CN206546417U - A kind of GIS switch fault automatic recognition systems based on picture recognition - Google Patents
A kind of GIS switch fault automatic recognition systems based on picture recognition Download PDFInfo
- Publication number
- CN206546417U CN206546417U CN201621203959.6U CN201621203959U CN206546417U CN 206546417 U CN206546417 U CN 206546417U CN 201621203959 U CN201621203959 U CN 201621203959U CN 206546417 U CN206546417 U CN 206546417U
- Authority
- CN
- China
- Prior art keywords
- picture
- capture card
- ray
- imaging plate
- switch fault
- 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
Landscapes
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The utility model embodiment discloses a kind of GIS switch fault automatic recognition systems based on picture recognition, X-ray detection is largely used for solving the totally enclosed power equipment of current China, under normal circumstances, X-ray collection of illustrative plates quality classification method is by manually being evaluated, when manually evaluation testing result, the workload of evaluating member is big, eyes are easily by strong light injury, do not utilize former ray detection photo, efficiency is low and intelligence degree is low, and defect analysis is by the technical quality of evaluating member, the influence of experience and external condition, as a result the technical problem often varied with each individual.The utility model embodiment provides a kind of GIS switch fault automatic recognition systems based on picture recognition, including：Power supply module, x-ray source, imaging plate, capture card, data interface module, PC.
Description
Technical field
The utility model is related to power network Intelligent Measurement field, more particularly to a kind of GIS switch faults based on picture recognition
Automatic recognition system.
Background technology
The grid equipment of full-closed structure is widely used in transformer station, and its safe and reliable operation is most important.Traditional electricity
Quantity measuring method can not detect the potential safety hazard of the equipment presence that puts into operation of full-closed structure completely.The totally enclosed electricity of current China
Power equipment largely uses X-ray detection.The image of internal wiring is projected and formed on DR imaging plates by X-ray transparent closure
Image, is judged to it at the scene by testing staff.Due to the X-ray meeting do harm to huamn body that X-ray production apparatus is sent, therefore examine
The personnel of repairing must outside be operated away from about 30 meters of X-ray emission source.Many times due to pendulum during the X-ray real time imagery of routine
Put position not good, shooting image often image overlap, lack of wisdom recognition capability, detection efficiency is low, lacks for power equipment
Develop image identification function.Under normal circumstances, X-ray collection of illustrative plates quality classification method is commented by manually being evaluated when manually
When determining testing result, the workload of evaluating member is big, and eyes are easily by strong light injury, not using former ray detection photo,
Efficiency is low and intelligence degree is low, and defect analysis is influenceed by the technical quality of evaluating member, experience and external condition,
As a result often vary with each individual.
Utility model content
The utility model embodiment discloses a kind of GIS switch fault automatic recognition systems based on picture recognition, solves
The totally enclosed power equipment of current China largely uses X-ray detection, it is generally the case that X-ray collection of illustrative plates quality classification method
By manually being evaluated, when manually evaluation testing result, the workload of evaluating member is big, eyes easily by strong light injury,
Former ray detection photo is not utilized, efficiency is low and intelligence degree is low, and defect analysis is by the technology of evaluating member
The influence of quality, experience and external condition, the technical problem as a result often varied with each individual.
The utility model embodiment provides a kind of GIS switch fault automatic recognition systems based on picture recognition, including：
Power supply module, x-ray source, imaging plate, capture card, data interface module, PC；
The imaging plate is connected with the capture card by optical fiber；
The capture card refers to：The analog signal that image-forming module is obtained is converted into data signal by capture card, PC and soft
Part system reads data signal by interface module, obtains complete image data.Capture card uses the N ES of XRD 1621
Series capture cards.Software systems use windowXP and system above.Driven using the N ES Series capture cards of XRD 1621
Dynamic program reads image data.
Interface conversion is USB interface by the data interface module；
X-ray source is connected with the power supply module, imaging plate；
4 power supply modules, with the x-ray source, the imaging plate, the capture card and data interface module, institute
PC electric connection is stated, for for the x-ray source, the imaging plate, the capture card and data interface module, the PC
Power supply is provided.
As can be seen from the above technical solutions, the utility model embodiment has advantages below：
The utility model embodiment provides a kind of GIS switch fault automatic recognition systems based on picture recognition, including：
Power supply module, x-ray source, imaging plate, capture card, data interface module, PC.In the present embodiment, penetrated by power supply module, X
Line source, imaging plate, capture card, data interface module, PC, solve the totally enclosed power equipment of current China and largely use X
Ray detection, it is generally the case that X-ray collection of illustrative plates quality classification method is by manually being evaluated, when artificial evaluation detection knot
During fruit, the workload of evaluating member is big, and eyes are easily by strong light injury, not using former ray detection photo, efficiency it is low and
Intelligence degree is low, and defect analysis is influenceed by the technical quality of evaluating member, experience and external condition, as a result often
The technical problem that can be varied with each individual, realizes GIS switchgear failures and quickly recognizes, reduces testing staff sudden and violent in X-ray environment
The dew time, so that the personal injury to testing staff of reduction, and automatic classification storage tube can be carried out to the picture of shooting
Reason is easy to testing staff's quick search.
Brief description of the drawings
, below will be to embodiment in order to illustrate more clearly of the utility model embodiment or technical scheme of the prior art
Or the accompanying drawing used required in description of the prior art is briefly described, it should be apparent that, drawings in the following description are only
It is some embodiments of the present utility model, for those of ordinary skill in the art, before creative labor is not paid
Put, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of GIS switch fault automatic identifications system based on picture recognition for providing in the utility model embodiment
The structural representation of one embodiment of system；
Fig. 2 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
PC flow frame diagram；
Fig. 3 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
The structural representation of one embodiment of PC；
Fig. 4 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
The structural representation of another embodiment of PC；
Fig. 5 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
Original image；
Fig. 6 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
Median filter process picture；
Fig. 7 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
Normalized picture；
Fig. 8 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
Cut picture；
Fig. 9 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
Rim detection picture；
Figure 10 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
Contours extract picture；
Figure 11 is a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
Contours segmentation picture.
Embodiment
The utility model embodiment discloses a kind of GIS switch fault automatic recognition systems based on picture recognition,
X-ray detection is largely used for solving the totally enclosed power equipment of current China, it is generally the case that X-ray graph-spectrum quality is commented
Level method is by manually being evaluated, and when manually evaluation testing result, the workload of evaluating member is big, and eyes are easily by strong light
Damage, not using former ray detection photo, efficiency is low and intelligence degree is low, and defect analysis is by evaluating member
The influence of technical quality, experience and external condition, the technical problem as a result often varied with each individual.
Referring to Fig. 1, a kind of GIS switch faults based on picture recognition provided in the utility model embodiment are known automatically
Other system, including：Power supply module, x-ray source, imaging plate, capture card 6, data interface module, PC；
The imaging plate is connected with the capture card 6 by optical fiber；
The acquisition module refers to：The analog signal that image-forming module is obtained is converted into data signal by capture card, PC and
Software systems read data signal by interface module, obtain complete image data.Capture card uses the N ES of XRD 1621
Series capture cards.Software systems use windowXP and system above.Driven using the N ES Series capture cards of XRD 1621
Dynamic program reads image data.
Interface conversion is USB interface by the data interface module；
X-ray source is connected with the power supply module, imaging plate；
4 power supply modules, with the x-ray source, the imaging plate, the capture card 6, the data-interface mould
Block, the PC are electrically connected with, for for the x-ray source, the imaging plate, the capture card 6, the data-interface mould
Block, the PC provide power supply.
Referring to Fig. 1, a kind of GIS switch faults based on picture recognition provided in the utility model embodiment are known automatically
Other system includes：
Power supply module, x-ray source, imaging plate, capture card 6, data interface module, PC；
The x-ray source is wherein excited by the power supply module, Radiolucent object under test on the imaging plate into
Picture；
The imaging plate is connected with the capture card 6 by optical fiber, and the imaging plate will be imaged by the cable to be believed
Breath is transmitted to the capture card 6, and the image-forming information is converted into data signal by the capture card 6, and the imaging plate is by information
Transmitted by the optical fiber to the capture card 6；
The capture card 6 carries out interface conversion by the data interface module；
The data interface module transmits the data signal to affiliated PC and software systems 6 with USB line.
As shown in figure 1, the GIS switch fault automatic recognition systems based on picture recognition, including x-ray source, imaging plate, adopt
Truck 6, data interface module, PC, power supply module.When GIS switchs inspection or broken down, DR bats are carried out to GIS switches
According to.X-ray source is placed in GIS to be checked and switchs a side position, 1 meter or so of focal length, imaging plate is placed on the opposite side of GIS switches.
Switch on power, during X ray excited source, ray is passed through and is imaged after object under test on imaging plate.Imaging plate passes through with capture card 6
Fiber optic links, image-forming information is transmitted to capture card 6, and the analog signal of imaging is converted into data signal, data-interface by capture card 6
Module sends data to PC, and transmission can be usb mode.
As shown in figure 1, a kind of one embodiment of the GIS switchgear fault finding systems based on picture recognition includes：
It is working with notebook computer station 1, X-ray machine controller 2, X-ray production apparatus 3, detected mechanism 4, flat panel detector 5, capture card 6, flat
Plate power supply conditioning 7；Wherein X-ray machine controller 2 is connected by controller cable with AC220v, and X-ray machine controller 2 passes through X
Ray electric cable is connected with X-ray production apparatus, and flat panel detector 5 is connected by flat board cable line with capture card 6, and capture card 6 passes through number
It is connected according to line with working with notebook computer station 1, capture card 6 is connected by capture card power line with AC220v, flat panel detector 5 leads to
Cross detector power line to be connected with flat board power supply conditioning 7, flat board power supply conditioning 7 is connected by conditioner power line with AC220v.
The purpose of this utility model is to provide a kind of GIS switchgear fault finding systems based on picture recognition, bag
Include：X-ray source, image-forming module, capture card 6, data interface module, PC and power module.X-ray source sends x-ray, wears
Cross after examined object to be irradiated on image-forming module and be imaged.The signal that image-forming module is obtained is gathered by capture card 6 and obtained
Original image, then transmitted by data interface module to PC.PC and its software systems 1 are carried out after original image is handled
Picture feature is extracted, and sets up characteristic vector, then carries out signature analysis, identification and judged result, finally by picture and characteristic storage
To database.PC can also be shown to picture, analyzed, be recognized and be stored.
PC flow framework is as shown in Fig. 2 including original image input, picture processing, picture feature is extracted, characteristic vector
Set up, characteristic vector analysis, identification, picture and characteristic storage.
Referring to Fig. 3, a kind of GIS switch faults based on picture recognition provided in the utility model embodiment are known automatically
One embodiment of other PC includes：
Processing unit 301, the original image for being obtained to capture card carries out picture processing；
Processing unit 301 refers to：Picture processing is carried out to the original image that capture card is obtained, processing procedure is filtered including intermediate value
Ripple, normalized, picture cutting, rim detection, contours extract, image segmentation etc..
Extraction unit 302, for carrying out picture feature extraction to the original image after picture processing；
The specific position of GIS switchgears, specific angle has corresponding standard feature, treated picture reference
Corresponding standard feature, extraction unit 302 extracts the feature of picture with respective algorithms, and its feature includes narrow location, sensitivity
Outline in region etc..
Unit 303 is set up, for setting up characteristic vector by the picture feature；
Set up unit 303 and utilize the picture feature, find corresponding standard point of reference, feature is set up by the datum mark
Vector, 4,8,16 or more vector values.
Analytic unit 304, for carrying out signature analysis, identification and judged result to the characteristic vector；
Analytic unit 304 using foundation characteristic vector and database standard fault type characteristic vector carry out contrast into
Row failure picture recognition, and it is identified result.Identification process includes：By characteristic vector with being deposited in advance in standard failure database
The feature vector set of storage is matched, and is calculated by distance, and the calculating gained smaller then similarity of distance is higher, apart from reckling then
It is identified as the defect type corresponding to this defect.
Memory cell 305, for the result to be stored in database.
Memory cell 305 stores the result of identification to database, and picture storage can be according to shooting time, power transformation name of station
Claim, take the photograph the storage such as position and fault type, and failure picture is added to standard failure database.
The above is to carry out detailed retouch to a kind of unit of PC of the GIS switch fault automatic identifications based on picture recognition
State, detailed retouch will be carried out to a kind of extra cell of PC of the GIS switch fault automatic identifications based on picture recognition below
State, referring to Fig. 4, a kind of GIS switch fault automatic identifications based on picture recognition provided in the utility model embodiment
Another embodiment of PC includes：
Processing unit 401, the original image for being obtained to capture card carries out picture processing；
Original image is as shown in figure 5, picture processing is to filter off interference that may be present, mistake in image taking and transmitting procedure
Journey includes medium filtering, normalized, picture cutting, rim detection, contours extract, image segmentation etc..
The processing unit 401 is specifically included：
Medium filtering subelement 4011, the original image for being filtered off capture card acquisition using filtering is being shot and is being transmitted across
The interference being mixed into journey；
Medium filtering subelement 4011 filters off interference that may be present in image taking and transmitting procedure using filtering, such as schemes
6。
Normalized subelement 4012, the bright dark contrast for increasing the picture for filtering off interference；
Normalized subelement 4012 increases the bright dark contrast of image, becomes apparent from picture, is easy to machine recognition, such as schemes
7。
Subelement 4013 is cut, the target area for the picture after the prominent bright dark contrast of increase；
Cut the target area on the protrusion picture of subelement 4013, such as Fig. 8.
Rim detection subelement 4014, the profile information of the picture for retaining prominent target area；
Rim detection subelement 4014 retains the profile information in image, is easy to machine recognition defect area, such as Fig. 9.
Contours extract subelement 4015, the integrity profile for extracting the picture for remaining profile information；
Discontinuous profile is easy to judge its general profile for people, but for machine, it is necessary to contours extract
Subelement 4015 provides complete profile, such as Figure 10.
Split subelement 4016, for splitting to the picture for being extracted integrity profile.
4016 pairs of subelement of segmentation obtains integrity profile image and split, such as Figure 11.
Extraction unit 402, specifically for for the picture after segmentation with reference to corresponding standard feature, with corresponding algorithm
Extract the individual features of picture；
The specific position of GIS switchgears, specific angle has corresponding standard feature, treated picture reference
Corresponding standard feature, extraction unit 402 extracts the feature of picture with respective algorithms, and its feature includes narrow location, sensitivity
Outline in region etc..
Unit 403 is set up, specifically for the individual features by the picture, corresponding standard point of reference is found, and lead to
Cross the standard point of reference and set up characteristic vector；
The picture feature of unit 403 is set up, corresponding standard point of reference is found, characteristic vector, 4 are set up by the datum mark
Individual, 8,16 or more vector values.
Analytic unit 404, specifically for by by Characteristic Vectors preset in the characteristic vector and standard failure database
Amount is matched, and is calculated by distance, and the corresponding defect type of this defect is then identified as apart from reckling；
Analytic unit 404 using foundation characteristic vector and database standard fault type characteristic vector carry out contrast into
Row failure picture recognition, and it is identified result.Identification process includes：By characteristic vector with being deposited in advance in standard failure database
The feature vector set of storage is matched, and is calculated by distance, and the calculating gained smaller then similarity of distance is higher, apart from reckling then
It is identified as the defect type corresponding to this defect.
Memory cell 405, specifically for by the corresponding defect characteristic vector defect picture of the defect type according to bat
Take the photograph time, power transformation station name, take the photograph position and the defect type is stored in database, and the defect picture is added to
Standard failure database.
Memory cell 405 stores the result of identification to database, and picture storage can be according to shooting time, power transformation name of station
Claim, take the photograph the storage such as position and fault type, and failure picture is added to standard failure database.
A kind of GIS switch faults automatic recognition system based on picture recognition provided by the utility model is carried out above
It is discussed in detail, for those of ordinary skill in the art, according to the thought of the utility model embodiment, in embodiment
And will change in application, in summary, this specification content should not be construed as to limitation of the present utility model.
Claims (1)
1. a kind of GIS switch fault automatic recognition systems based on picture recognition, it is characterised in that including：Power supply module, X are penetrated
Line source, imaging plate, capture card, data interface module, PC；
The imaging plate is connected with the capture card by cable；
The capture card is connected by optical fiber with the data interface module；
X-ray source is connected with the power supply module, imaging plate；
4 power supply modules, with the x-ray source, the imaging plate, the capture card and data interface module, PC electricity
Property connection, for providing electricity for the x-ray source, the imaging plate, the capture card and data interface module, the PC
Source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621203959.6U CN206546417U (en) | 2016-11-08 | 2016-11-08 | A kind of GIS switch fault automatic recognition systems based on picture recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621203959.6U CN206546417U (en) | 2016-11-08 | 2016-11-08 | A kind of GIS switch fault automatic recognition systems based on picture recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206546417U true CN206546417U (en) | 2017-10-10 |
Family
ID=59993642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201621203959.6U Active CN206546417U (en) | 2016-11-08 | 2016-11-08 | A kind of GIS switch fault automatic recognition systems based on picture recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206546417U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116908222A (en) * | 2023-09-13 | 2023-10-20 | 广东天信电力工程检测有限公司 | X-ray detection method and system for GIS equipment faults |
-
2016
- 2016-11-08 CN CN201621203959.6U patent/CN206546417U/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116908222A (en) * | 2023-09-13 | 2023-10-20 | 广东天信电力工程检测有限公司 | X-ray detection method and system for GIS equipment faults |
| CN116908222B (en) * | 2023-09-13 | 2023-12-19 | 广东天信电力工程检测有限公司 | X-ray detection method and system for GIS equipment faults |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN108365557B (en) | Method and system for fine routing inspection of power transmission line by unmanned aerial vehicle | |
| CN106371013A (en) | Picture identification-based GIS switch fault automatic identification system | |
| CN111751002B (en) | Intelligent charged equipment fault diagnosis method based on infrared thermal imaging | |
| CN101893686B (en) | Digital radiography-based breaker operating characteristic on-line detection device and method | |
| CN109308447A (en) | The method of equipment operating parameter and operating status is automatically extracted in remote monitoriong of electric power | |
| CN105404867B (en) | A kind of substation isolating-switch state identification method of view-based access control model | |
| CN106991731A (en) | Intelligent polling method and system that integrated equipment is safeguarded | |
| CN103324943A (en) | Identification method of complex device panel image multi-sub zone state | |
| CN107024478A (en) | A kind of part processes automatic defect identifying system | |
| CN111753712A (en) | Method, system and equipment for monitoring safety of power production personnel | |
| CN106570948A (en) | Transformer substation intelligent meter reading system provided with portable device | |
| CN109308448A (en) | A method of it prevents from becoming distribution maloperation using image processing techniques | |
| CN111044149A (en) | Method and device for detecting temperature abnormal point of voltage transformer and readable storage medium | |
| CN105303162A (en) | Target proposed algorithm-based insulator recognition algorithm for aerial images | |
| CN113177614A (en) | Image recognition system and method for power supply switch cabinet of urban rail transit | |
| CN115661057A (en) | Industrial nondestructive testing system and method based on cloud edge cooperation and deep learning | |
| CN206546417U (en) | A kind of GIS switch fault automatic recognition systems based on picture recognition | |
| CN106767683A (en) | Measurement apparatus and method of a kind of unmanned plane of electronic information field to ground level | |
| CN106019145A (en) | System and method for recognizing external load switches of electric energy meter | |
| CN108898187A (en) | A kind of method and device of automatic identification power distribution room indicating equipment image | |
| CN103984967B (en) | A kind of automatic checkout system being applied to Commercial goods labels detection and automatic testing method | |
| CN116297199B (en) | Detection system for automatically detecting lithium battery parameters based on machine vision | |
| CN115378140A (en) | Unmanned aerial vehicle power equipment inspection system and method based on image recognition | |
| CN212208397U (en) | Security inspection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |