CN111738156A - Intelligent inspection management method and system for state of high-voltage switchgear - Google Patents
Intelligent inspection management method and system for state of high-voltage switchgear Download PDFInfo
- Publication number
- CN111738156A CN111738156A CN202010582565.0A CN202010582565A CN111738156A CN 111738156 A CN111738156 A CN 111738156A CN 202010582565 A CN202010582565 A CN 202010582565A CN 111738156 A CN111738156 A CN 111738156A
- Authority
- CN
- China
- Prior art keywords
- data
- voltage switch
- model
- intelligent
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention discloses a method and a system for intelligent inspection management of high-voltage switchgear state, wherein the method comprises the following steps: establishing a live detection task, acquiring an infrared image and label information of the high-voltage switch equipment to be detected, determining the specific high-voltage switch equipment to be detected, carrying out live detection on the site through an inspection terminal to acquire site data, and completing the live detection task; uploading all data files acquired by the live detection task to a database, completing comprehensive intelligent diagnosis through a trained target detection model, acquiring an intelligent diagnosis result, acquiring a maintenance suggestion according to the intelligent diagnosis result, and matching and pushing the intelligent diagnosis result with the corresponding maintenance suggestion; the target detection model adopts a YOLO network; the system comprises: the system comprises an equipment state inspection management module, a database, an infrared image acquisition module, an inspection terminal, a target detection module and a matching pushing module; the invention greatly improves the inspection efficiency of the state of the high-voltage switch equipment.
Description
Technical Field
The invention relates to the technical field of power equipment, in particular to a method and a system for intelligently managing states of high-voltage switch equipment.
Background
Along with the popularization of smart power grids, power equipment internet of things and intelligent substations and the development of on-line monitoring technology of switch equipment, the monitoring data volume of the switch equipment increases in a geometric trend, and power enterprises put forward higher requirements on state detection and state evaluation levels of high-voltage switch equipment. However, the traditional method for evaluating the equipment state cannot effectively utilize related monitoring data, and the requirement of power grid development is difficult to meet. Therefore, by utilizing an artificial intelligence technology and infrared detection equipment, a high-voltage switchgear classification identification and target detection algorithm based on infrared images is researched, a safe and reliable electrical equipment infrared image management system is established, and the collection, arrangement, detection and evaluation of the infrared states of the high-voltage switchgear are realized, so that the system is not only the trend of the intelligent development of urban power grid reliability management, but also the requirement of the lean management of power grid assets.
After decades of rapid development, thermal infrared imager thermometers are largely used in equipment thermal fault diagnosis and detection in the field of electric power, and have a good effect, but most of the infrared imager thermometers are in a primary stage of analyzing infrared images of electrical equipment by means of detection experience and judging whether the equipment has faults or not, so that the infrared imager thermometers cannot be applied to the current rapidly-developed electric power system, and the popularization of an infrared image management system and the application of an infrared thermometry technology in live detection are seriously hindered.
Therefore, how to provide an intelligent inspection management method and system for the state of the high-voltage switchgear based on infrared image target detection is a problem that needs to be solved urgently by technical personnel in the field.
Disclosure of Invention
In view of the above, the invention provides a method and a system for intelligent inspection management of a state of a high-voltage switchgear, and aims to solve the problem that faults need to be judged and processed manually according to experience in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
the intelligent inspection management method for the states of the high-voltage switch equipment comprises the following steps of:
s1, establishing a live detection task, acquiring an infrared image of high-voltage switch equipment to be detected and label information of an electronic label, identifying the electronic label through an inspection terminal to determine the specific high-voltage switch equipment to be detected, and carrying out live detection and field data acquisition on the site through the inspection terminal to complete the live detection task;
s2, uploading all data files acquired by the live detection task to a database;
s3, inputting all the acquired data into the trained target detection model, performing data analysis, completing comprehensive intelligent diagnosis, and acquiring an intelligent diagnosis result;
s4, storing the intelligent diagnosis result, obtaining a maintenance suggestion according to the intelligent diagnosis result, and matching and pushing the intelligent diagnosis result with the corresponding maintenance suggestion;
wherein, the target detection model adopts a YOLO network.
Preferably, the step S1 of determining the specific content of the specific high-voltage switchgear to be tested by identifying the electronic tag through the inspection terminal includes:
the high-voltage switch equipment to be tested receives the remote instruction to obtain the infrared image, the electronic tag on the high-voltage switch equipment to be tested sends out a radio frequency signal, and the radio frequency signal is identified through the inspection terminal, or the two-dimensional code on the high-voltage switch equipment is scanned through the inspection terminal to determine the specific high-voltage switch equipment to be tested.
Preferably, the method for training the target detection model comprises the following specific steps:
s01, acquiring infrared images and field data of each high-voltage switch device with an electronic tag, and storing tag information carried by the electronic tag, image information of the corresponding infrared image and field data information into a database;
s02, using an image annotation tool, outlining the outline information of the target object through a polygon, recording the boundary frame information of the target object through a rectangle or a circle, and storing the outline information, the boundary frame information, the label information and the field data information into a file with the same name as the original infrared image;
s03, dividing the acquired data into a training set, a verification set and a test set, packaging the data into a DataSet class, processing the data, reading the training set and the verification set in batches by a DataLoader class, circularly sending the training set and the verification set into a YOLO network, selecting random gradient descent with momentum as an optimizer, setting a self-adaptive adjustment learning rate, and obtaining an optimal model by an iteration and comparison precision method;
and S04, calculating the precision ratio P and the recall ratio R of the model obtained in the S03 to form a PR curve, using the area AP under the PR curve as a judgment standard of the model performance, comparing the loss function value during model training with the loss function value under the test set, and judging whether the function is over-fitted or not.
Preferably, the collected data is divided into a training set, a verification set and a test set, the data is packaged into a DataSet class, the data is processed, and the training set and the verification set are read in batch by a DataLoader class;
sending the training set into a YOLO network, calculating to obtain a predicted value, calculating the mean square error of a predicted coordinate and a real coordinate according to a verification set, calculating the cross entropy loss of a predicted category and a real category, calculating a predicted average precision mean value, and judging the size between the average precision mean value and a preset threshold value or judging whether the iteration number reaches a preset number;
if the average precision average value is smaller than a preset threshold value or the iteration times do not reach the preset times, carrying out the next iteration, modifying the model parameters by using a random gradient descent method, and carrying out the content of S03 again;
if the average precision mean value is larger than a preset threshold value or the iteration times reach preset times, the model parameters with the highest average precision mean value are reserved, and the optimal model is obtained.
Preferably, the processing of the data in S03 specifically includes: and carrying out normalization, size transformation and random horizontal turnover on the data.
Preferably, S04 further includes the following: if the overfitting condition exists, the overfitting phenomenon is slowed down or avoided by adopting the modes of increasing the data set, transferring the model and modifying the network structure.
The utility model provides a management system is patrolled and examined to high tension switchgear state intelligence, includes: the system comprises an equipment state inspection management module, a database, an infrared image acquisition module, an inspection terminal, a target detection module and a matching pushing module;
the equipment state inspection management module is used for creating a live detection task and storing data acquired by the live detection task into a database;
the infrared image acquisition module is used for acquiring an infrared image of the high-voltage switch equipment to be detected according to the live detection task and sending the acquired infrared image to the equipment state inspection management module;
the inspection terminal is used for identifying the high-voltage switch equipment to be detected and acquiring field data;
the target detection module is used for analyzing the received data, completing intelligent diagnosis and acquiring an intelligent diagnosis result;
and the matching pushing module is used for receiving the intelligent diagnosis result, matching the corresponding overhaul suggestion by combining the intelligent diagnosis result and completing pushing.
Preferably, an electronic tag reading unit or a two-dimensional code reading unit is arranged in the inspection terminal and used for identifying the high-voltage switch equipment to be detected.
Preferably, the object detection module includes:
the data receiving unit is used for receiving the label information, the image information and the field data information and storing the received data into the database;
the image processing unit is used for processing the infrared image to obtain contour information and boundary frame information;
the data processing unit is used for dividing and processing data;
the model training unit is used for inputting the processed data into a YOLO network for training to obtain model parameters so as to obtain an optimal model;
and the test unit is used for solving the problem of overfitting by testing the model.
According to the technical scheme, compared with the prior art, the intelligent routing inspection management method and system for the state of the high-voltage switch equipment are disclosed and provided, the key technology of classifying and identifying the state of the high-voltage switch equipment and detecting the target is carried out on the basis of the infrared image, the infrared image target detection model of the high-voltage switch equipment is trained, intelligent diagnosis is carried out through the target detection model, and on the basis, field data are combined, so that the intelligent diagnosis precision is further improved, powerful technical support is provided for equipment state risk assessment, and the operation and maintenance efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for intelligent inspection management of high voltage switchgear status according to the present invention;
fig. 2 is a flowchart illustrating a training process of a target detection model in the intelligent inspection management method for the state of the high-voltage switchgear according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses an intelligent inspection management method for states of high-voltage switch equipment, each high-voltage switch equipment is provided with an electronic tag, and each electronic tag stores relevant information of the corresponding high-voltage switch equipment, and the method comprises the following steps:
s1, establishing a live detection task, acquiring an infrared image of high-voltage switch equipment to be detected and label information of an electronic label, identifying the electronic label through an inspection terminal to determine the specific high-voltage switch equipment to be detected, and carrying out live detection and field data acquisition through the inspection terminal to complete the live detection task;
s2, uploading all data files acquired by the live detection task to a database;
s3, inputting all the acquired data into the trained target detection model, performing data analysis, completing comprehensive intelligent diagnosis, and acquiring an intelligent diagnosis result;
s4, storing the intelligent diagnosis result, obtaining a maintenance suggestion according to the intelligent diagnosis result, and matching and pushing the intelligent diagnosis result with the corresponding maintenance suggestion;
wherein, the target detection model adopts a YOLO network.
Specifically, the flow chart of the method is shown in fig. 1, and before a live detection task is created, first, the check point ledger information is acquired, and the ledger is downloaded, and the relevant information such as the model of the high-voltage switch device is acquired.
In order to further implement the above technical solution, the identifying of the electronic tag by the inspection terminal in S1 determines the specific content of the specific high-voltage switch device to be tested, including:
the high-voltage switch equipment to be tested receives the remote instruction to obtain the infrared image, the electronic tag on the high-voltage switch equipment to be tested sends out a radio frequency signal, and the radio frequency signal is identified through the inspection terminal, or the two-dimensional code on the high-voltage switch equipment is scanned through the inspection terminal to determine the specific high-voltage switch equipment to be tested.
In order to further implement the above technical solution, as shown in fig. 2, the method for training the target detection model includes the following specific steps:
s01, acquiring infrared images and field data of each high-voltage switch device with an electronic tag, and storing tag information carried by the electronic tag, image information of the corresponding infrared image and field data information into a database;
s02, using an image annotation tool, outlining the outline information of the target object through a polygon, recording the boundary frame information of the target object through a rectangle or a circle, and storing the outline information, the boundary frame information, the label information and the field data information into a file with the same name as the original infrared image;
s03, dividing the acquired data into a training set, a verification set and a test set, packaging the data into a DataSet class, processing the data, reading the training set and the verification set in batches by a DataLoader class, circularly sending the training set and the verification set into a YOLO network, selecting random gradient descent with momentum as an optimizer, setting a self-adaptive adjustment learning rate, and obtaining an optimal model by an iteration and comparison precision method;
and S04, calculating the precision ratio P and the recall ratio R of the model obtained in the S03 to form a PR curve, using the area AP under the PR curve as a judgment standard of the model performance, comparing the loss function value during model training with the loss function value under the test set, and judging whether the function is over-fitted or not.
In order to further realize the technical scheme, the acquired data is divided into a training set, a verification set and a test set, the data is encapsulated into a DataSet class, the data is processed, and the training set and the verification set are read in batch by a DataLoader class;
sending the training set into a YOLO network, calculating to obtain a predicted value, calculating the mean square error of a predicted coordinate and a real coordinate according to a verification set, calculating the cross entropy loss of a predicted category and a real category, calculating a predicted average precision mean value, and judging the size between the average precision mean value and a preset threshold value or judging whether the iteration number reaches a preset number;
if the average precision average value is smaller than a preset threshold value or the iteration times do not reach the preset times, carrying out the next iteration, modifying the model parameters by using a random gradient descent method, and carrying out the content of S03 again;
if the average precision mean value is larger than a preset threshold value or the iteration times reach preset times, the model parameters with the highest average precision mean value are reserved, and the optimal model is obtained.
In order to further implement the above technical solution, the processing of the data in S03 specifically includes: and carrying out normalization, size transformation and random horizontal turnover on the data.
In order to further implement the above technical solution, S04 further includes the following: if the overfitting condition exists, the overfitting phenomenon is slowed down or avoided by adopting the modes of increasing the data set, transferring the model and modifying the network structure.
The utility model provides a management system is patrolled and examined to high tension switchgear state intelligence, includes: the system comprises an equipment state inspection management module, a database, an infrared image acquisition module, an inspection terminal, a target detection module and a matching pushing module;
the equipment state inspection management module is used for creating a live detection task and storing data acquired by the live detection task into a database;
the infrared image acquisition module is used for acquiring an infrared image of the high-voltage switch equipment to be detected according to the live detection task and sending the acquired infrared image to the equipment state inspection management module;
the inspection terminal is used for identifying the high-voltage switch equipment to be detected and acquiring field data;
the target detection module is used for analyzing the received data, completing intelligent diagnosis and acquiring an intelligent diagnosis result;
and the matching pushing module is used for receiving the intelligent diagnosis result, matching the corresponding overhaul suggestion by combining the intelligent diagnosis result and completing pushing.
In order to further realize the technical scheme, an electronic tag reading unit or a two-dimensional code reading unit is arranged in the inspection terminal and is used for identifying the high-voltage switch equipment to be detected.
In order to further realize the above technical solution, the target detection module includes:
the data receiving unit is used for receiving the label information, the image information and the field data information and storing the received data into a database;
the image processing unit is used for processing the infrared image to obtain contour information and boundary frame information;
the data processing unit is used for dividing and processing data;
the model training unit is used for inputting the processed data into a YOLO network for training to obtain model parameters so as to obtain an optimal model;
and the test unit is used for solving the problem of overfitting by testing the model.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. The intelligent inspection management method for the states of the high-voltage switch equipment is characterized by comprising the following steps of:
s1, establishing a live detection task, acquiring an infrared image of high-voltage switch equipment to be detected and label information of an electronic label, identifying the electronic label through an inspection terminal to determine the specific high-voltage switch equipment to be detected, and carrying out live detection and field data acquisition through the inspection terminal to complete the live detection task;
s2, uploading all data files acquired by the live detection task to a database;
s3, inputting all the acquired data into the trained target detection model, performing data analysis, completing comprehensive intelligent diagnosis, and acquiring an intelligent diagnosis result;
s4, storing the intelligent diagnosis result, obtaining a maintenance suggestion according to the intelligent diagnosis result, and matching and pushing the intelligent diagnosis result with the corresponding maintenance suggestion;
wherein, the target detection model adopts a YOLO network.
2. The intelligent inspection management method for the state of the high-voltage switchgear according to claim 1, wherein the step of determining the specific content of the specific high-voltage switchgear to be tested through the identification of the inspection terminal on the electronic tag in the step S1 comprises the following steps:
the high-voltage switch equipment to be tested receives the remote instruction to obtain the infrared image, the electronic tag on the high-voltage switch equipment to be tested sends out a radio frequency signal, and the radio frequency signal is identified through the inspection terminal, or the two-dimensional code on the high-voltage switch equipment is scanned through the inspection terminal to determine the specific high-voltage switch equipment to be tested.
3. The intelligent inspection management method for the state of the high-voltage switchgear according to claim 1, wherein the training method of the target detection model comprises the following specific steps:
s01, acquiring infrared images and field data of each high-voltage switch device with an electronic tag, and storing tag information carried by the electronic tag, image information of the corresponding infrared image and field data information into a database;
s02, using an image annotation tool, outlining the outline information of the target object through a polygon, recording the boundary frame information of the target object through a rectangle or a circle, and storing the outline information, the boundary frame information, the label information and the field data information into a file with the same name as the original infrared image;
s03, dividing the acquired data into a training set, a verification set and a test set, packaging the data into a DataSet class, processing the data, reading the training set and the verification set in batches by a DataLoader class, circularly sending the training set and the verification set into a YOLO network, selecting random gradient descent with momentum as an optimizer, setting a self-adaptive adjustment learning rate, and obtaining an optimal model by an iteration and comparison precision method;
and S04, calculating the precision ratio P and the recall ratio R of the model obtained in the S03 to form a PR curve, using the area AP under the PR curve as a judgment standard of the model performance, comparing the loss function value during model training with the loss function value under the test set, and judging whether the function is over-fitted or not.
4. The intelligent inspection management method for the state of the high-voltage switchgear according to claim 3, wherein S03 specifically includes the following contents:
dividing the acquired data into a training set, a verification set and a test set, packaging the data into a DataSet class, processing the data, and reading the training set and the verification set in batches by a DataLoader class;
sending the training set into a YOLO network, calculating to obtain a predicted value, calculating the mean square error of a predicted coordinate and a real coordinate according to a verification set, calculating the cross entropy loss of a predicted category and a real category, calculating a predicted average precision mean value, and judging the size between the average precision mean value and a preset threshold value or judging whether the iteration number reaches a preset number;
if the average precision average value is smaller than a preset threshold value or the iteration times do not reach the preset times, carrying out the next iteration, modifying the model parameters by using a random gradient descent method, and carrying out the content of S03 again;
if the average precision mean value is larger than a preset threshold value or the iteration times reach preset times, the model parameters with the highest average precision mean value are reserved, and the optimal model is obtained.
5. The intelligent inspection management method for the state of the high-voltage switchgear according to claim 3, wherein the processing of the data in S03 specifically comprises: and carrying out normalization, size transformation and random horizontal turnover on the data.
6. The intelligent inspection management method for the state of the high-voltage switchgear according to claim 3, wherein S04 further includes the following contents: if the overfitting condition exists, the overfitting phenomenon is slowed down or avoided by adopting the modes of increasing the data set, transferring the model and modifying the network structure.
7. The utility model provides a management system is patrolled and examined to high tension switchgear state intelligence which characterized in that: the method comprises the following steps: the system comprises an equipment state inspection management module, a database, an infrared image acquisition module, an inspection terminal, a target detection module and a matching pushing module;
the equipment state inspection management module is used for creating a live detection task and storing data acquired by the live detection task into a database;
the infrared image acquisition module is used for acquiring an infrared image of the high-voltage switch equipment to be detected according to the live detection task and sending the acquired infrared image to the equipment state inspection management module;
the inspection terminal is used for identifying the high-voltage switch equipment to be detected and acquiring field data;
the target detection module is used for analyzing the received data, completing intelligent diagnosis and acquiring an intelligent diagnosis result;
and the matching pushing module is used for receiving the intelligent diagnosis result, matching the corresponding overhaul suggestion by combining the intelligent diagnosis result and completing pushing.
8. The intelligent inspection management system for the state of the high-voltage switchgear according to claim 7, characterized in that: an electronic tag reading unit or a two-dimensional code reading unit is arranged in the inspection terminal and used for identifying the high-voltage switch equipment to be detected.
9. The intelligent inspection management system according to claim 7, wherein the target detection module comprises:
the data receiving unit is used for receiving the label information, the image information and the field data information and storing the received data into the database;
the image processing unit is used for processing the infrared image to obtain contour information and boundary frame information;
the data processing unit is used for dividing and processing data;
the model training unit is used for inputting the processed data into a YOLO network for training to obtain model parameters so as to obtain an optimal model;
and the test unit is used for solving the problem of overfitting by testing the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010582565.0A CN111738156A (en) | 2020-06-23 | 2020-06-23 | Intelligent inspection management method and system for state of high-voltage switchgear |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010582565.0A CN111738156A (en) | 2020-06-23 | 2020-06-23 | Intelligent inspection management method and system for state of high-voltage switchgear |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111738156A true CN111738156A (en) | 2020-10-02 |
Family
ID=72650784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010582565.0A Pending CN111738156A (en) | 2020-06-23 | 2020-06-23 | Intelligent inspection management method and system for state of high-voltage switchgear |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738156A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598040A (en) * | 2020-12-16 | 2021-04-02 | 浙江方圆检测集团股份有限公司 | Switch consistency real-time detection method based on deep learning |
| CN112734968A (en) * | 2020-12-02 | 2021-04-30 | 湖南强智科技发展有限公司 | Method and device for polling data equipment and computer storage medium |
| CN112749771A (en) * | 2020-11-02 | 2021-05-04 | 郑州富联智能工坊有限公司 | Multimedia analysis device, multimedia analysis system, and multimedia analysis method |
| WO2022088082A1 (en) * | 2020-10-30 | 2022-05-05 | 京东方科技集团股份有限公司 | Task processing method, apparatus and device based on defect detection, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110160922A1 (en) * | 2009-12-30 | 2011-06-30 | Eduardo Pedrosa Santos | Decentralized system and architecture for remote real time monitoring of power transformers, reactors, circuit breakers, instrument transformers, disconnect switches and similar high voltage equipment for power plants and electric power substations |
| CN107063467A (en) * | 2017-04-15 | 2017-08-18 | 山东信通电子股份有限公司 | Intelligent infrared thermal imaging device and method for inspecting for the online inspection of grid equipment |
| CN110334661A (en) * | 2019-07-09 | 2019-10-15 | 国网江苏省电力有限公司扬州供电分公司 | Infrared power transmission and transformation abnormal heating point target detecting method based on deep learning |
| CN111104906A (en) * | 2019-12-19 | 2020-05-05 | 南京工程学院 | Transmission tower bird nest fault detection method based on YOLO |
| CN111179249A (en) * | 2019-12-30 | 2020-05-19 | 南京南瑞信息通信科技有限公司 | Power equipment detection method and device based on deep convolutional neural network |
-
2020
- 2020-06-23 CN CN202010582565.0A patent/CN111738156A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110160922A1 (en) * | 2009-12-30 | 2011-06-30 | Eduardo Pedrosa Santos | Decentralized system and architecture for remote real time monitoring of power transformers, reactors, circuit breakers, instrument transformers, disconnect switches and similar high voltage equipment for power plants and electric power substations |
| CN107063467A (en) * | 2017-04-15 | 2017-08-18 | 山东信通电子股份有限公司 | Intelligent infrared thermal imaging device and method for inspecting for the online inspection of grid equipment |
| CN110334661A (en) * | 2019-07-09 | 2019-10-15 | 国网江苏省电力有限公司扬州供电分公司 | Infrared power transmission and transformation abnormal heating point target detecting method based on deep learning |
| CN111104906A (en) * | 2019-12-19 | 2020-05-05 | 南京工程学院 | Transmission tower bird nest fault detection method based on YOLO |
| CN111179249A (en) * | 2019-12-30 | 2020-05-19 | 南京南瑞信息通信科技有限公司 | Power equipment detection method and device based on deep convolutional neural network |
Non-Patent Citations (1)
| Title |
|---|
| 裴少通: "基于红外紫外成像检测技术的绝缘子运行状态分析与评估", 《中国优秀博硕士学位论文全文数据库(博士) 工程科技Ⅱ辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022088082A1 (en) * | 2020-10-30 | 2022-05-05 | 京东方科技集团股份有限公司 | Task processing method, apparatus and device based on defect detection, and storage medium |
| CN112749771A (en) * | 2020-11-02 | 2021-05-04 | 郑州富联智能工坊有限公司 | Multimedia analysis device, multimedia analysis system, and multimedia analysis method |
| CN112749771B (en) * | 2020-11-02 | 2024-04-05 | 富联智能工坊(郑州)有限公司 | Multimedia analysis device, multimedia analysis system, and multimedia analysis method |
| CN112734968A (en) * | 2020-12-02 | 2021-04-30 | 湖南强智科技发展有限公司 | Method and device for polling data equipment and computer storage medium |
| CN112598040A (en) * | 2020-12-16 | 2021-04-02 | 浙江方圆检测集团股份有限公司 | Switch consistency real-time detection method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111738156A (en) | Intelligent inspection management method and system for state of high-voltage switchgear | |
| CN112380952A (en) | Power equipment infrared image real-time detection and identification method based on artificial intelligence | |
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN105404867B (en) | A kind of substation isolating-switch state identification method of view-based access control model | |
| CN106991731A (en) | Intelligent polling method and system that integrated equipment is safeguarded | |
| CN112327100B (en) | Power failure detection method and system based on Internet of things | |
| CN116148679A (en) | Battery health state prediction method and related device | |
| CN113723189B (en) | Intelligent power equipment fault diagnosis method based on single-order infrared image target detection | |
| CN111831430A (en) | Electrical equipment defect identification system based on edge calculation | |
| CN115272983B (en) | Contact net suspension state monitoring method and system based on image recognition | |
| CN110188888A (en) | Power equipments defect management method, system and terminal based on AHP and remote support | |
| CN117218495A (en) | Risk detection method and system for electric meter box | |
| CN114119528A (en) | Defect detection method and device for distribution line insulator | |
| CN115932661A (en) | Method for analyzing and judging noise compliance of transformer | |
| CN112347889B (en) | Substation operation behavior identification method and device | |
| CN111931721B (en) | Method and device for detecting color and number of annual inspection label and electronic equipment | |
| CN112101375A (en) | Intelligent substation equipment state detection method and system based on deep learning | |
| CN109975686A (en) | A kind of circuit board short circuit automatic identifying method based on infrared image processing | |
| CN117368651B (en) | Comprehensive analysis system and method for faults of power distribution network | |
| Wang et al. | Substation Equipment Defect Detection based on Temporal-spatial Similarity Calculation | |
| CN117648237B (en) | Automatic monitoring method for performance test process | |
| Hou et al. | Multi angle location and identification method of suspension insulators based on R2CNN algorithm | |
| CN117197558A (en) | Transformer substation monitoring interface entity identification test method and system based on machine vision | |
| CN117372403A (en) | Method and system for detecting defects of visible light and infrared transformer sleeve image of mobile phone | |
| CN114387242A (en) | Defect determination method, device, medium and equipment for voltage heating type equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |