CN113794277A - Method and system for identifying pressing plate state image - Google Patents
Method and system for identifying pressing plate state image Download PDFInfo
- Publication number
- CN113794277A CN113794277A CN202110980430.4A CN202110980430A CN113794277A CN 113794277 A CN113794277 A CN 113794277A CN 202110980430 A CN202110980430 A CN 202110980430A CN 113794277 A CN113794277 A CN 113794277A
- Authority
- CN
- China
- Prior art keywords
- pressing plate
- screen cabinet
- state
- mobile terminal
- transformer substation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003825 pressing Methods 0.000 title claims abstract description 240
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012423 maintenance Methods 0.000 claims abstract description 25
- 238000007689 inspection Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 33
- 238000013528 artificial neural network Methods 0.000 claims description 32
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000005266 casting Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
- G06K17/0025—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device the arrangement consisting of a wireless interrogation device in combination with a device for optically marking the record carrier
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- H02J13/00006—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 information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00022—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 information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission
- H02J13/00024—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 information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission by means of mobile telephony
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Power Engineering (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a pressing plate state image identification method and a pressing plate state image identification system, which can be used for verifying an operation result when an operation and maintenance person executes pressing plate switching operation on a transformer substation screen cabinet according to an electronic operation ticket, wherein the identification method identifies the current state of each pressing plate of the transformer substation screen cabinet after the pressing plate switching operation by a mobile terminal APP, also identifies a label at the transformer substation screen cabinet by the mobile terminal APP, and inquires the pressing plate switching target state of the transformer substation screen cabinet after the pressing plate switching operation from a pressing plate account management module according to the label identification result; when one-step or multi-step pressing plate feeding and withdrawing operations are executed according to the electronic operation ticket, the identification method checks the identified current state of the pressing plate according to the inquired pressing plate feeding and withdrawing target state, and prevents the subsequent operation of the pressing plate in the electronic operation ticket when the pressing plate state identification result is not consistent with the pressing plate feeding and withdrawing target state; the invention can improve the efficiency and accuracy of the pressure plate state checking and reduce the workload and difficulty of the pressure plate state checking and pressure plate inspection.
Description
Technical Field
The invention relates to the technical field of power grid operation and maintenance, in particular to a method and a system for identifying a pressure plate state image.
Background
The checking work of the pressing plate switching-in and switching-out correctness in the pressing plate inspection, operation and maintenance daily switching-off and maintenance operation processes of the transformer substation is the important work of operation and maintenance daily, the checking of the pressing plate switching-in and switching-out state is generally carried out according to seasons and operation processes monthly in order to meet the requirement that the working efficiency and quality of operation and maintenance personnel are high.
The object of pressure plate state checking is the pressure plate on each protection device screen cabinet of the transformer substation, a 220kV conventional transformer substation generally has 50-80 screen cabinets, each screen cabinet has 32-64 pressure plates on average, the existing pressure plate on-off state checking depends on a working system and subjective judgment of personnel, whether dozens of pressure plates on each screen are on-off is judged in the pressure plate state checking process, and a lot of problems and difficulties exist for operation and maintenance personnel.
The prior art has the following defects and shortcomings in the operation of the pressing plate on and off.
The number of the multiple pressing plates of the screen cabinet facing the pressing plate on-off state checking process is large, the operation frequency is high, and operation and maintenance personnel subjectively judge whether the pressing plate on-off is correct or not and easily make mistakes;
when the state of the pressing plate is checked, each screen cabinet is basically consistent with the pressing plate on site, and no obvious mark is available to prompt whether the pressing plate of the screen cabinet is required to be thrown or withdrawn, so that operators can easily miss or wrongly patrol the pressing plate of the screen cabinet;
the pressing plate is not normally provided with a forced locking device for locking and forbidding the operation of switching in and switching out, the operation of switching in and switching out can be carried out at will after the screen cabinet door is opened, and the risk of mistakenly switching in, mistakenly switching out, leaking in, switching in and leaking out the pressing plate exists.
And the next operation can be carried out after the corresponding pressing plate operation step is operated in place without a mandatory means in the switching operation process.
Disclosure of Invention
The invention provides a method and a system for identifying a pressure plate state image, which can improve the efficiency and the accuracy of pressure plate state checking and reduce the workload and the difficulty of pressure plate state checking and pressure plate inspection.
The invention adopts the following technical scheme.
A pressing plate state image recognition method can be used for verifying operation results when operation and maintenance personnel perform pressing plate switching operation on a transformer substation screen cabinet according to an electronic operation ticket, the recognition method uses a mobile terminal APP to recognize the current state of each pressing plate of the transformer substation screen cabinet after the pressing plate switching operation, and also uses the mobile terminal APP to recognize a label at the transformer substation screen cabinet, and inquires about the pressing plate switching target state of the transformer substation screen cabinet after the pressing plate switching operation from a pressing plate account management module according to the label recognition result; when one-step or multi-step pressing plate feeding and withdrawing operations are executed according to the electronic operation ticket, the identification method verifies the operation result of the identified current state of the pressing plate according to the inquired pressing plate feeding and withdrawing target state, and prevents the subsequent operation of the pressing plate in the electronic operation ticket when the pressing plate state identification result is not consistent with the pressing plate feeding and withdrawing target state.
A pressing plate state image recognition system is used for the recognition method, and comprises a pressing plate standing book management module, a mobile terminal capable of storing electronic operation tickets and a label attached to a transformer substation screen cabinet; the tag is provided with a screen cabinet two-dimensional code which can be recognized and read by the mobile terminal; recording the unique ID of the transformer substation screen cabinet by the screen cabinet two-dimensional code; the mobile terminal APP identifies the state of the pressing plate or identifies and reads a transformer substation screen cabinet label through a camera of the mobile terminal;
the mobile terminal is connected with the pressing plate standing book management module through a network; when an operation and maintenance person executes a pressing plate throwing-back operation on a current screen cabinet according to an electronic operation ticket, a mobile terminal camera is used for recognizing a label of the screen cabinet, judging whether the current screen cabinet is a target screen cabinet of the electronic operation ticket or not according to a recognition result, and inquiring a pressing plate throwing-back target state of the screen cabinet from a pressing plate ledger management module;
after the operation and maintenance personnel execute one-step or multi-step pressing plate switching operation according to the electronic operation ticket, the current state of the pressing plate of the screen cabinet is identified by the camera, the identification result and the pressing plate switching target state are compared by the mobile terminal, and the result of the pressing plate switching operation is verified.
After the operation and maintenance personnel perform pressing plate putting-in and putting-out operation on the transformer substation cabinet, the operation result is verified by using the mobile terminal to identify the state of the pressing plate; and when the pressure plate state identification result does not accord with the pressure plate throwing-returning target state, the mobile terminal prohibits executing the subsequent operation steps in the electronic operation ticket until the current state of the pressure plate identified by the mobile terminal accords with the pressure plate throwing-returning target state in the pressure plate ledger.
A plurality of pressing plates which are regularly arranged in a row-column mode are arranged at the transformer substation screen cabinet; the throwing and retreating states of all the pressing plates in the same screen cabinet can be shot in the same picture by the mobile terminal; the pressing plate standing book management module stores pressing plate standing book data; the pressing plate standing book data comprise pressing plate names and pressing plate row values; the row and column value records of the pressing plates correspond to the transformer substation cabinet, and the row and column positions and the correct pressing plate throwing and retreating states of all the pressing plates at the transformer substation cabinet are recorded.
The mobile terminal is a handheld mobile terminal and is provided with a pressing plate image acquisition and analysis module; when the mobile terminal enters a pressing plate image acquisition mode to identify the current state of each pressing plate of the transformer substation screen cabinet, the pressing plate image acquisition and analysis module firstly reads the two-dimensional code of the screen cabinet through identification to check whether the screen cabinet is an identification target corresponding to the electronic operation ticket, and then identifies the current state of each pressing plate corresponding to the row and column positions of the screen cabinet by using a pressing plate image identification AI algorithm according to the pressing plate row and column values recorded by pressing plate account data after confirming that the screen cabinet is the identification target, and evaluates the current state.
The handheld mobile terminal is also provided with a pressing plate state identification result display unit module, and the pressing plate image acquisition and analysis module outputs an identification result value to the pressing plate state identification result display unit module after finishing the pressing plate state identification;
the pressing plate state identification result display unit module receives pressing plate state identification result information given by the pressing plate image acquisition and analysis module, highlights prompt warning information in a color or character mode and the like, clearly expresses whether the current screen cabinet has the phenomenon that the screen cabinet is missed or not, and the pressing plate state is normal or wrong at the current corresponding position of the screen cabinet by arranging graphs with two different colors according to the row and column positions of each pressing plate.
The pressing plate image recognition AI algorithm is based on a neural network, and the training of the neural network comprises the following steps;
step A1, taking pictures of the pressing plate under various light rays and angles by different personnel to collect training samples; the acquisition amount of the training samples is that each kind of pressing plate is not less than 20 matrix images, and the divided and closed states of the pressing plates respectively account for 40-60%;
a2, carrying out accurate sample labeling on the collected training samples through sample labeling software;
a3, generating a training set and a test set according to the sample, wherein the training set is used for training the neural network, and the test set is used for testing the recognition rate of the neural network; training of the neural network is performed with a dark neural network learning framework using a computing device with GPU acceleration;
step A4, in the training process of the neural network, optimizing by parameter adjustment, namely verifying the network generated by training by using a test set after the training of the neural network is finished, and continuously adjusting and optimizing according to the test result to generate the neural network meeting the requirements; and obtaining a neural network recognition engine model including the weight file.
When the identification system is used for inspecting the pressing plate, the pressing plate image acquisition and analysis module judges whether the screen cabinet is an inspection target according to the identified screen cabinet two-dimensional code, and then quickly and automatically checks and checks the pressing plate throwing and withdrawing correctness of each screen cabinet according to the pressing plate account data record, and prompts a pressing plate state identification result.
The mobile terminal is provided with an electronic ticket APP; the electronic ticket APP is connected with an anti-misoperation cloud module of the transformer substation anti-misoperation system through a wireless network to obtain an electronic operation ticket; the anti-misoperation cloud module comprises a pressing plate standing book management module.
According to the invention, through the method for identifying the pressure plate state image, the efficiency and the accuracy of pressure plate state checking can be improved, and the workload and the difficulty of pressure plate state checking and pressure plate inspection are reduced.
In the invention, the two-dimension code value of each screen cabinet and the platen table account are stored and managed at the mobile terminal, the unique ID of each screen cabinet is stored and recorded and is used as the two-dimension code value of the screen cabinet, the two-dimension code is consistent with the two-dimension code value content pasted on the corresponding screen cabinet, when the platen state is identified, the two-dimension code of the screen cabinet is identified firstly, the identified two-dimension code value of the screen cabinet and the two-dimension code value of the screen cabinet corresponding to the platen recorded by the system are used for judgment, if the two-dimension code values are consistent, the screen cabinet to which the platen belongs is identified currently, the uniqueness and the correctness of an identification object are ensured, and thus the problem that operators are prone to mistakenly patrol the platen of the screen cabinet is solved.
In the invention, the platen ledger data is mainly used for recording the name of the platen, the row and column values of the physical position of the platen on the screen cabinet, the stationary state of the platen and the screen information of the platen, when the platen state is identified, the row and column values of the screen cabinet recorded by the system and the identified platen row and column values are used for comparison and confirmation, the platen on the corresponding physical position is identified, then the platen state of each row and column value identified is compared with the current casting and withdrawing state of each platen recorded by the system, whether the current state of the platen meets the casting and withdrawing requirements can be analyzed and judged, thereby the current situation that misjudgment and misjudgment are easy to occur in the casting and withdrawing results of the platen by manual judgment is solved, and the operation result confirmation and routing inspection efficiency of the platen are improved.
When the scheme is implemented in the transformer substation, the two-dimensional code of the screen cabinet only needs to be pasted on the existing screen cabinet, the installation and operation structures of the existing pressing plate cannot be influenced and changed, and the daily work of the transformer substation is not easily interfered.
Drawings
The invention is described in further detail below with reference to the following figures and detailed description:
FIG. 1 is a schematic diagram of the principles of the present invention;
FIG. 2 is a schematic flow chart of the present invention during platen recognition;
FIG. 3 is a schematic illustration of the deployment of the present invention;
FIG. 4 is a schematic flow chart of the invention when the pressing plate is used for carrying out the operation of switching on and off the transformer substation screen cabinet according to the electronic operation ticket.
Detailed Description
As shown in the figure, the pressing plate state image identification method can be used for verifying an operation result when an operation and maintenance person executes pressing plate switching operation on a transformer substation screen cabinet according to an electronic operation ticket, the identification method identifies the current state of each pressing plate of the transformer substation screen cabinet after the pressing plate switching operation by a mobile terminal APP, also identifies a label at the transformer substation screen cabinet by the mobile terminal APP, and inquires about a pressing plate switching target state which the transformer substation screen cabinet should have after the pressing plate switching operation from a pressing plate account management module according to the label identification result; when one-step or multi-step pressing plate feeding and withdrawing operations are executed according to the electronic operation ticket, the identification method verifies the operation result of the identified current state of the pressing plate according to the inquired pressing plate feeding and withdrawing target state, and prevents the subsequent operation of the pressing plate in the electronic operation ticket when the pressing plate state identification result is not consistent with the pressing plate feeding and withdrawing target state.
A pressing plate state image recognition system is used for the recognition method, and comprises a pressing plate standing book management module, a mobile terminal capable of storing electronic operation tickets and a label attached to a transformer substation screen cabinet; the tag is provided with a screen cabinet two-dimensional code which can be recognized and read by the mobile terminal; recording the unique ID of the transformer substation screen cabinet by the screen cabinet two-dimensional code; the mobile terminal APP identifies the state of the pressing plate or identifies and reads a transformer substation screen cabinet label through a camera of the mobile terminal;
the mobile terminal is connected with the pressing plate standing book management module through a network; when an operation and maintenance person executes a pressing plate throwing-back operation on a current screen cabinet according to an electronic operation ticket, a mobile terminal camera is used for recognizing a label of the screen cabinet, judging whether the current screen cabinet is a target screen cabinet of the electronic operation ticket or not according to a recognition result, and inquiring a pressing plate throwing-back target state of the screen cabinet from a pressing plate ledger management module;
after the operation and maintenance personnel execute one-step or multi-step pressing plate switching operation according to the electronic operation ticket, the current state of the pressing plate of the screen cabinet is identified by the camera, the identification result and the pressing plate switching target state are compared by the mobile terminal, and the result of the pressing plate switching operation is verified.
After the operation and maintenance personnel perform pressing plate putting-in and putting-out operation on the transformer substation cabinet, the operation result is verified by using the mobile terminal to identify the state of the pressing plate; and when the pressure plate state identification result does not accord with the pressure plate throwing-returning target state, the mobile terminal prohibits executing the subsequent operation steps in the electronic operation ticket until the current state of the pressure plate identified by the mobile terminal accords with the pressure plate throwing-returning target state in the pressure plate ledger.
A plurality of pressing plates which are regularly arranged in a row-column mode are arranged at the transformer substation screen cabinet; the throwing and retreating states of all the pressing plates in the same screen cabinet can be shot in the same picture by the mobile terminal; the pressing plate standing book management module stores pressing plate standing book data; the pressing plate standing book data comprise pressing plate names and pressing plate row values; the row and column value records of the pressing plates correspond to the transformer substation cabinet, and the row and column positions and the correct pressing plate throwing and retreating states of all the pressing plates at the transformer substation cabinet are recorded.
The mobile terminal is a handheld mobile terminal and is provided with a pressing plate image acquisition and analysis module; when the mobile terminal enters a pressing plate image acquisition mode to identify the current state of each pressing plate of the transformer substation screen cabinet, the pressing plate image acquisition and analysis module firstly reads the two-dimensional code of the screen cabinet through identification to check whether the screen cabinet is an identification target corresponding to the electronic operation ticket, and then identifies the current state of each pressing plate corresponding to the row and column positions of the screen cabinet by using a pressing plate image identification AI algorithm according to the pressing plate row and column values recorded by pressing plate account data after confirming that the screen cabinet is the identification target, and evaluates the current state.
The handheld mobile terminal is also provided with a pressing plate state identification result display unit module, and the pressing plate image acquisition and analysis module outputs an identification result value to the pressing plate state identification result display unit module after finishing the pressing plate state identification;
the pressing plate state identification result display unit module receives pressing plate state identification result information given by the pressing plate image acquisition and analysis module, highlights prompt warning information in a color or character mode and the like, clearly expresses whether the current screen cabinet has the phenomenon that the screen cabinet is missed or not, and the pressing plate state is normal or wrong at the current corresponding position of the screen cabinet by arranging graphs with two different colors according to the row and column positions of each pressing plate.
The pressing plate image recognition AI algorithm is based on a neural network, and the training of the neural network comprises the following steps;
step A1, taking pictures of the pressing plate under various light rays and angles by different personnel to collect training samples; the acquisition amount of the training samples is that each kind of pressing plate is not less than 20 matrix images, and the divided and closed states of the pressing plates respectively account for 40-60%;
a2, carrying out accurate sample labeling on the collected training samples through sample labeling software;
a3, generating a training set and a test set according to the sample, wherein the training set is used for training the neural network, and the test set is used for testing the recognition rate of the neural network; training of the neural network is performed with a dark neural network learning framework using a computing device with GPU acceleration;
step A4, in the training process of the neural network, optimizing by parameter adjustment, namely verifying the network generated by training by using a test set after the training of the neural network is finished, and continuously adjusting and optimizing according to the test result to generate the neural network meeting the requirements; and obtaining a neural network recognition engine model including the weight file.
When the identification system is used for inspecting the pressing plate, the pressing plate image acquisition and analysis module judges whether the screen cabinet is an inspection target according to the identified screen cabinet two-dimensional code, and then quickly and automatically checks and checks the pressing plate throwing and withdrawing correctness of each screen cabinet according to the pressing plate account data record, and prompts a pressing plate state identification result.
The mobile terminal is provided with an electronic ticket APP; the electronic ticket APP is connected with an anti-misoperation cloud module of the transformer substation anti-misoperation system through a wireless network to obtain an electronic operation ticket; the anti-misoperation cloud module comprises a pressing plate standing book management module.
Example (b):
in the embodiment, the mobile terminal adopts an Android system, integrates a trained neural network weight file and an engine model, has an automatic two-dimensional code recognition function for checking the uniqueness of a recognition object, performs key step processing such as automatic photographing image acquisition, image denoising processing, target edge detection, layout arrangement analysis, state feature discrimination and the like on secondary equipment (such as a pressing plate) by controlling a camera of the mobile terminal to adjust a focal length, and calls a secondary equipment recognition engine (an AI algorithm for pressing plate image recognition based on a neural network) to complete state monitoring and judgment on the position of the pressing plate and output a recognition result.
The platen identification technical parameters of the secondary equipment identification engine are as follows:
and (3) identification comprehensive accuracy: = 96%
Detecting picture resolution >
Single platen target imaging: > = 20x20 pixels
Time consumed by single pressing plate matrix image recognition is < = 300ms
Difference between platen target and background gray values: > = 20
False alarm rate: < = 3% (under ideal environment)
The rate of missing reports: < = 3% (under ideal environment)
When the pressing plate switching operation is performed on the transformer substation cabinet, the operation and maintenance personnel use the mobile terminal to unlock the relevant pressing plate switching equipment, so that the operation and maintenance personnel can switch the pressing plate on and off; if the operation and maintenance personnel operate wrongly (such as missed operation and wrong operation), the state distribution of each pressing plate of the screen cabinet is inconsistent with the expected state of each pressing plate registered in the pressing plate ledger, so that the pressing plate state identification result of the mobile terminal after the pressing plate identification is carried out on the screen cabinet is inconsistent with the pressing plate operation and retreat target state, and the mobile terminal does not unlock equipment related to the subsequent operation of the pressing plates, so that the operation and maintenance personnel are prevented from continuing the subsequent operation of the pressing plates of the transformer substation screen cabinet.
At the moment, the operation and maintenance personnel can operate the unlocked pressing plate again to correct errors until the current state of the pressing plate identified by the mobile terminal meets the pressing plate throwing-withdrawing target state in the pressing plate ledger, and then unlock other related equipment to enter the subsequent operation of the pressing plate.
Claims (9)
1. A method for identifying a pressing plate state image can be used for verifying an operation result when an operation and maintenance worker executes pressing plate switching operation on a transformer substation screen cabinet according to an electronic operation ticket, and is characterized in that: the identification method comprises the steps that the current state of each pressing plate of a screen cabinet is identified through a mobile terminal APP after the pressing plate is subjected to switching operation, the mobile terminal APP is used for reading a label at the screen cabinet of the transformer substation, and the pressing plate switching target state which the screen cabinet is required to have after the pressing plate is subjected to switching operation is inquired from a pressing plate machine account management module according to the label reading result; when one-step or multi-step pressing plate feeding and withdrawing operations are executed according to the electronic operation ticket, the identification method verifies the operation result of the identified current state of the pressing plate according to the inquired pressing plate feeding and withdrawing target state, and prevents the subsequent operation of the pressing plate in the electronic operation ticket when the pressing plate state identification result is not consistent with the pressing plate feeding and withdrawing target state.
2. A platen state image recognition system for use in the recognition method of claim 1, characterized in that: the identification system comprises a pressing plate standing book management module, a mobile terminal capable of storing electronic operation tickets and a label attached to a screen cabinet of the transformer substation; the tag is provided with a screen cabinet two-dimensional code which can be recognized and read by the mobile terminal; recording the unique ID of the transformer substation screen cabinet by the screen cabinet two-dimensional code; the mobile terminal APP identifies the state of the pressing plate or identifies and reads a transformer substation screen cabinet label through a camera of the mobile terminal;
the mobile terminal is connected with the pressing plate standing book management module through a network; when an operation and maintenance person executes a pressing plate throwing-back operation on a current screen cabinet according to an electronic operation ticket, a mobile terminal camera is used for recognizing a label of the screen cabinet, judging whether the current screen cabinet is a target screen cabinet of the electronic operation ticket or not according to a recognition result, and inquiring a pressing plate throwing-back target state of the screen cabinet from a pressing plate ledger management module;
after the operation and maintenance personnel execute one-step or multi-step pressing plate switching operation according to the electronic operation ticket, the current state of the pressing plate of the screen cabinet is identified by the camera, the identification result and the pressing plate switching target state are compared by the mobile terminal, and the result of the pressing plate switching operation is verified.
3. The platen status image recognition system of claim 2, wherein: after the operation and maintenance personnel perform pressing plate putting-in and putting-out operation on the transformer substation cabinet, the operation result is verified by using the mobile terminal to identify the state of the pressing plate; and when the pressure plate state identification result does not accord with the pressure plate throwing-returning target state, the mobile terminal prohibits executing the subsequent operation steps in the electronic operation ticket until the current state of the pressure plate identified by the mobile terminal accords with the pressure plate throwing-returning target state in the pressure plate ledger.
4. The platen status image recognition system of claim 2, wherein: a plurality of pressing plates which are regularly arranged in a row-column mode are arranged at the transformer substation screen cabinet; the throwing and retreating states of all the pressing plates in the same screen cabinet can be shot in the same picture by the mobile terminal; the pressing plate standing book management module stores pressing plate standing book data; the pressing plate standing book data comprise pressing plate names and pressing plate row values; the row and column value records of the pressing plates correspond to the transformer substation cabinet, and the row and column positions and the correct pressing plate throwing and retreating states of all the pressing plates at the transformer substation cabinet are recorded.
5. The platen status image recognition system of claim 4, wherein: the mobile terminal is a handheld mobile terminal and is provided with a pressing plate image acquisition and analysis module; when the mobile terminal enters a pressing plate image acquisition mode to identify the current state of each pressing plate of the transformer substation screen cabinet, the pressing plate image acquisition and analysis module firstly reads the two-dimensional code of the screen cabinet through identification to check whether the screen cabinet is an identification target corresponding to the electronic operation ticket, and then identifies the current state of each pressing plate corresponding to the row and column positions of the screen cabinet by using a pressing plate image identification AI algorithm according to the pressing plate row and column values recorded by pressing plate account data after confirming that the screen cabinet is the identification target, and evaluates the current state.
6. The platen status image recognition system of claim 5, wherein: the handheld mobile terminal is also provided with a pressing plate state identification result display unit module, and the pressing plate image acquisition and analysis module outputs an identification result value to the pressing plate state identification result display unit module after finishing the pressing plate state identification;
the pressing plate state identification result display unit module receives pressing plate state identification result information given by the pressing plate image acquisition and analysis module, highlights prompt warning information in a color or character mode and the like, clearly expresses whether the current screen cabinet has the phenomenon that the screen cabinet is missed or not, and the pressing plate state is normal or wrong at the current corresponding position of the screen cabinet by arranging graphs with two different colors according to the row and column positions of each pressing plate.
7. The platen status image recognition system of claim 5, wherein: the pressing plate image recognition AI algorithm is based on a neural network, and the training of the neural network comprises the following steps;
step A1, taking pictures of the pressing plate under various light rays and angles by different personnel to collect training samples; the acquisition amount of the training samples is that each kind of pressing plate is not less than 20 matrix images, and the divided and closed states of the pressing plates respectively account for 40-60%;
a2, carrying out accurate sample labeling on the collected training samples through sample labeling software;
a3, generating a training set and a test set according to the sample, wherein the training set is used for training the neural network, and the test set is used for testing the recognition rate of the neural network; training of the neural network is performed with a dark neural network learning framework using a computing device with GPU acceleration;
step A4, in the training process of the neural network, optimizing by parameter adjustment, namely verifying the network generated by training by using a test set after the training of the neural network is finished, and continuously adjusting and optimizing according to the test result to generate the neural network meeting the requirements; and obtaining a neural network recognition engine model including the weight file.
8. The platen status image recognition system of claim 5, wherein: when the identification system is used for inspecting the pressing plate, the pressing plate image acquisition and analysis module judges whether the screen cabinet is an inspection target according to the identified screen cabinet two-dimensional code, and then quickly and automatically checks and checks the pressing plate throwing and withdrawing correctness of each screen cabinet according to the pressing plate account data record, and prompts a pressing plate state identification result.
9. The platen status image recognition system of claim 5, wherein: the mobile terminal is provided with an electronic ticket APP; the electronic ticket APP is connected with an anti-misoperation cloud module of the transformer substation anti-misoperation system through a wireless network to obtain an electronic operation ticket; the anti-misoperation cloud module comprises a pressing plate standing book management module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110980430.4A CN113794277A (en) | 2021-08-25 | 2021-08-25 | Method and system for identifying pressing plate state image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110980430.4A CN113794277A (en) | 2021-08-25 | 2021-08-25 | Method and system for identifying pressing plate state image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113794277A true CN113794277A (en) | 2021-12-14 |
Family
ID=79182117
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110980430.4A Pending CN113794277A (en) | 2021-08-25 | 2021-08-25 | Method and system for identifying pressing plate state image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113794277A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113869473A (en) * | 2021-09-30 | 2021-12-31 | 广东电网有限责任公司 | Intelligent checking method and device for fixed value of power distribution terminal |
CN117408973A (en) * | 2023-10-26 | 2024-01-16 | 国网四川省电力公司绵阳供电公司 | Method, terminal and electronic equipment for checking state of pressing plate of relay protection device of transformer substation |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190191805A1 (en) * | 2017-12-22 | 2019-06-27 | State Grid Hunan Electric Power Company Limited | Wearable equipment for substation maintenance mobile inspection and application method thereof |
CN112069902A (en) * | 2020-08-06 | 2020-12-11 | 许继集团有限公司 | Transformer substation cabinet pressing plate identification method and system |
CN112085710A (en) * | 2020-08-25 | 2020-12-15 | 国网福建省电力有限公司龙岩供电公司 | Protection constant value and pressure plate inspection system and method |
CN113054748A (en) * | 2021-04-22 | 2021-06-29 | 国网天津市电力公司 | Pressing plate state identification system and method based on image identification in moving operation and maintenance |
CN113094669A (en) * | 2021-03-26 | 2021-07-09 | 国家电网有限公司 | Remote identification operation unlocking intelligent monitoring method based on five-prevention lock |
CN113192508A (en) * | 2021-05-26 | 2021-07-30 | 国家电网有限公司 | Multifunctional intelligent power transformation operation and inspection virtual monitoring system and monitoring method thereof |
-
2021
- 2021-08-25 CN CN202110980430.4A patent/CN113794277A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190191805A1 (en) * | 2017-12-22 | 2019-06-27 | State Grid Hunan Electric Power Company Limited | Wearable equipment for substation maintenance mobile inspection and application method thereof |
CN112069902A (en) * | 2020-08-06 | 2020-12-11 | 许继集团有限公司 | Transformer substation cabinet pressing plate identification method and system |
CN112085710A (en) * | 2020-08-25 | 2020-12-15 | 国网福建省电力有限公司龙岩供电公司 | Protection constant value and pressure plate inspection system and method |
CN113094669A (en) * | 2021-03-26 | 2021-07-09 | 国家电网有限公司 | Remote identification operation unlocking intelligent monitoring method based on five-prevention lock |
CN113054748A (en) * | 2021-04-22 | 2021-06-29 | 国网天津市电力公司 | Pressing plate state identification system and method based on image identification in moving operation and maintenance |
CN113192508A (en) * | 2021-05-26 | 2021-07-30 | 国家电网有限公司 | Multifunctional intelligent power transformation operation and inspection virtual monitoring system and monitoring method thereof |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113869473A (en) * | 2021-09-30 | 2021-12-31 | 广东电网有限责任公司 | Intelligent checking method and device for fixed value of power distribution terminal |
CN117408973A (en) * | 2023-10-26 | 2024-01-16 | 国网四川省电力公司绵阳供电公司 | Method, terminal and electronic equipment for checking state of pressing plate of relay protection device of transformer substation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113794277A (en) | Method and system for identifying pressing plate state image | |
CN102616613B (en) | Elevator monitoring system | |
CN110826538A (en) | Abnormal off-duty identification system for electric power business hall | |
CN102616617B (en) | Elevator monitoring method | |
CN106626834A (en) | Stamping management system based on cloud platform | |
CN106327605A (en) | Inspection method | |
CN102602762A (en) | Elevator repair monitoring method | |
CN106952419A (en) | A kind of examination paper automatic distributing recycling machine | |
CN106153639A (en) | circuit board detecting method based on artificial intelligence and detection device thereof | |
CN111539313A (en) | Examination cheating behavior detection method and system | |
CN113872332B (en) | Intelligent operation and maintenance and error prevention management and control system and method for secondary pressure plates of transformer substation | |
CN110992302A (en) | Method and device for automatically checking pressure plate | |
CN116245735B (en) | Print control instrument operation supervision system based on data analysis | |
CN113054748A (en) | Pressing plate state identification system and method based on image identification in moving operation and maintenance | |
CN112085710A (en) | Protection constant value and pressure plate inspection system and method | |
CN113850562A (en) | Intelligent side station supervision method and system | |
CN113177614A (en) | Image recognition system and method for power supply switch cabinet of urban rail transit | |
CN112528742A (en) | State checking method and device for transformer substation pressure plate | |
CN107564128A (en) | A kind of computer room method for inspecting | |
CN104574636A (en) | Bill mandarin-duck-number recognition and check system | |
CN113378646A (en) | Freight train information identification system and identification method | |
CN106364189A (en) | In-parallel multi-head stamping machine capable of automatic recognition of document thickness | |
CN113139541B (en) | Power distribution cabinet dial nixie tube visual identification method based on deep learning | |
CN112016509B (en) | Personnel station abnormality reminding method and device | |
CN201522724U (en) | Detonator safety tracking management 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211214 |