera module is fixedly arranged on the platform and is used for collecting visible light maps at different time periods and different brightnesses; the AI acceleration module is used for processing and identifying visible light maps under different time brightness; the switch is used for receiving the signals collected by the field visible light camera module and transmitting the signals to the AI accelerating module; the main processor module is used for collecting, processing and storing meter data identified by the AI acceleration module and communicating with the system cloud computing server through the 5G module; the 5G module is used for communicating the ring main unit meter pointer identification device with a system background cloud computing server; the power supply management module is used for converting the alternating-current voltage into a voltage grade required by the operation of the looped network cabinet meter identification device; the storage module is used for storing the historical data of the ring main unit meter and the atlas sample database.
Preferably, the visible light camera module is fixedly mounted on the platform.
Preferably, the camera of the visible light camera module is over against the position of the ring main unit meter.
Preferably, the main processor module is an MCU.
Preferably, optical fiber communication is adopted between the visible light camera module and the switch, and between the switch and the AI acceleration module.
Preferably, the 5G module is in wireless communication with a system cloud computing server.
Preferably, the 5G module has a short message notification function.
A looped netowrk cabinet meter map recognition method based on machine vision and edge calculation is applied to the looped netowrk cabinet meter map recognition device based on machine vision and edge calculation, and comprises the following steps:
a: performing spectrum recognition on a plurality of ring main unit meters on site, acquiring visible light spectrums of meters at different time periods through a visible light camera module, and transmitting the acquired visible light spectrums to an AI acceleration module through a switch;
b: the AI acceleration module identifies and processes the visible light maps of the meters at different periods in the step A, compares the data with the data in the storage module through the main processor module, identifies the meter reading in situ through edge calculation, and then transmits the maps and the processing result to the main processor;
c: the main processor transmits the result of the edge calculation of the on-site AI acceleration module and the map data to a system cloud computing server background through the 5G module;
d: and the background of the cloud computing server intelligently analyzes the information received from the 5G module, forms a new sample database, sends the new sample database to the main processor module through the 5G module, and stores the new sample database in the storage module.
Preferably, in the step a, the visible light spectrum of the lower meter at different time periods is collected through the visible light camera module, and the different time periods can be set as required.
Preferably, the background of the cloud computing server of the system updates the sample data in the storage module in real time.
Compared with the prior art, the beneficial effect of this application is:
(1) the looped netowrk cabinet table meter pointer recognition device has integrateed the AI accelerating module, through the marginal calculation local identification table meter reading, and the very first time discerns table meter abnormal information, transmits through 5G, transmits alarm information to fortune dimension managers, takes effectual disappearance measure as early as possible.
(2) The system background acquires the atlas sample information uploaded by the plurality of looped network cabinet meter pointer identification devices, the atlas sample information is fused into sample data through the system background, and the sample database is downloaded to each vehicle-mounted terminal, so that the problem that the atlas identification accuracy is reduced due to the fact that a local sample database of the looped network cabinet meter pointer identification devices is limited is effectively solved.
(3) Due to the design of the two-layer architecture, only effective information is transmitted in a network, the communication pressure of a server is reduced, and the local identification capability of the pointer identification device of the ring main unit meter is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a schematic diagram of a work flow of the pointer identification device of the ring main unit meter of the present application,
fig. 2 is a schematic diagram of the architecture design of the ring main unit meter map identification method based on machine vision and edge calculation.
The specific implementation mode is as follows:
the present application will be further described with reference to the following drawings and examples.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In the present disclosure, terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side", "bottom", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only relational terms determined for convenience in describing structural relationships of the parts or elements of the present disclosure, and do not refer to any parts or elements of the present disclosure, and are not to be construed as limiting the present disclosure.
Fig. 1 is a diagram of a ring main unit meter atlas identification apparatus based on machine vision and edge computing in this embodiment, including a ring main unit meter, a platform, a pointer identification apparatus and a system cloud computing server background;
the pointer identification device comprises a visible light camera module, an AI acceleration module, a switch, a main processor module, a 5G module, a power management module and a storage module, wherein the visible light camera module is fixedly arranged on the platform and is used for collecting visible light maps at different time periods and different brightnesses; the AI acceleration module is used for processing and identifying visible light maps under different time brightness; the switch is used for receiving the signals collected by the field visible light camera module and transmitting the signals to the AI accelerating module; the main processor module is used for collecting, processing and storing meter data identified by the AI acceleration module and communicating with the system cloud computing server through the 5G module; the 5G module is used for communicating the ring main unit meter pointer identification device with a system background cloud computing server; the power supply management module is used for converting the alternating-current voltage into a voltage grade required by the operation of the looped network cabinet meter identification device; the storage module is used for storing the historical data of the ring main unit meter and the atlas sample database.
When the device is used, the visible light camera module is fixedly installed on a platform opposite to a ring main unit meter, so that a camera of the visible light camera module is opposite to the ring main unit meter, optical fiber communication is realized among the visible light camera module, the switch and the AI acceleration module, the main processor module is an MCU, and the 5G module is wirelessly connected with a system cloud computing server and has a function of short message notification and reminding.
As shown in fig. 1 and fig. 2, when the apparatus is used, the embodiment provides a ring main unit meter map identification method based on machine vision and edge calculation, including the following steps:
a: performing spectrum recognition on a plurality of ring main unit meters on site, acquiring visible light spectrums of meters at different time periods through a visible light camera module, and transmitting the acquired visible light spectrums to an AI acceleration module through a switch; the visible light spectrums of the lower meter in different time periods are collected through the visible light camera module in the step, and the different time periods can be set according to requirements.
B: the AI acceleration module identifies and processes the visible light maps of the meters at different periods in the step A, compares the data with the data in the storage module through the main processor module, identifies the meter reading in situ through edge calculation, and then transmits the maps and the processing result to the main processor;
c: the main processor transmits the result of the edge calculation of the on-site AI acceleration module and the map data to a system cloud computing server background through the 5G module;
d: the background of the cloud computing server intelligently analyzes the information received from the 5G module, a new sample database is formed and is sent to the main processor module through the 5G module and stored in the storage module, and the background of the cloud computing server updates the sample data in the storage module in real time.
Fig. 2 shows the architecture of this embodiment, which includes an AI acceleration module edge computing analysis layer of the ring main unit meter pointer identification apparatus, and a cloud intelligent analysis layer of the system cloud computing server background. When the intelligent sample database is used, the AI acceleration module edge calculation analysis layer acquires dynamic information of the ring main unit meter in real time through the ring main unit meter recognition device, the information acquired by the meter recognition device is transmitted to the AI acceleration module through the switch for recognition and processing, the recognized and processed result is uploaded to the system background of the cloud intelligent analysis layer by the AI acceleration module, the system background further analyzes and processes the result acquired by the ring main unit meter recognition device in the AI acceleration module edge calculation analysis layer and recognized and analyzed by the AI module to form a new sample database, and then the new sample database is issued to the AI acceleration module edge calculation analysis layer.
According to the looped network cabinet meter atlas identification method based on machine vision and edge calculation, the meter identification device is provided with the AI acceleration module and used for local atlas identification, the meter identification device is communicated with the system background through the 5G module, a system background sample database is continuously updated, and the atlas identification efficiency is improved. According to the method and the device, the system integration level and the interaction efficiency of the system are improved through visible light collection, image local intelligent recognition and 5G communication.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Although the embodiments of the present application have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present application, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive effort by those skilled in the art.
Claims (10)
1. The utility model provides a looped netowrk cabinet table meter atlas recognition device based on machine vision and edge calculation, includes looped netowrk cabinet table meter, platform, its characterized in that: the device also comprises a pointer identification device and a system cloud computing server background;
the pointer identification device comprises a visible light camera module, an AI acceleration module, a switch, a main processor module, a 5G module, a power management module and a storage module, wherein the visible light camera module is fixedly arranged on the platform and is used for collecting visible light maps at different time periods and different brightnesses; the AI acceleration module is used for processing and identifying visible light maps under different time brightness; the switch is used for receiving the signals collected by the field visible light camera module and transmitting the signals to the AI accelerating module; the main processor module is used for collecting, processing and storing meter data identified by the AI acceleration module and communicating with the system cloud computing server through the 5G module; the 5G module is used for communicating the ring main unit meter pointer identification device with a system background cloud computing server; the power supply management module is used for converting the alternating-current voltage into a voltage grade required by the operation of the looped network cabinet meter identification device; the storage module is used for storing the historical data of the ring main unit meter and the atlas sample database.
2. The ring main unit meter map recognition device based on machine vision and edge calculation as claimed in claim 1, wherein:
the visible light camera module is fixedly arranged on the platform.
3. The ring main unit meter map recognition device based on machine vision and edge calculation according to claim 1 or 3, wherein:
the camera of the visible light camera module is over against the position of the ring main unit meter.
4. The ring main unit meter map recognition device based on machine vision and edge calculation as claimed in claim 1, wherein:
the main processor module is an MCU.
5. The ring main unit meter map recognition device based on machine vision and edge calculation as claimed in claim 1, wherein:
and the visible light camera module is in optical fiber communication with the switch, the switch and the AI acceleration module.
6. The ring main unit meter map recognition device based on machine vision and edge calculation as claimed in claim 1, wherein:
and the 5G module is in wireless communication with the system cloud computing server.
7. The ring main unit meter map recognition device based on machine vision and edge calculation as claimed in claim 1, wherein:
the 5G module has a short message notification function.
8. A looped network cabinet meter map recognition method based on machine vision and edge calculation is applied to the looped network cabinet meter map recognition device based on machine vision and edge calculation, and is characterized by comprising the following steps:
a: performing spectrum recognition on a plurality of ring main unit meters on site, acquiring visible light spectrums of meters at different time periods through a visible light camera module, and transmitting the acquired visible light spectrums to an AI acceleration module through a switch;
b: the AI acceleration module identifies and processes the visible light maps of the meters at different periods in the step A, compares the data with the data in the storage module through the main processor module, identifies the meter reading in situ through edge calculation, and then transmits the maps and the processing result to the main processor;
c: the main processor transmits the result of the edge calculation of the on-site AI acceleration module and the map data to a system cloud computing server background through the 5G module;
d: and the background of the cloud computing server intelligently analyzes the information received from the 5G module, forms a new sample database, sends the new sample database to the main processor module through the 5G module, and stores the new sample database in the storage module.
9. The ring main unit meter map identification method based on machine vision and edge calculation according to claim 8, wherein:
and in the step A, the visible light spectrums of the lower meter at different time periods are collected through a visible light camera module, and the different time periods can be set as required.
10. The ring main unit meter map identification method based on machine vision and edge calculation according to claim 8, wherein:
and the background of the cloud computing server of the system updates the sample data in the storage module in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111422489.8A CN114024370A (en) | 2021-11-26 | 2021-11-26 | Ring main unit meter map identification method based on machine vision and edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111422489.8A CN114024370A (en) | 2021-11-26 | 2021-11-26 | Ring main unit meter map identification method based on machine vision and edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114024370A true CN114024370A (en) | 2022-02-08 |
Family
ID=80066626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111422489.8A Pending CN114024370A (en) | 2021-11-26 | 2021-11-26 | Ring main unit meter map identification method based on machine vision and edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114024370A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992481A (en) * | 2015-07-13 | 2015-10-21 | 广东电网有限责任公司惠州供电局 | Metered inspection system and method based on image recognition technology |
| CN112290683A (en) * | 2020-11-06 | 2021-01-29 | 安徽电科恒钛智能科技有限公司 | Edge calculation-based distribution substation monitoring system |
| CN112671104A (en) * | 2020-12-24 | 2021-04-16 | 国网山东省电力公司淄博供电公司 | Transformer substation multidimensional scene control platform facing complex scene |
| CN112927464A (en) * | 2020-11-23 | 2021-06-08 | 北京宏链科技有限公司 | Job site macro-chain safety management and control system based on edge intelligence |
| CN113629870A (en) * | 2021-08-11 | 2021-11-09 | 江苏工程职业技术学院 | Cloud computing-based power grid data acquisition system |
-
2021
- 2021-11-26 CN CN202111422489.8A patent/CN114024370A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992481A (en) * | 2015-07-13 | 2015-10-21 | 广东电网有限责任公司惠州供电局 | Metered inspection system and method based on image recognition technology |
| CN112290683A (en) * | 2020-11-06 | 2021-01-29 | 安徽电科恒钛智能科技有限公司 | Edge calculation-based distribution substation monitoring system |
| CN112927464A (en) * | 2020-11-23 | 2021-06-08 | 北京宏链科技有限公司 | Job site macro-chain safety management and control system based on edge intelligence |
| CN112671104A (en) * | 2020-12-24 | 2021-04-16 | 国网山东省电力公司淄博供电公司 | Transformer substation multidimensional scene control platform facing complex scene |
| CN113629870A (en) * | 2021-08-11 | 2021-11-09 | 江苏工程职业技术学院 | Cloud computing-based power grid data acquisition system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111508097B (en) | Site inspection method, device, equipment and storage medium | |
| CN110865917A (en) | AR technology-based electric power machine room inspection operation method, system and application | |
| CN102616613B (en) | Elevator monitoring system | |
| CN109255288A (en) | A kind of road surface breakage detection method, device and terminal device | |
| CN111754483A (en) | Method and system for identifying abnormal equipment based on thermal imager | |
| CN110807460B (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
| CN112506205B (en) | Robot inspection task planning method and device | |
| CN111896549A (en) | Building crack monitoring system and method based on machine learning | |
| CN116366002A (en) | Intelligent operation and maintenance system and method for photovoltaic power station | |
| CN110796754A (en) | Machine room inspection method based on image processing technology | |
| CN116866512A (en) | Photovoltaic power station inspection system and operation method thereof | |
| CN116147697B (en) | Unattended monitoring method and system for aluminum hydroxide | |
| CN114024370A (en) | Ring main unit meter map identification method based on machine vision and edge calculation | |
| CN111767913A (en) | Motor train unit vehicle fault dynamic image detection method based on deep learning | |
| CN114662619B (en) | Bridge monitoring system based on multi-source data fusion | |
| CN115938009A (en) | Intelligent electronic patrol positioning method and system | |
| CN116363397A (en) | Equipment fault checking method, device and inspection system | |
| CN115877993A (en) | Three-dimensional view display method and device based on digital twins | |
| CN114744756A (en) | Intelligent power transmission line inspection system based on machine vision | |
| CN115086391A (en) | Fault expert system based on wearable distribution network inspection equipment and use method thereof | |
| CN115083212A (en) | Unmanned aerial vehicle location intelligent management system based on three-dimensional modeling | |
| CN115086801A (en) | Wearable distribution network intelligent inspection system and method based on portable computing terminal | |
| CN111126771B (en) | Safety inspector identification picture quality supervision and guarantee system and method based on regional attention prediction | |
| CN113421356B (en) | Inspection system and method for equipment in complex environment | |
| CN111179458A (en) | Method and device for routing inspection of rail transit equipment |
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 |