CN102722166B - Intelligent vision detection system and state detection method of transformer substation device - Google Patents
Intelligent vision detection system and state detection method of transformer substation device Download PDFInfo
- Publication number
- CN102722166B CN102722166B CN201210222443.6A CN201210222443A CN102722166B CN 102722166 B CN102722166 B CN 102722166B CN 201210222443 A CN201210222443 A CN 201210222443A CN 102722166 B CN102722166 B CN 102722166B
- Authority
- CN
- China
- Prior art keywords
- module
- image
- equipment
- state
- information
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 62
- 230000002159 abnormal effect Effects 0.000 claims abstract description 21
- 230000005540 biological transmission Effects 0.000 claims abstract description 18
- 230000033001 locomotion Effects 0.000 claims abstract description 11
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 238000004458 analytical method Methods 0.000 claims description 38
- 238000000034 method Methods 0.000 claims description 27
- 230000000007 visual effect Effects 0.000 claims description 24
- 238000000605 extraction Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 7
- 238000012546 transfer Methods 0.000 claims description 6
- 238000007726 management method Methods 0.000 claims description 5
- 241000196324 Embryophyta Species 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 14
- 238000012360 testing method Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 230000021615 conjugation Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a routing inspection robot vision system and a state detection method of a transformer substation. The routing inspection robot vision system comprises a motion control module, wherein a holder control module is arranged on the motion control module and connected with an image acquisition module through a vision servo module, the image acquisition module is connected with an image intelligent analyzing system through an image transmission module, the image intelligent analyzing system comprises a device classifying module, a disconnecting link state recognition module, a high-voltage breaker recognition module, an instrument reading module and an appearance abnormal recognition module, and modules of the image intelligent analyzing system are connected with a comprehensive analyzing module which is connected with a transformer substation information control system interface module. The routing inspection robot vision system and the state detection method of the transformer substation can automatically analyze the current device states including all detection contents of the daily patrol working of the transformer substation, achieve conversion from a cycle patrol mode to the patrol mode based on the states, complete automatic recognition and recording of the device states of the transformer substation and greatly reduce engagement of working staff.
Description
Technical field
The present invention relates to a kind of intelligent visual detection system and detection method.Particularly relate to a kind of substation equipment intelligent visual detection system and condition detection method.
Background technology
In the last few years, the high speed sustainable development of the national economy of China, the basis that electric power develops as every profession and trade, transmission line length and transformer station's quantity were followed by sharply rising.Work patrolled and examined by traditional power equipment, relies on human at periodic intervals to make an inspection tour equipment state, ensures that transformer station's routine safety runs.Along with power consumption increases day by day, increasing of transformer station's quantity, the dispersion of manual inspection inefficiency, Detection job, with existing information system without the contradiction such as being connected day by day significantly, obvious manual inspection can not meet the demand of era development.
Particularly after the Special Geographic conditioned disjunction such as plateau, Gobi desert is as extreme weather generations such as strong wind, greasy weather, ice and snow, hail, thunderstorms, cause and manually cannot patrol and examine in time, and patrol and examine the larger security risk of existence by condition restriction, now transformer station is once the accident that meets accident, decision maker is because obtaining field data intuitively in time, often affect the opportunity of optimization process accident adversely, cause the unnecessary economic loss accident that even casualties etc. is great.The O&M robotization of power equipment and modernization demonstrate its urgency day by day.
Along with the development of science and technology, intelligent substation construction technique is more and more ripe, and unattended operation transformer station becomes possibility.Power Robot can replace or indirect labor patrols and examines, and increases work efficiency, and reduces labour intensity, reduces operating risk, has become national grid to one of normative content that intelligent substation is built.
Vision detection system, as the important component part of robot, in replacement manual patrol process, occupies very consequence.Vision detection system, main view-based access control model sensor, as CCD, CMOS etc., obtains the image information of power equipment, by processing image, analyzing, the state that the equipment that detects is current.
, there is following feature in the existing vision detection system based on Intelligent Mobile Robot:
(1) function singleness.Existing power equipment vision detection system, often only possesses the measuring ability of several specific installation, if the automated graphics identification of Chinese Patent Application No. 200610080730.2-power high voltage circuit breaker switch state and monitoring method, Chinese Patent Application No. 201110216378.1-are based on transformer station's disconnecting link mode identification method of infrared detection, wait the condition detection method specially for isolating switch and disconnecting link.Obviously, the state-detection of above-mentioned several specific installation, cannot meet the detection realized all equipment states of transformer station, then also cannot realize the function replacing manual patrol completely.
(2) single image testing result judgment device state is only relied on, poor reliability.Existing vision-based detection module, only provides the Condition Detection result of single image, time not with reference to manual inspection, confirms the routine inspection mode of equipment state from multiple angle.Therefore, the result that image detects just directly affects the reliability that robotary detects, and due under outdoor environment, the many factors such as picture quality, illumination effect causes, more difficult realize that image detects completely reliable.Therefore, simple dependence single image result, the reliability of existing vision detection system cannot ensure.
(3) image information collecting mode is large to robot localization precision dependence.Existing vision-based detection mode, point of fixity is mostly adopted to detect, namely robot patrols and examines at every turn and all can rest in fixed position, setting The Cloud Terrace carries out the collection of equipment drawing picture to fixed position, due to factors such as robot moving platform machine error, The Cloud Terrace resetting errors, target device can not ensure to appear at accurately within the scope of field of view, and this is the key factor causing vision-based detection failure.
(4) intellectual analysis function is lacked.Existing vision detection system, after mostly adopting state-detection to complete merit, still need manually to judge that whether state is correct according to work ticket information and historical record, and not high with substation information management system conjugation, the automatic renewal of Site Detection result to information management system cannot be realized.
Due to the problems referred to above of existing vision detection system, the more difficult testing automatically reliably realizing the state of transformer station's all devices, accuracy of detection and stability all have much room for improvement, the reliability that substation equipment State-dependence robot is detected cannot ensure, thus has buried hidden danger to substation safety operation.How to address the aforementioned drawbacks, realize a set ofly possessing transformer station's all devices automatic detection function and there is high reliability, high-precision vision detection system, become a very urgent problem.
Summary of the invention
The object of the invention is for overcoming the imperfect of above-mentioned prior art, a kind of substation equipment intelligent visual detection system based on Intelligent Mobile Robot platform and detection method are provided.Its complete function, covers the automatic inspection function of all transformer stations visual plant; Possess visual servo function, do not rely on The Cloud Terrace and mobile device system precision; Comprehensively can also analyze according to historical information and associate device state, directly provide warning message, make an inspection tour substation equipment without the need to staff by modes such as monitoring in real time, manually record.
For achieving the above object, the present invention adopts following technical proposals:
A kind of Intelligent Mobile Robot vision system, it comprises motion-control module, described motion-control module is provided with cradle head control module, cradle head control module is connected with image capture module by visual servo module, image capture module is connected with image intelligent analytic system by image transmission module, image intelligent analytic system comprises device class module, disconnecting link state recognition module, primary cut-out identification module, meter reading module and abnormal appearance identification module, each module of image intelligent analytic system with comprehensively analyze model calling, comprehensive analysis module is connected with substation information control system interface module.
Image by device type identification module automatic identification equipment type, and is input in corresponding identification module by described image intelligent analytic system; After corresponding identification module state-detection completes, result is input in comprehensive analysis module, by analyzing with historical data comparative analysis, associate device state vs, obtain final detection result and early warning information, finally by status information of equipment and the whether normal judged result of state, have by oneself in infosystem by substation information system interface module and transformer station, for work of transformer substation librarian use.
Described meter reading module, adopt similar round readings of pointer type meters method to the Instrument image that picture signal collecting device obtains, automatically extract similar round region, extraction apparatus list index position, provides instrument current time index.
Described disconnecting link state recognition module, carries out treatment and analyses to the disconnecting link image confidence that picture signal collecting device obtains, automatically identify disconnecting link closed, disconnect, closed three kinds of situations not in place;
Described primary cut-out identification module, the isolating switch image obtained by picture signal collecting device is identified, main utilize the method based on template matches judge isolating switch point, conjunction state;
Described abnormal appearance identification module, mainly to equipment having hanger, there is spark tracking in equipment surface, oil stain class situation detects.
Described motion-control module also comprises mobile platform and controls the motion controller of mobile platform movement; Described cradle head control module comprises The Cloud Terrace and cradle head controllor, and cradle head controllor controls cloud platform rotation angle; The present image that described visual servo module utilizes picture signal collecting device to obtain is analyzed with the template image gathered in advance, obtain The Cloud Terrace adjustment amount, then The Cloud Terrace attitude is adjusted, ensure equipment drawing as complete appearance in the picture, for follow-up equipment state identification provides sufficient information; Image transmission module comprises wireless router, Signal reception base station, by the image information after compressed encoding by wireless network transmissions to background processing module in.
Utilize a condition detection method for Intelligent Mobile Robot vision system, step is as follows:
(1) control to move to assigned address based on Intelligent Mobile Robot Motion Control Platform, by visual servo module, image capture module adjustment is ensured that equipment drawing as complete appearance in the picture, then obtains the picture rich in detail of equipment to be detected by image capture module;
(2) image information will collected, first carries out compressed encoding, then is transferred in image intelligent analytic system by image transmission module;
(3) the device type identification module of image intelligent analytic system is according to disconnecting link, primary cut-out, instrument, classifies to image, and automatically the image of equipment is sent into corresponding identification module;
(4) respective present image is carried out consistency analysis with the device history image be associated by comprehensive analysis module by disconnecting link state recognition module, primary cut-out identification module, meter reading module and transformer abnormal appearance identification module respectively, and status information of equipment and early warning information transfer to substation information system interface module the most at last;
(5) determination and analysis results conversion is become the data type of substation information system identification by substation information system interface module, transfers in the substation information management system of host computer;
(6) staff directly monitors judged result.
In described step (3), the automatic classification of device class module, mainly through the configuration information of machine stop position, obtains current device type to be detected, thus automatically determines the detection module that will enter.The method simply, reliably, easily realizes.
In described step (4), disconnecting link state recognition module judges disconnecting link state, automatically identify disconnecting link closed, disconnect, closed three kinds of situations not in place;
Primary cut-out identification module judges high-voltage circuit-breaker status, judge primary cut-out point, close state;
Meter reading module judges meter status, the pointer position of automatic identifier table, provides instrument current time index;
Whether abnormal appearance identification module identification equipment has hanger, equipment surface exists the situation such as spark tracking, oil stain abnormal appearance state.
Described meter reading module judges that the detailed process of meter status is:
(1) the Instrument image gray processing that mobile robot gathers, binaryzation;
(2) marginal information of Canny algorithm extraction equipment bianry image is utilized; Marginal point is utilized to use least square fitting oval; The ellipse obtained is filtered, weeds out and be synthesized to oval non-elliptical image, obtain dial plate region and dial plate home position;
(3) obtaining in dial plate image-region the Straight Line Extraction extraction pointer used based on Hough transform, with reference to the dial plate center of circle, and then the angle of pointer is obtained;
(4) registration that the pointer angle of corresponding target instrument in database is corresponding with relation calculation procedure (3) the gained angle between registration is extracted.
In described step (4), the analytic process of comprehensive analysis module is: utilize substation equipment distributed intelligence, the state recording of equipment automatically will be associated, and preserves, and carries out consistency analysis; By this module, contrasting current device state longitudinal direction with historic state, horizontal carries out state comparison with associated devices, the state of comprehensive this equipment of analysis, and provide analysis result, for occurring that the equipment of abnormal state carries out alarm, its concrete steps are:
(1) according to transformer station's Daily Round Check task, the equipment-patrolling content be associated is associated;
(2) according to relevant device sequence of states control planning, after the end tasks carrying of association completes, the consistance of each equipment in associated task is judged;
(3) for producing abnormal equipment state, contrasting with the historical data of front secondary detection, in conjunction with work ticket order, carrying out consistency analysis, determine whether to occur extremely.
Beneficial effect of the present invention:
(1) this system covers the status detection function of all inspection devices of transformer station first, and propose instrument automatic detection algorithm, propose a kind of device type automatic identification algorithm, automatic identification equipment type, really realize full automation and detect various equipment state in transformer station;
(2) propose a kind of visual servo algorithm based on image, automatically according to target image position, realize the automatic servo of The Cloud Terrace, what guarantee target image was complete appears within sweep of the eye, improves overall accuracy of detection;
(3) propose by testing result automatically with historical data and the equipment state consistency check algorithm that is associated, add the reliability of state-detection, and directly provide warning message, really achieve the transformation to the routine inspection mode based on state;
(4) based on the equipment state comprehensive analysis module that this intelligent visual detection system proposes, transformer station's everyday devices patrol task, can be replaced by robot completely, the action of staff is transformed into only to occurring that the equipment of early warning is investigated from whole routine testing, substantially increases work efficiency;
(5) based on this intelligent visual detection system, Intelligent Mobile Robot possesses the automatic detecting mode of high precision, high reliability, for substation safety runs, reduces security incident, give firm technical guarantee, for power industry safety, stable development are laid a good foundation.
Accompanying drawing explanation
Fig. 1 is the structural representation of substation equipment intelligent visual detection system.
Wherein, 1. image capture module, 2. cradle head control module, 3. visual servo module, 4. image transmission module, 5. image intelligent analytic system, 6. device type identification module, 7. disconnecting link state recognition module, 8. primary cut-out identification module, 9. meter reading module, 10. abnormal appearance identification module, 11. comprehensive analysis modules, 12. substation information system interface modules, 13. motion-control modules.
Embodiment
Below in conjunction with accompanying drawing and embodiment, the invention will be further described.
As shown in Figure 1, a kind of Intelligent Mobile Robot intelligent visual detection system, comprises image capture module 1, cradle head control module 2, visual servo module 3, image transmission module 4, comprehensive analysis module 11, substation information system interface module 12, motion-control module 13; Wherein, motion-control module 13 is provided with cradle head control module 2, cradle head control module 2 is connected with image capture module 1 through visual servo module 3, image capture module 1 is connected with image transmission module 4, image transmission module 4 is connected with image intelligent analytic system 5, image intelligent analytic system 5 is connected with comprehensive analysis module 11, and comprehensive analysis module 11 is connected with substation information system interface 12.Image information is connected with image intelligent analytic system 5 by image transmission module 4 after image capture module 1 gathers.Described image intelligent analytic system 5 comprises device type identification module 6, disconnecting link state recognition module 7, primary cut-out identification module 8, meter reading module 9 and abnormal appearance identification module 10.
Described image capture module 1 comprises picture signal collecting device and image coding and decoding equipment, and picture signal collecting device can adopt monocular-camera or CCD industrial camera, and image encoding apparatus is responsible for image analoging signal to carry out compressed encoding.
Described motion-control module 13 comprises mobile platform and controls the motion controller of mobile platform movement.
Described cradle head control module 2 comprises The Cloud Terrace, cradle head controllor, and cradle head controllor can set, preserve, control cloud platform rotation angle.Picture signal collecting device in image capture module 1 carries on The Cloud Terrace, and cradle head controllor controls the rotational angle of The Cloud Terrace level, vertical direction, thus controls the attitude of camera, takes the different equipment of multiple angle flexibly.
The present image that described visual servo module 3 utilizes picture signal collecting device to obtain is analyzed with the template image gathered in advance, obtain The Cloud Terrace adjustment amount, then The Cloud Terrace attitude is adjusted, ensure equipment drawing as complete appearance in the picture, for follow-up equipment state identification provides sufficient information.The structure that this system adopts adopts the structure described in Chinese granted patent ZL201020685635.7.View-based access control model servo function, Intelligent Mobile Robot arrives fixed test point, can independently according to present image information, and adjustment The Cloud Terrace, makes target image appear at completely within sweep of the eye.Eliminate the target caused due to clouds terrace system error and mobile platform system error and deflect away from situation beyond field range, improve accuracy of detection and fiduciary level.
Described image transmission module 4 comprises wireless router, Signal reception base station, by the image information after compressed encoding by wireless network transmissions to background processing module in.The structure that this system adopts adopts the wireless communication module structure of Chinese granted patent number described in 201110005671.3.
Image, by device type identification module 6 automatic identification equipment type, as types of image such as disconnecting link, primary cut-out, instrument, is input in corresponding identification module by described image intelligent analytic system 5 automatically.After corresponding identification module state-detection completes, result being input in comprehensive analysis module 11, by analyzing with historical data comparative analysis, associate device state vs, obtaining final detection result and early warning information.Finally by status information of equipment and the whether normal judged result of state, have by oneself in infosystem, for work of transformer substation librarian use by substation information system interface module 12 with transformer station.
Described device type identification module 6 automatic identification equipment type, mainly through the configuration information of machine stop position, obtains current device type to be detected, thus automatically determines the detection module that will enter.
Described disconnecting link state recognition module 7, carries out treatment and analyses to the disconnecting link image that picture signal collecting device obtains, automatically identify disconnecting link closed, disconnect, closed three kinds of situations not in place.The structure that this system adopts adopts structure and method described in Chinese granted patent numbers 2011102163781.
Described primary cut-out identification module 8, the isolating switch image obtained by picture signal collecting device is identified, main utilize the method based on template matches judge isolating switch point, conjunction state.The structure that this system adopts adopts structure and method described in Chinese granted patent 201110216396X.
Described meter reading module 9, adopt similar round readings of pointer type meters method to the Instrument image that picture signal collecting device obtains, automatically extract similar round region, extraction apparatus list index position, provides instrument current time index.This module manually extracts target instrument template, the corresponding relation of target-marking meter dial and angle, and stored in database, concrete grammar comprises following step:
(1) the Instrument image gray processing that mobile robot gathers, binaryzation;
(2) marginal information of Canny algorithm extraction equipment bianry image is utilized; Marginal point is utilized to use least square fitting oval; The ellipse obtained is filtered, weeds out and be synthesized to oval non-elliptical image, obtain dial plate region and dial plate home position;
(3) obtaining in dial plate image-region the Straight Line Extraction extraction pointer used based on Hough transform, with reference to the dial plate center of circle, and then the angle of pointer is obtained;
(4) registration that the pointer angle of corresponding target instrument in database is corresponding with relation calculation procedure (3) the gained angle between registration is extracted.
The method, based on existing crusing robot detection mode, based on fixed test point, adopts visual servo function simultaneously, substantially increases reliability and the dirigibility of Meter recognition, be better than existing instrument detection means.
Described abnormal appearance identification module 10, refer to by analytical equipment surface visual information, detect the equipment surface abnormal conditions such as hanger, spark tracking, oil stain, this type of situation is run substation safety exists larger potential safety hazard, is one of important content of substation inspection.The structure that this system adopts adopts structure and method described in Chinese granted patent ZL 201020555312.6.
Described comprehensive analysis module 11 utilizes substation equipment distributed intelligence, the state recording of equipment automatically will be associated, and preserves, and carries out consistency analysis.By this module, can contrasting current device state longitudinal direction with historic state, horizontal carries out state comparison with associated devices, the comprehensive state analyzing this equipment, and provides analysis result, for occurring that the equipment of abnormal state carries out alarm.This module concrete methods of realizing:
(1) according to transformer station's Daily Round Check task, the equipment-patrolling content be associated is associated,
(2) according to relevant device sequence of states control planning, after the end tasks carrying of association completes, the consistance of each equipment in associated task is judged;
(3) for producing abnormal equipment state, contrasting with the historical data of front secondary detection, in conjunction with work ticket order, carrying out consistency analysis, determine whether to occur extremely.
The equipment state detected and early warning information are connected with transformer station mis system by described substation information system interface module 12, work of transformer substation personnel can be directly acquainted with the state of various kinds of equipment in current transformer substation by station internal information system, manual inspection can be replaced completely, only according to early warning information, unit exception is investigated, will greatly reduce the labour intensity of staff.
Use the substation equipment condition detection method of said system, concrete implementation process is as follows:
(1) ad-hoc location is moved to based on Intelligent Mobile Robot Motion Control Platform, obtained the picture rich in detail of equipment to be detected by image capture module 1, and adjust to ensure that equipment drawing as complete appearance in the picture by visual servo module 3 pairs of image capture modules 1;
(2) image information will taked, first carries out compressed encoding, then is transferred in background processor by image transmission module 4;
(3) use device type identification module, automatically device type is classified, and image is input to corresponding Condition Detection module;
(4) testing result is transferred to comprehensive analysis 11 modules by corresponding Condition Detection system, current device state is carried out consistency analysis with historical data with the equipment be associated by this module automatically, and status information of equipment and early warning information transfer to substation information system interface module 12 the most at last;
(5) determination and analysis results conversion is become the type of substation information system identification by substation information system interface module 12, transfers in substation information management system;
(6) staff directly monitors judged result.
Similar flow process, is equally applicable to the identification of primary cut-out, meter reading, equipment appearance anomalous identification.
By reference to the accompanying drawings the specific embodiment of the present invention is described although above-mentioned; but not limiting the scope of the invention; one of ordinary skill in the art should be understood that; on the basis of technical scheme of the present invention, those skilled in the art do not need to pay various amendment or distortion that creative work can make still within protection scope of the present invention.
Claims (1)
1., based on a condition detection method for Intelligent Mobile Robot vision system, it is characterized in that,
Described Intelligent Mobile Robot vision system, it comprises motion-control module, described motion-control module is provided with cradle head control module, cradle head control module is connected with image capture module by visual servo module, image capture module is connected with image intelligent analytic system by image transmission module, image intelligent analytic system comprises device class module, disconnecting link state recognition module, primary cut-out identification module, meter reading module and abnormal appearance identification module, each module of image intelligent analytic system with comprehensively analyze model calling, comprehensive analysis module is connected with substation information control system interface module,
Image by device type identification module automatic identification equipment type, and is input in corresponding identification module by described image intelligent analytic system; After corresponding identification module state-detection completes, result is input in comprehensive analysis module, by analyzing with historical data comparative analysis, associate device state vs, obtain final detection result and early warning information, finally by status information of equipment and the whether normal judged result of state, have by oneself in infosystem by substation information system interface module and transformer station, for work of transformer substation librarian use;
Described meter reading module adopts similar round readings of pointer type meters method to the Instrument image that picture signal collecting device obtains, and automatically extract similar round region, extraction apparatus list index position, provides instrument current time index;
Described disconnecting link state recognition module, carries out treatment and analyses to the disconnecting link picture signal that picture signal collecting device obtains, automatically identify disconnecting link closed, disconnect, closed three kinds of situations not in place;
Described primary cut-out identification module, the isolating switch image obtained by picture signal collecting device is identified, utilize the method based on template matches judge isolating switch point, conjunction state;
Described abnormal appearance identification module, to equipment having hanger, there is spark tracking in equipment surface, oil stain class situation detects;
Described motion-control module also comprises mobile platform and controls the motion controller of mobile platform movement; Described cradle head control module comprises The Cloud Terrace and cradle head controllor, and cradle head controllor controls cloud platform rotation angle; The present image that described visual servo module utilizes picture signal collecting device to obtain is analyzed with the template image gathered in advance, obtain The Cloud Terrace adjustment amount, then The Cloud Terrace attitude is adjusted, ensure equipment drawing as complete appearance in the picture, for follow-up equipment state identification provides sufficient information; Image transmission module comprises wireless router, Signal reception base station, by the image information after compressed encoding by wireless network transmissions in background processing module;
Described method concrete steps are as follows:
(1) control to move to assigned address based on Intelligent Mobile Robot Motion Control Platform, by visual servo module, image capture module adjustment is ensured that equipment drawing as complete appearance in the picture, then obtains the picture rich in detail of equipment to be detected by image capture module;
(2) image information will collected, first carries out compressed encoding, then is transferred in image intelligent analytic system by image transmission module;
(3) the device type identification module of image intelligent analytic system is according to disconnecting link, primary cut-out, instrument and transformer, identifies image, and automatically the image of equipment is sent into corresponding identification module;
(4) respective present image is carried out consistency analysis with the device history image be associated by comprehensive analysis module by disconnecting link state recognition module, primary cut-out identification module, meter reading module and abnormal appearance identification module respectively, and status information of equipment and early warning information transfer to substation information system interface module the most at last;
(5) determination and analysis results conversion is become the data type of substation information system identification by substation information system interface module, transfers in the substation information management system of host computer;
(6) staff directly monitors judged result;
In described step (3), the automatic classification of device class module, mainly through the configuration information of machine stop position, obtains current device type to be detected, thus automatically determines the detection module that will enter;
In described step (4), disconnecting link state recognition module judges disconnecting link state, automatically identify disconnecting link closed, disconnect, closed three kinds of situations not in place;
Primary cut-out identification module judges high-voltage circuit-breaker status, judge primary cut-out point, close state;
Meter reading module judges meter status, the pointer position of automatic identifier table, provides instrument current time index;
Whether abnormal appearance identification module identification equipment has hanger, equipment surface exists spark tracking, oil stain class situation abnormal appearance state;
Described meter reading module judges that the detailed process of meter status is:
1) the Instrument image gray processing that mobile robot gathers, binaryzation;
2) marginal information of Canny algorithm extraction equipment bianry image is utilized; Marginal point is utilized to use least square fitting oval; The ellipse obtained is filtered, weeds out and be synthesized to oval non-elliptical image, obtain dial plate region and dial plate home position;
3) obtaining in dial plate image-region the Straight Line Extraction extraction pointer used based on Hough transform, with reference to the dial plate center of circle, and then the angle of pointer is obtained;
4) the pointer angle of corresponding target instrument and the relation computation process 3 between registration in database is extracted) registration corresponding to gained angle;
In described step (4), the analytic process of comprehensive analysis module is: utilize substation equipment distributed intelligence, the state recording of equipment automatically will be associated, and preserves, and carries out consistency analysis; By comprehensive analysis module, contrasting current device state longitudinal direction with historic state, horizontal carries out state comparison with associated devices, the state of comprehensive this equipment of analysis, and provide analysis result, for occurring that the equipment of abnormal state carries out alarm, its concrete steps are:
A the equipment-patrolling content be associated, according to transformer station's Daily Round Check task, associates by (),
B (), according to relevant device sequence of states control planning, after the end tasks carrying of association completes, judges the consistance of each equipment in associated task;
C (), for producing abnormal equipment state, contrasts with the historical data of front secondary detection, in conjunction with work ticket order, carry out consistency analysis, determines whether to occur extremely.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210222443.6A CN102722166B (en) | 2012-06-29 | 2012-06-29 | Intelligent vision detection system and state detection method of transformer substation device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210222443.6A CN102722166B (en) | 2012-06-29 | 2012-06-29 | Intelligent vision detection system and state detection method of transformer substation device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102722166A CN102722166A (en) | 2012-10-10 |
| CN102722166B true CN102722166B (en) | 2015-03-04 |
Family
ID=46947967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210222443.6A Active CN102722166B (en) | 2012-06-29 | 2012-06-29 | Intelligent vision detection system and state detection method of transformer substation device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102722166B (en) |
Families Citing this family (69)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102058918B1 (en) * | 2012-12-14 | 2019-12-26 | 삼성전자주식회사 | Home monitoring method and apparatus |
| CN103927507A (en) * | 2013-01-12 | 2014-07-16 | 山东鲁能智能技术有限公司 | Improved multi-instrument reading identification method of transformer station inspection robot |
| CN103105581A (en) * | 2013-01-24 | 2013-05-15 | 上海毕励电子科技有限公司 | Electrical equipment quantity of state collection method based on video recognition |
| CN103532238B (en) * | 2013-10-22 | 2016-08-24 | 国家电网公司 | A kind of system and method preventing misoperation of change-over switch of transformer substation |
| CN103605365B (en) * | 2013-11-07 | 2016-01-20 | 成都赛康信息技术有限责任公司 | The entire roboticized work method that substation equipment filth is patrolled and examined, judges and cleaned |
| CN104391506A (en) * | 2014-09-19 | 2015-03-04 | 福州大学 | Transformer station guide rail type inspection robot |
| CN105530456A (en) * | 2014-09-28 | 2016-04-27 | 深圳中兴力维技术有限公司 | Method, device and system for substation monitoring |
| CN104320580A (en) * | 2014-10-25 | 2015-01-28 | 国家电网公司 | Equipment and method for identifying SF6 density meter pointer based on image acquisition |
| CN104457621A (en) * | 2014-12-22 | 2015-03-25 | 国家电网公司 | Pattern displacement sensor system for detecting position state of disconnecting link of transformer substation |
| CN104994334A (en) * | 2015-06-09 | 2015-10-21 | 海南电网有限责任公司 | Automatic substation monitoring method based on real-time video |
| CN105262994A (en) * | 2015-10-14 | 2016-01-20 | 南京第五十五所技术开发有限公司 | Instrument identification device and method based on intelligent track video camera |
| CN105446336A (en) * | 2015-12-08 | 2016-03-30 | 哈尔滨工业大学 | Robot inspection system and inspection method for cold region transformer substation |
| CN105652872B (en) * | 2016-02-26 | 2018-07-31 | 郑州金惠计算机系统工程有限公司 | The automatic method for tracking and positioning of substation's laser navigation crusing robot intelligent console |
| CN105554479A (en) * | 2016-03-02 | 2016-05-04 | 浙江群力电气有限公司 | Intelligent monitoring system for electric power transmission and transformation and distribution equipment |
| CN106125744B (en) * | 2016-06-22 | 2019-01-22 | 山东鲁能智能技术有限公司 | The Intelligent Mobile Robot cloud platform control method of view-based access control model servo |
| CN106651840A (en) * | 2016-11-25 | 2017-05-10 | 国网北京市电力公司 | Electrical device detection system |
| CN106529559A (en) * | 2016-12-30 | 2017-03-22 | 山东鲁能软件技术有限公司 | Pointer-type circular multi-dashboard real-time reading identification method |
| CN108345820A (en) * | 2017-01-23 | 2018-07-31 | 许继集团有限公司 | High-tension apparatus image-recognizing method and device based on variety of components and component locations |
| CN107036642B (en) * | 2017-04-12 | 2020-10-09 | 中国电力科学研究院 | Method for carrying out meter inspection performance test on intelligent inspection robot of transformer substation |
| CN107067013A (en) * | 2017-04-25 | 2017-08-18 | 航天科技控股集团股份有限公司 | One kind is based on many instrument hawkeye fuzzy detection system and methods |
| CN107257161B (en) * | 2017-06-20 | 2020-10-09 | 安徽南瑞继远电网技术有限公司 | Transformer substation disconnecting link remote control auxiliary checking method and system based on state recognition algorithm |
| CN107481223B (en) * | 2017-07-21 | 2020-03-24 | 中车青岛四方机车车辆股份有限公司 | Method and device for automatically identifying wiring state image |
| CN107393270B (en) * | 2017-07-26 | 2019-11-08 | 河海大学常州校区 | A kind of mobile vision inspection device and method for electric meter detection |
| CN107688349A (en) * | 2017-08-17 | 2018-02-13 | 武汉大学 | A kind of crusing robot tele-control system and control method |
| CN107976214A (en) * | 2017-10-11 | 2018-05-01 | 国网浙江省电力公司湖州供电公司 | The detecting system and method for a kind of protective relaying device |
| CN107907753B (en) * | 2017-10-11 | 2020-01-10 | 国网浙江省电力公司湖州供电公司 | Detection device and method for relay protection device |
| CN107680195A (en) * | 2017-11-13 | 2018-02-09 | 国网内蒙古东部电力有限公司 | A kind of transformer station intelligent robot inspection Computer Aided Analysis System and method |
| CN107817052A (en) * | 2017-11-30 | 2018-03-20 | 国网辽宁省电力有限公司电力科学研究院 | Based on the collection of infrared imaging power transformer crusing robot thermal map and communication system |
| CN107895409B (en) * | 2017-12-28 | 2023-07-28 | 国网福建省电力有限公司 | Automatic inspection device and inspection method for water inlet door slot of hydropower station |
| CN108737550A (en) * | 2018-05-25 | 2018-11-02 | 山东鲁能智能技术有限公司 | A kind of robot interface's device and robot based on robot centralized control system |
| CN108627794B (en) * | 2018-06-27 | 2020-09-29 | 方汝松 | Intelligent instrument detection method based on deep learning |
| CN108900808A (en) * | 2018-07-17 | 2018-11-27 | 广州市君望机器人自动化有限公司 | The method and device that robot is monitored equipment |
| CN109271844B (en) * | 2018-07-29 | 2023-03-28 | 国网上海市电力公司 | Electrical cabinet electrical symbol recognition method based on OpenCV |
| CN109271407A (en) * | 2018-09-27 | 2019-01-25 | 西安银石科技发展有限责任公司 | A kind of equipment routing inspection method based on machine learning |
| CN109245942A (en) * | 2018-10-19 | 2019-01-18 | 国网山东省电力公司滨州市滨城区供电公司 | A kind of information equipment intelligent management method based on image recognition |
| CN111102966A (en) * | 2018-10-29 | 2020-05-05 | 所罗门股份有限公司 | Method for automatically acquiring equipment state |
| CN109412069A (en) * | 2018-11-24 | 2019-03-01 | 四川都睿感控科技有限公司 | The state monitoring method and device of switchgear |
| CN110059610A (en) * | 2018-12-25 | 2019-07-26 | 苏州百卓网络技术有限公司 | A kind of pointer instrument method for early warning based on image recognition |
| CN109740507A (en) * | 2018-12-29 | 2019-05-10 | 国网浙江省电力有限公司 | A kind of method of transformer equipment abnormality sensing |
| CN111668925A (en) * | 2019-03-05 | 2020-09-15 | 特变电工智能电气有限责任公司 | Transformer inspection tour inspection device based on intelligent vision |
| CN110188786B (en) * | 2019-04-11 | 2022-12-06 | 广西电网有限责任公司电力科学研究院 | Robot image recognition algorithm for leakage current of pot-type lightning arrester |
| CN110084251A (en) * | 2019-04-29 | 2019-08-02 | 北京史河科技有限公司 | A kind of Meter recognition method, apparatus and storage medium |
| CN110348380B (en) * | 2019-07-10 | 2024-01-23 | 无锡地铁集团有限公司 | Visual grounding disconnecting link state video identification system and method |
| CN110427882A (en) * | 2019-08-01 | 2019-11-08 | 北京派克盛宏电子科技有限公司 | For the intelligent analysis method of tour, device, equipment and its storage medium |
| CN110430078B (en) * | 2019-08-05 | 2022-04-08 | 云南电网有限责任公司电力科学研究院 | Method and system for recognizing type, configuring and functionally enabling electric power automation terminal |
| CN110514957A (en) * | 2019-08-19 | 2019-11-29 | 深圳供电局有限公司 | Substation's automatic detecting method and platform |
| CN110587629A (en) * | 2019-10-15 | 2019-12-20 | 云南电网有限责任公司电力科学研究院 | Transformer substation inspection robot, inspection method and inspection robot control method |
| CN110823907A (en) * | 2019-11-21 | 2020-02-21 | 张红兵 | System and method for checking integrity condition of blades of aircraft engine |
| CN110996053B (en) * | 2019-11-26 | 2021-06-01 | 浙江吉城云创科技有限公司 | Environment safety detection method and device, terminal and storage medium |
| CN110962126B (en) * | 2019-12-06 | 2022-04-01 | 深圳优艾智合机器人科技有限公司 | Operation method and operation system of intelligent robot in power distribution room |
| CN111044224A (en) * | 2019-12-30 | 2020-04-21 | 深圳供电局有限公司 | Method for identifying and detecting transformer by patrol trolley |
| CN111460969B (en) * | 2020-03-27 | 2021-08-06 | 震兑工业智能科技有限公司 | Intelligent industrial information monitoring system based on cloud computing |
| CN111526330A (en) * | 2020-04-17 | 2020-08-11 | 广东电网有限责任公司 | Transformer substation equipment state intelligent recognition system based on machine vision |
| CN111830342B (en) * | 2020-07-04 | 2023-04-28 | 中国南方电网有限责任公司 | Multi-system fusion intelligent substation relay protection dynamic fixed inspection method |
| CN111931605B (en) * | 2020-07-23 | 2024-05-14 | 中核核电运行管理有限公司 | Nuclear power plant high-risk operation intelligent monitoring system and method |
| CN111814742A (en) * | 2020-07-29 | 2020-10-23 | 南方电网数字电网研究院有限公司 | Knife switch state identification method based on deep learning |
| CN112083000B (en) * | 2020-08-12 | 2022-12-02 | 中国电力科学研究院有限公司 | Intelligent identification method and system for appearance defects of substation equipment |
| CN112183194B (en) * | 2020-08-19 | 2024-01-19 | 中国南方电网有限责任公司超高压输电公司广州局 | Non-contact type convertor station workstation equipment parameter identification method and system |
| CN112364740B (en) * | 2020-10-30 | 2024-04-19 | 交控科技股份有限公司 | Unmanned aerial vehicle room monitoring method and system based on computer vision |
| CN112484908A (en) * | 2020-11-17 | 2021-03-12 | 广东电网有限责任公司阳江供电局 | Online monitoring system for gas pressure of SF6 circuit breaker |
| CN112525921B (en) * | 2020-11-23 | 2023-06-30 | 卡奥斯工业智能研究院(青岛)有限公司 | Household appliance appearance detection equipment and image transmission method implemented by same |
| CN112669316B (en) * | 2021-01-29 | 2023-05-30 | 南方电网调峰调频发电有限公司 | Power production abnormality monitoring method, device, computer equipment and storage medium |
| CN113008896A (en) * | 2021-02-23 | 2021-06-22 | 江苏力沛电力工程技术服务有限公司 | Power failure detection device based on machine vision |
| CN113569714A (en) * | 2021-07-24 | 2021-10-29 | 国网河南省电力公司检修公司 | Intelligent image recognition system of transformer substation based on unmanned aerial vehicle patrols and examines |
| CN113762185A (en) * | 2021-09-14 | 2021-12-07 | 珠海理想科技有限公司 | Intelligent system for achieving state acquisition of power equipment based on computer vision |
| CN113947754A (en) * | 2021-10-15 | 2022-01-18 | 大连海事大学 | Vision-based ship machinery running state monitoring method and system and storage medium |
| CN114492636B (en) * | 2022-01-26 | 2023-11-24 | 上海交通大学 | Transformer winding state signal acquisition system |
| CN117406160B (en) * | 2023-10-23 | 2024-05-17 | 国网黑龙江省电力有限公司营销服务中心 | Intelligent ammeter fault diagnosis system based on historical state comparison |
| CN117499596A (en) * | 2023-11-15 | 2024-02-02 | 岳阳华润燃气有限公司 | Gas station inspection system and method based on intelligent AR glasses |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005346463A (en) * | 2004-06-03 | 2005-12-15 | Toshiba Corp | Remote supervisory device and remote supervisory method for electric power facility |
| JP2007006283A (en) * | 2005-06-24 | 2007-01-11 | Chugoku Electric Power Co Inc:The | Circuit monitoring system |
| CN102082466A (en) * | 2010-10-15 | 2011-06-01 | 重庆市电力公司超高压局 | Intelligent inspection robot system for transformer substation equipment |
| CN201998168U (en) * | 2010-12-29 | 2011-10-05 | 浙江省电力公司 | Visual servo-based accurate tripod head positioning system for movable robot |
| CN102280826B (en) * | 2011-07-30 | 2013-11-20 | 山东鲁能智能技术有限公司 | Intelligent robot inspection system and intelligent robot inspection method for transformer station |
| CN102521560B (en) * | 2011-11-14 | 2014-11-19 | 上海交通大学 | Instrument pointer image identification method of high-robustness rod |
-
2012
- 2012-06-29 CN CN201210222443.6A patent/CN102722166B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN102722166A (en) | 2012-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102722166B (en) | Intelligent vision detection system and state detection method of transformer substation device | |
| CN112910094B (en) | Remote automatic transformer substation inspection system and method based on ubiquitous power Internet of things | |
| CN106771856B (en) | Electric power transmission line lightning stroke point determination method based on unmanned aerial vehicle technology | |
| CN108957240A (en) | Electric network fault is remotely located method and system | |
| CN109683609B (en) | Intelligent power inspection system and method | |
| CN104994334A (en) | Automatic substation monitoring method based on real-time video | |
| CN106774322B (en) | Photovoltaic power station inspection system and operation method thereof | |
| CN204465736U (en) | A kind of power transmission line intelligent long distance control system based on Internet of Things | |
| CN111754483A (en) | Method and system for identifying abnormal equipment based on thermal imager | |
| CN105930837A (en) | Transformer station instrument equipment image recognition method based on autonomous routing inspection robot | |
| CN203455912U (en) | System for on-line monitoring foreign matter interference of power transmission line | |
| CN103499774A (en) | Electricity transmission insulator arc-over on-line monitoring and safety early-warning device | |
| CN205265369U (en) | Cable and tunnel operation and maintenance management field data application apparatus | |
| CN102446390A (en) | Method and system for safety detection and early warning of monitoring areas near power transmission lines | |
| KR102196719B1 (en) | System for measuring and forecasting of fine dust | |
| CN103427366A (en) | Helicopter airborne system for controlling and recognizing power transmission line | |
| CN103595125A (en) | An electrical device on-line monitoring system based on an image identification technique | |
| CN106650746B (en) | Transformer substation pointer instrument identification method based on angle step length | |
| CN102798469B (en) | Angular-point-characteristic-based method for accurately measuring temperature of electrical equipment | |
| CN203759160U (en) | Integrated intelligent monitoring system of transformer station | |
| CN110492616A (en) | A kind of intelligent patrol auxiliary system and inspection method for substation | |
| CN105655920A (en) | Multifunctional air-ground dual-purpose electric unmanned aerial vehicle | |
| CN110188786B (en) | Robot image recognition algorithm for leakage current of pot-type lightning arrester | |
| CN102540278A (en) | Online monitoring system for multiple weather parameters | |
| CN204066357U (en) | A kind of data transmission set of transmission line long-distance Intelligent line patrolling |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| ASS | Succession or assignment of patent right |
Owner name: STATE ELECTRIC NET CROP. Effective date: 20120905 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20120905 Address after: 250002, No. 1, South Second Ring Road, Shizhong District, Shandong, Ji'nan Applicant after: Electric Power Research Institute of Shandong Electric Power Corporation Applicant after: State Grid Corporation of China Address before: 250002, No. 1, South Second Ring Road, Shizhong District, Shandong, Ji'nan Applicant before: Electric Power Research Institute of Shandong Electric Power Corporation |
|
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 250002, No. 1, South Second Ring Road, Shizhong District, Shandong, Ji'nan Co-patentee after: State Grid Corporation of China Patentee after: Electric Power Research Institute of State Grid Shandong Electric Power Company Address before: 250002, No. 1, South Second Ring Road, Shizhong District, Shandong, Ji'nan Co-patentee before: State Grid Corporation of China Patentee before: Electric Power Research Institute of Shandong Electric Power Corporation |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20121010 Assignee: National Network Intelligent Technology Co., Ltd. Assignor: Electric Power Research Institute of State Grid Shandong Electric Power Company Contract record no.: X2019370000006 Denomination of invention: Intelligent vision detection system and state detection method of transformer substation device Granted publication date: 20150304 License type: Exclusive License Record date: 20191014 |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201028 Address after: 250101 Electric Power Intelligent Robot Production Project 101 in Jinan City, Shandong Province, South of Feiyue Avenue and East of No. 26 Road (ICT Industrial Park) Patentee after: National Network Intelligent Technology Co.,Ltd. Address before: 250002, No. 1, South Second Ring Road, Shizhong District, Shandong, Ji'nan Patentee before: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Patentee before: STATE GRID CORPORATION OF CHINA |
|
| EC01 | Cancellation of recordation of patent licensing contract | ||
| EC01 | Cancellation of recordation of patent licensing contract |
Assignee: National Network Intelligent Technology Co.,Ltd. Assignor: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Contract record no.: X2019370000006 Date of cancellation: 20210324 |