CN112380907A - Intelligent image identification method for defects of power transformation equipment and management system thereof - Google Patents
Intelligent image identification method for defects of power transformation equipment and management system thereof Download PDFInfo
- Publication number
- CN112380907A CN112380907A CN202011122094.1A CN202011122094A CN112380907A CN 112380907 A CN112380907 A CN 112380907A CN 202011122094 A CN202011122094 A CN 202011122094A CN 112380907 A CN112380907 A CN 112380907A
- Authority
- CN
- China
- Prior art keywords
- image
- defects
- power transformation
- handheld terminal
- transformation equipment
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 79
- 230000009466 transformation Effects 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000007689 inspection Methods 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 23
- 230000002159 abnormal effect Effects 0.000 description 8
- 239000012212 insulator Substances 0.000 description 7
- 238000011176 pooling Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000004913 activation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- 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
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Water Supply & Treatment (AREA)
- Multimedia (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention firstly discloses an intelligent image identification method for the defects of power transformation equipment, which comprises the following steps: s1: shooting the power transformation equipment by using the handheld terminal to obtain a patrol image of the power transformation equipment; s2: processing the software polling image of the handheld terminal, outputting a target identification image, identifying defects of the target identification image, and outputting an identification result; s3: after the defect identification is finished, the inspection brief report is automatically generated, and the inspection image and the identification result are uploaded to the main station through the network. Secondly, an intelligent image recognition management system for the defects of the power transformation equipment is disclosed, which comprises a master station, a database server and a handheld terminal; the master station is connected with the database server through a network; and the master station is in communication connection with the handheld terminal. The invention can find and eliminate the defects of the power transformation equipment in time, prevent equipment accidents from happening and effectively supervise the equipment state.
Description
Technical Field
The invention relates to the field of intelligent identification of defects of power transformation equipment, in particular to an intelligent image identification method of defects of the power transformation equipment and a management system thereof.
Background
During operation, the composite insulating outer sleeve of the power transformation equipment can crack, the pressure of SF6 gas charging equipment can be reduced, and other defects can occur to the power transformation equipment. If the defects cannot be found in time, short circuit, tripping and even explosion of equipment can be caused, large-area power failure and other accidents are caused, and huge economic loss is caused. In order to prevent accidents of the power transformation equipment, how to timely find and eliminate the defects of the insulator bushing equipment and the SF6 gas charging equipment instrument becomes the center of gravity of research and development.
In the prior art, a chinese patent publication No. CN110567964A discloses a method, an apparatus, and a storage medium for detecting defects of a power transformation device in 12/13/2019, which achieve to some extent that whether defects exist on the surface of the power transformation device is judged by a visible light image, and whether defects exist inside the power transformation device is judged by an infrared image, but the above problems cannot be solved, so that users urgently need an intelligent image identification method for defects of the power transformation device and a management system thereof.
Disclosure of Invention
The invention provides an intelligent image identification method for the defects of a power transformation device and a management system thereof, aiming at solving the problem that the defects of the power transformation device cannot be identified in time.
The primary objective of the present invention is to solve the above technical problems, and the technical solution of the present invention is as follows:
firstly, an intelligent image recognition method for the defects of the power transformation equipment is disclosed, which comprises the following steps: s1: shooting the power transformation equipment by using the handheld terminal to obtain a patrol image of the power transformation equipment; s2: processing the software polling image of the handheld terminal, outputting a target identification image, identifying defects of the target identification image, and outputting an identification result; s3: after the defect identification is finished, the inspection brief report is automatically generated, and the inspection image and the identification result are uploaded to the main station through the network.
Preferably, the handheld terminal in steps S1 and S2 is a portable device integrating a high-definition camera and an embedded unit.
Preferably, in step S2, the process of processing the patrol inspection image acquired by the handheld terminal includes: the method comprises the steps of image input, image graying, image enhancement, image denoising and smoothing, image binarization and target identification image output.
Preferably, in step S2, the convolutional neural network algorithm is used to perform defect recognition on the target recognition image, and the process includes: image preprocessing, feature extraction, neural network identification and output of an identification result.
Preferably, in step S3, if the image has a defect as a result of the identification, the handheld terminal issues a defect alarm; and if the identification result is that the image has no defects, the handheld terminal sends a normal prompt.
Secondly, an intelligent image recognition management system for the defects of the power transformation equipment is disclosed, which comprises a master station, a database server and a handheld terminal; the master station is connected with the database server through a network; and the master station is in communication connection with the handheld terminal.
Preferably, the master station constructs a functional module of the management system by adopting a Spring framework technology and an MVC (model view controller) level technology, and the functional module comprises a system user management module, a log behavior management module, an equipment ledger information module, a handheld terminal management module, an intelligent image recognition algorithm module and an inspection result analysis module.
Preferably, the database server automatically establishes the relationship between each interval and the power transformation equipment by importing a data table form.
Preferably, the database server stores the image information using a NoSQL non-relational database.
Preferably, the database server stores the standing book information by using a MySQL relational database, and establishes the association between the standing book information and the image information.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the invention firstly provides an intelligent image recognition method for the defects of the power transformation equipment, when the power transformation equipment is patrolled, the defects of the power transformation equipment are timely handled by realizing recognition by taking a picture through a handheld terminal and uploading patrolled image data and a recognition result to a main station, so that accidents are prevented; secondly, the transformer equipment defect intelligent image recognition management system is provided and comprises a main station, a database server and a handheld terminal, intelligent transformer equipment defect image recognition is achieved through the handheld terminal, image data and ledger information association is achieved through the database server, inspection images and recognition results are obtained through the main station, and equipment fault tracing and equipment state supervision are achieved.
Drawings
FIG. 1 is a diagram of the steps of the method of the present invention;
FIG. 2 is a flow chart of the inspection of the power transformation equipment in the method of the present invention;
FIG. 3 is a flowchart of inspection image processing in the method of the present invention;
FIG. 4 is a flow chart of defect identification in the method of the present invention;
FIG. 5 is a schematic diagram of the system of the present invention;
fig. 6 is a functional block diagram of the system according to the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Example 1
As shown in fig. 1, first, an intelligent image recognition method for a transformer equipment defect includes the following steps: s1: shooting the power transformation equipment by using the handheld terminal to obtain a patrol image of the power transformation equipment; s2: processing the software polling image of the handheld terminal, outputting a target identification image, identifying defects of the target identification image, and outputting an identification result; s3: after the defect identification is finished, the inspection brief report is automatically generated, and the inspection image and the identification result are uploaded to the main station through the network.
In the above scheme, as shown in fig. 2, the routing inspection process of the power transformation equipment is as follows: the method comprises the steps of firstly selecting power transformation equipment (such as an insulator and an SF6 gas-filled equipment instrument), then shooting a patrol inspection image of the power transformation equipment by using a handheld terminal, then processing the patrol inspection image through software of the handheld terminal to obtain a target identification image, carrying out defect identification on the target identification image through a defect intelligent image identification model of the handheld terminal and outputting an identification result, and finally finishing patrol inspection to generate a briefing and uploading patrol inspection image data and the identification result to a main station in a wired or wireless mode.
Specifically, the handheld terminal in steps S1 and S2 is a portable device integrating a high-definition camera and an embedded unit.
In the scheme, the handheld terminal realizes a photographing function through the high-definition camera and trains and identifies the defect intelligent image identification model through the embedded unit; the inspection personnel use the equipment, and can realize photographing, identification, diagnosis and early warning.
As shown in fig. 3, specifically, in step S2, the process of processing the patrol inspection image acquired by the handheld terminal includes: the method comprises the steps of image input, image graying, image enhancement, image denoising and smoothing, image binarization and target identification image output.
In the scheme, the purpose of processing the inspection image is to highlight the outlines of the insulator and the SF6 gas charging equipment instrument, remove interference, find the defect of the micro cracks on the surface of the composite insulating outer sleeve and the defect of pressure drop of the SF6 gas charging equipment, and judge whether the defects meet the standard and judge the defect grade.
As shown in fig. 4, specifically, in step S2, defect identification is performed on the target identification image by using a convolutional neural network algorithm, which includes: image preprocessing, feature extraction, neural network identification and output of an identification result.
In the above scheme, the convolutional neural network algorithm includes a convolutional layer, an active layer, a pooling layer, and a full-link layer, and the basic principle of each part is as follows: rolling up layers: the characteristic graph of the interconnection between layers extracts the pixel-level image characteristics through convolution operation by one or more convolution kernels (also called Filter), and the result of the convolution operation forms a characteristic mapping relation from input to output after being mapped and transformed by an activation function; each convolution kernel traverses the whole feature map by adopting a mechanism similar to a sliding window, and the convolution kernels converge and fuse the feature information of each small region to finish the characterization of a small local region feature of the image; the convolution layer is in the form of z (x, y) ═ f (x, y) × g (x, y) ═ m Σnf (x-m, y-n) g (m, n), where f represents the input, typically a 2-dimensional image, g represents the convolution kernel, and m and n are the sizes of the convolution kernels, respectively; a color image of the transformer equipment with the length and the width of 32 x 32 and containing RGB three channels is used as an input, namely the input size is 3 x 32; assuming that the convolution kernel contains 20 5 × 5 convolution kernels, filled with 0 zeros, and stepped to 1 as a hyper-parameter, the output through the convolution layer is 20 × (32-5 +1) × (32-5 + 1); as parameter sharing, after passing through the convolution layer, each convolution kernel generates (5 × 5) × 3 ═ 75 weight parameters, and then generates (5 × 5) × 3 ═ 20 ═ 1500 weight parameters in total; activation layer: an activation function is mainly set in a convolution network, the essence of the activation function is function mapping, input data is subjected to mapping transformation, and the nonlinear modeling capability of the network is provided; in the operation process, element-by-element calculation is carried out, the size of original data is not changed, namely the size of input data is equal to that of output data; the method uses the PReLU function and the MPELU function with self-learning capability and uses the regularization technology to add a Batch Normalization layer in the network; ③ a pooling layer: the pooling units calculate the value of a local block in the characteristic diagram, and the adjacent pooling units read data from a small block area by moving one row or one column, so that the dimensionality of data expression is reduced, the translational invariance of the data is ensured, and the parameter quantity and the calculated amount in a network are greatly reduced; only after the pooling operation, the depth of the feature map after pooling and the depth before pooling are kept unchanged; fourthly, full connecting layer: each neuron of the full connection layer is fully connected with each neuron of the previous layer; the last output of the network is the high-level characteristics of the input image, and then the probability of the class label corresponding to the input image is output through the statistical calculation of the classifier.
Specifically, if the image has a defect as a result of the identification in step S3, the handheld terminal sends a defect alarm; and if the identification result is that the image has no defects, the handheld terminal sends a normal prompt.
In the scheme, the patrol personnel can carry out intelligent image recognition and diagnosis on the defects of the power transformation equipment through the handheld terminal, and send out early warning when the defects are judged, so that technical personnel are reminded to timely handle the defects, and equipment accidents are prevented.
As shown in fig. 5, secondly, an intelligent image recognition management system for substation equipment defects comprises a master station, a database server and a handheld terminal; the master station is connected with the database server through a network; and the master station is in communication connection with the handheld terminal.
In the scheme, the master station is responsible for receiving the inspection image and the identification result uploaded by the handheld terminal and storing the image information in the database server; the database server is used for storing the inspection image information, storing the equipment standing book information and performing correlation management on the inspection image information and the equipment standing book information; in addition, the master station can also receive patrol images acquired by third-party equipment (such as a robot, an unmanned aerial vehicle and the like); the database server can also perform information interaction with the power grid service processing platform, and data is called as required.
As shown in fig. 6, specifically, the master station constructs function modules of the management system by using a Spring framework technology and an MVC hierarchical technology, where the function modules include a system user management module, a log behavior management module, an equipment ledger information module, a handheld terminal management module, an intelligent image recognition algorithm module, and a patrol result analysis module.
In the scheme, the master station establishes a functional module to manage substation account information, defect image information, inspection record information and defect identification report information of the power transformation equipment, provide an intelligent identification algorithm training function and provide a visualization function of information management; the method comprises the following specific steps: the system user management module comprises a function menu and a function module, wherein the function menu comprises user basic information and stores the user basic information; the system also comprises role authority management, which can configure corresponding authority for each user, so that the function menu is only opened for users with the authority, different function menus are opened for different user types, and the information safety is ensured; the log behavior management module and the function menu comprise 'log record query', so that the operation logs of each user can be managed, the safety of the system is effectively improved, and the system can be conveniently maintained and upgraded by managers in the later period; the equipment standing book information module is characterized in that a function menu comprises 'insulator equipment standing book information management' and 'SF 6 instrument standing book information management', field specification arrangement is respectively carried out on standing book basic data of an insulator and an SF6 gas-filled equipment instrument, information needing to be managed is extracted from daily standing book data, comprehensive, rapid and efficient management is carried out on the standing book basic data by using an informatization means, and the functions of leading in and leading out can be realized, so that on one hand, the existing transformer equipment information can be led in an Excel form, and on the other hand, the transformer equipment information in the system can be led out in the Excel form; the handheld terminal management module is used for managing the basic information of the handheld terminal by the function menu, wherein the function menu comprises basic information, so that the basic information of the handheld terminal can be managed, the basic information records of the handheld terminal can be additionally modified and deleted, and the managed basic information of the handheld terminal comprises the model of the handheld terminal, the number of a user, the number of a station to which the handheld terminal belongs, the number of assets and the like; the system also comprises software upgrading, wherein a user can connect the handheld terminal and the master station through a data line or WIFI to upgrade software on the handheld terminal; the system also comprises data import which can synchronize the equipment ledger information and the historical patrol information recorded by the master station to the handheld terminal; the system also comprises data export, and inspection image information, an identification result and inspection record information shot by the handheld terminal can be synchronized to the master station; the system also comprises an inspection report which can display the current or historical inspection report, and the display contents comprise the functional position of equipment, the name of the equipment, the inspection time, the existence of abnormality, the number of abnormal insulators, the number of abnormal SF6 instruments and the abnormality details; the power transformation equipment also comprises abnormal information which can display the abnormal information of the power transformation equipment in real time, and the display content comprises identification time, interval names, equipment names and abnormal results; the intelligent image recognition algorithm module comprises an algorithm training function menu, can realize the training operation of the fault diagnosis algorithm of the defects of the power transformation equipment, can perform algorithm training aiming at the new defect types of the power transformation equipment when the defects of some equipment are not met during the previous algorithm training in the practical application process, and downloads the trained algorithm model into the embedded unit so as to keep the defect recognition algorithm in the embedded unit in the latest state; the intelligent equipment defect identification system also comprises intelligent equipment defect identification, can carry out defect identification on the equipment images uploaded in batch or individually, and forms an equipment defect identification report in PDF, Word and Excel file formats for downloading; sixthly, an inspection result analysis module, wherein the function menu comprises an inspection result overview, and the inspection result overview displays the content of the total equipment number, the insulator number, the SF6 instrument number, the abnormal equipment number, the alarm and the like in the current inspection; the system also comprises 'inspection result browsing', wherein the records of inspection of the past can be checked on line, and the information of inspection personnel, inspection time, inspection content, inspection results, equipment defects and the like of each time is displayed; the method also comprises 'abnormal alarm query', which can be used for querying abnormal alarm information of the equipment according to the screening conditions of time and equipment name, wherein the alarm information comprises inspection time, interval names, equipment numbers, equipment names and inspection results; the system also comprises a patrol report which can download a defect report file in PDF, Word and Excel formats, wherein the content of the defect report file comprises patrol time, equipment name, patrol personnel, defect information and the like.
Specifically, the database server automatically establishes the relationship between each interval and the transformer equipment by importing a data table form.
In the scheme, the relationship between each interval and the power transformation equipment in the transformer substation is established, and when the inspection personnel inspect the power transformation equipment at different intervals, the inspection personnel can respectively record the inspection personnel at the corresponding positions of the data table.
Specifically, the database server stores the image information by using a NoSQL non-relational database.
In the scheme, the management of the image data of the power transformation equipment is realized through the NoSQL non-relational database.
Specifically, the database server stores the standing book information by using a MySQL relational database, and establishes the association between the standing book information and the image information.
In the scheme, the substation equipment ledger information database is established through the MySQL relational database, and the correlation management of image data, ledger information, alarm information, report information and the like is realized.
The same or similar reference numerals correspond to the same or similar parts;
the terms describing positional relationships in the drawings are for illustrative purposes only and are not to be construed as limiting the patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. The intelligent image recognition method for the defects of the power transformation equipment is characterized by comprising the following steps of:
s1: shooting the power transformation equipment by using the handheld terminal to obtain a patrol image of the power transformation equipment;
s2: processing the software polling image of the handheld terminal, outputting a target identification image, identifying defects of the target identification image, and outputting an identification result;
s3: after the defect identification is finished, the inspection brief report is automatically generated, and the inspection image and the identification result are uploaded to the main station through the network.
2. The method for intelligently identifying the defects of the power transformation equipment as claimed in claim 1, wherein the handheld terminal in steps S1 and S2 is a portable device integrating a high-definition camera and an embedded unit.
3. The method for intelligently identifying the defects of the power transformation equipment as claimed in claim 1, wherein the process of processing the inspection image acquired by the handheld terminal in the step S2 comprises the following steps: the method comprises the steps of image input, image graying, image enhancement, image denoising and smoothing, image binarization and target identification image output.
4. The intelligent image recognition method for the defects of the power transformation equipment as recited in claim 1, wherein in step S2, defect recognition is performed on the target recognition image by using a convolutional neural network algorithm, and the process comprises: image preprocessing, feature extraction, neural network identification and output of an identification result.
5. The intelligent image identification method for the defects of the power transformation equipment as claimed in claim 1, wherein in step S3, if the identification result is that the image has the defects, the handheld terminal sends a defect alarm; and if the identification result is that the image has no defects, the handheld terminal sends a normal prompt.
6. An intelligent image recognition management system for substation equipment defects is characterized by comprising a master station, a database server and a handheld terminal; the master station is connected with the database server through a network; and the master station is in communication connection with the handheld terminal.
7. The intelligent image recognition management system for the defects of the power transformation equipment as claimed in claim 6, wherein the master station adopts a Spring framework and an MVC hierarchy to construct functional modules of the management system, and the functional modules comprise a system user management module, a log behavior management module, an equipment ledger information module, a handheld terminal management module, an intelligent image recognition algorithm module and an inspection result analysis module.
8. The intelligent image recognition management system for the defects of the power transformation equipment as claimed in claim 6, wherein the database server automatically establishes the relationship between each interval and the power transformation equipment by importing a data table form.
9. The intelligent image recognition management system for the defects of the power transformation equipment as claimed in claim 6, wherein the database server stores the image information by using a NoSQL non-relational database.
10. The intelligent image recognition management system for the defects of the power transformation equipment as recited in claim 6, wherein the database server stores the ledger information by adopting a MySQL relational database, and establishes the association between the ledger information and the image information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011122094.1A CN112380907A (en) | 2020-10-20 | 2020-10-20 | Intelligent image identification method for defects of power transformation equipment and management system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011122094.1A CN112380907A (en) | 2020-10-20 | 2020-10-20 | Intelligent image identification method for defects of power transformation equipment and management system thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112380907A true CN112380907A (en) | 2021-02-19 |
Family
ID=74581689
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011122094.1A Pending CN112380907A (en) | 2020-10-20 | 2020-10-20 | Intelligent image identification method for defects of power transformation equipment and management system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112380907A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011954A (en) * | 2021-04-23 | 2021-06-22 | 贵州兴泰科技有限公司 | Multifunctional machine account management system of Internet of things identification and query equipment |
| CN114154562A (en) * | 2021-11-15 | 2022-03-08 | 国网河北省电力有限公司电力科学研究院 | Device and method for detecting image recognition capability of intelligent monitoring terminal |
| CN114627119A (en) * | 2022-05-16 | 2022-06-14 | 山东通广电子有限公司 | Visual neural network-based appearance defect intelligent identification system and identification method |
| CN118249517A (en) * | 2024-05-21 | 2024-06-25 | 国网江西省电力有限公司南昌供电分公司 | Wi-Fi probe-based multi-mode substation operation and maintenance management method and system |
Citations (4)
| 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 |
| CN110648420A (en) * | 2019-09-20 | 2020-01-03 | 云南恒协科技有限公司 | Intelligent inspection system for scheduling master station system equipment |
| CN111080634A (en) * | 2019-12-23 | 2020-04-28 | 北京新松融通机器人科技有限公司 | Transformer appearance defect identification method based on inspection robot and Cascade RCNN algorithm |
| CN111510688A (en) * | 2020-05-19 | 2020-08-07 | 国网上海市电力公司 | Intelligent auxiliary control method for transformer substation with unmanned inspection function |
-
2020
- 2020-10-20 CN CN202011122094.1A patent/CN112380907A/en active Pending
Patent Citations (4)
| 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 |
| CN110648420A (en) * | 2019-09-20 | 2020-01-03 | 云南恒协科技有限公司 | Intelligent inspection system for scheduling master station system equipment |
| CN111080634A (en) * | 2019-12-23 | 2020-04-28 | 北京新松融通机器人科技有限公司 | Transformer appearance defect identification method based on inspection robot and Cascade RCNN algorithm |
| CN111510688A (en) * | 2020-05-19 | 2020-08-07 | 国网上海市电力公司 | Intelligent auxiliary control method for transformer substation with unmanned inspection function |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011954A (en) * | 2021-04-23 | 2021-06-22 | 贵州兴泰科技有限公司 | Multifunctional machine account management system of Internet of things identification and query equipment |
| CN114154562A (en) * | 2021-11-15 | 2022-03-08 | 国网河北省电力有限公司电力科学研究院 | Device and method for detecting image recognition capability of intelligent monitoring terminal |
| CN114627119A (en) * | 2022-05-16 | 2022-06-14 | 山东通广电子有限公司 | Visual neural network-based appearance defect intelligent identification system and identification method |
| CN114627119B (en) * | 2022-05-16 | 2022-08-02 | 山东通广电子有限公司 | Visual neural network-based appearance defect intelligent identification system and identification method |
| CN118249517A (en) * | 2024-05-21 | 2024-06-25 | 国网江西省电力有限公司南昌供电分公司 | Wi-Fi probe-based multi-mode substation operation and maintenance management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112380907A (en) | Intelligent image identification method for defects of power transformation equipment and management system thereof | |
| CN111091609B (en) | Transformer substation field operation management and control system and method based on three-dimensional dynamic modeling | |
| CN110048878B (en) | Three-span visual management system for power transmission line | |
| CN110415220A (en) | A kind of device intelligence method for inspecting of large hydropower station | |
| CN112734692A (en) | Transformer equipment defect identification method and device | |
| CN110598655B (en) | Artificial intelligent cloud computing multispectral smoke high-temperature spark fire monitoring method | |
| CN115395646B (en) | Intelligent operation and maintenance system of digital twin traction substation | |
| CN104573155B (en) | A kind of near surface PM2.5 Concentration Estimation Methods and estimating system | |
| CN108389007A (en) | Security risk managing and control system and method | |
| CN110379036A (en) | Intelligent substation patrol recognition methods, system, device and storage medium | |
| CN111104622A (en) | WEBGL-based three-dimensional GIS intelligent monitoring method and device | |
| CN108537422A (en) | Security risk early warning system and method | |
| CN111311133B (en) | Monitoring system applied to power grid production equipment | |
| CN110232089A (en) | A kind of three-dimensional city electric service command centre data visualization method | |
| CN113541315A (en) | Power transformation information comprehensive processing system | |
| CN108761199A (en) | Monitoring system and method is transported in the start and stop of contamination type enterprise | |
| CN112613569A (en) | Image recognition method, and training method and device of image classification model | |
| CN112186901B (en) | Panoramic sensing monitoring method and system for transformer substation | |
| CN113343998A (en) | Reading monitoring system and method for electric power mechanical meter, computer equipment and application | |
| CN114995259A (en) | Intelligent unmanned system for power grid distribution room inspection and flight inspection method | |
| CN107169627B (en) | Electric energy meter quality control method and system based on augmented reality technology | |
| CN116720242A (en) | Digital twin panoramic monitoring system for high-voltage cable tunnel | |
| CN110706365A (en) | Image characteristic data modeling method for power equipment | |
| CN111709597B (en) | Power grid production domain operation monitoring system | |
| CN109188153A (en) | A kind of high-tension switch gear three-dimensional panorama intelligent condition monitoring system |
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 |