CN114740007A - Non-contact surface defect detection device and use method - Google Patents
Non-contact surface defect detection device and use method Download PDFInfo
- Publication number
- CN114740007A CN114740007A CN202210297981.5A CN202210297981A CN114740007A CN 114740007 A CN114740007 A CN 114740007A CN 202210297981 A CN202210297981 A CN 202210297981A CN 114740007 A CN114740007 A CN 114740007A
- Authority
- CN
- China
- Prior art keywords
- contact surface
- surface defect
- detection
- data
- signal output
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 111
- 230000007547 defect Effects 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000013135 deep learning Methods 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims 8
- 238000007405 data analysis Methods 0.000 abstract description 4
- 230000001360 synchronised effect Effects 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 239000000463 material Substances 0.000 description 6
- 238000013480 data collection Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 239000004033 plastic Substances 0.000 description 3
- 229920003023 plastic Polymers 0.000 description 3
- 229910000838 Al alloy Inorganic materials 0.000 description 2
- 208000034656 Contusions Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 241000512668 Eunectes Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
Abstract
The application discloses a non-contact surface defect detection device and a using method thereof, and relates to the field of surface defect detection. The non-contact surface defect detection device comprises: the camera distance detection device comprises a shell provided with an opening, wherein the opening of the shell is provided with a camera and a distance detector which are adjacently arranged, and the shell is also provided with a control panel, an acquisition switch, a power switch and a signal output end; the camera, the distance detector, the acquisition switch, the power switch and the signal output end are electrically connected with the control panel; the signal output end is in signal connection with the data processor. The detection device is compact in structure, the signal output end is directly in signal connection with the data processor, and synchronous defect identification and data analysis are realized, namely the surface defects of the components can be quickly identified; and all parts are connected in a special connection mode, so that the method is suitable for the requirement of surface defect detection and identification of aviation components.
Description
Technical Field
The application relates to the field of surface defect detection, in particular to a non-contact surface defect detection device and a using method thereof.
Background
The aircraft manufacturing is a process of combining and assembling a large number of parts, finished products, conduits and the like to form a whole, and in the process, the surfaces of the parts of the aircraft are easy to have surface defects such as scratches and bruises due to the influence of tools, measuring tools and the like and the collision in the carrying process. If the defects are not discovered and reasonably treated in time, the greater quality problems of breakage, leakage and the like of the parts of the airplane can be further caused, and the flight safety of the airplane is directly influenced.
At present, two methods of manual detection and visual detection are mainly used for detecting the surface defects. Wherein, artifical measuring mainly relies on human eye, with the help of instruments visual inspection such as flashlight, has that the artificial error that detects is big, human eye is tired easily, takes place wrong examination easily and leak hunting, detection efficiency low grade problem. The visual detection is based on visual image processing, the detection problems of scratches and the like of surface defects of products are solved, but the aviation component has the characteristics of variable surface curvature, different surface materials (aluminum alloy, composite materials, plastics and the like), multiple defect types (such as pits, scratches, pits and the like), large detection objects and the like, and the detection method and the detection tool are difficult to meet the detection requirements of the surface defects of the aviation component.
Disclosure of Invention
The application provides a non-contact surface defect detection device and a use method, which are suitable for the defect detection requirement of aviation components with curvature surfaces and can realize the rapid detection of the surface defects of the components.
To achieve the above object, the present application provides a non-contact surface defect detecting apparatus, comprising:
the camera distance detection device comprises a shell provided with an opening, wherein the opening of the shell is provided with a camera and a distance detector which are adjacently arranged, and the shell is also provided with a control panel, an acquisition switch, a power switch and a signal output end;
the camera, the distance detector, the acquisition switch, the power switch and the signal output end are electrically connected with the control panel;
the signal output end is in signal connection with the data processor.
As a further improvement of the invention, the distance detector is a point laser;
the point laser and the camera are both oriented in the same direction.
As a further improvement of the invention, the signal output end is an aviation plug;
the aviation plug is in signal connection with the data processor through a connecting wire.
As a further improvement of the invention, a power supply is also arranged in the shell;
the power supply is electrically connected with the control panel.
As a further improvement of the invention, the shell is also provided with a collecting switch state lamp and a power supply state lamp;
the acquisition switch state lamp and the power supply state lamp are both electrically connected with the control panel.
As a further improvement of the invention, the shell comprises a detection head shell and a handle which are connected;
the opening of the housing, the camera and the distance detector are all disposed on the detector head housing.
As a further improvement of the invention, the surface of the handle is provided with a concave-convex curved surface;
the control panel, the acquisition switch, the power switch and the signal output end are all arranged on the handle.
In addition, in order to solve the above technical problem, the present application further provides a method for using a non-contact surface defect detecting apparatus, including the following steps:
the non-contact surface defect detection device is adopted to collect the image of the surface of the part sample to obtain detection data;
obtaining a detection data set by deep learning of the detection data;
and identifying the surface defects of the components according to the detection data set.
As a further improvement of the present invention, the step of acquiring the image of the surface of the component sample by using the non-contact surface defect detecting device to obtain the detection data includes:
carrying out artificial defect manufacturing on the surface of the part sample to obtain the part sample with surface defects;
and acquiring data of the image on the surface of the part sample by adopting a non-contact surface defect detection device under different angles, different light rays and different focal lengths to obtain detection data.
As a further improvement of the present invention, the step of acquiring the detection data by acquiring the data of the image of the surface of the component sample with the non-contact surface defect detection device under different angles, different light rays and different focal lengths comprises:
acquiring data of images on the surface of a part sample by using a non-contact surface defect detection device under different angles, different light rays and different focal lengths to obtain first detection data;
and obtaining expanded second detection data after the first detection data is subjected to cutting, splicing, visual angle conversion and contrast sharpening.
The non-contact surface defect detection device provided by the application has a compact structure, the signal output end is directly in signal connection with the data processor, and synchronous defect identification and data analysis are realized, namely the surface defects of the zero component can be quickly identified; the camera, the distance detector, the control panel and the like are connected in a special connection mode to realize the portability of the surface defect detection device; therefore, the method can be better suitable for the surface defect detection and identification requirements of aviation components with the characteristics of variable surface curvatures, different surface materials, multiple defect types, large detection objects and the like.
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 some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of a non-contact surface defect detecting apparatus;
FIG. 2 is an original image of the surface of a component;
FIG. 3 is an image of a component with surface defects marked;
FIG. 4 is a classification diagram of the surface defect detection results of the components;
wherein, 1 is a camera, 12 is a switch state lamp, 13 is a power state lamp, 2 is a distance detector, 3 is a shell, 31 is a detection head shell, 32 is a handle, 4 is an acquisition switch, 5 is a data processor, 6 is a power switch, 7 is a support frame, 8 is a control panel, 9 is a signal output end, 10 is a connecting wire, 11 is a power supply,
the implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The aircraft manufacturing is a process of combining and assembling a large number of parts, finished products, conduits and the like to form a whole, and in the process, the surfaces of the parts of the aircraft are easy to have surface defects such as scratches and bruises due to the influence of tools, measuring tools and the like and the collision in the carrying process. If the defects are not discovered and reasonably treated in time, the greater quality problems of breakage, leakage and the like of the parts of the airplane can be further caused, and the flight safety of the airplane is directly influenced.
At present, two methods of manual detection and visual detection are mainly used for detecting the surface defects. Wherein, artifical measuring mainly relies on human eye, with the help of instruments visual inspection such as flashlight, has that the artificial error that detects is big, human eye is tired easily, takes place wrong examination easily and leak hunting, detection efficiency low grade problem. The visual detection is based on visual image processing, the detection problems of scratches and the like of surface defects of products are solved, but the aviation component has the characteristics of variable surface curvature, different surface materials (aluminum alloy, composite materials, plastics and the like), multiple defect types (such as pits, scratches, pits and the like), large detection objects and the like, and the detection method and the detection tool are difficult to meet the detection requirements of the surface defects of the aviation component.
Therefore, a portable detection device capable of rapidly detecting a plurality of surface defects is needed.
Based on this, the main solutions of the embodiments of the present application are:
as shown in fig. 1, a non-contact surface defect detecting device includes a housing 3 having an opening, a camera 1 and a distance detector are adjacently disposed on the opening of the housing 3, and the housing 3 is further provided with a control panel 8, a collecting switch 4, a power switch 6 and a signal output terminal. The camera 1, the distance detector, the acquisition switch 4, the power switch 6 and the signal output end are all electrically connected with the control panel 8. The signal output end is in signal connection with the data processor 5.
The non-contact surface defect detection device provided by the application has a compact structure, the signal output end is directly in signal connection with the data processor, and synchronous defect identification and data analysis are realized, namely the surface defects of the zero component can be quickly identified; the camera, the distance detector, the control panel and the like are connected in a special connection mode to realize the portability of the surface defect detection device; therefore, the method can be better suitable for the surface defect detection and identification requirements of aviation components with the characteristics of variable surface curvatures, different surface materials, multiple defect types, large detection objects and the like.
As some possible embodiments of the present application, the distance detector comprises a spot laser 2, both spot laser 2 and camera 1 being oriented in the same direction. The point laser 2 emits a point light source to the surface of the product, the photoelectric element receives the laser beam reflected by the target, the timer of the control panel 8 measures the time from the emission to the reception of the laser beam, the distance from the point laser 2 to the target is calculated, and the acquisition of the distance information of the detection surface is realized. The camera 1 has an automatic focusing function, and the data processor 5 focuses the picture by the camera 1 according to the distance information, so that the surface image of the product can be rapidly acquired. The shell is made of light plastic materials through 3D printing, and the weight of the device is reduced while the connection strength of the camera 1 and the dot laser 2 is guaranteed.
In order to better adapt to the surface defect detection of aviation components, as some possible embodiments of the present application, the signal output terminal is an aviation plug 9, and the aviation plug 9 is in signal connection with the data processor 5 through a connection line 10. The data processor 5 acquires the acquired data through a connecting line 10 and performs data processing and display.
In order to better control the state of the non-contact surface defect detection device, as some possible embodiments of the present application, a power supply 11 is further disposed in the housing 3, and the power supply 11 is electrically connected to the control panel 8. Still be equipped with collection on off state lamp 12 and power status lamp 13 on the shell 3, gather on off state lamp 12 and power status lamp 13 both and control panel 8 electric connection.
As some possible embodiments of the present application, the housing 3 includes a detection head housing 31 and a handle 32 connected together. The opening of the housing 3, the camera 1, and the distance detector are all provided on the detection head housing 31. Control panel 8, collection switch 4, switch 6 and signal output part all set up on handle 32, as some implementable ways of this application, control panel 8, collection switch 4, switch 6 and signal output part all fix through the support frame on handle 32. The surface of the handle 32 is provided with a concave-convex curved surface, which is convenient for taking during measurement. The acquisition switch 4 is a key, and when the acquisition key is pressed, the acquisition switch state lamp 12 emits light; the power status light 13 is illuminated by pressing the power switch 6.
As some possible embodiments of the present application, the data processor 5 constructs data processing software in a deep learning manner, so as to implement processing of detection data, and implements functions of detection data entry, defect positioning operation, defect size measurement, and defect detection result storage through the data processing software, thereby implementing detection of large-area surface defects and having a large detection range.
In addition, the application also provides a using method of the non-contact surface defect detecting device, which comprises the following steps:
the non-contact surface defect detection device is adopted to collect the image of the surface of the part sample to obtain detection data;
obtaining a detection data set by deep learning of the detection data;
and identifying the surface defects of the components according to the detection data set.
As some possible embodiments of the present application, the step of acquiring an image of a surface of a component sample by using a non-contact surface defect detection apparatus to obtain detection data includes:
carrying out artificial defect manufacturing on the surface of the part sample to obtain the part sample with surface defects;
and acquiring data of the image on the surface of the part sample by adopting a non-contact surface defect detection device under different angles, different light rays and different focal lengths to obtain detection data.
In order to improve the data collection amount of the detection device to the component and ensure the accuracy of subsequent analysis and identification, artificial defect manufacturing is carried out on the surface of the component sample, mainly for simulating the surface defects of the component, for example, after at least one of the modes of friction, scratch and knocking is randomly adopted on the component sample manually to form the defects of scratch, dent, bulge and pock, a non-contact surface defect detection device is adopted to carry out data collection on the images on the surface of the component sample under different angles, different light rays and different focal lengths, so as to obtain detection data.
In order to further improve the data collection quantity of the detection device to the zero component and to guarantee the accuracy of subsequent analysis and identification, as some implementable modes of the application, adopt non-contact surface defect detection device to carry out data collection to the image of the surface of the zero component sample piece under different angles, different light rays and different focal lengths, the step of obtaining the detection data includes:
acquiring data of images on the surface of a part sample by using a non-contact surface defect detection device under different angles, different light rays and different focal lengths to obtain first detection data;
and obtaining expanded second detection data after the first detection data is subjected to cutting, splicing, visual angle conversion and contrast sharpening.
And the number of model parameters of the expanded second detection data is not less than 30M, so that the time consumption of a single recognition result is ensured to be less than 0.05 s.
The deep learning framework is PyTorch, and the EfficientNet and the U-Net are used as main algorithms of the deep learning neural network in the deep learning. The deep learning algorithm adopts U-Net as a network backbone, EfficientNet as an encoder to extract features, and adopts pre-weighting to fix network parameters, so that the features are fully extracted under the condition of small data volume. The training of deep learning is carried out on an operating system and an integrated management platform Anaconda, a deep learning framework tool PyTorch is adopted, a data set is expanded after samples are processed by cutting, splicing, visual angle conversion, sharpening contrast and the like, the number of parameters of a typical model is not less than 30M, the time consumption of a single recognition result is guaranteed to be less than 0.05s, and the rapid detection of surface defects of all scales of the surface of a component is realized.
The surface original image obtained by collecting the surface of the component by the non-contact surface defect detection device is shown in fig. 2, the image labeled by the device after identifying the surface defect of the component is shown in fig. 3, and the image obtained by classifying the surface defect result of the defect labeled image shown in fig. 3 is shown in fig. 4. The non-contact surface defect detection device provided by the application has a compact structure, the signal output end is directly in signal connection with the data processor, the defect identification and data analysis are synchronously performed, and the surface defect of the component can be quickly identified; the camera, the distance detector, the control panel and the like are connected in a special connection mode to realize the portability of the surface defect detection device; therefore, the method can be better suitable for the surface defect detection and identification requirements of aviation components with the characteristics of variable surface curvatures, different surface materials, multiple defect types, large detection objects and the like. By combining the detection method, a large amount of data are collected and expanded to obtain a data set with model parameters not less than 30M, and the data set is subjected to deep network learning to extract features of the data set, so that the accuracy of detection and identification is improved.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. A non-contact surface defect inspection apparatus, comprising:
the camera distance detection device comprises a shell (3) provided with an opening, wherein the opening of the shell (3) is provided with a camera (1) and a distance detector which are adjacently arranged, and the shell (3) is also provided with a control panel (8), a collection switch (4), a power switch (6) and a signal output end;
the camera (1), the distance detector, the acquisition switch (4), the power switch (6) and the signal output end are electrically connected with the control panel (8);
the signal output end is in signal connection with the data processor (5).
2. A non-contact surface defect detection apparatus according to claim 1, wherein said distance detector is a spot laser (2);
the orientation of the point laser (2) is the same as that of the camera (1).
3. A non-contact surface defect detection apparatus according to claim 1, wherein said signal output is an aircraft plug (9);
the aviation plug (9) is in signal connection with the data processor (5) through a connecting wire (10).
4. A non-contact surface defect detecting device according to claim 1, characterized in that a power source (11) is further provided in the housing (3);
the power supply (11) is electrically connected with the control panel (8).
5. A non-contact surface defect detecting device according to claim 1, characterized in that the housing (3) is further provided with a collecting switch status lamp (12) and a power status lamp (13);
the acquisition switch state lamp (12) and the power supply state lamp (13) are both electrically connected with the control panel (8).
6. A non-contact surface defect inspection apparatus according to claim 1, wherein the housing (3) comprises a head housing (31) and a handle (32) connected together;
the opening of the housing (3), the camera (1) and the distance detector are all arranged on the detection head housing (31).
7. A non-contact surface defect detecting device according to claim 6, characterized in that the surface of the handle (32) is provided with a concave-convex curved surface;
the control panel (8), the acquisition switch (4), the power switch (6) and the signal output end are all arranged on the handle (32).
8. A method of using a non-contact surface defect inspection apparatus, comprising the steps of:
acquiring an image of the surface of a component sample by using the non-contact surface defect detection device according to any one of claims 1 to 7 to obtain detection data;
obtaining a detection data set by deep learning of the detection data;
and identifying the surface defects of the components according to the detection data set.
9. The method for using a non-contact surface defect inspection apparatus according to claim 8, wherein the step of acquiring the image of the surface of the component sample by using the non-contact surface defect inspection apparatus to obtain the inspection data comprises:
carrying out artificial defect manufacturing on the surface of the part sample to obtain the part sample with surface defects;
and acquiring data of the image on the surface of the part sample by adopting a non-contact surface defect detection device under different angles, different light rays and different focal lengths to obtain detection data.
10. The method of claim 9, wherein the step of acquiring the inspection data by acquiring the image of the surface of the component sample with the non-contact surface defect inspection apparatus under different angles, different light beams and different focal lengths comprises:
acquiring data of images on the surface of a part sample by using a non-contact surface defect detection device under different angles, different light rays and different focal lengths to obtain first detection data;
and obtaining expanded second detection data after the first detection data is subjected to cutting, splicing, visual angle conversion and contrast sharpening.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210297981.5A CN114740007A (en) | 2022-03-23 | 2022-03-23 | Non-contact surface defect detection device and use method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210297981.5A CN114740007A (en) | 2022-03-23 | 2022-03-23 | Non-contact surface defect detection device and use method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114740007A true CN114740007A (en) | 2022-07-12 |
Family
ID=82276764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210297981.5A Pending CN114740007A (en) | 2022-03-23 | 2022-03-23 | Non-contact surface defect detection device and use method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114740007A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103543161A (en) * | 2013-10-16 | 2014-01-29 | 湖南镭目科技有限公司 | On-line detection method of continuous casting billet surface quality |
| WO2016020826A1 (en) * | 2014-08-07 | 2016-02-11 | Ingenera Sa | Method and relevant device for measuring distance with auto-calibration and temperature compensation |
| CN109636772A (en) * | 2018-10-25 | 2019-04-16 | 同济大学 | The defect inspection method on the irregular shape intermetallic composite coating surface based on deep learning |
| CN109934811A (en) * | 2019-03-08 | 2019-06-25 | 中国科学院光电技术研究所 | A kind of optical element surface defect inspection method based on deep learning |
| CN111322954A (en) * | 2020-03-19 | 2020-06-23 | 北京神工科技有限公司 | Assembly tool pose measuring method and device, storage medium and electronic equipment |
| CN113390882A (en) * | 2021-06-10 | 2021-09-14 | 青岛理工大学 | Tire inner side defect detector based on machine vision and deep learning algorithm |
| CN113989271A (en) * | 2021-11-25 | 2022-01-28 | 江苏科技大学 | Paint image segmentation system and method based on double-attention mechanism and U-net network |
-
2022
- 2022-03-23 CN CN202210297981.5A patent/CN114740007A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103543161A (en) * | 2013-10-16 | 2014-01-29 | 湖南镭目科技有限公司 | On-line detection method of continuous casting billet surface quality |
| WO2016020826A1 (en) * | 2014-08-07 | 2016-02-11 | Ingenera Sa | Method and relevant device for measuring distance with auto-calibration and temperature compensation |
| CN109636772A (en) * | 2018-10-25 | 2019-04-16 | 同济大学 | The defect inspection method on the irregular shape intermetallic composite coating surface based on deep learning |
| CN109934811A (en) * | 2019-03-08 | 2019-06-25 | 中国科学院光电技术研究所 | A kind of optical element surface defect inspection method based on deep learning |
| CN111322954A (en) * | 2020-03-19 | 2020-06-23 | 北京神工科技有限公司 | Assembly tool pose measuring method and device, storage medium and electronic equipment |
| CN113390882A (en) * | 2021-06-10 | 2021-09-14 | 青岛理工大学 | Tire inner side defect detector based on machine vision and deep learning algorithm |
| CN113989271A (en) * | 2021-11-25 | 2022-01-28 | 江苏科技大学 | Paint image segmentation system and method based on double-attention mechanism and U-net network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US4988202A (en) | Solder joint inspection system and method | |
| CN102854192B (en) | Method for detecting apple surface defect based on apple surface defect detecting system | |
| CN110018178A (en) | A kind of mobile phone bend glass typical defect on-line measuring device and method | |
| CN109767497B (en) | Detection method for automatically detecting surface quality of aviation blade | |
| CN101021478A (en) | Laser inducing fluorescent high spectral image detecting method and device for fruit quality | |
| CN109544548A (en) | Defect inspection method, device, server, equipment and the storage medium of cutlery box | |
| CN114119461B (en) | Deep learning-based lithium battery module side weld appearance detection method and system | |
| CN114034704A (en) | Waste roller three-dimensional detection device and method based on multi-source data fusion | |
| CN210071686U (en) | Fruit grading plant based on orthogonal binocular machine vision | |
| CN103760146A (en) | Non-contact component detection system and method for powder | |
| CN107578047A (en) | The degree of eccentricity detection method of power cable | |
| CN104132945A (en) | On-line surface quality visual inspection device for bar based on optical fiber conduction | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN113850228A (en) | Road crack detection method and system based on multi-mode fusion | |
| CN108830840A (en) | A kind of active intelligent detecting method of circuit board defect and its application | |
| CN112455676A (en) | Intelligent monitoring and analyzing system and method for health state of photovoltaic panel | |
| CN104008366A (en) | 3D intelligent recognition method and system for biology | |
| JP2013156173A (en) | Inspection method for turbine blade and device therefor | |
| CN114740007A (en) | Non-contact surface defect detection device and use method | |
| CN111105413B (en) | Intelligent spark plug appearance defect detection system | |
| CN107741430A (en) | A kind of compact structure eyeglass detecting system based on contact-type image sensor | |
| CN213067467U (en) | Transparent member scratch depth detection device | |
| CN113706484A (en) | Crack damage detection system that aircraft structure fatigue test inner deck patrolled and examined | |
| CN115131518A (en) | Three-dimensional display method for millimeter wave near-field imaging perspective detection of building curtain wall | |
| CN114240896A (en) | Method for detecting welding quality of stud welding based on convolutional neural network |
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 |