CN111855678A - Device and method for identifying surface defects of metal wire - Google Patents

Device and method for identifying surface defects of metal wire Download PDF

Info

Publication number
CN111855678A
CN111855678A CN202010849723.4A CN202010849723A CN111855678A CN 111855678 A CN111855678 A CN 111855678A CN 202010849723 A CN202010849723 A CN 202010849723A CN 111855678 A CN111855678 A CN 111855678A
Authority
CN
China
Prior art keywords
metal wire
cavity
image
image acquisition
hole
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
Application number
CN202010849723.4A
Other languages
Chinese (zh)
Inventor
闫坤
张李轩
程明
卢建福
李慧慧
李执
刘威
陈德富
傅琪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guilin University of Electronic Technology
Original Assignee
Guilin University of Electronic Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guilin University of Electronic Technology filed Critical Guilin University of Electronic Technology
Priority to CN202010849723.4A priority Critical patent/CN111855678A/en
Publication of CN111855678A publication Critical patent/CN111855678A/en
Pending legal-status Critical Current

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
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • 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
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8854—Grading and classifying of flaws
    • G01N2021/8861—Determining coordinates of flaws
    • G01N2021/8864—Mapping zones of defects

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)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention discloses a device and a method for identifying surface defects of metal wires, wherein the device comprises a cavity and a marking unit which are connected with a control terminal and are closed at two ends, a group of image acquisition units are arranged on the inner wall of the cavity at intervals, a first through hole is arranged on one end surface of the cavity, a second through hole is arranged on the other end surface of the cavity, the metal wires enter the cavity from the first through hole and penetrate out from the second through hole, the marking unit is positioned near the second through hole through which the metal wires penetrate out of the cavity, and the image acquisition unit arranged on the inner wall of the cavity is connected with the control terminal, and the method comprises 1) image acquisition; 2) positioning a target; 3) extracting a region of interest (ROI); 4) normalizing the picture; 5) detecting defects; 6) and outputting the result. The device has low cost, good practicability and easy networking. The method is convenient to operate, can improve the identification efficiency and the identification accuracy, lightens the labor intensity of workers and reduces the production cost.

Description

Device and method for identifying surface defects of metal wire
Technical Field
The invention relates to the field of machine vision, in particular to a device and a method for identifying surface defects of metal wires.
Background
With the development and the innovation of science and technology, metal wires are widely applied in various fields, and various defects such as pits, crush damage and sawtooth defects are generated on the surfaces of the metal wires due to factors such as uneven stress and the like in the production and use processes of the metal wires; scraping and peeling the metal wire in the transferring process; the surface blistering is caused by the over-high temperature, or the surface has water and oil stains and the like, the defects of the metal wire can be further deepened and expanded after the metal wire is used for a long time, if the surface defects of the metal wire cannot be detected in time, hidden dangers are buried in the reliability and the safety of the metal wire, and huge safety accidents can be caused in serious cases. The detection of the surface quality of metal wires is one of the key links of product quality control, the accurate detection and accurate classification of surface defects are two basic tasks of the detection process, and the quality of the wires is screened through the defect detection, so that the method is an effective measure for improving the product competitiveness.
The traditional manual visual detection method for the surface defects of the metal wire materials has the problems that the labor cost is high, the method is limited by subjective evaluation factors, the defects are too small to be identified, the sampling coverage rate is low and the like, in addition, the sharp parts of the metal surface defects are easy to scratch in the sampling detection process, occupational diseases such as cervical spondylosis and visual deterioration are easily caused by long-term detection operation, and the manual quality inspection cannot meet the requirements in the production environment of high-temperature and high-speed operation. Therefore, continuous, accurate and instant defect detection is performed in the production process through a machine vision-based detection technology, so that the labor intensity of workers is reduced, and the yield and the generation efficiency are improved, and the urgent needs of enterprises are met.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a device and a method for identifying surface defects of metal wires. The device has low cost, good practicability and easy networking. The method is convenient to operate, can improve the identification efficiency and the identification accuracy, lightens the labor intensity of workers and reduces the production cost.
The technical scheme for realizing the purpose of the invention is as follows:
the utility model provides a device for discerning metal wire material surface defect, includes both ends confined cavity and the mark unit of being connected with control terminal, the interval is equipped with a set of image acquisition unit on the inner wall of cavity, is equipped with first through-hole on the terminal surface of cavity, is equipped with the second through-hole on another terminal surface of cavity, and the metal wire material gets into the cavity by first through-hole and is worn out by the second through-hole, and the mark unit is located near the second through-hole that the cavity was worn out to the metal wire material, and the image acquisition unit of setting on the inner wall of cavity is connected with control terminal.
The inner wall of the cavity is coated with the same color, the color of the color is selected according to the highlighting degree of the surface defects of the metal wires made of different materials under different color illumination, and the color selection is based on the color matching of the color phase ring.
The image acquisition unit includes the industry camera and sets up a set of light near the industry camera, and the quantity of light is 2 at least, and the industry camera is used for gathering and treats discernment metal wire surface image, and the light is used for throwing light to treating discernment metal wire, and supplementary industry camera gathers and treats discernment metal wire surface image, and the industry camera will treat discernment metal wire surface image data transmission to control terminal.
The marking unit comprises a container filled with a marking paint, the container is connected with a spray gun with a belt air pressure function, the spray gun is connected with a control terminal, the control terminal controls the marking paint to be sprayed on the surface of the metal wire through a nozzle of the spray gun, and the position of the surface defect of the metal wire is identified so as to timely process the defect and ensure the quality of the metal wire.
The surface defect positions of the metal wire are as follows: the spraying time of the spray gun is determined by three factors of the length Lcm of the cavity, the moving speed vcm/s (centimeter/second) of the metal wire and the surface defect of the metal wire detected by the image acquisition units, the image acquisition units are numbered from 1 to N from the moving direction of the metal wire 11, and a certain time t is assumedkThe k, k is 1,2, …, and the N image capturing units detect the defect
Figure BDA0002644314640000021
Spraying after the time delay of second, wherein gamma is a time delay adjusting parameter,
Figure BDA0002644314640000022
the marking paint is high-adhesion quick-drying pigment or fluorescent powder.
The positions and the number of the image acquisition units arranged on the inner wall of the cavity are determined according to the following principles: the length L of the cavity is divided into N equal-length regions, the number of the image acquisition units is 2N, each equal-length region image acquisition unit is arranged in a manner of taking the metal wire as an axis, and the 2N image acquisition units can acquire the surface image of the metal wire to be identified in each region in 360 degrees.
The apertures of the first through hole and the second through hole are consistent and adjustable so as to adapt to metal wires with different wire diameters.
The control terminal processes the image data of the surface of the metal wire acquired by the image acquisition unit, performs defect identification and judgment on the image data, and sends an instruction according to an image judgment result, the image judgment result of the surface of the metal wire comprises two results of a defect image and a non-defect image, and the following instruction is sent according to the judgment result:
1) when the result is a defect map, performing spraying marking operation on the area where the defect detection is located;
2) if the result is a non-defective map, the machine continues to operate normally.
A method for identifying surface defects of a metal wire, which comprises the device for identifying the surface defects of the metal wire, and comprises the following steps:
1) image acquisition: the control terminal controls the image acquisition unit to acquire an image of the surface of the metal wire;
2) target positioning: determining the position of the section of metal wire in the cavity by adopting a dynamic threshold segmentation method for the metal wire in the surface image of the metal wire obtained in the step 1), wherein the dynamic threshold segmentation method comprises the following steps: assuming that the gray value of the original image to be segmented is f (x, y), the gray value of the background image is g (x, y), and the segmented binary image is:
Figure BDA0002644314640000031
wherein (x, y) is an image pixel point, T is a threshold value set when f (x, y) and g (x, y) images are segmented, the threshold value binaryzes an image designated area, and effective information can be highlighted by setting a reasonable threshold value to remove redundant information;
3) extracting a Region of Interest (ROI): extracting the region in the cavity where the metal wire material is in the step 2), namely the region of interest ROI, and segmenting the region in the original image;
4) picture normalization: normalizing the ROI image into an image size supported by a neural network model, wherein the neural network model is the neural network model in the patent application number of 201910277354.3 and the patent name of 'metal surface fine defect detection method and device based on deep learning';
5) and (3) defect detection: inputting the normalized image obtained in the step 4) into a trained neural network model, and carrying out defect detection and judgment on the normalized image by the neural network model;
6) and (4) outputting a result: the output of the detection judgment result is divided into two cases of a non-defective graph and a defective graph.
Compared with the prior art, the technical scheme has the following characteristics:
(1) because the existing adaptive algorithms for light rays are difficult to be completely and properly applied to industrial occasions, the technical scheme isolates external light, avoids the influence of the change of the external light on image acquisition, and can stably and efficiently acquire the surface image of the metal wire to be detected;
(2) according to the technical scheme, multiple metal wire surface samples are collected in advance to serve as a training set for model training, and a deep learning algorithm is used for defect identification, so that the defect identification is not limited to single-form defect identification, has certain robustness and has higher defect identification accuracy;
(3) because the shooting background colors are different, the surface defects of the metal wire are difficult to show and different, the optimal shooting background can be found by changing the background color according to the actual condition, the color of the inner wall of the cavity can be coated and the color can be changed and selected, a better shooting environment is provided, and the reliability is higher;
(4) the technical scheme can carry out all-around image acquisition on the surface of the metal wire, and effectively reduces the missing rate of the wire defects;
(5) the technical scheme can be matched with automatic transportation modes such as a wire drawing machine and a vibration disc, can realize the automation of defect identification and detection, and improves the production efficiency.
The device has low cost, good practicability and easy networking. The method is convenient to operate, can improve the identification efficiency and the identification accuracy, lightens the labor intensity of workers and reduces the production cost.
Drawings
FIG. 1 is a schematic diagram of the structure of an apparatus according to an embodiment;
FIG. 2 is a schematic structural diagram of an image acquisition unit in an embodiment;
FIG. 3 is a side view of FIG. 1;
FIG. 4 is a side view of FIG. 2;
FIG. 5 is a front view of FIG. 1;
FIG. 6 is a flow chart of the method in the embodiment.
In the figure, 1, a cavity 2, a labeling unit 3, an image acquisition unit 4, a first through hole 5, a second through hole 6, an industrial camera 7, an illuminating lamp 8, a control terminal 9, a container 10, a spray gun 11 and metal wires are arranged.
Detailed Description
The invention will be further elucidated with reference to the drawings and examples, without however being limited thereto.
Example (b):
referring to fig. 1, 3, 5, a device for discerning metal silk material surface defect, include both ends confined cavity 1 and mark unit 2 be connected with control terminal 8, the interval is equipped with a set of image acquisition unit 3 on the inner wall of cavity 1, is equipped with first through-hole 4 on the terminal surface of cavity 1, is equipped with second through-hole 5 on another terminal surface of cavity 1, and metal silk material 11 gets into cavity 1 by first through-hole 4 and wears out by second through-hole 5, and mark unit 2 is located near second through-hole 5 that metal silk material 11 wore out cavity 1, and image acquisition unit 3 that sets up on the inner wall of cavity 1 is connected with control terminal 8.
The inner wall of the cavity 1 is coated with the same color, the color of the color is selected according to the highlighting degree of the surface defects of the metal wire materials 11 made of different materials under different colors of illumination, and the color selection is based on the color matching of the color phase ring.
As shown in fig. 2 and 4, the image acquisition unit 3 includes an industrial camera 6 and a set of illuminating lamp 7 arranged near the industrial camera 6, the number of the illuminating lamps 7 is at least 2, the industrial camera 6 is used for acquiring the surface image of the metal wire to be identified 11, the illuminating lamp 7 is used for projecting illuminating light to the metal wire to be identified 11, the auxiliary industrial camera 6 acquires the surface image of the metal wire to be identified 11, and the industrial camera 6 sends the surface image data of the metal wire to be identified 11 to the control terminal 8.
The marking unit 2 comprises a container 9 filled with marking paint, the container 9 is communicated with a spray gun 10 with an air pressure function, the spray gun 10 is connected with a control terminal 8, the control terminal 8 controls the marking paint to be sprayed on the surface of the metal wire 11 through a nozzle of the spray gun 10, and the position of a defect on the surface of the metal wire 11 is marked, so that the defect can be timely processed to ensure the quality of the metal wire 11.
The surface defect positions of the metal wire 11 are as follows: the spraying time of the spray gun 10 is determined by the length Lcm of the cavity 1 and the moving speed vcm/s of the metal wire 11 (Centimeter per second) and the surface defects of the metal wire 11 detected by the image acquisition units 3, numbering the image acquisition units 3 from 1 to N from the moving direction of the metal wire 11, and assuming a certain time tkThe k, k is 1,2, …, and if N image capturing units 3 detect a defect, the image capturing unit is turned on
Figure BDA0002644314640000041
Spraying after the time delay of second, wherein gamma is a time delay adjusting parameter,
Figure BDA0002644314640000042
this example γ is 1.74.
The marking paint is high-adhesion quick-drying pigment or fluorescent powder, and the fluorescent powder is adopted in the example.
The positions and the number of the image acquisition units 3 arranged on the inner wall of the cavity 1 are determined by the following principles: the length L of the cavity 1 is divided into N equal-length regions, the number of the image acquisition units 3 is 2N, each equal-length region image acquisition unit 3 is arranged in 2 by taking the metal wire 11 as an axis, and the 2N image acquisition units 3 can acquire the surface image of the metal wire 11 to be identified in each region in 360 degrees.
The apertures of the first through hole 4 and the second through hole 5 are consistent and adjustable so as to adapt to metal wires 11 with different wire diameters.
The control terminal 8 processes the image data of the surface of the metal wire 11 acquired by the image acquisition unit 3, performs defect identification and judgment on the image data, and sends out an instruction according to the image judgment result, the image judgment result of the surface of the metal wire 11 comprises two results of a defect image and a non-defect image, and the following instruction is sent out according to the judgment result:
1) when the result is a defect map, performing spraying marking operation on the area where the defect detection is located;
2) if the result is a non-defective map, the machine continues to operate normally.
A method for identifying surface defects of a metal wire, which comprises the device for identifying the surface defects of the metal wire, and comprises the following steps:
1) image acquisition: the control terminal 8 controls the image acquisition unit 3 to acquire an image of the surface of the metal wire 11;
2) target positioning: determining the area position of the section of the metal wire 11 in the cavity 1 by adopting a dynamic threshold segmentation method for the metal wire 11 in the surface image of the metal wire 11 obtained in the step 1), wherein the dynamic threshold segmentation method comprises the following steps: assuming that the gray value of the original image to be segmented is f (x, y), the gray value of the background image is g (x, y), and the segmented binary image is:
Figure BDA0002644314640000051
wherein (x, y) is an image pixel point, T is a threshold value set when f (x, y) and g (x, y) images are segmented, the threshold value binaryzes an image designated area, and effective information can be highlighted by setting a reasonable threshold value to remove redundant information;
3) extracting a region of interest ROI: extracting the region in the cavity 1 where the metal wire 11 in the step 2) is, namely the region of interest ROI, and segmenting the region in the original image;
4) picture normalization: normalizing the ROI image into an image size supported by a neural network model, wherein the neural network model is the neural network model in the patent application number of 201910277354.3 and the patent name of 'metal surface fine defect detection method and device based on deep learning';
5) and (3) defect detection: inputting the normalized image obtained in the step 4) into a trained neural network model, and carrying out defect detection and judgment on the normalized image by the neural network model;
6) and (4) outputting a result: the output of the detection judgment result is divided into two cases of a non-defective graph and a defective graph.
In this example, image acquisition unit 3 includes 1 industry camera 6 and 2 light 7, industry camera 6 chooses for use the pixel to be 2K, the scanning line frequency is 28KHz, the line camera of sweeping that the pixel size is 10um, light 7 chooses for use is luminance, linear light source of colour temperature adjustable, image acquisition unit 3 is 8, cavity 1 divides into N4, 6 apart from the silk material of industry camera about 4cm are the standard, the angle is about 30 between light 7 and the industry camera 6, the 6 shooting range of industry camera covers metal silk material 11 surface length about 7cm under this condition, can clearly shoot the silk material defect with the microspur mode, the length L of cavity 1 is 24cm, the terminal surface radius is 6cm, first through-hole 4 and second through-hole 5 radius are 1.5 cm.

Claims (9)

1. The utility model provides a device for discerning metal wire material surface defect, its characterized in that includes both ends confined cavity and the mark unit of being connected with control terminal, the interval is equipped with a set of image acquisition unit on the inner wall of cavity, is equipped with first through-hole on the terminal surface of cavity, is equipped with the second through-hole on another terminal surface of cavity, and the metal wire material gets into the cavity by first through-hole and wears out by the second through-hole, and the mark unit is located near the second through-hole that the cavity was worn out to the metal wire material, and the image acquisition unit of setting on the inner wall of cavity is connected with control terminal.
2. The device for identifying the surface defects of the metal wires according to claim 1, wherein the inner wall of the cavity is coated with the same color, the color of the color is selected according to the highlighting degree of the surface defects of the metal wires made of different materials under different colors of illumination, and the color selection is based on the color matching of the color phase rings.
3. The device for identifying the surface defects of the metal wires according to claim 1, wherein the image acquisition unit comprises an industrial camera and a group of illuminating lamps arranged near the industrial camera, the number of the illuminating lamps is at least 2, the industrial camera is used for acquiring the surface images of the metal wires to be identified, the illuminating lamps are used for projecting illuminating light rays to the metal wires to be identified, the auxiliary industrial camera is used for acquiring the surface images of the metal wires to be identified, and the industrial camera sends the surface image data of the metal wires to be identified to the control terminal.
4. The apparatus for identifying the surface defects of the metal wire according to claim 1, wherein the marking unit comprises a container filled with marking paint, the container is connected with a spray gun with an air pressure function, the spray gun is connected with a control terminal, and the control terminal controls the marking paint to be sprayed on the surface of the metal wire through a nozzle of the spray gun to identify the surface defect positions of the metal wire.
5. The apparatus for identifying surface defects of metal wires according to claim 4, wherein the marking paint is a high adhesion quick drying pigment or a fluorescent powder.
6. The apparatus for identifying surface defects of metal wires according to claim 4, wherein the positions of the surface defects of the metal wires are: the spraying time of the spray gun is determined by three factors of the length L cm of the cavity, the moving speed v cm/s (centimeter/second) of the metal wire and the surface defect of the metal wire detected by the image acquisition units, the image acquisition units are numbered from 1 to N from the moving direction of the metal wire, and a certain time t is assumedkThe k, k is 1,2, …, and the N image capturing units detect the defect
Figure FDA0002644314630000011
Spraying after the time delay of second, wherein gamma is a time delay adjusting parameter,
Figure FDA0002644314630000012
7. the device for identifying the surface defects of the metal wire according to claim 1, wherein the positions and the number of the image acquisition units arranged on the inner wall of the cavity are determined according to the following principle: the length L of the cavity is divided into N equal-length regions, the number of the image acquisition units is 2N, each equal-length region image acquisition unit is arranged in a manner of taking the metal wire as an axis, and the 2N image acquisition units can acquire the surface image of the metal wire to be identified in each region in 360 degrees.
8. The apparatus for identifying surface defects of metal wires according to claim 1, wherein the first through hole and the second through hole have uniform and adjustable hole diameters.
9. A method for identifying surface defects of a metal wire, comprising the apparatus for identifying surface defects of a metal wire according to any one of claims 1 to 8, the method comprising the steps of:
1) image acquisition: the control terminal controls the image acquisition unit to acquire an image of the surface of the metal wire;
2) target positioning: determining the position of the section of metal wire in the cavity by adopting a dynamic threshold segmentation method for the metal wire in the surface image of the metal wire obtained in the step 1), wherein the dynamic threshold segmentation method comprises the following steps: assuming that the gray value of the original image to be segmented is f (x, y), the gray value of the background image is g (x, y), and the segmented binary image is:
Figure FDA0002644314630000021
wherein (x, y) is an image pixel point, T is a threshold value set when f (x, y) and g (x, y) images are segmented, and the threshold value is used for carrying out binarization on an image designated area;
3) extracting a region of interest ROI: extracting the region in the cavity where the metal wire material is in the step 2), namely the region of interest ROI, and segmenting the region in the original image;
4) picture normalization: normalizing the ROI image into an image size supported by a neural network model, wherein the neural network model is the neural network model in the patent application number of 201910277354.3 and the patent name of 'metal surface fine defect detection method and device based on deep learning';
5) and (3) defect detection: inputting the normalized image obtained in the step 4) into a trained neural network model, and carrying out defect detection and judgment on the normalized image by the neural network model;
6) and (4) outputting a result: the output of the detection judgment result is divided into two cases of a non-defective graph and a defective graph.
CN202010849723.4A 2020-08-21 2020-08-21 Device and method for identifying surface defects of metal wire Pending CN111855678A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010849723.4A CN111855678A (en) 2020-08-21 2020-08-21 Device and method for identifying surface defects of metal wire

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010849723.4A CN111855678A (en) 2020-08-21 2020-08-21 Device and method for identifying surface defects of metal wire

Publications (1)

Publication Number Publication Date
CN111855678A true CN111855678A (en) 2020-10-30

Family

ID=72970003

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010849723.4A Pending CN111855678A (en) 2020-08-21 2020-08-21 Device and method for identifying surface defects of metal wire

Country Status (1)

Country Link
CN (1) CN111855678A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116213487A (en) * 2023-05-08 2023-06-06 浙江求是半导体设备有限公司 Wire drawing die maintenance method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116213487A (en) * 2023-05-08 2023-06-06 浙江求是半导体设备有限公司 Wire drawing die maintenance method
CN116213487B (en) * 2023-05-08 2023-08-08 浙江求是半导体设备有限公司 Wire drawing die maintenance method

Similar Documents

Publication Publication Date Title
CN109269951B (en) Image-based flotation tailing ash content, concentration and coarse particle content detection method
CN101226108B (en) Method for testing droplet distribution consistency degree
CN109872300B (en) Visual saliency detection method for appearance defects of friction plate
US7773214B2 (en) Apparatus and methods for container inspection
US7771776B2 (en) Apparatus and method for inspecting golf balls using spectral analysis
CA2759600C (en) System and method for monitoring painting quality of components, in particular of motor-vehicle bodies
CN107154039B (en) Rubber tube online defect detection method
CN1633592A (en) Web inspection method and device
CN102654464A (en) Copper strip surface defect detection system based on multi-feature fuzzy recognition
CN109993154B (en) Intelligent identification method for single-pointer sulfur hexafluoride instrument of transformer substation
Liu et al. Automatic detection technology of surface defects on plastic products based on machine vision
CN110646431B (en) Automatic teaching method of gluing sensor
CN206772850U (en) CCD lines for Intelligent Measurement surface defects of products sweep camera system
US7551766B2 (en) Apparatus and method for inspecting golf balls using threshold analysis
CN104792794A (en) Machine vision based optical film surface defect detecting method
CN110726720B (en) Method for detecting suspended substances in drinking mineral water
CN210071686U (en) Fruit grading plant based on orthogonal binocular machine vision
CN114638797A (en) Method and device for detecting copper surface defects based on linear array camera
CN110930366A (en) Nut loosening detection method for wind power tower cylinder
CN114708325A (en) Method for quickly positioning rubber production problem based on rubber blooming defect
CN104700417A (en) Computer image based automatic identification method of timber knot flaws
CN104535589A (en) Online detection method and device for low-voltage current mutual inductor
CN110956627A (en) Intelligent optical detection sample characteristic and flaw intelligent lighting image capturing method and device
CN111855678A (en) Device and method for identifying surface defects of metal wire
CN111665251A (en) Visual detection method for surface defects

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