CN110490862A - A kind of method and device improving continuous casting flaw detection qualification rate - Google Patents
A kind of method and device improving continuous casting flaw detection qualification rate Download PDFInfo
- Publication number
- CN110490862A CN110490862A CN201910777803.0A CN201910777803A CN110490862A CN 110490862 A CN110490862 A CN 110490862A CN 201910777803 A CN201910777803 A CN 201910777803A CN 110490862 A CN110490862 A CN 110490862A
- Authority
- CN
- China
- Prior art keywords
- continuous casting
- casting billet
- information
- image information
- field trash
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30116—Casting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Continuous Casting (AREA)
- Investigating And Analyzing Materials By Characteristic Methods (AREA)
Abstract
This specification embodiment provides a kind of method and device for improving continuous casting flaw detection qualification rate, training pattern is inputted by the continuous casting billet image information that will be obtained, wherein, the training pattern is obtained by the training of multiple groups training data, and each group of training data in training data in the multiple groups includes: the continuous casting billet image information, mark continuous casting billet center metallographic structure label information and default field trash indication information；Obtain the output information of the training pattern, wherein the output information includes the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and field trash information；According to the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and field trash information, screening and filtering is carried out to the continuous casting billet image information, obtain the qualified standard continuous casting billet image information of flaw detection, the flaw detection qualification rate for improving continuous casting billet is reached, reduce inclusion content, the internal soundness for guaranteeing continuous casting billet, reduces the technical effect of production cost.
Description
Technical field
This specification embodiment be related to metallurgical technology field more particularly to it is a kind of improve continuous casting flaw detection qualification rate method and
Device.
Background technique
Currently, steel industry production cost is high, whole profit is not high, especially cut deal enterprise, is in meagre profit
Or loss of capital state.Flaw detection qualification rate is a principal economic indicators of cut deal iron and steel enterprise, and the height of flaw detection qualification rate is direct
Determine economic benefit, production cost and the contract encashment ratio of enterprise.Cut deal steel are easy to appear steel in continuous casting production working procedure
It is unqualified that plate center portion element segregation, loose and micro-crack lead to roll rear steel plate inspection, therefore, promotes steel plate inspection qualification rate to steel
Iron production is of great significance.
But present inventor during inventive technique scheme, has found above-mentioned technology extremely in realizing the embodiment of the present application
It has the following technical problems less:
In the prior art since Large Inclusions, micro-crack easily occurs during the rolling process in continuous casting billet, and easily aggravate continuous casting
Base center segregation and banded structure cause to detect a flaw unqualified, and can not quickly identify the flaw detection qualification rate of continuous casting billet.
Summary of the invention
This specification embodiment provides and a kind of method and device for improving continuous casting flaw detection qualification rate, solves the prior art
In easily occur Large Inclusions, micro-crack during the rolling process due to continuous casting billet, and easily aggravation continuous casting billet center segregation and band-like
Tissue, the technical issues of causing to detect a flaw unqualified, and can not quickly identify the flaw detection qualification rate of continuous casting billet, has reached raising continuous casting
The flaw detection qualification rate of base reduces inclusion content, guarantees the internal soundness of continuous casting billet, reduce the technical effect of production cost.
In view of the above problems, propose the embodiment of the present application in order to provide it is a kind of improve continuous casting flaw detection qualification rate method and
Device.
In a first aspect, this specification embodiment provides a kind of method for improving continuous casting flaw detection qualification rate, the acquisition continuous casting
Base image information；The continuous casting billet image information is inputted into training pattern, wherein the training pattern passes through multiple groups training data
Training obtains, and each group of training data in training data in the multiple groups includes: the continuous casting billet image information, mark
Continuous casting billet center metallographic structure label information and default field trash indication information；The output information of the training pattern is obtained,
In, the output information includes the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and field trash letter
Breath；According to the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and field trash information, to the continuous casting
Base image information carries out screening and filtering, obtains the qualified standard continuous casting billet image information of flaw detection.
Preferably, the acquisition continuous casting billet image information, comprising: obtain continuous casting billet image information to be detected；To described
Continuous casting billet image information to be detected is pre-processed, and the continuous casting billet image information is obtained, wherein the continuous casting billet image letter
Breath is size, ratio, the identical image information of pixel.
Preferably, each group of training data in the training data in the multiple groups includes mark continuous casting billet center metallographic group
Knit label information, comprising: obtain the crackle in the metallographic structure of continuous casting billet center；Judge in the metallographic structure of the continuous casting billet center
Whether crackle meets preassigned image；When the crackle in the metallographic structure of the continuous casting billet center does not meet preassigned image
When, obtain mark continuous casting billet center metallographic structure label information；The mark continuous casting billet center metallographic structure label information is made
For the first label data, input in each group of training data.
Preferably, each group of training data in the training data in the multiple groups includes default field trash indication information,
It include: the content for obtaining the ingredient of the ingredient and field trash of field trash in continuous casting billet；According to the ingredient of the field trash with
The content of the ingredient of the field trash obtains the default field trash indication information；Using the default field trash indication information as
Second label data inputs in each group of training data.
Preferably, described according to the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and field trash
Information carries out screening and filtering to the continuous casting billet image information, obtains the qualified standard continuous casting billet image information of flaw detection, comprising:
Judge whether the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information meets preassigned image；If institute
It states the corresponding continuous casting billet center metallographic structure information of continuous casting billet image information and meets preassigned image, obtain predetermined field trash threshold
Value；If the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information does not meet preassigned image, by institute
Continuous casting billet image information is stated to filter out.
Preferably, after the predetermined field trash threshold value of acquisition, comprising: judge the corresponding folder of the continuous casting billet image information
Whether sundries information reaches predetermined field trash threshold value；If the corresponding field trash information of the continuous casting billet image information does not reach
Predetermined field trash threshold value obtains the qualified standard continuous casting billet image information of flaw detection；If the continuous casting billet image information is corresponding
Field trash information reaches predetermined field trash threshold value, and the continuous casting billet image information is filtered out.
Second aspect, this specification embodiment provide a kind of raising continuous casting flaw detection qualification rate device, and described device includes:
First obtains unit, for obtaining continuous casting billet image information；
First input unit, for the continuous casting billet image information to be inputted training pattern, wherein the training pattern is logical
It crosses the training of multiple groups training data to obtain, each group of training data in training data in the multiple groups includes: the continuous casting
Base image information, mark continuous casting billet center metallographic structure label information and default field trash indication information；
First output unit, for obtaining the output information of the training pattern, wherein the output information includes described
The corresponding continuous casting billet center metallographic structure information of continuous casting billet image information and field trash information；
Second obtaining unit, for according to the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and
Field trash information carries out screening and filtering to the continuous casting billet image information, obtains the qualified standard continuous casting billet image information of flaw detection.
Preferably, continuous casting billet image information is obtained described in the first obtains unit, comprising:
Third obtaining unit, for obtaining continuous casting billet image information to be detected；
4th obtaining unit obtains the continuous casting for pre-processing to the continuous casting billet image information to be detected
Base image information, wherein the continuous casting billet image information is size, ratio, the identical image information of pixel.
Preferably, each group of training data in the training data in multiple groups described in first input unit includes mark
Know continuous casting billet center metallographic structure label information, comprising:
5th obtaining unit, for obtaining the crackle in the metallographic structure of continuous casting billet center；
Whether the first judging unit, the crackle for judging in the metallographic structure of the continuous casting billet center meet preassigned figure
Picture；
6th obtaining unit, for not meeting preassigned image when the crackle in the metallographic structure of the continuous casting billet center
When, obtain mark continuous casting billet center metallographic structure label information；
Second input unit, for using the mark continuous casting billet center metallographic structure label information as the first number of tags
According in the input each group of training data.
Preferably, each group of training data in the training data in multiple groups described in first input unit includes pre-
If field trash indication information, comprising:
7th obtaining unit, for obtaining the content of the ingredient of the ingredient of field trash and the field trash in continuous casting billet；
8th obtaining unit, for according to the acquisition of the content of the ingredient of the field trash and the ingredient of the field trash
Default field trash indication information；
Third input unit, for inputting described every using the default field trash indication information as the second label data
In one group of training data.
Preferably, according to the corresponding continuous casting billet center gold of the continuous casting billet image information described in second obtaining unit
Phase constitution information and field trash information carry out screening and filtering to the continuous casting billet image information, obtain the qualified standard of flaw detection and connect
Slab image information, comprising:
Second judgment unit, for judging that the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information is
It is no to meet preassigned image；
9th obtaining unit, if for the corresponding continuous casting billet center metallographic structure information symbol of the continuous casting billet image information
Preassigned image is closed, predetermined field trash threshold value is obtained；
First execution unit, if not for the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information
Meet preassigned image, the continuous casting billet image information is filtered out.
Preferably, after the 9th obtaining unit, comprising:
Third judging unit, for judging whether the corresponding field trash information of the continuous casting billet image information reaches pre- clamp
Sundries threshold value；
Tenth obtaining unit, if not reaching pre- clamp for the corresponding field trash information of the continuous casting billet image information
Sundries threshold value obtains the qualified standard continuous casting billet image information of flaw detection；
Second execution unit, if reaching predetermined field trash for the corresponding field trash information of the continuous casting billet image information
Threshold value filters out the continuous casting billet image information.
The third aspect, the present invention provides a kind of computer readable storage mediums, are stored thereon with computer program, the journey
The step of any of the above-described the method is realized when sequence is executed by processor.
Fourth aspect, this specification embodiment provide a kind of device for improving continuous casting flaw detection qualification rate, including memory, place
The computer program managing device and storage on a memory and can running on a processor, which is characterized in that the processor executes
The step of any of the above-described the method.
Said one or multiple technical solutions in the embodiment of the present application at least have following one or more technology effects
Fruit:
The method and device for the raising continuous casting flaw detection qualification rate that this specification embodiment provides, passes through the continuous casting billet that will be obtained
Image information inputs training pattern, wherein the training pattern is obtained by the training of multiple groups training data, the instruction in the multiple groups
Practicing each group of training data in data includes: the continuous casting billet image information, mark continuous casting billet center metallographic structure label
Information and default field trash indication information；By by the mark continuous casting billet center metallographic in continuous casting billet image information and training pattern
Tissue label information and default field trash indication information are compared, and obtain the output information of the training pattern, wherein described
Output information includes the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and field trash information；According to institute
The corresponding continuous casting billet center metallographic structure information of continuous casting billet image information and field trash information are stated, to the continuous casting billet image information
Screening and filtering is carried out, the qualified standard continuous casting billet image information of flaw detection is obtained, is able to solve due to continuous casting billet during the rolling process
Easily there is Large Inclusions, micro-crack, and easily aggravation continuous casting billet center segregation and banded structure, causes to detect a flaw unqualified, and nothing
Method quickly identifies the technical issues of flaw detection qualification rate of continuous casting billet, has reached the flaw detection qualification rate for improving continuous casting billet, and reduction is mingled with
Object content guarantees the internal soundness of continuous casting billet, reduces the technical effect of production cost.
Detailed description of the invention
Fig. 1 is a kind of method flow diagram of the raising continuous casting flaw detection qualification rate provided in this specification embodiment；
Fig. 2 is a kind of raising continuous casting flaw detection qualification rate schematic device provided in this specification embodiment；
Fig. 3 is another raising continuous casting flaw detection qualification rate schematic device provided in this specification embodiment.
Drawing reference numeral explanation: bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface
306。
Specific embodiment
The embodiment of the invention provides a kind of method and devices for improving continuous casting flaw detection qualification rate, for solving existing skill
Since Large Inclusions, micro-crack, and easily aggravation continuous casting billet center segregation and band easily occurs during the rolling process in continuous casting billet in art
Shape tissue causes to detect a flaw unqualified, and the technical issues of can not quickly identify the flaw detection qualification rate of continuous casting billet, provided by the invention
Technical solution general thought is as follows:
In the technical solution of the embodiment of the present invention, by obtaining continuous casting billet image information；The continuous casting billet image is believed
Breath input training pattern, wherein the training pattern is obtained by the training of multiple groups training data, the training data in the multiple groups
In each group of training data include: the continuous casting billet image information, mark continuous casting billet center metallographic structure label information and
Default field trash indication information；Obtain the output information of the training pattern, wherein the output information includes the continuous casting billet
The corresponding continuous casting billet center metallographic structure information of image information and field trash information；It is corresponding according to the continuous casting billet image information
Continuous casting billet center metallographic structure information and field trash information carry out screening and filtering to the continuous casting billet image information, are detected a flaw
Qualified standard continuous casting billet image information.It is able to solve since Large Inclusions, fine fisssure easily occurs during the rolling process in continuous casting billet
Line, and easily aggravation continuous casting billet center segregation and banded structure, cause to detect a flaw unqualified, and can not quickly identify the flaw detection of continuous casting billet
The technical issues of qualification rate, has reached the flaw detection qualification rate for improving continuous casting billet, reduces inclusion content, guarantees the inside of continuous casting billet
Quality reduces the technical effect of production cost.
In order to better understand the above technical scheme, below by attached drawing and specific embodiment to this specification embodiment
Technical solution be described in detail, it should be understood that the specific features in this specification embodiment and embodiment are to this explanation
The detailed description of book embodiment technical solution, rather than the restriction to this specification technical solution, in the absence of conflict,
Technical characteristic in this specification embodiment and embodiment can be combined with each other.
It is only to be not intended to be limiting this public affairs merely for for the purpose of describing particular embodiments the term used is disclosed herein
It opens.Packet is also intended to the "an" of singular used in the attached claims, " described " and "the" being disclosed herein
Most forms are included, unless the context clearly indicates other meaning.The terms "and/or", only a kind of description association
The incidence relation of object indicates may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously A
And B, individualism B these three situations.In addition, character "/" herein, typicallys represent the pass that forward-backward correlation object is a kind of "or"
System.
Embodiment one
Fig. 1 is a kind of flow diagram for the method for improving continuous casting flaw detection qualification rate in the embodiment of the present invention.Such as Fig. 1 institute
Show.The method is applied to the equipment for improving continuous casting flaw detection qualification rate, the processing equipment for improving continuous casting flaw detection qualification rate
Including an input equipment and a display equipment, there is picture input module, picture processing module, storage inside the input equipment
Device, signal input module, the equipment that the input equipment can generate output signal with energy-spectrum scanning instrument, scanning electron microscope etc. carry out
Connection, the display equipment connect with the input equipment, can will be at the input equipments such as the energy-spectrum scanning instrument, scanning electron microscope
The equipment such as the display screen that the image of reason is shown.The method comprising the steps of S101-S104.
S101: continuous casting billet image information is obtained；
Further, the acquisition continuous casting billet image information, comprising: obtain continuous casting billet image information to be detected；To institute
It states continuous casting billet image information to be detected to be pre-processed, obtains the continuous casting billet image information, wherein the continuous casting billet image
Information is size, ratio, the identical image information of pixel.
Specifically, the embodiment of the present application provides a kind of method for improving continuous casting flaw detection qualification rate, by continuous casting billet
Process environment under shooting be scanned to continuous casting billet to be detected using energy-spectrum scanning instrument, scanning electron microscope etc. obtain company to be detected
Slab image information, for example, certain steel plant before obtaining continuous casting billet image information to be detected, carries out the continuous casting billet to be detected
Slow cooling processing can reduce the micro-flaw of continuous casting billet by slow cooling processing, reduce continuous casting billet center segregation and banded structure, keep away
Exempt from the appearance of Large Inclusions, and then can be improved the flaw detection qualification rate of continuous casting billet, wherein flaw detection refers to detection metal material or portion
Crackle or defect inside part.The continuous casting billet image information to be detected is pre-processed, image processing software pair is passed through
Continuous casting billet image information to be detected is uniformly processed, and the continuous casting billet image information is obtained, wherein the continuous casting billet image
Information is size, ratio, the identical image information of pixel, and convenient for training pattern, quickly analysis is handled, and improves the flaw detection of continuous casting billet
Qualification rate reduces inclusion content, guarantees the internal soundness of continuous casting billet.
S102: the continuous casting billet image information is inputted into training pattern, wherein the training pattern passes through multiple groups training number
It is obtained according to training, each group of training data in training data in the multiple groups includes: the continuous casting billet image information, mark
Know continuous casting billet center metallographic structure label information and default field trash indication information；
Further, each group of training data in the training data in the multiple groups includes mark continuous casting billet center metallographic
Organize label information, comprising: obtain the crackle in the metallographic structure of continuous casting billet center；Judge in the metallographic structure of the continuous casting billet center
Crackle whether meet preassigned image；When the crackle in the metallographic structure of the continuous casting billet center does not meet preassigned image
When, obtain mark continuous casting billet center metallographic structure label information；The mark continuous casting billet center metallographic structure label information is made
For the first label data, input in each group of training data.
Further, each group of training data in the training data in the multiple groups includes default field trash index letter
Breath, comprising: obtain the content of the ingredient of the ingredient and field trash of field trash in continuous casting billet；According to the ingredient of the field trash
The default field trash indication information is obtained with the content of the ingredient of the field trash；The default field trash indication information is made
For the second label data, input in each group of training data.
Specifically, the continuous casting billet image information of acquisition is inputted training pattern, wherein the training pattern passes through
The training of multiple groups training data obtains, that is to say, that each group of training in the training data in the multiple groups in training pattern
Data include: the continuous casting billet image information, mark continuous casting billet center metallographic structure label information and default field trash index
Information.In order to improve the flaw detection qualification rate of continuous casting billet, width, the size, depth of the inside micro-flaw of continuous casting billet need to be limited, with
And the composition of inclusions and content of continuous casting billet.Firstly, passing through the label letter of micro-flaw in mark continuous casting billet center metallographic structure
Breath, wherein influence continuous casting billet inside micro-flaw because being known as continuous casting billet center segregation and banded structure.Pass through energy-spectrum scanning instrument
The micro-flaw in the metallographic structure of continuous casting billet center is obtained with scanning electron microscope, judges splitting in the metallographic structure of the continuous casting billet center
Whether line meets preassigned image, wherein the preassigned image is the width of the qualified crackle of continuous casting billet flaw detection, size
And the predetermined threshold of depth.When the crackle in the metallographic structure of the continuous casting billet center does not meet preassigned image, marked
Know continuous casting billet center metallographic structure label information, the i.e. underproof label of continuous casting billet flaw detection.By the mark continuous casting billet center gold
Phase constitution label information inputs in each group of training data as the first label data, can with inputted in training pattern
The continuous casting billet image information compares training.Secondly, by default field trash indication information as each in training pattern
One of group training data.By obtaining the content of the ingredient of the ingredient and field trash of field trash in continuous casting billet, such as certain steel
It is higher at middle Al, Ca, O content, find that line inclusion is aluminium calcium oxide in the steel by energy spectrum analysis.According to described
The content of the ingredient of the ingredient of field trash and the field trash obtains the default field trash indication information, i.e., the described field trash
When the content of the ingredient of ingredient and the field trash is more than identification standard, it is unqualified which will cause flaw detection, by such
The content of the ingredient of the ingredient of field trash and the field trash is set as field trash indication information.By the default field trash index
Information inputs in each group of training data as the second label data, can be with the continuous casting billet that inputs in training pattern
Image information compares training.
S103: the output information of the training pattern is obtained, wherein the output information includes the continuous casting billet image letter
Cease corresponding continuous casting billet center metallographic structure information and field trash information；
Specifically, through the above steps S102 by the continuous casting billet image information input training pattern compare training
Afterwards, the output information of the training pattern is obtained.The output information includes the corresponding continuous casting billet of the continuous casting billet image information
Center metallographic structure information and the corresponding field trash information of the continuous casting billet image information, i.e., the described continuous casting billet image information and mark
Continuous casting billet center metallographic structure information, the continuous casting billet image information after knowing the comparison of continuous casting billet center metallographic structure label information
With the field trash information after the comparison of default field trash indication information.
S104: according to the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and field trash information,
Screening and filtering is carried out to the continuous casting billet image information, obtains the qualified standard continuous casting billet image information of flaw detection.
Further, described according to the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and being mingled with
Object information carries out screening and filtering to the continuous casting billet image information, obtains the qualified standard continuous casting billet image information of flaw detection, packet
It includes: judging whether the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information meets preassigned image；Such as
The corresponding continuous casting billet center metallographic structure information of continuous casting billet image information described in fruit meets preassigned image, obtains predetermined be mingled with
Object threshold value；If the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information does not meet preassigned image,
The continuous casting billet image information is filtered out.
Further, after the predetermined field trash threshold value of acquisition, comprising: judge that the continuous casting billet image information is corresponding
Whether field trash information reaches predetermined field trash threshold value；If the corresponding field trash information of the continuous casting billet image information does not reach
To predetermined field trash threshold value, the qualified standard continuous casting billet image information of flaw detection is obtained；If the continuous casting billet image information is corresponding
Field trash information reach predetermined field trash threshold value, the continuous casting billet image information is filtered out.
Specifically, by judging whether the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information accords with
Close preassigned image, wherein the preassigned image is width, size and the depth of the qualified crackle of continuous casting billet flaw detection
Predetermined threshold.Wherein, the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information is divided into two kinds of situations, and first
Kind, if the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information meets preassigned image, obtain pre-
Clamp sundries threshold value, that is to say, that the crackle in the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information
It is more subtle, meet flaw detection qualification rate, is so as to further compare ingredient and the content of the field trash in the continuous casting billet
It is no to will affect flaw detection qualification rate.Second, if the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information
Preassigned image is not met, i.e., more apparent crackle occurs in the inside of the described continuous casting billet, and the data of the crackle have been more than institute
Width, size and the depth of crackle specified in preassigned image are stated, therefore the continuous casting billet image information is filtered out, is filtered out
The continuous casting billet is that flaw detection is underproof.Such as, there is subtle disconnected or continuous micro-flaw not in certain continuous casting billet center image
Meet preassigned image, which is filtered out.Meanwhile in the corresponding continuous casting billet of the continuous casting billet image information
In the first situation that metallographic structure information in center occurs, the subtle influence to flaw detection of the underbead crack of the continuous casting billet is little,
The field trash in the continuous casting billet need to further be probed into.After obtaining predetermined field trash threshold value, the continuous casting billet image letter is judged
It ceases corresponding field trash information and whether reaches predetermined field trash threshold value and be also classified into two kinds of situations, the first, if the continuous casting billet
The corresponding field trash information of image information does not reach predetermined field trash threshold value, obtains the qualified standard continuous casting billet image letter of flaw detection
The content of breath, i.e., the corresponding field trash of described continuous casting billet image information is lower, will not be because of extension in subsequent rolling process
Large Inclusions are formed, therefore such continuous casting billet image information belongs to flaw detection qualification.Second, if the continuous casting billet image information
Corresponding field trash information reaches predetermined field trash threshold value, and the continuous casting billet image information is filtered out, e.g., in certain continuous casting billet ingredient
Al, Ca, O, Mg content are higher, these elements are exclusive for covering slag, and continuous casting billet extends in the subsequent operation of rolling, easy shape
It is unqualified so as to cause detecting a flaw at multilayer chain Large Inclusions at center, therefore such continuous casting billet image information is filtered out.
Embodiment two
Based on inventive concept same as the raising method of continuous casting flaw detection qualification rate a kind of in previous embodiment, the present invention is also
A kind of raising continuous casting flaw detection qualification rate device is provided, as shown in Figure 2, comprising:
First obtains unit 11, for obtaining continuous casting billet image information；
First input unit 12, for the continuous casting billet image information to be inputted training pattern, wherein the training pattern
It is obtained by the training of multiple groups training data, each group of training data in training data in the multiple groups includes: the company
Slab image information, mark continuous casting billet center metallographic structure label information and default field trash indication information；
First output unit 13, for obtaining the output information of the training pattern, wherein the output information includes institute
State the corresponding continuous casting billet center metallographic structure information of continuous casting billet image information and field trash information；
Second obtaining unit 14, for according to the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information
With field trash information, screening and filtering is carried out to the continuous casting billet image information, obtains the qualified standard continuous casting billet image letter of flaw detection
Breath.
Further, continuous casting billet image information is obtained described in the first obtains unit, comprising:
Third obtaining unit, for obtaining continuous casting billet image information to be detected；
4th obtaining unit obtains the continuous casting for pre-processing to the continuous casting billet image information to be detected
Base image information, wherein the continuous casting billet image information is size, ratio, the identical image information of pixel.
Further, each group of training data in the training data in multiple groups described in first input unit includes
Identify continuous casting billet center metallographic structure label information, comprising:
5th obtaining unit, for obtaining the crackle in the metallographic structure of continuous casting billet center；
Whether the first judging unit, the crackle for judging in the metallographic structure of the continuous casting billet center meet preassigned figure
Picture；
6th obtaining unit, for not meeting preassigned image when the crackle in the metallographic structure of the continuous casting billet center
When, obtain mark continuous casting billet center metallographic structure label information；
Second input unit, for using the mark continuous casting billet center metallographic structure label information as the first number of tags
According in the input each group of training data.
Further, each group of training data in the training data in multiple groups described in first input unit includes
Default field trash indication information, comprising:
7th obtaining unit, for obtaining the content of the ingredient of the ingredient of field trash and the field trash in continuous casting billet；
8th obtaining unit, for according to the acquisition of the content of the ingredient of the field trash and the ingredient of the field trash
Default field trash indication information；
Third input unit, for inputting described every using the default field trash indication information as the second label data
In one group of training data.
Further, according to the corresponding continuous casting billet center of the continuous casting billet image information described in second obtaining unit
Metallographic structure information and field trash information carry out screening and filtering to the continuous casting billet image information, obtain the qualified standard of flaw detection
Continuous casting billet image information, comprising:
Second judgment unit, for judging that the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information is
It is no to meet preassigned image；
9th obtaining unit, if for the corresponding continuous casting billet center metallographic structure information symbol of the continuous casting billet image information
Preassigned image is closed, predetermined field trash threshold value is obtained；
First execution unit, if not for the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information
Meet preassigned image, the continuous casting billet image information is filtered out.
Further, after the 9th obtaining unit, comprising:
Third judging unit, for judging whether the corresponding field trash information of the continuous casting billet image information reaches pre- clamp
Sundries threshold value；
Tenth obtaining unit, if not reaching pre- clamp for the corresponding field trash information of the continuous casting billet image information
Sundries threshold value obtains the qualified standard continuous casting billet image information of flaw detection；
Second execution unit, if reaching predetermined field trash for the corresponding field trash information of the continuous casting billet image information
Threshold value filters out the continuous casting billet image information.
One of 1 embodiment one of earlier figures improves the various change mode and specific reality of the method for continuous casting flaw detection qualification rate
Example is equally applicable to a kind of raising continuous casting flaw detection qualification rate device of the present embodiment, is closed by aforementioned detect a flaw to a kind of raising continuous casting
The detailed description of the method for lattice rate, those skilled in the art are clear that a kind of raising continuous casting flaw detection conjunction in the present embodiment
The implementation method of lattice rate device, so this will not be detailed here in order to illustrate the succinct of book.
Embodiment three
Based on inventive concept same as the raising method of continuous casting flaw detection qualification rate a kind of in previous embodiment one, the present invention
A kind of computer readable storage medium is also provided, computer program is stored thereon with, before being realized when which is executed by processor
A kind of the step of text either method method for improving continuous casting flaw detection qualification rate.
Wherein, in Fig. 3, bus architecture (is represented) with bus 300, and bus 300 may include any number of interconnection
Bus and bridge, bus 300 will include the one or more processors represented by processor 302 and what memory 304 represented deposits
The various circuits of reservoir link together.Bus 300 can also will peripheral equipment, voltage-stablizer and management circuit etc. it
Various other circuits of class link together, and these are all it is known in the art, therefore, no longer carry out further to it herein
Description.Bus interface 306 provides interface between bus 300 and receiver 301 and transmitter 303.Receiver 301 and transmitter
303 can be the same element, i.e. transceiver, provide the unit for communicating over a transmission medium with various other devices.Place
It manages device 302 and is responsible for management bus 300 and common processing, and memory 304 can be used for storage processor 302 and execute behaviour
Used data when making.
Said one or multiple technical solutions in the embodiment of the present application at least have following one or more technology effects
Fruit:
The method and device for the raising continuous casting flaw detection qualification rate that this specification embodiment provides, passes through the continuous casting billet that will be obtained
Image information inputs training pattern, wherein the training pattern is obtained by the training of multiple groups training data, the instruction in the multiple groups
Practicing each group of training data in data includes: the continuous casting billet image information, mark continuous casting billet center metallographic structure label
Information and default field trash indication information；By by the mark continuous casting billet center metallographic in continuous casting billet image information and training pattern
Tissue label information and default field trash indication information are compared, and obtain the output information of the training pattern, wherein described
Output information includes the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and field trash information；According to institute
The corresponding continuous casting billet center metallographic structure information of continuous casting billet image information and field trash information are stated, to the continuous casting billet image information
Screening and filtering is carried out, the qualified standard continuous casting billet image information of flaw detection is obtained, is able to solve due to continuous casting billet during the rolling process
Easily there is Large Inclusions, micro-crack, and easily aggravation continuous casting billet center segregation and banded structure, causes to detect a flaw unqualified, and nothing
Method quickly identifies the technical issues of flaw detection qualification rate of continuous casting billet, has reached the flaw detection qualification rate for improving continuous casting billet, and reduction is mingled with
Object content guarantees the internal soundness of continuous casting billet, reduces the technical effect of production cost.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
This specification is referring to the method, equipment (system) and computer program product according to this specification embodiment
Flowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagram
The combination of process and/or box in one process and/or box and flowchart and/or the block diagram.It can provide these computers
Processor of the program instruction to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices
To generate a machine, so that generating use by the instruction that computer or the processor of other programmable data processing devices execute
In setting for the function that realization is specified in one or more flows of the flowchart and/or one or more blocks of the block diagram
It is standby.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of equipment, the commander equipment realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although the preferred embodiment of this specification has been described, once a person skilled in the art knows basic wounds
The property made concept, then additional changes and modifications may be made to these embodiments.So the following claims are intended to be interpreted as includes
Preferred embodiment and all change and modification for falling into this specification range.
Obviously, those skilled in the art can carry out various modification and variations without departing from this specification to this specification
Spirit and scope.In this way, if these modifications and variations of this specification belong to this specification claim and its equivalent skill
Within the scope of art, then this specification is also intended to include these modifications and variations.
Claims (9)
1. a kind of method for improving continuous casting flaw detection qualification rate, which is characterized in that the described method includes:
Obtain continuous casting billet image information；
The continuous casting billet image information is inputted into training pattern, wherein the training pattern is obtained by the training of multiple groups training data
, each group of training data in the training data in the multiple groups includes: the continuous casting billet image information, mark continuous casting billet
Center metallographic structure label information and default field trash indication information；
Obtain the output information of the training pattern, wherein the output information includes that the continuous casting billet image information is corresponding
Continuous casting billet center metallographic structure information and field trash information；
According to the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and field trash information, to the continuous casting
Base image information carries out screening and filtering, obtains the qualified standard continuous casting billet image information of flaw detection.
2. the method as described in claim 1, which is characterized in that the acquisition continuous casting billet image information, comprising:
Obtain continuous casting billet image information to be detected；
The continuous casting billet image information to be detected is pre-processed, obtains the continuous casting billet image information, wherein the company
Slab image information is size, ratio, the identical image information of pixel.
3. the method as described in claim 1, which is characterized in that each group of training data in the training data in the multiple groups
Including identifying continuous casting billet center metallographic structure label information, comprising:
Obtain the crackle in the metallographic structure of continuous casting billet center；
Judge whether the crackle in the metallographic structure of the continuous casting billet center meets preassigned image；
When the crackle in the metallographic structure of the continuous casting billet center does not meet preassigned image, mark continuous casting billet center gold is obtained
Phase constitution label information；
Using the mark continuous casting billet center metallographic structure label information as the first label data, each group of trained number is inputted
In.
4. the method as described in claim 1, which is characterized in that each group of training data in the training data in the multiple groups
Including presetting field trash indication information, comprising:
Obtain the content of the ingredient of the ingredient and field trash of field trash in continuous casting billet；
The default field trash indication information is obtained according to the content of the ingredient of the field trash and the ingredient of the field trash；
Using the default field trash indication information as the second label data, input in each group of training data.
5. method as claimed in claim 3, which is characterized in that described according to the corresponding continuous casting billet of the continuous casting billet image information
Center metallographic structure information and field trash information carry out screening and filtering to the continuous casting billet image information, obtain flaw detection qualification
Standard continuous casting billet image information, comprising:
Judge whether the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information meets preassigned image；
If the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information meets preassigned image, obtain pre-
Clamp sundries threshold value；
If the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information does not meet preassigned image, by institute
Continuous casting billet image information is stated to filter out.
6. method as claimed in claim 5, which is characterized in that after the predetermined field trash threshold value of acquisition, comprising:
Judge whether the corresponding field trash information of the continuous casting billet image information reaches predetermined field trash threshold value；
If the corresponding field trash information of the continuous casting billet image information does not reach predetermined field trash threshold value, it is qualified to obtain flaw detection
Standard continuous casting billet image information；
If the corresponding field trash information of the continuous casting billet image information reaches predetermined field trash threshold value, by the continuous casting billet image
Information Filtration.
7. a kind of device for improving continuous casting flaw detection qualification rate, which is characterized in that described device includes:
First obtains unit, for obtaining continuous casting billet image information；
First input unit, for the continuous casting billet image information to be inputted training pattern, wherein the training pattern passes through more
Group training data training obtains, and each group of training data in training data in the multiple groups includes: the continuous casting billet figure
As information, mark continuous casting billet center metallographic structure label information and default field trash indication information；
First output unit, for obtaining the output information of the training pattern, wherein the output information includes the continuous casting
The corresponding continuous casting billet center metallographic structure information of base image information and field trash information；
Second obtaining unit, for according to the corresponding continuous casting billet center metallographic structure information of the continuous casting billet image information and being mingled with
Object information carries out screening and filtering to the continuous casting billet image information, obtains the qualified standard continuous casting billet image information of flaw detection.
8. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claim 1-6 the method is realized when row.
9. a kind of device for improving continuous casting flaw detection qualification rate, including memory, processor and storage on a memory and can located
The computer program run on reason device, which is characterized in that the processor realizes that claim 1-6 is any when executing described program
The step of item the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910777803.0A CN110490862B (en) | 2019-08-22 | 2019-08-22 | Method and device for improving continuous casting flaw detection qualification rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910777803.0A CN110490862B (en) | 2019-08-22 | 2019-08-22 | Method and device for improving continuous casting flaw detection qualification rate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110490862A true CN110490862A (en) | 2019-11-22 |
| CN110490862B CN110490862B (en) | 2022-08-09 |
Family
ID=68552900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910777803.0A Active CN110490862B (en) | 2019-08-22 | 2019-08-22 | Method and device for improving continuous casting flaw detection qualification rate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110490862B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112182910A (en) * | 2020-10-21 | 2021-01-05 | 江苏中利集团股份有限公司 | Method and device for controlling preparation effect of cross-linked material |
| CN112182874A (en) * | 2020-09-25 | 2021-01-05 | 江苏中利集团股份有限公司 | Method and device for improving performance of polymer material based on toughness and heat resistance |
| CN112182979A (en) * | 2020-10-21 | 2021-01-05 | 江苏中利集团股份有限公司 | Method and device for improving compatibility effect of resin and filling aid |
| CN112331280A (en) * | 2020-10-21 | 2021-02-05 | 江苏中利集团股份有限公司 | Processing method and device for flame retardant modification technology |
| CN112396131A (en) * | 2020-12-11 | 2021-02-23 | 广西味豪食品有限公司 | Papaya shred quality monitoring method and device |
| CN112666912A (en) * | 2020-12-31 | 2021-04-16 | 南通市天赫软件科技有限公司 | Dyeing control method and device for textile printing and dyeing |
| CN112818810A (en) * | 2021-01-27 | 2021-05-18 | 广西融安蚂蚁农业发展有限公司 | Kumquat intelligent sorting method and device based on big data |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1355145A1 (en) * | 2002-04-19 | 2003-10-22 | Central Iron & Steel Research Institute | A method for analysing metals in the fundamental state utilizing the statistical distribution of elements |
| CN1651905A (en) * | 2005-02-05 | 2005-08-10 | 石家庄钢铁股份有限公司 | Quantitative analyzing method for non-metal residue in steel |
| CN101995489A (en) * | 2010-09-29 | 2011-03-30 | 山西太钢不锈钢股份有限公司 | Method for inspecting inclusion of steel for low temperature pressure vessel |
| CN102608126A (en) * | 2012-02-23 | 2012-07-25 | 中冶连铸技术工程股份有限公司 | On-line detection method and device for surface defects of high-temperature continuously cast bloom |
| CN102637258A (en) * | 2012-04-01 | 2012-08-15 | 首钢总公司 | Method for creating online surface quality detection system defect library |
| CN102937784A (en) * | 2012-10-30 | 2013-02-20 | 中冶南方工程技术有限公司 | Artificial neural network based method for controlling online prediction of casting billet quality |
| CN103245711A (en) * | 2013-04-18 | 2013-08-14 | 沈阳理工大学 | Neutral network-based molten aluminum nonmetallic inclusion online soft measurement device and method |
| CN109087280A (en) * | 2018-07-02 | 2018-12-25 | 北京百度网讯科技有限公司 | Continuous casting billet quality detection method, device, control equipment, server and medium |
| CN109142533A (en) * | 2018-10-22 | 2019-01-04 | 广东工业大学 | A kind of rapid detection method and equipment of internal defect in cast |
| CN109472798A (en) * | 2018-12-10 | 2019-03-15 | 重庆理工大学 | Live pig fat content detection model training method and live pig fat content detection method |
| CN109658396A (en) * | 2018-12-06 | 2019-04-19 | 华中科技大学 | A kind of casting x-ray image defect identification method based on selective search and CNN |
| CN109668897A (en) * | 2019-03-04 | 2019-04-23 | 南京大学 | The vision detection system and its detection method of cyclic annular precision component surface micro defect |
| CN109743879A (en) * | 2016-12-30 | 2019-05-10 | 同济大学 | A kind of underground pipe gallery leakage detection method based on the processing of Dynamic IR thermography |
| CN109856359A (en) * | 2019-01-31 | 2019-06-07 | 江苏省沙钢钢铁研究院有限公司 | Method for acquiring continuous casting billet center segregation quantitative standard |
-
2019
- 2019-08-22 CN CN201910777803.0A patent/CN110490862B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1355145A1 (en) * | 2002-04-19 | 2003-10-22 | Central Iron & Steel Research Institute | A method for analysing metals in the fundamental state utilizing the statistical distribution of elements |
| CN1651905A (en) * | 2005-02-05 | 2005-08-10 | 石家庄钢铁股份有限公司 | Quantitative analyzing method for non-metal residue in steel |
| CN101995489A (en) * | 2010-09-29 | 2011-03-30 | 山西太钢不锈钢股份有限公司 | Method for inspecting inclusion of steel for low temperature pressure vessel |
| CN102608126A (en) * | 2012-02-23 | 2012-07-25 | 中冶连铸技术工程股份有限公司 | On-line detection method and device for surface defects of high-temperature continuously cast bloom |
| CN102637258A (en) * | 2012-04-01 | 2012-08-15 | 首钢总公司 | Method for creating online surface quality detection system defect library |
| CN102937784A (en) * | 2012-10-30 | 2013-02-20 | 中冶南方工程技术有限公司 | Artificial neural network based method for controlling online prediction of casting billet quality |
| CN103245711A (en) * | 2013-04-18 | 2013-08-14 | 沈阳理工大学 | Neutral network-based molten aluminum nonmetallic inclusion online soft measurement device and method |
| CN109743879A (en) * | 2016-12-30 | 2019-05-10 | 同济大学 | A kind of underground pipe gallery leakage detection method based on the processing of Dynamic IR thermography |
| CN109087280A (en) * | 2018-07-02 | 2018-12-25 | 北京百度网讯科技有限公司 | Continuous casting billet quality detection method, device, control equipment, server and medium |
| CN109142533A (en) * | 2018-10-22 | 2019-01-04 | 广东工业大学 | A kind of rapid detection method and equipment of internal defect in cast |
| CN109658396A (en) * | 2018-12-06 | 2019-04-19 | 华中科技大学 | A kind of casting x-ray image defect identification method based on selective search and CNN |
| CN109472798A (en) * | 2018-12-10 | 2019-03-15 | 重庆理工大学 | Live pig fat content detection model training method and live pig fat content detection method |
| CN109856359A (en) * | 2019-01-31 | 2019-06-07 | 江苏省沙钢钢铁研究院有限公司 | Method for acquiring continuous casting billet center segregation quantitative standard |
| CN109668897A (en) * | 2019-03-04 | 2019-04-23 | 南京大学 | The vision detection system and its detection method of cyclic annular precision component surface micro defect |
Non-Patent Citations (2)
| Title |
|---|
| SHUIGEN WANG 等，: "development and application of CISDI online slab quality diagnosis & analysis system", 《ADVANCED MATERIALS RESEARCH》 * |
| 陈丹，: "钢中夹杂物的高频水浸超声检测与评价方法研究", 《中国博士学位论文全文数据库工程科技Ⅰ辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112182874A (en) * | 2020-09-25 | 2021-01-05 | 江苏中利集团股份有限公司 | Method and device for improving performance of polymer material based on toughness and heat resistance |
| CN112182874B (en) * | 2020-09-25 | 2022-12-16 | 江苏中利集团股份有限公司 | Method and device for improving performance of polymer material based on toughness and heat resistance |
| CN112182910A (en) * | 2020-10-21 | 2021-01-05 | 江苏中利集团股份有限公司 | Method and device for controlling preparation effect of cross-linked material |
| CN112182979A (en) * | 2020-10-21 | 2021-01-05 | 江苏中利集团股份有限公司 | Method and device for improving compatibility effect of resin and filling aid |
| CN112331280A (en) * | 2020-10-21 | 2021-02-05 | 江苏中利集团股份有限公司 | Processing method and device for flame retardant modification technology |
| CN112182910B (en) * | 2020-10-21 | 2022-12-20 | 江苏中利集团股份有限公司 | Method and device for controlling preparation effect of cross-linked material |
| CN112331280B (en) * | 2020-10-21 | 2023-01-17 | 江苏中利集团股份有限公司 | Processing method and device for flame retardant modification technology |
| CN112182979B (en) * | 2020-10-21 | 2023-01-17 | 江苏中利集团股份有限公司 | Method and device for improving compatibility effect of resin and filling aid |
| CN112396131A (en) * | 2020-12-11 | 2021-02-23 | 广西味豪食品有限公司 | Papaya shred quality monitoring method and device |
| CN112666912A (en) * | 2020-12-31 | 2021-04-16 | 南通市天赫软件科技有限公司 | Dyeing control method and device for textile printing and dyeing |
| CN112818810A (en) * | 2021-01-27 | 2021-05-18 | 广西融安蚂蚁农业发展有限公司 | Kumquat intelligent sorting method and device based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110490862B (en) | 2022-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110490862A (en) | A kind of method and device improving continuous casting flaw detection qualification rate | |
| WO2021036636A1 (en) | Vibration detection method and apparatus for lifting device, server and storage medium | |
| CN110503641A (en) | A kind of method and apparatus improving continuous casting billet face crack | |
| CN114926463B (en) | Production quality detection method suitable for chip circuit board | |
| WO2006063268B1 (en) | Computer-implemented methods for detecting and/or sorting defects in a design pattern of a reticle | |
| CN110533032A (en) | A kind of method and apparatus obtaining high-purity cryogenic steel | |
| CN106789844B (en) | Malicious user identification method and device | |
| CN107240092A (en) | A kind of image blur detection method and device | |
| CN109724993A (en) | Detection method, device and the storage medium of the degree of image recognition apparatus | |
| CN104749801B (en) | High Precision Automatic optical detecting method and system | |
| CN109614873A (en) | Train safety sign detection method, server and storage medium neural network based | |
| CN112749735B (en) | Converter tapping steel flow identification method, system, medium and terminal based on deep learning | |
| CN104243967A (en) | Image detection method and device | |
| CN110394432A (en) | A kind of method of inspection and device of continuous casting protection pouring | |
| CN110631475B (en) | On-site target size detection method | |
| US20230048649A1 (en) | Method of processing image, electronic device, and medium | |
| CN109584224B (en) | Method for analyzing and displaying X-ray image of casting | |
| CN110532924A (en) | A kind of identifying processing method and device of high heat resistance steel | |
| JP5257063B2 (en) | Defect detection method and defect detection apparatus | |
| CN107767372B (en) | Chip pin online visual detection system and method for layered parallel computing | |
| CN112650789B (en) | Monitoring and early warning system for steel product data channel | |
| CN104463180B (en) | The method for identifying conducting particles press mark | |
| CN107578168A (en) | A kind of method, apparatus and electronic equipment for the transplanting of defect storehouse | |
| CN114663365A (en) | Defect detection method, device and computer storage medium | |
| CN106778675A (en) | A kind of recognition methods of target in video image object and device |
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 |