CN112184600A - Hub model identification method in mixed line production line - Google Patents
Hub model identification method in mixed line production line Download PDFInfo
- Publication number
- CN112184600A CN112184600A CN202010831407.4A CN202010831407A CN112184600A CN 112184600 A CN112184600 A CN 112184600A CN 202010831407 A CN202010831407 A CN 202010831407A CN 112184600 A CN112184600 A CN 112184600A
- Authority
- CN
- China
- Prior art keywords
- hub
- image
- spoke
- production line
- identification method
- 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.)
- Withdrawn
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000003708 edge detection Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- 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
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- 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
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a hub model identification method in a mixed line production line, which comprises the following steps: acquiring wheel hub height data through a grating ruler; measuring the size of the hub; counting the number of spokes and the spoke-to-window ratio of the hub; judging the model; the method can effectively extract the size of the hub, the number of spokes and the ratio of spoke to spoke, can successfully identify various hub models produced in a mixed line, has less time consumption, consumes about 2s of total time, meets the real-time requirement and meets the requirement of full-automatic production.
Description
Technical Field
The invention belongs to the technical field of digital image processing, and particularly relates to a hub model identification method in a mixed line production line.
Background
Since the 21 st century, the automobile reserves in China are gradually increased, and the demand of the wheel hubs serving as main stress parts of the automobile is also rapidly increased; the main manufacturing method of the wheel hub is a casting method, defects are inevitably generated in the production process, and therefore, the quality inspection of the wheel hub needs to be carried out before the wheel hub is shipped.
Because the processing mode of the blank hub on the production line is mixed line production, the diameters, heights and spoke numbers of different hubs are different, the quality detection positions are different, and if the model of the hub is detected incorrectly, wrong equipment is used for detection, the hub can be scrapped, the equipment is damaged, and even operators are injured; therefore, the identification of the type of the hub has very important significance for the quality detection, equipment processing, warehousing management and the like of the hub.
Disclosure of Invention
In view of the above situation, the invention provides a hub model identification method in a mixed line production line, which can successfully identify the model of the hub, effectively extract the size of the hub, the number of spokes and the spoke-to-window ratio, and has the advantages of less time consumption and high measurement accuracy.
The purpose of the invention is realized as follows: a hub model identification method in a mixed line production line comprises the following steps:
s1, acquiring the height data of the hub through a grating ruler;
s2, measuring the size of the hub;
s3, counting the number of spokes and the spoke-to-window ratio of the hub;
and S4, judging the model.
Further, the step S1 includes the following steps:
and S11, acquiring the height information of the hub by calculating the number of grating shading points.
Further, the step S2 includes the following steps:
s21: acquiring a hub image by using an image acquisition device, and taking an acquired image I (r, c) as an input image;
s22: firstly, performing closed operation on the image obtained in the step S21 to repair image holes and cracks caused by shaking of a production line and unstable shooting of a camera;
s23: performing opening operation on the image obtained in the step S22 to remove background interference of the lane line;
s24: performing threshold segmentation on the image obtained in the step S23, performing binarization processing on the image, and acquiring a complete contour binarization image;
s25: performing closed operation on the image obtained in the step S24, and filling gaps of the spoke windows;
s26: and (4) carrying out Canny edge detection on the image obtained in the step (S25) to obtain the outer contour of the hub, fitting the contour based on a fitting circle algorithm, outputting the position (R1, c1) and the diameter (R) of the circle center, and measuring the size of the hub by using the center and the diameter.
Further, the step S3 includes the following steps:
s31: cutting the image obtained in the step S21 by using the circle center position and the diameter obtained in the step S26 to obtain a spoke image I (r, c);
s32: carrying out binarization processing on the image obtained in the step S31 to obtain a binary image of the spoke;
s33: performing edge detection on the image obtained in the step S32, wherein the detection mode is that the edge is from dark to bright, and the number of the detected edges is the number of spokes of the hub;
s34: performing edge detection on the image obtained in the step S32 in a manner that the edge changes from light to dark;
s35: from the data obtained in S33 and S34, from the image obtained in S31, the spoke area S spoke window is calculated from the data, and the spoke window ratio = S spoke window/total area can be calculated.
Further, the step S4 includes the following steps:
and S41, counting the height of the hub obtained in the step S11, the diameter of the hub obtained in the step S26, the number of spokes obtained in the step S33 and the spoke-to-window ratio obtained in the step S35, and judging the type of the hub according to the relevant characteristics.
The invention has the beneficial effects that: the invention can effectively extract the size of the hub, the number of spokes and the ratio of spoke to spoke, can successfully identify various hub models produced in a mixed line, has less time consumption, consumes about 2s of total time, meets the real-time requirement and meets the requirement of full-automatic production.
Drawings
FIG. 1 is a general flow chart of a hub model identification method in a mixed line production line according to the present invention;
FIG. 2 is a hub image acquired in the hub model identification method in a mixed line production line according to the present invention;
FIG. 3 is a hub contour binarization image obtained by the hub model identification method in the mixed line production line;
FIG. 4 is a hub outline image obtained by the hub model identification method in the mixed line production line of the present invention;
fig. 5 is a spoke image obtained by the hub model identification method in the mixed line production line of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Example 1
As shown in fig. 1-5, a method for identifying the hub model in the mixed line production line comprises the following steps:
and S1, using a grating ruler with 5mm optical axis distance, total length of 400mm, optical axis number of 80 and emission distance of 0.8m to detect the height of the hub. And a 485 or 232 communication protocol and a baud rate of 57600bit/s are adopted to output the number of the shading points. Calculating the number of grating shielding points to obtain the height data of the hub;
s2: the method comprises the following steps of measuring the size of a hub according to a front image of the hub:
s21: collecting a hub image I (r, c) shown in FIG. 2 through an image collecting device;
s22: because the equipment can generate slight jitter in the running process, the input image can generate tiny cracks and faults, and the kernel Kb with the size of 41 x 41 is adopted for closed operation, so that the optimization of the input image is completed. The closed operation is to convolute the image I (r, c) by using a kernel Kb, the center point of the kernel Kb is defined as an anchor point, the kernel Kb is drawn through the image, the maximum pixel value of the kernel coverage area is extracted and replaces the pixel at the anchor point position, the step can fill and level up the fine crack in the object, but the total area is increased, then the Kb is used to draw the image, the minimum pixel value of the kernel Kb coverage area is extracted and replaces the pixel at the anchor point position, the step can reduce the total area, and therefore the total area is ensured to be unchanged before and after the treatment;
s23: because the wheel hub is placed on the raceway, the raceway line exists in the image as an interference background, and the kernel Ko with the size of 9 x 9 is used for performing open operation to finish background removal on the input image;
s24: based on the image output in S23, according to the luminance of the light source of the device, we select the segmentation threshold value to be 100, that is, only the pixel points with pixel values higher than 100 in the image are retained, and the pixel point values are reset to 255, and the obtained result is shown in fig. 3;
s25: performing a closing operation on the image output in the step S24 by using a kernel K having a size of 5 × 5, so as to eliminate pores caused by uneven illumination;
s26: performing canny edge detection on the image obtained in the step S25 to obtain a hub edge profile, wherein the result is shown in fig. 4;
s3: counting the number of spokes and the spoke-to-window ratio of the hub, and specifically comprising the following steps of:
s31: and cutting the spoke area of the hub image by taking the center of the hub as the center. The region diameters satisfied 0.45 × R < R cut <0.7 × R, the results are shown in fig. 5;
s32: for the image output in S31, we select the segmentation threshold value as 100 here, and segment the image;
s33, edge detection is carried out on the image of S32. The detection mode is to find a set formed by pixel points with severe brightness change in the image, and the expressed outline is usually the outline. The number of spokes can be calculated according to the number of the detected profiles;
s34, detecting a severe change area from light to dark in the image, and combining the detected area in S33 to calculate the area of the spoke;
s35, calculating the spoke-to-window ratio according to the total area of the hub and the calculated area of the spoke;
s4: and (4) counting the height of the hub obtained in the step S11, the diameter of the hub obtained in the step S26, the number of spokes obtained in the step S33 and the spoke-to-window ratio obtained in the step S35, and judging the type of the hub according to the relevant characteristics.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may be modified, or some or all of the technical features may be equally replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (5)
1. A hub model identification method in a mixed line production line is characterized in that: it comprises the following steps:
s1, acquiring the height data of the hub through a grating ruler;
s2, measuring the size of the hub;
s3, counting the number of spokes and the spoke-to-window ratio of the hub;
and S4, judging the model.
2. The hub model identification method in the wire mixing production line according to claim 1, characterized in that: the step S1 includes the following steps:
and S11, acquiring the height information of the hub by calculating the number of grating shading points.
3. The hub model identification method in the wire mixing production line according to claim 1, characterized in that: the step S2 includes the following steps:
s21: acquiring a hub image by using an image acquisition device, and taking an acquired image I (r, c) as an input image;
s22: firstly, performing closed operation on the image obtained in the step S21 to repair image holes and cracks caused by shaking of a production line and unstable shooting of a camera;
s23: performing opening operation on the image obtained in the step S22 to remove background interference of the lane line;
s24: performing threshold segmentation on the image obtained in the step S23, performing binarization processing on the image, and acquiring a complete contour binarization image;
s25: performing closed operation on the image obtained in the step S24, and filling gaps of the spoke windows;
s26: and (4) carrying out Canny edge detection on the image obtained in the step (S25) to obtain the outer contour of the hub, fitting the contour based on a fitting circle algorithm, outputting the position (R1, c1) and the diameter (R) of the circle center, and measuring the size of the hub by using the center and the diameter.
4. The hub model identification method in the wire mixing production line according to claim 1, characterized in that: the step S3 includes the following steps:
s31: cutting the image obtained in the step S21 by using the circle center position and the diameter obtained in the step S26 to obtain a spoke image I (r, c);
s32: carrying out binarization processing on the image obtained in the step S31 to obtain a binary image of the spoke;
s33: performing edge detection on the image obtained in the step S32, wherein the detection mode is that the edge is from dark to bright, and the number of the detected edges is the number of spokes of the hub;
s34: performing edge detection on the image obtained in the step S32 in a manner that the edge changes from light to dark;
s35: from the data obtained in S33 and S34, from the image obtained in S31, the spoke area S spoke window is calculated from the data, and the spoke window ratio = S spoke window/total area can be calculated.
5. The hub model identification method in the wire mixing production line according to claim 1, characterized in that: the step S4 includes the following steps:
and S41, counting the height of the hub obtained in the step S11, the diameter of the hub obtained in the step S26, the number of spokes obtained in the step S33 and the spoke-to-window ratio obtained in the step S35, and judging the type of the hub according to the relevant characteristics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010831407.4A CN112184600A (en) | 2020-08-18 | 2020-08-18 | Hub model identification method in mixed line production line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010831407.4A CN112184600A (en) | 2020-08-18 | 2020-08-18 | Hub model identification method in mixed line production line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112184600A true CN112184600A (en) | 2021-01-05 |
Family
ID=73919232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010831407.4A Withdrawn CN112184600A (en) | 2020-08-18 | 2020-08-18 | Hub model identification method in mixed line production line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112184600A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279763A (en) * | 2013-05-25 | 2013-09-04 | 中北大学 | Method for automatically identifying wheel hub types based on structural features |
| CN111210392A (en) * | 2019-12-18 | 2020-05-29 | 中信重工机械股份有限公司 | Wheel hub valve hole positioning method based on digital image processing |
| CN111445512A (en) * | 2020-06-17 | 2020-07-24 | 浙江大学 | Hub parameter feature extraction method in complex production line background |
-
2020
- 2020-08-18 CN CN202010831407.4A patent/CN112184600A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279763A (en) * | 2013-05-25 | 2013-09-04 | 中北大学 | Method for automatically identifying wheel hub types based on structural features |
| CN111210392A (en) * | 2019-12-18 | 2020-05-29 | 中信重工机械股份有限公司 | Wheel hub valve hole positioning method based on digital image processing |
| CN111445512A (en) * | 2020-06-17 | 2020-07-24 | 浙江大学 | Hub parameter feature extraction method in complex production line background |
Non-Patent Citations (1)
| Title |
|---|
| 郭智杰: "基于机器视觉的轮毂型号在线识别技术与系统", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109141232B (en) | Online detection method for disc castings based on machine vision | |
| CN116721106B (en) | Profile flaw visual detection method based on image processing | |
| CN116758061B (en) | Casting surface defect detection method based on computer vision | |
| CN109242853B (en) | PCB defect intelligent detection method based on image processing | |
| CN116385439B (en) | Motor rubber shock pad quality detection method based on image processing | |
| CN108896278A (en) | A kind of optical filter silk-screen defect inspection method, device and terminal device | |
| CN112330663B (en) | Method for detecting width of cut tobacco based on reducing circle by computer vision | |
| CN110021012B (en) | Mobile phone lens window glass defect detection method based on machine vision technology | |
| CN112330598B (en) | Method, device and storage medium for detecting stiff yarn defects on chemical fiber surface | |
| CN117173661B (en) | Asphalt road quality detection method based on computer vision | |
| CN107230207A (en) | The detection method and system of tire | |
| CN111426693A (en) | Quality defect detection system and detection method thereof | |
| CN116703251A (en) | Rubber ring production quality detection method based on artificial intelligence | |
| CN118071753A (en) | Visual inspection method for surface defects of injection mold | |
| CN111815575B (en) | Bearing steel ball part detection method based on machine vision | |
| WO2024045963A1 (en) | Appearance defect detection method, electronic device, and storage medium | |
| CN112184600A (en) | Hub model identification method in mixed line production line | |
| CN111062912B (en) | Feature extraction, detection and positioning method for key targets of tire section | |
| CN111008960A (en) | Aluminum electrolytic capacitor bottom appearance detection method and device based on machine vision | |
| CN113191997B (en) | Clamp spring measuring method based on machine vision | |
| CN112129700B (en) | Image detection method and device for flexible circuit board | |
| CN113763491A (en) | Visual detection method for tobacco shred barrel residues | |
| CN113870299A (en) | 3D printing fault detection method based on edge detection and morphological image processing | |
| CN113570524A (en) | Restoration method for high-reflection noise depth image | |
| CN112966746A (en) | Stable variable gray template generation method suitable for tire defect detection |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210105 |