CN109145134A - A kind of method and device of detection device failure - Google Patents
A kind of method and device of detection device failure Download PDFInfo
- Publication number
- CN109145134A CN109145134A CN201810844845.7A CN201810844845A CN109145134A CN 109145134 A CN109145134 A CN 109145134A CN 201810844845 A CN201810844845 A CN 201810844845A CN 109145134 A CN109145134 A CN 109145134A
- Authority
- CN
- China
- Prior art keywords
- target
- fault
- signature
- image
- detection device
- 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
Classifications
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/185—Electrical failure alarms
Abstract
The invention discloses a kind of methods of detection device failure, comprising: obtains the image of target device, and extracts the target signature in image；Judge to whether there is and the matched fault signature of target signature in preset database；If so, determining with the maximum fault signature of target signature matching degree, and will fault message corresponding with the maximum fault signature of target signature matching degree, be determined as the fault message of target device.This method can determine whether target device breaks down, and determine the specific fault message that target device occurs.The efficiency of detection device failure, accuracy and comprehensive are which thereby enhanced, provides necessary foundation for plant maintenance.Correspondingly, device, equipment and the computer readable storage medium of a kind of detection device failure disclosed by the invention, similarly has above-mentioned technique effect.
Description
Technical field
The present invention relates to field of computer technology, more specifically to a kind of detection device failure method, apparatus,
Equipment and computer readable storage medium.
Background technique
In the normal use process of physical equipment, inevitably there are circuit board fracture, device housings fracture or other hardware
Failure.
In industrial circle, in order to avoid device hardware failure bring adverse effect, generally by the patrol officer of profession
Physical equipment is overhauled one by one, and shoots the image for the equipment of hardware fault occur, and then the tool occurred by image identifying equipment
Body failure, and the reason of speculate failure and then failures that other may occur simultaneously.But due to hard in industrial plant
Part equipment is numerous, and the efficiency of manual measuring device's failure is more slow, simultaneously because artificial detection is inevitably made a fault, therefore examines
The accuracy of survey and comprehensive it is unable to get guarantee.
Therefore, the efficiency of detection device failure, accuracy and comprehensive how are improved, is that those skilled in the art need to solve
Certainly the problem of.
Summary of the invention
The purpose of the present invention is to provide a kind of method, apparatus of detection device failure, equipment and computer-readable storages
Medium, to improve the efficiency of detection device failure, accuracy and comprehensive.
To achieve the above object, the embodiment of the invention provides following technical solutions:
A kind of method of detection device failure, comprising:
The image of target device is obtained, and extracts the target signature in described image；
Judge to whether there is and the matched fault signature of the target signature in preset database；
If so, the determining and maximum fault signature of target signature matching degree, and will be matched with the target signature
The corresponding fault message of maximum fault signature is spent, the fault message of the target device is determined as.
Wherein, before the image for obtaining target device, further includes:
The image of the target device is acquired by camera, and screens described image.
Wherein, it is described will fault message corresponding with the maximum fault signature of target signature matching degree, be determined as institute
After the fault message for stating target device, further includes:
Generate include described image and the fault message warning message, and the warning message is transmitted to preset
Management end.
Wherein, further includes:
Statistical classification is carried out to the warning message in preset time period, generates fault statistics table.
Wherein, the generation step of the preset database includes:
Using 3D technology simulated failure information, the multiple fault simulation images for carrying different faults information are generated；
The failure true picture obtained in advance and each fault simulation image are iterated by instruction using deep learning network
Practice, generates multiple target faults images；
The fault signature is extracted from each target faults image, constitutes the database.
Wherein, the deep learning network is unsupervised VGG convolutional neural networks.
Wherein, further includes:
According to the database and CNN convolutional neural networks training fault identification model；
The image of the target device is inputted into the fault identification model, exports the image carrying of the target device
Fault message.
A kind of device of detection device failure, comprising:
Module is obtained, for obtaining the image of target device, and extracts the target signature in described image；
Judgment module whether there is and the matched fault signature of the target signature in preset database for judging；
Detection module, for determining when there is fault signature matched with the target signature in preset database
It, and will be corresponding with the maximum fault signature of target signature matching degree with the maximum fault signature of target signature matching degree
Fault message, be determined as the fault message of the target device.
A kind of equipment of detection device failure, comprising:
Memory, for storing computer program；
Processor realizes the side of detection device failure described in above-mentioned any one when for executing the computer program
The step of method.
A kind of computer readable storage medium is stored with computer program on the computer readable storage medium, described
The step of method of detection device failure described in above-mentioned any one is realized when computer program is executed by processor.
By above scheme it is found that a kind of method of detection device failure provided in an embodiment of the present invention, comprising: obtain mesh
The image of marking device, and extract the target signature in described image；Judge to whether there is and the target in preset database
The fault signature of characteristic matching；If so, the determining and maximum fault signature of target signature matching degree, and will be with the mesh
The corresponding fault message of the maximum fault signature of characteristic matching degree is marked, the fault message of the target device is determined as.
As it can be seen that the target signature in image of the method by extracting the target device got, and judge preset
In database with the presence or absence of with the matched fault signature of the target signature, if in preset database exist and the target signature
The fault signature matched then shows that fault message, and then the determining and maximum failure of target signature matching degree occurs in target device
Feature, and will fault message corresponding with the maximum fault signature of target signature matching degree, be determined as target device failure letter
Breath to can determine whether target device breaks down, and determines the specific fault message that target device occurs, without people
Work detects equipment one by one.The efficiency of detection device failure, accuracy and comprehensive are which thereby enhanced, is provided for plant maintenance
Necessary foundation.
Correspondingly, device, equipment and the computer-readable storage of a kind of detection device failure provided in an embodiment of the present invention
Medium similarly has above-mentioned technique effect.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of method flow diagram of detection device failure disclosed by the embodiments of the present invention；
Fig. 2 is the method flow diagram of another detection device failure disclosed by the embodiments of the present invention；
Fig. 3 is a kind of schematic device of detection device failure disclosed by the embodiments of the present invention；
Fig. 4 is a kind of equipment schematic diagram of detection device failure disclosed by the embodiments of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The embodiment of the invention discloses method, apparatus, equipment and the computer-readable storage mediums of a kind of detection device failure
Matter, to improve the efficiency of detection device failure, accuracy and comprehensive.
Referring to Fig. 1, a kind of method of detection device failure provided in an embodiment of the present invention, comprising:
S101, the image for obtaining target device, and extract the target signature in image；
In the present embodiment, the image that can obtain target device immediately can extract target signature from the image got.
Wherein, target signature is the feature of expression device fault information, such as: the fracture of circuitry plate, breakage, device housings are broken
Broken, interfacility link road breakage etc..
S102, judge to whether there is and the matched fault signature of target signature in preset database；If so, executing
S103；If it is not, then executing S104；
Specifically, various faults feature has been stored in advance in preset database, i.e., mentioned above " circuitry plate is disconnected
It splits, is damaged, broken, interfacility link road breakage of device housings etc. ", carried out for the target signature in the image with target device
Matching.It is matched to corresponding fault signature if target signature, then showing target device, there are failures；If not being target signature
It is matched to corresponding fault signature, then the fault message for showing that target device is indicated there is no failure or the target signature is not received
It records to the database, or the image of the target device currently got is not comprehensive, at this time angle variable and orientation, to obtain
To the more fully image of target device, so as to complete detection target device；At the same time it can also which the image of target device is passed
Maintenance personal is transported to, so that maintenance personal checks.
S103, determination and the maximum fault signature of target signature matching degree, and will be with the maximum event of target signature matching degree
Hinder the corresponding fault message of feature, is determined as the fault message of target device；
Specifically, obtained matching fault signature can when being matched to corresponding fault signature for target signature
Can be it is multiple, then determined from multiple fault signatures at this time with the maximum fault signature of target signature matching degree, and will be with mesh
The corresponding fault message of the maximum fault signature of characteristic matching degree is marked, is determined as the fault message of target device, can be detected out
The fault message that target device occurs.
S104, the image of target device is visualized.
Specifically, then showing target device, there is no events when not being that target signature is matched to corresponding fault signature
The fault message that barrier or the target signature indicate is not included to the database, or the image of the target device currently got
Not comprehensively, angle variable and orientation at this time, to get the more fully image of target device, so as to complete detection target
Equipment；So the image of target device is visualized, so that maintenance personal checks.
As it can be seen that a kind of method for present embodiments providing detection device failure, the method is by extracting the mesh got
Target signature in the image of marking device, and judge in preset database with the presence or absence of special with the matched failure of the target signature
Sign, if in preset database exist with the matched fault signature of the target signature, show that failure letter occurs in target device
Breath, and then the determining and maximum fault signature of target signature matching degree, and will be with the maximum fault signature of target signature matching degree
Corresponding fault message, is determined as the fault message of target device, to can determine whether target device breaks down, and determines
The specific fault message that target device occurs out.The efficiency of detection device failure, accuracy and comprehensive are which thereby enhanced, to set
Standby maintenance provides necessary foundation.
The embodiment of the invention discloses the methods of another detection device failure, relative to a upper embodiment, the present embodiment
Further instruction and optimization have been made to technical solution.
Referring to fig. 2, the method for another detection device failure provided in an embodiment of the present invention, comprising:
S201, the image for obtaining target device, and extract the target signature in image；
S202, judge to whether there is and the matched fault signature of target signature in preset database；If so, executing
S203；If it is not, then executing S205；
S203, determination and the maximum fault signature of target signature matching degree, and will be with the maximum event of target signature matching degree
Hinder the corresponding fault message of feature, is determined as the fault message of target device, and execute S204；
S204, the warning message for generating the image comprising target device and fault message, and warning message is transmitted to pre-
If management end；
In the present embodiment, it after determining fault message existing for target device, can be generated comprising target device
The warning message of image and fault message, and warning message is transmitted to preset management end, so that maintenance personal checks alarm
Information, and target device is repaired according to warning message.
S205, the image of target device is visualized.
Preferably for the warning message in a period of time, statistical classification can be carried out, in order to opening for plant maintenance work
Exhibition.It is possible to carry out statistical classification to the warning message in preset time period, fault statistics table is generated, so as to maintenance personal
Maintenance policy is formulated according to fault statistics table, ensures the even running of hardware device.
As it can be seen that the method for present embodiments providing another detection device failure, the method is got by extraction
Target signature in the image of target device, and judge to whether there is and the matched failure of the target signature in preset database
Feature, if in preset database exist with the matched fault signature of the target signature, show that failure occurs in target device
Information, and then the determining and maximum fault signature of target signature matching degree, and will be special with the maximum failure of target signature matching degree
Corresponding fault message is levied, the fault message of target device is determined as, to can determine whether target device breaks down, and really
Make the specific fault message of target device appearance.The efficiency of detection device failure, accuracy and comprehensive are which thereby enhanced, is
Plant maintenance provides necessary foundation.
Based on above-mentioned any embodiment, it should be noted that before the image for obtaining target device, further includes: logical
It crosses camera and acquires the image of the target device, and screen described image.Specifically, target device can be acquired by camera
Image, the camera be zoom camera or cameras with fixed focus；Meanwhile camera can be installed on Rotatable base, with
Just camera omnidirectional shooting target device.It is, of course, also possible to acquire the figure of target device by the inspection machine of autonomous
Picture.
Based on above-mentioned any embodiment, it should be noted that the generation step of the preset database includes:
Using 3D technology simulated failure information, the multiple fault simulation images for carrying different faults information are generated；
The failure true picture obtained in advance and each fault simulation image are iterated by instruction using deep learning network
Practice, generates multiple target faults images；
The fault signature is extracted from each target faults image, constitutes the database.
Wherein, the deep learning network is unsupervised VGG convolutional neural networks.
Specifically, the VGG convolutional neural networks include: multiple convolutional layers, for rendering event according to failure true picture
Hinder analog image, to compensate the content lacked in fault simulation image, makes the target faults image generated and failure true picture
Indifference.Meanwhile can store multiple target faults images of generation, with the statistical analysis for equipment fault provide effectively according to
According to.Wherein, a target faults image can correspond to a fault simulation image, i.e., simulate how many a failure moulds by 3D technology
Quasi- image, can obtain how many a target faults images, the quantity of fault simulation image and the quantity of target faults image are equal.
It is of course also possible to generate multiple target faults images by a fault simulation image.
Based on above-mentioned any embodiment, it should be noted that after generating the database comprising various faults feature, may be used also
To identify mesh using the fault identification model according to the database and CNN convolutional neural networks training fault identification model
The fault message of marking device.That is: by the image input fault identification model of the target device, the figure of the target device is exported
As the fault message carried.
It should be noted that in detection device failure, the feature and number that can directly carry the image for needing to detect
It is matched according to the fault signature in library, the fault message of target device is determined according to matching result；It can also utilize comprising big
The database and CNN convolutional neural networks training fault identification model for measuring fault signature, identify target using fault identification model
The fault message of equipment.Wherein, according to database and CNN convolutional neural networks training fault identification model, and according to failure knowledge
The concrete methods of realizing of the fault message of other model identification target device, can be specifically real according to existing any neural network algorithm
It applies, therefore details are not described herein for this specification.
A kind of device of detection device failure provided in an embodiment of the present invention is introduced below, one kind described below
The device of detection device failure can be cross-referenced with a kind of above-described method of detection device failure.
Referring to Fig. 3, a kind of device of detection device failure provided in an embodiment of the present invention, comprising:
Module 301 is obtained, for obtaining the image of target device, and extracts the target signature in described image；
Judgment module 302, for judging in preset database with the presence or absence of special with the matched failure of the target signature
Sign；
Detection module 303 is used for when there is fault signature matched with the target signature in preset database, really
The fixed and maximum fault signature of target signature matching degree, and will be with the maximum fault signature pair of target signature matching degree
The fault message answered is determined as the fault message of the target device.
Wherein, further includes:
Acquisition module for acquiring the image of the target device by camera, and screens described image.
Wherein, further includes:
Warning message generation module, for generating the warning message comprising described image and the fault message, and by institute
It states warning message and is transmitted to preset management end.
Wherein, further includes:
Statistical module generates fault statistics table for carrying out statistical classification to the warning message in preset time period.
It wherein, further include database generation module, the database generation module includes:
Generation unit generates the multiple failure moulds for carrying different faults information for using 3D technology simulated failure information
Quasi- image；
Acquiring unit, for using deep learning network by the failure true picture obtained in advance and each fault simulation figure
As being iterated training, multiple target faults images are generated；
Extraction unit constitutes the database for extracting the fault signature from each target faults image.
Further include:
Training module, for according to the database and CNN convolutional neural networks training fault identification model；
Identification module exports the target and sets for the image of the target device to be inputted the fault identification model
The fault message that standby image carries.
As it can be seen that present embodiments providing a kind of device of detection device failure, comprising: obtain module, judgment module, detection
Module.The image of target device is obtained by acquisition module first, and extracts the target signature in described image；Then by judgement mould
Block judges to whether there is and the matched fault signature of the target signature in preset database；It is determined finally by detection module
It, and will be corresponding with the maximum fault signature of target signature matching degree with the maximum fault signature of target signature matching degree
Fault message, be determined as the fault message of the target device.Share out the work and help one another between such modules, Each performs its own functions, from
And it defines target device and whether breaks down, and determine the specific fault message that target device occurs.It which thereby enhances
The efficiency of detection device failure, accuracy and comprehensive, provide necessary foundation for plant maintenance.
A kind of equipment of detection device failure provided in an embodiment of the present invention is introduced below, one kind described below
The equipment of detection device failure can be cross-referenced with a kind of above-described method and device of detection device failure.
Referring to fig. 4, the equipment of a kind of detection device failure provided in an embodiment of the present invention, comprising:
Memory 401, for storing computer program；
Processor 402 realizes the event of detection device described in above-mentioned any embodiment when for executing the computer program
The step of method of barrier.
A kind of computer readable storage medium provided in an embodiment of the present invention is introduced below, one kind described below
Computer readable storage medium can be cross-referenced with a kind of above-described method, device and equipment of detection device failure.
A kind of computer readable storage medium is stored with computer program on the computer readable storage medium, described
The step of method of the detection device failure as described in above-mentioned any embodiment is realized when computer program is executed by processor.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of method of detection device failure characterized by comprising
The image of target device is obtained, and extracts the target signature in described image；
Judge to whether there is and the matched fault signature of the target signature in preset database；
If so, the determining and maximum fault signature of target signature matching degree, and will be with the target signature matching degree most
The corresponding fault message of big fault signature, is determined as the fault message of the target device.
2. the method for detection device failure according to claim 1, which is characterized in that the image for obtaining target device
Before, further includes:
The image of the target device is acquired by camera, and screens described image.
3. the method for detection device failure according to claim 1, which is characterized in that it is described will be with the target signature
With the corresponding fault message of maximum fault signature is spent, it is determined as after the fault message of the target device, further includes:
The warning message comprising described image and the fault message is generated, and the warning message is transmitted to preset management
End.
4. the method for detection device failure according to claim 3, which is characterized in that further include:
Statistical classification is carried out to the warning message in preset time period, generates fault statistics table.
5. the method for detection device failure according to any one of claims 1-4, which is characterized in that the preset number
Include: according to the generation step in library
Using 3D technology simulated failure information, the multiple fault simulation images for carrying different faults information are generated；
The failure true picture obtained in advance and each fault simulation image are iterated by training using deep learning network, it is raw
At multiple target faults images；
The fault signature is extracted from each target faults image, constitutes the database.
6. the method for detection device failure according to claim 5, which is characterized in that the deep learning network is no prison
The VGG convolutional neural networks superintended and directed.
7. the method for detection device failure according to claim 5, which is characterized in that further include:
According to the database and CNN convolutional neural networks training fault identification model；
The image of the target device is inputted into the fault identification model, exports the failure that the image of the target device carries
Information.
8. a kind of device of detection device failure characterized by comprising
Module is obtained, for obtaining the image of target device, and extracts the target signature in described image；
Judgment module whether there is and the matched fault signature of the target signature in preset database for judging；
Detection module is used for when there is fault signature matched with the target signature in preset database, determining and institute
The maximum fault signature of target signature matching degree is stated, and will event corresponding with the maximum fault signature of target signature matching degree
Hinder information, is determined as the fault message of the target device.
9. a kind of equipment of detection device failure characterized by comprising
Memory, for storing computer program；
Processor realizes the detection device event as described in claim 1-7 any one when for executing the computer program
The step of method of barrier.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the detection device failure as described in claim 1-7 any one when the computer program is executed by processor
Method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810844845.7A CN109145134A (en) | 2018-07-27 | 2018-07-27 | A kind of method and device of detection device failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810844845.7A CN109145134A (en) | 2018-07-27 | 2018-07-27 | A kind of method and device of detection device failure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109145134A true CN109145134A (en) | 2019-01-04 |
Family
ID=64798336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810844845.7A Pending CN109145134A (en) | 2018-07-27 | 2018-07-27 | A kind of method and device of detection device failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109145134A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110207832A (en) * | 2019-06-26 | 2019-09-06 | 深圳市微纳集成电路与系统应用研究院 | High-tension line cruising inspection system and its method for inspecting based on unmanned plane |
| CN110851296A (en) * | 2019-10-29 | 2020-02-28 | 北京海益同展信息科技有限公司 | Fault detection method and device and storage medium |
| CN110851329A (en) * | 2019-11-12 | 2020-02-28 | 黑龙江电力调度实业有限公司 | Machine room state diagnosis system and method |
| CN113791929A (en) * | 2021-11-17 | 2021-12-14 | 北京中科开迪软件有限公司 | Method and system for automatically recovering optical disk library fault based on image recognition |
| CN114937043A (en) * | 2022-07-26 | 2022-08-23 | 中国工业互联网研究院 | Equipment defect detection method, device, equipment and medium based on artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331521A (en) * | 2014-11-27 | 2015-02-04 | 国家电网公司 | Automatic power transformation equipment abnormity identification method based on image processing |
| CN106248368A (en) * | 2016-09-21 | 2016-12-21 | 哈尔滨工程大学 | A kind of combustion engine turbine blade fault detection method based on degree of depth study |
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| CN107826919A (en) * | 2017-10-20 | 2018-03-23 | 中国矿业大学 | A kind of lifting system critical component multimode health monitoring device and monitoring method |
-
2018
- 2018-07-27 CN CN201810844845.7A patent/CN109145134A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331521A (en) * | 2014-11-27 | 2015-02-04 | 国家电网公司 | Automatic power transformation equipment abnormity identification method based on image processing |
| CN106248368A (en) * | 2016-09-21 | 2016-12-21 | 哈尔滨工程大学 | A kind of combustion engine turbine blade fault detection method based on degree of depth study |
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| CN107826919A (en) * | 2017-10-20 | 2018-03-23 | 中国矿业大学 | A kind of lifting system critical component multimode health monitoring device and monitoring method |
Non-Patent Citations (1)
| Title |
|---|
| AI科技大本营: "苹果机器学习博客解读CVPR论文：通过对抗训练从模拟的和无监督的图像中学习", 《HTTPS://CLOUD.TENCENT.COM/DEVELOPER/ARTICLE/1111976》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110207832A (en) * | 2019-06-26 | 2019-09-06 | 深圳市微纳集成电路与系统应用研究院 | High-tension line cruising inspection system and its method for inspecting based on unmanned plane |
| CN110851296A (en) * | 2019-10-29 | 2020-02-28 | 北京海益同展信息科技有限公司 | Fault detection method and device and storage medium |
| CN110851329A (en) * | 2019-11-12 | 2020-02-28 | 黑龙江电力调度实业有限公司 | Machine room state diagnosis system and method |
| CN113791929A (en) * | 2021-11-17 | 2021-12-14 | 北京中科开迪软件有限公司 | Method and system for automatically recovering optical disk library fault based on image recognition |
| CN114937043A (en) * | 2022-07-26 | 2022-08-23 | 中国工业互联网研究院 | Equipment defect detection method, device, equipment and medium based on artificial intelligence |
| CN114937043B (en) * | 2022-07-26 | 2022-10-25 | 中国工业互联网研究院 | Equipment defect detection method, device, equipment and medium based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145134A (en) | A kind of method and device of detection device failure | |
| CN110674790B (en) | Abnormal scene processing method and system in video monitoring | |
| CN111598132B (en) | Portrait recognition algorithm performance evaluation method and device | |
| CN113343779B (en) | Environment abnormality detection method, device, computer equipment and storage medium | |
| CN110473375A (en) | Monitoring method, device, equipment and the system of forest fire | |
| CN113191699A (en) | Power distribution construction site safety supervision method | |
| CN112541393A (en) | Transformer substation personnel detection method and device based on deep learning | |
| CN109660518A (en) | Communication data detection method, device and the machine readable storage medium of network | |
| CN111063144A (en) | Abnormal behavior monitoring method, device, equipment and computer readable storage medium | |
| CN111428694A (en) | Abnormal smoke monitoring system of wisdom building site based on block chain | |
| CN110379036A (en) | Intelligent substation patrol recognition methods, system, device and storage medium | |
| CN111353399A (en) | Tamper video detection method | |
| CN110740298A (en) | Distributed classroom discipline behavior detection system, method and medium | |
| CN106130762A (en) | A kind of network training comprehensive analysis method based on finite automaton | |
| CN111695493A (en) | Method and system for detecting hidden danger of power transmission line | |
| CN115861173A (en) | Automatic detection system and method for accuracy of optical splitter resources based on digital twin and AI | |
| CN114639152A (en) | Multi-modal voice interaction method, device, equipment and medium based on face recognition | |
| CN111913619B (en) | Fire-fighting data reading and interaction method based on BIM lightweight | |
| CN103824074A (en) | Crowd density estimation method based on background subtraction and texture features and system | |
| CN114049568A (en) | Object shape change detection method, device, equipment and medium based on image comparison | |
| CN113065026A (en) | Intelligent abnormal event detection system, method and medium based on security micro-service architecture | |
| CN111723656B (en) | Smog detection method and device based on YOLO v3 and self-optimization | |
| CN116189063B (en) | Key frame optimization method and device for intelligent video monitoring | |
| CN112966547A (en) | Neural network-based gas field abnormal behavior recognition early warning method, system, terminal and storage medium | |
| CN117422695A (en) | CR-deep-based anomaly detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190104 |
|
| RJ01 | Rejection of invention patent application after publication |