CN108890652A - A kind of Intelligent Mobile Robot and method for inspecting substation equipment - Google Patents
A kind of Intelligent Mobile Robot and method for inspecting substation equipment Download PDFInfo
- Publication number
- CN108890652A CN108890652A CN201810684707.7A CN201810684707A CN108890652A CN 108890652 A CN108890652 A CN 108890652A CN 201810684707 A CN201810684707 A CN 201810684707A CN 108890652 A CN108890652 A CN 108890652A
- Authority
- CN
- China
- Prior art keywords
- target
- image information
- equipment
- scene
- routing inspection
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The present invention provides a kind of Intelligent Mobile Robot and method for inspecting substation equipment, which includes:Robot body, movement controller, image acquisition equipment, vision response unit, movement controller receives the patrol task of user's input, and generates control instruction according to patrol task, to drive robot body to be moved by preset path;Image acquisition equipment obtains image information, and image information is sent to vision response unit;Vision response unit receives image information, carries out the analysis of target question and answer to each equipment routing inspection target in image information respectively according to default vision Question-Answering Model and patrol task, generates analysis as a result, simultaneously adjusting the movement routine of robot body based on the analysis results.By applying the present invention, the image acquired in conjunction with crusing robot carries out movement routine adjustment, it can be improved the accuracy for obtaining equipment routing inspection target image, ensured the accuracy of inspection recognition result, improved the routing inspection efficiency of substation equipment.
Description
Technical field
The present invention relates to electric device maintenance fields, and in particular to a kind of Intelligent Mobile Robot and substation equipment patrol
Detecting method.
Background technique
Substation equipment and environment inspection are to ensure that the normal important method of substation operation, with the hair of smart grid
Exhibition, unattended operation transformer station quantity are continuously increased, and crusing robot is more and more applied in unattended operation transformer station.
Existing Intelligent Mobile Robot carries various sensors, instrument and video camera etc., in unattended operation transformer station
Inspection is carried out to outdoor high-tension apparatus and environment, the various data of substation's capital equipment and environment is obtained in real time, utilizes backstage
Parser can find defects of power equipment and exception in time, provide necessary guarantee for substation safety operation.But it is existing
Some Intelligent Mobile Robots can not accurately identify instrument all kinds of on substation equipment, when robot location pays no attention to
Think, when obtaining less than high-quality image information, the identification work of equipment will be unable to complete, to influence substation inspection work
It carries out;And when porcelain vase occur the common equipment appearance defect such as crackle, equipment leakage oil, existing substation inspection machine
Device people can not detected.
Summary of the invention
The technical problem to be solved in the present invention is that overcoming in the prior art when Intelligent Mobile Robot position is paid no attention to
Think, when obtaining less than high-quality image information, the identification work of equipment will be unable to complete, to influence substation inspection work
The problems such as accuracy.
According in a first aspect, the embodiment of the invention provides a kind of Intelligent Mobile Robots, including:Robot body,
Movement controller, image acquisition equipment, vision response unit, wherein the inspection that the movement controller receives user's input is appointed
Business, and control instruction is generated according to the patrol task, to drive the robot body to be moved by preset path;It is described
Image acquisition equipment obtains image information, and described image information is sent to the vision response unit;The vision question and answer
Unit receives described image information, according to default vision Question-Answering Model and the patrol task respectively in described image information
Each equipment routing inspection target carries out the analysis of target question and answer, generates analysis as a result, and adjusting the robot according to the analysis result
The movement routine of ontology.
With reference to first aspect, in the first embodiment of first aspect, the vision response unit includes:Scene analysis
Module, for being judged according to scene image information, the patrol task and the default vision Question-Answering Model in described image information
Whether the robot body reaches equipment routing inspection mesh target area;Scene adjustment instruction generation module, when the machine
When human body is not up to the region, the scene adjustment instruction generation module is according to the equipment routing inspection target and the scene
The positional relationship of image information generates scene adjustment instruction, and the scene adjustment instruction is sent to the movement controller;
The movement controller receives the scene adjustment instruction, and adjusts the movement routine according to the scene adjustment instruction.
With reference to first aspect, in the second embodiment of first aspect, the scene adjustment instruction generation module is specific
For executing following steps:According to the positional relationship of scene locating for the equipment routing inspection target and the scene image information,
Calculate the direction distance value of image center location in the scene and the scene image information;According to the direction distance value meter
The movement routine is calculated, and the scene adjustment instruction comprising the movement routine is generated according to the movement routine;By institute
It states scene adjustment instruction and is sent to the movement controller.
With reference to first aspect, in the third embodiment of first aspect, the vision response unit further includes:Target point
Module is analysed, when the robot body reaches the region, the target analysis module is set for controlling described image acquisition
It is standby to obtain target image information, and whether judged in the target image information according to the default vision Question-Answering Model comprising institute
State equipment routing inspection target;Target adjustment directive generation module, when the scene image information does not include the equipment routing inspection mesh
When mark, the target adjustment directive generation module is according to the positional relationship of the equipment routing inspection target and the target image information
Target adjustment instruction is generated, and target adjustment instruction is sent to the movement controller;The movement controller receives
The target adjustment instruction, and the movement routine is adjusted according to target adjustment instruction.
With reference to first aspect, in the 4th embodiment of first aspect, the target adjustment directive generation module is specific
For executing following steps:According to the positional relationship of the equipment routing inspection target and the target image information, set described in calculating
The offset distance value of image center location in standby inspection target and the target image information;It is calculated according to the offset distance value
The movement routine, and the target adjustment comprising the movement routine is generated according to the movement routine and is instructed;It will be described
Target adjustment instruction is sent to the movement controller.
With reference to first aspect, in the 5th embodiment of first aspect, the vision response unit further includes:State point
Module is analysed, when in the target image information including the equipment routing inspection target, the state analyzing module is for controlling institute
It states image acquisition equipment and obtains dbjective state image information, the dbjective state figure is analyzed according to the default vision Question-Answering Model
The working condition of equipment routing inspection target as described in information generates target inspection result.
With reference to first aspect, in the sixth embodiment of first aspect, the Intelligent Mobile Robot further includes:Nothing
Line communication unit, the robot body obtains the patrol task that user inputs by the wireless communication unit, by institute
It states patrol task and is sent to the movement controller, the robot body is also by the wireless communication unit by the target
Inspection result is sent to the user.
According to second aspect, the embodiment of the invention provides a kind of method for inspecting substation equipment, including:It is defeated to receive user
The patrol task entered, and drive the Intelligent Mobile Robot to enter inspection area according to the preset path in the patrol task
Domain;The image information of the region of patrolling and examining is obtained, and according to the patrol task and default vision Question-Answering Model respectively to described
Each equipment routing inspection target in image information carries out the analysis of target question and answer, generates analysis result;It is adjusted according to the analysis result
The movement routine of the robot body.
In conjunction with second aspect, in the first embodiment of second aspect, the method for inspecting substation equipment further includes:
Dbjective state image information is obtained, is analyzed according to the default vision Question-Answering Model and is set described in the dbjective state image information
The working condition of standby inspection target, generates target inspection result.
In conjunction with second aspect, in the second embodiment of second aspect, the method for inspecting substation equipment further includes:
According to default patrol task screening conditions, the target inspection result is sent to the user.
Technical solution of the present invention has the following advantages that:
Intelligent Mobile Robot provided in an embodiment of the present invention, including:Robot body, movement controller, image obtain
Equipment, vision response unit are taken, which receives the patrol task that user inputs, root by movement controller
Control instruction is generated according to patrol task, to drive robot body to be moved by preset path, is then set by image acquisition
It is standby to obtain image information, image information is sent to vision response unit;Vision response unit after receiving image information, according to
Default vision Question-Answering Model and patrol task carry out the analysis of target question and answer to each equipment routing inspection target in image information respectively, raw
At analysis as a result, adjusting the movement routine of robot body based on the analysis results.Machine is continuously adjusted by vision response unit
The movement routine of device human body believes the sharp picture of each equipment routing inspection target in the available patrol task of image acquisition equipment
Breath, improves picture quality, and the image acquired in conjunction with crusing robot carries out the adjustment of movement routine, can be improved setting for acquisition
The accuracy of standby inspection target image, has ensured the accuracy of inspection recognition result, has improved the routing inspection efficiency of substation equipment.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is the structural schematic diagram of Intelligent Mobile Robot in the embodiment of the present invention;
Fig. 2 is the structural schematic diagram of vision response unit in the embodiment of the present invention;
Fig. 3 is another structural schematic diagram of Intelligent Mobile Robot in the embodiment of the present invention;
Fig. 4 is the flow chart of method for inspecting substation equipment in the embodiment of the present invention;
Fig. 5 is another flow chart of method for inspecting substation equipment in the embodiment of the present invention.
Specific embodiment
Technical solution of the present invention is clearly and completely described below in conjunction with attached drawing, it is clear that described implementation
Example is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
As long as in addition, the non-structure each other of technical characteristic involved in invention described below different embodiments
It can be combined with each other at conflict.
Embodiment 1
The embodiment of the invention provides a kind of Intelligent Mobile Robots, as shown in Figure 1, the Intelligent Mobile Robot packet
It includes:Robot body 1, movement controller 2, image acquisition equipment 3, vision response unit 4 etc..
Wherein, movement controller 2 receives the patrol task of user's input, and generates control instruction according to patrol task, with
Driving robot body 1 is moved by preset path.Specifically, above-mentioned movement controller 2 is according to pre- in patrol task
If path positions the mobile destination of above-mentioned robot body 1, moving direction and moving distance are then determined, and
Control robot body 1 executes corresponding shift action, moves it to target area.
Image acquisition equipment 3 obtains image information, and image information is sent to vision response unit 4.Specifically, above-mentioned
Image acquisition equipment 3 can be for thermal camera or visible light camera etc..
Vision response unit 4 receives image information, is believed respectively image according to default vision Question-Answering Model and patrol task
Each equipment routing inspection target in breath carries out the analysis of target question and answer, generates analysis as a result, simultaneously adjusting robot sheet based on the analysis results
The movement routine of body 1.Specifically, above-mentioned default vision Question-Answering Model is according to existing image data base, by depth
It practises algorithm and is trained image-image problem-image answer corresponding relationship model that test obtains, the default vision question and answer mould
Image problem input in type exports composition problem pair with image answer.After input picture, vision question and answer mould is preset according to this
Each problem in type to carrying out the analysis of target question and answer, such as:Input is the image of image acquisition equipment acquisition, according to default view
Feel that the image input problem of Question-Answering Model carries out the analysis of target question and answer for current equipment routing inspection target, generates analysis result.
When analysis result, which meets patrol task, to be required, illustrate the position without adjusting crusing robot, i.e., without adjusting robot sheet
The movement routine of body can directly control the image information etc. that crusing robot further acquires equipment routing inspection target;When analysis is tied
When fruit does not meet patrol task requirement, illustrates the position for needing to adjust crusing robot at this time, that is, need to adjust robot body
Movement routine, then execute the processes such as subsequent Image Acquisition, analysis.
Intelligent Mobile Robot provided in an embodiment of the present invention carries out mobile road in conjunction with the image that crusing robot acquires
The adjustment of diameter can be improved the accuracy of the equipment routing inspection target image of acquisition, ensure the accuracy of inspection recognition result, mention
The high routing inspection efficiency of substation equipment.
In a preferred embodiment, as shown in Fig. 2, above-mentioned vision response unit 4 includes:
Scene analysis module 41, for being asked according to scene image information, patrol task and the default vision in image information
It answers model and judges whether robot body 1 reaches equipment routing inspection mesh target area.
Specifically, in one embodiment, after above-mentioned movement controller 2 drives robot body 1 to be moved to destination,
The above-mentioned shooting of image acquisition equipment 3 includes the scene image of robot location's current scene, and the scene analysis module 41 is using in advance
If vision Question-Answering Model judge the equipment routing inspection target area of wanted inspection in patrol task whether in the scene image, the figure
It can according to need setting acquisition parameters as obtaining equipment 3, adjust the range of the included image information of scene image.
Scene adjustment instruction generation module 42, when robot body 1 is not up to region, scene adjustment instruction generation module
42 generate scene adjustment instruction according to the positional relationship of equipment routing inspection target and scene image information, and scene adjustment instruction is sent out
It send to movement controller 2.
Specifically, in one embodiment, above-mentioned scene adjustment instruction generation module 42 is for executing following steps:
Step a:According to the positional relationship of scene locating for equipment routing inspection target and scene image information, scene and field are calculated
The direction distance value of image center location in scape image information.Such as:Scene locating for equipment routing inspection target is located at scene image
In information in front of image center location at 10 meters, then obtained direction distance value is 10 meters of front.
Step b:Movement routine is calculated according to direction distance value, and the scene comprising movement routine is generated according to movement routine
Adjustment instruction.Such as when direction distance value is 10 meters of front, which is to drive above-mentioned robot body 1 along working as
Preceding path moves forward 10 meters.
Step c:Scene adjustment instruction is sent to movement controller 2.Above-mentioned scene adjustment instruction generation module 42 is in life
After scene adjustment instruction, which is sent to movement controller 2, the shifting of robot body 1 is controlled by movement controller 2
It is dynamic.
In a preferred embodiment, as shown in Fig. 2, above-mentioned vision response unit 4 further includes:
Target analysis module 43, when robot body 1 reaches region, target analysis module 43 is for controlling image acquisition
Equipment 3 obtains target image information, and judges in target image information whether to patrol comprising equipment according to default vision Question-Answering Model
Examine target.
Specifically, in one embodiment, when robot body 1 reaches region, above-mentioned image acquisition equipment 3 is shot currently
The target image of robot location, the target analysis module 43 using default vision Question-Answering Model judge in the target image whether
Comprising equipment routing inspection target, which can according to need setting acquisition parameters, and adjustment target image includes figure
As the range of information.
Target adjustment directive generation module 44, when scene image information does not include equipment routing inspection target, target adjustment
Directive generation module 44 generates target adjustment instruction according to the positional relationship of equipment routing inspection target and target image information, and by mesh
Mark adjustment instruction is sent to movement controller 2.
Specifically, in one embodiment, above-mentioned target adjustment directive generation module 44 is for executing following steps:
Step d:According to the positional relationship of equipment routing inspection target and target image information, equipment routing inspection target and target are calculated
The offset distance value of image center location in image information.Such as:Equipment routing inspection target is located in target image information in image
On the left of heart position at 50cm, then obtained offset distance value is -50cm.
Step e:Movement routine is calculated according to offset distance value, and the target comprising movement routine is generated according to movement routine
Adjustment instruction.Such as-the 50cm when direction distance value is, target adjustment instruction are to drive above-mentioned robot body 1 to the left
Mobile 50cm.
Step f:Target adjustment instruction is sent to movement controller 2.Above-mentioned target adjustment directive generation module 44 is in life
After instructing at target adjustment, which is sent to movement controller 2, the shifting of robot body 1 is controlled by movement controller 2
It is dynamic.
In a preferred embodiment, as shown in Fig. 2, above-mentioned vision response unit 4 further includes:State analyzing module 45,
When in target image information including equipment routing inspection target, state analyzing module 45 obtains mesh for controlling image acquisition equipment 3
State image information is marked, the work shape of equipment routing inspection target in dbjective state image information is analyzed according to default vision Question-Answering Model
State generates target inspection result.
Specifically, in one embodiment, above-mentioned target inspection result includes:The work at present shape of equipment routing inspection target
State and the corresponding various image informations of the equipment routing inspection target, such as:When equipment routing inspection target is oil temperature gauge on transformer,
The target inspection result includes that oil temperature meter reading is abnormal/normal, work image of the oil temperature meter reading of shooting etc..To realize
Image processing work is completed on Intelligent Mobile Robot, improves routing inspection efficiency and accuracy, and avoiding will be all kinds of
Image data is transmitted to computer terminal and is handled, and improves routing inspection efficiency.
In a preferred embodiment, as shown in figure 3, above-mentioned Intelligent Mobile Robot further includes:Wireless communication unit
5, unit 5 obtains the patrol task that user inputs to robot body 1 by wireless communication, and patrol task is sent to action control
Device 2, also target inspection result is sent to user to robot body 1 by unit 5 by wireless communication.
Specifically, in one embodiment, above-mentioned wireless communication unit 5 can according to default patrol task screening conditions,
Target inspection result is sent to user, in practical applications, when equipment routing inspection target operation exception, is easy to cause equipment event
Barrier, there are security risks, therefore user may focus more on the equipment routing inspection target in abnormal work, at this point it is possible to will set
The working condition of standby inspection target only sends the mesh for being in abnormal operation as default patrol task screening conditions to user
Mark inspection effectively avoids delay caused by mass data as a result, to reduce volume of transmitted data, improves routing inspection efficiency, Jin Erjia
Fast troubleshooting speed.
Pass through the cooperative cooperating of above-mentioned each component part, Intelligent Mobile Robot provided in an embodiment of the present invention, knot
The image for closing crusing robot acquisition carries out the adjustment of movement routine, can be improved the accurate of the equipment routing inspection target image of acquisition
Degree, realizes and completes image processing work on Intelligent Mobile Robot, improve routing inspection efficiency and accuracy, and avoid
All kinds of image datas are transmitted to computer terminal to handle, volume of transmitted data is reduced, has ensured the accurate of inspection recognition result
Property, and then delay caused by mass data is effectively avoided, accelerate troubleshooting speed etc..
Below with reference to concrete application example, to the specific works of Intelligent Mobile Robot provided in an embodiment of the present invention
Process is described further.
Patrol task in the embodiment of the present invention is carried out the oil temperature gauge of transformer as equipment routing inspection target, is used
Image acquisition equipment 3 be video camera, firstly, movement controller 2 receive patrol task in preset path, according to preset path
Control instruction is generated, driving robot body 1 reaches scene according to preset path;Start video camera and acquire image, by acquisition
Image is sent to scene analysis module 41;Scene analysis module 41 utilizes default according to transformer patrol task and the image of input
Whether vision Question-Answering Model analysis Intelligent Mobile Robot reaches transformer scene;If scene is not met, pass through scene
Adjustment instruction generation module 42 sends scene adjustment instruction to movement controller 2;Scene adjusts movement controller 2 based on the received
Instruction control Intelligent Mobile Robot is moved to transformer scene;When Intelligent Mobile Robot is moved to transformer scene
Afterwards, starting video camera acquires new image and is sent to target analysis module 43;Target analysis module 43 is appointed according to transformer inspection
Can the new image of business and input find oil temperature gauge target using default vision Question-Answering Model analysis;If can not find oil temperature gauge
Target then sends target adjustment instruction to movement controller 2 by target adjustment directive generation module 44;Movement controller 2
Control Intelligent Mobile Robot is instructed to be moved at target image according to received target adjustment;When Intelligent Mobile Robot moves
When moving to target image, starting video camera acquisition oil temperature meter reading image is sent to state analyzing module 45;State analysis mould
Block 45 analyzes the oil temperature gauge using default vision Question-Answering Model according to transformer patrol task and the oil temperature meter reading image of input
Whether reading is normal/abnormal, can not such as judge, then adjusts Intelligent Mobile Robot in target area by movement controller 2
Position, and resurvey image;If the normal/abnormal target inspection of reading for obtaining the oil temperature gauge as a result, if by the mesh
Unit 5 is sent to user terminal by wireless communication for mark inspection result and oil temperature meter reading image;User receives and stores the inspection
The inspection of target is as a result, and input new patrol task, continuation inspection;Above procedure is repeated, until arriving this substation inspection
All tasks terminate.
Embodiment 2
Originally it applies example and a kind of method for inspecting substation equipment is provided, as shown in figure 4, the method for inspecting substation equipment includes:
Step S1:The patrol task of user's input is received, and is patrolled according to the preset path driving substation in patrol task
Inspection robot enters region of patrolling and examining.
Step S2:The image information of region of patrolling and examining is obtained, and right respectively according to patrol task and default vision Question-Answering Model
Each equipment routing inspection target in image information carries out the analysis of target question and answer, generates analysis result.
Step S3:The movement routine of robot body is adjusted based on the analysis results.
S1 to step S3 through the above steps, the method for inspecting substation equipment of the embodiment of the present invention, in conjunction with inspection machine
The image of people's acquisition carries out the adjustment of movement routine, can be improved the accuracy of the equipment routing inspection target image of acquisition, ensures
The accuracy of inspection recognition result improves the routing inspection efficiency of substation equipment.
In a preferred embodiment, as shown in figure 5, the method for inspecting substation equipment further includes:
Step S4:Dbjective state image information is obtained, dbjective state image information is analyzed according to default vision Question-Answering Model
The working condition of middle equipment routing inspection target generates target inspection result.
Step S5:According to default patrol task screening conditions, target inspection result is sent to user.
S1 to step S5 through the above steps, the method for inspecting substation equipment of the embodiment of the present invention, in conjunction with inspection machine
The image of people's acquisition carries out the adjustment of movement routine, can be improved the accuracy of the equipment routing inspection target image of acquisition, improves
Routing inspection efficiency and accuracy, and avoid and all kinds of image datas are transmitted to computer terminal handle, volume of transmitted data is reduced,
It has ensured the accuracy of inspection recognition result, and then has effectively avoided delay caused by mass data, accelerated troubleshooting speed etc..
Obviously, the above embodiments are merely examples for clarifying the description, and does not limit the embodiments.It is right
For those of ordinary skill in the art, can also make on the basis of the above description it is other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And it is extended from this it is obvious variation or
It changes still within the protection scope of the invention.
Claims (10)
1. a kind of Intelligent Mobile Robot, which is characterized in that including:Robot body (1), movement controller (2), image obtain
Take equipment (3), vision response unit (4), wherein
The movement controller (2) receives the patrol task of user's input, and generates control instruction according to the patrol task, with
The robot body (1) is driven to be moved by preset path;
Described image obtains equipment (3) and obtains image information, and described image information is sent to the vision response unit
(4);
The vision response unit (4) receives described image information, according to default vision Question-Answering Model and the patrol task point
Other each equipment routing inspection target in described image information carries out the analysis of target question and answer, generates analysis as a result, simultaneously according to described point
Analyse the movement routine that result adjusts the robot body (1).
2. Intelligent Mobile Robot according to claim 1, which is characterized in that the vision response unit (4) includes:
Scene analysis module (41), for according to scene image information, the patrol task and default in described image information
Vision Question-Answering Model judges whether the robot body (1) reaches equipment routing inspection mesh target area;
Scene adjustment instruction generation module (42), when the robot body (1) is not up to the region, the scene adjustment
Directive generation module (42) generates scene adjustment according to the positional relationship of the equipment routing inspection target and the scene image information
Instruction, and the scene adjustment instruction is sent to the movement controller (2);
The movement controller (2) receives the scene adjustment instruction, and adjusts the movement according to the scene adjustment instruction
Path.
3. Intelligent Mobile Robot according to claim 2, which is characterized in that the scene adjustment instruction generation module
(42) it is specifically used for executing following steps:
According to the positional relationship of scene locating for the equipment routing inspection target and the scene image information, calculate the scene with
The direction distance value of image center location in the scene image information;
The movement routine is calculated according to the direction distance value, and generating according to the movement routine includes the movement routine
The scene adjustment instruction;
The scene adjustment instruction is sent to the movement controller (2).
4. Intelligent Mobile Robot according to claim 2, which is characterized in that the vision response unit (4) is also wrapped
It includes:
Target analysis module (43), when the robot body (1) reaches the region, the target analysis module (43) is used
Equipment (3) are obtained in control described image and obtain target image information, and according to the default vision Question-Answering Model judgement
It whether include the equipment routing inspection target in target image information;
Target adjustment directive generation module (44), when the scene image information does not include the equipment routing inspection target, institute
It is raw according to the positional relationship of the equipment routing inspection target and the target image information to state target adjustment directive generation module (44)
It is instructed at target adjustment, and target adjustment instruction is sent to the movement controller (2);
The movement controller (2) receives the target adjustment instruction, and adjusts the movement according to target adjustment instruction
Path.
5. Intelligent Mobile Robot according to claim 4, which is characterized in that the target adjustment directive generation module
(44) it is specifically used for executing following steps:
According to the positional relationship of the equipment routing inspection target and the target image information, the equipment routing inspection target and institute are calculated
State the offset distance value of image center location in target image information;
The movement routine is calculated according to the offset distance value, and generating according to the movement routine includes the movement routine
The target adjustment instruction;
Target adjustment instruction is sent to the movement controller (2).
6. Intelligent Mobile Robot according to claim 4, which is characterized in that the vision response unit (4) is also wrapped
It includes:
State analyzing module (45), when in the target image information including the equipment routing inspection target, the state analysis
Module (45) obtains equipment (3) acquisition dbjective state image information for controlling described image, according to the default vision question and answer
The working condition of equipment routing inspection target described in dbjective state image information described in model analysis generates target inspection result.
7. Intelligent Mobile Robot according to claim 5, which is characterized in that further include:
Wireless communication unit (5), the robot body (1) obtain the institute of user's input by the wireless communication unit (5)
Patrol task is stated, the patrol task is sent to the movement controller (2), the robot body (1) is also by described
The target inspection result is sent to the user by wireless communication unit (5).
8. a kind of method for inspecting substation equipment, which is characterized in that including:
The patrol task of user's input is received, and the substation inspection machine is driven according to the preset path in the patrol task
Device people enters region of patrolling and examining;
The image information of the region of patrolling and examining is obtained, and according to the patrol task and default vision Question-Answering Model respectively to described
Each equipment routing inspection target in image information carries out the analysis of target question and answer, generates analysis result;
The movement routine of the robot body is adjusted according to the analysis result.
9. method for inspecting substation equipment according to claim 8, which is characterized in that further include:Obtain dbjective state figure
As information, the work of equipment routing inspection target described in the dbjective state image information is analyzed according to the default vision Question-Answering Model
Make state, generates target inspection result.
10. method for inspecting substation equipment according to claim 9, which is characterized in that further include:
According to default patrol task screening conditions, the target inspection result is sent to the user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810684707.7A CN108890652B (en) | 2018-06-28 | 2018-06-28 | Transformer substation inspection robot and transformer substation equipment inspection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810684707.7A CN108890652B (en) | 2018-06-28 | 2018-06-28 | Transformer substation inspection robot and transformer substation equipment inspection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108890652A true CN108890652A (en) | 2018-11-27 |
CN108890652B CN108890652B (en) | 2021-02-09 |
Family
ID=64346615
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810684707.7A Active CN108890652B (en) | 2018-06-28 | 2018-06-28 | Transformer substation inspection robot and transformer substation equipment inspection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108890652B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109739226A (en) * | 2018-12-27 | 2019-05-10 | 国网北京市电力公司 | Target inspection method for determining position and device |
CN109977874A (en) * | 2019-03-28 | 2019-07-05 | 北京易达图灵科技有限公司 | A kind of meter register method and device |
CN109979633A (en) * | 2019-04-08 | 2019-07-05 | 韦尔德海润(北京)智能科技有限公司 | A kind of nuclear power plant's secondary control system |
CN110430081A (en) * | 2019-08-13 | 2019-11-08 | 北京市天元网络技术股份有限公司 | The intelligent method for inspecting and device of automatic editing based on instruction |
CN110514957A (en) * | 2019-08-19 | 2019-11-29 | 深圳供电局有限公司 | Substation's automatic detecting method and platform |
CN110509278A (en) * | 2019-09-06 | 2019-11-29 | 云南电网有限责任公司电力科学研究院 | A kind of centralized management system and method for Intelligent Mobile Robot |
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 |
CN111415432A (en) * | 2020-03-20 | 2020-07-14 | 四川华能宝兴河水电有限责任公司 | Intelligent inspection method for hydropower station |
CN111966105A (en) * | 2020-08-24 | 2020-11-20 | 湖南凯迪工程科技有限公司 | Intelligent robot data acquisition method and visual interaction system thereof |
CN112329530A (en) * | 2020-09-30 | 2021-02-05 | 北京航空航天大学 | Method, device and system for detecting mounting state of bracket |
CN113095331A (en) * | 2021-04-22 | 2021-07-09 | 合肥工业大学 | Visual question answering method, system and equipment for appearance defects of electric equipment and storage medium thereof |
CN113324998A (en) * | 2021-05-13 | 2021-08-31 | 常州博康特材科技有限公司 | Production quality inspection supervision system for titanium alloy bars |
CN114140899A (en) * | 2021-12-20 | 2022-03-04 | 浙江交通职业技术学院 | Engineering inspection system and method based on artificial intelligence |
CN114723077A (en) * | 2022-03-04 | 2022-07-08 | 贵州电网有限责任公司 | Intelligent inspection method and system for transformer substation |
CN114721403A (en) * | 2022-06-02 | 2022-07-08 | 中国海洋大学 | Automatic driving control method and device based on OpenCV and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127180A (en) * | 2016-06-30 | 2016-11-16 | 广东电网有限责任公司电力科学研究院 | A kind of robot assisted localization method and device |
CN106514654A (en) * | 2016-11-11 | 2017-03-22 | 国网浙江宁海县供电公司 | Patrol method of robot and patrol robot |
US20180036890A1 (en) * | 2016-08-03 | 2018-02-08 | Kevin Cole Hollister | Autonomous inspection system |
CN107784310A (en) * | 2017-11-08 | 2018-03-09 | 浙江国自机器人技术有限公司 | Status information of equipment acquisition methods, device, system, storage medium and robot |
CN108205314A (en) * | 2016-12-19 | 2018-06-26 | 广东技术师范学院 | Based on the matched robot navigation device of stereoscopic vision and system |
-
2018
- 2018-06-28 CN CN201810684707.7A patent/CN108890652B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127180A (en) * | 2016-06-30 | 2016-11-16 | 广东电网有限责任公司电力科学研究院 | A kind of robot assisted localization method and device |
US20180036890A1 (en) * | 2016-08-03 | 2018-02-08 | Kevin Cole Hollister | Autonomous inspection system |
CN106514654A (en) * | 2016-11-11 | 2017-03-22 | 国网浙江宁海县供电公司 | Patrol method of robot and patrol robot |
CN108205314A (en) * | 2016-12-19 | 2018-06-26 | 广东技术师范学院 | Based on the matched robot navigation device of stereoscopic vision and system |
CN107784310A (en) * | 2017-11-08 | 2018-03-09 | 浙江国自机器人技术有限公司 | Status information of equipment acquisition methods, device, system, storage medium and robot |
Non-Patent Citations (1)
Title |
---|
张德秀: "基于Mean Shift算法和灰度模板匹配的运动目标主动跟踪", 《电脑知识与技术》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109739226A (en) * | 2018-12-27 | 2019-05-10 | 国网北京市电力公司 | Target inspection method for determining position and device |
CN109977874A (en) * | 2019-03-28 | 2019-07-05 | 北京易达图灵科技有限公司 | A kind of meter register method and device |
CN109979633A (en) * | 2019-04-08 | 2019-07-05 | 韦尔德海润(北京)智能科技有限公司 | A kind of nuclear power plant's secondary control system |
CN110430081A (en) * | 2019-08-13 | 2019-11-08 | 北京市天元网络技术股份有限公司 | The intelligent method for inspecting and device of automatic editing based on instruction |
CN110514957A (en) * | 2019-08-19 | 2019-11-29 | 深圳供电局有限公司 | Substation's automatic detecting method and platform |
CN110509278A (en) * | 2019-09-06 | 2019-11-29 | 云南电网有限责任公司电力科学研究院 | A kind of centralized management system and method for Intelligent Mobile Robot |
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 |
CN111415432A (en) * | 2020-03-20 | 2020-07-14 | 四川华能宝兴河水电有限责任公司 | Intelligent inspection method for hydropower station |
CN111966105A (en) * | 2020-08-24 | 2020-11-20 | 湖南凯迪工程科技有限公司 | Intelligent robot data acquisition method and visual interaction system thereof |
CN112329530A (en) * | 2020-09-30 | 2021-02-05 | 北京航空航天大学 | Method, device and system for detecting mounting state of bracket |
CN112329530B (en) * | 2020-09-30 | 2023-03-21 | 北京航空航天大学 | Method, device and system for detecting mounting state of bracket |
CN113095331A (en) * | 2021-04-22 | 2021-07-09 | 合肥工业大学 | Visual question answering method, system and equipment for appearance defects of electric equipment and storage medium thereof |
CN113324998A (en) * | 2021-05-13 | 2021-08-31 | 常州博康特材科技有限公司 | Production quality inspection supervision system for titanium alloy bars |
CN114140899A (en) * | 2021-12-20 | 2022-03-04 | 浙江交通职业技术学院 | Engineering inspection system and method based on artificial intelligence |
CN114723077A (en) * | 2022-03-04 | 2022-07-08 | 贵州电网有限责任公司 | Intelligent inspection method and system for transformer substation |
CN114721403A (en) * | 2022-06-02 | 2022-07-08 | 中国海洋大学 | Automatic driving control method and device based on OpenCV and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108890652B (en) | 2021-02-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108890652A (en) | A kind of Intelligent Mobile Robot and method for inspecting substation equipment | |
CN109977813A (en) | A kind of crusing robot object localization method based on deep learning frame | |
CN109978820B (en) | Unmanned aerial vehicle route acquisition method, system and equipment based on laser point cloud | |
CN110400387A (en) | A kind of joint method for inspecting, system and storage medium based on substation | |
CN104501737B (en) | A kind of device and method of liquid jet spraying boundary alignment | |
CN105171115B (en) | The flying shear control method of flying shear control system based on machine vision | |
CN111896549B (en) | Building crack monitoring system and method based on machine learning | |
CN103677274A (en) | Interactive projection method and system based on active vision | |
CN111985352B (en) | AI front-end substation inspection video real-time identification method and system | |
CN114093052A (en) | Intelligent inspection method and system suitable for machine room management | |
CN110244687A (en) | A kind of test macro of camera controller | |
CN105405115A (en) | Image module group alignment system and method thereof | |
CN104931070B (en) | A kind of optical signal injected simulation method | |
CN111055275A (en) | Action simulation method and device, computer readable storage medium and robot | |
CN111046943A (en) | Method and system for automatically identifying state of isolation switch of transformer substation | |
CN106326632A (en) | Object analyzing method and object analyzing system | |
CN108896658B (en) | Ultrasonic automatic detection method based on PLC | |
CN106454338A (en) | Method and apparatus for detecting picture display effect of electronic device | |
CN109885091A (en) | A kind of unmanned plane autonomous flight control method and system | |
CN111103306A (en) | Method for detecting and marking defects | |
CN117218311A (en) | Real-time three-dimensional modeling method and system based on unmanned aerial vehicle aerial image data | |
CN117197412A (en) | AR-based intelligent highway disease inspection system and method | |
CN107331279A (en) | Teaching apparatus and system | |
CN114419496A (en) | Image polling updating method and device, electronic equipment and storage medium | |
CN108520568A (en) | A kind of equipment indicating lamp positioning identifying method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |