CN111830048A - Automobile fuel spray nozzle defect detection equipment based on deep learning and detection method thereof - Google Patents
Automobile fuel spray nozzle defect detection equipment based on deep learning and detection method thereof Download PDFInfo
- Publication number
- CN111830048A CN111830048A CN202010695821.7A CN202010695821A CN111830048A CN 111830048 A CN111830048 A CN 111830048A CN 202010695821 A CN202010695821 A CN 202010695821A CN 111830048 A CN111830048 A CN 111830048A
- Authority
- CN
- China
- Prior art keywords
- mode
- light source
- fixed support
- deep learning
- oil nozzle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G01N21/8806—Specially adapted optical and illumination features
-
- 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
- G01N21/13—Moving of cuvettes or solid samples to or from the investigating station
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8835—Adjustable illumination, e.g. software adjustable screen
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of machine vision detection automation, and discloses an automobile fuel spray nozzle defect detection device based on deep learning, which comprises a first fixed support and a second fixed support, the top end of the first fixed support is provided with a second fixed support, the first fixed support and the second fixed support are main shafts, an XY fine-tuning platform is assembled on the outer wall of the main shaft, one end of a camera fixing bracket is assembled on the side surface of the XY fine-tuning platform, an industrial camera is assembled at the other end of the camera fixing bracket, the industrial camera can move on the main shaft for fine adjustment of focal length under the drive of the XY fine adjustment platform, the outer wall of the main shaft is provided with a first light source fixing support, the upper side and the lower side of the first light source fixing support are respectively provided with a telecentric lens and a first light source, and the outer wall of the second light source fixing support is provided with a second light source. The invention has the characteristics of high speed, high precision, high stability and the like, and can play an important role in the production process.
Description
Technical Field
The invention relates to the technical field of machine vision detection automation, in particular to an automobile fuel spray nozzle defect detection device based on deep learning and a detection method thereof.
Background
The fuel spray nozzle is used as an important part of an automobile power system, and the collision around the spray hole and the integrity of the spray hole are particularly important for the whole product. For defect detection, conventional vision usually uses traditional methods such as template matching, Blob analysis, edge extraction and the like for detection, and such methods have obvious effect on samples with simpler background and stability, but for products with complex background and serious interference, defects and background areas are difficult to distinguish. For such detection, manual detection is mainly used at present. However, the manual detection has the defects of low efficiency, high error rate, high cost and the like.
Disclosure of Invention
The invention aims to provide automobile fuel spray nozzle defect detection equipment based on deep learning and a detection method thereof, and aims to solve the problems of low detection efficiency, high error rate, high cost and the like in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme: an automobile fuel spray nozzle defect detection device based on deep learning comprises a first fixing support and a second fixing support, wherein the top end of the first fixing support is provided with the second fixing support, the first fixing support and the second fixing support are main shafts, an XY fine adjustment platform is assembled on the outer wall of each main shaft, one end of a camera fixing support is assembled on the side face of the XY fine adjustment platform, an industrial camera is assembled at the other end of the camera fixing support, the industrial camera can move on the main shafts under the driving of the XY fine adjustment platform to perform focal length fine adjustment, a first light source fixing support is assembled on the outer wall of each main shaft, a telecentric lens and a first light source are respectively assembled on the upper side and the lower side of the first light source fixing support, a second light source is assembled on the outer wall of the second light source fixing support, and one end of a pressing block fixing support is assembled at the bottom end of the outer wall of each main shaft, the other end of the pressing block fixing support is provided with a material part fixing pressing block, a feeding turntable is arranged on the side face of the material part fixing pressing block, and the industrial camera, the telecentric lens, the first light source, the second light source, the material part fixing pressing block, the XY fine adjustment platform and the feeding turntable are all driven by the control module.
Preferably, the industrial camera is selected from Basler4600-7gc, and the detection precision can reach 0.002 mm.
Preferably, the detection visual field of the telecentric lens is 6mm, and the telecentric lens with the magnification of 1.5 times is selected for detection according to the visual field requirement and the depth of field requirement.
Preferably, the first light source and the second light source are annular light sources for detection, so that the integral light uniformity of the product is ensured.
Preferably, the control module comprises a PLC servo motor feeding platform and an industrial personal computer.
Preferably, the industrial personal computer selects 610H, I7-8700CPU of Hua.
A detection method of an automobile fuel spray nozzle defect detection device based on deep learning comprises the following steps;
s1, the PLC controls the servo motor to rotate for a fixed angle, and the oil nozzle falls into a hole position of the loading turntable;
s2, controlling the servo motor to rotate by a fixed angle by the PLC, and carrying out material loading rotation on the material loading rotating disc to a detection position right below the industrial camera;
s3, fixing the oil nozzle by the material part fixing pressing block controlled by the PLC;
s4, triggering photographing to obtain an image;
s5, processing the acquired image by visual software;
and S6, classifying good products and defective products of the oil nozzle according to the image processing result.
Preferably, in S5, the specific flow of processing the acquired image by the vision software is as follows:
a1, acquiring an image by a camera;
a2, judging a current mode of software, wherein the current mode is divided into an operation mode and a training mode, the operation mode is used during normal production, and the training mode is used for marking and training defects and generating an operation file;
a3: when the mode is a training mode, marking the flaw part in the picture by using a marking tool, and circling the area where the flaw is located, wherein the flaw is only required to be drawn, and the part which is not the flaw can not be selected;
a4: when the mode is a training mode, adjusting defect parameters and training the marked defects;
a5: and when the mode is a training mode, verifying the trained result, and verifying whether the trained defects can be found out, if so, using the defects. When the parameter can not be found or the misjudgment is more, the parameter is readjusted to train again;
a6: when the mode is a training mode, generating a running use file, namely a network structure result based on the neural network, for use in a normal production mode;
a7: when the mode is the operation mode, positioning the product according to the characteristics on the product;
a8: when the mode is the operation mode, detecting strip-shaped defects on the product;
a9: when the mode is the operation mode, detecting the blocky defects on the product;
a10: when the mode is the operation mode, detecting the gray defect which is close to the background on the product;
a11: and when the mode is the running mode, comprehensively judging the result of the product according to the detection result.
The invention provides a device and a method for detecting the defect of an automobile fuel spray nozzle based on deep learning, which have the beneficial effects that: the oil nozzle defect detection equipment based on the deep learning algorithm realizes system integration in the fields of photoelectricity, machinery, artificial intelligence deep learning algorithm and the like, the detection technology is combined with a large number of technologies such as core artificial intelligence deep learning algorithm, optical principle, image processing and the like, images are collected in an optical mode to obtain the surface state of a product, the product defects and the like are detected by the artificial intelligence algorithm and the image processing technology, and the oil nozzle defect detection equipment has the characteristics of high speed, high precision, high stability and the like, and plays an important role in the production process.
Drawings
FIG. 1 is a schematic view of a visual part structure of an automobile fuel spray nozzle defect detection device based on deep learning, which is disclosed by the invention;
FIG. 2 is a schematic structural diagram of a loading turntable of the deep learning-based automobile fuel injection nozzle defect detection equipment, provided by the invention;
FIG. 3 is an equipment detection flow chart of the deep learning-based automobile fuel injection nozzle defect detection equipment;
FIG. 4 is a flow chart of the visual part software detection of the automobile fuel injector defect detection equipment based on deep learning.
In the figure: 1. an industrial camera; 2. a camera fixing bracket; 3. a telecentric lens; 4. a first light source fixing bracket; 5. a first light source; 6. a second light source fixing bracket; 7. a second light source; 8. a material part fixing pressing block; 9. a pressing block fixing bracket; 10. a first fixed support; 11. an XY fine tuning platform; 12. a second fixed support; 13. a material loading turntable.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-4, the present invention provides a technical solution: an automobile fuel spray nozzle defect detection device based on deep learning comprises a first fixed support 10 and a second fixed support 12, wherein the top end of the first fixed support 10 is provided with the second fixed support 12, the first fixed support 10 and the second fixed support 12 are main shafts, an XY fine adjustment platform 11 is assembled on the outer wall of each main shaft, one end of a camera fixed support 2 is assembled on the side surface of each XY fine adjustment platform 11, an industrial camera 1 is assembled on the other end of each camera fixed support 2, the industrial camera 1 selects Bas460ler 0-7gc, the detection precision can reach 0.002mm, the industrial camera 1 can move on the main shafts to perform fine adjustment under the driving of the XY fine adjustment platform 11, a first light source fixed support 4 is assembled on the outer wall of each main shaft, a telecentric lens 3 and a light source 5 are respectively assembled on the upper side and the lower side of the first light source fixed support 4, the detection visual field of the telecentric lens 3 is 6mm, and according, selecting a telecentric lens with 1.5 times magnification for detection, assembling a light source fixing support II 6 on the outer wall of the main shaft, assembling a light source II 7 on the outer wall of the light source fixing support II 6, detecting the light source I5 and the light source II 7 by annular light sources, ensuring the integral light uniformity of products, respectively testing products of different models, debugging the light source effect according to different products, assembling one end of a pressing block fixing support 9 at the bottom end of the outer wall of the main shaft, assembling a material fixing pressing block 8 at the other end of the pressing block fixing support 9, arranging a feeding turntable 13 on the side surface of the material fixing pressing block 8, driving an industrial camera 1, the telecentric lens 3, the light source I5, the material fixing pressing block 8 of the light source II 7, an XY fine tuning platform 11 and the feeding turntable 13 by a control module, wherein the control module comprises a PLC servo motor feeding platform and an industrial personal computer, selecting Mohua 610H, i7-8700 CPU.
A detection method of an automobile fuel spray nozzle defect detection device based on deep learning comprises the following steps;
s1, the PLC controls the servo motor to rotate for a fixed angle, and the oil nozzle falls into a hole position of the loading turntable 13;
s2, the PLC controls the servo motor to rotate for a fixed angle, and the loading turntable 13 rotates to a detection position right below the industrial camera 1 with the material level;
s3, fixing the oil nozzle by the material part fixing pressing block 8 under the control of the PLC;
s4, triggering photographing to obtain an image;
s5, processing the acquired image by visual software;
a1, acquiring an image by a camera;
a2, judging a current mode of software, wherein the current mode is divided into an operation mode and a training mode, the operation mode is used during normal production, and the training mode is used for marking and training defects and generating an operation file;
a3: when the mode is a training mode, marking the flaw part in the picture by using a marking tool, and circling the area where the flaw is located, wherein the flaw is only required to be drawn, and the part which is not the flaw can not be selected;
a4: when the mode is a training mode, adjusting defect parameters and training the marked defects;
a5: and when the mode is a training mode, verifying the trained result, and verifying whether the trained defects can be found out, if so, using the defects. When the parameter can not be found or the misjudgment is more, the parameter is readjusted to train again;
a6: when the mode is a training mode, generating a running use file, namely a network structure result based on the neural network, for use in a normal production mode;
a7: when the mode is the operation mode, positioning the product according to the characteristics on the product;
a8: when the mode is the operation mode, detecting strip-shaped defects on the product;
a9: when the mode is the operation mode, detecting the blocky defects on the product;
a10: when the mode is the operation mode, detecting the gray defect which is close to the background on the product;
a11: and when the mode is the running mode, comprehensively judging the result of the product according to the detection result.
And S6, classifying good products and defective products of the oil nozzle according to the image processing result.
Example (b): the material loading needs 1s, check-out time needs 4-5 seconds, the unloading needs 1s, whole detection flow needs 6-7s, the automatic unloading design of going up of vibration dish, the carousel that this equipment adopted, material loading unloading and visual detection time only need 3s altogether, production efficiency has improved more than one time, among the visual algorithm, compare in traditional machine visual detection, the rate of detection of degree of depth learning algorithm to the defect reaches more than 99%, satisfy the customer demand, it possesses several big advantages that traditional vision does not possess simultaneously:
firstly, the problem that the traditional vision cannot process completely irregular complex images is solved;
secondly, the problems of missing detection and high false detection rate caused by poor anti-interference capability of the traditional machine vision are solved;
thirdly, the problem that the traditional vision has high dependence on a hardware environment is solved.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The utility model provides an automobile fuel sprayer defect detecting equipment based on degree of depth study which characterized in that: the device comprises a first fixed support (10) and a second fixed support (12), wherein the second fixed support (12) is arranged at the top end of the first fixed support (10), the first fixed support (10) and the second fixed support (12) are main shafts, an XY fine-tuning platform (11) is assembled on the outer wall of each main shaft, one end of a camera fixed support (2) is assembled on the side surface of the XY fine-tuning platform (11), an industrial camera (1) is assembled at the other end of the camera fixed support (2), the industrial camera (1) can move on the main shafts to perform focus fine tuning under the driving of the XY fine-tuning platform (11), a first light source fixed support (4) is assembled on the outer wall of each main shaft, a telecentric lens (3) and a first light source (5) are respectively assembled on the upper side and the lower side of the first light source fixed support (4), and a second light source fixed support (6) is assembled on the outer wall of each, be equipped with light source two (7) on the outer wall of light source fixed bolster two (6), the outer wall bottom of main shaft is equipped with the one end of briquetting fixed bolster (9), the other end of briquetting fixed bolster (9) is equipped with material fixing pressing block (8), the side of material fixing pressing block (8) is provided with material loading carousel (13), industry camera (1), telecentric lens (3), light source one (5), light source two (7) material fixing pressing block (8), XY fine setting platform (11) and material loading carousel (13) all are controlled the module drive.
2. The deep learning-based automobile oil nozzle defect detection equipment as claimed in claim 1, wherein: the industrial camera (1) selects Basler4600-7gc, and the detection precision can reach 0.002 mm.
3. The deep learning-based automobile oil nozzle defect detection equipment as claimed in claim 1, wherein: the detection visual field of the telecentric lens (3) is 6mm, and the telecentric lens with 1.5 times of magnification is selected for detection according to the visual field requirement and the depth of field requirement.
4. The deep learning-based automobile oil nozzle defect detection equipment as claimed in claim 1, wherein: the first light source (5) and the second light source (7) are annular light sources for detection, and the uniformity of the whole light of the product is guaranteed.
5. The deep learning-based automobile oil nozzle defect detection equipment as claimed in claim 1, wherein: the control module comprises a PLC servo motor feeding platform and an industrial personal computer.
6. The automobile oil nozzle defect detection equipment based on deep learning of claim 5, characterized in that: the industrial personal computer selects 610H, I7-8700CPU of Hua.
7. The method for detecting the automobile oil nozzle defect detection equipment based on the deep learning of any one of claims 1 to 6, is characterized in that: comprises the following steps;
s1, the PLC controls the servo motor to rotate for a fixed angle, and the oil nozzle falls into a hole position of the loading turntable (13);
s2, the PLC controls the servo motor to rotate for a fixed angle, and the loading turntable (13) rotates to a detection position right below the industrial camera (1) with the material level;
s3, fixing the oil nozzle by a material fixing pressing block (8) controlled by a PLC;
s4, triggering photographing to obtain an image;
s5, processing the acquired image by visual software;
and S6, classifying good products and defective products of the oil nozzle according to the image processing result.
8. The method for detecting the automobile oil nozzle defect detection equipment based on the deep learning of claim 7, wherein the method comprises the following steps: in S5, the specific process of processing the acquired image by the vision software is as follows:
a1, acquiring an image by a camera;
a2, judging a current mode of software, wherein the current mode is divided into an operation mode and a training mode, the operation mode is used during normal production, and the training mode is used for marking and training defects and generating an operation file;
a3: when the mode is a training mode, marking the flaw part in the picture by using a marking tool, and circling the area where the flaw is located, wherein the flaw is only required to be drawn, and the part which is not the flaw can not be selected;
a4: when the mode is a training mode, adjusting defect parameters and training the marked defects;
a5: and when the mode is a training mode, verifying the trained result, and verifying whether the trained defects can be found out, if so, using the defects. When the parameter can not be found or the misjudgment is more, the parameter is readjusted to train again;
a6: when the mode is a training mode, generating a running use file, namely a network structure result based on the neural network, for use in a normal production mode;
a7: when the mode is the operation mode, positioning the product according to the characteristics on the product;
a8: when the mode is the operation mode, detecting strip-shaped defects on the product;
a9: when the mode is the operation mode, detecting the blocky defects on the product;
a10: when the mode is the operation mode, detecting the gray defect which is close to the background on the product;
a11: and when the mode is the running mode, comprehensively judging the result of the product according to the detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010695821.7A CN111830048A (en) | 2020-07-17 | 2020-07-17 | Automobile fuel spray nozzle defect detection equipment based on deep learning and detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010695821.7A CN111830048A (en) | 2020-07-17 | 2020-07-17 | Automobile fuel spray nozzle defect detection equipment based on deep learning and detection method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111830048A true CN111830048A (en) | 2020-10-27 |
Family
ID=72922951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010695821.7A Pending CN111830048A (en) | 2020-07-17 | 2020-07-17 | Automobile fuel spray nozzle defect detection equipment based on deep learning and detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111830048A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103909069A (en) * | 2014-03-27 | 2014-07-09 | 宁波兴德磁业有限公司 | Full-automatic intelligent sheet selection machine for neodymium-iron-boron magnetic workpieces based on machine vision |
| CN104634790A (en) * | 2015-02-09 | 2015-05-20 | 杭州乔戈里科技有限公司 | Capsule detection method and high-speed fully-automatic detection device |
| CN106872474A (en) * | 2017-03-08 | 2017-06-20 | 苏州易瑞得电子科技有限公司 | Exploded perspective vision testing machine and its detection method |
| CN107664644A (en) * | 2017-09-30 | 2018-02-06 | 电子科技大学 | A kind of apparent automatic detection device of object based on machine vision and method |
| CN108240995A (en) * | 2016-12-27 | 2018-07-03 | 张家港康得新光电材料有限公司 | Detecting system, detection method and the device of diaphragm |
| CN109675832A (en) * | 2019-01-21 | 2019-04-26 | 深圳精创视觉科技有限公司 | A kind of ndfeb magnet size and open defect detection device |
| CN110006919A (en) * | 2018-12-10 | 2019-07-12 | 浙江大学台州研究院 | A kind of apparatus and method polishing the shallow scratch detection of quartz wafer |
| CN110473806A (en) * | 2019-07-13 | 2019-11-19 | 河北工业大学 | The deep learning identification of photovoltaic cell sorting and control method and device |
| CN110530875A (en) * | 2019-08-29 | 2019-12-03 | 珠海博达创意科技有限公司 | A kind of FPCB open defect automatic detection algorithm based on deep learning |
| CN110689539A (en) * | 2019-11-12 | 2020-01-14 | 南京大学 | Workpiece surface defect detection method based on deep learning |
| CN111307826A (en) * | 2020-03-03 | 2020-06-19 | 桂林电子科技大学 | Online visual detection device and method for foreign matters in powder in bottle |
-
2020
- 2020-07-17 CN CN202010695821.7A patent/CN111830048A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103909069A (en) * | 2014-03-27 | 2014-07-09 | 宁波兴德磁业有限公司 | Full-automatic intelligent sheet selection machine for neodymium-iron-boron magnetic workpieces based on machine vision |
| CN104634790A (en) * | 2015-02-09 | 2015-05-20 | 杭州乔戈里科技有限公司 | Capsule detection method and high-speed fully-automatic detection device |
| CN108240995A (en) * | 2016-12-27 | 2018-07-03 | 张家港康得新光电材料有限公司 | Detecting system, detection method and the device of diaphragm |
| CN106872474A (en) * | 2017-03-08 | 2017-06-20 | 苏州易瑞得电子科技有限公司 | Exploded perspective vision testing machine and its detection method |
| CN107664644A (en) * | 2017-09-30 | 2018-02-06 | 电子科技大学 | A kind of apparent automatic detection device of object based on machine vision and method |
| CN110006919A (en) * | 2018-12-10 | 2019-07-12 | 浙江大学台州研究院 | A kind of apparatus and method polishing the shallow scratch detection of quartz wafer |
| CN109675832A (en) * | 2019-01-21 | 2019-04-26 | 深圳精创视觉科技有限公司 | A kind of ndfeb magnet size and open defect detection device |
| CN110473806A (en) * | 2019-07-13 | 2019-11-19 | 河北工业大学 | The deep learning identification of photovoltaic cell sorting and control method and device |
| CN110530875A (en) * | 2019-08-29 | 2019-12-03 | 珠海博达创意科技有限公司 | A kind of FPCB open defect automatic detection algorithm based on deep learning |
| CN110689539A (en) * | 2019-11-12 | 2020-01-14 | 南京大学 | Workpiece surface defect detection method based on deep learning |
| CN111307826A (en) * | 2020-03-03 | 2020-06-19 | 桂林电子科技大学 | Online visual detection device and method for foreign matters in powder in bottle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102590218B (en) | Device and method for detecting micro defects on bright and clean surface of metal part based on machine vision | |
| CN101261234B (en) | Surface flaw detection device | |
| CN109840900B (en) | Fault online detection system and detection method applied to intelligent manufacturing workshop | |
| CN111999308A (en) | Defect detection control method, control device and control system | |
| CN206113866U (en) | Six automatic check out test sets of inductance | |
| Konstantinidis et al. | The role of machine vision in industry 4.0: an automotive manufacturing perspective | |
| CN1928535A (en) | Machine vision based LCD spot flaw detection method and system | |
| CN103240863A (en) | Apparatus and method for inspecting preform | |
| CN209446480U (en) | Vehicle lacquer painting and apparent flaws detection device | |
| CN109580404A (en) | The abrasion of industrial robot internally-arranged type harness and accelerated wear test test method and device | |
| CN102890093A (en) | Machine vision detecting device of surface quality of master cylinder piston of automobile brake | |
| CN212301356U (en) | Wheel hub welding seam visual detection device | |
| CN111672773A (en) | Product surface defect detection system and method based on machine vision | |
| CN111830048A (en) | Automobile fuel spray nozzle defect detection equipment based on deep learning and detection method thereof | |
| CN113358070B (en) | Automobile brake pad flatness and pin height detection system and detection method thereof | |
| CN202471610U (en) | Automatic bottle body defect detecting device based on machine vision | |
| CN213529672U (en) | Button blank defect detection device | |
| CN106645185A (en) | Method and device for intelligently detecting surface quality of industrial parts | |
| CN212759762U (en) | Online automatic detection system for appearance defects of washing machine | |
| CN110567966A (en) | Gear detection method based on line laser scanner | |
| JPH0417987A (en) | Image processing system for laser beam machine | |
| CN212442109U (en) | Detection device for positioning and feeding | |
| CN111398294B (en) | Straw particle defect detection system and detection method based on machine vision | |
| CN114473463B (en) | Intelligent screw mounting method and device for industrial distribution box | |
| CN208255443U (en) | A kind of crystal coupling assembling detection device based on machine vision |
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: 20201027 |
|
| RJ01 | Rejection of invention patent application after publication |