CN112085710A - Protection constant value and pressure plate inspection system and method - Google Patents
Protection constant value and pressure plate inspection system and method Download PDFInfo
- Publication number
- CN112085710A CN112085710A CN202010860082.2A CN202010860082A CN112085710A CN 112085710 A CN112085710 A CN 112085710A CN 202010860082 A CN202010860082 A CN 202010860082A CN 112085710 A CN112085710 A CN 112085710A
- Authority
- CN
- China
- Prior art keywords
- pressing plate
- standard
- value data
- protection
- fixed value
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000003825 pressing Methods 0.000 claims abstract description 65
- 238000012549 training Methods 0.000 claims description 11
- 238000002372 labelling Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a system and a method for protecting fixed value and pressing plate inspection, comprising the following steps: the system comprises a mobile terminal, a screen cabinet identifier, a fixed value data comparison module and a pressing plate identification comparison module; the fixed value data comparison module associates the coding information corresponding to the screen cabinet identification with the standard fixed value data, compares the protection fixed value data acquired by the mobile terminal through the printer interface of the protection screen cabinet with the standard fixed value data and outputs a comparison result; the pressing plate identification comparison module associates the coded information corresponding to the screen cabinet identification with the state of the standard pressing plate, performs switching identification on the pressing plate running state image acquired by the mobile terminal through the camera, compares the pressing plate running state image with the state of the standard pressing plate and outputs a comparison result. The problems that the traditional protection setting value and the operation state of the pressing plate of the transformer substation are checked to be 'paper + manual record' and are prone to fatigue, error and labor consumption, efficiency is low and the like can be effectively solved, and the intelligent checking work and paperless operation of the protection setting value and the operation state of the pressing plate are achieved.
Description
Technical Field
The invention relates to the field of power maintenance, in particular to a protection constant value and pressure plate inspection system and a method.
Background
With the increasing stock of relay protection equipment, under the condition that the power utilization safety requirements of high-risk users such as industry, high-speed railways and the like are gradually increased, the power enterprises are forced to increase the irregular inspection work, particularly the inspection of a protection fixed value and the inspection of a pressing plate. The recent statistical data of protection supervision shows that the absolute value of accidents caused by the fact that the pressure plate is thrown and withdrawn by mistake or thrown and withdrawn without leakage is high, and the load loss is more serious, so that professionals are required to be regularly arranged to check the protection constant value and the operation state of the pressure plate.
The current protection definite value is checked and is usually the standard definite value list that the patrolman takes the paper to print, and to transformer substation's protection screen cabinet department, on-the-spot follow screen cabinet external connection commercial power to put through the printer, print the definite value list in the protection screen, and the manual work is checked one by one, and work is loaded down with trivial details, and the volume is big, makes mistakes easily.
The checking of the state of the pressing plate is generally carried out by manual 'paper + manual record', and the problems that the manual inspection workload is large, the efficiency is low, manual error inspection/omission occurs, operation and maintenance conditions cannot be controlled by managers, data communication with a production system (PMS) cannot be achieved and the like exist.
The following are the main problems of the prior art:
1. the manual checking workload is large and the efficiency is low
The manual 'paper + manual record' is checked, the protection screen cabinet needs to be checked one by one, the checked data is sorted, and the operation and maintenance personnel have large workload and low efficiency.
2. Manual wrong or missed checking
The operation and maintenance personnel check one by one, and the wrong check and the missed check are easily caused by negligence;
the correct switching modes of the multiple protection pressure plates are different and are changed frequently, so that operation and maintenance personnel are easy to check errors due to confusion or untimely understanding of changed information; the protection fixed value and the waveform data volume are large, and the manual work is not easy to remember.
3. The manager can not control and check the task condition
The administrator cannot manage and control the protection setting value and the operation state of the pressing plate to check the task execution condition, and the paper record is complicated and inconvenient to carry out problem tracing management aiming at identifying the information such as the recorded inspection room, the inspection date and the like.
Disclosure of Invention
The invention provides a protection constant value and pressure plate inspection system and a method aiming at the defects and shortcomings in the prior art.
The technical scheme is as follows:
the utility model provides a protection definite value and clamp plate system of patrolling and examining, its characterized in that includes: the system comprises a mobile terminal, a screen cabinet identifier, a fixed value data comparison module and a pressing plate identification comparison module; the fixed value data comparison module associates the coding information corresponding to the screen cabinet identification with the standard fixed value data, compares the protection fixed value data acquired by the mobile terminal through the printer interface of the protection screen cabinet with the standard fixed value data and outputs a comparison result; the pressing plate identification comparison module associates the coded information corresponding to the screen cabinet identification with the state of the standard pressing plate, performs switching identification on the pressing plate running state image acquired by the mobile terminal through the camera, compares the pressing plate running state image with the state of the standard pressing plate and outputs a comparison result.
Preferably, the image recognition model of the platen recognition alignment module is obtained by training through a YOLO V3 machine learning framework.
Preferably, the screen cabinet identifier is a two-dimensional code arranged on the protection screen cabinet.
Preferably, the fixed value data comparison module or the pressing plate identification comparison module selects corresponding standard fixed value data or a standard pressing plate state according to coding information extracted from the two-dimensional code image acquired by the mobile terminal through the camera.
Preferably, the fixed value data comparison module outputs data information inconsistent with standard fixed value data; and the pressing plate identification comparison module highlights the retreating state inconsistent with the standard pressing plate state.
Preferably, the training process of the image recognition model comprises the following steps:
step A1: generating a candidate region on a picture of a training set, and labeling the candidate region according to the position relation between the candidate region and a real frame on the picture; dividing a positive sample and a negative sample;
step A2: extracting picture characteristics by adopting a convolutional neural network and predicting the positions and the types of the candidate regions; taking each prediction frame as a sample, and labeling according to the position and the category of the real frame relative to the sample to obtain a label value;
step A3: and comparing the network predicted value with the label value to establish a loss function.
Preferably, the standard pressing plate state is obtained through a standard pressing plate image, and the fixed value data comparison module performs throw-back recognition and comparison on the pressing plate running state image through the following steps:
step B1: respectively detecting the pressure plate running state image and the standard pressure plate image according to the image identification model to generate a position coordinate and a label;
step B2: respectively carrying out secondary treatment, including: reducing the threshold value and removing the duplicate by the IOU, and outputting a framing position coordinate and a label;
step B3: sorting in a two-dimensional array mode respectively and outputting a matrix;
step B4: and comparing the output matrix of the pressure plate running state image and the standard pressure plate image, and outputting a comparison result.
And one of the inspection methods of the inspection system according to the protection fixed value and the pressing plate is characterized by comprising the following steps:
step C1: importing a standard fixed value data set to the mobile terminal;
step C2: scanning a screen cabinet identifier by adopting the mobile terminal, and associating coding information corresponding to the screen cabinet identifier with standard fixed value data corresponding to equipment to be inspected;
step C3: connecting the mobile terminal with a printer interface of a protection screen cabinet, setting a baud rate and acquiring protection constant value data;
step C4: and comparing the protection constant value data with standard constant value data and outputting a comparison result.
And according to the protection fixed value and the second inspection method of the pressing plate inspection system, the method is characterized by comprising the following steps:
step D1: importing a standard platen image set to the mobile terminal;
step D2: scanning a screen cabinet identifier by adopting the mobile terminal, and associating coding information corresponding to the screen cabinet identifier with a standard pressing plate image corresponding to equipment to be inspected;
step D3: shooting a pressure plate running state image of the equipment to be inspected by adopting the mobile terminal;
step D4: and performing on-off recognition on the pressure plate running state image, comparing the pressure plate running state image with a standard pressure plate state corresponding to the standard pressure plate image, and outputting a comparison result.
Compared with the existing manual checking mode, the method and the device have the advantages that the mobile terminal is used as a carrier, the screen cabinet identifier is used as the minimum execution unit, the protection constant value data are obtained by butting the printer interface of the protection screen cabinet and are compared with the standard data, and the comparison abnormal index data can be displayed; the operating state of the screen cabinet protective pressing plate can be rapidly identified by utilizing an image identification technology, and the abnormal operating state of the current pressing plate can be rapidly checked by comparing with the state of a standard pressing plate. The scheme can effectively solve the problems that the traditional protection fixed value and the operation state of the pressing plate of the transformer substation are checked to be paper and manual recording, so that the transformer substation is easy to fatigue, make mistakes, consume working hours and have low efficiency, and the checking work of the protection fixed value and the operation state of the pressing plate is intelligent and paperless.
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 training process of the YOLO V3 algorithm according to the embodiment of the present invention;
FIG. 2 is a schematic diagram of a platen image prediction and identification comparison process according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a system main interface according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an interface for acquiring protection-fixed-value data according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an output interface for comparing protection fixed value data according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating a protection fixed value data comparison result historical state interface according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a comparison result interface of the operation states of the pressing plates according to the embodiment of the present invention.
Detailed Description
In order to make the features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail as follows:
as shown in fig. 3, the present embodiment provides a protection constant value and pressure plate inspection system, including: the mobile terminal, the screen cabinet identification, the fixed value data comparison module and the pressing plate identification comparison module.
In this embodiment, the cabinet identifier is a two-dimensional code disposed on the protection cabinet.
The fixed value data comparison module associates the coding information corresponding to the screen cabinet identification with the standard fixed value data, compares the protection fixed value data acquired by the mobile terminal through the printer interface of the protection screen cabinet with the standard fixed value data and outputs a comparison result; the pressing plate identification comparison module associates the coded information corresponding to the screen cabinet identification with the standard pressing plate state, performs switching identification on the pressing plate running state image acquired by the mobile terminal through the camera, compares the pressing plate running state image with the standard pressing plate state and outputs a comparison result. The mobile terminal adopted in the embodiment is a tablet computer, and the hardware configuration is as follows:
CPU : Intel Cherrytrail Z8350 1.44G
RAM : 2G
ROM : 32GB
screen size 10.1 inch 16:10
Screen resolution of 800 × 1280 IPS screen
Rear 5.0MP camera
USB line for converting USB into micro 5P L =1.2M
Operating System windows 10
The corresponding function can be realized through the smart phone, the fixed value data comparison module and the pressing plate identification comparison module are installed in the mobile terminal in an app mode, and the comparison task can be effectively executed under the condition of no network environment and no flow cost pressure.
The process of using the system to carry out comparison operation of the fixed value data comprises the following steps:
step C1: importing a standard fixed value data set to the mobile terminal; for example, a template document corresponding to the device code provided by the bureau is imported through the PC 1;
step C2: scanning a screen cabinet identifier by using a mobile terminal, and associating coding information corresponding to the screen cabinet identifier with standard fixed value data corresponding to equipment to be inspected, as shown in fig. 3;
step C3: connecting the mobile terminal with a printer interface of a protection screen cabinet, setting a baud rate, and acquiring protection constant value data, wherein the interface is shown in fig. 4;
step C4: and comparing the protection constant value data with the standard constant value data and outputting a comparison result. As shown in fig. 5, the present embodiment may check information of occurrence of an anomaly and provide standard information for comparison, and as shown in fig. 6, the present embodiment further provides a function of querying historical anomaly information.
The process for checking the running state of the pressing plate by adopting the system comprises the following steps:
step D1: importing a standard pressing plate image set into the mobile terminal;
step D2: scanning a screen cabinet identifier by adopting a mobile terminal, and associating coding information corresponding to the screen cabinet identifier with a standard pressing plate image corresponding to equipment to be inspected;
step D3: shooting a pressure plate running state image of equipment to be inspected by adopting a mobile terminal;
step D4: the operation state image of the pressing plate is subjected to throw-back recognition, and compared with the standard pressing plate state corresponding to the standard pressing plate image, and a comparison result is output, as shown in fig. 7, the embodiment respectively outputs throw-back matrixes of the operation state image of the pressing plate and the standard pressing plate image, and marks inconsistent places.
In this embodiment, the image recognition model of the compression plate recognition alignment module is obtained by training through a YOLO V3 machine learning framework, which is based on a DARKNET model.
Specifically, as shown in fig. 1, the training process of the image recognition model includes the following steps:
step A1: generating a candidate region on the picture of the training set, and labeling the candidate region according to the position relation between the candidate region and the real frame on the picture; dividing a positive sample and a negative sample;
step A2: extracting picture characteristics by adopting a convolutional neural network and predicting the positions and the types of the candidate regions; taking each prediction frame as a sample, and labeling according to the position and the category of the real frame relative to the sample to obtain a label value;
step A3: and comparing the network predicted value with the label value to establish a loss function.
The basic idea of the algorithm can be divided into two parts: firstly, a series of candidate regions are generated on the picture according to a certain rule, and then the candidate regions are marked according to the position relation between the candidate regions and the real frame of the object on the picture. Those candidate regions that are close enough to the real box will be labeled as positive samples, with the position of the real box being targeted for the position of the positive samples. Those candidate regions that deviate more from the true box are then labeled as negative examples, which do not require prediction of location or category. And secondly, extracting picture features by using a convolutional neural network and predicting the positions and the types of the candidate regions. Therefore, each prediction box can be regarded as a sample, a label value is obtained by labeling the position and the category of the real box relative to the real box, the position and the category of the real box are predicted through a network model, and the loss function can be established by comparing the network prediction value with the label value.
As shown in fig. 2, in this embodiment, the standard platen state is obtained by a standard platen image, and the fixed value data comparison module performs the on-off recognition and comparison on the platen running state image by the following steps:
step B1: respectively detecting the pressure plate running state image and the standard pressure plate image according to the image identification model to generate a position coordinate and a label;
step B2: respectively carrying out secondary treatment, including: reducing a threshold and an IOU (interaction over Unit, which is a standard for measuring the accuracy of detecting a corresponding object in a specific data set) to remove the duplicate, and outputting a framing position coordinate and a label;
step B3: sorting in a two-dimensional array mode respectively and outputting a matrix;
step B4: and comparing the output matrix of the pressure plate running state image and the standard pressure plate image, and outputting a comparison result.
When the mobile terminal initializes a loading program, the trained model is loaded, the images and the template images are detected on site, a series of frames are generated on the images according to a certain rule, the frames are regarded as possible candidate areas, whether the frames contain the target object or not is predicted, and if the frames contain the target object, the type of the contained object is also required to be predicted. When the position coordinates and the labels are generated, the program carries out secondary processing on the position coordinates and the labels, wherein the secondary processing mainly comprises threshold value reduction and IOU duplication elimination, and when the duplication elimination IOU is larger than 0.8, the program identifies the position coordinates and the labels as the same frame and directly outputs the frame selection position coordinates and the labels; otherwise, overlapping area duplication elimination is carried out, and then the frame selection position coordinates and the labels are output. And sorting the output frame selection position coordinates and the output labels in a two-dimensional array mode, and outputting a matrix. At the moment, the output matrixes of the local detection image and the template image are respectively displayed, the local detection image and the template image are compared, and if the local detection image and the template image are different in comparison, the difference between the local detection image and the template image is highlighted and output and displayed; otherwise, directly outputting the display result.
According to the method, the two targets are detected, the features of the local detection image and the template image are respectively extracted, the feature value convolution training is carried out, an image model is generated, the intelligent terminal carries out a de-duplication mode of reducing the threshold value and the IOU on the basis, the image features are fully utilized, the adaptability of the model to the pressing plate image is enhanced, and the prediction ratio and the recognition rate can be effectively improved.
The present invention is not limited to the above preferred embodiments, and other various protection and platen inspection systems and methods can be devised by anyone with the benefit of the present disclosure.
Claims (9)
1. The utility model provides a protection definite value and clamp plate system of patrolling and examining, its characterized in that includes: the system comprises a mobile terminal, a screen cabinet identifier, a fixed value data comparison module and a pressing plate identification comparison module; the fixed value data comparison module associates the coding information corresponding to the screen cabinet identification with the standard fixed value data, compares the protection fixed value data acquired by the mobile terminal through the printer interface of the protection screen cabinet with the standard fixed value data and outputs a comparison result; the pressing plate identification comparison module associates the coded information corresponding to the screen cabinet identification with the state of the standard pressing plate, performs switching identification on the pressing plate running state image acquired by the mobile terminal through the camera, compares the pressing plate running state image with the state of the standard pressing plate and outputs a comparison result.
2. The protection valuables and pressure plate inspection system of claim 1, wherein: the image recognition model of the pressing plate recognition and comparison module is obtained through training of a YOLO V3 machine learning framework.
3. The protection valuables and pressure plate inspection system of claim 1, wherein: the screen cabinet identification is a two-dimensional code arranged on the protection screen cabinet.
4. The protection valuables and pressure plate inspection system of claim 3, wherein: and the fixed value data comparison module or the pressing plate identification comparison module selects corresponding standard fixed value data or standard pressing plate states according to coding information extracted from the two-dimensional code image acquired by the mobile terminal through the camera.
5. The protection valuables and pressure plate inspection system of claim 1, wherein: the fixed value data comparison module outputs data information inconsistent with the standard fixed value data; and the pressing plate identification comparison module highlights the retreating state inconsistent with the standard pressing plate state.
6. The protection valuables and pressure plate inspection system of claim 2, wherein: the training process of the image recognition model comprises the following steps:
step A1: generating a candidate region on a picture of a training set, and labeling the candidate region according to the position relation between the candidate region and a real frame on the picture; dividing a positive sample and a negative sample;
step A2: extracting picture characteristics by adopting a convolutional neural network and predicting the positions and the types of the candidate regions; taking each prediction frame as a sample, and labeling according to the position and the category of the real frame relative to the sample to obtain a label value;
step A3: and comparing the network predicted value with the label value to establish a loss function.
7. The protection valuables and pressure plate inspection system of claim 6, wherein: the standard pressing plate state is obtained through a standard pressing plate image, and the fixed value data comparison module is used for performing on-off identification and comparison on the pressing plate running state image through the following steps:
step B1: respectively detecting the pressure plate running state image and the standard pressure plate image according to the image identification model to generate a position coordinate and a label;
step B2: respectively carrying out secondary treatment, including: reducing the threshold value and removing the duplicate by the IOU, and outputting a framing position coordinate and a label;
step B3: sorting in a two-dimensional array mode respectively and outputting a matrix;
step B4: and comparing the output matrix of the pressure plate running state image and the standard pressure plate image, and outputting a comparison result.
8. The inspection method of the protection rating and pressure plate inspection system according to any one of claims 1 to 7, comprising the steps of:
step C1: importing a standard fixed value data set to the mobile terminal;
step C2: scanning a screen cabinet identifier by adopting the mobile terminal, and associating coding information corresponding to the screen cabinet identifier with standard fixed value data corresponding to equipment to be inspected;
step C3: connecting the mobile terminal with a printer interface of a protection screen cabinet, setting a baud rate and acquiring protection constant value data;
step C4: and comparing the protection constant value data with standard constant value data and outputting a comparison result.
9. The inspection method of the protection rating and pressure plate inspection system according to any one of claims 1 to 7, comprising the steps of:
step D1: importing a standard platen image set to the mobile terminal;
step D2: scanning a screen cabinet identifier by adopting the mobile terminal, and associating coding information corresponding to the screen cabinet identifier with a standard pressing plate image corresponding to equipment to be inspected;
step D3: shooting a pressure plate running state image of the equipment to be inspected by adopting the mobile terminal;
step D4: and performing on-off recognition on the pressure plate running state image, comparing the pressure plate running state image with a standard pressure plate state corresponding to the standard pressure plate image, and outputting a comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010860082.2A CN112085710A (en) | 2020-08-25 | 2020-08-25 | Protection constant value and pressure plate inspection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010860082.2A CN112085710A (en) | 2020-08-25 | 2020-08-25 | Protection constant value and pressure plate inspection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112085710A true CN112085710A (en) | 2020-12-15 |
Family
ID=73728007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010860082.2A Pending CN112085710A (en) | 2020-08-25 | 2020-08-25 | Protection constant value and pressure plate inspection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112085710A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159097A (en) * | 2021-02-05 | 2021-07-23 | 广东驰行电力设备有限公司 | Method for realizing automatic identification system of pressing plate switch state under network-free condition |
| CN113794277A (en) * | 2021-08-25 | 2021-12-14 | 国网福建省电力有限公司 | Method and system for identifying pressing plate state image |
| 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 |
| CN114422689A (en) * | 2021-12-03 | 2022-04-29 | 国网山西省电力公司超高压变电分公司 | Hard pressing plate state recognition device and method based on edge intelligence |
| CN117541028A (en) * | 2024-01-09 | 2024-02-09 | 国网山东省电力公司菏泽供电公司 | Management system for protecting pressing plate |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108802547A (en) * | 2018-06-12 | 2018-11-13 | 国网江苏省电力有限公司电力科学研究院 | A kind of relay protection device of intelligent substation Auto-Test System and method based on cloud storage |
| CN209028642U (en) * | 2018-11-28 | 2019-06-25 | 朱明增 | A kind of protection pressing plate automatic checking calibration equipment |
| AU2019101142A4 (en) * | 2019-09-30 | 2019-10-31 | Dong, Qirui MR | A pedestrian detection method with lightweight backbone based on yolov3 network |
-
2020
- 2020-08-25 CN CN202010860082.2A patent/CN112085710A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108802547A (en) * | 2018-06-12 | 2018-11-13 | 国网江苏省电力有限公司电力科学研究院 | A kind of relay protection device of intelligent substation Auto-Test System and method based on cloud storage |
| CN209028642U (en) * | 2018-11-28 | 2019-06-25 | 朱明增 | A kind of protection pressing plate automatic checking calibration equipment |
| AU2019101142A4 (en) * | 2019-09-30 | 2019-10-31 | Dong, Qirui MR | A pedestrian detection method with lightweight backbone based on yolov3 network |
Non-Patent Citations (1)
| Title |
|---|
| 赖宝鹏等: ""基于图像识别的保护压板投退状态APP设计"", 《山东工业技术》, 17 August 2018 (2018-08-17), pages 114 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159097A (en) * | 2021-02-05 | 2021-07-23 | 广东驰行电力设备有限公司 | Method for realizing automatic identification system of pressing plate switch state under network-free condition |
| CN113794277A (en) * | 2021-08-25 | 2021-12-14 | 国网福建省电力有限公司 | Method and system for identifying pressing plate state image |
| 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 |
| CN114422689A (en) * | 2021-12-03 | 2022-04-29 | 国网山西省电力公司超高压变电分公司 | Hard pressing plate state recognition device and method based on edge intelligence |
| CN117541028A (en) * | 2024-01-09 | 2024-02-09 | 国网山东省电力公司菏泽供电公司 | Management system for protecting pressing plate |
| CN117541028B (en) * | 2024-01-09 | 2024-04-12 | 国网山东省电力公司菏泽供电公司 | Management system for protecting pressing plate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112085710A (en) | Protection constant value and pressure plate inspection system and method | |
| CN104992481A (en) | Metered inspection system and method based on image recognition technology | |
| CN110992302A (en) | Method and device for automatically checking pressure plate | |
| CN110807460A (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
| CN110738289A (en) | Multi-dimensional linkage comprehensive studying and judging device for electric power operation standardization and using method thereof | |
| CN113054748A (en) | Pressing plate state identification system and method based on image identification in moving operation and maintenance | |
| CN112839200A (en) | Power plant violation behavior identification method and system based on 5G technology and network server | |
| CN112564291A (en) | Power equipment pressing plate state monitoring system and monitoring method | |
| CN112364145A (en) | Work order processing method and device, electronic equipment and storage medium | |
| CN113343998A (en) | Reading monitoring system and method for electric power mechanical meter, computer equipment and application | |
| CN114460519A (en) | On-site and terminal fusion management system and method based on power transformer inspection | |
| CN111950745B (en) | Image processing-based switching operation management method and system | |
| CN109165753B (en) | Transformer substation defect management method based on mobile platform | |
| CN111382710A (en) | Drawing comparison method based on image recognition | |
| CN116862843A (en) | Construction site safety risk noninductive inspection method and system | |
| CN115454648A (en) | Inspection system and method for abnormal state of secondary equipment pressing plate of power system | |
| CN113176962B (en) | Computer room IT equipment fault accurate detection method and system for data center | |
| CN114996697A (en) | Intelligent control system for micro-grid | |
| CN115187086A (en) | Intelligent management and control system for emergency management | |
| CN114118908A (en) | Electric power material acceptance judging system and method | |
| CN116778407B (en) | Identification analysis method and device for automatically identifying state of device in transformer substation protection screen | |
| CN113837178A (en) | Deep learning-based automatic positioning and unified segmentation method for meter of transformer substation | |
| TWI801830B (en) | Monitoring system and method thereof | |
| CN117077040B (en) | Large-scale complex equipment fault diagnosis and prediction system based on machine learning | |
| He et al. | Intelligent recognition system of substation hard platen state based on machine learning |
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 |