CN112013789B - High-precision part deviation detection system based on 3D vision algorithm - Google Patents
High-precision part deviation detection system based on 3D vision algorithm Download PDFInfo
- Publication number
- CN112013789B CN112013789B CN202011159483.1A CN202011159483A CN112013789B CN 112013789 B CN112013789 B CN 112013789B CN 202011159483 A CN202011159483 A CN 202011159483A CN 112013789 B CN112013789 B CN 112013789B
- Authority
- CN
- China
- Prior art keywords
- central controller
- searchlight
- coordinate set
- outline
- detection
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 97
- 230000007547 defect Effects 0.000 claims abstract description 44
- 230000000007 visual effect Effects 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 65
- 238000000034 method Methods 0.000 claims description 22
- 239000007787 solid Substances 0.000 claims description 20
- 238000005286 illumination Methods 0.000 claims description 7
- 238000013473 artificial intelligence Methods 0.000 claims description 4
- 230000002950 deficient Effects 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- 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
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- 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
- G01N2021/8874—Taking dimensions of defect into account
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Acoustics & Sound (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a high-precision part deviation detection system based on a 3D visual algorithm, which comprises: the detection device comprises a detection box body, a bearing circular table, an ultrasonic detector, a guide rail, a camera, a searchlight and a central controller, wherein the central controller is used for accurately controlling the components and adjusting control parameters, so that the difference of detection results caused by the difference of part bodies is reduced; the central controller establishes model coordinate data according to a 3D algorithm and judges the integrity of the acquired data according to whether the detected shot image has light reflection and adjusts the light brightness, the shooting angle of the searchlight and the position of the searchlight at the guide rail, and the defect detection is performed on qualified part data, so that the defect detection precision is improved.
Description
Technical Field
The invention belongs to the field of part deviation detection systems, and particularly relates to a high-precision part deviation detection system based on a 3D visual algorithm.
Background
With the development of computer science, computers are applied more and more in the industrial field, artificial intelligence, computer vision algorithms and neural network algorithms are gradually mature, so that the application prospect is wider and wider, three-dimensional coordinate information of each point position in a visual field can be collected through a 3D camera, three-dimensional stereo imaging is obtained through restoration intelligence of the 3D vision algorithms, the three-dimensional stereo imaging cannot be easily influenced by external environment and complex light, the technology is more stable, the problem that the traditional two-dimensional experience and safety are poor can be solved, and the three-dimensional stereo imaging method is widely applied to the fields of face recognition and three-dimensional modeling; in industrial development, the traditional part defect detection is usually manual detection, scratches and defects are identified by human eyes, or whether deviation and errors occur in the part is measured according to tools; however, the traditional part defect detection method has the following problems;
1. the manual identification is time-consuming and labor-consuming and is influenced by human factors such as fatigue and personal cognitive factors;
2. for the detection of high-precision parts, the requirement is high, and the error of the traditional detection mode is large;
3. for the detection of high-precision parts, the requirements on detection scenes are high, such as the control of light irradiation intensity; for small defects, the defects can be covered by part reflection caused by high illumination intensity, the defects are too small and difficult to identify, and the traditional detection mode has no accurate control on the problems;
4. for the detection of high-precision parts, the internal defects are difficult to detect, and the traditional detection equipment has no function of identifying the types of the parts, so that different detection methods cannot be implemented for different parts.
Disclosure of Invention
The present invention is to solve the above problems, and therefore the present invention provides a high-precision part deviation detecting system based on a 3D vision algorithm, which includes:
a detection box body for loading a detection component, wherein the inner wall of the detection box body is provided with a temperature sensor;
the bearing circular table is arranged at the bottom of the detection box body and used for bearing the pre-detection part, a clamp is arranged on the upper surface of the bearing circular table and used for clamping the pre-detection part placed on the bearing circular table, a gravity sensor is further arranged in the bearing circular table and used for detecting the weight of the pre-detection part, and the bearing circular table is connected with a motor so as to enable the bearing circular table to rotate under the driving of the motor;
the ultrasonic detector is arranged on the side wall of the detection box body and used for carrying out ultrasonic scanning on the part to be detected, and the ultrasonic detector is connected with the central controller and used for finishing data exchange with the central controller;
the guide rail is arranged on the inner wall of the detection box body;
the camera is arranged on the guide rail so as to enable the camera to slide along the guide rail, and the camera is provided with a movable structure so that the shooting angle can be adjusted;
the searchlight is arranged on the guide rail so that the searchlight can slide along the guide rail, is used for supplementing light to the pre-detection part and has a movable structure so that the illumination angle of the supplementing light can be adjusted;
the central controller is used for processing information, is arranged on the outer wall of the detection box body, is connected with the motor, the ultrasonic detector, the camera and the searchlight and completes data exchange, when the pre-detected part is placed on the bearing circular truncated cone, the central controller controls the camera to start pre-shooting the pre-detected part, judges the maximum height H and the maximum width L of the pre-detected part and calculates an adjusting parameter K according to the following formula,
wherein: h represents the maximum height of the pre-detected part, L represents the maximum width of the pre-detected part, V0 is preset in volume, T represents actual temperature, T0 represents preset temperature, M represents actual part quality, M0 represents preset part quality, and k represents a parameter;
when the central controller carries out pre-shooting, the central controller controls the camera to shoot a preset number of pieces of pre-detection part image information of X0 at a preset position W1, W2 and W3 of the guide rail, and judges the maximum height H of the part and the maximum width L of the pre-detection part by taking the information as a reference;
the central controller adjusts the running power of the motor and detection parameters during defect detection according to the adjusting parameter K, and simultaneously judges whether an ultrasonic detector is used or not according to the appearance type of the part; when the pre-shooting is completed, the central controller controls the motor to be started to drive the bearing circular truncated cone to rotate and control the camera to shoot the pre-detection part, when the bearing circular truncated cone rotates 360 degrees, the central controller completes the acquisition of the outline data of the pre-detection part and establishes the outline coordinate set f (x, y, z), and the type of the outline of the part is judged through the outline coordinate set f (x, y, z).
Further, the central controller needs to perform part identification pre-storage on the central controller before use, and the part identification pre-storage step is as follows:
the method comprises the following steps of firstly, selecting a plurality of sheet-shaped parts of different shapes, shooting the parts and obtaining a shape contour coordinate set f (x, y, z) of the parts;
secondly, the central controller performs artificial intelligence algorithm training on the outline coordinate set f (x, y, z) of the parts to generate sheet shape type part judgment data, so that the central controller recognizes that the corresponding parts are sheet shape types according to the shot images;
and step three, repeating the method of the step one and the method of the step two, performing part identification and pre-storage on the parts of the three-dimensional hollow external shape type and the three-dimensional solid external shape type, generating part judgment data of the three-dimensional hollow external shape type and part judgment data of the three-dimensional solid external shape type, and finally determining a part identification information matrix B (B1, B2 and B3), wherein B1 represents plate-shaped external shape type part judgment data, B2 represents three-dimensional hollow external shape type judgment data, and B3 represents three-dimensional solid external shape type judgment data.
Further, when the central controller determines the external shape of the part, acquiring an external shape profile coordinate set f (x, y, z) of the part, and comparing the external shape profile coordinate set f (x, y, z) of the part with data in the part identification information matrix B (B1, B2, B3), wherein:
when the set f (x, y, z) of the outline coordinates of the part matches the sheet-like outline type part determination data B1, the central controller determines that the part is of the sheet-like outline type;
when the set f (x, y, z) of the outline coordinates of the part matches the three-dimensional hollow outline type part determination data B2, the central controller determines that the part is of the three-dimensional hollow outline type;
when the set of outline coordinates f (x, y, z) of the part matches the solid outline type part determination data B3, the central controller determines that the part is of the solid outline type.
Further, the central controller is used for judging pixel points of image information transmitted by the camera in real time, adjusting the light supplement intensity and the light supplement angle of the searchlight according to the judgment result, determining the number S of the pixel points of the reflective area of the part to be shot on the shot image in real time when the central controller judges, and is internally provided with threshold value parameters S1, S2 and S3 of the pixel points,
when the number of the pixel points S of the reflecting area is smaller than a threshold value parameter S1 of the pixel points, judging that the shot image is normal;
when the number of the reflective area pixel points S is larger than or equal to the pixel point threshold parameter S1 and smaller than the pixel point threshold parameter S2, judging that the first-level reflective area appears in the shot image, and recording a three-dimensional coordinate set Y1(x, Y, z) of the reflective area;
when the number of the reflective area pixel points S is larger than or equal to the pixel point threshold parameter S2 and smaller than the pixel point threshold parameter S3, judging that a second-level reflective area appears in the shot image, and recording a three-dimensional coordinate set Y2 (x, Y, z) of the reflective area;
and when the number S of the pixels of the reflective area is larger than or equal to a pixel threshold parameter S3, judging that a third-level reflective area appears in the shot image, and recording a three-dimensional coordinate set Y3 (x, Y, z) of the reflective area.
Further, a light adjusting matrix D (D1, D2, D3) is arranged inside the central controller, wherein D1 represents first-level light brightness, D2 represents second-level light brightness, and D3 represents third-level light brightness, and a searchlight irradiation position adjusting matrix F (F1, F2... Fn) is further arranged inside the central controller, wherein F1 represents a first position searchlight control information matrix, and F2 represents a second position searchlight control information matrix.. Fn represents an nth position searchlight control information matrix; for the ith position searchlight control information matrix Fi (Fi 1, Fi 2), wherein Fi1 represents the ith position coordinate set Fi 1(x, y, z) which is a preset value, and Fi2 represents the ith position searchlight moving position and shooting angle data which is a preset value; the central controller judges and adjusts the brightness and the irradiation direction of the searchlight according to the pixel points in real time, and during adjustment, the three-dimensional coordinate data Yi (x, y, z) of the light reflection area is compared with data in a searchlight irradiation position adjusting matrix F (F1, F2... Fn), wherein:
if the three-dimensional coordinate data Yi (x, y, z) of the light reflecting area belongs to a first position coordinate set F11 (x, y, z), the central controller calls first position searchlight moving position and shooting angle data F12 to control the searchlight to move to a specified position and the irradiation angle of the searchlight;
if the three-dimensional coordinate data Yi (x, y, z) of the light reflecting area belongs to a second position coordinate set F21 (x, y, z), the central controller calls second position searchlight moving position and shooting angle data F22 to control the searchlight to move to a specified position and the irradiation angle of the searchlight;
...
if the three-dimensional coordinate data Yi (x, y, z) of the light reflecting area belongs to the nth position coordinate set Fn 1(x, y, z), the central controller calls the nth position searchlight moving position and shooting angle data Fn2 to control the searchlight to move to the specified position and the irradiation angle of the searchlight.
Furthermore, when the central controller adjusts the brightness of the light,
when the first grade of light reflecting area appears in the shot image, the central controller adjusts the light
An intensity at a first light level D1;
when the second-level reflecting area appears in the shot image, the central controller adjusts the light
Intensity is at a third light level D2;
when the third-level light reflecting area appears in the shot image, the central controller adjusts the light
The intensity is at a third light level D3.
Further, the central controller has a standard part information matrix Z (Z1, Z2... Zn) preset therein, wherein: z1 represents a first set of three-dimensional coordinates Z1 (x, y, Z), Z2 represents a second set of three-dimensional coordinates Z2 (x, y, Z).. Zn represents an nth set of three-dimensional coordinates of a standard, and the step of the central controller when determining the part defect based on the set of coordinates f (x, y, Z) of the contour of the pre-inspected part is as follows:
the method comprises the steps of firstly, detecting standard parts of a plurality of pre-detected parts, acquiring a three-dimensional coordinate set of the standard parts, establishing a standard part information matrix Z (Z1, Z2... Zn) and storing the standard part information matrix Z (Z1, Z2... Zn) in a central controller;
secondly, processing the image information of the part to be detected, generating an outline coordinate set f (x, y, z) of the part to be detected, and simultaneously calculating an adjusting parameter K of the part;
thirdly, comparing the difference value between the outline coordinate set f (x, y, Z) of the pre-detected part and the corresponding standard part coordinate set Zi (x, y, Z) in the standard part information matrix Z (Z1, Z2... Zn), determining the i-th area difference coordinate set Ci (x, y, Z) i =1, 2.. n, and if the volume range represented by the i-th area difference coordinate set Ci (x, y, Z) exceeds the preset defect comparison threshold position
And Y0 is a preset value, and K is the adjusting parameter K, and the part is judged to be defective.
Further, a camera adjustment matrix J (J1, J2... Jn) is arranged inside the central controller, wherein J1 represents a first control matrix, and J2 represents a second control matrix.. Jn represents an nth control matrix; for the ith control matrix Ji (Ji 1, Ji 2), i =1, 2.. n, where Ji1 represents the ith coordinate range set Ji 1(x, y, z), and Ji2 represents the ith control information;
when the outline coordinate set f (x, y, z) is established, the central controller judges the integrity of the outline coordinate set f (x, y, z), a contrast parameter U is arranged in the central controller, when an outline model represented by the outline coordinate set f (x, y, z) is missing and the missing range exceeds the contrast parameter U, the central controller acquires a defect coordinate set Q (x, y, z) of the missing part, and matches the defect coordinate set Q (x, y, z) with data in the camera adjusting matrix J (J1, J2... Jn),
when matching, when the defect coordinate set Q (x, y, z) belongs to a first coordinate range set J11 (x, y, z), the central controller calls first control information J12 to control the camera to move to a specified position on the guide rail;
when the defect coordinate set Q (x, y, z) belongs to a second coordinate range set J21 (x, y, z), the central controller calls second control information J22 to control the camera to move to a specified position on the guide rail;
...
when the defect coordinate set Q (x, y, z) belongs to the nth coordinate range set Jn 1(x, y, z), the central controller calls nth control information Jn2 to control the camera to move to a designated position on the guide rail.
Further, a motor control matrix D (D1, D2, D3) is arranged inside the central controller, wherein D1 represents first-level motor driving power, D2 represents second-level motor driving power, D3 represents third-level motor driving power, wherein the ith-level motor driving power Di is reduced along with the increase of i, and contrast parameters K01 and K02 are also arranged inside the central controller
When K < K01, the central controller controls the motor to drive the bearing circular table to move at a first-level motor driving power D1;
when K01 is not more than K < K02, the central controller controls the motor to drive the bearing circular table to move with the driving power D2 of the second-level motor;
when K is larger than or equal to K02, the central controller controls the motor to drive the bearing circular table to move with the driving power D3 of the third-level motor.
Furthermore, when the central controller is arranged to control the ultrasonic detector,
when the central controller judges that the pre-detected part is of the flaky shape type, the central controller does not start the ultrasonic detector;
when the central controller judges that the pre-detection part is of a three-dimensional solid shape type, the central controller does not start the ultrasonic detector;
and when the central controller judges that the pre-detected part is in a three-dimensional hollow shape type, the central controller starts the ultrasonic detector to detect the defect of the hollow part of the pre-detected part.
Compared with the prior art, the invention has the technical effects that the invention comprises the following steps: a detection box body,
The device comprises a bearing circular table, an ultrasonic detector, a guide rail, a camera, a searchlight and a central controller, wherein the central controller is used for accurately controlling the components, the height, the width and the weight of a part to be detected are obtained through pre-shooting, the ambient temperature is obtained at the same time, the parameters are applied to the control process, and the difference of detection results caused by part difference is reduced; the central controller controls the camera to shoot the pre-detected part in real time, controls the rotating speed of the circular truncated cone, detects whether a shot image has light reflection and adjusts the light brightness, the shooting angle of the searchlight and the position of the searchlight at the guide rail to ensure the information acquisition precision of the pre-detected part, judges the defect of the generated part outline coordinate set f (x, y, z), acquires the data of the pre-detected part again according to the defective data to ensure the information acquisition integrity of the part, and improves the defect detection precision;
particularly, the central controller of the invention carries out part identification and pre-storage on the algorithm to generate a part identification information matrix B (B1, B2 and B3) so as to judge the type of the part appearance, thereby judging whether an ultrasonic detector is used or not, for solid and sheet parts, the image of the solid and sheet parts can be processed by a 3D vision algorithm to obtain the characteristics, for hollow parts, the internal defects of the hollow parts need to be detected by the ultrasonic detector, and the detection breadth and the applicability of the invention to the parts are improved.
Particularly, the central controller of the invention determines the number S of the reflective area pixels of the part to be shot on the shot image in real time, generates the three-dimensional coordinate set Yi (x, y, z) of the reflective area, and adjusts the position of the searchlight and the illumination intensity of the searchlight through the three-dimensional coordinate set Yi (x, y, z) of the reflective area, so that the defect of the 3D data acquisition of the part to be detected due to the fact that the defect position is covered by reflection of light in part of the part to be detected is avoided, and the accuracy of the defect detection is indirectly improved by improving the accuracy of the data acquisition process.
In particular, the central controller of the invention is internally provided with a light adjusting matrix D (D1, D2, D3) and a searchlight irradiation position adjusting matrix F (F1, F2... Fn), which are preset values, and acquires adjusting data from the light adjusting matrix D (D1, D2, D3) and the searchlight irradiation position adjusting matrix F (F1, F2... Fn) according to a three-dimensional coordinate set Yi (x, y, z), so that the processing process is faster and easier to implement, the position of the searchlight can be accurately adjusted according to the light reflection area of the part, and the data integrity and accuracy of the whole part acquiring process are improved.
Particularly, the image information of the pre-detected part is processed through a 3D vision algorithm to generate a part outline coordinate set f (x, y, z), and the part outline coordinate set f (x, y, z) is compared with the outline coordinate set f (x, y, z) of the standard part on the basis to determine the defects of the part.
Particularly, the method judges the real-time integrity of the acquired outline coordinate set f (x, y, z), acquires the incomplete part defect coordinate set Q (x, y, z) for incomplete part information, adjusts the position of a camera according to information in a camera adjusting matrix J (J1, J2... Jn), and repeats the part information acquisition process again, so that the more accurately acquired part information is more complete and accurate, and the accuracy and the integrity of a final detection result are indirectly improved.
Particularly, the rotating speed of the motor is controlled according to the adjusting parameter K, so that the rotating speed of the bearing disc is adjusted, the height, the width and the quality information of the parts contained in the parameter K influence the acquiring process of the data of the parts, if the maximum height H and the maximum width L are larger under the condition that other conditions are not changed, the K is overlarge, and if the quality of the parts is smaller under the condition that other conditions are not changed, the parts have more hollow structures or protruding structures, the K is larger, the rotating speed of the disc is adjusted to be slow for the parts with the larger adjusting parameter K, so that the central controller can process the image information of the parts, the processor can process the image information of the parts for enough time, the camera can acquire the characteristics of the parts more fully, and the information acquiring precision is improved.
Drawings
FIG. 1 is a schematic structural diagram of a high-precision part deviation detection system based on a 3D vision algorithm according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a detection box guide rail arrangement of a high-precision part deviation detection system based on a 3D vision algorithm according to an embodiment of the present invention.
Detailed Description
The above and further features and advantages of the present invention are described in more detail below with reference to the accompanying drawings.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are only for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Referring to fig. 1 and fig. 2, a schematic structural diagram of a high-precision part deviation detecting system based on a 3D vision algorithm and a schematic layout diagram of a box rail of the high-precision part deviation detecting system based on the 3D vision algorithm provided in an embodiment of the present invention are shown, where the high-precision part deviation detecting system based on the 3D vision algorithm in the embodiment includes:
a detection box body 1 for loading detection components, the inner wall of which is provided with a temperature sensor 4;
the bearing circular table 2 is arranged at the bottom of the detection box body 1 and used for bearing the pre-detection part, a clamp 22 is arranged on the upper surface of the bearing circular table and used for clamping the pre-detection part placed on the bearing circular table, a gravity sensor 21 is further arranged in the bearing circular table and used for detecting the weight of the pre-detection part, and the bearing circular table is connected with a motor (not shown in the figure) so as to enable the bearing circular table to rotate under the driving of the motor;
the ultrasonic detector 3 is arranged on the side wall of the detection box body 1 and used for carrying out ultrasonic scanning on the part to be detected, and the ultrasonic detector is connected with the central controller and used for finishing data exchange with the central controller;
the guide rail 5 is arranged on the inner wall of the detection box body;
a camera 6 movably disposed on the guide rail 5 so that the camera 6 slides along the guide rail 5, the camera 6 having a movable structure so that it can adjust a photographing angle, the camera being movable to a designated position under the control of a central controller 9;
the searchlight 7 is movably arranged on the guide rail 5 so that the searchlight 7 slides along the guide rail 5, the searchlight 7 is used for supplementing light for a pre-detection part and has a movable structure so that the illumination angle of the supplement light can be adjusted, and the searchlight 7 can move to a specified position under the control of the central controller 9;
the illuminating lamp 8 is fixedly arranged at the top of the detection box body 1 and used for providing illumination for the detection box body;
a central controller 9 for processing information, which is arranged on the outer wall of the detection box body, is connected with the motor, the ultrasonic detector, the camera and the searchlight and completes data exchange, when the pre-detection part is placed on the bearing circular truncated cone, the central controller controls the camera to start pre-shooting the pre-detection part, judges the maximum height H and the maximum width L of the pre-detection part, and calculates an adjusting parameter K according to the following formula,
wherein: h represents the maximum height of the pre-detected part, L represents the maximum width of the pre-detected part, V0 is preset in volume, T represents actual temperature, T0 represents preset temperature, M represents actual part quality, M0 represents preset part quality, and k represents a parameter;
the central controller adjusts the running power of the motor and detection parameters during defect detection according to the adjusting parameter K, and simultaneously judges whether an ultrasonic detector is used or not according to the appearance type of the part; when the pre-shooting is completed, the central controller controls the motor to be started to drive the bearing circular truncated cone to rotate and control the camera to shoot the pre-detection part, when the bearing circular truncated cone rotates 360 degrees, the central controller completes the acquisition of the outline data of the pre-detection part and establishes the outline coordinate set f (x, y, z), and the type of the outline of the part is judged through the outline coordinate set f (x, y, z).
Specifically, the central controller needs to perform part identification pre-storage on the part before use, and the part identification pre-storage step is as follows:
the method comprises the following steps of firstly, selecting a plurality of sheet-shaped parts of different shapes, shooting the parts and obtaining a shape contour coordinate set f (x, y, z) of the parts;
secondly, the central controller performs artificial intelligence algorithm training on the outline coordinate set f (x, y, z) of the parts to generate sheet shape type part judgment data, so that the central controller recognizes that the corresponding parts are sheet shape types according to the shot images;
and step three, repeating the method of the step one and the method of the step two, performing part identification and pre-storage on the parts of the three-dimensional hollow external shape type and the three-dimensional solid external shape type, generating part judgment data of the three-dimensional hollow external shape type and part judgment data of the three-dimensional solid external shape type, and finally determining a part identification information matrix B (B1, B2 and B3), wherein B1 represents plate-shaped external shape type part judgment data, B2 represents three-dimensional hollow external shape type judgment data, and B3 represents three-dimensional solid external shape type judgment data.
Specifically, when the central controller determines the external shape of the part, the external shape profile coordinate set f (x, y, z) of the part is acquired, and the external shape profile coordinate set f (x, y, z) of the part is compared with the data in the part identification information matrix B (B1, B2, B3), wherein:
when the set f (x, y, z) of the outline coordinates of the part matches the sheet-like outline type part determination data B1, the central controller determines that the part is of the sheet-like outline type;
when the set f (x, y, z) of the outline coordinates of the part matches the three-dimensional hollow outline type part determination data B2, the central controller determines that the part is of the three-dimensional hollow outline type;
when the set of outline coordinates f (x, y, z) of the part matches the solid outline type part determination data B3, the central controller determines that the part is of the solid outline type.
Specifically, the central controller performs pixel point judgment on image information transmitted by the camera in real time, adjusts the fill-in light intensity and the fill-in light angle of the searchlight according to the judgment result, determines the number S of the pixel points of the reflective area of the part to be shot on the shot image in real time when the judgment is performed, and sets threshold value parameters S1, S2 and S3 inside the central controller,
when the number of the pixel points S of the reflecting area is smaller than a threshold value parameter S1 of the pixel points, judging that the shot image is normal;
when the number of the reflective area pixel points S is larger than or equal to the pixel point threshold parameter S1 and smaller than the pixel point threshold parameter S2, judging that the first-level reflective area appears in the shot image, and recording a three-dimensional coordinate set Y1(x, Y, z) of the reflective area;
when the number of the reflective area pixel points S is larger than or equal to the pixel point threshold parameter S2 and smaller than the pixel point threshold parameter S3, judging that a second-level reflective area appears in the shot image, and recording a three-dimensional coordinate set Y2 (x, Y, z) of the reflective area;
and when the number S of the pixels of the reflective area is larger than or equal to a pixel threshold parameter S3, judging that a third-level reflective area appears in the shot image, and recording a three-dimensional coordinate set Y3 (x, Y, z) of the reflective area.
Specifically, a light adjusting matrix D (D1, D2, D3) is arranged inside the central controller, wherein D1 represents first-level light brightness, D2 represents second-level light brightness, and D3 represents third-level light brightness, and a searchlight irradiation position adjusting matrix F (F1, F2... Fn) is further arranged inside the central controller, wherein F1 represents a first position searchlight control information matrix, and F2 represents a second position searchlight control information matrix.. Fn represents an nth position searchlight control information matrix; for the ith position searchlight control information matrix Fi (Fi 1, Fi 2), wherein Fi1 represents the ith position coordinate set Fi 1(x, y, z) which is a preset value, and Fi2 represents the ith position searchlight moving position and shooting angle data which is a preset value; the central controller judges and adjusts the brightness and the irradiation direction of the searchlight according to the pixel points in real time, and during adjustment, the three-dimensional coordinate data Yi (x, y, z) of the light reflection area is compared with data in a searchlight irradiation position adjusting matrix F (F1, F2... Fn), wherein:
if the three-dimensional coordinate data Yi (x, y, z) of the light reflecting area belongs to a first position coordinate set F11 (x, y, z), the central controller calls first position searchlight moving position and shooting angle data F12 to control the searchlight to move to a specified position and the irradiation angle of the searchlight;
if the three-dimensional coordinate data Yi (x, y, z) of the light reflecting area belongs to a second position coordinate set F21 (x, y, z), the central controller calls second position searchlight moving position and shooting angle data F22 to control the searchlight to move to a specified position and the irradiation angle of the searchlight;
...
if the three-dimensional coordinate data Yi (x, y, z) of the light reflecting area belongs to the nth position coordinate set Fn 1(x, y, z), the central controller calls the nth position searchlight moving position and shooting angle data Fn2 to control the searchlight to move to the specified position and the irradiation angle of the searchlight.
Specifically, when the central controller adjusts the brightness of the lamp light,
when the first grade of light reflecting area appears in the shot image, the central controller adjusts the light
An intensity at a first light level D1;
when the second-level reflecting area appears in the shot image, the central controller adjusts the light
Intensity is at a third light level D2;
when the third-level light reflecting area appears in the shot image, the central controller adjusts the light
The intensity is at a third light level D3.
Specifically, the central controller is internally preset with a standard part information matrix Z (Z1, Z2... Zn), wherein: z1 represents a first set of three-dimensional coordinates Z1 (x, y, Z), Z2 represents a second set of three-dimensional coordinates Z2 (x, y, Z).. Zn represents an nth set of three-dimensional coordinates of a standard, and the step of the central controller when determining the part defect based on the set of coordinates f (x, y, Z) of the contour of the pre-inspected part is as follows:
the method comprises the steps of firstly, detecting standard parts of a plurality of pre-detected parts, acquiring a three-dimensional coordinate set of the standard parts, establishing a standard part information matrix Z (Z1, Z2... Zn) and storing the standard part information matrix Z (Z1, Z2... Zn) in a central controller;
secondly, processing the image information of the part to be detected, generating an outline coordinate set f (x, y, z) of the part to be detected, and simultaneously calculating an adjusting parameter K of the part;
thirdly, comparing the difference value between the outline coordinate set f (x, y, Z) of the pre-detected part and the corresponding standard part coordinate set Zi (x, y, Z) in the standard part information matrix Z (Z1, Z2... Zn), determining the i-th area difference coordinate set Ci (x, y, Z) i =1, 2.. n, and if the volume range represented by the i-th area difference coordinate set Ci (x, y, Z) exceeds the preset defect comparison threshold position
And Y0 is a preset value, and K is the adjusting parameter K, and the part is judged to be defective.
Specifically, a camera adjustment matrix J (J1, J2... Jn) is arranged inside the central controller, wherein J1 represents a first control matrix, and J2 represents a second control matrix.. Jn represents an nth control matrix; for the ith control matrix Ji (Ji 1, Ji 2), i =1, 2.. n, where Ji1 represents the ith coordinate range set Ji 1(x, y, z), and Ji2 represents the ith control information;
when the outline coordinate set f (x, y, z) is established, the central controller judges the integrity of the outline coordinate set f (x, y, z), a contrast parameter U is arranged in the central controller, when an outline model represented by the outline coordinate set f (x, y, z) is missing and the missing range exceeds the contrast parameter U, the central controller acquires a defect coordinate set Q (x, y, z) of the missing part, and matches the defect coordinate set Q (x, y, z) with data in the camera adjusting matrix J (J1, J2... Jn),
when matching, when the defect coordinate set Q (x, y, z) belongs to a first coordinate range set J11 (x, y, z), the central controller calls first control information J12 to control the camera to move to a specified position on the guide rail;
when the defect coordinate set Q (x, y, z) belongs to a second coordinate range set J21 (x, y, z), the central controller calls second control information J22 to control the camera to move to a specified position on the guide rail;
...
when the defect coordinate set Q (x, y, z) belongs to the nth coordinate range set Jn 1(x, y, z), the central controller calls the nth control information Jn2 to control the camera to move to a specified position on the guide rail.
Specifically, a motor control matrix D (D1, D2, D3) is arranged inside the central controller, wherein D1 represents first-level motor driving power, D2 represents second-level motor driving power, and D3 represents third-level motor driving power, wherein the i-th-level motor driving power Di decreases as i increases, and contrast parameters K01, K02 are also arranged inside the central controller
When K < K01, the central controller controls the motor to drive the bearing circular table to move at a first-level motor driving power D1;
when K01 is not more than K < K02, the central controller controls the motor to drive the bearing circular table to move with the driving power D2 of the second-level motor;
when K is larger than or equal to K02, the central controller controls the motor to drive the bearing circular table to move with the driving power D3 of the third-level motor.
Specifically, when the central controller is provided for controlling the ultrasonic probe,
when the central controller judges that the pre-detected part is of the flaky shape type, the central controller does not start the ultrasonic detector;
when the central controller judges that the pre-detection part is of a three-dimensional solid shape type, the central controller does not start the ultrasonic detector;
and when the central controller judges that the pre-detected part is in a three-dimensional hollow shape type, the central controller starts the ultrasonic detector to detect the defect of the hollow part of the pre-detected part.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (10)
1. A high-precision part deviation detection system based on a 3D vision algorithm is characterized by comprising:
a detection box body for loading a detection component, wherein the inner wall of the detection box body is provided with a temperature sensor;
the bearing circular table is arranged at the bottom of the detection box body and used for bearing the pre-detection part, a clamp is arranged on the upper surface of the bearing circular table and used for clamping the pre-detection part placed on the bearing circular table, a gravity sensor is further arranged in the bearing circular table and used for detecting the weight of the pre-detection part, and the bearing circular table is connected with a motor so as to enable the bearing circular table to rotate under the driving of the motor;
the ultrasonic detector is arranged on the side wall of the detection box body and used for carrying out ultrasonic scanning on the part to be detected, and the ultrasonic detector is connected with the central controller and used for finishing data exchange with the central controller;
the guide rail is arranged on the inner wall of the detection box body;
the camera is movably arranged on the guide rail so as to enable the camera to slide along the guide rail;
the searchlight is movably arranged on the guide rail so as to enable the searchlight to slide along the guide rail, and the searchlight is used for supplementing light for the pre-detection part;
the irradiation lamp is fixedly arranged at the top of the detection box body and used for providing illumination for the detection box body;
the central controller is used for processing information, is arranged on the outer wall of the detection box body, is connected with the motor, the ultrasonic detector, the camera and the searchlight and completes data exchange, when a pre-detection part is placed on the bearing circular truncated cone, the central controller controls the camera to start pre-shooting the pre-detection part, judges the maximum height H and the maximum width L of the pre-detection part, and calculates an adjusting parameter K according to the following formula,
wherein: h represents the maximum height of the pre-detected part, L represents the maximum width of the pre-detected part, V0 is preset in volume, T represents actual temperature, T0 represents preset temperature, M represents actual part quality, M0 represents preset part quality, and k represents a parameter;
the central controller adjusts the running power of the motor and detection parameters during defect detection according to the adjusting parameter K, and simultaneously judges whether an ultrasonic detector is used or not according to the appearance type of the part; when the pre-shooting is completed, the central controller controls the motor to be started to drive the bearing circular truncated cone to rotate and control the camera to shoot the pre-detection part, when the bearing circular truncated cone rotates 360 degrees, the central controller completes the acquisition of the outline data of the pre-detection part and establishes the outline coordinate set f (x, y, z), and the type of the outline of the part is judged through the outline coordinate set f (x, y, z).
2. The 3D vision algorithm-based high-precision part deviation detection system according to claim 1, wherein the central controller needs to perform part identification pre-storage on the part deviation detection system before use, and the part identification pre-storage comprises the following steps:
the method comprises the following steps of firstly, selecting a plurality of sheet-shaped parts of different shapes, shooting the parts and obtaining a shape contour coordinate set f (x, y, z) of the parts;
secondly, the central controller performs artificial intelligence algorithm training on the outline coordinate set f (x, y, z) of the parts to generate sheet shape type part judgment data, so that the central controller recognizes that the corresponding parts are sheet shape types according to the shot images;
and step three, repeating the method of the step one and the method of the step two, performing part identification and pre-storage on the parts of the three-dimensional hollow external shape type and the three-dimensional solid external shape type, generating part judgment data of the three-dimensional hollow external shape type and part judgment data of the three-dimensional solid external shape type, and finally determining a part identification information matrix B (B1, B2 and B3), wherein B1 represents plate-shaped external shape type part judgment data, B2 represents three-dimensional hollow external shape type judgment data, and B3 represents three-dimensional solid external shape type judgment data.
3. A high precision part variation detection system based on 3D vision algorithm as claimed in claim 2, characterized in that when the central controller determines the part shape, it obtains the part shape outline coordinate set f (x, y, z), compares the part shape outline coordinate set f (x, y, z) with the data in the part identification information matrix B (B1, B2, B3), wherein:
when the set f (x, y, z) of the outline coordinates of the part matches the sheet-like outline type part determination data B1, the central controller determines that the part is of the sheet-like outline type;
when the set f (x, y, z) of the outline coordinates of the part matches the three-dimensional hollow outline type part determination data B2, the central controller determines that the part is of the three-dimensional hollow outline type;
when the set of outline coordinates f (x, y, z) of the part matches the solid outline type part determination data B3, the central controller determines that the part is of the solid outline type.
4. The system for detecting the deviation of a high-precision part based on a 3D visual algorithm as claimed in claim 1, wherein the central controller determines pixel points of the image information transmitted by the camera in real time, adjusts the fill-in light intensity and fill-in light angle of the searchlight according to the determination result, determines pixel points S of the reflective area of the part to be shot on the shot image in real time when determining, and sets threshold pixel parameters S1, S2, S3 inside the central controller,
when the number of the pixel points S of the reflecting area is smaller than a threshold value parameter S1 of the pixel points, judging that the shot image is normal;
when the number of the reflective area pixel points S is larger than or equal to the pixel point threshold parameter S1 and smaller than the pixel point threshold parameter S2, judging that the first-level reflective area appears in the shot image, and recording a three-dimensional coordinate set Y1(x, Y, z) of the reflective area;
when the number of the reflective area pixel points S is larger than or equal to the pixel point threshold parameter S2 and smaller than the pixel point threshold parameter S3, judging that a second-level reflective area appears in the shot image, and recording a three-dimensional coordinate set Y2 (x, Y, z) of the reflective area;
and when the number S of the pixels of the reflective area is larger than or equal to a pixel threshold parameter S3, judging that a third-level reflective area appears in the shot image, and recording a three-dimensional coordinate set Y3 (x, Y, z) of the reflective area.
5. A high-precision part deviation detection system based on 3D vision algorithm as claimed in claim 4, characterized in that a light adjustment matrix D (D1, D2, D3) is arranged inside the central controller, wherein D1 represents first level light brightness, D2 represents second level light brightness, D3 represents third level light brightness, and a searchlight illumination position adjustment matrix F (F1, F2... Fn) is further arranged inside the central controller, wherein F1 represents a first position searchlight control information matrix, F2 represents a second position searchlight control information matrix; for the ith position searchlight control information matrix Fi (Fi 1, Fi 2), wherein Fi1 represents the ith position coordinate set Fi 1(x, y, z) which is a preset value, and Fi2 represents the ith position searchlight moving position and shooting angle data which is a preset value; the central controller judges and adjusts the brightness and the irradiation direction of the searchlight according to the pixel points in real time, and during adjustment, the three-dimensional coordinate data Yi (x, y, z) of the light reflection area is compared with data in a searchlight irradiation position adjusting matrix F (F1, F2... Fn), wherein:
if the three-dimensional coordinate data Yi (x, y, z) of the light reflecting area belongs to a first position coordinate set F11 (x, y, z), the central controller calls first position searchlight moving position and shooting angle data F12 to control the searchlight to move to a specified position and the irradiation angle of the searchlight;
if the three-dimensional coordinate data Yi (x, y, z) of the light reflecting area belongs to a second position coordinate set F21 (x, y, z), the central controller calls second position searchlight moving position and shooting angle data F22 to control the searchlight to move to a specified position and the irradiation angle of the searchlight;
...
if the three-dimensional coordinate data Yi (x, y, z) of the light reflecting area belongs to the nth position coordinate set Fn 1(x, y, z), the central controller calls the nth position searchlight moving position and shooting angle data Fn2 to control the searchlight to move to the specified position and the irradiation angle of the searchlight.
6. A high-precision part deviation detecting system based on 3D visual algorithm according to claim 5, wherein when said central controller adjusts the light brightness,
when the first grade of light reflecting area appears in the shot image, the central controller adjusts the light
An intensity at a first light level D1;
when the second-level reflecting area appears in the shot image, the central controller adjusts the light
Intensity is at a third light level D2;
when the third-level light reflecting area appears in the shot image, the central controller adjusts the light
The intensity is at a third light level D3.
7. A high precision part deviation detection system based on 3D vision algorithm as claimed in claim 1, characterized in that said central controller has a standardized part information matrix Z (Z1, Z2... Zn) pre-programmed inside it, where: z1 represents a first set of three-dimensional coordinates Z1 (x, y, Z), Z2 represents a second set of three-dimensional coordinates Z2 (x, y, Z).. Zn represents an nth set of three-dimensional coordinates of a standard, and the step of the central controller when determining the part defect based on the set of coordinates f (x, y, Z) of the contour of the pre-inspected part is as follows:
the method comprises the steps of firstly, detecting standard parts of a plurality of pre-detected parts, acquiring a three-dimensional coordinate set of the standard parts, establishing a standard part information matrix Z (Z1, Z2... Zn) and storing the standard part information matrix Z (Z1, Z2... Zn) in a central controller;
secondly, processing the image information of the part to be detected, generating an outline coordinate set f (x, y, z) of the part to be detected, and simultaneously calculating an adjusting parameter K of the part;
and thirdly, comparing the difference value between the outline coordinate set f (x, Y, Z) of the pre-detected part and a corresponding standard part coordinate set Zi (x, Y, Z) in the standard part information matrix Z (Z1, Z2... Zn), determining the i-th region difference coordinate set Ci (x, Y, Z) i =1, 2.. n, and if the volume range represented by the i-th region difference coordinate set Ci (x, Y, Z) exceeds a preset defect comparison threshold, wherein Y0 is a preset value, and K is the adjusting parameter K, judging that the part is defective.
8. A high precision part deviation detection system based on 3D vision algorithm as claimed in claim 1, characterized in that inside said central controller is provided a camera adjustment matrix J (J1, J2... Jn) where J1 represents the first control matrix and J2 represents the second control matrix.. Jn represents the nth control matrix; for the ith control matrix Ji (Ji 1, Ji 2), i =1, 2.. n, where Ji1 represents the ith coordinate range set Ji 1(x, y, z), and Ji2 represents the ith control information;
when the outline coordinate set f (x, y, z) is established, the central controller judges the integrity of the outline coordinate set f (x, y, z), a contrast parameter U is arranged in the central controller, when an outline model represented by the outline coordinate set f (x, y, z) is missing and the missing range exceeds the contrast parameter U, the central controller acquires a defect coordinate set Q (x, y, z) of the missing part, and matches the defect coordinate set Q (x, y, z) with data in the camera adjusting matrix J (J1, J2... Jn),
when matching, when the defect coordinate set Q (x, y, z) belongs to a first coordinate range set J11 (x, y, z), the central controller calls first control information J12 to control the camera to move to a specified position on the guide rail;
when the defect coordinate set Q (x, y, z) belongs to a second coordinate range set J21 (x, y, z), the central controller calls second control information J22 to control the camera to move to a specified position on the guide rail;
...
when the defect coordinate set Q (x, y, z) belongs to the nth coordinate range set Jn 1(x, y, z), the central controller calls nth control information Jn2 to control the camera to move to a designated position on the guide rail.
9. A high precision part variation detection system based on 3D vision algorithm as claimed in claim 1,
the method is characterized in that a motor control matrix D (D1, D2, D3) is arranged inside the central controller, wherein D1 represents first-level motor driving power, D2 represents second-level motor driving power, D3 represents third-level motor driving power, the ith-level motor driving power Di is reduced along with the increase of i, and contrast parameters K01 and K02 are also arranged inside the central controller
When K < K01, the central controller controls the motor to drive the bearing circular table to move at a first-level motor driving power D1;
when K01 is not more than K < K02, the central controller controls the motor to drive the bearing circular table to move with the driving power D2 of the second-level motor;
when K is larger than or equal to K02, the central controller controls the motor to drive the bearing circular table to move with the driving power D3 of the third-level motor.
10. The 3D vision algorithm-based high-precision part deviation detecting system according to claim 1, wherein the central controller is provided with a central control unit for controlling the ultrasonic detector,
when the central controller judges that the pre-detected part is of the flaky shape type, the central controller does not start the ultrasonic detector;
when the central controller judges that the pre-detection part is of a three-dimensional solid shape type, the central controller does not start the ultrasonic detector;
and when the central controller judges that the pre-detected part is in a three-dimensional hollow shape type, the central controller starts the ultrasonic detector to detect the defect of the hollow part of the pre-detected part.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011159483.1A CN112013789B (en) | 2020-10-27 | 2020-10-27 | High-precision part deviation detection system based on 3D vision algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011159483.1A CN112013789B (en) | 2020-10-27 | 2020-10-27 | High-precision part deviation detection system based on 3D vision algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112013789A CN112013789A (en) | 2020-12-01 |
| CN112013789B true CN112013789B (en) | 2021-04-06 |
Family
ID=73528284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011159483.1A Active CN112013789B (en) | 2020-10-27 | 2020-10-27 | High-precision part deviation detection system based on 3D vision algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112013789B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359266B (en) * | 2022-03-04 | 2022-06-28 | 成都创像科技有限公司 | Method for detecting detected part through visual detection equipment and visual detection equipment |
| CN116168375B (en) * | 2022-12-29 | 2023-07-04 | 中汽传媒(天津)有限公司 | Intelligent identification method and system for automobile parts |
| CN116805311B (en) * | 2023-08-18 | 2023-11-07 | 长春师范大学 | Automobile part surface defect monitoring method based on robot vision |
-
2020
- 2020-10-27 CN CN202011159483.1A patent/CN112013789B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112013789A (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112013789B (en) | High-precision part deviation detection system based on 3D vision algorithm | |
| CN111928930B (en) | 3D visual detection system based on structured light imaging | |
| CN111007073B (en) | Method and system for online detection of part defects in additive manufacturing process | |
| CN111929309B (en) | Cast part appearance defect detection method and system based on machine vision | |
| CN109030498B (en) | Visual detection device and method for blade knife lines and surface defects | |
| CN112067555B (en) | Part detection system capable of automatically visually identifying part types | |
| CN101660894B (en) | Device and method for multi-vision visual detection based on parallel light illumination | |
| CN111982921B (en) | Method and device for detecting hole defects, conveying platform and storage medium | |
| Saeed et al. | Weld pool surface depth measurement using a calibrated camera and structured light | |
| CN105675610A (en) | Online detection system for object surface texture characteristics and working principle | |
| CN105571502A (en) | Measuring method of weld gap in friction-stir welding | |
| CN112097683B (en) | 3D high-precision detection system based on laser scanning imaging | |
| US20160063691A1 (en) | Plenoptic cameras in manufacturing systems | |
| CN107345789A (en) | A kind of pcb board hole location detecting device and method | |
| CN110966956A (en) | Binocular vision-based three-dimensional detection device and method | |
| CN113467067B (en) | Automatic focusing method and device of microscopic imaging system based on multi-image area relation | |
| CN112067626B (en) | 3D visual detection system based on structured light imaging | |
| CN112435252B (en) | Warhead fragment perforation and pit detection method | |
| FI129042B (en) | Machine vision system with a computer generated virtual reference object | |
| CN113935971A (en) | Method and device for detecting surface defects of composite material | |
| CN111928797B (en) | 3D high-precision detection system based on laser scanning imaging | |
| CN108335332A (en) | A kind of axial workpiece central axes measurement method based on binocular vision | |
| CN104008366A (en) | 3D intelligent recognition method and system for biology | |
| CN110657750B (en) | Detection system and method for passivation of cutting edge of cutter | |
| CN113552133A (en) | Cell skirt edge cracking detection method and visual detection device |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230403 Address after: 512200 No. 3, Paradise Avenue, Lechang industrial transfer industrial park, Lechang City, Shaoguan City, Guangdong Province Patentee after: GUANGDONG COYO PRECISION MACHINERY MANUFACTURING CO.,LTD. Address before: 261000 Yuqing community, Xincheng street, high tech Zone, Weifang City, Shandong Province Patentee before: Shandong Haide Intelligent Technology Co.,Ltd. Patentee before: Beijing burns Intelligent Technology Co.,Ltd. |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A high-precision component deviation detection system based on 3D vision algorithm Effective date of registration: 20231031 Granted publication date: 20210406 Pledgee: Guangdong Lechang Rural Commercial Bank Co.,Ltd. Pledgor: GUANGDONG COYO PRECISION MACHINERY MANUFACTURING CO.,LTD. Registration number: Y2023980063317 |