CN114371179A - System, method and device for online detection and removal of foreign matters on surface of fine blanking die - Google Patents

System, method and device for online detection and removal of foreign matters on surface of fine blanking die Download PDF

Info

Publication number
CN114371179A
CN114371179A CN202111646332.3A CN202111646332A CN114371179A CN 114371179 A CN114371179 A CN 114371179A CN 202111646332 A CN202111646332 A CN 202111646332A CN 114371179 A CN114371179 A CN 114371179A
Authority
CN
China
Prior art keywords
image
die
fine blanking
foreign matters
camera
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.)
Granted
Application number
CN202111646332.3A
Other languages
Chinese (zh)
Other versions
CN114371179B (en
Inventor
王蕾
郭钰瑶
张泽琳
刘翔
夏绪辉
李文喜
刘玉波
赵林昌
严旭果
陈宝通
王瞳
曹建华
张欢
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.)
Wuhan University of Science and Engineering WUSE
Xiangyang Boya Precision Industrial Equipments Co Ltd
Original Assignee
Wuhan University of Science and Engineering WUSE
Xiangyang Boya Precision Industrial Equipments Co Ltd
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 Wuhan University of Science and Engineering WUSE, Xiangyang Boya Precision Industrial Equipments Co Ltd filed Critical Wuhan University of Science and Engineering WUSE
Priority to CN202111646332.3A priority Critical patent/CN114371179B/en
Publication of CN114371179A publication Critical patent/CN114371179A/en
Application granted granted Critical
Publication of CN114371179B publication Critical patent/CN114371179B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • B08B1/30—
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B08—CLEANING
    • B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
    • B08B13/00—Accessories or details of general applicability for machines or apparatus for cleaning
    • 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
    • G01N21/84—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
    • G01N2021/8887—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 based on image processing techniques

Abstract

The invention belongs to the technical field of fine blanking equipment detection, and discloses a system, a method and a device for detecting and removing foreign matters on the surface of a fine blanking die on line, wherein an image data acquisition module acquires image data of the surfaces of an upper die and a lower die by using an industrial camera; the image acquisition control module controls the start and stop of the data acquisition module; the image data processing module is used for preprocessing, segmenting and extracting texture features of the acquired surface image of the mold; meanwhile, the system is used for controlling the starting and stopping of the foreign matter removing module; the foreign matter removal control module is used for removing foreign matters. The invention provides an online detection and removal system for foreign matters on the surface of a fine blanking die, which can be used for quickly detecting and removing the foreign matters on the surface of the fine blanking die, extracting the defect characteristics of the obtained image data through a computer and identifying and detecting the foreign matters, and avoiding die damage and resource waste. The invention simultaneously detects the upper and lower fine blanking dies through the multi-angle combined light and the industrial camera, thereby being more comprehensive.

Description

System, method and device for online detection and removal of foreign matters on surface of fine blanking die
Technical Field
The invention belongs to the technical field of fine blanking detection, and particularly relates to a system, a method and a device for detecting and removing foreign matters on the surface of a fine blanking die on line.
Background
At present, fine blanking is a fine blanking method developed on the basis of common stamping and plays a great role in the field of automobile part manufacturing.
The typical structure of the fine blanking die comprises a movable convex mode structure, a fixed convex mode structure and a continuous fine blanking die. The fine blanking process requires the fine blanking equipment to have accurate blanking force, edge pressing force and back pressure. Therefore, the mechanical fine stamping press is generally adopted for producing the fine stamping parts in large batch, and the parts are fine stamped on the oil press by using the hydraulic die frame. In the fine blanking process, the metal material is subjected to fine stamping through a die, after the stamping is finished, the die is opened, and the material returning force and the ejecting force are used for ejecting the waste material and the part respectively. And blowing off the blank by using compressed air for carrying out next stamping. However, the process cannot determine whether the scraps are completely removed, and metal scraps are easily generated to adhere to the die during the stamping process, so that foreign matter residues on the die are easily generated, and the die is damaged and the product is not qualified.
Through the above analysis, the problems and defects of the prior art are as follows: the prior art has no method or device for detecting or removing foreign matters on the surface of a fine blanking die on line.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a system, a method and a device for detecting and removing foreign matters on the surface of a fine blanking die on line.
The invention is realized in this way, a fine blanking die surface foreign matter on-line detecting and removing system, the fine blanking die surface foreign matter on-line detecting and removing system includes:
the device comprises an image data acquisition module, an image acquisition control module, an image data processing module and a foreign matter removal control module;
the image data acquisition module is connected with the image acquisition control module and is used for acquiring the surface image data of the upper die and the lower die by utilizing an industrial camera;
the image acquisition control module is connected with the fine blanking die and the image data acquisition module and is used for controlling the start and stop of the data acquisition module;
the image data processing module is connected with the image data acquisition module and the foreign matter removal control module; the image segmentation method comprises an image preprocessing unit, an image segmentation unit and an image texture feature extraction unit; the system is used for preprocessing, segmenting and extracting textural features of the acquired surface images of the mold; meanwhile, the system is used for controlling the starting and stopping of the foreign matter removing module;
the foreign matter removal control module is connected with the image data processing module and the image acquisition control module; used for removing foreign matters.
Further, the image data processing module includes:
the image preprocessing unit is used for carrying out noise reduction processing and contrast brightness adjustment on the collected mold surface illumination pattern;
the image segmentation unit is used for segmenting the preprocessed die image and extracting a defect area image;
and the image texture feature extraction unit is used for extracting texture features of the extracted defect image area.
Another objective of the present invention is to provide an online detecting and removing method for foreign matter on the surface of a fine blanking die, which is applied to the online detecting and removing system for foreign matter on the surface of a fine blanking die, and the online detecting and removing method for foreign matter on the surface of a fine blanking die comprises:
firstly, collecting images of the surfaces of an upper die and a lower die; preprocessing the collected surface images of the upper and lower dies; processing the preprocessed upper and lower die surface images by adopting a global threshold, and determining an area where the foreign matters are located, namely an image defect area;
calculating a gray level image for the extracted image defect area to obtain a co-occurrence matrix; obtaining a part of characteristic values of the matrix, namely texture characteristics of the defect image, by calculating a co-occurrence matrix;
judging whether the image on the surface of the die has foreign matters or not based on the extracted textural features of the defect image through a minimum distance discrimination function, and if not, continuing stamping; when the residual foreign matters exist, turning to the fourth step;
controlling the blowing device to perform secondary blowing, acquiring the image data of the surface of the mold again by using the industrial camera after the blowing is finished, and judging whether the foreign matter on the surface of the mold is removed or not based on the acquired image; and if the foreign matters exist, controlling an alarm to give an alarm.
Further, in the first step, the collecting of the images of the surfaces of the upper and lower molds includes:
the camera position controller determines the position and the angle of the camera and the combined light source according to the mould; after the metal material is punched, the displacement sensor determines that punching is finished through the displacement distance of the upper die table and the lower die table and sends an electric signal to the camera controller to control the industrial camera to acquire the surface images of the upper die and the lower die after the parts and the waste materials are blown.
Further, the collecting of the surface images of the upper mold and the lower mold further comprises: and controlling an industrial camera to carry out time-delay shooting according to the blowing time of the blowing device to obtain the surface images of the upper die and the lower die.
Further, the pretreatment of the collected upper and lower mold surfaces comprises:
adopting BM3D algorithm to perform noise reduction processing on the collected upper and lower die illumination diagrams, and performing contrast brightness adjustment on the images through a sigmoid function, as follows:
f(x)＝1/(1+e-x)；
as x approaches negative infinity, y approaches 0; as x approaches positive infinity, y approaches 1; when x is 1/2, y is 0.
Further, the extracting the texture features of the defect image comprises:
(1) 4 directions of theta of 0 degree, 45 degrees, 90 degrees and 135 degrees are selected to calculate the gray level co-occurrence matrix, and the method comprises the following steps:
p＝(i，j，δ，θ)＝{[(x，y)，(x+Δx，y+Δy)]|f(x，y)＝i，f(x+Δx，y+Δy)＝j；x＝ 0，1，…，Nx-1；y＝0，1，…，Ny-1}；
wherein: i, j ═ 0, 1,. ·, L-1; x, y represent pixel coordinates in the image; l represents the number of gray levels of an image; n is a radical ofx，NyRespectively representing the row number and the column number of the image;
(2) extracting image texture features by adopting energy, contrast, correlation and entropy:
energy:
Figure BDA0003443961800000041
contrast ratio:
Figure BDA0003443961800000042
correlation degree:
Figure BDA0003443961800000043
entropy:
Figure BDA0003443961800000044
(3) and calculating the mean value and the variance of the characteristic values of the gray level co-occurrence matrix in all directions to obtain 4 mean values and 4 variances, and obtaining the characteristics of the defect image.
Another object of the present invention is to provide an online detecting and removing device for foreign matter on the surface of a fine blanking die, which is applied to the online detecting and removing system for foreign matter on the surface of a fine blanking die, wherein the online detecting and removing device for foreign matter on the surface of a fine blanking die is provided with:
the device comprises an image acquisition device, an image acquisition control device, a computer and a foreign matter removal control device;
the image acquisition device consists of an industrial camera, a combined light source, a displacement sensor, a sliding table, a telescopic bracket and a guide rail;
the image acquisition control device consists of a camera controller, a displacement sensor and a camera position controller;
the foreign matter removing control device consists of a blowing device and an alarm.
Further, the online detection and removal method and device for the foreign matters on the surface of the fine blanking die comprises the following steps:
the industrial camera is fixed on a telescopic bracket, and the telescopic bracket is arranged on a rotary joint of the sliding table; the sliding table is in sliding connection with the guide rails, and the guide rails are fixed on the inner walls of the two sides of the fine blanking machine; a combined light source with the same angle is fixed in front of the industrial camera;
the camera controller is connected with the industrial camera, the combined light source and the displacement sensor; the displacement sensor is arranged on the outer side of the lower die table;
the blowing device consists of an air compressor, a hydraulic pump, a bracket and a blowing pipe; the air compressor and the hydraulic pump are arranged above the upper die table; the blowing pipe is arranged on a bracket outside the lower die table, and the blowing pipe is connected with the bracket in a sliding manner;
the alarm is arranged outside the fine blanking machine.
Further, the image acquisition control device includes:
the displacement sensor is used for measuring the displacement distance of the upper die table and the lower die table;
the camera controller is used for determining the end of stamping according to the displacement distance and controlling the industrial camera to carry out time-delay shooting;
and the camera position controller is used for changing the optimal shooting position and the optimal shooting angle of the camera and the combined light source on the guide rail according to different molds.
By combining all the technical schemes, the invention has the advantages and positive effects that:
the invention provides an online detection and removal system for foreign matters on the surface of a fine blanking die, which can be used for quickly detecting and removing the foreign matters on the surface of the fine blanking die, extracting the defect characteristics of the obtained image data through a computer and identifying and detecting the foreign matters, and avoiding die damage and resource waste.
The invention simultaneously detects the upper and lower fine blanking dies through the multi-angle combined light and the industrial camera, thereby being more comprehensive.
According to the detection device, different-angle illumination maps of the mold are obtained, after preprocessing is carried out, gray level images are calculated for the extracted defect image areas to obtain a co-occurrence matrix, and then characteristic values of the co-occurrence matrix, such as energy, contrast, correlation degree and entropy, are calculated to respectively represent texture characteristics of the images, so that rapid detection of foreign matters on the surface of the mold is realized.
The invention can carry out secondary blowing on the surface of the die through the control system, thereby ensuring the safety of the stamping process.
Drawings
FIG. 1 is a schematic structural diagram of an online detection and removal system for foreign matter on the surface of a fine blanking die according to an embodiment of the present invention;
in the figure: 1. an image data acquisition module; 2. an image acquisition control module; 3. an image data processing module; 4. and a foreign matter removal control module.
Fig. 2 is a schematic diagram of a method for online detecting and removing foreign matters on the surface of a fine blanking die according to an embodiment of the present invention.
Fig. 3 is a flowchart of a method for online detecting and removing foreign matter on the surface of a fine blanking die according to an embodiment of the present invention.
Fig. 4 is an overall schematic view of an online detection and removal device for foreign matter on the surface of a fine blanking die according to an embodiment of the present invention.
Fig. 5 is a schematic side view of an online detection and removal device for foreign matter on the surface of a fine blanking die according to an embodiment of the present invention.
Fig. 6 is a schematic top view of an online detection and removal device for foreign matter on the surface of a fine blanking die according to an embodiment of the present invention.
Fig. 7 is an overall schematic view of an image capturing apparatus according to an embodiment of the present invention.
Fig. 8 is a schematic diagram of a camera controller according to an embodiment of the present invention.
Fig. 9 is a schematic view of a guide rail provided by an embodiment of the present invention.
In fig. 4-9: 2-1, a displacement sensor; 2-2, an upper die; 2-3, lower die; 2-4, a lower die table; 2-5, an alarm; 2-6, an air compressor; 2-7, a hydraulic pump; 2-8, a bracket; 2-9, a blowing pipe; 2-10, an upper die table; 2-11, a first industrial camera; 2-12, a second industrial camera; 2-13, a third industrial camera; 2-14, a fourth industrial camera; 3-1, industrial camera; 3-2, a combined light source; 3-3, a sliding table; 3-4, a telescopic bracket; 3-5, guide rails; 3-6, a camera controller; 3-7, a camera position controller.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides an online detection and removal system for foreign matters on the surface of a fine blanking die, and the invention is described in detail with reference to the attached drawings.
As shown in fig. 1, an online detecting and removing system for foreign matter on the surface of a fine blanking die according to an embodiment of the present invention includes:
the image data acquisition module 1 is connected with the image acquisition control module 2 and is used for acquiring the image data of the surfaces of the upper die and the lower die by utilizing an industrial camera;
the image acquisition control module 2 is connected with the fine blanking die and the image data acquisition module 1 and is used for controlling the start and stop of the data acquisition module;
the image data processing module 3 is connected with the image data acquisition module 1 and the foreign matter removal control module 4; the image segmentation method comprises an image preprocessing unit, an image segmentation unit and an image texture feature extraction unit; the system is used for preprocessing, segmenting and extracting textural features of the acquired surface images of the mold; meanwhile, the system is used for controlling the starting and stopping of the foreign matter removing module;
the foreign matter removal control module 4 is connected with the image data processing module 3 and the image acquisition control module 2; used for removing foreign matters.
The image data processing module provided by the embodiment of the invention comprises:
the image preprocessing unit is used for carrying out noise reduction processing and contrast brightness adjustment on the collected mold surface illumination pattern;
the image segmentation unit is used for segmenting the preprocessed die image and extracting a defect area image;
and the image texture feature extraction unit is used for extracting texture features of the extracted defect image area.
As shown in fig. 2 to fig. 3, the online detecting and removing method for foreign matters on the surface of a fine blanking die according to an embodiment of the present invention includes:
s101, collecting the surface images of an upper die and a lower die; preprocessing the collected surface images of the upper and lower dies; processing the preprocessed upper and lower die surface images by adopting a global threshold, and determining an area where the foreign matters are located, namely an image defect area;
s102, calculating a gray level image of the extracted image defect area to obtain a co-occurrence matrix; obtaining a part of characteristic values of the matrix, namely texture characteristics of the defect image, by calculating a co-occurrence matrix;
s103, judging whether the foreign matter exists in the surface image of the die or not based on the extracted texture features of the defect image through a minimum distance discriminant function, and if not, continuing to punch; when the residual foreign matter exists, the process goes to step S104;
s104, controlling the blowing device to perform secondary blowing, acquiring the image data of the surface of the mold again by using the industrial camera after the blowing is finished, and judging whether the foreign matter on the surface of the mold is removed or not based on the acquired image; and if the foreign matters exist, controlling an alarm to give an alarm.
The embodiment of the invention provides a method for collecting the surface images of an upper die and a lower die, which comprises the following steps:
the camera position controller determines the position and the angle of the camera and the combined light source according to the mould; after the metal material is punched, the displacement sensor determines that punching is finished through the displacement distance of the upper die table and the lower die table and sends an electric signal to the camera controller to control the industrial camera to acquire the surface images of the upper die and the lower die after the parts and the waste materials are blown.
The embodiment of the invention provides the following steps of collecting the surface images of the upper die and the lower die: and controlling an industrial camera to carry out time-delay shooting according to the blowing time of the blowing device to obtain the surface images of the upper die and the lower die.
The pretreatment of the collected upper and lower die surfaces provided by the embodiment of the invention comprises the following steps:
adopting BM3D algorithm to perform noise reduction processing on the collected upper and lower die illumination diagrams, and performing contrast brightness adjustment on the images through a sigmoid function, as follows:
f(x)＝1/(1+e-x)；
as x approaches negative infinity, y approaches 0; as x approaches positive infinity, y approaches 1; when x is 1/2, y is 0.
The extraction of the texture features of the defect image provided by the embodiment of the invention comprises the following steps:
(1) 4 directions of theta of 0 degree, 45 degrees, 90 degrees and 135 degrees are selected to calculate the gray level co-occurrence matrix, and the method comprises the following steps:
p＝(i，j，δ，θ)＝{[(x，y)，(x+Δx，y+Δy)]|f(x，y)＝i，f(x+Δx，y+Δy)＝j；x＝ 0，1，…，Nx-1；y＝0，1，…，Ny-1}；
wherein: i, j ═ 0, 1,. ·, L-1; x, y represent pixel coordinates in the image; l represents the number of gray levels of an image; n is a radical ofx，NyRespectively representing the row number and the column number of the image;
(2) extracting image texture features by adopting energy, contrast, correlation and entropy:
energy:
Figure BDA0003443961800000091
contrast ratio:
Figure BDA0003443961800000092
correlation degree:
Figure BDA0003443961800000093
entropy:
Figure BDA0003443961800000094
(3) and calculating the mean value and the variance of the characteristic values of the gray level co-occurrence matrix in all directions to obtain 4 mean values and 4 variances, and obtaining the characteristics of the defect image.
As shown in fig. 4 to 9, the device for detecting and removing foreign matter on the surface of a fine blanking die provided by the embodiment of the present invention includes:
the device comprises an image acquisition device, an image acquisition control device, a computer and a foreign matter removal control device;
the image acquisition device consists of an industrial camera 3-1, a combined light source 3-2, a sliding table 3-3, a telescopic bracket 3-4 and a guide rail 3-5; the industrial camera 3-1 is a WP-UT miniature high-speed camera, and the combined light source 3-2 is an LED combined light source.
The industrial camera 3-1 is fixed on a telescopic bracket 3-4, the telescopic bracket 3-4 is arranged on a rotary joint of the sliding table 3-3, the position and the angle are regulated and controlled by the sliding table 3-3, the sliding table 3-3 is in sliding connection with the guide rail 3-5, and the guide rail 3-5 is fixed on the inner walls of the two sides of the fine blanking machine. The combined light source 3-2 is fixed at the same angle in front of the industrial camera 3-1. In the working process, the end of stamping can be determined according to electric signals sent by the displacement sensor 2-1, and then image data of the surface of the upper die 2-2 and the surface of the lower die 2-3 can be obtained according to the first industrial camera 2-11, the second industrial camera 2-12, the third industrial camera 2-13 and the fourth industrial camera 2-14.
The image acquisition control device consists of a camera controller 3-6, a displacement sensor 2-1 and a camera position controller 3-7; the camera controller 3-6 is connected with the industrial camera 3-1, the combined light source 3-2 and the displacement sensor 2-1. The displacement sensor 2-1 is located on the outer side of the lower die table 2-4, the displacement distance of the upper die table and the lower die table is measured and then fed back to the camera controller 3-6, and the camera controller 3-6 determines the end of stamping according to the displacement distance so as to control the industrial camera 3-1 to carry out time-delay shooting. The camera position controller 3-7 changes the shooting position and angle of the industrial camera 3-1 and the combined light source 3-2 on the guide rail 3-5 according to different molds.
The foreign matter removing control device consists of a blowing device and an alarm 2-5.
The blowing device consists of an air compressor 2-6, a hydraulic pump 2-7, a bracket 2-8 and a blowing pipe 2-9. An air compressor 2-6 and a hydraulic pump 2-7 are mounted above the upper die table 2-10. The injection pipe 2-9 is arranged on a bracket 2-8 at the outer side of the lower die table 2-4, and the injection pipe 2-9 is in sliding connection with the bracket 2-8. The alarm 2-5 is installed outside the fine blanking machine and is used for reminding a technician when foreign matters cannot be removed.
The technical solution of the present invention is further illustrated by the following specific examples.
Example 1:
an online detection and removal device and method for foreign matters on the surface of a fine blanking die comprises an image data acquisition system, an image acquisition control system, an image data processing system and a foreign matter removal control system.
The image data acquisition system includes: industrial camera, combined light source, displacement sensor, slip table, telescopic bracket, guide rail. The industrial camera is respectively fixed on the telescopic supports, the telescopic supports are installed on the rotary joints of the sliding tables, the positions and angles of the telescopic supports are regulated and controlled by the sliding tables, the sliding tables are connected with the guide rails in a sliding mode, and the guide rails are fixed on the inner walls of the two sides of the fine blanking machine. The combined light source is fixed in front of the camera at the same angle. And the displacement sensor is arranged on the outer side of the lower die table. The end of stamping can be determined according to the electric signals sent by the displacement sensor, and then the image data of the surface of the die can be obtained according to an industrial camera.
The image acquisition control system is connected with the fine blanking die and the image data acquisition device, and the image data acquisition device can be opened or closed by the image acquisition control system. The position and the angle of the industrial camera can be adjusted through different molds, and delayed shooting can be performed according to the blowing time of the blowing device, so that the image acquisition device can acquire image data of the upper mold and the lower mold after blowing is finished.
The image acquisition control system includes: a camera controller and a camera position controller. The camera controller is connected with the industrial camera, the combined light source and the displacement sensor. The displacement sensor is positioned on the outer side of the lower die table, the displacement distance of the upper die table and the lower die table is measured and then fed back to the camera controller, and the camera controller determines the end of stamping according to the displacement distance so as to control the industrial camera to carry out time-delay shooting. The camera position controller changes the optimal shooting position and the optimal shooting angle of the camera and the combined light source on the guide rail according to different molds.
The image data processing system mainly utilizes a computer, and the computer comprises: the image processing device comprises an image preprocessing unit, an image segmentation unit and an image texture feature extraction unit.
The image preprocessing unit is used for performing noise reduction processing and contrast brightness adjustment on the mold surface illumination pattern obtained by the image data acquisition system.
The image segmentation unit is used for segmenting the processed image, extracting the image of the defect area and performing subsequent processing.
The image texture feature extraction unit calculates a gray level image for the extracted defect image area to obtain a co-occurrence matrix thereof, and then calculates the co-occurrence matrix to obtain partial feature values of the matrix to respectively represent the texture features of the image.
The foreign matter removal control system is connected with the image data processing system and the image acquisition control system, and the output result of the image data processing system can control the foreign matter removal control system to be turned on or turned off. The image acquisition control system can ensure whether the foreign matter is removed completely.
The foreign matter removal control system includes: a blowing device and an alarm. The blowing device consists of an air compressor, a hydraulic pump, a bracket and a blowing pipe. The air compressor and the hydraulic pump are installed above the upper die table. The blowing pipe is arranged on a bracket outside the lower die table, and the blowing pipe is connected with the bracket in a sliding manner. The alarm is arranged outside the fine blanking machine and used for reminding technicians when foreign matters cannot be removed.
The method specifically comprises the following steps of online detecting and removing the foreign matters on the surface of the fine blanking die:
the method comprises the following steps: the camera position controller determines the position and angle of the camera and the combined light source according to the mold. And (3) the metal material enters the stamping, a detection system is started, the displacement sensor determines the end of the stamping through the displacement distance between the upper die table and the lower die table and transmits an electric signal to the camera controller, and the industrial camera is controlled to acquire the surface images of the upper die and the lower die after the parts and the waste are blown.
Step two: and (5) image preprocessing. And (3) carrying out noise reduction processing on the illumination pattern acquired by the industrial camera by adopting a BM3D algorithm, and carrying out contrast brightness adjustment on the image by using a sigmoid function. Namely:
f(x)＝1/(1+e-x) (1)
as x approaches negative infinity, y approaches 0; as x approaches positive infinity, y approaches 1; when x is 1/2, y is 0.
Step three: and acquiring an image defect area. And acquiring a region where the foreign matter is approximately positioned by adopting global threshold processing, and taking the region as an image defect region.
Step four: and extracting the texture features of the defect image. Extracting texture features through a gray level co-occurrence matrix, wherein the expression is as follows:
p＝(i,j,δ,θ)＝{[(x,y),(x+Δx,y+Δy)]|f(x,y)＝i,f(x+Δx,y+Δy)＝j；x＝ 0,1,…,Nx-1；y＝0,1,…,Ny-1} (2)
in the formula: i, j ═ 0, 1, …, L — 1; x, y are pixel coordinates in the image; l is the gray level number of the image; nx and Ny are the number of rows and columns of the image, respectively.
4 directions of 0 degree, 45 degrees, 90 degrees and 135 degrees are selected to calculate the gray level co-occurrence matrix. The four most common features are used to extract the texture features of the image: energy, contrast, correlation, entropy.
Energy (angular second order distance):
Figure BDA0003443961800000121
the energy is the sum of the squares of the elements of the gray level co-occurrence matrix, also known as the angular second order distance. The method is a measure for uniform change of the texture gray level of an image, and reflects the uniform degree of the gray level distribution of the image and the thickness degree of the texture.
Contrast ratio:
Figure BDA0003443961800000122
the contrast is the moment of inertia near the principal diagonal of the gray level co-occurrence matrix, which reflects how the values of the matrix are distributed, reflecting the definition of the image and the depth of texture grooves.
Correlation degree:
Figure BDA0003443961800000131
the correlation represents the similarity of the elements of the space gray level co-occurrence matrix in the row or column direction, and reflects the local gray level correlation of the image.
Entropy:
Figure BDA0003443961800000132
entropy embodies the randomness of image texture. If all the values in the co-occurrence matrix are equal, obtaining a maximum value; if the values in the co-occurrence matrix are not uniform, the values become small.
After the characteristic values of the gray level co-occurrence matrix in all directions are obtained, the mean value and the variance of the characteristic values are calculated to obtain 4 mean values and 4 variances, and therefore the influence of the direction components on the texture characteristics is eliminated.
Step five: and judging whether the foreign matter exists in the surface image of the mold through the minimum distance discrimination function, and determining whether to start a foreign matter removing system. And when no foreign matters remain on the surface of the die, continuously stamping. When foreign matters remain on the surface of the mold, the foreign matter removing system controls the blowing device to perform secondary blowing, after the blowing is finished, the image acquisition control system controls the industrial camera to acquire image data again, and the image data processing system judges whether the removal of the foreign matters on the surface of the mold is finished. When the foreign matter still exists, start the siren, remind the technical staff to inspect the mould.
Example 2:
the overall schematic diagram of the online detection and removal device for the foreign matters on the surface of the fine blanking die is shown in the attached figure 4. The system comprises an image data acquisition system, an image acquisition control system, an image data processing system and a foreign matter removal control system.
The image data acquisition device consists of an industrial camera 3-1, a combined light source 3-2, a sliding table 3-3, a telescopic bracket 3-4 and a guide rail 3-5.
The industrial camera is a WP-UT miniature high-speed camera, and the combined light source is an LED combined light source.
Fig. 4 to 9 are schematic diagrams of an image data acquisition device, an industrial camera 3-1 is fixed on a telescopic bracket 3-4, the telescopic bracket 3-4 is installed on a rotary joint of a sliding table 3-3, the position and the angle are regulated and controlled by the sliding table 3-3, the sliding table 3-3 is in sliding connection with a guide rail 3-5, and the guide rail 3-5 is fixed on the inner walls of two sides of a fine blanking machine. The combined light source 3-2 is fixed at the same angle in front of the industrial camera 3-1. In the working process, the end of stamping can be determined according to the electric signals sent by the displacement sensor 2-1, and then image data of the surface of the upper die 2-2 and the surface of the lower die 2-3 can be obtained according to the industrial cameras 2-11, 2-12, 2-13 and 2-14.
The image acquisition control system is composed of a camera controller 3-6 and a camera position controller 3-7. The camera controller 3-6 is connected with the industrial camera 3-1, the combined light source 3-2 and the displacement sensor 2-1. The displacement sensor 2-1 is located on the outer side of the lower die table 2-4, the displacement distance of the upper die table and the lower die table is measured and then fed back to the camera controller 3-6, and the camera controller 3-6 determines the end of stamping according to the displacement distance so as to control the industrial camera 3-1 to carry out time-delay shooting. The camera position controller 3-7 changes the shooting position and angle of the industrial camera 3-1 and the combined light source 3-2 on the guide rail 3-5 according to different molds.
The image data processing system mainly utilizes a computer, and the computer comprises: the image processing device comprises an image preprocessing unit, an image segmentation unit and an image texture feature extraction unit.
The image preprocessing unit performs noise reduction processing and contrast brightness adjustment on the surface illumination pattern of the upper die 2-2 and the surface illumination pattern of the lower die 2-3 obtained by the industrial camera 3-1.
The image segmentation unit is used for segmenting the processed image, extracting the image of the defect area and performing subsequent processing.
The image texture feature extraction unit calculates a gray level image for the extracted defect image area to obtain a co-occurrence matrix thereof, and then calculates the co-occurrence matrix to obtain partial feature values of the matrix to respectively represent the texture features of the image.
The foreign matter removal control system consists of a blowing device and an alarm 2-5.
The blowing device consists of an air compressor 2-6, a hydraulic pump 2-7, a bracket 2-8 and a blowing pipe 2-9. An air compressor 2-6 and a hydraulic pump 2-7 are mounted above the upper die table 2-10. The injection pipe 2-9 is arranged on a bracket 2-8 at the outer side of the lower die table 2-4, and the injection pipe 2-9 is in sliding connection with the bracket 2-8. The alarm 2-5 is installed outside the fine blanking machine and is used for reminding a technician when foreign matters cannot be removed.
The method specifically comprises the following steps of online detecting and removing the foreign matters on the surface of the fine blanking die:
the method comprises the following steps: the camera position controller 3-7 determines the position and angle of the industrial camera 3-1 and the combined light source 3-2 according to the mold. And (3) the metal material enters the stamping, a detection system is started, the displacement sensor 2-1 determines the end of stamping through the displacement distance between the upper die table and the lower die table and sends an electric signal to the camera controller 3-6, and the industrial camera 3-1 is controlled to acquire the surface images of the upper die and the lower die after the parts and the waste materials are blown.
Step two: and (5) image preprocessing. And (3) carrying out noise reduction processing on the illumination patterns collected by the industrial cameras 2-11, 2-12, 2-13 and 2-14 by adopting a BM3D algorithm, and carrying out contrast brightness adjustment on the images by a sigmoid function. Namely:
f(x)＝1/(1+e-x) (1)
as x approaches negative infinity, y approaches 0; as x approaches positive infinity, y approaches 1; when x is 1/2, y is 0.
Step three: and acquiring an image defect area. And acquiring a region where the foreign matter is approximately positioned by adopting global threshold processing, and taking the region as an image defect region.
Step four: and extracting the texture features of the defect image. Extracting texture features through a gray level co-occurrence matrix, wherein the expression is as follows:
p＝(i,j,δ,θ)＝{[(x,y),(x+Δx,y+Δy)]|f(x,y)＝i,f(x+Δx,y+Δy)＝j；x＝ 0,1,…,Nx-1；y＝0,1,…,Ny-1} (2)
in the formula: i, j ═ 0, 1, …, L — 1; x, y are pixel coordinates in the image; l is the gray level number of the image; nx and Ny are the number of rows and columns of the image, respectively.
4 directions of 0 degree, 45 degrees, 90 degrees and 135 degrees are selected to calculate the gray level co-occurrence matrix. The four most common features are used to extract the texture features of the image: energy, contrast, correlation, entropy.
Energy (angular second order distance):
Figure BDA0003443961800000151
the energy is the sum of the squares of the elements of the gray level co-occurrence matrix, also known as the angular second order distance. The method is a measure for uniform change of the texture gray level of an image, and reflects the uniform degree of the gray level distribution of the image and the thickness degree of the texture.
Contrast ratio:
Figure BDA0003443961800000161
the contrast is the moment of inertia near the principal diagonal of the gray level co-occurrence matrix, which reflects how the values of the matrix are distributed, reflecting the definition of the image and the depth of texture grooves.
Correlation degree:
Figure BDA0003443961800000162
the correlation represents the similarity of the elements of the space gray level co-occurrence matrix in the row or column direction, and reflects the local gray level correlation of the image.
Entropy:
Figure BDA0003443961800000163
entropy embodies the randomness of image texture. If all the values in the co-occurrence matrix are equal, obtaining a maximum value; if the values in the co-occurrence matrix are not uniform, the values become small.
After the characteristic values of the gray level co-occurrence matrix in all directions are obtained, the mean value and the variance of the characteristic values are calculated to obtain 4 mean values and 4 variances, and therefore the influence of the direction components on the texture characteristics is eliminated.
Step five: and judging whether foreign matters exist in the surface images of the upper die 2-2 and the lower die 2-3 or not through a minimum distance discrimination function, and determining whether a foreign matter removing system is started or not. And when no foreign matters remain on the surfaces of the upper die 2-2 and the lower die 2-3, continuously punching. When foreign matters remain on the surfaces of the upper die 2-2 and the lower die 2-3, the foreign matter removing system controls the blowing device to carry out secondary blowing, after the blowing is finished, the image acquisition control system controls the industrial cameras 2-11, 2-12, 2-13 and 2-14 to acquire image data again, and the image data processing system judges whether the foreign matters on the surfaces of the upper die 2-2 and the lower die 2-3 are removed or not. When foreign matter still exists, the alarm 2-5 is started to remind technicians to check the die.
In the description of the present invention, "a plurality" means two or more unless otherwise specified; the terms "upper", "lower", "left", "right", "inner", "outer", "front", "rear", "head", "tail", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the invention. Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
It should be noted that the embodiments of the present invention can be realized by hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided on a carrier medium such as a disk, CD-or DVD-ROM, programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier, for example. The apparatus and its modules of the present invention may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of hardware circuits and software, e.g., firmware.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.

Claims (10)

1. The online detection and removal method for the foreign matters on the surface of the fine blanking die is characterized by comprising the following steps of:
firstly, collecting images of the surfaces of an upper die and a lower die; preprocessing the collected surface images of the upper and lower dies; processing the preprocessed upper and lower die surface images by adopting a global threshold, and determining an area where the foreign matters are located, namely an image defect area;
calculating a gray level image for the extracted image defect area to obtain a co-occurrence matrix; obtaining a part of characteristic values of the matrix, namely texture characteristics of the defect image, by calculating a co-occurrence matrix;
judging whether the image on the surface of the die has foreign matters or not based on the extracted textural features of the defect image through a minimum distance discrimination function, and if not, continuing stamping; when the residual foreign matters exist, turning to the fourth step;
controlling the blowing device to perform secondary blowing, acquiring the image data of the surface of the mold again by using the industrial camera after the blowing is finished, and judging whether the foreign matter on the surface of the mold is removed or not based on the acquired image; and if the foreign matters exist, controlling an alarm to give an alarm.
2. The method for on-line detecting and removing the foreign matters on the surface of the fine blanking die as claimed in claim 1, wherein in the first step, the collecting of the images of the surfaces of the upper die and the lower die comprises:
the camera position controller determines the position and the angle of the camera and the combined light source according to the mould; after the metal material is punched, the displacement sensor determines that punching is finished through the displacement distance of the upper die table and the lower die table and sends an electric signal to the camera controller to control the industrial camera to acquire the surface images of the upper die and the lower die after the parts and the waste materials are blown.
3. The online detection and removal method for foreign matters on the surface of a fine blanking die as claimed in claim 1, wherein the step of collecting the images of the upper and lower die surfaces further comprises the steps of: and controlling an industrial camera to carry out time-delay shooting according to the blowing time of the blowing device to obtain the surface images of the upper die and the lower die.
4. The online detection and removal method for foreign matters on the surface of a fine blanking die as claimed in claim 1, wherein in the first step, the pretreatment of the collected upper and lower die surfaces comprises:
adopting BM3D algorithm to perform noise reduction processing on the collected upper and lower die illumination diagrams, and performing contrast brightness adjustment on the images through a sigmoid function, as follows:
f(x)＝1/(1+e-x)；
as x approaches negative infinity, y approaches 0; as x approaches positive infinity, y approaches 1; when x is 1/2, y is 0.
5. The online detection and removal method for the foreign matters on the surface of the fine blanking die as claimed in claim 1, wherein the texture feature extraction of the defect image in the second step comprises:
(1) 4 directions of theta of 0 degree, 45 degrees, 90 degrees and 135 degrees are selected to calculate the gray level co-occurrence matrix, and the method comprises the following steps:
p＝(i，j，δ，θ)＝{[(x，y)，(x+Δx，y+Δy)]|f(x，y)＝i，f(x+Δx，y+Δy)＝j；x＝0，1，…，Nx-1；y＝0，1，…，Ny-1}；
wherein: i, j ═ 0, 1,. ·, L-1; x, y represent pixel coordinates in the image; l represents the number of gray levels of an image; n is a radical ofx，NyRespectively representing the row number and the column number of the image;
(2) extracting image texture features by adopting energy, contrast, correlation and entropy:
energy:
Figure FDA0003443961790000021
contrast ratio:
Figure FDA0003443961790000022
correlation degree:
Figure FDA0003443961790000023
entropy:
Figure FDA0003443961790000024
(3) and calculating the mean value and the variance of the characteristic values of the gray level co-occurrence matrix in all directions to obtain 4 mean values and 4 variances, and obtaining the characteristics of the defect image.
6. The utility model provides a fine blanking mould surface foreign matter on-line measuring and clearance system which characterized in that, fine blanking mould surface foreign matter on-line measuring and clearance system includes:
the image data acquisition module is connected with the image acquisition control module and is used for acquiring the surface image data of the upper die and the lower die by utilizing an industrial camera;
the image acquisition control module is connected with the fine blanking die and the image data acquisition module and is used for controlling the start and stop of the data acquisition module;
the image data processing module is connected with the image data acquisition module and the foreign matter removal control module; the image segmentation method comprises an image preprocessing unit, an image segmentation unit and an image texture feature extraction unit; the system is used for preprocessing, segmenting and extracting textural features of the acquired surface images of the mold; meanwhile, the system is used for controlling the starting and stopping of the foreign matter removing module;
the foreign matter removal control module is connected with the image data processing module and the image acquisition control module; used for removing foreign matters.
7. The online detection and removal system for foreign matters on the surface of a fine blanking die as claimed in claim 6, wherein the image data processing module comprises:
the image preprocessing unit is used for carrying out noise reduction processing and contrast brightness adjustment on the collected mold surface illumination pattern;
the image segmentation unit is used for segmenting the preprocessed die image and extracting a defect area image;
and the image texture feature extraction unit is used for extracting texture features of the extracted defect image area.
8. An online detection and removal device for foreign matters on the surface of a fine blanking die, which is applied to the online detection and removal method for the foreign matters on the surface of the fine blanking die as claimed in any one of claims 1 to 5, and is characterized in that the online detection and removal device for the foreign matters on the surface of the fine blanking die is provided with:
the device comprises an image acquisition device, an image acquisition control device, a computer and a foreign matter removal control device;
the image acquisition device consists of an industrial camera, a combined light source, a displacement sensor, a sliding table, a telescopic bracket and a guide rail;
the image acquisition control device consists of a camera controller, a displacement sensor and a camera position controller;
the foreign matter removing control device consists of a blowing device and an alarm.
9. The online detecting and removing device for the foreign matters on the surface of the fine blanking die as claimed in claim 8, wherein the online detecting and removing method for the foreign matters on the surface of the fine blanking die further comprises:
the industrial camera is fixed on a telescopic bracket, and the telescopic bracket is arranged on a rotary joint of the sliding table; the sliding table is in sliding connection with the guide rails, and the guide rails are fixed on the inner walls of the two sides of the fine blanking machine; a combined light source with the same angle is fixed in front of the industrial camera;
the camera controller is connected with the industrial camera, the combined light source and the displacement sensor; the displacement sensor is arranged on the outer side of the lower die table;
the blowing device consists of an air compressor, a hydraulic pump, a bracket and a blowing pipe; the air compressor and the hydraulic pump are arranged above the upper die table; the blowing pipe is arranged on a bracket outside the lower die table, and the blowing pipe is connected with the bracket in a sliding manner;
the alarm is arranged outside the fine blanking machine.
10. The fine blanking die surface foreign matter on-line detection and removal device of claim 8, wherein the image acquisition control device comprises:
the displacement sensor is used for measuring the displacement distance of the upper die table and the lower die table;
the camera controller is used for determining the end of stamping according to the displacement distance and controlling the industrial camera to carry out time-delay shooting;
and the camera position controller is used for changing the optimal shooting position and the optimal shooting angle of the camera and the combined light source on the guide rail according to different molds.
CN202111646332.3A 2021-12-29 2021-12-29 Online detection and removal system, method and device for foreign matters on surface of fine blanking die Active CN114371179B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111646332.3A CN114371179B (en) 2021-12-29 2021-12-29 Online detection and removal system, method and device for foreign matters on surface of fine blanking die

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111646332.3A CN114371179B (en) 2021-12-29 2021-12-29 Online detection and removal system, method and device for foreign matters on surface of fine blanking die

Publications (2)

Publication Number Publication Date
CN114371179A true CN114371179A (en) 2022-04-19
CN114371179B CN114371179B (en) 2023-12-26

Family

ID=81141364

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111646332.3A Active CN114371179B (en) 2021-12-29 2021-12-29 Online detection and removal system, method and device for foreign matters on surface of fine blanking die

Country Status (1)

Country Link
CN (1) CN114371179B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050004588A (en) * 2003-07-03 2005-01-12 주식회사 한택 Apparatus and method for detecting defects of display panel
JP2010196189A (en) * 2009-02-24 2010-09-09 Teijin Fibers Ltd Apparatus for examining spinneret with function for removing foreign matter in hole
CN108500081A (en) * 2018-03-27 2018-09-07 重庆长安汽车股份有限公司 Blank surface foreign bodies detection suitable for stamping die clears up system
CN110458176A (en) * 2019-07-11 2019-11-15 中科光绘（上海）科技有限公司 Foreign body intrusion detection method for laser foreign matter remover
CN110480181A (en) * 2018-06-16 2019-11-22 南京理工大学 The target prediction method of foreign matter device is removed based on laser

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050004588A (en) * 2003-07-03 2005-01-12 주식회사 한택 Apparatus and method for detecting defects of display panel
JP2010196189A (en) * 2009-02-24 2010-09-09 Teijin Fibers Ltd Apparatus for examining spinneret with function for removing foreign matter in hole
CN108500081A (en) * 2018-03-27 2018-09-07 重庆长安汽车股份有限公司 Blank surface foreign bodies detection suitable for stamping die clears up system
CN110480181A (en) * 2018-06-16 2019-11-22 南京理工大学 The target prediction method of foreign matter device is removed based on laser
CN110458176A (en) * 2019-07-11 2019-11-15 中科光绘（上海）科技有限公司 Foreign body intrusion detection method for laser foreign matter remover

Also Published As

Publication number Publication date
CN114371179B (en) 2023-12-26

Similar Documents

Publication Publication Date Title
CN106018422B (en) Based on matched special-shaped stamping parts profile defects vision detection system and method
CN108332689A (en) A kind of optical measuring system and method for detection surface roughness and surface damage
WO2007062563A1 (en) On-line automatic inspection method for detecting surface flaws of steel during the pretreatment of the ship steel
CN115184368B (en) Casting defect detection control system
CN102529019B (en) Method for mould detection and protection as well as part detection and picking
CN114279357A (en) Die casting burr size measurement method and system based on machine vision
CN112037203A (en) Side surface defect detection method and system based on complex workpiece outer contour registration
CN111982921A (en) Hole defect detection method and device, conveying platform and storage medium
CN111307819A (en) Wafer edge defect detection system and method
Peng et al. Application of machine vision method in tool wear monitoring
CN109816627B (en) Method for detecting weak and small defect target in ink area of plane glass element
CN108802051B (en) System and method for detecting bubble and crease defects of linear circuit of flexible IC substrate
CN114419437A (en) Workpiece sorting system based on 2D vision and control method and control device thereof
CN114371179B (en) Online detection and removal system, method and device for foreign matters on surface of fine blanking die
CN113705564A (en) Pointer type instrument identification reading method
CN111815575A (en) Bearing steel ball part detection method based on machine vision
CN112763496A (en) Mobile phone battery surface defect detection device and detection method thereof
US6473537B1 (en) Process and system for detecting bend angle
CN117021440A (en) Automatic resin lens pouring method and system based on machine vision
CN116883498A (en) Visual cooperation target feature point positioning method based on gray centroid extraction algorithm
CN113240629B (en) Edge-based image matching narrow-gap weld initial point positioning device and method
CN114354631A (en) Valve blank surface defect detection method based on vision
JP4658779B2 (en) Haze detection method, apparatus, and computer program
CN113793321A (en) Casting surface defect dynamic detection method and device based on machine vision
Ghafar et al. Pre-Forming Inspection System to Detect Deep Drawing Defect Due to Punch-Die Misalignment using Image Processing Technique

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
GR01 Patent grant
GR01 Patent grant