CN104914111A - Strip steel surface defect on-line intelligent identification and detection system and detection method - Google Patents
Strip steel surface defect on-line intelligent identification and detection system and detection method Download PDFInfo
- Publication number
- CN104914111A CN104914111A CN201510252979.6A CN201510252979A CN104914111A CN 104914111 A CN104914111 A CN 104914111A CN 201510252979 A CN201510252979 A CN 201510252979A CN 104914111 A CN104914111 A CN 104914111A
- Authority
- CN
- China
- Prior art keywords
- detection
- defect
- image
- defects
- identification
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 150
- 238000001514 detection method Methods 0.000 title claims abstract description 129
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 67
- 239000010959 steel Substances 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000003384 imaging method Methods 0.000 claims abstract description 22
- 238000007689 inspection Methods 0.000 claims abstract description 13
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 238000012937 correction Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000012512 characterization method Methods 0.000 claims description 8
- 238000005303 weighing Methods 0.000 claims description 8
- 230000008676 import Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000011002 quantification Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 230000009395 genetic defect Effects 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 12
- 238000011897 real-time detection Methods 0.000 abstract description 7
- 230000008901 benefit Effects 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 8
- 230000006872 improvement Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000005098 hot rolling Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000010960 cold rolled steel Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000005554 pickling Methods 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000007858 starting material Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a strip steel surface defect on-line intelligent identification and detection method. The method comprises image acquisition, feature extraction, multistage defect detection and identification, and result output. The invention also provides a strip steel surface defect on-line intelligent identification and detection system. The system comprises an encoder, a linear LED light source, a high speed linear array CCD camera, an image processor, a detection computer, a server computer, a quality inspection terminal computer and a printer. The detection system and detection method optimize a defect image acquisition and imaging technology, can acquire clear and complete defect images, improve a detect image processing technology, and realize complete and effective extraction of image characteristics. The method utilizes the multistage defect detection and identification method comprising primary defect detection and identification, secondary defect detection and identification and SVM identification, solves the problem that the prior art has a single detection method, is suitable for detection of a plurality of types of strip steel defects and has the advantages of real-time detection, accurate classification and high accuracy.
Description
Technical field
The present invention relates to surface of cold-rolled steel plate quality information online measuring technique, particularly relate to a kind of steel strip surface defect online intelligent recognition detection system and detection method thereof.
Background technology
China is iron and steel big producing country, band steel due to its widely range of application become the industrial indispensable starting material such as automobile production, machine-building, chemical industry, Aero-Space, shipbuilding, wherein the quality of belt steel surface plays decisive role to its oeverall quality and even the market competitiveness.Band steel preparation technology is divided into cold-strip steel technique, strip steel hot rolling process two kinds.Wherein, cold-strip steel technique comprises: pickling, rolling, annealing, rolling size are synchronously lubricated, upper rust preventive oil, smooth scale, polishing and packaging; Strip steel hot rolling process comprises: heating furnace, dephosphorizing machine, roughing mill, dephosphorizing machine, finishing mill, surperficial quality inspection instrument, layer are cold, coiling machine, bundling, jetting device for making number and item pool slab.
Band steel step of preparation process more complicated, simultaneously can due to the impact by the aspect such as rolling equipment, processing technology factor, make belt steel surface easily form the dissimilar defect of roll marks, scratch, hole etc. tens kinds, these defects have had a strong impact on the Performance and quality of final products.At present, the method for strip surface quality defects detection many employings artificial visually examine, or simple mechanical & electrical technology or optical technology detection method.
Manual detection mode has following shortcoming: have and cannot keep watch at the scene for a long time, especially severe production environment, cannot accomplish 24 hours on-line checkingi; Cannot be small in cavity to some, the major defects such as scuffing detect; Very large subjectivity is had to the identification of defect and differentiation, especially in the larger situation of on-the-spot interference, very large to quality influence of fluctuations; Cannot complete and accurate record and follow the trail of steel defect, careful classification and scalar quantization process cannot be carried out to defect.Based on simple mechanical & electrical technology or optics, the craftsmenship that requires as EDDY CURRENT of check system is high timely, and polished surface or rough surface can affect testing result.Flux-leakage detection method can not detect coarse surface, can not precisely identify defect.Laser detecting method cost is high-leveled and difficult in maintenance.
Application number is disclose a kind of steel strip surface defect test platform based on machine vision and detection method thereof in the patent application document of 200610117168.6, can analog band steel rectilinear motion, by camera and light source compatibility test, thus obtain the construction method of the test platform of steel defect optimized image; Application number is disclose a kind of image type online flaws detection equipment in line array for surface of strip steel and detection method thereof in the patent application document of 200510010049.6, is realized the method completed on a computer belt steel surface Real-Time Monitoring by a kind of structure of on-Line Monitor Device; Above-mentioned two kinds of detection methods all do not propose new detection and sorting technique, can not detect in real time, comprehensively, accurately to steel strip surface defect and classify.Application number is disclose a kind of on-line detection method for continuous plate blank surface crack in the patent application document of 200910092408.5, the method achieve the online crack detection to high temperature slab, but the method can only realize on-line checkingi for a kind of defect, and can not realize on-line checkingi and the classification of number of drawbacks simultaneously.
Therefore, how to invent that a kind of to have real-time detection, the steel strip surface defect online intelligent recognition detection system of exact classification and high-accuracy and detection method thereof be that those skilled in the art have technical barrier to be solved.
Summary of the invention
For prior art Problems existing, the present invention is that the technical matters that will solve provides a kind of steel strip surface defect online intelligent recognition detection method with real-time detection, exact classification and high-accuracy, this method solves the problem that in steel strip surface defect detection technique, detection means is single.The present invention additionally provides a kind of steel strip surface defect online intelligent recognition detection system on the other hand, and this system architecture is simple, complete function, and detection means is enriched, and is applicable to the detection of dissimilar steel strip surface defect.
For solving the problems of the technologies described above, the present invention includes following technical scheme:
A kind of steel strip surface defect online intelligent recognition detection method, comprises the following steps,
The upper and lower surface of step 101 light source irradiation band steel, gathered belt steel surface original image by high speed linear array CCD, the original image collected imports image processor into after being converted to numerical information;
The numerical information of step 201 image processor to the original image imported into corrects, and then carries out to the those suspected defects image after correction the extraction implementing segmentation and characteristics of image, and imports detection computations machine into;
False defect target removed by step 301 detection computations machine, merges defect of the same type based on pacing items filter type simultaneously, then carries out characterization rules and detects identification;
Step 401 detection computations machine loads some classification of defects rule sets, carries out detection identification by classification of defects rule set to the defect target that characterization rules detects identification None-identified;
The defect type of step 501 detection computations machine to classification of defects rule set None-identified carries out characteristic weighing normalized and is quantized, and carries out detection identify based on sample pattern storehouse by SVM method to the defect target after quantification treatment;
The classification process that step 601 detection computations machine carries out the defect target identified based on setting attribute conditions;
Step 701 carries out Storage & Display with the genetic defects image of steel and the detection recognition result of detection computations machine.
Step 201 of the present invention is specially: image processor adopts the self-adaptation image enhancement technique of GPU parallel computation to carry out gamma correction and Imaging enhanced to defect image; By partitioning algorithm, Real-time segmentation is carried out to the those suspected defects image after correction, and extract the characteristics of image such as its geometry, color, texture and topology.
Classification of defects rule set in step 401 is the intended target rule of being synthesized by detection computations machine by artificial editing classification rule.
In step 501, characteristic weighing normalized is specially: the geometry of defect image, color, the characteristics of image such as texture and topology carry out mixed weighting after being endowed eigenwert, are quantized into specific proper vector.
Sample pattern storehouse in step 501 is the database that detection computations machine generates after target sample simulated training.
Recognition detection method of the present invention optimizes collection and the imaging technique of defect image, adopts the image imaging mode of high speed linear array camera and linear monochromatic source, can collect those suspected defects image clearly; The optics correcting function of Corpus--based Method, effectively eliminates the interference of external environment condition to imaging simultaneously; Adopt the adaptive image enhancement technology of GPU parallel computation in addition, make imaging more clear and complete.
Recognition detection method of the present invention has also made improvement to the process of defect image, by the self-adaptive projection method/extractive technique based on global statistics and partial analysis, no matter for the high single defect of accuracy requirement or the large planar defect of distribution range, all can the complete abnormal area effectively extracted in image.
Recognition detection method of the present invention overcomes the single problem of detection means in prior art, first carries out characterization rules detection to defect image, determines first defects detection recognition result; Based on classification of defects rule set, secondary defect is carried out to the Unidentified defect type of first defects detection identification and detects identification; Because steel defect kind is many, the morphologic appearance difference of defect is very large, thus cause steel defect feature relative distribution, be not easy to extract general character, secondary defect is detected and identifies that Unidentified defect type carries out characteristic weighing normalized and quantized, and by SVM method, detection identification is carried out to the defect target after quantification treatment based on sample pattern storehouse; The present invention devises above-mentioned multistage defects detection recognition methods, has the advantage of real-time detection, exact classification and high-accuracy.
A kind of steel strip surface defect online intelligent recognition detection system, this system comprises the mechanical component of travelling belt steel, be arranged on the scrambler above measuring tape steel to be checked, be positioned at measuring tape the steel to be checked relatively linear LED light source of both sides and high speed linear array CCD camera up and down, by the image processor that gigabit internal lan is connected with scrambler, CCD camera, for the detection computations machine of defects detection, recognition and classification, for controlling the operation of whole system, the storage of data, the server computer of result display, and for the quality inspection end computing machine of data analysis.
The real-time derivation of conveniently form and defect analysis result in the present invention, quality inspection end computing machine is also connected with printer.
Beneficial effect of the present invention is as follows:
Detection system of the present invention and detection method optimize collection and the imaging technique of defect image, effectively eliminate the interference of external environment condition to imaging, can collect clear complete defect image; The present invention has also made improvement to the treatment technology of defect image, by the self-adaptive projection method/extractive technique based on global statistics and partial analysis, and can the complete characteristics of image effectively extracted in image; The present invention have also been devised the multistage defects detection recognition methods comprising first defects detection identification, secondary defect detection identification and SVM and identify, overcome the problem that detection means in prior art is single, detect the advantage that polytype steel defect all has real-time detection, exact classification and high-accuracy.
Accompanying drawing explanation
Fig. 1 is target sample simulated training and the defects detection identification process figure of embodiment 1.
Fig. 2 is the workflow diagram of embodiment 1 steel strip surface defect online intelligent recognition detection system.
Fig. 3 is the structural representation of embodiment 1 steel strip surface defect online intelligent recognition detection system.
Fig. 4 is the fundamental diagram of embodiment 2 steel strip surface defect online intelligent recognition detection system.
Embodiment
For enabling above-mentioned purpose of the present invention, feature and advantage become apparent more, are described in detail the specific embodiment of the present invention below in conjunction with accompanying drawing.
Embodiment 1
Fig. 1 is target sample simulated training and the defects detection identification process figure of the present embodiment.Steel strip surface defect online intelligent recognition detection method, comprises the following steps,
The upper and lower surface of step 101 light source irradiation band steel, is gathered belt steel surface original image by high speed linear array CCD, imports image processor into after the genetic defects image collected is converted to numerical information;
The recognition detection method of the present embodiment optimizes collection and the imaging technique of defect image, adopts the video imaging mode of high speed linear array camera and linear monochromatic source, can collect defect image clearly; The optics correcting function of Corpus--based Method, effectively eliminates the interference of external environment condition to imaging simultaneously; Adopt the self-adaptation image enhancement technique of GPU parallel computation in addition, make defect imaging more clear and complete.
The numerical information of step 201 image processor to the original image imported into corrects, and then carries out to the defect image after correction the extraction implementing segmentation and characteristics of image, and imports detection computations machine into;
Particularly, image processor adopts the self-adaptation image enhancement technique of GPU parallel computation to carry out gamma correction and Imaging enhanced to original image; By partitioning algorithm, Real-time segmentation is carried out to the those suspected defects image after correction, and extract the characteristics of image such as its geometry, color, texture and topology.
The recognition detection method of the present embodiment has also made improvement to the process of defect image, by the self-adaptation Image Segmentation/extractive technique based on global statistics and partial analysis, no matter for the high single defect of accuracy requirement or the large planar defect of distribution range, all can the complete abnormal area effectively extracted in image.
False defect target removed by step 301 detection computations machine, merges defect of the same type based on pacing items filter type simultaneously, then carries out characterization rules and detects identification;
Step 401 detection computations machine loads some classification of defects rule sets, carries out detection identification by classification of defects rule set to the defect target that characterization rules detects identification None-identified;
Wherein, classification of defects rule set is the intended target rule of being synthesized by detection computations machine by artificial editing classification rule.
The defect type of step 501 detection computations machine to classification of defects rule set None-identified carries out characteristic weighing normalized and is quantized, and carries out detection identify based on sample pattern storehouse by SVM method to the defect target after quantification treatment;
Particularly, characteristic weighing normalized is specially: the geometry of defect image, color, the characteristics of image such as texture and topology carry out mixed weighting after being endowed eigenwert, are quantized into specific proper vector; Sample pattern storehouse is the database that detection computations machine generates after target sample simulated training.
The classification process that step 601 detection computations machine carries out the defect target identified based on setting attribute conditions;
Step 701 carries out Storage & Display with the genetic defects image of steel and the detection recognition result of detection computations machine.
The recognition detection method of the present embodiment overcomes the single problem of detection means in prior art, first carries out characterization rules detection to defect image, determines first defects detection recognition result; Based on classification of defects rule set, secondary defect is carried out to the Unidentified defect type of first defects detection identification and detects identification; Because steel defect kind is many, the morphologic appearance difference of defect is very large, thus cause steel defect feature relative distribution, be not easy to extract general character, secondary defect is detected and identifies that Unidentified defect type carries out characteristic weighing normalized and quantized, and by SVM method, detection identification is carried out to the defect target after quantification treatment based on sample pattern storehouse; The present invention devises above-mentioned multistage defects detection recognition methods, has the advantage of real-time detection, exact classification and high-accuracy.
Fig. 3 is the structural representation of steel strip surface defect online intelligent recognition detection system, this system comprises the mechanical component 1 of travelling belt steel, be arranged on the scrambler 2 above measuring tape steel to be checked, be positioned at measuring tape the steel to be checked relatively linear LED light source 3 of both sides and high speed linear array CCD camera 4 up and down, by gigabit internal lan and scrambler 1, CCD camera is 4 image processors 5 connected mutually, for defects detection, the detection computations machine 6 of recognition and classification, for controlling the operation of whole system, the storage of data, the server computer 7 of result display, and for the quality inspection end computing machine 8 of data analysis.The conveniently real-time derivation of form and defect analysis result, quality inspection end computing machine 8 is also connected with printer 9.
Again as shown in Figure 2, the system of the present embodiment is divided into imaging acquisition system, detects recognition system, controls service system and quality inspection browing system four levels.Imaging acquisition system comprises linear LED light source, high speed linear array CCD camera and mechanical component; Detect recognition system and comprise some detection computations machines; Control service system and comprise server computer; Quality inspection browing system comprises quality inspection end counter.
Embodiment 2
Fig. 4 is the fundamental diagram of the steel strip surface defect online intelligent recognition detection system of the present embodiment.The system that this system comprises the present embodiment is divided into imaging acquisition system, detects recognition system, controls service system and quality inspection browing system four levels.
Wherein, acquisition system comprises illuminator, imaging system, physical construction and NBC protection system, detect recognition system and comprise some defects detection computing machines, detect recognition system and carry out light source control, camera control and system status monitoring to imaging acquisition system, imaging acquisition system carries out image acquisitions and transmission.Detect recognition system to distribute by detections end to end, weld seam detection, hardware controls, defects detection, defect filtrations, defect merging, classification of defects, defect system and result and carry out detection and indentification to defect, raw video and detection recognition result are transferred to control service system by detection recognition system.Control service system comprises System control computer and data store computing machine, carries out communication between system state control and system to detection recognition system, controls service system and monitors in real time for flow process supervision, system state, show testing result and archives data.Quality inspection browing system comprises Quality control computer, quality monitoring computing machine and quality analysis and calculates machine, is mainly used in quality report generation, defect statistical analysis, causes of defects analysis and defects liability and reviews.
In sum, detection system of the present invention and detection method optimize collection and the imaging technique of defect image, effectively eliminate the interference of external environment condition to imaging, can collect the original image of complete display; The present invention has also made improvement to the treatment technology of image, by the self-adaptive projection method/extractive technique based on global statistics and partial analysis, and can the complete characteristics of image effectively extracted in image; The present invention have also been devised comprise first defects detection identification, secondary defect detects the multistage defects detection recognition methods identifying and identify with SVM, detects the advantage that polytype steel defect all has real-time detection, exact classification and high-accuracy.
The above embodiment is only that the preferred embodiment of the present invention is described; not scope of the present invention is limited; under not departing from the present invention and designing the prerequisite of spirit; the various distortion that those of ordinary skill in the art make technical scheme of the present invention and improvement, all should fall in protection domain that claims of the present invention determine.
Claims (7)
1. a steel strip surface defect online intelligent recognition detection method, is characterized in that, said method comprising the steps of,
The upper and lower surface of step 101 light source irradiation band steel, gathered belt steel surface original image by high speed linear array CCD, the original image collected imports image processor into after being converted to numerical information;
The numerical information of step 201 image processor to the original image imported into corrects, and then carries out to the those suspected defects image after correction the extraction implementing segmentation and characteristics of image, and imports detection computations machine into;
False defect target removed by step 301 detection computations machine, merges defect of the same type based on pacing items filter type simultaneously, then carries out characterization rules and detects identification;
Step 401 detection computations machine loads some classification of defects rule sets, carries out detection identification by classification of defects rule set to the defect target that characterization rules detects identification None-identified;
The defect type of step 501 detection computations machine to classification of defects rule set None-identified carries out characteristic weighing normalized and is quantized, and carries out detection identify based on sample pattern storehouse by SVM method to the defect target after quantification treatment;
The classification process that step 601 detection computations machine carries out the defect target identified based on setting attribute conditions;
Step 701 carries out Storage & Display with the genetic defects image of steel and the detection recognition result of detection computations machine.
2. steel strip surface defect online intelligent recognition detection method as claimed in claim 1, it is characterized in that, step 201 is specially: image processor adopts the self-adaptation image enhancement technique of GPU parallel computation to carry out gamma correction and Imaging enhanced to original image; By partitioning algorithm, Real-time segmentation is carried out to the those suspected defects image after correction, and extract the characteristics of image such as its geometry, color, texture and topology.
3. steel strip surface defect online intelligent recognition detection method as claimed in claim 1, is characterized in that, the classification of defects rule set in step 401 is the intended target rule of being synthesized by detection computations machine by artificial editing classification rule.
4. steel strip surface defect online intelligent recognition detection method as claimed in claim 1, it is characterized in that, in step 501, characteristic weighing normalized is specially: the geometry of defect image, color, the characteristics of image such as texture and topology carry out mixed weighting after being endowed eigenwert, are quantized into specific proper vector.
5. steel strip surface defect online intelligent recognition detection method as claimed in claim 1, it is characterized in that, the sample pattern storehouse in step 501 is the database that detection computations machine generates after target sample simulated training.
6. a steel strip surface defect online intelligent recognition detection system, it is characterized in that, this system comprises the mechanical component (1) of travelling belt steel, be arranged on the scrambler (2) above measuring tape steel to be checked, be positioned at measuring tape the steel to be checked relatively linear LED light source (3) of both sides and high speed linear array CCD camera (4) up and down, by gigabit internal lan and scrambler (2), the image processor (5) that CCD camera (4) is connected, for defects detection, the detection computations machine (6) of recognition and classification, for controlling the operation of whole system, the storage of data, the server computer (7) of result display, and for the quality inspection end computing machine (8) of data analysis.
7. steel strip surface defect online intelligent recognition detection system as claimed in claim 6, it is characterized in that, described quality inspection end computing machine (8) is connected with printer (9).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510252979.6A CN104914111B (en) | 2015-05-18 | 2015-05-18 | A kind of steel strip surface defect online intelligent recognition detecting system and its detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510252979.6A CN104914111B (en) | 2015-05-18 | 2015-05-18 | A kind of steel strip surface defect online intelligent recognition detecting system and its detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104914111A true CN104914111A (en) | 2015-09-16 |
| CN104914111B CN104914111B (en) | 2018-08-03 |
Family
ID=54083361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510252979.6A Expired - Fee Related CN104914111B (en) | 2015-05-18 | 2015-05-18 | A kind of steel strip surface defect online intelligent recognition detecting system and its detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104914111B (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105158273A (en) * | 2015-09-30 | 2015-12-16 | 江苏亨通光电股份有限公司 | Optical cable surface defect detecting system based on planar array CMOS cameras |
| CN105354848A (en) * | 2015-11-11 | 2016-02-24 | 首钢总公司 | Optimization method of Cognex surface quality detection system of hot galvanizing production line |
| CN106767416A (en) * | 2017-01-04 | 2017-05-31 | 纵科（武汉）信息技术有限公司 | Piece test system and method |
| CN107202797A (en) * | 2017-07-06 | 2017-09-26 | 天津电气科学研究院有限公司 | Contactless Continuous Hot Dip Galvanizing Line strip steel weld joint detecting system and its method |
| CN107730486A (en) * | 2017-09-15 | 2018-02-23 | 首钢京唐钢铁联合有限责任公司 | Rolling mill protection method and device for acid continuous rolling production line |
| CN107967681A (en) * | 2017-11-24 | 2018-04-27 | 常熟理工学院 | Defect inspection method is hindered in a kind of elevator compensation chain punching based on machine vision |
| CN108020554A (en) * | 2017-10-31 | 2018-05-11 | 无锡港湾网络科技有限公司 | A kind of steel strip surface defect recognition detection method |
| CN108445008A (en) * | 2018-02-27 | 2018-08-24 | 首钢京唐钢铁联合有限责任公司 | Method for detecting surface defects of strip steel |
| CN108463717A (en) * | 2016-01-26 | 2018-08-28 | 富士胶片株式会社 | Be cracked information detector, cracking information detecting method and cracking infomation detection program |
| CN108665452A (en) * | 2018-05-09 | 2018-10-16 | 广东大鹏液化天然气有限公司 | A kind of pipeline-weld film scanning storage and identification of Weld Defects and its system based on big data |
| CN108760746A (en) * | 2018-04-17 | 2018-11-06 | 苏州富鑫林光电科技有限公司 | A kind of micro-nano defect detecting device based on machine vision |
| CN109829883A (en) * | 2018-12-19 | 2019-05-31 | 歌尔股份有限公司 | Product quality detection method and device |
| CN109881356A (en) * | 2018-12-25 | 2019-06-14 | 西安工程大学 | Hosiery machine knitting needle on-line measuring device and method based on SVM image classification |
| CN109978883A (en) * | 2019-04-11 | 2019-07-05 | 中民筑友科技投资有限公司 | A kind of grout sleeve quality determining method, system, device and readable storage medium storing program for executing |
| CN110118784A (en) * | 2019-06-20 | 2019-08-13 | 山西大数据产业发展有限公司 | Coil of strip surface quality defect detection system based on machine vision |
| CN110530889A (en) * | 2018-05-25 | 2019-12-03 | 上海翌视信息技术有限公司 | A kind of optical detecting method suitable for industrial production line |
| CN110618134A (en) * | 2019-09-16 | 2019-12-27 | 山西大数据产业发展有限公司 | Steel plate surface quality defect detection and rating system and method |
| CN110956627A (en) * | 2019-12-13 | 2020-04-03 | 智泰科技股份有限公司 | Intelligent optical detection sample characteristic and flaw intelligent lighting image capturing method and device |
| CN110998463A (en) * | 2017-01-18 | 2020-04-10 | Asml荷兰有限公司 | Knowledge recommendation for defect inspection |
| CN111652834A (en) * | 2019-03-02 | 2020-09-11 | 周口师范学院 | Steel coil strapping tape identification method based on support vector machine |
| CN112598621A (en) * | 2020-11-27 | 2021-04-02 | 攀钢集团西昌钢钒有限公司 | Intelligent determination method for surface quality of cold-rolled strip steel |
| CN112666248A (en) * | 2020-12-16 | 2021-04-16 | 上海交通大学 | Weld defect automatic detection method and system based on deep learning |
| CN112775182A (en) * | 2020-12-29 | 2021-05-11 | 广州市荻亚机电设备有限公司 | Manufacturing equipment for producing cold-rolled steel plate for manufacturing high-end equipment |
| CN112881403A (en) * | 2021-01-08 | 2021-06-01 | 王玮佳 | Hot rolling strip steel surface defect detection device |
| CN112986277A (en) * | 2021-04-01 | 2021-06-18 | 北京科技大学设计研究院有限公司 | Detection method for hot-rolled strip steel finish rolling roll mark |
| CN113030114A (en) * | 2021-02-25 | 2021-06-25 | 首钢京唐钢铁联合有限责任公司 | Strip steel detection system and manufacturing method of vertical quality inspection platform |
| CN113252682A (en) * | 2021-04-15 | 2021-08-13 | 首钢集团有限公司 | Method for improving accuracy of surface quality detection system for identifying surface defects of strip steel |
| CN113256624A (en) * | 2021-06-29 | 2021-08-13 | 中移(上海)信息通信科技有限公司 | Continuous casting round billet defect detection method and device, electronic equipment and readable storage medium |
| CN113252683A (en) * | 2021-04-19 | 2021-08-13 | 唐山学院 | Material grouping optimization method of cold-rolled strip steel surface detection system |
| CN113670941A (en) * | 2021-08-30 | 2021-11-19 | 宝钢湛江钢铁有限公司 | Method for online quantitative evaluation of oxidation color defects on surface of multifunctional continuous annealing strip steel |
| CN117092116A (en) * | 2023-10-20 | 2023-11-21 | 上海嘉朗实业南通智能科技有限公司 | Automobile aluminum alloy casting defect detection system and method based on machine vision |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06323824A (en) * | 1993-05-13 | 1994-11-25 | Sharp Corp | Method and equipment for inspecting appearance of bump |
| CN102654464A (en) * | 2012-03-13 | 2012-09-05 | 浙江工业大学 | Copper strip surface defect detection system based on multi-feature fuzzy recognition |
| CN104318556A (en) * | 2014-10-16 | 2015-01-28 | 东北大学 | Silicon steel plate surface defect image detection method under oil pollution interference |
| CN104820985A (en) * | 2015-04-28 | 2015-08-05 | 电子科技大学 | Cable surface defect detection and character recognition device |
-
2015
- 2015-05-18 CN CN201510252979.6A patent/CN104914111B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06323824A (en) * | 1993-05-13 | 1994-11-25 | Sharp Corp | Method and equipment for inspecting appearance of bump |
| CN102654464A (en) * | 2012-03-13 | 2012-09-05 | 浙江工业大学 | Copper strip surface defect detection system based on multi-feature fuzzy recognition |
| CN104318556A (en) * | 2014-10-16 | 2015-01-28 | 东北大学 | Silicon steel plate surface defect image detection method under oil pollution interference |
| CN104820985A (en) * | 2015-04-28 | 2015-08-05 | 电子科技大学 | Cable surface defect detection and character recognition device |
Non-Patent Citations (3)
| Title |
|---|
| 朱向华等: "《一种基于支持向量机的带钢表面缺陷识别方法》", 《浙江工商职业技术学院学报》 * |
| 胡慧君等: "《基于机器学习的带钢表面缺陷分类方法研究》", 《计算机工程与设计》 * |
| 高雪梅: "《基于机器视觉的带钢表面缺陷检测系统研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105158273A (en) * | 2015-09-30 | 2015-12-16 | 江苏亨通光电股份有限公司 | Optical cable surface defect detecting system based on planar array CMOS cameras |
| CN105354848A (en) * | 2015-11-11 | 2016-02-24 | 首钢总公司 | Optimization method of Cognex surface quality detection system of hot galvanizing production line |
| CN105354848B (en) * | 2015-11-11 | 2019-04-23 | 首钢集团有限公司 | A kind of optimization method of the Cognex Surface Quality Inspection System of hot galvanizing producing line |
| CN108463717A (en) * | 2016-01-26 | 2018-08-28 | 富士胶片株式会社 | Be cracked information detector, cracking information detecting method and cracking infomation detection program |
| US10937138B2 (en) | 2016-01-26 | 2021-03-02 | Fujifilm Corporation | Crack information detection device, method of detecting crack information, and crack information detection program |
| CN108463717B (en) * | 2016-01-26 | 2021-05-25 | 富士胶片株式会社 | Crack information detection device, crack information detection method, and storage medium |
| CN106767416A (en) * | 2017-01-04 | 2017-05-31 | 纵科（武汉）信息技术有限公司 | Piece test system and method |
| US11650576B2 (en) | 2017-01-18 | 2023-05-16 | Asml Netherlands B.V. | Knowledge recommendation for defect review |
| CN110998463B (en) * | 2017-01-18 | 2023-08-25 | Asml荷兰有限公司 | Knowledge recommendation server and method for defect inspection |
| CN110998463A (en) * | 2017-01-18 | 2020-04-10 | Asml荷兰有限公司 | Knowledge recommendation for defect inspection |
| CN107202797A (en) * | 2017-07-06 | 2017-09-26 | 天津电气科学研究院有限公司 | Contactless Continuous Hot Dip Galvanizing Line strip steel weld joint detecting system and its method |
| CN107730486A (en) * | 2017-09-15 | 2018-02-23 | 首钢京唐钢铁联合有限责任公司 | Rolling mill protection method and device for acid continuous rolling production line |
| CN108020554A (en) * | 2017-10-31 | 2018-05-11 | 无锡港湾网络科技有限公司 | A kind of steel strip surface defect recognition detection method |
| CN107967681A (en) * | 2017-11-24 | 2018-04-27 | 常熟理工学院 | Defect inspection method is hindered in a kind of elevator compensation chain punching based on machine vision |
| CN107967681B (en) * | 2017-11-24 | 2020-04-21 | 常熟理工学院 | Elevator compensation chain impact defect detection method based on machine vision |
| CN108445008A (en) * | 2018-02-27 | 2018-08-24 | 首钢京唐钢铁联合有限责任公司 | Method for detecting surface defects of strip steel |
| CN108760746A (en) * | 2018-04-17 | 2018-11-06 | 苏州富鑫林光电科技有限公司 | A kind of micro-nano defect detecting device based on machine vision |
| CN108665452B (en) * | 2018-05-09 | 2019-06-07 | 广东大鹏液化天然气有限公司 | Pipeline-weld film scanning storage and identification of Weld Defects and its system |
| CN108665452A (en) * | 2018-05-09 | 2018-10-16 | 广东大鹏液化天然气有限公司 | A kind of pipeline-weld film scanning storage and identification of Weld Defects and its system based on big data |
| CN110530889A (en) * | 2018-05-25 | 2019-12-03 | 上海翌视信息技术有限公司 | A kind of optical detecting method suitable for industrial production line |
| CN109829883A (en) * | 2018-12-19 | 2019-05-31 | 歌尔股份有限公司 | Product quality detection method and device |
| CN109829883B (en) * | 2018-12-19 | 2020-11-17 | 歌尔光学科技有限公司 | Product quality detection method and device |
| CN109881356A (en) * | 2018-12-25 | 2019-06-14 | 西安工程大学 | Hosiery machine knitting needle on-line measuring device and method based on SVM image classification |
| CN111652834A (en) * | 2019-03-02 | 2020-09-11 | 周口师范学院 | Steel coil strapping tape identification method based on support vector machine |
| CN109978883A (en) * | 2019-04-11 | 2019-07-05 | 中民筑友科技投资有限公司 | A kind of grout sleeve quality determining method, system, device and readable storage medium storing program for executing |
| CN110118784A (en) * | 2019-06-20 | 2019-08-13 | 山西大数据产业发展有限公司 | Coil of strip surface quality defect detection system based on machine vision |
| CN110618134A (en) * | 2019-09-16 | 2019-12-27 | 山西大数据产业发展有限公司 | Steel plate surface quality defect detection and rating system and method |
| CN110956627A (en) * | 2019-12-13 | 2020-04-03 | 智泰科技股份有限公司 | Intelligent optical detection sample characteristic and flaw intelligent lighting image capturing method and device |
| CN112598621A (en) * | 2020-11-27 | 2021-04-02 | 攀钢集团西昌钢钒有限公司 | Intelligent determination method for surface quality of cold-rolled strip steel |
| CN112666248A (en) * | 2020-12-16 | 2021-04-16 | 上海交通大学 | Weld defect automatic detection method and system based on deep learning |
| CN112775182A (en) * | 2020-12-29 | 2021-05-11 | 广州市荻亚机电设备有限公司 | Manufacturing equipment for producing cold-rolled steel plate for manufacturing high-end equipment |
| CN112881403A (en) * | 2021-01-08 | 2021-06-01 | 王玮佳 | Hot rolling strip steel surface defect detection device |
| CN113030114B (en) * | 2021-02-25 | 2023-03-17 | 首钢京唐钢铁联合有限责任公司 | Strip steel detection system and manufacturing method of vertical quality inspection platform |
| CN113030114A (en) * | 2021-02-25 | 2021-06-25 | 首钢京唐钢铁联合有限责任公司 | Strip steel detection system and manufacturing method of vertical quality inspection platform |
| CN112986277A (en) * | 2021-04-01 | 2021-06-18 | 北京科技大学设计研究院有限公司 | Detection method for hot-rolled strip steel finish rolling roll mark |
| CN113252682A (en) * | 2021-04-15 | 2021-08-13 | 首钢集团有限公司 | Method for improving accuracy of surface quality detection system for identifying surface defects of strip steel |
| CN113252682B (en) * | 2021-04-15 | 2022-12-16 | 首钢集团有限公司 | Method for improving accuracy of surface quality detection system for identifying strip steel surface defects |
| CN113252683A (en) * | 2021-04-19 | 2021-08-13 | 唐山学院 | Material grouping optimization method of cold-rolled strip steel surface detection system |
| CN113256624A (en) * | 2021-06-29 | 2021-08-13 | 中移(上海)信息通信科技有限公司 | Continuous casting round billet defect detection method and device, electronic equipment and readable storage medium |
| CN113670941A (en) * | 2021-08-30 | 2021-11-19 | 宝钢湛江钢铁有限公司 | Method for online quantitative evaluation of oxidation color defects on surface of multifunctional continuous annealing strip steel |
| CN117092116A (en) * | 2023-10-20 | 2023-11-21 | 上海嘉朗实业南通智能科技有限公司 | Automobile aluminum alloy casting defect detection system and method based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104914111B (en) | 2018-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104914111A (en) | Strip steel surface defect on-line intelligent identification and detection system and detection method | |
| CN115294113B (en) | Quality detection method for wood veneer | |
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN106934800B (en) | Metal plate strip surface defect detection method and device based on YOLO9000 network | |
| CN101657277A (en) | Method for detecting and classifying surface defects on continuously cast slabs | |
| CN110992349A (en) | Underground pipeline abnormity automatic positioning and identification method based on deep learning | |
| CN103499585A (en) | Non-continuity lithium battery thin film defect detection method and device based on machine vision | |
| CN115541601A (en) | Steel low-power digital detection method based on machine vision | |
| CN104568956B (en) | The detection method of the steel strip surface defect based on machine vision | |
| CN110554052A (en) | artificial board surface defect detection method and system | |
| CN110096980A (en) | Character machining identifying system | |
| CN111591715A (en) | Belt longitudinal tearing detection method and device | |
| CN103033476A (en) | Equipment and method for online detecting tobacco leaves with stems based on infrared imaging | |
| CN113012098A (en) | Iron tower angle steel punching defect detection method based on BP neural network | |
| CN101949865B (en) | Method for optimizing Parsytec on-line surface defect detection system | |
| Litvintseva et al. | Real-time steel surface defect recognition based on CNN | |
| CN210775265U (en) | Artificial board surface defect detection system | |
| CN114565314A (en) | Hot rolled steel coil end face quality control system and method based on digital twinning | |
| CN105414206A (en) | Online rapid positioning method for cold-rolled strip steel edge | |
| CN110243475B (en) | Fabric color difference detection method based on machine vision recognition technology | |
| Bharat et al. | Surface finish evaluation using curvelet transforms based machine vision system | |
| Carruthers-Watt et al. | A vision based system for strip tracking measurement in the finishing train of a hot strip mill | |
| CN104849280A (en) | Continuous casting plate billet surface longitudinal crack detection method | |
| RU2426069C1 (en) | Rail surface quality nondestructive examination | |
| CN114813748A (en) | Steel surface defect detection method and system based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20181031 Address after: 100043 Beijing Shijingshan District apple orchard three District 19 19 1507 Patentee after: Liu Qiang Address before: 100041 Shijingshan District, Beijing, 30 street, No. 17, 6 floor, 31. Patentee before: BEIJING HUAJIAN ZHIYAN SOFTWARE TECHNOLOGY CO., LTD. |
|
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180803 Termination date: 20190518 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |