CN116448671A - Surface defect detection method for high-reflection multi-curved-surface product - Google Patents
Surface defect detection method for high-reflection multi-curved-surface product Download PDFInfo
- Publication number
- CN116448671A CN116448671A CN202310509746.4A CN202310509746A CN116448671A CN 116448671 A CN116448671 A CN 116448671A CN 202310509746 A CN202310509746 A CN 202310509746A CN 116448671 A CN116448671 A CN 116448671A
- Authority
- CN
- China
- Prior art keywords
- imaging
- product
- curved
- field
- assembly
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 title abstract description 30
- 238000003384 imaging method Methods 0.000 claims abstract description 142
- 238000000034 method Methods 0.000 claims abstract description 17
- 230000008447 perception Effects 0.000 claims abstract description 12
- 238000012634 optical imaging Methods 0.000 claims description 11
- 230000006698 induction Effects 0.000 claims description 7
- 238000007599 discharging Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 238000002310 reflectometry Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Textile Engineering (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to AOI surface defect detection, in particular to a method for detecting surface defects of high-reflection multi-curved-surface products, which comprises the following steps: setting up a product imaging station (6); carrying out bright field 2D imaging, dark field 2D imaging and 3D imaging on each part of the surface of a product placed in a product imaging position; uploading the obtained bright field 2D imaging data, dark field 2D imaging data and 3D imaging data to an AI perception recognition host, and enabling the AI perception recognition host to recognize defect content in an image and feed back recognition results in real time. The invention can effectively confirm the positions and types of the surface flaws of the highly reflective complex curved surface products, and has the advantages of time and labor saving in detection, high detection efficiency and high accuracy.
Description
Technical Field
The invention relates to an AOI surface defect detection system, in particular to a method for detecting surface defects of high-reflection multi-curved-surface products.
Background
In the current AOI surface defect detection, the high-reflection curved surface product is influenced by the surface complexity and the high-reflection characteristic of the surface of the product, and the defects of the product are various in variety, and the surface defect detection difficulty of the product is very high due to the fact that the directions (such as the directions of scratches), the depths and the shapes of the defects are different.
At present, the detection methods for the products at home and abroad are mostly as follows: multi-angle 2D imaging detection. There are many limitations to this detection method: 1) Space limitations, the design of multiple stations necessarily takes up more equipment space. 2) The limitation of imaging quality is that due to high reflectivity, the imaging is easy to be unclear in a single bright field and a single dark field, and the omission and false detection of detection equipment are easy to increase. 3) Due to the wide variety of defects, single 2D inspection cannot meet customer inspection requirements.
At present, 3D imaging detection is also adopted, but the existing 3D imaging detection has huge acquired data and long processing time, and in addition, the single 3D detection is difficult to meet the requirement of customer detection due to various defects.
Therefore, it is very important to invent an imaging technology and a related device which can overcome the requirement of installation space, improve imaging quality and rapidly detect the surface defects suitable for high-reflection multi-curved surfaces.
Disclosure of Invention
The invention aims to solve the technical problem that the existing 2D or 3D imaging detection is insufficient, and provides a method for detecting the surface defects of a high-reflection multi-curved-surface product, which can improve imaging quality and realize rapid detection.
The high light reflection referred to in the present invention means that the surface glossiness reaches 80 degrees or more.
In order to solve the technical problems, the invention adopts the following technical scheme:
a method for detecting surface defects of a high-reflection multi-curved-surface product comprises the following steps:
setting up a product imaging position;
carrying out bright field 2D imaging, dark field 2D imaging and 3D imaging on each part of the surface of a product placed in a product imaging position;
uploading the obtained bright field 2D imaging data, dark field 2D imaging data and 3D imaging data to an AI perception recognition host, and enabling the AI perception recognition host to recognize defect content in an image and feed back recognition results in real time.
According to the invention, bright field 2D imaging, dark field 2D imaging and 3D imaging are respectively carried out on a product to be detected, imaging data are all uploaded to the AI perception recognition host, and defect content in an image is recognized by the AI perception recognition host, so that the surface defects of the product are respectively shot by comprehensively utilizing the 3D imaging assembly, the bright field imaging assembly and the dark field imaging assembly, so that the surface defects of the high-reflection multi-curved-surface product are clearly imaged, the relevant information such as the surface defect positions, the defect types and the like of the high-reflection complex-curved-surface product can be effectively confirmed, the detection mode is time-saving and labor-saving, the detection efficiency is obviously improved, and the detection accuracy is further improved.
In the implementation, a bright field imaging component for bright field 2D imaging of a product and a dark field imaging component for dark field 2D imaging of the product are arranged at one side in front of the product imaging position, and a 3D imaging component for 3D imaging of the product is arranged at the other side; and the product placed in the product imaging position is controlled to rotate, and each time the product rotates once, the bright field imaging assembly and the dark field imaging assembly respectively shoot one side surface of the product once, and simultaneously, one side surface of the product of the 3D imaging assembly is once, so that the rotation and the imaging are sequentially and circularly carried out, and the whole 2D imaging and the 3D imaging of the surface of the product are completed.
According to the invention, the imaging assembly is fixed, and the product rotates, so that the defect detection can be realized by imaging the product at the same station by using the same imaging assembly, and the equipment space of the surface defect imaging device is greatly saved.
In order to realize full-automatic assembly line operation of detection, the full-automatic assembly line operation detection device comprises a feeding area, an optical imaging area and a discharging area, wherein the feeding area, the optical imaging area and the discharging area are connected through a conveyor, a product rotating mechanism is arranged on a conveying belt of the conveyor and rotates reciprocally along with the conveying belt, a product carrying table for placing products and a motor for driving the product carrying table are arranged on the product rotating mechanism, the motor drives the products to rotate, and the angles and distances between the products and the bright field imaging assembly, the dark field imaging assembly and the 3D imaging assembly are always unchanged.
Preferably, the feeding area is provided with a material induction sensor for confirming whether the product is correctly placed at the initial position, and a signal output end of the material induction sensor is connected into a control circuit of the conveyor.
Preferably, after the collected 3D imaging data is converted into 2D image data by a 3D mapping mode by using a phase deflection method, the depth or height information of the surface defect of the product is obtained, and the surface defect characteristic of the product is obtained.
Preferably, the AI-perception recognition host is connected with the cameras of the bright-field imaging assembly, the dark-field imaging assembly and the 3D imaging assembly through data lines, stores the collected image data, performs model training according to recognized content, and feeds back recognition results in real time.
In order to avoid mutual interference of 3D imaging and 2D imaging, the 3D imaging assembly is arranged on one side of the product imaging position, and the bright field imaging assembly and the dark field imaging assembly are arranged on the other side of the product imaging position.
In particular, the 3D imaging assembly includes a multi-view camera and a structured light source.
Specifically, the bright field imaging assembly comprises a bright field area array camera and a bright field parallel area light source.
Specifically, the dark field imaging component comprises a dark field area array camera and a dark field parallel area light source.
To avoid interference with natural light, the optical imaging zone is set up within the dark room.
For the convenience of confirming whether the product is correctly placed at the initial position, a material induction sensor is arranged in the feeding area, and the signal output end of the material induction sensor is connected into a control circuit of the conveyor.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention uses the combination of the area array camera and the parallel area light source to adjust the parallel area light source to form bright or dark light fields on different curved surfaces, and controls the trigger of the related camera to image the bright or dark light fields by high-speed switching of the bright or dark fields, thereby enabling the imaging of different defects to be more obvious and clear.
2. According to the invention, the multi-view camera and the 3D structure light source are utilized to collect 3D image data of the curved surface, and the collected 3D data is converted into a 2D image in a 3D mapping mode by using a phase deflection method, so that some tiny defects can be clearly shown in imaging.
3. The invention can realize the defect imaging of complex curved surface products through the combination of the 3D imaging component, the bright field imaging component and the dark field imaging component, and ensures the quality of all defect imaging.
4. The invention may also be used to assist in imaging by incorporating a high definition camera.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic plan view of the overall structure of a surface defect imaging device for a highly reflective multi-curved product of the present invention;
FIG. 2 is a schematic diagram of the installation structure of the surface defect imaging device of the high-reflection multi-curved-surface product of the invention;
FIG. 3 is a schematic diagram of a product rotation mechanism of the high-reflectivity multi-curved product surface defect imaging device;
fig. 4 is a schematic diagram of data transmission of the surface defect imaging device for the high-reflection multi-curved-surface product of the invention.
Detailed Description
The invention is further described below in connection with specific preferred embodiments, but it is not intended to limit the scope of the invention.
For convenience of description, the relative positional relationship of the components, such as: the descriptions of the upper, lower, left, right, etc. are described according to the layout directions of the drawings in the specification, and do not limit the structure of the present patent.
Referring to fig. 1 and 2, an embodiment of the surface defect imaging device for a highly reflective multi-curved product of the present invention includes a feeding area 1, an optical imaging area 2, and a discharging area 3, which are sequentially arranged, and further includes a conveyor 4 continuously arranged in the feeding area 1, the optical imaging area 2, and the discharging area 3;
a product rotating mechanism 5 is arranged on the conveying belt of the conveyor 4, and the product rotating mechanism 5 rotates reciprocally along with the conveying belt of the conveyor 4;
a product imaging position 6 is arranged in the optical imaging area 2, and a 3D imaging assembly 7, a bright field imaging assembly 8 and a dark field imaging assembly 9 are arranged in front of the product imaging position 6. The 3D imaging component 7 is arranged on one side of the product imaging position 6, and the bright field imaging component 8 and the dark field imaging component 9 are arranged on the other side of the product imaging position 6, so that bright field imaging, dark field imaging and 3D imaging can be performed simultaneously without interference. The mounting angles of the 3D imaging assembly 7, the bright field imaging assembly 8 and the dark field imaging assembly 9 are adjustable.
As shown in fig. 3, the product rotating mechanism 5 includes a mounting base 51 fixedly connected with the conveyor belt, a motor 51 mounted on the mounting base 54, a product carrying platform 52 and a transmission assembly 53, the product carrying platform 52 is rotatably mounted on the mounting base 54, the transmission assembly 53 includes a driving wheel 531 mounted on an output shaft of the motor 51 and a driven wheel 532 mounted on a rotating shaft of the product carrying platform 52, and the motor 51 is connected with the product carrying platform 52 through the transmission assembly 53. When the motor 51 is started, the motor 51 drives the product carrier 52 to rotate through the driving wheel 531 and the driven wheel 532, thereby driving the product placed on the product carrier 52 to rotate. The motor 51 is preferably a servo motor.
The 3D imaging assembly 7 comprises a multi-view camera 71 and a structured light source 72. In the present embodiment, the multi-camera 71 is formed by two industrial camera frames, and it is apparent that the present invention is not limited thereto, and three, four or more industrial camera frames may be used. The structured light source 72 is a commercially available product that functions to provide a light source for the multi-camera 71 for enabling highly reflective curved products to clearly exhibit defective image characteristics.
The bright field imaging assembly 8 comprises a bright field area array camera 81 and a bright field parallel surface light source 82.
The dark field imaging assembly 9 includes a dark field area camera 91 and a dark field parallel area light source 92.
To avoid interference of the imaging by the external natural light, the optical imaging area 2 is arranged in the darkroom 10.
In order to facilitate the automatic control of the high-reflection multi-curved-surface product surface defect imaging device, the feeding area 1 is provided with a material induction sensor 11. When the material-sensing sensor 11 senses that the product is properly placed on the product carrier 52 of the loading zone 1, the material-sensing sensor 11 transmits a product-ready signal to the control system of the conveyor 4, and the conveyor 4 is started to transfer the product to the product imaging station 6 of the optical imaging zone 2.
The detection principle of the invention is as follows:
the product is rotated through the product rotating mechanism 5, meanwhile, the bright field area array camera 81, the dark field area array camera 91, the bright field parallel surface light source 82, the dark field parallel surface light source 92 and other devices are mutually matched to form a bright light field and a dark light field, 2D data are collected, one surface of the product is subjected to bright light field imaging and dark light field imaging, and meanwhile, the other surface of the product is combined through the multi-eye camera 71 and the structural light source 72 to quickly collect 3D data, so that the imaging of the surface defects of the high-reflection curved surface product is realized through the combination of bright light field imaging and dark light field imaging and 3D structural light source imaging, further, the relevant information such as the positions of the surface defects and the defect types of the high-reflection complex curved surface product is effectively confirmed, the detection mode is time-saving and labor-saving, the detection efficiency is obviously improved, and the detection accuracy is further improved.
The method for detecting the surface defects of the high-reflection multi-curved-surface product comprises the following specific steps:
1. and (3) feeding: the high-reflection curved surface type product is placed on a product carrying table 52 of a product rotating mechanism 5 of the feeding area 1.
2. Initial position confirmation: sensing the high-reflection curved surface product by using a material sensing sensor 11 to confirm that the product is correctly placed at the initial position;
3. and (3) mechanical movement: the conveyor 4 moves the correctly placed products to the product imaging station 6 of the optical imaging area 2 ready for image data acquisition;
4. and (3) image acquisition: the product is driven to rotate through the product rotating mechanism 5, each time the product rotates, image acquisition is carried out on one surface of the product by using a bright field imaging component 8 (a bright field area array camera 81 and a bright field parallel surface light source 82) and a dark field imaging component 9 (a dark field area array camera 91 and a dark field parallel surface light source 92) respectively, then the defect characteristic information of the surface of the product is obtained by adopting an image processing technology (the prior art) of image characteristic extraction fusion, 3D image acquisition is carried out on the other surface of the product by using a 3D imaging component 7 (a multi-view camera 71 and a structural light source 72) while bright and dark field imaging is carried out, then the acquired 3D image data is converted into a 2D image by using a phase deflection method in a 3D mapping mode, the acquisition of defect depth or height information of the other surface of the product is realized, and the cycle is carried out until the image acquisition and defect characteristic extraction of each surface of the product are completed, and finally the detection of the integral surface defect characteristic of the product is obtained.
5. And (3) image transmission: after the image acquisition is completed, whether the shot picture meets the image acquisition requirement is confirmed, and the image meeting the requirement is transmitted to an AI perception recognition host (as shown in fig. 4) through a gigabit network cable, namely the AI perception recognition host is connected with a bright field area array camera 81, a dark field area array camera 91 and a multi-view camera 71 through data lines.
6. And (3) image identification: firstly, an AI perception recognition host stores the acquired image, then recognizes the image, recognizes the defect content in the image, and performs model training according to the recognized content.
7. And (3) feedback of identification results: the AI perception recognition host feeds back the recognition result in the software operating system and the upper computer in real time, an operator can check relevant information such as the defect position, the defect type and the like of the product through the operating system, and the upper computer controls the next working procedure to sort the product according to the feedback result.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and modifications may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. Therefore, any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present invention shall fall within the scope of the technical solution of the present invention.
Claims (6)
1. A method for detecting surface defects of a high-reflection multi-curved-surface product is characterized by comprising the following steps:
setting up a product imaging station (6);
carrying out bright field 2D imaging, dark field 2D imaging and 3D imaging on each part of the surface of a product placed in a product imaging position;
uploading the obtained bright field 2D imaging data, dark field 2D imaging data and 3D imaging data to an AI perception recognition host, and enabling the AI perception recognition host to recognize defect content in an image and feed back recognition results in real time.
2. The method for detecting surface defects of a highly reflective multi-curved surface product according to claim 1, wherein,
a bright field imaging component (8) for bright field 2D imaging of a product and a dark field imaging component (9) for dark field 2D imaging of the product are arranged at one side in front of the product imaging position, and a 3D imaging component (7) for 3D imaging of the product is arranged at the other side;
and the product placed in the product imaging position is controlled to rotate, and each time the product rotates once, the bright field imaging assembly and the dark field imaging assembly respectively shoot one side surface of the product once, and simultaneously, one side surface of the product of the 3D imaging assembly is once, so that the rotation and the imaging are sequentially and circularly carried out, and the whole 2D imaging and the 3D imaging of the surface of the product are completed.
3. The method for detecting the surface defects of the high-reflection multi-curved-surface products according to claim 2 is characterized by further comprising a feeding area (1), an optical imaging area (2) and a discharging area (3), wherein the feeding area (1), the optical imaging area (2) and the discharging area (3) are connected through a conveyor;
the product rotating mechanism (5) is arranged on a conveying belt of the conveyor and rotates along with the conveying belt in a reciprocating mode, a product carrying table (52) for placing products and a motor (51) for driving the product carrying table are arranged on the product rotating mechanism, the motor drives the products to rotate, and the angles and distances between the products and the bright field imaging assembly (8), the dark field imaging assembly (9) and the 3D imaging assembly (7) are unchanged all the time.
4. The method for detecting surface defects of high-reflectivity multi-curved-surface products according to claim 3, wherein the feeding area is provided with a material induction sensor (11) for confirming whether the products are correctly placed at the initial position, and the signal output end of the material induction sensor is connected into a control circuit of the conveyor.
5. The method for detecting surface defects of a highly reflective multi-curved-surface product according to any one of claims 1 to 4, wherein the acquisition of depth or height information of the surface defects of the product is realized after the acquired 3D imaging data is converted into 2D image data by a 3D mapping method by using a phase deviation method, so as to obtain the surface defect characteristics of the product.
6. The method for detecting surface defects of a highly reflective multi-curved-surface product according to any one of claims 1 to 4, wherein the AI-perception recognition host is connected to cameras of the bright-field imaging assembly (8), the dark-field imaging assembly (9) and the 3D imaging assembly (7) through data lines, and stores the acquired image data, performs model training according to the recognized content, and feeds back the recognition result in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310509746.4A CN116448671A (en) | 2023-05-08 | 2023-05-08 | Surface defect detection method for high-reflection multi-curved-surface product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310509746.4A CN116448671A (en) | 2023-05-08 | 2023-05-08 | Surface defect detection method for high-reflection multi-curved-surface product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116448671A true CN116448671A (en) | 2023-07-18 |
Family
ID=87128631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310509746.4A Pending CN116448671A (en) | 2023-05-08 | 2023-05-08 | Surface defect detection method for high-reflection multi-curved-surface product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116448671A (en) |
-
2023
- 2023-05-08 CN CN202310509746.4A patent/CN116448671A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101697119B1 (en) | apparatus for vision inspection of semiconductor | |
| CN108627457B (en) | Automatic optical inspection system and method of operation thereof | |
| CN203899959U (en) | Automatic barcode reader | |
| CN107515226A (en) | A kind of method of work of the image measuring device of product automatic detection sorting | |
| CN208505916U (en) | A kind of glass detection machine | |
| CN108759754A (en) | Height dimension automatic checkout equipment | |
| CN110524241B (en) | Automatic assembling equipment for connector | |
| CN109772721A (en) | Engine commutator open defect automatic online vision inspection apparatus and detection method | |
| CN110018176A (en) | A kind of multi-work piece defects detection mechanism and method | |
| CN108593673A (en) | A kind of gold stamping product defects vision testing machine of full-automatic rotating printing | |
| CN107121796A (en) | A kind of measurement jig for mobile phone liquid crystal screen defects detection | |
| CN112595727A (en) | Imaging system and detection method for detecting defects of ink glass of rear cover plate of mobile phone | |
| CN109013387A (en) | Electrical core of power battery appearance detecting device | |
| CN114252452A (en) | Online detection device and method for appearance defects and contour dimension of small-sized revolving body | |
| CN205333535U (en) | Metal strainometer defect automatic check out system | |
| CN208091943U (en) | A kind of gold stamping product defects vision testing machine of full-automatic rotating printing | |
| CN212747699U (en) | Automatic visual inspection device of car pipe fitting | |
| CN211282860U (en) | A transfer device and system for edge defect detection experiment | |
| CN109596633A (en) | Light guide plate defect detection equipment and detection method | |
| CN220170855U (en) | High reflection of light curved surface product surface defect image device | |
| CN206146851U (en) | Intellectual detection system industrial part surface quality's device | |
| CN116448671A (en) | Surface defect detection method for high-reflection multi-curved-surface product | |
| CN209565257U (en) | Engine commutator open defect automatic online vision inspection apparatus | |
| KR101683589B1 (en) | Vision inspection apparatus and vision inspection method therefor | |
| CN113103248B (en) | Automatic detection line of three-dimensional image scanning robot |
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 |