CN115326814A - Online intelligent identification and detection method and medium for manufacturing defects of automobile stamping parts - Google Patents
Online intelligent identification and detection method and medium for manufacturing defects of automobile stamping parts Download PDFInfo
- Publication number
- CN115326814A CN115326814A CN202211084417.1A CN202211084417A CN115326814A CN 115326814 A CN115326814 A CN 115326814A CN 202211084417 A CN202211084417 A CN 202211084417A CN 115326814 A CN115326814 A CN 115326814A
- Authority
- CN
- China
- Prior art keywords
- defects
- stamping parts
- detection
- intelligent identification
- online intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 69
- 238000001514 detection method Methods 0.000 title claims abstract description 39
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000000007 visual effect Effects 0.000 claims abstract description 9
- 230000004044 response Effects 0.000 claims abstract description 4
- 238000003860 storage Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000007689 inspection Methods 0.000 description 15
- 238000013135 deep learning Methods 0.000 description 4
- 238000009432 framing Methods 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005498 polishing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000005336 cracking Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000013072 incoming material Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect 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
- G01N21/8806—Specially adapted optical and illumination features
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Automobile Manufacture Line, Endless Track Vehicle, Trailer (AREA)
Abstract
The invention provides an online intelligent identification and detection method for manufacturing defects of automobile stamping parts, which comprises the following steps: s1, triggering a signal, namely triggering a PLC signal through a photoelectric signal when a stamping part is off-line; s2, shooting, namely triggering a visual camera to shoot to obtain a photo of the stamping part; s3, image processing, namely performing image processing on the photo of the stamping part; and S4, judging by a system, judging whether the defects exist, if the defects do not exist, continuing production or transferring the stamping part to a manual rechecking table for manual rechecking, and if the defects exist, taking different response measures according to the grade of the defects. The invention also provides a readable storage medium. The invention has the beneficial effects that: the online defect detection of the stamping part is realized, and the efficiency is improved.
Description
Technical Field
The invention relates to an automobile stamping part, in particular to an online intelligent identification and detection method and medium for manufacturing defects of the automobile stamping part.
Background
In the stamping of automobile parts, defects such as cracking, wrinkling, strain and the like may be caused by various factors, and quality inspection is required before framing to prevent poor outflow.
In the current industrial production mode, the quality inspection of stamping parts is mainly carried out manually. The inspection method mainly comprises touch inspection, oilstone polishing, flexible gauze polishing, oiling inspection and the like. The general worker needs about 8-10min for carrying out overall quality inspection on each stamping part, and the beat of the current stamping line can reach 12-20 pieces per minute. The quality full-inspection speed is far lower than the production speed, the full inspection of parts cannot be realized, and only on-line spot inspection or multi-person on-line multi-point inspection can be realized.
The manual sampling inspection mode has the risks of accidental poor omission and poor batch quality. And the quality testing personnel repeatedly act for a long time, and the risk of missing detection caused by operation fatigue and detection capability fluctuation also exists. With the application of the unmanned automatic stamping line of a company, the robot framing replaces the manual framing, the unmanned forklift replaces the manned forklift, only the quality inspection link is left, the unmanned final difficulty is achieved, the online quality inspection link is lacked, and the risk of quality defect overflow exists.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an online intelligent identification and detection method and medium for manufacturing defects of automobile stamping parts.
The invention provides an online intelligent identification and detection method for manufacturing defects of automobile stamping parts, which comprises the following steps:
s1, triggering a signal, namely triggering a PLC signal through a photoelectric signal when a stamping part is off-line;
s2, shooting, namely triggering a visual camera to shoot to obtain a photo of the stamping part;
s3, image processing, namely performing image processing on the photo of the stamping part;
s4, judging whether a defect exists or not by a system, if not, continuing production or transferring the stamping part to a manual rechecking table for manual rechecking, and if so, taking different response measures according to the grade of the defect;
and S5, defect confirmation is carried out, in the manual reinspection, the defect confirmation is carried out, and the confirmed defect pictures are subjected to model automatic cycle learning iterative training, wherein the model automatic cycle learning iterative training comprises defect definition, defect identification, sample collection, model building and model training.
As a further improvement of the invention, in step S4, if the defect exists, the defect and the position of the stamping part are alarmed, if the alarming frequency is less than 3 times, the stamping part is transferred to a manual rechecking table for manual rechecking, and if the alarming frequency is more than or equal to 3 times, the wire stopping processing is carried out.
As a further improvement of the invention, before the step S1, a professional detection room is built on a tail belt of a production line, and at least two groups of vision systems are arranged in the professional detection room, wherein the cameras of the vision systems adopt high-speed industrial cameras up to 70FPS, and the light sources adopt diffuse reflection strip-shaped dot matrix light sources.
As a further improvement of the present invention, in step S2, based on CAE process prediction, a high risk area of the stamping is identified and a photograph is taken of the high risk area.
As a further improvement of the present invention, the front end of the photo supply system for stamping parts taken in step S2 is subjected to model training for deep learning.
As a further improvement of the method, before the model training, the classification and definition of the defects are carried out.
As a further improvement of the invention, before the step S1, parameters of the stamping part are set according to the PLC information of the production line, including a workshop standard part grid diagram, a communication state, a camera selection and a photographing parameter.
As a further improvement of the invention, in step S4, if the defect exists, the defective picture is automatically numbered and stored, and after screening, iterative model training is performed.
As a further improvement of the present invention, in step S4, the detection data is stored to a database.
The invention also provides a readable storage medium having stored therein executable instructions for implementing the method of any one of claims 1 to 9 when executed by a processor.
The invention has the beneficial effects that: through the scheme, the online defect detection of the stamping part is realized, and the efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other solutions can be obtained according to the drawings without inventive efforts.
FIG. 1 is a flow chart of the online intelligent identification and detection method for manufacturing defects of automobile stamping parts.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore, should not be taken as limiting the scope of the present invention. Furthermore, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate a number of the indicated technical features. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The invention is further described in the following description and embodiments with reference to the drawings.
As shown in fig. 1, an online intelligent identification and detection method for manufacturing defects of automobile stamping parts mainly comprises the following steps: deep learning stamping part defect definition and identification, production vehicle type information PLC connection, and professional detection room photographing based on process defect prediction. Through an online integration scheme, a professional detection room is built on an online tail belt, a plurality of groups of visual systems are arranged in the professional detection room, the parts are photographed and uploaded to a visual monitoring system to analyze and judge images, and the defects and the positions of the parts are alarmed.
The specific process is as follows:
s1, triggering a signal, namely triggering a PLC signal through a photoelectric signal when a stamping part is off-line;
s2, shooting, namely triggering a visual camera to shoot to obtain a photo of the stamping part;
s3, image processing, namely performing image processing on the photo of the stamping part;
s4, judging whether a defect exists or not by a system, if not, continuing production or transferring the stamping part to a manual rechecking table for manual rechecking, and if so, taking different response measures according to the grade of the defect;
and S5, confirming the defects, namely confirming the defects in the manual reinspection, and performing model automatic loop learning iterative training on the confirmed defect pictures, wherein the model automatic loop learning iterative training comprises defect definition, defect identification, sample collection, model building and model training.
In step S4, if the defects exist, alarming is carried out on the defects and the positions of the stamping parts, if the alarming times are less than 3 times, the stamping parts are transferred to a manual rechecking table to be rechecked manually, and if the alarming times are more than or equal to 3 times, the line stopping processing is carried out.
Based on CAE process prediction, high-risk areas of parts are identified, 16 single-side cameras in the detection chamber can be arranged at most, and special areas are photographed in an all-round and dead-angle-free mode.
The high-speed industrial camera of up to 70FPS is adopted to the camera, and the light source adopts diffuse reflection bar dot matrix light source, can satisfy high quality defect under the different takts and shoot.
The shot photos can be supplied to the front end of the system for model training.
The integrated system sets parameters of the tested parts according to PLC information of the production line, and the parameters comprise part information (a workshop standard part grid diagram), communication states, camera selection, photographing parameters and the like.
The part is shot and is triggered to shoot through photoelectric development.
And analyzing and judging the shot images, giving an alarm for the defects and the positions of the parts for less than 3 times of off-line alarm, transferring the parts to a manual re-inspection table, giving continuous alarm for more than 3 times, and controlling the inspection process within 1m by field workers through a PLC (programmable logic controller) data line stop instruction to meet the requirements of a production line.
And automatically numbering and storing the defective pictures, and performing iterative model training after screening.
And carrying out image processing through an intelligent algorithm, carrying out defect identification on the stamping part, and carrying out deep learning on the extracted defects.
The invention provides an online intelligent identification and detection method and medium for manufacturing defects of automobile stamping parts, which have the following advantages:
1) The quality of the stamping part is detected on line in real time, the detection speed is high, and the accuracy is high.
2) The consistency of standardized execution of the defect judgment of the stamping parts is improved, and the high consistency of the production control process and the product quality is ensured.
3) Visual detection is used for replacing manual detection, each line can be reduced by 2 persons/shift, and the labor cost is saved by about 12 ten thousand/year.
4) And thirdly, providing precondition for the cooperative operation of automatic feeding at the head of the line, automatic replacement of an end pick-up in the line, automatic framing of a line tail robot and 4 large automatic logistics systems in the later period, and realizing the full unmanned production and manufacturing process of the whole line.
5) The intelligent identification and detection system for the manufacturing defects of the automobile stamping parts can be applied to automobile body workshop incoming material detection in an expanded mode, and the requirement for quality detection of unmanned factories in the automobile body workshop is met.
6) The intelligent recognition detection system data control center can expand automatic deep learning training and gradually improve the judgment accuracy of defects.
7) The system meets the standard of a front-end architecture and a rear-end architecture, and can be used as a port to be accessed into a future intelligent factory quality monitoring system.
The foregoing is a further detailed description of the invention in connection with specific preferred embodiments and it is not intended to limit the invention to the specific embodiments described. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (10)
1. The online intelligent identification and detection method for the manufacturing defects of the automobile stamping parts is characterized by comprising the following steps:
s1, triggering a signal, namely triggering a PLC signal through a photoelectric signal when a stamping part is off-line;
s2, shooting, namely triggering a visual camera to shoot to obtain a photo of the stamping part;
s3, image processing, namely performing image processing on the photo of the stamping part;
s4, judging whether the defects exist or not by a system, if the defects do not exist, continuing production or transferring the stamping part to a manual rechecking table for manual rechecking, and if the defects exist, taking different response measures according to the grade of the defects;
and S5, confirming the defects, namely confirming the defects in the manual reinspection, and performing model automatic loop learning iterative training on the confirmed defect pictures, wherein the model automatic loop learning iterative training comprises defect definition, defect identification, sample collection, model building and model training.
2. The online intelligent identification and detection method for the manufacturing defects of the automobile stamping parts according to claim 1 is characterized in that: in step S4, if the defects exist, alarming is carried out on the defects and the positions of the stamping parts, if the alarming times are less than 3 times, the stamping parts are transferred to a manual rechecking table for manual rechecking, and if the alarming times are more than or equal to 3 times, the wire stopping processing is carried out.
3. The method for online intelligent identification and detection of the manufacturing defects of the automobile stamping parts according to claim 1, characterized in that: before the step S1, a professional detection room is built on a tail belt of a production line, at least two groups of visual systems are arranged in the professional detection room, cameras of the visual systems are high-speed industrial cameras up to 70FPS, and light sources are diffuse reflection strip-shaped dot matrix light sources.
4. The online intelligent identification and detection method for the manufacturing defects of the automobile stamping parts according to claim 1 is characterized in that: in step S2, based on CAE process prediction, a high risk area of the stamping is identified and photographed.
5. The method for online intelligent identification and detection of the manufacturing defects of the automobile stamping parts according to claim 1, characterized in that: and (5) carrying out deep learning model training on the front end of the stamping part photo supply system shot in the step (S2).
6. The method for online intelligent identification and detection of the manufacturing defects of the automobile stamping parts according to claim 5, characterized in that: before the model training, the classification and definition of the defects are carried out.
7. The online intelligent identification and detection method for the manufacturing defects of the automobile stamping parts according to claim 1 is characterized in that: before the step S1, parameters of the stamping part are set according to PLC information of a production line, and the parameters comprise a workshop standard part grid diagram, a communication state, camera selection and photographing parameters.
8. The method for online intelligent identification and detection of the manufacturing defects of the automobile stamping parts according to claim 1, characterized in that: in step S4, if there is a defect, the defective picture is automatically numbered and stored, and after being filtered, iterative model training is performed.
9. The online intelligent identification and detection method for the manufacturing defects of the automobile stamping parts according to claim 1 is characterized in that: in step S4, the detection data is stored in the database.
10. A readable storage medium, characterized by: the readable storage medium has stored therein execution instructions for implementing the method of any one of claims 1 to 9 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211084417.1A CN115326814A (en) | 2022-09-06 | 2022-09-06 | Online intelligent identification and detection method and medium for manufacturing defects of automobile stamping parts |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211084417.1A CN115326814A (en) | 2022-09-06 | 2022-09-06 | Online intelligent identification and detection method and medium for manufacturing defects of automobile stamping parts |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115326814A true CN115326814A (en) | 2022-11-11 |
Family
ID=83929415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211084417.1A Pending CN115326814A (en) | 2022-09-06 | 2022-09-06 | Online intelligent identification and detection method and medium for manufacturing defects of automobile stamping parts |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115326814A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665138A (en) * | 2023-08-01 | 2023-08-29 | 临朐弘泰汽车配件有限公司 | Visual detection method and system for stamping processing of automobile parts |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111060518A (en) * | 2019-12-20 | 2020-04-24 | 重庆大学 | Stamping part defect identification method based on instance segmentation |
| CN213633208U (en) * | 2020-10-21 | 2021-07-06 | 广州柔视智能科技有限公司 | Stamping workpiece defect detection device |
| CN114113109A (en) * | 2021-11-26 | 2022-03-01 | 科士恩智能科技(上海)有限公司 | Automatic and intelligent automobile instrument desk defect detection method |
| CN114494105A (en) * | 2020-10-23 | 2022-05-13 | 福特全球技术公司 | System and method for monitoring press line defects |
| CN114897886A (en) * | 2022-06-17 | 2022-08-12 | 西安交通大学 | Industrial defect detection optimization method, system, device, equipment and storage medium |
-
2022
- 2022-09-06 CN CN202211084417.1A patent/CN115326814A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111060518A (en) * | 2019-12-20 | 2020-04-24 | 重庆大学 | Stamping part defect identification method based on instance segmentation |
| CN213633208U (en) * | 2020-10-21 | 2021-07-06 | 广州柔视智能科技有限公司 | Stamping workpiece defect detection device |
| CN114494105A (en) * | 2020-10-23 | 2022-05-13 | 福特全球技术公司 | System and method for monitoring press line defects |
| CN114113109A (en) * | 2021-11-26 | 2022-03-01 | 科士恩智能科技(上海)有限公司 | Automatic and intelligent automobile instrument desk defect detection method |
| CN114897886A (en) * | 2022-06-17 | 2022-08-12 | 西安交通大学 | Industrial defect detection optimization method, system, device, equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665138A (en) * | 2023-08-01 | 2023-08-29 | 临朐弘泰汽车配件有限公司 | Visual detection method and system for stamping processing of automobile parts |
| CN116665138B (en) * | 2023-08-01 | 2023-11-07 | 临朐弘泰汽车配件有限公司 | Visual detection method and system for stamping processing of automobile parts |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106226325B (en) | A kind of seat surface defect detecting system and its method based on machine vision | |
| CN109840900A (en) | A kind of line detection system for failure and detection method applied to intelligence manufacture workshop | |
| CN113727022B (en) | Method and device for collecting inspection image, electronic equipment and storage medium | |
| CN110895716B (en) | Inspection device and machine learning method | |
| CN115326814A (en) | Online intelligent identification and detection method and medium for manufacturing defects of automobile stamping parts | |
| CN115423785A (en) | Defect detection system, method and device, electronic equipment and storage medium | |
| CN101762589A (en) | On-line monitoring method of machine vision on stationery combined set flaw and equipment thereof | |
| CN108593681A (en) | Vehicle body side wall glass defect detection system and detection method | |
| JP6823025B2 (en) | Inspection equipment and machine learning method | |
| CN110802042A (en) | Lithium battery intelligent detection and control system based on machine vision | |
| WO2023045037A1 (en) | Automatic sorting system and method | |
| CN111751898A (en) | Device and method for detecting whether core print falls off | |
| CN111842212A (en) | Automatic feeding structure, appearance detection device, mask appearance detection device and method | |
| CN117218428A (en) | Casting surface defect detection method and system based on deep learning | |
| CN106990113A (en) | Automobile connecting bar blank is swollen cross section quality vision inspection apparatus | |
| CN111127462A (en) | Ready-made garment printing defect detection system and detection method based on multi-exposure imaging | |
| CN110020809A (en) | A kind of framework of steel reinforcement detection method, device, equipment and readable storage medium storing program for executing | |
| CN114318426B (en) | Exception handling method and system based on slot outlet information detection | |
| CN116563194A (en) | Visual inspection system for defect detection | |
| CN113618737A (en) | Visual identification system for industrial platform | |
| CN112295945A (en) | Call box detection method and device, computer equipment and storage medium | |
| Wiangtong et al. | Deployment of machine vision platform for checking spot welds on metal strap belts | |
| CN117969553B (en) | On-line visual detection system for appearance of TPV knitted composite pipe | |
| CN219496189U (en) | Coating detection device | |
| CN115615663A (en) | Positioning vision detection system and detection method for tray supporting legs |
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 |