CN113504239A - Quality control data analysis method - Google Patents
Quality control data analysis method Download PDFInfo
- Publication number
- CN113504239A CN113504239A CN202110647600.7A CN202110647600A CN113504239A CN 113504239 A CN113504239 A CN 113504239A CN 202110647600 A CN202110647600 A CN 202110647600A CN 113504239 A CN113504239 A CN 113504239A
- Authority
- CN
- China
- Prior art keywords
- detection
- welding seam
- image
- quality
- welding
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000003908 quality control method Methods 0.000 title claims abstract description 16
- 238000007405 data analysis Methods 0.000 title claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 122
- 238000003466 welding Methods 0.000 claims abstract description 85
- 230000008859 change Effects 0.000 claims abstract description 11
- 238000004519 manufacturing process Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 8
- 238000009795 derivation Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000033001 locomotion Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 6
- 230000006378 damage Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000006748 scratching Methods 0.000 description 3
- 230000002393 scratching effect Effects 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011895 specific detection Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 229910000881 Cu alloy Inorganic materials 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007373 indentation Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Laser Beam Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a data analysis method for quality control of welded part product quality in automobile production, which comprises the steps of collecting a welding seam macroscopic image by a detection camera, detecting a welding seam contour and planning a detection path according to the contour; acquiring a welding seam microscopic image along a detection path, calculating the width of a welding seam and the change rate of the width of the welding seam, and detecting holes on the welding seam; the laser ranging sensor measures the distance along the detection path, calculates the roughness of the welding seam, detects welding burrs and verifies whether the detection result of the hole is accurate or not; and finally, analyzing and controlling the quality of each detected parameter. The invention overcomes the problems of single detection item and inaccurate detection in the prior art, ensures good control of the quality of the automobile welding parts and ensures the quality of the whole automobile production.
Description
Technical Field
The invention belongs to the technical field of quality control data analysis, and particularly relates to a quality control data analysis method which is used for quality control of welding quality in automobile production.
Background
The welding plays a vital role in vehicle production, and is widely applied to each link in the vehicle production, and the appearance of a welding spot or a welding seam requires shallow and smooth surface indentation and uniform transition without obvious shoulder or local extruded surface bulge; the outer surface has no obvious annular or radial cracks, and also has no molten, burnt or adhered copper alloy, and the welding core has regular and uniform shape, no overproof cracks, shrinkage cavities and other internal defects, no obvious change of the metal structure and mechanical property of a heat affected zone and the like when viewed from the inside.
In the prior art, various weld detection means have appeared, such as a machine vision-based weld detection method, an X-ray-based weld detection method, an ultrasonic-based weld detection method, and an optical-device-based weld detection method. However, the detection means have the defects of complex detection means, insufficient detection precision, harm to human bodies and the like more importantly, the detection means have single detection items, cannot detect weld seams comprehensively, cannot realize good control of welding quality in automobile production, and restricts the development of the automobile industry.
Disclosure of Invention
In order to solve the technical problem, the invention provides a quality control data analysis method for quality control of welded part product quality in automobile production, which comprises the following steps:
s1, collecting a macroscopic image of the welding seam by the detection camera, detecting to obtain the welding seam outline, comparing the welding seam outline with the standard welding seam shape, calculating the similarity, judging whether the welding seam outline is qualified or not, and planning a detection path according to the detected outline;
s2, acquiring a welding seam microscopic image along a detection path, calculating the width and the width change rate of the welding seam according to the microscopic image, and detecting holes on the welding seam;
s3, the laser ranging sensor measures the distance along the detection path, calculates the roughness of the welding seam according to the distance measurement value, detects the welding burr, and verifies whether the detection result of the hole in the step S2 is accurate;
and S4, analyzing the detected parameters, and managing and controlling the quality of the welding parts according to the analysis result.
Optionally, step S1 specifically includes the following steps:
s1-1: positioning the welded component to be detected on a positioning device matched with the welded component;
s1-2: unifying coordinate systems of the detection camera and the laser ranging sensor, and unifying the coordinate systems of the detection camera and the laser ranging sensor into a world coordinate system;
s1-3: calibrating the detection system to obtain internal parameters of the detection camera and obtain translation matrix parameters and rotation matrix parameters between the detection camera and the laser ranging sensor;
s1-4: a macroscopic image of the entire part to be inspected is taken while the entire part can be seen within the inspection camera field of view.
Alternatively, in step S2, after the width direction of the weld occupies two thirds of the width of the field of view, a microscopic image of the weld is acquired along the detection path.
Optionally, in step S2, the controller controls the detection camera to move at a fixed speed on the detection path, and during the movement, the detection camera captures the weld image at a fixed frequency, where the moving speed is proportional to the capturing frequency, so that two adjacent front and back images are at least partially overlapped.
Optionally, in step S2, after the image of the weld is captured, an image processing algorithm is used to detect whether a hole appears in the weld, calculate the width of the weld, calculate the change rate of the width of the weld, and associate a specific image with a specific position on the path to achieve fault location; when the holes are detected, the median filtering is firstly carried out on the image, then the image is sharpened, and then the histogram threshold segmentation algorithm is adopted for processing to determine whether the holes appear in the welding line.
Optionally, in step S3, when it is detected that the result of the laser ranging suddenly increases and the increase value exceeds a threshold value, it is determined that there is a hole, the hole acquired by the image is verified, and it is verified whether the image detection result is accurate.
Optionally, in step S3, after the laser ranging data of the entire contour is obtained, curve fitting is performed on the distance point cloud data, differential derivation operation is performed on the curve, and when the differential derivation result at a certain position is higher than a certain threshold, it is determined that a relatively sharp burr exists in the weld at the position.
Optionally, in step S4, after the parameter detection is completed, the data items are collected and grouped, each group of data is drawn into a histogram, a quality distribution state is obtained according to the distribution condition of the statistical data, and the quality fluctuation is analyzed to determine and predict the product quality and the reject ratio.
The invention has the beneficial effects that:
1. the method can simultaneously detect the welding seam profile, the welding seam width change rate, holes on the welding seam, the welding seam roughness and welding burrs, verify whether the detection result of the holes is accurate or not, overcome the problem of single detection item in the prior art, and comprehensively and accurately detect the welding seam.
2. Meanwhile, macroscopic image detection, microscopic image detection and laser ranging detection are carried out on the welding seam, and the three are mutually matched and verified, so that the effectiveness and the accuracy of detection are improved.
3. The macroscopic image detection provides a detection path for microscopic image detection and laser ranging detection, fault location can be achieved, and the measurement efficiency can be improved.
4. By carrying out differential derivation operation on the fitting curve of the laser ranging result, whether burrs appear on the welding line or not is detected, cutting, scratching or scratching workers or consumers and the like are avoided, and damage to parts assembled with the welding line can be caused.
5. The hole detection efficiency is high by adopting an image processing mode, the detection speed is high, but false detection may exist, so that the data of laser ranging is adopted to verify the hole detection efficiency, the false judgment is avoided on the basis of ensuring the detection speed, and the accuracy of hole detection can be ensured while the detection efficiency is ensured.
6. The moving speed of the detection camera is in direct proportion to the shooting frequency, so that at least part of two adjacent front and back images are overlapped, the images are clear, and the problems of shaking, blurring, ghosting and the like do not occur.
Drawings
FIG. 1 is a flow chart of a quality control data analysis method;
fig. 2 shows a flowchart of the quality control data analysis method step S1.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention, are within the scope of the invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, only for the purpose of facilitating description of the present invention and simplifying description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Example 1
After the welding of the automobile parts is completed, positioning devices, such as a positioning seat, a positioning frame, a positioning fixture and the like, which are correspondingly matched with the welded automobile parts are arranged according to the shapes of the welded automobile parts, so that the welded automobile parts can be stably positioned, and the subsequent weld joint detection is facilitated.
The welding seam detection device is arranged right above the positioning device and specifically comprises a detection camera, a laser ranging sensor, a three-dimensional mobile support structure of the detection camera, a two-dimensional mobile support structure of the laser ranging sensor and a controller, and the detection camera is preferably realized by adopting a high-precision CCD camera so as to facilitate subsequent image processing. The detection camera is arranged on the detection camera three-dimensional moving support structure, the detection camera three-dimensional moving support structure can flexibly move in an XYZ three-dimensional space above the automobile part to be detected, and moving position information can be fed back to the controller.
The laser ranging sensor is arranged on the two-dimensional moving support structure of the laser ranging sensor, can move in an XY two-dimensional plane above the automobile part, and feeds back moving position information to the controller.
In the moving process of the detection camera and the laser ranging sensor, the controller can control the motion process and the track of the detection camera and the laser ranging sensor, and the controller also processes and analyzes detection data of the detection camera and the laser ranging sensor to obtain an automobile welding seam detection result.
As shown in fig. 2, when the detection is started, the welded automobile part to be detected is first positioned on the positioning device matched with the welded automobile part, and preferably, the welded automobile part is positioned by a positioning pin or clamped by a clamping device such as a clamp, so that the welded automobile part is stable during the detection, and the stability of the detection is ensured.
For example, after the engine cover assembly is welded, the engine cover assembly positioning seat is used for positioning the engine cover assembly, the engine cover assembly positioning seat comprises a bottom plate, a plurality of positioning blocks are arranged on the bottom plate, the shapes of the positioning blocks are matched with the shapes of corresponding areas of the engine cover, a clamping structure corresponding to the positions of the positioning blocks is further arranged above the positioning blocks, and the engine cover assembly is firmly positioned on the engine cover assembly positioning seat.
Before the detection starts, coordinate systems of the detection camera and the laser ranging sensor are unified, and the coordinate systems of the detection camera and the laser ranging sensor are unified into a world coordinate system so as to facilitate subsequent control, calculation and analysis. Meanwhile, in the image measuring process and machine vision application, in order to determine the correlation between the three-dimensional geometric position of a certain point on the surface of an object in space and the corresponding point in the image, geometric models of camera imaging must be established, and the geometric model parameters are camera parameters so as to facilitate subsequent calculation and analysis.
Preferably, a checkerboard calibration board can be adopted, and a span-friend calibration algorithm is adopted to calibrate a detection camera of the detection system, so that internal parameters such as distortion of the detection camera are obtained, and translation matrix parameters and rotation matrix parameters of the detection camera and the laser ranging sensor are obtained.
The specific detection steps are as shown in fig. 1, after the preliminary preparation work is completed, the specific detection of the welding seam is started, the controller controls the detection camera to move in the Z-axis direction, namely the vertical direction, until the whole automobile part to be detected can be seen in the field of view, the movement is stopped, then the macroscopic image of the whole part is shot, an image processing algorithm is adopted to obtain the contour of the welding seam, the similarity calculation is carried out on the contour of the welding seam and the ideal contour of the welding seam, and whether the contour of the welding seam is qualified or not is judged.
Preferably, an edge detection algorithm is adopted to extract the contour of the welding seam, and specifically, Sobel operators, Roberts operators, Laplacian operators, Canny operators and other operators can be adopted to carry out detection.
And after the welding seam profile is obtained, the controller plans to obtain a subsequent detection path according to the welding seam profile obtained in the previous step and the shape and the trend of the welding seam profile. After obtaining the detection path, the controller controls the detection camera to move in the Z-axis direction, i.e. the vertical direction, so that the detection camera can shoot the detailed structure of the weld joint, preferably, when the width direction of the weld joint occupies two thirds of the field of view of the detection camera, the controller stops moving the detection camera in the Z-axis direction, and acquires the microscopic image of the weld joint along the detection path.
Then, the detection camera is moved in the XY plane according to the detection path obtained above, and the controller controls the three-dimensional moving support structure of the detection camera to move the detection camera on the detection path at a fixed speed, and the detection camera shoots the welding seam image at a fixed frequency during the movement. The moving speed is in direct proportion to the shooting frequency, the shooting frequency is also higher when the moving speed is higher, and the shooting frequency is also lower when the moving speed is lower, so that two adjacent front and back images are at least partially overlapped, the images are clear, and the problems of shaking, blurring, ghosting and the like are avoided.
After the series of images of the welding seam are shot, an image processing algorithm is adopted to detect whether the welding seam has holes or not, calculate the width of the welding seam, calculate the change rate of the width of the welding seam at the same time, and correlate the specific image with the specific position on the path so as to facilitate subsequent fault location.
When the hole detection is carried out, the median filtering is carried out on the image, then the image is sharpened, and then the histogram threshold segmentation algorithm is adopted for processing to obtain the hole image. If the welding seam is too narrow or too wide or the width of the welding seam changes too fast, the problem of welding quality is solved, so that the width of the welding seam is calculated by adopting the distance of pixels, the change rate of the width of the welding seam is judged according to the tangent of the edge of the welding seam, and the welding quality is judged by synthesizing the parameters.
After the detection is finished, the controller controls the detection camera to exit from the three-dimensional space above the automobile part, then the controller controls the two-dimensional movement supporting structure of the laser ranging sensor to drive the laser ranging sensor to move in the two-dimensional plane, the moving path is the detection path, the distance data of the welding line at the specific position on the detection path is obtained, the roughness of the welding line is calculated according to the distance data, whether burrs exist in the welding line is detected, and the detected hole is verified and verified during image detection.
Specifically, although the hole detection efficiency is high and the detection speed is high by adopting the image processing mode, the hole detection is realized by adopting the image processing mode during the image detection, the shape of the hole is possibly similar to that of a welding spot, and the situation that the welding spot is mistakenly judged as the hole exists, so that the laser ranging data is adopted to verify the hole, and the misjudgment is avoided on the basis of ensuring the detection speed. The specific verification principle and the specific verification method are that because the distance measurement result obtained by the laser distance measurement sensor is very large in contrast with the normal distance measurement result of the welding seam at the position of the hole of the welding seam, when the sudden change of the laser distance measurement result is detected, more specifically, the laser distance measurement result is suddenly increased, and the increased value exceeds the moving threshold value, the hole is judged to exist at the position, and the detection result is adopted to verify and verify the hole result detected by the image.
On the basis of obtaining laser ranging data of the whole contour, curve fitting is carried out on the distance point cloud data, differential derivation operation is carried out on a curve, when the differential derivation result at a certain position is higher than a certain threshold value, it is judged that sharp burrs exist in a welding seam at the position, injury possibly occurs to a contacter, such as cutting, scratching workers or consumers, and damage possibly occurs to parts assembled with the welding seam, therefore, the welding seam is detected through the laser ranging result, subsequent processing is carried out after detection, and hidden dangers are eliminated.
After the detection of each item is completed, the conditions of the contour, the width change rate, the holes, the roughness and the burrs of the welding line are obtained, the specific position of the welding line can be positioned, the detected holes are verified, each parameter of the welding line is ensured to be accurately detected, and the technical problems that the detection project is single and not accurate enough in the prior art are solved. Through the analysis to above-mentioned detected data, guaranteed the good management and control to the quality of car welded part, guaranteed the quality of whole car production.
Specifically, various data are collected and grouped, each group of data is drawn into a histogram, and according to the distribution condition of statistical data, the research on the production process and the quality distribution state of a product, the investigation on engineering capacity, the analysis on control capacity and the like are carried out. And the product quality condition can be predicted and monitored, and the quality fluctuation can be analyzed. And (3) processing the collected apparent disorder data by using the histogram to reflect the distribution condition of the product quality, and judging and predicting the product quality and the reject ratio. The data features that can be found through the histogram are: the distribution state of the data, the center position of the data, the size of the data discrete degree, and the relationship between the data and the specification. By these data characteristics, information on the quality status of the process can be transmitted more intuitively, the state of quality fluctuation can be found, and by studying the state of quality fluctuation, the status of the process can be grasped, thereby determining where to concentrate the force to perform quality improvement work.
Example 2
The embodiment is further improved on the basis of embodiment 1, and common parts of the technical solutions are not described herein again. In order to improve the quality of image acquisition, an annular light source matched with the detection camera is arranged on the three-dimensional moving support structure of the detection camera, the annular light source is an LED light source, and the three-dimensional moving support structure has the advantages of adjustable brightness, low temperature, balance, no flicker and no shadow, and can be added with a polaroid in a special embedded structure.
Example 3
The present embodiment is further improved on the basis of embodiment 1 or embodiment 2, and common parts of the technical solutions are not described herein again. Due to the influence of factors such as the emitting power of the semiconductor laser, the receiving and transmitting distance, and the like, the intensity of the optical signal received by the receiving circuit can be greatly changed, and if proper calibration is not carried out, the normal measurement result can be influenced. Therefore, the laser ranging sensor is provided with a temperature compensation circuit for reducing the influence of the ambient temperature on the laser ranging.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A quality control data analysis method is used for quality control of welded part product quality in automobile production and is characterized by comprising the following steps:
s1, collecting a macroscopic image of the welding seam by the detection camera, detecting to obtain the welding seam outline, comparing the welding seam outline with the standard welding seam shape, calculating the similarity, judging whether the welding seam outline is qualified or not, and planning a detection path according to the detected outline;
s2, acquiring a welding seam microscopic image along a detection path, calculating the width and the width change rate of the welding seam according to the microscopic image, and detecting holes on the welding seam;
s3, the laser ranging sensor measures the distance along the detection path, calculates the roughness of the welding seam according to the distance measurement value, detects the welding burr, and verifies whether the detection result of the hole in the step S2 is accurate;
and S4, analyzing the detected parameters, and managing and controlling the quality of the welding parts according to the analysis result.
2. The method of claim 1, wherein step S1 specifically includes the following steps:
s1-1: positioning the welded component to be detected on a positioning device matched with the welded component;
s1-2: unifying coordinate systems of the detection camera and the laser ranging sensor, and unifying the coordinate systems of the detection camera and the laser ranging sensor into a world coordinate system;
s1-3: calibrating the detection system to obtain internal parameters of the detection camera and obtain translation matrix parameters and rotation matrix parameters between the detection camera and the laser ranging sensor;
s1-4: a macroscopic image of the entire part to be inspected is taken while the entire part can be seen within the inspection camera field of view.
3. The quality control data analysis method according to claim 1 or 2, wherein in step S2, after the width direction of the weld occupies two thirds of the width of the field of view, a microscopic image of the weld is acquired along the detection path.
4. The quality control data analysis method according to claim 3, wherein in step S2, the controller is configured to control the detection camera to move at a fixed speed on the detection path, and during the movement, the detection camera captures the weld image at a fixed frequency, and the moving speed is proportional to the capturing frequency, so that two adjacent front and back images at least partially overlap.
5. The quality control data analysis method according to claim 4, wherein in step S2, after the image of the weld is captured, an image processing algorithm is adopted to detect whether the weld has a hole or not, calculate the width of the weld, calculate the change rate of the width of the weld, and associate a specific image with a specific position on the path to realize fault location; when the holes are detected, the median filtering is firstly carried out on the image, then the image is sharpened, and then the histogram threshold segmentation algorithm is adopted for processing to determine whether the holes appear in the welding line.
6. The method as claimed in claim 5, wherein in step S3, when it is detected that the result of laser ranging suddenly increases and the increase value exceeds a certain threshold, it is determined that there is a hole, the hole acquired by the image is verified, and it is verified whether the result of image detection is accurate.
7. The method for analyzing quality control data according to claim 6, wherein in step S3, after obtaining the laser ranging data of the entire profile, curve fitting is performed on the distance point cloud data, and differential derivation operation is performed on the curve, and when the differential derivation result at a certain position is higher than a certain threshold, it is determined that a sharp burr exists in the weld at the position.
8. The method as claimed in claim 1, wherein in step S4, after the parameter detection is completed, the data are collected and grouped, each group of data is drawn into a histogram, the quality distribution status is obtained according to the distribution of statistical data, and the quality fluctuation is analyzed to determine and predict the product quality and the failure rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110647600.7A CN113504239B (en) | 2021-06-10 | 2021-06-10 | Quality control data analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110647600.7A CN113504239B (en) | 2021-06-10 | 2021-06-10 | Quality control data analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113504239A true CN113504239A (en) | 2021-10-15 |
| CN113504239B CN113504239B (en) | 2022-12-02 |
Family
ID=78009828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110647600.7A Active CN113504239B (en) | 2021-06-10 | 2021-06-10 | Quality control data analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113504239B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115760568A (en) * | 2022-11-02 | 2023-03-07 | 中国兵器科学研究院 | Target image generation method and device and electronic equipment |
| CN116684724A (en) * | 2023-05-19 | 2023-09-01 | 中科慧远视觉技术（洛阳）有限公司 | Workpiece image acquisition control method and device, workpiece detection equipment and storage medium |
| CN118023756A (en) * | 2024-04-12 | 2024-05-14 | 山东亚泰机械有限公司 | Welding method for vehicle cab |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2237640A1 (en) * | 1996-08-12 | 1998-02-19 | Centre De Recherche Industrielle Du Quebec | Apparatus and method for detecting surface defects |
| JP2003065985A (en) * | 2001-08-28 | 2003-03-05 | Matsushita Electric Works Ltd | Method for inspecting laser welding part and apparatus therefor |
| CN107931802A (en) * | 2017-11-27 | 2018-04-20 | 中北大学 | Arc welding weldquality online test method based on middle infrared temperature sensing |
| CN108896577A (en) * | 2018-05-30 | 2018-11-27 | 昆山睿力得软件技术有限公司 | A kind of automatic testing method of brake block profile defects |
| CN110245599A (en) * | 2019-06-10 | 2019-09-17 | 深圳市超准视觉科技有限公司 | A kind of intelligent three-dimensional weld seam Auto-searching track method |
| US20190308277A1 (en) * | 2018-04-05 | 2019-10-10 | Georg Fischer Rohrleitungssysteme Ag | Sensing Of A Weld Seam Geometry |
| CN110403232A (en) * | 2019-07-24 | 2019-11-05 | 浙江中烟工业有限责任公司 | A kind of cigarette quality detection method based on second level algorithm |
| CN112296822A (en) * | 2020-10-23 | 2021-02-02 | 宝鸡宇喆工业科技有限公司 | Polishing method of steel pipe end spiral weld polishing robot |
-
2021
- 2021-06-10 CN CN202110647600.7A patent/CN113504239B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2237640A1 (en) * | 1996-08-12 | 1998-02-19 | Centre De Recherche Industrielle Du Quebec | Apparatus and method for detecting surface defects |
| JP2003065985A (en) * | 2001-08-28 | 2003-03-05 | Matsushita Electric Works Ltd | Method for inspecting laser welding part and apparatus therefor |
| CN107931802A (en) * | 2017-11-27 | 2018-04-20 | 中北大学 | Arc welding weldquality online test method based on middle infrared temperature sensing |
| US20190308277A1 (en) * | 2018-04-05 | 2019-10-10 | Georg Fischer Rohrleitungssysteme Ag | Sensing Of A Weld Seam Geometry |
| CN108896577A (en) * | 2018-05-30 | 2018-11-27 | 昆山睿力得软件技术有限公司 | A kind of automatic testing method of brake block profile defects |
| CN110245599A (en) * | 2019-06-10 | 2019-09-17 | 深圳市超准视觉科技有限公司 | A kind of intelligent three-dimensional weld seam Auto-searching track method |
| CN110403232A (en) * | 2019-07-24 | 2019-11-05 | 浙江中烟工业有限责任公司 | A kind of cigarette quality detection method based on second level algorithm |
| CN112296822A (en) * | 2020-10-23 | 2021-02-02 | 宝鸡宇喆工业科技有限公司 | Polishing method of steel pipe end spiral weld polishing robot |
Non-Patent Citations (3)
| Title |
|---|
| 安康: ""焊缝外观的自动检测及质量评估方法研究"", 《中国优秀硕士学位论文全文数据库（电子期刊）》 * |
| 赵森: ""钢筋焊缝三维扫描检测技术与评价方法研究"", 《中国优秀硕士学位论文全文数据库（电子期刊）》 * |
| 霍平等: "一种基于结构光的V型焊缝实时图像处理方法", 《电焊机》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115760568A (en) * | 2022-11-02 | 2023-03-07 | 中国兵器科学研究院 | Target image generation method and device and electronic equipment |
| CN116684724A (en) * | 2023-05-19 | 2023-09-01 | 中科慧远视觉技术（洛阳）有限公司 | Workpiece image acquisition control method and device, workpiece detection equipment and storage medium |
| CN116684724B (en) * | 2023-05-19 | 2024-04-09 | 中科慧远视觉技术（洛阳）有限公司 | Workpiece image acquisition control method and device, workpiece detection equipment and storage medium |
| CN118023756A (en) * | 2024-04-12 | 2024-05-14 | 山东亚泰机械有限公司 | Welding method for vehicle cab |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113504239B (en) | 2022-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113504239B (en) | Quality control data analysis method | |
| CN103857490B (en) | For method and the laser processing device of defect during identifying laser processing procedure | |
| JP5676387B2 (en) | Appearance inspection method and apparatus | |
| KR102056076B1 (en) | Apparatus for weld bead detecting and method for detecting welding defects of the same | |
| CN106392304B (en) | A kind of laser assisted weld seam Intelligent tracing system and method | |
| CN102455171B (en) | Method for detecting geometric shape of back of tailor-welding weld and implementing device thereof | |
| CN101750416A (en) | Visual welding seam surface quality detection sensor based on line structure light | |
| CN103231162A (en) | Device and method for visual detection of welding quality of robot | |
| CN106735749B (en) | A kind of laser assisted weld seam Intelligent tracing system | |
| CN103492834B (en) | For detecting automatic utensil and the method for inspection of pivoting part quality | |
| WO2010090605A1 (en) | Methods for examining a bonding structure of a substrate and bonding structure inspection devices | |
| JP2012529027A (en) | Image measuring probe and operation method | |
| CN111965198A (en) | Solder joint detection device and detection method | |
| CN103630544B (en) | A kind of vision on-line detecting system | |
| JP5913903B2 (en) | Shape inspection method and apparatus | |
| JP2019197018A (en) | Flatness detection method, flatness detection device and flatness detection program | |
| CN111307812A (en) | Welding spot appearance detection method based on machine vision | |
| CN109990711A (en) | A kind of appearance quality detection method of punched nickel-plated steel band | |
| CN111397529A (en) | Complex surface shape detection method based on binocular vision structured light | |
| CN114894808A (en) | Device and method for detecting defects of heat pipe orifice based on machine vision | |
| CN107797517B (en) | Method and system for realizing steel belt punching processing detection by adopting machine vision | |
| CN116393982B (en) | Screw locking method and device based on machine vision | |
| JP2015129751A (en) | Inspection method and device for the same | |
| CN111077162A (en) | Glass bottle defect detecting system | |
| JP2005283267A (en) | Through hole measuring device, method, and program for through hole measurement |
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: 20240423 Address after: Floor 2, 3, 21 and 22, No. 89, Yunling East Road, Putuo District, Shanghai, 200333 Patentee after: Shanghai Xixin Software Engineering Co.,Ltd. Country or region after: China Address before: 200333 14th floor, 235 Yunling East Road, Putuo District, Shanghai Patentee before: Shanghai Xixin Information Technology Co.,Ltd. Country or region before: China |