CN111654106B - Power grid dispatching system based on image recognition technology in deep learning - Google Patents
Power grid dispatching system based on image recognition technology in deep learning Download PDFInfo
- Publication number
- CN111654106B CN111654106B CN202010528878.8A CN202010528878A CN111654106B CN 111654106 B CN111654106 B CN 111654106B CN 202010528878 A CN202010528878 A CN 202010528878A CN 111654106 B CN111654106 B CN 111654106B
- Authority
- CN
- China
- Prior art keywords
- image
- camera
- directional
- data
- target
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
- Y04S40/126—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment using wireless data transmission
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a power grid dispatching system based on an image recognition technology in deep learning, which belongs to the technical field of power grid dispatching and comprises an image recognition terminal and a directional acquisition terminal, wherein the power grid dispatching system based on the image recognition technology in deep learning is provided with a big differential data extraction and restoration system for intelligently preprocessing an acquired target image and extracting differential data in the target image in advance, so that a dispatcher can more quickly and accurately recognize the target image according to the differential data and simultaneously store the extracted differential data; the handheld acquisition end and the directional acquisition end are combined for use, so that the reason causing the difference of the target image can be quickly detected, and the image identification result can be quickly obtained.
Description
Technical Field
The invention relates to the technical field of power grid dispatching, in particular to a power grid dispatching system based on an image recognition technology in deep learning.
Background
Image recognition technology is an important field of artificial intelligence. It refers to a technique of performing object recognition on an image to recognize various different modes of objects and objects.
The power grid dispatching system is an important working platform for the operation of the power system. In the early stage of the development of the power system, due to the restriction of technologies such as automation and communication, a dispatcher generally manually inquires the field condition of each operating station by a telephone or the like so as to master the current operating state of the system. When a certain line or a certain device has a fault, the judgment is given mainly by the experience of a dispatcher so as to process the fault.
With the continuous development and improvement of computer technology, communication technology, database technology and electric power system analysis theory, in order to meet the requirements of power grid dispatching monitoring and control, advanced application software such as automatic power generation control, economic dispatching, dispatcher training simulation, safety analysis, state estimation, load prediction and the like are gradually added on the basis of a monitoring and data acquisition system, the power grid dispatching operation work is upgraded from an empirical stage to an analytical dispatching stage, and the reliability, stability and economy of the operation of an electric power system are improved.
The automatic judgment of the equipment state is realized through an intelligent image recognition technology, and the equipment state can be docked with a scheduling service in a service mode to become an auxiliary judgment basis for scheduling operation and fault exception handling, so that the operation handling efficiency is improved, and the safety level of a power grid is improved. For example, the judgment of the on/off state of the switch knife switch is mainly to recognize and judge the on/off indication plate and the auxiliary contact. The judgment of the state of the switch-ON/OFF indicator can be realized only by the mode of an image, the characteristics of the switch-ON/OFF indicator are obvious, mainly the ground color of red or green is matched with characters such as ON/OFF and switch-ON/OFF, and therefore, the image recognition algorithm of the switch-ON/OFF indicator is simple and direct.
However, the existing image recognition technology is applied to power grid dispatching, image analysis and comparison are also carried out manually, the efficiency is low, the judgment accuracy is low, in addition, the image acquisition technology in the image recognition technology is the basis, but external factors influencing the image acquisition are numerous, and the image accuracy directly influences the power grid fault detection result.
Disclosure of Invention
1. Technical problem to be solved
Aiming at the problems in the prior art, the invention aims to provide a power grid dispatching system based on an image recognition technology in deep learning, which intelligently preprocesses a collected target image by arranging a big differential data extraction and restoration system, extracts differential data in the target image in advance, enables a dispatcher to more quickly and accurately recognize the target image according to the differential data, stores the extracted differential data, and can quickly acquire a recognition result according to the existing differential data when extracting the same or similar differential data next time, thereby reducing unnecessary recognition work; the handheld acquisition end and the directional acquisition end are combined for use, so that the reason causing the difference of the target image can be quickly detected, and the image identification result can be quickly obtained.
2. Technical scheme
In order to solve the above problems, the present invention adopts the following technical solutions.
The invention relates to a power grid dispatching system based on an image recognition technology in deep learning, which comprises an image recognition terminal and a directional acquisition terminal, wherein the image recognition terminal comprises an image transmission system, a large differential data extraction and restoration system and an image contrast recognition system, the image transmission system is wirelessly connected with the directional acquisition terminal, the large differential data extraction and restoration system comprises a differential image extraction module, the differential image extraction module is connected with the image transmission system, the differential image extraction module is also connected with a multi-data transmission module and an ideal data reference library, the multi-data transmission module is connected with a differential data repository, the ideal data reference library is connected with an ideal data restoration module, the ideal data restoration module is connected with the image transmission system, and the multi-data transmission module is connected with the image contrast recognition system. The method comprises the steps of extracting the difference data in the target image in advance, enabling a dispatcher to identify the target image more quickly and accurately according to the difference data, storing the extracted difference data, and enabling the dispatcher to quickly acquire an identification result according to the existing difference data when the same or similar difference data are extracted next time, so that unnecessary identification work is reduced.
The invention can quickly detect the reason causing the difference of the target image (the target object is in failure or the image acquired by the directional acquisition end is inaccurate) by combining the handheld acquisition end and the directional acquisition end, thereby quickly acquiring the image identification result.
Further, handheld camera includes the handle, the upper end fixedly connected with controller of handle, the upper end fixedly connected with electric telescopic handle of controller, electric telescopic handle's upper end fixedly connected with electronic cloud platform, the upper end fixedly connected with of electronic cloud platform removes the camera.
Furthermore, the controller comprises an image acquisition system, a positioning system and a sighting system, wherein the image acquisition system and the positioning system are both connected with the directional acquisition end, and the controller plays roles of equipment connection, control command, data transmission and the like.
Further, remove the camera and be connected with image acquisition system, electric telescopic handle and electronic cloud platform all are connected with aiming system, and the removal camera plays image acquisition's effect, and the direction position of realizing removing the camera through electric telescopic handle's lift and the rotation of electronic cloud platform is adjusted, conveniently removes the camera and carries out image acquisition.
The power grid dispatching system based on the image recognition technology in the deep learning comprises a dispatching method as follows:
s1, acquiring images of the target object through the directional camera, and transmitting the target images to an image recognition terminal;
s2, the image transmission system transmits the target image to the difference data extraction and restoration system, and the difference image extraction module extracts the image data which are different from the reference image in the target image according to the reference image in the ideal data reference library to obtain a difference data image;
and S3, the multi-data transmission module transmits the extracted difference data images to a difference data storage library for storage, and transmits the difference data images and the target images to an image contrast identification system together, so that the difference data images and the target images are displayed at an image identification terminal, a dispatcher can quickly and accurately analyze the target images by combining the difference data images, the analysis results are two, wherein one result is that the target images are consistent with the reference images, and the other result is that the target images are inconsistent with the reference images.
Further, the reference image in the ideal data reference library in S2 is an image of the target object in the initial normal operation state acquired by the directional camera, and when the operation state of the power grid is changed in a later stage, the image acquired in the initial normal operation state loses the referential property, and at this time, image acquisition needs to be performed on the operation state again, and the newly acquired ideal image is replaced with the original ideal image through the ideal data restoration module.
Further, the handheld collection terminal is used in case of the occurrence of the result two in S3.
Further, the use method of the handheld acquisition end comprises the following steps:
the method comprises the following steps: closing the image acquisition process of the directional camera, and connecting the handheld camera and the directional camera through Bluetooth by a worker;
step two: the handle is held by hand, the electric holder is started to adjust the position of the mobile camera, the mobile camera firstly acquires images of a target object, the position of the mobile camera is adjusted again, the directional camera is acquired, and meanwhile, the positioning system is used for positioning the position information of the directional camera;
step three: and the image information of the directional camera and the target object and the position information of the directional camera are transmitted to the directional camera through the image acquisition system and the positioning system, and then transmitted to the image recognition terminal through the directional camera.
3. Advantageous effects
Compared with the prior art, the invention has the advantages that:
(1) according to the scheme, the big difference data extraction and restoration system is arranged to intelligently preprocess the collected target image and extract difference data in the target image in advance, so that a dispatcher can more quickly and accurately identify the target image according to the difference data, the extracted difference data is stored, and when the same or similar difference data is extracted next time, the dispatcher can quickly acquire an identification result according to the existing difference data, and unnecessary identification work is reduced.
(2) The invention can quickly detect the reason (the target object has a fault or the image acquired by the directional acquisition end is inaccurate) causing the difference of the target image by combining the handheld acquisition end and the directional acquisition end, thereby quickly acquiring the image identification result.
(3) When the target image acquired by the directional camera has obvious difference data, and the difference data is judged by people possibly caused by external factors (an obstacle appears on the lens of the directional camera, the image is not clear, and the like), at the moment, in order to acquire a more accurate target image, the reason of the difference data (a target object is in a fault or the image acquired by the directional acquisition end is not accurate) is judged, and a handheld acquisition end can be selected for image acquisition.
(4) The reference image in the ideal data reference library is an image of a target object in an initial normal operation state acquired by the directional camera, when the operation state of the power grid is changed in a later stage, the image acquired in the initial normal operation state loses the referential property, at the moment, the image acquisition needs to be carried out on the operation state again, and the newly acquired ideal image and the original ideal image are replaced through the ideal data restoration module.
Drawings
FIG. 1 is a first block diagram of the system of the present invention;
FIG. 2 is a block diagram of the system of the present invention;
FIG. 3 is a schematic diagram of the connection of a directional acquisition end and a handheld acquisition end of the present invention;
FIG. 4 is a perspective view of the hand held camera of the present invention;
fig. 5 is a system block diagram of the handheld acquisition end of the present invention.
The reference numbers in the figures illustrate:
the system comprises a directional camera 1, a handheld camera 2, a handle 21, a controller 22, an electric telescopic rod 23, an electric tripod head 24 and a mobile camera 25.
Detailed Description
The drawings in the embodiments of the invention will be combined; the technical scheme in the embodiment of the invention is clearly and completely described; obviously; the described embodiments are only some of the embodiments of the invention; but not all embodiments, are based on the embodiments of the invention; all other embodiments obtained by a person skilled in the art without making any inventive step; all fall within the scope of protection of the present invention.
In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "top/bottom", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "sleeved/connected," "connected," and the like are to be construed broadly, e.g., "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example (b):
please refer to fig. 1 and 2, the power grid dispatching system based on the image recognition technology in the deep learning includes an image recognition terminal and a directional acquisition end, the image recognition terminal includes an image transmission system, a big system for differential data extraction and restoration and an image contrast recognition system, the image transmission system is wirelessly connected with the directional acquisition end, the big system for differential data extraction and restoration includes a module for differential image extraction, the module for differential image extraction is connected with the image transmission system, the module for differential image extraction is further connected with a multi-data transmission module and an ideal data reference library, the multi-data transmission module is connected with a differential data repository, the ideal data reference library is connected with an ideal data restoration module, the ideal data restoration module is connected with the image transmission system, and the multi-data transmission module is connected with the image contrast recognition system.
Referring to fig. 3, the present invention further includes a handheld collecting end, the handheld collecting end includes a handheld camera 2, the directional collecting end includes a directional camera 1, the directional camera 1 is wirelessly connected with the handheld camera 2 through bluetooth, and the present invention can quickly detect the reason (the target object is faulty or the image collected by the directional collecting end is inaccurate) causing the difference of the target image by combining the handheld collecting end and the directional collecting end, so as to quickly obtain the image recognition result.
Referring to fig. 4, the hand-held camera 2 includes a handle 21, a controller 22 is fixedly connected to the upper end of the handle 21, an electric telescopic rod 23 is fixedly connected to the upper end of the controller 22, an electric pan-tilt 24 is fixedly connected to the upper end of the electric telescopic rod 23, a mobile camera 25 is fixedly connected to the upper end of the electric pan-tilt 24, referring to fig. 5, the controller 22 includes an image acquisition system, a positioning system and a sighting system, the image acquisition system and the positioning system are both connected to a directional acquisition end, the controller 22 plays roles of equipment connection, control command, data transmission and the like, the mobile camera 25 is connected to the image acquisition system, the electric telescopic rod 23 and the electric pan-tilt 24 are both connected to the sighting system, the mobile camera 25 plays a role of image acquisition, the adjustment of the directional position of the mobile camera 25 is realized by the lifting of the electric telescopic rod 23 and the rotation of the electric pan-tilt 24, the camera 25 is conveniently moved for image acquisition.
The power grid dispatching system based on the image recognition technology in the deep learning comprises a dispatching method as follows:
s1, acquiring an image of the target object through the directional camera 1, and transmitting the target image to an image recognition terminal;
s2, the image transmission system transmits the target image to the difference data extraction and restoration system, and the difference image extraction module extracts the image data which are different from the reference image in the target image according to the reference image in the ideal data reference library to obtain a difference data image;
and S3, the multi-data transmission module transmits the extracted difference data images to a difference data storage library for storage, and transmits the difference data images and the target images to an image contrast identification system together, so that the difference data images and the target images are displayed at an image identification terminal, a dispatcher can quickly and accurately analyze the target images by combining the difference data images, the analysis results are two, namely, the target images are consistent with the reference images, and the target images are inconsistent with the reference images.
The reference image in the ideal data reference library in S2 is an image of the target object acquired by the directional camera 1 in the initial normal operation state, and when the operation state of the power grid is changed in the later stage, the image acquired in the initial normal operation state loses the referential property, and at this time, the image acquisition needs to be performed on the operation state again, and the newly acquired ideal image is replaced with the original ideal image through the ideal data restoration module.
The handheld collecting end is used under the condition that a second result appears in S3, when the target image collected by the directional camera 1 has obvious difference data, and the difference data is judged by people possibly caused by external factors (an obstacle appears on the lens of the directional camera 1, the image is not clear, and the like), at the moment, in order to obtain a more accurate target image, the reason for the difference data (the target object has a fault or the image collected by the directional collecting end is not accurate) is judged, and the handheld collecting end can be selected to be used for collecting the image.
The use method of the handheld acquisition end comprises the following steps:
the method comprises the following steps: closing the image acquisition process of the directional camera 1, and connecting the handheld camera 2 with the directional camera 1 through Bluetooth by a worker;
step two: the handle 21 is held by hand, the electric pan-tilt 24 is started to adjust the position of the mobile camera 25, the target object is firstly subjected to image acquisition through the mobile camera 25, the position of the mobile camera 25 is adjusted again, the directional camera 1 is subjected to image acquisition, and meanwhile, the position information of the directional camera 1 is positioned through the positioning system;
step three: the image information of the directional camera 1 and the target object and the position information of the directional camera 1 are transmitted to the directional camera 1 through an image acquisition system and a positioning system, and then transmitted to an image recognition terminal through the directional camera 1.
When the target image acquired by the mobile camera 25 is consistent with the target image acquired by the directional camera 1 in S1, it indicates that the target image acquired by the directional camera 1 is accurate, and otherwise, it indicates that the image acquired by the directional camera 1 is interfered by external factors; when the positioning system detects that the position information of the directional camera 1 is inconsistent with the initial position information, it indicates that the acquisition position of the directional camera 1 is deviated, and errors may exist in the acquired image; by observing the images of the directional camera 1 collected by the mobile camera 25, it can be observed whether there is an obvious obstacle on the directional camera 1 to affect the image collection. The handheld camera 2 can obtain a more accurate target image, and can detect whether the image acquired by the directional camera 1 is in error or is interfered by external factors, so that the reason for the occurrence of the different data can be rapidly known.
According to the invention, the collected target image is intelligently preprocessed by the big difference data extraction and restoration system, the difference data in the target image is extracted in advance, so that a dispatcher can more quickly and accurately identify the target image according to the difference data, the extracted difference data is stored, and when the same or similar difference data is extracted next time, the dispatcher can quickly obtain an identification result according to the existing difference data, thereby reducing unnecessary identification work. In addition, the handheld acquisition end and the directional acquisition end are combined for use, so that the reason causing the difference of the target image can be quickly detected, and the image identification result can be quickly acquired.
The above; but are merely preferred embodiments of the invention; the scope of the invention is not limited thereto; any person skilled in the art is within the technical scope of the present disclosure; the technical scheme and the improved concept of the invention are equally replaced or changed; are intended to be covered by the scope of the present invention.
Claims (7)
1. Power grid dispatching system based on image recognition technology in deep learning, including image recognition terminal and directional collection end, its characterized in that: the image identification terminal comprises an image transmission system, a large differential data extraction and restoration system and an image contrast identification system, wherein the image transmission system is wirelessly connected with the directional acquisition end, the large differential data extraction and restoration system comprises a differential image extraction module, the differential image extraction module is connected with the image transmission system, the differential image extraction module extracts image data which is different from a reference image in a target image to obtain a differential data image, the differential image extraction module is further connected with a multi-data transmission module and an ideal data reference library, the multi-data transmission module is connected with a differential data repository, the ideal data reference library is connected with an ideal data restoration module, the ideal data restoration module is connected with the image transmission system, and the multi-data transmission module is connected with the image contrast identification system;
the device is characterized by further comprising a handheld acquisition end, wherein the handheld acquisition end comprises a handheld camera (2), the directional acquisition end comprises a directional camera (1), and the directional camera (1) is in wireless connection with the handheld camera (2) through Bluetooth;
the handheld camera (2) comprises a handle (21), the upper end of the handle (21) is fixedly connected with a controller (22), the upper end of the controller (22) is fixedly connected with an electric telescopic rod (23), the upper end of the electric telescopic rod (23) is fixedly connected with an electric pan-tilt (24), and the upper end of the electric pan-tilt (24) is fixedly connected with a mobile camera (25);
when the target image collected by the mobile camera (25) is consistent with the target image collected by the directional camera (1), the target image collected by the directional camera (1) is accurate, otherwise, the image collected by the directional camera (1) is interfered by external factors.
2. The power grid dispatching system based on image recognition technology in deep learning of claim 1, wherein: the controller (22) comprises an image acquisition system, a positioning system and a sighting system, wherein the image acquisition system and the positioning system are connected with the directional acquisition end.
3. The power grid dispatching system based on image recognition technology in deep learning of claim 2, wherein: the mobile camera (25) is connected with an image acquisition system, and the electric telescopic rod (23) and the electric holder (24) are both connected with a sighting system.
4. The power grid dispatching system based on image recognition technology in deep learning of claim 3, wherein: the scheduling method comprises the following steps:
s1, acquiring an image of the target object through the directional camera (1), and transmitting the target image to an image recognition terminal;
s2, the image transmission system transmits the target image to the difference data extraction and restoration system, and the difference image extraction module extracts the image data which are different from the reference image in the target image according to the reference image in the ideal data reference library to obtain a difference data image;
and S3, the multi-data transmission module transmits the extracted difference data images to a difference data storage library for storage, and transmits the difference data images and the target images to an image contrast identification system together, so that the difference data images and the target images are displayed at an image identification terminal, a dispatcher can quickly and accurately analyze the target images by combining the difference data images, the analysis results are two, wherein one result is that the target images are consistent with the reference images, and the other result is that the target images are inconsistent with the reference images.
5. The power grid dispatching system based on image recognition technology in deep learning of claim 4, wherein:
the reference image in the ideal data reference library in S2 is the image of the target object in the initial normal operation state acquired by the directional camera (1).
6. The power grid dispatching system based on image recognition technology in deep learning of claim 5, wherein: the handheld acquisition end is used in case of a result two in S3.
7. The power grid dispatching system based on image recognition technology in deep learning of claim 6, wherein: the use method of the handheld acquisition end comprises the following steps:
the method comprises the following steps: closing the image acquisition process of the directional camera (1), and connecting the handheld camera (2) with the directional camera (1) through Bluetooth by a worker;
step two: the method comprises the steps that a handle (21) is held by a hand, an electric pan-tilt (24) is started to adjust the position of a mobile camera (25), the mobile camera (25) is used for firstly collecting images of a target object, the position of the mobile camera (25) is adjusted again, the directional camera (1) is collected, and meanwhile, the positioning system is used for positioning the position information of the directional camera (1);
step three: the image information of the directional camera (1) and the target object and the position information of the directional camera (1) are transmitted to the directional camera (1) through the image acquisition system and the positioning system, and then transmitted to the image recognition terminal through the directional camera (1).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010528878.8A CN111654106B (en) | 2020-06-11 | 2020-06-11 | Power grid dispatching system based on image recognition technology in deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010528878.8A CN111654106B (en) | 2020-06-11 | 2020-06-11 | Power grid dispatching system based on image recognition technology in deep learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111654106A CN111654106A (en) | 2020-09-11 |
CN111654106B true CN111654106B (en) | 2021-08-24 |
Family
ID=72349100
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010528878.8A Expired - Fee Related CN111654106B (en) | 2020-06-11 | 2020-06-11 | Power grid dispatching system based on image recognition technology in deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111654106B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1157077A (en) * | 1994-07-26 | 1997-08-13 | 马克斯普罗体系有限公司 | Video security system |
CN103268501A (en) * | 2013-06-04 | 2013-08-28 | 成都思晗科技有限公司 | Image recognition method for intelligent transmission line patrol |
CN103279098A (en) * | 2013-05-17 | 2013-09-04 | 苏州福丰科技有限公司 | Electrical equipment monitoring device based on image identification |
CN203376551U (en) * | 2013-07-22 | 2014-01-01 | 张奉果 | Multifunctional videography/cinematography balancing support |
CN104581054A (en) * | 2014-12-22 | 2015-04-29 | 深圳供电局有限公司 | Power transmission line inspection method and system based on video |
CN109685075A (en) * | 2018-11-27 | 2019-04-26 | 山东鲁能软件技术有限公司 | A kind of power equipment recognition methods based on image, apparatus and system |
-
2020
- 2020-06-11 CN CN202010528878.8A patent/CN111654106B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1157077A (en) * | 1994-07-26 | 1997-08-13 | 马克斯普罗体系有限公司 | Video security system |
CN103279098A (en) * | 2013-05-17 | 2013-09-04 | 苏州福丰科技有限公司 | Electrical equipment monitoring device based on image identification |
CN103268501A (en) * | 2013-06-04 | 2013-08-28 | 成都思晗科技有限公司 | Image recognition method for intelligent transmission line patrol |
CN203376551U (en) * | 2013-07-22 | 2014-01-01 | 张奉果 | Multifunctional videography/cinematography balancing support |
CN104581054A (en) * | 2014-12-22 | 2015-04-29 | 深圳供电局有限公司 | Power transmission line inspection method and system based on video |
CN109685075A (en) * | 2018-11-27 | 2019-04-26 | 山东鲁能软件技术有限公司 | A kind of power equipment recognition methods based on image, apparatus and system |
Also Published As
Publication number | Publication date |
---|---|
CN111654106A (en) | 2020-09-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102722166B (en) | Intelligent vision detection system and state detection method of transformer substation device | |
CN107204587A (en) | A kind of method that use augmented reality makes an inspection tour power distribution network operation data | |
CN101984382A (en) | Method for intelligently inspection substation equipment by using robot | |
CN112270267B (en) | Camera shooting identification system capable of automatically capturing line faults | |
CN112651516A (en) | Intelligent inspection system and method for transformer substation machine room based on AR technology | |
CN110008937B (en) | Switch cabinet running state management monitoring system and method and computing equipment | |
CN207268846U (en) | Electric inspection process robot | |
CN210100021U (en) | Automatic obstacle-removing robot system for transformer substation | |
CN110807460A (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
CN105373130A (en) | Special device accident on-site information detection system based on stereo modeling | |
CN113177614A (en) | Image recognition system and method for power supply switch cabinet of urban rail transit | |
CN111654106B (en) | Power grid dispatching system based on image recognition technology in deep learning | |
CN211402669U (en) | Low-voltage distribution network leakage current monitoring device | |
CN112529840A (en) | SF6 inflation equipment pressure drop defect image recognition device | |
CN110148118B (en) | Switch cabinet grounding knife state non-contact monitoring method, system, medium and equipment | |
CN112348990A (en) | Power equipment inspection system | |
CN213582214U (en) | Data acquisition system for efficacy analysis | |
CN115690687A (en) | Safe wearing standard detection system based on deep learning technology | |
CN111562447B (en) | System and method for identifying voltage class of high-voltage overhead transmission line | |
CN115693911A (en) | Equipment state sensing system of power distribution network | |
CN113720309A (en) | Unmanned aerial vehicle remote sensing urban component data acquisition method | |
CN211060960U (en) | Electric power operation site monitoring device | |
CN114330477A (en) | Power equipment defect detection system and method based on mixed reality equipment | |
CN109034097B (en) | Image-based switch equipment inspection positioning method | |
CN107356242B (en) | Indoor positioning method and system for intelligent mobile equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210824 |
|
CF01 | Termination of patent right due to non-payment of annual fee |