CN113916900A - Online image detection system for surface defects of steel plate - Google Patents
Online image detection system for surface defects of steel plate Download PDFInfo
- Publication number
- CN113916900A CN113916900A CN202010661263.2A CN202010661263A CN113916900A CN 113916900 A CN113916900 A CN 113916900A CN 202010661263 A CN202010661263 A CN 202010661263A CN 113916900 A CN113916900 A CN 113916900A
- Authority
- CN
- China
- Prior art keywords
- steel plate
- defects
- defect
- analysis module
- module
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- 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
- 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)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses an online image detection system for steel plate surface defects, which comprises a management module, a control analysis module, a 3D space acquisition and processing module, an object form visualization module and a defect intelligent identification statistical analysis module, wherein the management module is used for acquiring and processing the surface defects of a steel plate; the management module manages and controls the operation of a steel plate surface treatment production line, controls the analysis module to store detection data, identifies and analyzes the acquired images and classifies steel plate grades; the 3D space acquisition processing module detects the surface defect area and depth of the steel plate by adopting a 3D structured light imaging principle; the object form visualization module is used for displaying the suspected defect position and the actual state of the steel plate in real time; and the defect intelligent identification statistical analysis module identifies and counts suspected defects. The system overcomes the defects of the traditional steel plate surface defect detection, realizes the simultaneous detection of the two sides of the steel plate, can quickly and accurately detect the steel plate surface defects, improves the detection precision and efficiency, avoids the false detection and the omission, and avoids the potential safety hazard of the detection operation.
Description
Technical Field
The invention relates to the technical field of detection, in particular to an online image detection system for surface defects of a steel plate.
Background
In the surface treatment process of the steel sheet, surface defects such as pockmarks, peeling and the like are caused by raw materials, corrosion and the like, so that the surface of the steel sheet needs to be detected and classified according to the distribution and degree of the defects on the surface of the steel sheet. Most of traditional steel plate surface defect detection methods are manually searched and marked, and the steel plate needs to be turned over, namely, an off-line detection method, and the method has the defects of low detection precision, lag in reflection problem, consumption of manpower and material resources, low detection efficiency, error detection, omission detection and the like. And the steel plate turnover process needs to adopt a sucker, so that certain potential safety hazards exist in the operation process.
Disclosure of Invention
The invention aims to solve the technical problem of providing an online image detection system for the surface defects of the steel plate, which overcomes the defects of the traditional steel plate surface defect detection, realizes the simultaneous detection of two surfaces of the steel plate, can quickly and accurately detect the surface defects of the steel plate, improves the detection precision and efficiency, avoids the false detection and the missed detection, and avoids the potential safety hazard of the detection operation.
In order to solve the technical problem, the online image detection system for the surface defects of the steel plate comprises a management module, a control analysis module, a 3D space acquisition and processing module, an object form visualization module and a defect intelligent identification statistical analysis module;
the management module manages and controls the operation of the steel plate surface treatment production line, is in communication connection with the control analysis module, and sends a steel plate surface detection instruction and a current steel plate sequence number;
the control analysis module receives a management module instruction and is in communication connection with the 3D space acquisition and processing module, the object form visualization module and the defect intelligent identification statistical analysis module;
the 3D space acquisition processing module comprises camera imaging units symmetrically arranged on the front side and the back side of the steel plate, and the camera imaging units acquire images of the front side and the back side of the steel plate by adopting 3D structured light and transmit the images to the control analysis module;
the object form visualization module acquires images of the front side and the back side of the steel plate from the control analysis module, the images are projected by the linear array laser light source and are influenced by surface defects of the steel plate, the linear array laser light source is reflected to be in a bending state, the resolutions of suspected defects in different directions are acquired by the triangulation principle, so that the area and the depth of the suspected defects are acquired, and the suspected defects on the front side and the back side of the steel plate are identified and transmitted to the control analysis module;
the defect intelligent identification statistical analysis module acquires images of the front side and the back side of the steel plate and suspected defect identification from the control analysis module, analyzes and calculates the area and the depth of the suspected defect, compares the area and the depth with a set threshold of the surface defect of the steel plate, judges the surface defect of the steel plate if the area and the depth are larger than the set threshold, and transmits the surface defect and distribution data of the steel plate to the control analysis module according to the distribution of the statistical defect of the surface defect of the steel plate on the front side and the back side of the steel plate;
the control analysis module integrates the defects on the front side and the back side of the steel plate and the defect distribution images according to the defects and the distribution data on the surface of the steel plate, analyzes and calculates the characteristic data of the defects of the steel plate, and performs grade classification on the steel plate according to the characteristic data of the defects of the steel plate.
Further, a camera imaging unit of the 3D space acquisition and processing module projects the projection position of the suspected defect on the surface of the steel plate by using 3D structured light.
Furthermore, the object form visualization module acquires resolutions of suspected defects in different directions through a triangulation principle, an encoder is adopted to record a moving distance of the steel plate in the moving process of the steel plate to obtain an X coordinate of the moving direction of the steel plate, an inherent coordinate system of a camera imaging unit represents a Y coordinate of the width direction of the steel plate, and an offset of a curve of a linear array light source reflecting in a bending state represents a Z coordinate of the depth direction of the defect; the X-direction moving distance corresponding to the front image and the back image of the front surface and the back surface of the steel plate is determined, the smaller the distance is, the higher the X-direction resolution is, the highest frame frequency exists in a camera imaging unit, the X-direction resolution is determined by the frame frequency and the moving linear speed of the steel plate, the Y-direction resolution is determined by a camera pixel, and the Z-direction resolution is determined by the camera pixel, the included angle between the camera and a plane normal and the included angle between 3D structured light and the plane normal.
Further, the intelligent defect identification statistical analysis module obtains a continuous 3D structured light image of the surface of the steel plate, calculates to obtain 3D point cloud data information of the defects on the surface of the steel plate, and performs clustering analysis on the defects with suspected defect areas and overproof depths by iteratively fitting a reference surface.
Further, the management module acquires real-time information of the surface defects of the steel plate in the steel plate surface treatment process through the control analysis module, stores and displays images of the upper surface and the lower surface of the steel plate, defects, defect distribution and statistical classification charts in real time, and gives an alarm when the surface defects of the steel plate are detected.
The online image detection system for the surface defects of the steel plate adopts the technical scheme, namely the system comprises a management module, a control analysis module, a 3D space acquisition and processing module, an object form visualization module and a defect intelligent identification statistical analysis module; the management module manages and controls the operation of a steel plate surface treatment production line, controls the analysis module to store detection data, identifies and analyzes the acquired images and classifies steel plate grades; the 3D space acquisition processing module detects the surface defect area and depth of the steel plate by adopting a 3D structured light imaging principle; the object form visualization module is used for displaying the suspected defect position and the actual state of the steel plate in real time; and the defect intelligent identification statistical analysis module identifies and counts suspected defects. The system overcomes the defects of the traditional steel plate surface defect detection, realizes the simultaneous detection of the two sides of the steel plate, can quickly and accurately detect the steel plate surface defects, improves the detection precision and efficiency, avoids the false detection and the omission, and avoids the potential safety hazard of the detection operation.
Drawings
The invention is described in further detail below with reference to the following figures and embodiments:
FIG. 1 is a schematic block diagram of an on-line image detection system for surface defects of a steel plate according to the present invention.
Detailed Description
In the embodiment, as shown in fig. 1, the online image detection system for the surface defects of the steel plate comprises a management module, a control analysis module, a 3D space acquisition and processing module, an object morphology visualization module and a defect intelligent identification statistical analysis module;
the management module manages and controls the operation of the steel plate surface treatment production line, is in communication connection with the control analysis module, and sends a steel plate surface detection instruction and a current steel plate sequence number;
the control analysis module receives a management module instruction and is in communication connection with the 3D space acquisition and processing module, the object form visualization module and the defect intelligent identification statistical analysis module;
the 3D space acquisition processing module comprises camera imaging units symmetrically arranged on the front side and the back side of the steel plate, and the camera imaging units acquire images of the front side and the back side of the steel plate by adopting 3D structured light and transmit the images to the control analysis module;
the object form visualization module acquires images of the front side and the back side of the steel plate from the control analysis module, the images are projected by the linear array laser light source and are influenced by surface defects of the steel plate, the linear array laser light source is reflected to be in a bending state, the resolutions of suspected defects in different directions are acquired by the triangulation principle, so that the area and the depth of the suspected defects are acquired, and the suspected defects on the front side and the back side of the steel plate are identified and transmitted to the control analysis module;
the defect intelligent identification statistical analysis module acquires images of the front side and the back side of the steel plate and suspected defect identification from the control analysis module, analyzes and calculates the area and the depth of the suspected defect, compares the area and the depth with a set threshold of the surface defect of the steel plate, judges the surface defect of the steel plate if the area and the depth are larger than the set threshold, and transmits the surface defect and distribution data of the steel plate to the control analysis module according to the distribution of the statistical defect of the surface defect of the steel plate on the front side and the back side of the steel plate;
the control analysis module integrates the defects on the front side and the back side of the steel plate and the defect distribution images according to the defects and the distribution data on the surface of the steel plate, analyzes and calculates the characteristic data of the defects of the steel plate, and performs grade classification on the steel plate according to the characteristic data of the defects of the steel plate.
Preferably, the camera imaging unit of the 3D space acquisition and processing module projects the projection position of the suspected defect on the surface of the steel plate by using 3D structured light.
Preferably, the object form visualization module acquires resolutions of suspected defects in different directions by a triangulation principle, and in the moving process of the steel plate, an encoder is adopted to record the moving distance of the steel plate to obtain an X coordinate of the moving direction of the steel plate, an inherent coordinate system of a camera imaging unit represents a Y coordinate of the width direction of the steel plate, and an offset of a curve of a linear array light source reflecting in a bending state represents a Z coordinate of the depth direction of the defect; the X-direction moving distance corresponding to the front image and the back image of the front surface and the back surface of the steel plate is determined, the smaller the distance is, the higher the X-direction resolution is, the highest frame frequency exists in a camera imaging unit, the X-direction resolution is determined by the frame frequency and the moving linear speed of the steel plate, the Y-direction resolution is determined by a camera pixel, and the Z-direction resolution is determined by the camera pixel, the included angle between the camera and a plane normal and the included angle between 3D structured light and the plane normal.
Preferably, the defect intelligent identification statistical analysis module obtains a continuous 3D structured light image of the surface of the steel plate, calculates to obtain 3D point cloud data information of the defects on the surface of the steel plate, and performs clustering analysis on the defects with the suspected defect areas and the defects with the overproof depth through iterative fitting of a reference surface. The iterative fitting reference surface can complete point cloud collection and reverse modeling, so that the information of the curved surface of the sample piece is obtained. The steel plate surface of the sample piece is detected to be a simple plane, and the qualified area is taken as the main part of the steel plate surface, so that a reference plane can be preliminarily fitted, possible defect areas can be obtained through cluster analysis, and a reference plane can be obtained through an iteration method of preliminary fitting, cluster analysis and secondary fitting analysis.
Preferably, the management module acquires real-time information of the surface defects of the steel plate in the steel plate surface treatment process through the control analysis module, stores and displays images of the upper surface and the lower surface of the steel plate, defects, defect distribution and statistical classification charts in real time, and gives an alarm when the surface defects of the steel plate are detected. An operator can detect and confirm the surface defects of the steel plate on site, quickly position the defect area through the defect position provided by the management module, and further perform quality inspection, confirmation and detection on the defect area. Historical defect records can be inquired through the management module, the defect condition of the historical steel plate is backtracked, and real-time or historical inquiry is realized on defects, defect distribution and steel plate classification through a human-computer interface according to the steel plate sequence number.
The system is characterized in that camera imaging units of the 3D space acquisition processing module are respectively arranged above and below a plurality of conveying rollers between the rear end of shot blasting equipment and the front end of paint spraying equipment of a steel plate surface treatment production line, and the camera imaging units adopt 3D structured light to realize space measurement of surface defects of the steel plate. The 3D structured light detection principle is adopted to replace the traditional 2D camera image recognition, effective projection can be made on the surface defects of the steel plate through linear array laser light source projection, the area and the depth of suspected defects are obtained through the bending degree of the 3D structured light, the detection precision is greatly increased, and the detection precision can reach 0.1 mm.
Claims (5)
1. The on-line image detection system for the surface defects of the steel plate comprises a management module and is characterized in that: the system also comprises a control analysis module, a 3D space acquisition and processing module, an object form visualization module and a defect intelligent identification statistical analysis module;
the management module manages and controls the operation of the steel plate surface treatment production line, is in communication connection with the control analysis module, and sends a steel plate surface detection instruction and a current steel plate sequence number;
the control analysis module receives a management module instruction and is in communication connection with the 3D space acquisition and processing module, the object form visualization module and the defect intelligent identification statistical analysis module;
the 3D space acquisition processing module comprises camera imaging units symmetrically arranged on the front side and the back side of the steel plate, and the camera imaging units acquire images of the front side and the back side of the steel plate by adopting 3D structured light and transmit the images to the control analysis module;
the object form visualization module acquires images of the front side and the back side of the steel plate from the control analysis module, the images are projected by the linear array laser light source and are influenced by surface defects of the steel plate, the linear array laser light source is reflected to be in a bending state, the resolutions of suspected defects in different directions are acquired by the triangulation principle, so that the area and the depth of the suspected defects are acquired, and the suspected defects on the front side and the back side of the steel plate are identified and transmitted to the control analysis module;
the defect intelligent identification statistical analysis module acquires images of the front side and the back side of the steel plate and suspected defect identification from the control analysis module, analyzes and calculates the area and the depth of the suspected defect, compares the area and the depth with a set threshold of the surface defect of the steel plate, judges the surface defect of the steel plate if the area and the depth are larger than the set threshold, and transmits the surface defect and distribution data of the steel plate to the control analysis module according to the distribution of the statistical defect of the surface defect of the steel plate on the front side and the back side of the steel plate;
the control analysis module integrates the defects on the front side and the back side of the steel plate and the defect distribution images according to the defects and the distribution data on the surface of the steel plate, analyzes and calculates the characteristic data of the defects of the steel plate, and performs grade classification on the steel plate according to the characteristic data of the defects of the steel plate.
2. The system for on-line image detection of surface defects of steel sheets according to claim 1, wherein: and a camera imaging unit of the 3D space acquisition and processing module projects the projection position of the suspected defect on the surface of the steel plate by adopting 3D structured light.
3. The system for on-line image detection of surface defects of steel sheets according to claim 1 or 2, wherein: the object form visualization module acquires resolutions of suspected defects in different directions through a triangulation principle, an encoder is adopted to record a moving distance of a steel plate in a moving process of the steel plate to obtain an X coordinate of the moving direction of the steel plate, a camera imaging unit inherent coordinate system represents a Y coordinate of the width direction of the steel plate, and an offset of a linear array light source reflecting a curve in a bending state represents a Z coordinate of the depth direction of the defects; the X-direction moving distance corresponding to the front image and the back image of the front surface and the back surface of the steel plate is determined, the smaller the distance is, the higher the X-direction resolution is, the highest frame frequency exists in a camera imaging unit, the X-direction resolution is determined by the frame frequency and the moving linear speed of the steel plate, the Y-direction resolution is determined by a camera pixel, and the Z-direction resolution is determined by the camera pixel, the included angle between the camera and a plane normal and the included angle between 3D structured light and the plane normal.
4. The system for on-line image detection of surface defects of steel sheets according to claim 3, wherein: the intelligent defect identification statistical analysis module obtains a continuous 3D structured light image of the surface of the steel plate, calculates to obtain 3D point cloud data information of the surface defects of the steel plate, and performs clustering analysis on the defects with suspected defect areas and overproof depths through iterative fitting of a reference surface.
5. The system for on-line image detection of surface defects of steel sheets according to claim 3, wherein: the management module acquires real-time information of the surface defects of the steel plate in the steel plate surface treatment process through the control analysis module, stores and displays images of the upper surface and the lower surface of the steel plate, defects, defect distribution and statistical classification charts in real time, and gives an alarm when the surface defects of the steel plate are detected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010661263.2A CN113916900A (en) | 2020-07-10 | 2020-07-10 | Online image detection system for surface defects of steel plate |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010661263.2A CN113916900A (en) | 2020-07-10 | 2020-07-10 | Online image detection system for surface defects of steel plate |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113916900A true CN113916900A (en) | 2022-01-11 |
Family
ID=79232068
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010661263.2A Pending CN113916900A (en) | 2020-07-10 | 2020-07-10 | Online image detection system for surface defects of steel plate |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113916900A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114527072A (en) * | 2022-02-05 | 2022-05-24 | 上海研视信息科技有限公司 | Steel plate defect detection system based on structured light scanning |
-
2020
- 2020-07-10 CN CN202010661263.2A patent/CN113916900A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114527072A (en) * | 2022-02-05 | 2022-05-24 | 上海研视信息科技有限公司 | Steel plate defect detection system based on structured light scanning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101871895B (en) | Laser scanning imaging nondestructive inspection method for hot continuous casting blank surface defects | |
CN103913468B (en) | Many defects of vision checkout equipment and the method for large-scale LCD glass substrate on production line | |
CN210155545U (en) | Be used for automatic on-line measuring equipment of switch manufacturing process | |
US7495758B2 (en) | Apparatus and methods for two-dimensional and three-dimensional inspection of a workpiece | |
CN113465511B (en) | Steel coil size online measurement and omnibearing end surface defect online detection method | |
KR101602376B1 (en) | A train faulty monitoring system | |
CN108458668A (en) | Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method | |
CN107678036A (en) | A kind of vehicle-mounted contactless contact net geometric parameter dynamic detection system and method | |
CN104897052A (en) | Method for measuring steel rail appearance geometric dimension and surface quality and device thereof | |
EP3775854B1 (en) | System for the detection of defects on a surface of at least a portion of a body and method thereof | |
CN104394385A (en) | Online detection device and detection method for ceramic tile quality | |
CN116678399B (en) | Multisource information fusion positioning method and system of container internal transport sensing system | |
CN114037703B (en) | Subway valve state detection method based on two-dimensional positioning and three-dimensional attitude calculation | |
CN112378344A (en) | Tire pattern depth measuring device and method and computer readable storage medium | |
CN107561083A (en) | A kind of surface quality of steel detecting system | |
CN114638797A (en) | Method and device for detecting copper surface defects based on linear array camera | |
CN212540183U (en) | Rod surface defect on-line measuring system | |
CN108582075A (en) | A kind of intelligent robot vision automation grasping system | |
CN113916900A (en) | Online image detection system for surface defects of steel plate | |
CN116429768A (en) | Sealing nail welding quality detection method, system, equipment and storage medium | |
CN116908107A (en) | Paint surface flaw detection system based on machine vision | |
CN114596301A (en) | Coating roller surface defect detection system adopting 3D line laser profile technology | |
EP4009273A1 (en) | Cloud-to-cloud comparison using artificial intelligence-based analysis | |
CN110715623A (en) | Ceramic tile flatness detection equipment and method | |
CN107806824A (en) | The detection method and device of contact net geometric parameter under a kind of lower-speed state |
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 |