CN111672773A - Product surface defect detection system and method based on machine vision - Google Patents
Product surface defect detection system and method based on machine vision Download PDFInfo
- Publication number
- CN111672773A CN111672773A CN202010667158.XA CN202010667158A CN111672773A CN 111672773 A CN111672773 A CN 111672773A CN 202010667158 A CN202010667158 A CN 202010667158A CN 111672773 A CN111672773 A CN 111672773A
- Authority
- CN
- China
- Prior art keywords
- connecting plate
- fixedly connected
- hose
- motor
- retainer ring
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to a product surface defect detection system and method based on machine vision, which solve the technical problems of low efficiency, low accuracy and high labor cost of detecting surface defects of a small-modulus worm by an existing manual visual inspection method. The invention is widely used for quality detection of the surface defects of the products.
Description
Technical Field
The invention relates to the technical field of worm quality inspection equipment, in particular to a product surface defect detection system and method based on machine vision.
Background
The worm is an important mechanical basic part in industrial production, and is affected by factors such as a processing technology, a production environment and the like in a processing process, so that surface defects such as pits, notches, scratches and the like are inevitably generated. Products with surface defects are removed through a quality detection process.
In actual industrial production, the output of the worm with small modulus is huge, and the detection efficiency is very important for detecting the quality of the worm. However, the quality of the surface defects of the small-modulus worm is generally detected by adopting a manual visual inspection method at present, so that the technical problems of low detection efficiency, low detection accuracy and high labor cost exist. Especially for some defects with small size, the defects need to be detected under a brighter light source, which can rapidly aggravate eye fatigue and reduce detection efficiency and accuracy.
Disclosure of Invention
The invention provides a product surface defect detection system and method based on machine vision, and aims to solve the technical problems of low efficiency, low accuracy and high labor cost of the conventional method for detecting surface defects of small-modulus worms by manual visual inspection.
The invention provides a product surface defect detection system based on machine vision, which comprises a machine table, a feeding device, a detection device, a mechanical arm and a discharging sorting device, wherein the machine table is provided with a plurality of loading holes;
the feeding device comprises a motor, a rotating shaft, a motor support, a first bearing seat, a second bearing seat, a retainer ring, a rotary table and a supporting plate, wherein the motor support is fixedly connected with the machine table; the supporting plate is fixedly connected with the machine table, the check ring is fixedly connected with the supporting plate, the check ring is provided with a central through hole, the supporting plate is provided with a shaft hole, and the rotating shaft penetrates through the shaft hole of the supporting plate and the central through hole of the check ring; the retainer ring surrounds the turntable, and a gap is formed between the outer edge of the turntable and the inner wall of the retainer ring; the retainer ring is provided with a feeding port, a bottom discharge port and a top opening; the turntable is provided with a plurality of to-be-detected product accommodating grooves which are uniformly distributed along the circumferential direction and a plurality of plane needle bearing accommodating chambers which correspond to the to-be-detected product accommodating grooves in number and are uniformly distributed along the circumferential direction, the bottom surface of each plane needle bearing accommodating chamber is connected with a positioning cylinder, a plane needle bearing is arranged in each plane needle bearing accommodating chamber, and the positioning cylinders penetrate through the plane needle bearings;
the detection device comprises an installation support, a linear array camera and a light source, the installation support is fixedly connected with the machine table, the linear array camera is connected with the installation support, the light source is connected with the installation support, and a lens of the linear array camera is over against the top position of the turntable;
the manipulator is connected with the machine table, is positioned right above the opening at the top of the check ring and is used for driving a product to be tested placed in the product containing tank to be tested at the top of the turntable to rotate;
unloading sorting device is connected with the board, and unloading sorting device is used for sorting the product of the completion test of the bottom discharge gate output of retaining ring according to qualified class and unqualified class.
Preferably, unloading sorting device includes the hose connecting plate, the unloading hose, unqualified class ejection of compact hose, qualified class ejection of compact hose, ejection of compact hose connecting plate and electronic slip table, the unloading hose is connected with the hose connecting plate, unqualified class ejection of compact hose, qualified class ejection of compact hose is connected with ejection of compact hose connecting plate respectively, ejection of compact hose connecting plate is connected with the slider on the electronic slip table, the bottom surface fixed connection of electronic slip table and board, hose connecting plate and backup pad fixed connection, the upper end entry of unloading hose is located the bottom discharge gate of retaining ring under, the unloading hose passes the board, the lower extreme export of unloading hose is located the top of ejection of compact hose connecting plate.
Preferably, the manipulator comprises a Z-axis sliding table, a rotation driving motor, a motor base, a connecting plate, a push rod, a sleeve, a spring, an infrared sensor, a shaft sleeve and a connecting block, wherein the Z-axis sliding table is fixedly connected with a machine table, the connecting plate is fixedly connected with a sliding block on the Z-axis sliding table, the motor base is fixedly connected with the connecting plate, the connecting block is fixedly connected with the connecting plate, the rotation driving motor is fixedly connected with the upper part of the motor base, the sleeve is fixedly connected with the connecting block, the shaft sleeve is connected with an output shaft of the rotation driving motor through a coupler, the upper end of the push rod is connected with the shaft sleeve, the middle part of the push rod is positioned in the sleeve, the spring is arranged in the sleeve, the spring is sleeved in the middle part of the push rod, the connecting block is provided with a bearing chamber, a plane bearing is arranged in the bearing chamber, the, the lower end of the spring is contacted with the circular plate, and the infrared sensor is connected with the circular plate of the ejector rod;
the lower end of the ejector rod is positioned right above the top opening of the retainer ring.
Preferably, the manipulator includes Z axle slip table, connecting plate, rotation driving motor, motor cabinet, ejector pin and infrared sensor, and Z axle slip table and board fixed connection, connecting plate and the slider fixed connection on the Z axle slip table, motor cabinet and connecting plate fixed connection, rotation driving motor and motor cabinet fixed connection, the ejector pin passes through the shaft coupling and rotates driving motor's output shaft, the sub-unit connection of infrared sensor and ejector pin.
Preferably, the product surface defect detection system based on machine vision further comprises a conveyor belt device, the conveyor belt device is located below the machine table, and the lower ends of the unqualified discharging hose and the qualified discharging hose of the blanking sorting device are arranged on two conveyor belts of the conveyor belt device.
The invention has the advantages that based on the machine vision technology, the visual inspection method by naked eyes can be effectively replaced, the labor cost is reduced, and the detection efficiency and the accuracy are improved. Degree of automation is high, convenient operation, and detection speed is fast, and the material can be arranged to the classification.
Further features of the invention will be apparent from the description of the embodiments which follows.
Drawings
FIG. 1 is a schematic diagram of a machine vision based system for detecting surface defects of a product;
FIG. 2 is a top view of the machine vision based product surface defect detection system of FIG. 1;
FIG. 3 is a diagram showing the positional relationship between the robot and the turntable of the loading device in the structure shown in FIG. 1;
FIG. 4 is an enlarged view of a portion of the top of the turntable in the configuration of FIG. 1;
FIG. 5 is a partial enlarged view at B in FIG. 3;
FIG. 6 is a schematic view of a retainer ring of the feeding device fixedly mounted on a machine table;
FIG. 7 is a cross-sectional view of the retainer ring and the turntable of FIG. 6;
FIG. 8 is a schematic view of the robot;
FIG. 9 is a side view of the structure shown in FIG. 8;
FIG. 10 is a cross-sectional view of the robot;
fig. 11 is a schematic structural view of the blanking sorting device;
FIG. 12 is a connection diagram of the discharging sorting device and the machine;
FIG. 13 is a view showing the positional relationship between the blanking hose and the defective and the non-defective discharge hoses, respectively, in FIG. 12;
FIG. 14 is a schematic diagram of one embodiment of a robot;
fig. 15 is a flowchart of a computer image processing procedure.
The symbols in the drawings illustrate that:
100. the device comprises a machine table, 200, a feeding device, 210, a motor, 220, a coupler, 230, a rotating shaft, 240, a motor support, 250, a first bearing seat, 260, a second bearing seat, 270, a retainer ring, 271, a feeding port, 272, a bottom discharging port, 273, a top opening, 280, a rotating disc, 281, a positioning cylinder, 282, a planar needle roller bearing, 283, a planar needle roller bearing accommodating chamber, 284, a product accommodating tank to be tested, 290 and a supporting plate; 300. the detection device comprises a detection device, 310 linear array cameras, 311 lenses, 320 light sources and 330 mounting brackets; 400. the mechanical arm comprises a mechanical arm 401, a Z-axis sliding table 402, a rotation driving motor 403, a coupler 404, a motor base 404, a connecting plate 405, a connecting plate 406, a push rod 407, a sleeve 407, a spring 408, an infrared sensor 409, a plane bearing 410, a shaft sleeve 411 and a connecting block 412; 500. the automatic feeding sorting device comprises a feeding sorting device, 510, a hose connecting plate, 520, a feeding hose, 530, an unqualified discharging hose, 540, a qualified discharging hose, 550, a discharging hose connecting plate and 560, and an electric sliding table; 600. conveyor means, 700. display; 800. the manipulator, 801, a rotation driving motor, 802, a motor base, 803, a coupler, 804, a push rod and 805, an infrared sensor; 1. a small module worm.
Detailed Description
The present invention will be described in further detail below with reference to specific embodiments thereof with reference to the attached drawings.
As shown in fig. 1 to 7, the system for detecting surface defects of products based on machine vision includes a machine table 100, a feeding device 200, a detecting device 300, a manipulator 400, a discharging sorting device 500, and a conveyor device 600, wherein the feeding device 200, the detecting device 300, the manipulator 400, and the discharging sorting device 500 are respectively installed on the machine table 100, and the conveyor device 600 is located below the machine table 100.
The feeding device 200 includes a motor 210, a coupler 220, a rotating shaft 230, a motor support 240, a first bearing seat 250, a second bearing seat 260, a retainer ring 270, a turntable 280, and a support plate 290, the motor support 240 is fixedly mounted on the machine table 100, the motor 210 is fixedly connected with the motor support 240, the rotating shaft 230 is connected with an output shaft of the motor 210 through the coupler 220, the first bearing seat 250 is fixedly mounted on the machine table 100 through the first support, the second bearing seat 260 is fixedly mounted on the machine table 100 through the second support, one end of the rotating shaft 230 is connected with the first bearing seat 250, and the other end of the rotating shaft 230 is connected with the second bearing seat 260. Backup pad 290 and board 100 fixed connection, through the screw with retaining ring 270 fixed mounting on backup pad 290, retaining ring 270 is equipped with central through-hole, is equipped with shaft hole 291 on backup pad 290, and pivot 230 passes shaft hole 291 and retaining ring 270's central through-hole. The retaining ring 270 surrounds the rotating disc 280, a certain gap is formed between the outer edge of the rotating disc 280 and the inner wall of the retaining ring 270, and the rotating disc 280 cannot interfere with the retaining ring 270 in the rotating process. The retainer ring 270 is provided with a feed port 271, a bottom discharge port 272, and a top opening 273. The rotary table 280 is provided with a plurality of product accommodating grooves 284 uniformly distributed in the circumferential direction, the rotary table 280 is provided with a plurality of planar needle bearing accommodating chambers 283 uniformly distributed in the circumferential direction, one planar needle bearing accommodating chamber 283 corresponds to one product accommodating groove 284 to be detected, the positioning cylinder 281 is fixedly connected with the bottom surface of the planar needle bearing accommodating chamber 283, the planar needle bearing 282 is sleeved on the positioning cylinder 281, and the planar needle bearing 282 is positioned in the planar needle bearing accommodating chamber 283. In this embodiment, the number of the positioning cylinders 281 is 24, the number of the corresponding planar needle bearings 28 is 24, and the setting of 24 stations is only an example, and the number of the positioning cylinders 281 may be designed according to actual needs.
The detecting device 300 includes a mounting bracket 330, a line camera 310 and a light source 320, the mounting bracket 330 is fixedly connected to the machine 100, the line camera 310 is fixedly connected to the mounting bracket 330, the light source 320 is fixedly connected to the mounting bracket 330, and a lens 311 of the line camera 310 faces the top of the turntable 280.
The mechanical hand 400 is used for driving a small module worm placed at the top of the turntable 280 to rotate, and with reference to fig. 8, 9 and 10, the mechanical hand 400 comprises a Z-axis sliding table 401, a rotation driving motor 402, a coupler 403, a motor base 404, a connecting plate 405, a push rod 406, a sleeve 407, a spring 408, an infrared sensor 409, a plane bearing 410, a shaft sleeve 411 and a connecting block 412, the Z-axis sliding table 401 is fixedly installed on the machine table 100, the connecting plate 405 is fixedly connected with a slider on the Z-axis sliding table 401, the motor base 404 is fixedly connected with the connecting plate 405, the connecting block 412 is fixedly connected with the connecting plate 405, the rotation driving motor 402 is fixedly installed at the upper position of the motor base 402, the sleeve 407 is fixedly connected with the connecting block 412, the shaft sleeve 411 is connected with an output shaft of the rotation driving motor 402 through the coupler 403, the upper end of the push rod 406, the spring 408 is sleeved in the middle of the top rod 406, the connecting block 412 is provided with a bearing chamber, the plane bearing 410 is installed in the bearing chamber, the plane bearing 410 is sleeved on the upper portion of the top rod 406, the upper portion of the top rod 406 is provided with a shaft shoulder 406-1, the shaft shoulder 406-1 presses the top of the plane bearing 410 downwards, the lower portion of the top rod 406 is connected with the circular plate 406-2, the upper end of the spring 408 is in contact with the bottom surface of the connecting block 412, the lower end of the spring 408 is in contact with the circular plate 406-2, and the infrared sensor 409 is connected with the circular plate 406-.
The lower end of the top bar 406 is located directly above the top opening 273 of the retainer ring 270.
Referring to fig. 11-13, the blanking sorting apparatus 500 includes a hose connection plate 510, a blanking hose 520, an unqualified discharge hose 530, an unqualified discharge hose 540, a discharge hose connection plate 550, and an electric slide table 560, the blanking hose 520 is connected to the hose connection plate 510, the unqualified discharge hose 530 and the qualified discharge hose 540 are respectively connected to the discharge hose connection plate 550, the discharge hose connection plate 550 is connected to a slider on the electric slide table 560, the electric slide table 560 is fixedly mounted on the bottom surface of the machine 100, the hose connection plate 510 is fixedly connected to the support plate 290, an upper inlet of the blanking hose 520 is located right below a bottom discharge port 272 of the retainer ring 270, the blanking hose 520 passes through the machine 100, the position of the blanking hose 520 is moderately unchanged, a lower outlet of the blanking hose 520 is located above the discharge hose connection plate 550, the electric slide table 560 operates to, it is possible to align the upper end inlet of the non-conforming type discharge hose 530 with the lower end outlet of the blanking hose 520 or align the upper end inlet of the conforming type discharge hose 540 with the lower end outlet of the blanking hose 520. The upper inlet of the discharging hose 520 is preferably a conical opening to facilitate discharging.
Referring to fig. 1, the lower ends of the unqualified discharge hose 530 and the qualified discharge hose 540 are placed on two conveyor belts of the conveyor belt device 600, and the two conveyor belts of the conveyor belt device 600 are collected with the small-module worm screws output from the unqualified discharge hose 530 and the qualified discharge hose 540 respectively.
The working process of the product surface defect detection system based on machine vision is described as follows:
the machined small-module worm is dedusted by a dedusting gun in a clean room, and then an operator manually puts the small-module worm into a feeding hole 271 of the retainer ring 270, and as shown in fig. 3, the small-module worm is sleeved on a positioning cylinder 281 of the turntable 280, namely the positioning cylinder 281 penetrates through a central through hole of the small-module worm. Then, under the action of the controller, the motor 210 operates to drive the turntable 280 to rotate, and the small module worm moves to the top opening 273 of the retainer ring 270, as shown in fig. 3 and 4; at this time, the infrared sensor 805 detects that a small-modulus worm is arranged below, the controller instructs the Z-axis sliding table 401 of the Z-axis sliding table 401 manipulator 400 to work according to a signal fed back by the infrared sensor 805 to drive the ejector rod 406 to gradually descend from an initial position to approach the small-modulus worm 1, so that the lower end of the ejector rod 406 is pressed against a central hole in the top end face of the small-modulus worm 1 (at this time, the spring 408 plays a buffering role), and the small-modulus worm 1 is pressed against the upper end face of the planar needle roller bearing 282. Then, the rotation driving motor 402 operates to drive the push rod 406 to rotate, the push rod 406 drives the small-modulus worm 1 to rotate for a circle, meanwhile, the linear array camera 310 of the detection device 300 operates to collect images on the surface of the small-modulus worm 1, the collected images are transmitted to a computer, the computer completes image processing, after the image collection is completed, the push rod 406 stops rotating and rises to be separated from the small-modulus worm 1 and returns to an initial position, the small-modulus worm 1 after the image collection continues to rotate to a bottom discharge port 272 of the retainer ring 270 along with the turntable 280, the small-modulus worm 1 falls under the action of gravity and enters the blanking hose 520 after passing through the bottom discharge port 272 of the retainer ring 270, the computer judges whether the small-modulus worm is defective or not according to the image processing result, instructs the blanking sorting device 500 to operate, so that the qualified type discharging hose 540 is aligned with the blanking hose 520, and then the qualified small-modulus, the unqualified discharging hose 530 is aligned with the discharging hose 520, so that the unqualified small-module worm enters the unqualified discharging hose 530, and the small-module worm output by the unqualified discharging hose 530 and the qualified discharging hose 540 is collected by the conveyor belt device 600.
The rotation of the turntable 280 is stopped after rotating for 15 degrees, manual feeding is performed, and image acquisition is performed on the small module worm at the detection position at the top of the turntable 280.
The display 700 is installed on the machine 100, the computer sends image information to the display 700, and the operator can observe the image of the surface of the small-module worm from the display 700.
As shown in fig. 14, the above-mentioned robot 400 may be replaced with a robot 800, the robot 800 includes a Z-axis sliding table, a connecting plate, a rotation driving motor 801, a motor base 802, a coupler 803, a push rod 804, and an infrared sensor 805, the Z-axis sliding table is fixedly mounted on the machine platform 100, the connecting plate is fixedly connected to a slider on the Z-axis sliding table, the motor base 802 is fixedly connected to the connecting plate 405, the rotation driving motor 801 is fixedly connected to the motor base 802, the push rod 804 is connected to an output shaft of the rotation driving motor 801 through the coupler 803, and the infrared sensor 805 is connected to a lower portion of the push.
It should be noted that the specific structure of the robot 400 may also adopt the prior art (such as a clamping type robot structure), as long as it can drive the small-module worm to rotate.
The image processing process of the image information collected by the line-array camera 310 by the computer may adopt related processing algorithms in the prior art, and may also adopt the following algorithms:
The adaptive median filtering calculation has 2 processes, denoted as a and B, respectively.
A：A1＝Zmed-Zmin
A2＝Zmed-Zmax
If A is1> 0 and A2If the value is less than 0, skipping to the process B; otherwise, increasing the window size, if the increased window size is less than SmaxIf so, repeat process A, otherwise, output Zmed；
B：B1＝Zxy-Zmin
Wherein Z ismin、Zmed、ZmaxEach being a rectangular window S centred on the coordinates (x, y)xyMinimum, median, maximum of medium grey values, ZxyIs the gray value at coordinate (x, y), SmaxIs SxyThe maximum size allowed.
Step 2, image segmentation, the purpose of which is to classify the image pixels into several statistically uniform sub-regions which are not intersected with each other according to some characteristics of the image, such as gray scale, color, texture, shape, etc., so that each region has consistency, and the attribute between adjacent regions is specialA significant difference is characterized, thereby separating the target region from the background image. The invention adopts a binarization threshold value based on the histogram to carry out image segmentation, and is suitable for images with obvious double peaks in the gray level histogram. Through image preprocessing, the filtered gray value t ═ Z of each pixel (x, y) in the image has been obtainedxyOr t ═ ZmedThen according to the formula
Calculating a gray level histogram of the image, wherein tkIs a certain gray value, nkFor having a grey value t in the imagekN is the total number of pixels in the image, g (t)k) As a grey value t in the imagekThe frequency of occurrence. The image segmentation method based on the histogram binarization threshold value adopts the principle that the minimum value of the valley between two wave crests is used as a global threshold value, namely:
is wherein t is1And t2Respectively the gray values at two peaks, t*Is the threshold value sought.
And 3, defect extraction, namely separating the defect area of the worm by adopting a morphological method, including the position and the size of the defect area. And filling the broken and inwards recessed areas of the tooth top part by adopting closed operation, and then performing difference between the filled areas and the original areas to obtain the dark areas existing in the bright areas of the tooth top. Opening operations generally smooth the contour of the object, breaking narrower necks and eliminating thin protrusions, closing operations also smooth a portion of the contour, but in contrast to opening operations, closing operations can close narrower discontinuities and elongated ravines, eliminate small holes, and fill breaks in the contour lines.
The definition of the open operation and the close operation of the set X by the structural element B is as follows:
wherein
And Θ represents expansion and corrosion, respectively. With B representing the structural element, X representing the binarization region, erosion and dilation of the working space X are defined as:
and 4, classifying and identifying.
It should be noted that the present invention is not limited to detecting a small module worm, and can also detect other types of worms or other mechanical parts or other products that can be positioned on the turntable.
The present invention and its embodiments have been described above schematically, without limitation, and what is shown in the drawings is only one of the embodiments of the present invention, and the actual structure is not limited thereto. Therefore, if the person skilled in the art should be informed by the teachings of the present invention, other configurations of the components, the driving device and the connection means, which are similar to the technical solution and are not designed creatively, shall fall within the protection scope of the present invention without departing from the inventive spirit of the present invention.
Claims (6)
1. A product surface defect detection system based on machine vision is characterized by comprising a machine table, a feeding device, a detection device, a mechanical arm and a discharging sorting device;
the feeding device comprises a motor, a rotating shaft, a motor support, a first bearing seat, a second bearing seat, a retainer ring, a rotary table and a supporting plate, wherein the motor support is fixedly connected with the machine table; the supporting plate is fixedly connected with the machine table, the retainer ring is fixedly connected with the supporting plate, the retainer ring is provided with a central through hole, the supporting plate is provided with a shaft hole, and the rotating shaft penetrates through the shaft hole of the supporting plate and the central through hole of the retainer ring; the retainer ring surrounds the turntable, and a gap is formed between the outer edge of the turntable and the inner wall of the retainer ring; the retainer ring is provided with a feeding hole, a bottom discharging hole and a top opening; the turntable is provided with a plurality of to-be-detected product accommodating grooves which are uniformly distributed along the circumferential direction and a plurality of plane needle bearing accommodating chambers which correspond to the to-be-detected product accommodating grooves in number and are uniformly distributed along the circumferential direction, the bottom surface of each plane needle bearing accommodating chamber is connected with a positioning cylinder, a plane needle bearing is arranged in each plane needle bearing accommodating chamber, and the positioning cylinders penetrate through the plane needle bearings;
the detection device comprises an installation support, a linear array camera and a light source, wherein the installation support is fixedly connected with the machine table, the linear array camera is connected with the installation support, the light source is connected with the installation support, and a lens of the linear array camera is over against the top position of the turntable;
the manipulator is connected with the machine table, is positioned right above the opening at the top of the check ring, and is used for driving a product to be tested placed in the product accommodating groove at the top of the turntable to rotate;
the blanking sorting device is connected with the machine table and used for sorting the products which are output by the bottom discharge port of the check ring and complete the test according to qualified types and unqualified types.
2. The product surface defect detecting system based on machine vision as claimed in claim 1, wherein the unloading sorting device comprises a hose connecting plate, an unloading hose, an unqualified unloading hose, a qualified unloading hose, an unloading hose connecting plate and an electric sliding table, the unloading hose is connected with the hose connecting plate, the unqualified unloading hose and the qualified unloading hose are respectively connected with the unloading hose connecting plate, the unloading hose connecting plate is connected with a slider on the electric sliding table, the electric sliding table is fixedly connected with the bottom surface of the machine table, the hose connecting plate is fixedly connected with a supporting plate, an upper end inlet of the unloading hose is positioned under a bottom discharge port of a retaining ring, the unloading hose passes through the machine table, and a lower end outlet of the unloading hose is positioned above the unloading hose connecting plate.
3. The product surface defect detecting system based on machine vision as claimed in claim 1 or 2, characterized in that the manipulator comprises a Z-axis sliding table, a rotation driving motor, a motor base, a connecting plate, a push rod, a sleeve, a spring, an infrared sensor, a shaft sleeve and a connecting block, the Z-axis sliding table is fixedly connected with a machine table, the connecting plate is fixedly connected with a slide block on the Z-axis sliding table, the motor base is fixedly connected with the connecting plate, the connecting block is fixedly connected with the connecting plate, the rotation driving motor is fixedly connected with the upper part of the motor base, the sleeve is fixedly connected with the connecting block, the shaft sleeve is connected with an output shaft of the rotation driving motor through a shaft coupling, the upper end of the push rod is connected with the shaft sleeve, the middle part of the push rod is located in the sleeve, the spring is, a plane bearing is arranged in the bearing chamber, the upper part of the ejector rod penetrates through the plane bearing, a shaft shoulder is arranged on the upper part of the ejector rod and presses the plane bearing downwards, a circular plate is connected to the lower part of the ejector rod, the upper end of the spring is in contact with the bottom surface of the connecting block, the lower end of the spring is in contact with the circular plate, and the infrared sensor is connected with the circular plate of the ejector rod;
the lower end of the ejector rod is positioned right above the top opening of the retainer ring.
4. The product surface defect detection system based on machine vision of claim 1 or 2, characterized in that, the manipulator includes Z axle slip table, connecting plate, rotation driving motor, motor cabinet, ejector pin and infrared sensor, Z axle slip table and board fixed connection, slider fixed connection on connecting plate and the Z axle slip table, motor cabinet and connecting plate fixed connection, rotation driving motor and motor cabinet fixed connection, the ejector pin passes through shaft coupling and rotation driving motor's output shaft, the sub-unit connection of infrared sensor and ejector pin.
5. The system for detecting surface defects of products based on machine vision according to claim 2, further comprising a conveyor belt device located below the machine table, wherein the lower ends of the unqualified discharge hoses and the qualified discharge hoses of the blanking sorting device are placed on two conveyor belts of the conveyor belt device.
6. The detection method of the product surface defect detection system based on the machine vision according to claim 1 is characterized by comprising the following steps:
step 1, preprocessing an image;
step 2, image segmentation;
step 3, defect extraction;
and 4, classifying and identifying.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010667158.XA CN111672773A (en) | 2020-07-13 | 2020-07-13 | Product surface defect detection system and method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010667158.XA CN111672773A (en) | 2020-07-13 | 2020-07-13 | Product surface defect detection system and method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111672773A true CN111672773A (en) | 2020-09-18 |
Family
ID=72457550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010667158.XA Pending CN111672773A (en) | 2020-07-13 | 2020-07-13 | Product surface defect detection system and method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111672773A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113387000A (en) * | 2021-06-15 | 2021-09-14 | 绍兴浩晨自动化设备有限公司 | High-efficient packing production system of temperature controller for household electrical appliances |
| CN114405842A (en) * | 2022-03-30 | 2022-04-29 | 常州市中天印务有限公司 | Appearance detection equipment for outer packaging material |
| CN115415190A (en) * | 2022-09-14 | 2022-12-02 | 欧拜欧(昆山)汽车紧固件有限公司 | Automatic screw aligning detection mechanism |
| CN116727274A (en) * | 2023-08-15 | 2023-09-12 | 沧州坤厚塑胶科技有限公司 | Bag making machine |
-
2020
- 2020-07-13 CN CN202010667158.XA patent/CN111672773A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113387000A (en) * | 2021-06-15 | 2021-09-14 | 绍兴浩晨自动化设备有限公司 | High-efficient packing production system of temperature controller for household electrical appliances |
| CN114405842A (en) * | 2022-03-30 | 2022-04-29 | 常州市中天印务有限公司 | Appearance detection equipment for outer packaging material |
| CN115415190A (en) * | 2022-09-14 | 2022-12-02 | 欧拜欧(昆山)汽车紧固件有限公司 | Automatic screw aligning detection mechanism |
| CN115415190B (en) * | 2022-09-14 | 2023-11-17 | 欧拜欧(昆山)汽车紧固件有限公司 | Automatic screw alignment detection mechanism |
| CN116727274A (en) * | 2023-08-15 | 2023-09-12 | 沧州坤厚塑胶科技有限公司 | Bag making machine |
| CN116727274B (en) * | 2023-08-15 | 2023-10-20 | 沧州坤厚塑胶科技有限公司 | Bag making machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111672773A (en) | Product surface defect detection system and method based on machine vision | |
| CN108230324B (en) | Visual detection method for microdefect on surface of magnetic shoe | |
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN104502356B (en) | A kind of automatic testing method of the sliding bearing defect in inner surface based on machine vision | |
| CN106670127A (en) | Full-automatic visual inspection system for screen defects | |
| CN110403232B (en) | Cigarette quality detection method based on secondary algorithm | |
| CN103913468A (en) | Multi-vision defect detecting equipment and method for large-size LCD glass substrate in production line | |
| CN110216080A (en) | Quality monitoring system of PCB processing production line based on image contrast | |
| CN111220544A (en) | Lens quality detection device and detection method | |
| CN215031306U (en) | Defect workpiece detecting and sorting device based on machine vision | |
| CN114705686A (en) | Method and system for detecting surface defects of cylindrical pot, controller and industrial personal computer | |
| CN111693535A (en) | Touch screen defect detection equipment and method based on machine vision analysis | |
| CN201141839Y (en) | Device for detecting tiny bearing surface defect by computer vision technology | |
| CN116718616A (en) | Machine vision detection system and detection method for flaw detection | |
| CN111323429A (en) | White spirit body foreign matter detection equipment and detection method | |
| KR102000907B1 (en) | Appearance vision inspection method for ferrite part | |
| Feng et al. | Image processing of the grinding wheel surface | |
| CN212284937U (en) | Machine vision detection system for product surface defects | |
| CN111398294B (en) | Straw particle defect detection system and detection method based on machine vision | |
| CN111458344A (en) | Mask defect visual detection method, equipment and storage medium | |
| US11327028B2 (en) | Ceramic ball automatic sorting system and method | |
| CN113953208B (en) | Full-automatic sorting device and method for electronic components | |
| CN109894391A (en) | A kind of automatic detection device detecting surface blemish | |
| CN116078704A (en) | Appearance detection equipment based on CCD | |
| CN214066962U (en) | Part 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 |