CN109692877A - A kind of Cold-strip Steel Surface quality control system and method - Google Patents
A kind of Cold-strip Steel Surface quality control system and method Download PDFInfo
- Publication number
- CN109692877A CN109692877A CN201811632987.3A CN201811632987A CN109692877A CN 109692877 A CN109692877 A CN 109692877A CN 201811632987 A CN201811632987 A CN 201811632987A CN 109692877 A CN109692877 A CN 109692877A
- Authority
- CN
- China
- Prior art keywords
- defect
- cold
- strip steel
- steel surface
- sample
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B38/00—Methods or devices for measuring, detecting or monitoring specially adapted for metal-rolling mills, e.g. position detection, inspection of the product
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention belongs to cold-strip steel technical field, a kind of Cold-strip Steel Surface quality control system and method are specifically provided.For the deficiency of existing Cold-strip Steel Surface quality on-line detection system, establish defect sample, establish Cold-strip Steel Surface mass defect treatment Countermeasures table, Cold-strip Steel Surface quality testing is associated with quality improvement, by Cold-strip Steel Surface defect and defect sample progress to the strip surface quality grade for judging Cold-strip Steel Surface defect, to Instructing manufacture process modification, Cold-strip Steel Surface quality is promoted；On the other hand, using angular distance method rejecting abnormalities sample, the label accuracy rate of defect sample is improved.
Description
Technical field
The invention belongs to cold-strip steel technical fields, and in particular to a kind of Cold-strip Steel Surface quality control system and side
Method.
Background technique
As the products such as automobile, household electrical appliances are higher and higher to strip surface quality requirement, enterprise is to Cold-strip Steel Surface quality
More pay attention to, domestic each Large Steel enterprise is each equipped with strip surface quality on-line detecting system on rolling mill production line, online to examine
Survey identification Cold-strip Steel Surface quality.
In the process of running, there are two aspect limitations for strip surface quality on-line detecting system: one, defect sample number
Amount, uniformity and label accuracy rate are inadequate, cause strip surface quality on-line detecting system discrimination relatively low；Two, band is identified
After steel surface mass defect, lack strip surface quality evaluation and quality improvement suggestion, so that strip surface quality on-line checking
System is practical, and to be converted to benefit unobvious.
Summary of the invention
The purpose of the present invention is overcome strip surface quality on-line detecting system is practical to be in the prior art converted to benefit not
Obvious problem.
For this purpose, the present invention provides a kind of Cold-strip Steel Surface quality control system, including Cold-strip Steel Surface quality lacks
Fall into identification module, Cold-strip Steel Surface mass defect memory module, Cold-strip Steel Surface mass defect sample labeling module, cold rolling
Strip surface quality evaluation module and Cold-strip Steel Surface quality improvement modules；
The Cold-strip Steel Surface mass defect identification module is used to detect the case of surface defects of cold-strip steel；
The Cold-strip Steel Surface mass defect memory module is for will test defective Cold-strip Steel Surface defect
It is saved；
The Cold-strip Steel Surface mass defect sample labeling module is for marking and storing defect sample；
The Cold-strip Steel Surface quality assessment module is used for the Cold-strip Steel Surface defect and the defect sample
Progress is to the classification and strip surface quality grade for judging the Cold-strip Steel Surface defect；
The Cold-strip Steel Surface quality improvement modules are used for classification and strip according to the Cold-strip Steel Surface defect
Surface quality grades offer is correspondingly improved strategy, and by the classification of Cold-strip Steel Surface defect, improvement strategy and processing result
It is stored.
Preferably, the Cold-strip Steel Surface defect and the defect sample include defect classification, coil of strip number, defect
Characteristic value and defect map piece path, the defect characteristic value are thin comprising defect area, defect length, defect perimeter, defect area
Long ratio and the defect shape factor.
Preferably, the Cold-strip Steel Surface quality assessment module according to every coiled strip steel defect classification in defect sample and lacks
Characteristic value data is fallen into, and strip surface quality evaluation model, quantization assessment sample belt steel surface matter are constructed based on analytic hierarchy process (AHP)
Measure grade.
Preferably, the strip surface quality evaluation model are as follows: sample strip surface quality grade=defect characteristic value ×
Rank power, the rank power are the size of corresponding weight in the defect characteristic value.
It preferably, further include that exceptional sample rejects module, the exceptional sample is rejected module and is used for according to the defect sample
This defect characteristic value rejects the anomalous body in the defect sample.
Preferably, the exceptional sample is rejected module and is picked according to the exceptional sample scalping method of the angular distance of defect
It removes, specifically includes:
S1, the i-th point A, i=1 in defect sample is chosen；
Non- i-th point of B and C two o'clock in S2, optional defect sample, obtains vector product<AB using A as vertex, AC>, vector
Mould | AB | and vector mould | AC |, and obtain co sinus vector included angle cos=<AB, AC>/, and traverse in the defect sample all
B, C point combines；
S3, i-th point of all mix vector included angle cosine value variance in the defect sample is calculatedWherein
σ2For variance, X is co sinus vector included angle, and μ is co sinus vector included angle mean value, and N is defect sample sum；
S4, compare i and N size, if i≤N, i=i+1, return to S1, if i=N, enter in next step；
S5, the co sinus vector included angle value variance of all the points is ranked up；
S6, take wherein the smallest k point of co sinus vector included angle value variance be abnormal point, k is positive integer；
S7, end.
Preferably, the system also includes classifier training module, the classifier training module includes classification based training device,
The classifier training module is according to the feature configuration classification based training device of the defect sample, and the classification based training device is to described scarce
Sunken sample is read out.
Preferably, the classification based training device includes in decision Tree algorithms, Adaboost algorithm or artificial neural network algorithm
It is one or more.
The present invention also provides a kind of Cold-strip Steel Surface method for quality control, comprising the following steps:
S100: defect sample is established；
S200: detecting the surface defect of cold-strip steel, will test defective Cold-strip Steel Surface defect and is saved；
S300: the Cold-strip Steel Surface defect and the defect sample are carried out to judging the Cold-strip Steel Surface
The strip surface quality grade of defect；
S400: being correspondingly improved strategy according to the offer of the classification of the Cold-strip Steel Surface defect, and by cold-strip steel table
Classification, improvement strategy and the processing result of planar defect are stored.
Beneficial effects of the present invention: this Cold-strip Steel Surface quality control system provided by the invention and method.For
The deficiency of existing Cold-strip Steel Surface quality on-line detection system, establishes defect sample, establishes Cold-strip Steel Surface mass defect
Treatment Countermeasures table associates Cold-strip Steel Surface quality testing with quality improvement, by Cold-strip Steel Surface defect and defect
Sample progress is to the strip surface quality grade for judging Cold-strip Steel Surface defect, so that Instructing manufacture process modification, is promoted
Cold-strip Steel Surface quality；On the other hand, using angular distance method rejecting abnormalities sample, the label for improving defect sample is accurate
Rate.
Cold-strip Steel Surface quality control system provided by the invention and method have the advantage that
(1) sample labeling of Cold-strip Steel Surface quality control system covers Cold-strip Steel Surface quality typical defect (hole
Hole folds, scabs while splitting, impression, and roll marks is pressed into, and scratches, sticks up skin, iron scale etc.), classification can be expanded；
(2) the every class defect sample quantity of the label of Cold-strip Steel Surface quality control system is 300~500, sample standard deviation
It is even, quantity is sufficient and facilitates update；
(3) Cold-strip Steel Surface quality control system is by angular distance method to Cold-strip Steel Surface Dealing the Quality Knowledge Database sample
Sample is handled in table, is based on sample characteristics rejecting abnormalities sample, it is ensured that sample is clean；
(4) Cold-strip Steel Surface quality control system is according to every coiled strip steel all defect type and Level in defect table
Data construct strip surface quality evaluation model, quantization assessment strip surface quality based on AHP method；
(5) Cold-strip Steel Surface quality control system provides surface quality to the defect for influencing Cold-strip Steel Surface quality
It handles improved method and suggests, scene is instructed to carry out quality improvement.
The present invention is described in further details below with reference to attached drawing.
Detailed description of the invention
Fig. 1 is Cold-strip Steel Surface quality control system module diagram of the present invention；
Fig. 2 is Cold-strip Steel Surface quality control system schematic diagram of logic principle of the present invention；
Fig. 3 is the rejecting algorithm flow chart of Cold-strip Steel Surface quality control system of the present invention and method；
Fig. 4 is the strip quality evaluation model based on AHP of Cold-strip Steel Surface quality control system of the present invention and method
Figure；
Fig. 5 is the user interface schematic diagram of Cold-strip Steel Surface quality control system of the present invention and method.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts all other
Embodiment shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that, term " center ", "upper", "lower", "front", "rear", " left side ",
The orientation or positional relationship of the instructions such as " right side ", "vertical", "horizontal", "top", "bottom", "inner", "outside" is based on the figure
Orientation or positional relationship is merely for convenience of description of the present invention and simplification of the description, rather than the device of indication or suggestion meaning or
Element must have a particular orientation, be constructed and operated in a specific orientation, therefore be not considered as limiting the invention.
Term " first ", " second " be used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance or
Implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or imply
Ground includes one or more of the features；In the description of the present invention, unless otherwise indicated, the meaning of " plurality " is two or
It is more than two.
The embodiment of the invention provides a kind of Cold-strip Steel Surface quality control systems, including Cold-strip Steel Surface quality to lack
Fall into identification module F0, Cold-strip Steel Surface mass defect memory module F1, Cold-strip Steel Surface mass defect sample labeling module
F2, Cold-strip Steel Surface quality assessment module F5 and Cold-strip Steel Surface quality improvement modules F6；
The Cold-strip Steel Surface mass defect identification module is used to detect the case of surface defects of cold-strip steel；
The Cold-strip Steel Surface mass defect memory module F1 is lacked for will test defective Cold-strip Steel Surface
It is trapped into capable preservation；
The Cold-strip Steel Surface mass defect sample labeling module F2 is for marking and storing defect sample；
The Cold-strip Steel Surface quality assessment module F5 is used for the Cold-strip Steel Surface defect and the defect sample
This progress is to the classification and strip surface quality grade for judging the Cold-strip Steel Surface defect；
The Cold-strip Steel Surface quality improvement modules F6 is used for classification and band according to the Cold-strip Steel Surface defect
The offer of steel surface credit rating is correspondingly improved strategy, and the classification of Cold-strip Steel Surface defect, improvement strategy and processing are tied
Fruit is stored.
It follows that as shown in Figure 1, Cold-strip Steel Surface quality control system includes that Cold-strip Steel Surface mass defect is known
It is other module F0, Cold-strip Steel Surface mass defect memory module F1, Cold-strip Steel Surface mass defect sample labeling module F2, cold
Roll strip surface quality evaluation module F5 and Cold-strip Steel Surface quality improvement modules F6.Cold-strip Steel Surface quality is first passed through to lack
Sample labeling module F2 retrieval and browsing Cold-strip Steel Surface mass defect picture are fallen into, classification is marked to defect, then will
The good defect sample of labeled bracketing is stored, by engineering real process it is possible that Cold-strip Steel Surface mass defect
The case where classified and saved, mainly in the form of picture save.Then Cold-strip Steel Surface mass defect identification module
F0 carries out defects detection to Cold-strip Steel Surface, and will test defective Cold-strip Steel Surface defect and saved to cold rolling
Strip surface quality defect memory module F1, then Cold-strip Steel Surface quality assessment module F5 is by the above-mentioned cold-rolled strip detected
Steel surface defect and defect sample progress are to the strip surface quality grade for judging the Cold-strip Steel Surface defect, most
It is provided afterwards by Cold-strip Steel Surface quality improvement modules F6 according to the classification and grade of the Cold-strip Steel Surface defect corresponding
Improvement strategy, and the classification of Cold-strip Steel Surface defect, improvement strategy and processing result are stored.
The overall framework of the system is as shown in Fig. 2, Cold-strip Steel Surface quality control system includes Cold-strip Steel Surface matter
Knowledge base and surface quality on-line detecting system are measured, the former is data flow, and the latter is software and hardware supporting body, mainly includes user circle
Surface layer 1, logical layer 2, data access layer 3 and data and file 4, user interface layer 1 receive user's input, carry out man-machine friendship
Mutually；Logical layer 2 carries out logic and mathematical operation, handles data；Data access layer 3 read/operate to data；Database and figure
The tissue of piece file 4 and storing data, wherein data base organization and storing data, Photo folder store defect picture.Surface
Quality on-line detection system, which is detected, to be stored with the defect recognized to defect table and defect Photo folder, and is read from sample table
Sample carries out classifier training and verifying.Wherein, user interface layer 1 can be browser, realizes the shared of network data, obtains
Sample carries out sample labeling by logical layer 2 and exceptional sample is rejected, carries out meter reading subsequently into data access layer 3 and write table
Defect sample is written and read, then forms defect table and sample table in database and Photo folder, and corresponding
It forms quality evaluation table and defect picture, surface quality on-line detecting system corresponds to Cold-strip Steel Surface mass defect identification module
F0, including surface quality on-line checking element, hardware, identification software and on-line checking classifier software.
Preferred scheme, the Cold-strip Steel Surface defect and the defect sample include defect classification, coil of strip number,
Defect characteristic value and defect map piece path, the defect characteristic value include defect area, defect length, defect perimeter, defect area
Domain slenderness ratio and the defect shape factor.It follows that defect sample and defective Cold-strip Steel Surface defect, defect attribute is all
Including defect classification, coil of strip number, defect characteristic value and defect map piece path, the defect characteristic value includes defect area, lacks
Fall into length, defect perimeter, defect area slenderness ratio and the defect shape factor.Defect sample type includes hole, while splitting, is folded,
It scabs, impression, roll marks is pressed into, and is scratched, and skin, iron scale etc. are stuck up, and it is strip table that every class defect sample quantity, which is 300~500,
(i.e. Cold-strip Steel Surface quality assessment module F5 study provides data with verifying and supports surface quality on-line detection system classifier.
Preferred scheme, the Cold-strip Steel Surface quality assessment module F5 is according to every coiled strip steel defect class in defect sample
Other and defect characteristic Value Data, and strip surface quality evaluation model, quantization assessment sample are constructed based on analytic hierarchy process (AHP) (AHP)
Strip surface quality grade.
Preferred scheme is based on AHP method according to every coiled strip steel all defect type and Level data in defect table
Building strip surface quality evaluation model, quantization assessment strip surface quality, as shown in Figure 4.One final mass of destination layer O
It scores as the index for measuring Cold-strip Steel Surface quality, ∑ score=∑ defect power × rank power, score is belt steel surface
Credit rating can be the different stage in every kind of defect with quantization assessment Cold-strip Steel Surface quality level, rule layer D, each
Rank has a weight, Level weight mainly consider defect area, defect length, defect perimeter, defect area slenderness ratio and
The defect shape factor, rule layer C are the various defect types of Strip, and all defective weight of every kind of defect mainly considers defect
Surface Quality influence degree, by constructing defect dipoles Matrix Solving defect weight, solution layer P is the steel of each winding defect
Plate includes the coiled strip steel all surface mass defect initial data.
Preferred scheme, product strip surface quality grade=defect characteristic value × rank power, the rank power are described lack
Fall into the size of corresponding weight in characteristic value.Correspond to above-mentioned ∑ score=∑ defect power × rank power.
Preferred scheme further includes that exceptional sample rejects module F3, and the exceptional sample is rejected module F3 and is used for according to institute
The defect characteristic value for stating defect sample rejects the anomalous body in the defect sample.It follows that by analysis sample,
Exceptional sample can be found out, is then rejected, the precision for influencing sample is avoided.
Preferred scheme, the exceptional sample reject module F3 according to the exceptional sample scalping method of the angular distance of defect into
Row is rejected, and is specifically included:
S1, the i-th point A, i=1 in defect sample is chosen；
Non- i-th point of B and C two o'clock in S2, optional defect sample, obtains vector product<AB using A as vertex, AC>, vector
Mould | AB | and vector mould | AC |, and obtain co sinus vector included angle cos (AB, AC)=<AB, AC>/(| AB | | AC |), and in institute
It states and traverses all B, C point combinations in defect sample；
S3, i-th point of all mix vector included angle cosine value variance in the defect sample is calculatedWherein
σ2For variance, X is co sinus vector included angle, and μ is co sinus vector included angle mean value, and N is defect sample sum；
S4, compare i and N size, if i≤N, i=i+1, return to S1, if i=N, enter in next step；
S5, the co sinus vector included angle value variance of all the points is ranked up；
S6, take wherein the smallest k point of co sinus vector included angle value variance be abnormal point, k is positive integer；
S7, end.
It follows that as shown in figure 3, rendering logic layer algorithm implementation flow chart, realizes logical layer algorithm, and be based on angle
Distance is come to exception, this is rejected.
Preferred scheme, the system also includes classifier training module F4, the classifier training module F4 includes point
Class training aids, feature configuration classification based training device of the classifier training module according to the defect sample, the classification based training
Device is read out the defect sample.The class device training module F4 includes decision Tree algorithms, Adaboost algorithm or artificial
One of neural network algorithm is a variety of.Classifier training module F4 keeps defective cold according to process experiences selection
The feature of steel strip surface defect is rolled, classifier parameters is configured, then read defect sample table, then the classifier of building is instructed
Practice and verify, is called assessment for subsequent Cold-strip Steel Surface quality assessment module F5.Classifier include decision tree,
Adaboost and artificial neural network.
The embodiment of the invention also provides a kind of Cold-strip Steel Surface method for quality control, comprising the following steps:
S100: defect sample is established；
S200: detecting the surface defect of cold-strip steel, will test defective Cold-strip Steel Surface defect and is saved；
S300: the Cold-strip Steel Surface defect and the defect sample are carried out to judging the Cold-strip Steel Surface
The strip surface quality grade of defect；
S400: being correspondingly improved strategy according to the offer of the classification of the Cold-strip Steel Surface defect, and by cold-strip steel table
Classification, improvement strategy and the processing result of planar defect are stored.
Case description is carried out to analysis, and to the strip of detection as shown in figure 5, will test value and sample progress, is provided
Processing method and processing result.
Beneficial effects of the present invention: this Cold-strip Steel Surface quality control system provided by the invention and method.For
The deficiency of existing Cold-strip Steel Surface quality on-line detection system, establishes defect sample, establishes Cold-strip Steel Surface mass defect
Treatment Countermeasures table associates Cold-strip Steel Surface quality testing with quality improvement, by Cold-strip Steel Surface defect and defect
Sample progress is to the strip surface quality grade for judging Cold-strip Steel Surface defect, so that Instructing manufacture process modification, is promoted
Cold-strip Steel Surface quality；On the other hand, using angular distance method rejecting abnormalities sample, the label for improving defect sample is accurate
Rate.
Cold-strip Steel Surface quality control system provided by the invention and method have the advantage that
(1) sample labeling of Cold-strip Steel Surface quality control system covers Cold-strip Steel Surface quality typical defect (hole
Hole folds, scabs while splitting, impression, and roll marks is pressed into, and scratches, sticks up skin, iron scale etc.), classification can be expanded；
(2) the every class defect sample quantity of the label of Cold-strip Steel Surface quality control system is 300~500, sample standard deviation
It is even, quantity is sufficient and facilitates update；
(3) Cold-strip Steel Surface quality control system is by angular distance method to Cold-strip Steel Surface Dealing the Quality Knowledge Database sample
Sample is handled in table, is based on sample characteristics rejecting abnormalities sample, it is ensured that sample is clean；
(4) Cold-strip Steel Surface quality control system is according to every coiled strip steel all defect type and Level in defect table
Data construct strip surface quality evaluation model, quantization assessment strip surface quality based on AHP method；
(5) Cold-strip Steel Surface quality control system provides surface quality to the defect for influencing Cold-strip Steel Surface quality
It handles improved method and suggests, scene is instructed to carry out quality improvement.
The foregoing examples are only illustrative of the present invention, does not constitute the limitation to protection scope of the present invention, all
It is within being all belonged to the scope of protection of the present invention with the same or similar design of the present invention.
Claims (9)
1. a kind of Cold-strip Steel Surface quality control system, it is characterised in that: identify mould including Cold-strip Steel Surface mass defect
Block (F0), Cold-strip Steel Surface mass defect memory module (F1), Cold-strip Steel Surface mass defect sample labeling module (F2),
Cold-strip Steel Surface quality assessment module (F5) and Cold-strip Steel Surface quality improvement modules (F6)；
The Cold-strip Steel Surface mass defect identification module is used to detect the case of surface defects of cold-strip steel；
The Cold-strip Steel Surface mass defect memory module (F1) is for will test defective Cold-strip Steel Surface defect
It is saved；
The Cold-strip Steel Surface mass defect sample labeling module (F2) is for marking and storing defect sample；
The Cold-strip Steel Surface quality assessment module (F5) is used for the Cold-strip Steel Surface defect and the defect sample
Progress is to the classification and strip surface quality grade for judging the Cold-strip Steel Surface defect；
The Cold-strip Steel Surface quality improvement modules (F6) are used for classification and strip according to the Cold-strip Steel Surface defect
Surface quality grades offer is correspondingly improved strategy, and by the classification of Cold-strip Steel Surface defect, improvement strategy and processing result
It is stored.
2. Cold-strip Steel Surface quality control system according to claim 1, it is characterised in that: the Cold-strip Steel Surface
Defect and the defect sample include that defect classification, coil of strip number, defect characteristic value and defect map piece path, the defect are special
Value indicative includes defect area, defect length, defect perimeter, defect area slenderness ratio and the defect shape factor.
3. Cold-strip Steel Surface quality control system according to claim 2, it is characterised in that: the Cold-strip Steel Surface
Quality assessment module (F5) is based on step analysis according to every coiled strip steel defect classification and defect characteristic Value Data in defect sample
Method (AHP) constructs strip surface quality evaluation model, quantization assessment sample strip surface quality grade.
4. Cold-strip Steel Surface quality control system according to claim 3, which is characterized in that the strip surface quality
Evaluation model are as follows: sample strip surface quality grade=defect characteristic value × rank power, the rank power is the defect characteristic
The size of corresponding weight in value.
5. Cold-strip Steel Surface quality control system according to claim 2, it is characterised in that: further include that exceptional sample picks
Except module (F3), the exceptional sample rejects module (F3) and is used for the defect characteristic value according to the defect sample to the defect
Anomalous body in sample is rejected.
6. Cold-strip Steel Surface quality control system according to claim 5, which is characterized in that the exceptional sample is rejected
Module (F3) is rejected according to the exceptional sample scalping method of the angular distance of defect, is specifically included:
S1, the i-th point A, i=1 in defect sample is chosen；
Non- i-th point of B and C two o'clock in S2, optional defect sample, obtains vector product<AB using A as vertex, AC>, vector mould | AB
| and vector mould | AC |, and obtain co sinus vector included angle cos (AB, AC)=<AB, AC>/(| AB | | AC |), and in the defect
All B, C point combinations are traversed in sample；
S3, i-th point of all mix vector included angle cosine value variance in the defect sample is calculatedWherein σ2For
Variance, X are co sinus vector included angle, and μ is co sinus vector included angle mean value, and N is defect sample sum；
S4, compare i and N size, if i≤N, i=i+1, return to S1, if i=N, enter in next step；
S5, the co sinus vector included angle value variance of all the points is ranked up；
S6, take wherein the smallest k point of co sinus vector included angle value variance be abnormal point, k is positive integer；
S7, end.
7. Cold-strip Steel Surface quality control system according to claim 1, it is characterised in that: the system also includes divide
Class device training module (F4), the classifier training module (F4) include classification based training device, the classifier training module (F4)
According to the feature configuration classification based training device of the defect sample, the classification based training device is read out the defect sample.
8. Cold-strip Steel Surface quality control system according to claim 7, it is characterised in that: the classification based training device packet
Containing one of decision Tree algorithms, Adaboost algorithm or artificial neural network algorithm or a variety of.
9. a kind of Cold-strip Steel Surface method for quality control, which comprises the following steps:
S100: defect sample is established；
S200: detecting the surface defect of cold-strip steel, will test defective Cold-strip Steel Surface defect and is saved；
S300: the Cold-strip Steel Surface defect and the defect sample are carried out to judging the Cold-strip Steel Surface defect
Strip surface quality grade；
S400: strategy is correspondingly improved according to the offer of the classification of the Cold-strip Steel Surface defect, and Cold-strip Steel Surface is lacked
Sunken classification, improvement strategy and processing result is stored.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811632987.3A CN109692877B (en) | 2018-12-29 | 2018-12-29 | Cold-rolled strip steel surface quality management system and method |
| PCT/CN2019/106449 WO2020134210A1 (en) | 2018-12-29 | 2019-09-18 | Cold-rolled strip steel surface quality management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811632987.3A CN109692877B (en) | 2018-12-29 | 2018-12-29 | Cold-rolled strip steel surface quality management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109692877A true CN109692877A (en) | 2019-04-30 |
| CN109692877B CN109692877B (en) | 2020-11-10 |
Family
ID=66232276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811632987.3A Active CN109692877B (en) | 2018-12-29 | 2018-12-29 | Cold-rolled strip steel surface quality management system and method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109692877B (en) |
| WO (1) | WO2020134210A1 (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175274A (en) * | 2019-05-22 | 2019-08-27 | 山西太钢不锈钢股份有限公司 | Defect system method and system based on table inspection instrument |
| CN110320337A (en) * | 2019-06-05 | 2019-10-11 | 广州Jfe钢板有限公司 | A kind of automatic evaluating system of strip surface quality and method |
| CN110400099A (en) * | 2019-08-09 | 2019-11-01 | 马鞍山钢铁股份有限公司 | A kind of belt steel product surface quality stage division |
| CN110717455A (en) * | 2019-10-10 | 2020-01-21 | 北京同创信通科技有限公司 | Method for classifying and detecting grades of scrap steel in storage |
| CN111223078A (en) * | 2019-12-31 | 2020-06-02 | 河南裕展精密科技有限公司 | Method for determining defect grade and storage medium |
| CN111299318A (en) * | 2020-03-02 | 2020-06-19 | 马鞍山钢铁股份有限公司 | Automatic determination method for surface quality of hot-rolled plate strip product |
| WO2020134210A1 (en) * | 2018-12-29 | 2020-07-02 | 中冶南方工程技术有限公司 | Cold-rolled strip steel surface quality management system and method |
| CN112547807A (en) * | 2020-10-30 | 2021-03-26 | 北京科技大学 | Decision tree algorithm-based hot rolled strip quality accurate judgment method |
| CN113578976A (en) * | 2021-07-28 | 2021-11-02 | 北京首钢股份有限公司 | Production method and production system of hot-rolled electrical steel capable of controlling edge warping |
| CN113578972A (en) * | 2021-04-08 | 2021-11-02 | 华院计算技术(上海)股份有限公司 | Hot-rolled product quality tracing method and device |
| CN114722973A (en) * | 2022-06-07 | 2022-07-08 | 江苏华程工业制管股份有限公司 | Defect detection method and system for steel pipe heat treatment |
| CN114972302A (en) * | 2022-06-17 | 2022-08-30 | 阿里云计算有限公司 | Discrimination criterion generating method, surface quality detecting method, storage medium, and program product |
| CN115983687A (en) * | 2022-12-22 | 2023-04-18 | 广州海秀敏网络科技有限公司 | Intelligent detection management system and method for quality of cold-rolled strip steel |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI766737B (en) * | 2021-06-24 | 2022-06-01 | 中國鋼鐵股份有限公司 | Wringer roll quality inspection system and method thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008055443A (en) * | 2006-08-29 | 2008-03-13 | Kobe Steel Ltd | Method for analyzing material quality of metallic material and method for stabilizing material quality |
| CN102554167A (en) * | 2012-02-14 | 2012-07-11 | 首钢总公司 | Method for controlling defects of H-shaped steel |
| CN202606510U (en) * | 2012-04-19 | 2012-12-19 | 中冶南方工程技术有限公司 | Cold-rolled strip steel plate shape and plate thickness comprehensive control system |
| JP2013114453A (en) * | 2011-11-29 | 2013-06-10 | Toshiba Mitsubishi-Electric Industrial System Corp | Product defect information tracking device |
| CN103399016A (en) * | 2013-07-26 | 2013-11-20 | 齐鲁工业大学 | Online detection system for surface defects of coldly-rolled aluminum plate and detection method of online detection system |
| CN104985002A (en) * | 2015-05-27 | 2015-10-21 | 北京首钢股份有限公司 | Hot rolled strip steel edge defect alarm method and apparatus |
| CN108021938A (en) * | 2017-11-29 | 2018-05-11 | 中冶南方工程技术有限公司 | A kind of Cold-strip Steel Surface defect online detection method and detecting system |
| 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 |
| CN109030503A (en) * | 2018-07-11 | 2018-12-18 | 无锡赛默斐视科技有限公司 | The online surface defects detection system of strip and its detection method |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4639858B2 (en) * | 2005-03-07 | 2011-02-23 | Ｊｆｅスチール株式会社 | Surface defect inspection method and apparatus |
| CN102253049B (en) * | 2011-06-30 | 2013-07-10 | 东北大学 | Method for accurately detecting surface quality on line in production process of band steel |
| DE102013109915B4 (en) * | 2013-09-10 | 2015-04-02 | Thyssenkrupp Steel Europe Ag | Method and device for checking an inspection system for detecting surface defects |
| CN103778445B (en) * | 2014-01-21 | 2017-02-01 | 武汉科技大学 | Cold-rolled strip steel surface defect reason analyzing method and system |
| CN106845825B (en) * | 2017-01-18 | 2020-04-28 | 西安交通大学 | Strip steel cold rolling quality problem tracing and control method based on improved PCA |
| CN106875104A (en) * | 2017-01-21 | 2017-06-20 | 西安交通大学 | A kind of cold-strip steel quality overall evaluation method |
| CN109692877B (en) * | 2018-12-29 | 2020-11-10 | 中冶南方工程技术有限公司 | Cold-rolled strip steel surface quality management system and method |
-
2018
- 2018-12-29 CN CN201811632987.3A patent/CN109692877B/en active Active
-
2019
- 2019-09-18 WO PCT/CN2019/106449 patent/WO2020134210A1/en active Application Filing
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008055443A (en) * | 2006-08-29 | 2008-03-13 | Kobe Steel Ltd | Method for analyzing material quality of metallic material and method for stabilizing material quality |
| JP2013114453A (en) * | 2011-11-29 | 2013-06-10 | Toshiba Mitsubishi-Electric Industrial System Corp | Product defect information tracking device |
| CN102554167A (en) * | 2012-02-14 | 2012-07-11 | 首钢总公司 | Method for controlling defects of H-shaped steel |
| CN202606510U (en) * | 2012-04-19 | 2012-12-19 | 中冶南方工程技术有限公司 | Cold-rolled strip steel plate shape and plate thickness comprehensive control system |
| CN103399016A (en) * | 2013-07-26 | 2013-11-20 | 齐鲁工业大学 | Online detection system for surface defects of coldly-rolled aluminum plate and detection method of online detection system |
| CN104985002A (en) * | 2015-05-27 | 2015-10-21 | 北京首钢股份有限公司 | Hot rolled strip steel edge defect alarm method and apparatus |
| CN108021938A (en) * | 2017-11-29 | 2018-05-11 | 中冶南方工程技术有限公司 | A kind of Cold-strip Steel Surface defect online detection method and detecting system |
| 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 |
| CN109030503A (en) * | 2018-07-11 | 2018-12-18 | 无锡赛默斐视科技有限公司 | The online surface defects detection system of strip and its detection method |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020134210A1 (en) * | 2018-12-29 | 2020-07-02 | 中冶南方工程技术有限公司 | Cold-rolled strip steel surface quality management system and method |
| CN110175274A (en) * | 2019-05-22 | 2019-08-27 | 山西太钢不锈钢股份有限公司 | Defect system method and system based on table inspection instrument |
| CN110320337A (en) * | 2019-06-05 | 2019-10-11 | 广州Jfe钢板有限公司 | A kind of automatic evaluating system of strip surface quality and method |
| CN110400099A (en) * | 2019-08-09 | 2019-11-01 | 马鞍山钢铁股份有限公司 | A kind of belt steel product surface quality stage division |
| CN110717455A (en) * | 2019-10-10 | 2020-01-21 | 北京同创信通科技有限公司 | Method for classifying and detecting grades of scrap steel in storage |
| CN111223078B (en) * | 2019-12-31 | 2023-09-26 | 富联裕展科技(河南)有限公司 | Method for determining flaw level and storage medium |
| CN111223078A (en) * | 2019-12-31 | 2020-06-02 | 河南裕展精密科技有限公司 | Method for determining defect grade and storage medium |
| CN111299318A (en) * | 2020-03-02 | 2020-06-19 | 马鞍山钢铁股份有限公司 | Automatic determination method for surface quality of hot-rolled plate strip product |
| CN111299318B (en) * | 2020-03-02 | 2022-04-12 | 马鞍山钢铁股份有限公司 | Automatic determination method for surface quality of hot-rolled plate strip product |
| CN112547807A (en) * | 2020-10-30 | 2021-03-26 | 北京科技大学 | Decision tree algorithm-based hot rolled strip quality accurate judgment method |
| CN113578972A (en) * | 2021-04-08 | 2021-11-02 | 华院计算技术(上海)股份有限公司 | Hot-rolled product quality tracing method and device |
| CN113578976A (en) * | 2021-07-28 | 2021-11-02 | 北京首钢股份有限公司 | Production method and production system of hot-rolled electrical steel capable of controlling edge warping |
| CN113578976B (en) * | 2021-07-28 | 2023-09-01 | 北京首钢股份有限公司 | Production method and production system for hot-rolled electrical steel with edge skin tilting control function |
| CN114722973A (en) * | 2022-06-07 | 2022-07-08 | 江苏华程工业制管股份有限公司 | Defect detection method and system for steel pipe heat treatment |
| CN114972302A (en) * | 2022-06-17 | 2022-08-30 | 阿里云计算有限公司 | Discrimination criterion generating method, surface quality detecting method, storage medium, and program product |
| CN115983687A (en) * | 2022-12-22 | 2023-04-18 | 广州海秀敏网络科技有限公司 | Intelligent detection management system and method for quality of cold-rolled strip steel |
| CN115983687B (en) * | 2022-12-22 | 2023-09-29 | 北京弥天科技有限公司 | Intelligent detection management system and method for quality of cold-rolled strip steel |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020134210A1 (en) | 2020-07-02 |
| CN109692877B (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109692877A (en) | A kind of Cold-strip Steel Surface quality control system and method | |
| TWI739798B (en) | Method and device for establishing data recognition model | |
| CN107194803A (en) | P2P net loan borrower credit risk assessment device | |
| US9842175B2 (en) | Methods and systems for automatic selection of classification and regression trees | |
| CN105612249B (en) | Image processing apparatus, program, information storage medium and image processing method | |
| CN111311128A (en) | Consumption financial credit scoring card development method based on third-party data | |
| WO2021232856A1 (en) | Big data-based online sales commodity sampling and testing method | |
| CN108304842A (en) | Meter reading recognition methods, device and electronic equipment | |
| CN104464079A (en) | Multi-currency-type and face value recognition method based on template feature points and topological structures of template feature points | |
| CN105956393A (en) | Board quality detection real-time calculation system and method | |
| CN110413973A (en) | Computer automatically generates the method and its system of set volume | |
| CN107507038A (en) | A kind of electricity charge sensitive users analysis method based on stacking and bagging algorithms | |
| CN114997612A (en) | Cluster analysis method and device for abnormal information of large grain pile | |
| CN116309564B (en) | Method and system for detecting appearance defects of battery cells based on artificial intelligent image recognition | |
| CN109003266A (en) | A method of based on fuzzy clustering statistical picture quality subjective evaluation result | |
| CN104463673A (en) | P2P network credit risk assessment model based on support vector machine | |
| CN107941812A (en) | Information processing method and electronic equipment | |
| CN115082225A (en) | Enterprise financing risk assessment method and device | |
| Decuseara | Using the general electric/Mckinsey Matrix in the process of selecting the central and east European markets | |
| CN110096708A (en) | A kind of determining method and device of calibration collection | |
| CN116993430A (en) | ERP e-commerce management system and method based on big data | |
| CN114707904A (en) | Quality detection method and system based on big data | |
| CN109784395A (en) | A kind of algorithm recommended method for unbalanced data | |
| CN114971805A (en) | Electronic commerce platform commodity intelligent analysis recommendation system based on deep learning | |
| CN106779843A (en) | A kind of competing method and apparatus for closing relationship analysis of trade company based on customer group's feature |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |