CN110490862B - Method and device for improving continuous casting flaw detection qualification rate - Google Patents
Method and device for improving continuous casting flaw detection qualification rate Download PDFInfo
- Publication number
- CN110490862B CN110490862B CN201910777803.0A CN201910777803A CN110490862B CN 110490862 B CN110490862 B CN 110490862B CN 201910777803 A CN201910777803 A CN 201910777803A CN 110490862 B CN110490862 B CN 110490862B
- Authority
- CN
- China
- Prior art keywords
- continuous casting
- casting billet
- information
- image information
- inclusion
- 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.)
- Active
Links
Images
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)
- Continuous Casting (AREA)
- Image Analysis (AREA)
- Investigating And Analyzing Materials By Characteristic Methods (AREA)
Abstract
The embodiment of the specification provides a method and a device for improving the continuous casting flaw detection yield, wherein the obtained continuous casting image information is input into a training model, the training model is obtained by training multiple groups of training data, and each group of training data in the multiple groups comprises: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained; acquiring output information of the training model, wherein the output information comprises continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information; according to continuous casting billet center metallographic structure information and inclusion information that continuous casting billet image information corresponds, right continuous casting billet image information screens and filters, obtains the qualified standard continuous casting billet image information of detecting a flaw, has reached the qualification rate of detecting a flaw that improves the continuous casting billet, reduces inclusion content, guarantees the internal quality of continuous casting billet, reduction in production cost's technological effect.
Description
Technical Field
The embodiment of the specification relates to the technical field of metallurgy, in particular to a method and a device for improving the qualification rate of continuous casting flaw detection.
Background
At present, the production cost of the steel industry is high, the overall profit is not high, and particularly medium plate enterprises are in a state of slight profit or cost loss. The flaw detection qualification rate is an important economic index of medium plate steel enterprises, and the economic benefit, the production cost and the contract exchange rate of the enterprises are directly determined by the flaw detection qualification rate. The steel plate is easy to have core element segregation, looseness and microcracks in the steel plate in the continuous casting production process, so that the flaw detection of the rolled steel plate is unqualified, and therefore, the improvement of the flaw detection qualification rate of the steel plate has important significance for steel production.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
in the prior art, large inclusions and microcracks are easy to appear in the continuous casting billet in the rolling process, and the center segregation and the banded structure of the continuous casting billet are easy to aggravate, so that the flaw detection is unqualified, and the flaw detection qualified rate of the continuous casting billet cannot be quickly identified.
Disclosure of Invention
The embodiment of the specification provides a method and a device for improving the flaw detection qualification rate of continuous casting, solves the technical problems that in the prior art, large inclusions and microcracks are easy to appear in the continuous casting billet in the rolling process, and the center segregation and the banded structure of the continuous casting billet are easy to aggravate, so that the flaw detection is unqualified, and the flaw detection qualification rate of the continuous casting billet cannot be quickly identified, and achieves the technical effects of improving the flaw detection qualification rate of the continuous casting billet, reducing the content of the inclusions, ensuring the internal quality of the continuous casting billet, and reducing the production cost.
In view of the above problems, embodiments of the present application are proposed to provide a method and an apparatus for improving the yield of continuous casting flaw detection.
In a first aspect, embodiments of the present specification provide a method for improving a continuous casting flaw detection yield, where image information of a continuous casting slab is obtained; inputting the image information of the continuous casting billet into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained; acquiring output information of the training model, wherein the output information comprises continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information; and screening and filtering the continuous casting billet image information according to continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information to obtain standard continuous casting billet image information qualified in flaw detection.
Preferably, the obtaining of the image information of the continuous casting billet comprises: acquiring continuous casting billet image information to be detected; and preprocessing the continuous casting billet image information to be detected to obtain the continuous casting billet image information, wherein the continuous casting billet image information is the same image information with the same size, proportion and pixel.
Preferably, each of the training data sets in the plurality of sets includes information identifying a slab center metallographic structure label, including: obtaining cracks in the central metallographic structure of the continuous casting billet; judging whether the cracks in the central metallographic structure of the continuous casting billet meet a preset standard image or not; when the cracks in the continuous casting billet central metallographic structure do not accord with the preset standard image, obtaining label information for identifying the continuous casting billet central metallographic structure; and inputting the label information for identifying the metallographic structure of the continuous casting slab center as first label data into each group of training data.
Preferably, each of the training data sets in the plurality of sets includes preset inclusion index information, including: obtaining the components of the inclusions in the continuous casting billet and the contents of the components of the inclusions; acquiring preset inclusion index information according to the components of the inclusions and the content of the components of the inclusions; and inputting the preset inclusion index information serving as second label data into each group of training data.
Preferably, the continuous casting billet image information is screened and filtered according to continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information, and standard continuous casting billet image information qualified in flaw detection is obtained, and the method comprises the following steps: judging whether the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a preset standard image or not; if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a preset standard image, a preset inclusion threshold value is obtained; and if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information does not accord with a preset standard image, filtering the continuous casting billet image information.
Preferably, after obtaining the predetermined inclusion threshold, the method includes: judging whether the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value; if the inclusion information corresponding to the continuous casting billet image information does not reach the preset inclusion threshold value, obtaining standard continuous casting billet image information qualified in flaw detection; and filtering the continuous casting billet image information if the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value.
In a second aspect, an embodiment of the present specification provides an apparatus for increasing yield of continuous casting flaw detection, where the apparatus includes:
the first obtaining unit is used for obtaining image information of a continuous casting billet;
the first input unit is used for inputting the image information of the continuous casting billet into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained;
the first output unit is used for obtaining output information of the training model, wherein the output information comprises continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information;
and the second obtaining unit is used for screening and filtering the continuous casting billet image information according to the continuous casting billet central metallographic structure information and the inclusion information corresponding to the continuous casting billet image information to obtain standard continuous casting billet image information qualified in flaw detection.
Preferably, the obtaining of the image information of the continuous casting slab in the first obtaining unit includes:
the third obtaining unit is used for obtaining image information of the continuous casting billet to be detected;
and the fourth obtaining unit is used for preprocessing the image information of the continuous casting billet to be detected to obtain the image information of the continuous casting billet, wherein the image information of the continuous casting billet is the same image information with the same size, proportion and pixel.
Preferably, each of the training data in the plurality of sets in the first input unit includes information identifying a slab center metallographic structure label, including:
a fifth obtaining unit, configured to obtain a crack in a central metallographic structure of the continuous casting slab;
the first judging unit is used for judging whether the cracks in the central metallographic structure of the continuous casting slab meet a preset standard image or not;
a sixth obtaining unit, configured to obtain label information for identifying the continuous casting billet central metallographic structure when the crack in the continuous casting billet central metallographic structure does not meet the predetermined standard image;
and the second input unit is used for inputting the label information for identifying the metallographic structure of the continuous casting slab center as first label data into each group of training data.
Preferably, each of the training data in the plurality of sets in the first input unit includes preset inclusion index information, including:
a seventh obtaining unit, configured to obtain a component of an inclusion in the continuous casting slab and a content of the component of the inclusion;
an eighth obtaining unit, configured to obtain the preset inclusion index information according to the components of the inclusions and the content of the components of the inclusions;
and the third input unit is used for inputting the preset inclusion index information serving as second label data into each group of training data.
Preferably, in the second obtaining unit, the continuous casting billet image information is filtered according to continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information, so as to obtain standard continuous casting billet image information qualified in flaw detection, and the method includes:
the second judging unit is used for judging whether the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a preset standard image or not;
a ninth obtaining unit, configured to obtain a predetermined inclusion threshold if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a predetermined standard image;
and the first execution unit is used for filtering the continuous casting billet image information if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information does not accord with a preset standard image.
Preferably, after the ninth obtaining unit, the method includes:
the third judging unit is used for judging whether the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value;
a tenth obtaining unit, configured to obtain standard continuous casting billet image information that is qualified for flaw detection if inclusion information corresponding to the continuous casting billet image information does not reach a predetermined inclusion threshold;
and the second execution unit is used for filtering the continuous casting billet image information if the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value.
In a third aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of any of the methods described above.
In a fourth aspect, an embodiment of the present disclosure provides an apparatus for improving yield of continuous casting flaw detection, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor performs the steps of any one of the above methods.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
in the method and the apparatus for improving the yield of continuous casting flaw detection provided by the embodiment of the present specification, the obtained image information of the continuous casting slab is input into a training model, wherein the training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets includes: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained; comparing continuous casting billet image information with continuous casting billet central metallographic structure label information and preset inclusion index information in a training model to obtain output information of the training model, wherein the output information comprises continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information; according to continuous casting billet center metallographic structure information and inclusion information that continuous casting billet image information corresponds, it is right continuous casting billet image information screens and filters, obtains flaw detection qualified standard continuous casting billet image information, can solve because the continuous casting billet is easy large-scale inclusion, microcrack to appear in rolling process, and easy aggravation continuous casting billet center segregation and banded structure, lead to detecting a flaw unqualified, and the technical problem of the qualification rate of detecting a flaw of unable quick identification continuous casting billet, reached the qualification rate of detecting a flaw that improves the continuous casting billet, reduce inclusion content, guarantee the internal quality of continuous casting billet, reduction in production cost's technological effect.
Drawings
FIG. 1 is a flow chart of a method for improving the yield of continuous casting flaw detection provided in the embodiments of the present specification;
FIG. 2 is a schematic diagram of an apparatus for increasing the yield of flaw detection in continuous casting provided in the embodiments of the present specification;
FIG. 3 is a schematic diagram of another apparatus for improving the continuous casting flaw detection yield provided in the embodiments of the present specification.
The reference numbers illustrate: a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, a bus interface 306.
Detailed Description
The embodiment of the invention provides a method and a device for improving the flaw detection qualification rate of continuous casting, which are used for solving the technical problems that the flaw detection is unqualified and the flaw detection qualification rate of a continuous casting billet cannot be rapidly identified because large-scale inclusions and microcracks are easy to appear in the rolling process of the continuous casting billet and the center segregation and the banded structure of the continuous casting billet are easy to aggravate in the prior art, and the technical scheme provided by the invention has the following general ideas:
in the technical scheme of the embodiment of the invention, the image information of the continuous casting billet is obtained; inputting the image information of the continuous casting billet into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained; acquiring output information of the training model, wherein the output information comprises continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information; and screening and filtering the continuous casting billet image information according to continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information to obtain standard continuous casting billet image information qualified in flaw detection. The technical problems that large impurities and microcracks are easy to appear in the rolling process of the continuous casting billet, and the center segregation and the banded structure of the continuous casting billet are easy to aggravate, so that the flaw detection is unqualified, and the flaw detection qualification rate of the continuous casting billet cannot be quickly identified can be solved, the flaw detection qualification rate of the continuous casting billet is improved, the content of the impurities is reduced, the internal quality of the continuous casting billet is guaranteed, and the production cost is reduced are solved.
In order to better understand the technical solutions of the embodiments of the present specification, the technical solutions of the embodiments of the present specification are described in detail below with reference to the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and examples of the present specification are detailed descriptions of the technical solutions of the embodiments of the present specification, and are not limitations of the technical solutions of the embodiments and examples of the present specification, and the technical features of the embodiments and examples of the present specification may be combined with each other without conflict.
The terminology used in the description presented herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Example one
FIG. 1 is a schematic flow chart of a method for improving the yield of continuous casting flaw detection in an embodiment of the invention. As shown in fig. 1. The method is applied to equipment for improving the continuous casting flaw detection qualification rate, the processing equipment for improving the continuous casting flaw detection qualification rate comprises input equipment and display equipment, a picture input module, a picture processing module, a memory and a signal input module are arranged in the input equipment, the input equipment can be connected with equipment for generating output signals such as an energy spectrum scanner and a scanning electron microscope, and the display equipment is connected with the input equipment and can display images processed by the input equipment such as the energy spectrum scanner and the scanning electron microscope. The method comprises steps S101-S104.
S101: acquiring continuous casting billet image information;
further, the obtaining of the image information of the continuous casting billet comprises: acquiring continuous casting billet image information to be detected; and preprocessing the continuous casting billet image information to be detected to obtain the continuous casting billet image information, wherein the continuous casting billet image information is the same image information with the same size, proportion and pixel.
Specifically, this application embodiment provides a method for improving continuous casting flaw detection qualification rate, treat to detect the continuous casting billet through adopting under the process environment of continuous casting billet energy spectrum scanner, scanning electron microscope etc. and scan the shooting and obtain the continuous casting billet image information that detects, for example, a certain steel plant is before obtaining to detect continuous casting billet image information, right it carries out slow cooling treatment to detect the continuous casting billet, can reduce the microcrack of continuous casting billet through slow cooling treatment, reduces continuous casting billet center segregation and banded structure, avoids the appearance of large-scale inclusion, and then can improve the flaw detection qualification rate of continuous casting billet, wherein, detect a flaw indicates the crackle or the defect of detecting metallic material or part inside. The image information of the continuous casting billet to be detected is preprocessed, and the image information of the continuous casting billet to be detected is processed in a unified mode through image processing software to obtain the image information of the continuous casting billet, wherein the image information of the continuous casting billet is the same in size, proportion and pixels, so that the rapid analysis and processing of a training model are facilitated, the flaw detection qualification rate of the continuous casting billet is improved, the content of inclusions is reduced, and the internal quality of the continuous casting billet is guaranteed.
S102: inputting the image information of the continuous casting billet into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained;
further, each of the training data in the plurality of sets includes identification continuous casting billet center metallographic structure label information, including: obtaining cracks in the central metallographic structure of the continuous casting billet; judging whether the cracks in the central metallographic structure of the continuous casting billet meet a preset standard image or not; when the cracks in the continuous casting billet central metallographic structure do not accord with the preset standard image, obtaining label information for identifying the continuous casting billet central metallographic structure; and inputting the label information for identifying the metallographic structure of the continuous casting slab center as first label data into each group of training data.
Further, each of the training data sets in the plurality of sets includes preset inclusion index information, including: obtaining the components of the inclusions in the continuous casting billet and the contents of the components of the inclusions; obtaining the preset inclusion index information according to the components of the inclusions and the content of the components of the inclusions; and inputting the preset inclusion index information serving as second label data into each group of training data.
Specifically, the obtained image information of the continuous casting billet is input into a training model, wherein the training model is obtained by training a plurality of sets of training data, that is, each set of training data in the plurality of sets in the training model includes: the device comprises continuous casting billet image information, identification continuous casting billet center metallographic structure label information and preset inclusion index information. In order to improve the flaw detection qualification rate of the continuous casting billet, the width, the size and the depth of an internal micro crack of the continuous casting billet and the components and the content of inclusions of the continuous casting billet need to be limited. Firstly, the label information of the microcracks in the central metallographic structure of the continuous casting billet is identified, wherein the factors influencing the microcracks in the continuous casting billet comprise the central segregation and the banded structure of the continuous casting billet. Obtaining the microcracks in the central metallographic structure of the continuous casting billet through an energy spectrum scanner and a scanning electron microscope, and judging whether the microcracks in the central metallographic structure of the continuous casting billet meet a preset standard image, wherein the preset standard image is a preset threshold value of the width, the size and the depth of the cracks qualified for flaw detection of the continuous casting billet. And when the cracks in the continuous casting billet central metallographic structure do not accord with the preset standard image, obtaining label information for identifying the continuous casting billet central metallographic structure, namely the unqualified continuous casting billet flaw detection label. And inputting the label information for identifying the metallographic structure of the continuous casting slab center as first label data into each group of training data, and performing comparison training with the continuous casting slab image information input into a training model. And secondly, presetting inclusion index information as one of each set of training data in the training model. By obtaining the components of the inclusions in the continuous casting billet and the contents of the components of the inclusions, for example, the contents of Al, Ca and O in a certain steel product are higher, the chain-shaped inclusions in the steel product are found to be aluminum-calcium oxides through energy spectrum analysis. And obtaining the preset inclusion index information according to the components of the inclusions and the contents of the components of the inclusions, namely, if the components of the inclusions and the contents of the components of the inclusions exceed the qualified standard, the inclusions can cause unqualified flaw detection, and setting the components of the inclusions and the contents of the components of the inclusions as the inclusion index information. And inputting the preset inclusion index information as second label data into each group of training data, and performing comparison training with the continuous casting billet image information input in the training model.
S103: acquiring output information of the training model, wherein the output information comprises continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information;
specifically, the image information of the continuous casting slab is input into a training model for comparison training through the step S102, and then the output information of the training model is obtained. The output information comprises continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information and inclusion information corresponding to the continuous casting billet image information, namely the continuous casting billet central metallographic structure information after the continuous casting billet image information is compared with identification continuous casting billet central metallographic structure label information and the inclusion information after the continuous casting billet image information is compared with preset inclusion index information.
S104: and screening and filtering the continuous casting billet image information according to continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information to obtain standard continuous casting billet image information qualified in flaw detection.
Further, according to continuous casting billet center metallographic structure information and inclusion information that continuous casting billet image information corresponds, it is right continuous casting billet image information screens and filters, obtains the qualified standard continuous casting billet image information of detecting a flaw, includes: judging whether the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a preset standard image or not; if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a preset standard image, a preset inclusion threshold value is obtained; and if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information does not accord with a preset standard image, filtering the continuous casting billet image information.
Further, after obtaining the predetermined inclusion threshold, the method includes: judging whether the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value; if the inclusion information corresponding to the continuous casting billet image information does not reach the preset inclusion threshold value, obtaining standard continuous casting billet image information qualified in flaw detection; and filtering the continuous casting billet image information if the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value.
Specifically, whether the metallographic structure information of the center of the continuous casting billet corresponding to the image information of the continuous casting billet meets a preset standard image is judged, wherein the preset standard image is a preset threshold value of the width, the size and the depth of a crack which is qualified for flaw detection of the continuous casting billet. The continuous casting billet image information corresponds to the continuous casting billet center metallographic structure information, and the first condition is that if the continuous casting billet center metallographic structure information corresponding to the continuous casting billet image information accords with a preset standard image, a preset inclusion threshold value is obtained, namely, cracks in the continuous casting billet center metallographic structure information corresponding to the continuous casting billet image information are fine and accord with the flaw detection qualification rate, so that the component and the content of inclusions in the continuous casting billet can be further compared to influence the flaw detection qualification rate. And secondly, if the central metallographic structure information of the continuous casting billet corresponding to the image information of the continuous casting billet does not accord with a preset standard image, namely, a relatively obvious crack appears in the continuous casting billet, and the data of the crack exceeds the width, size and depth of the crack specified in the preset standard image, so that the image information of the continuous casting billet is filtered, and the filtered continuous casting billet is unqualified for flaw detection. If the center image of a certain continuous casting billet has fine, or intermittent or continuous micro cracks which do not accord with the preset standard image, the image information of the continuous casting billet is filtered. Meanwhile, in the first situation that the metallographic structure information of the center of the continuous casting billet corresponding to the image information of the continuous casting billet appears, the influence of the tiny internal cracks of the continuous casting billet on flaw detection is not large, and inclusions in the continuous casting billet need to be further explored. And judging whether the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold or not after the preset inclusion threshold is obtained, wherein the first condition is that if the inclusion information corresponding to the continuous casting billet image information does not reach the preset inclusion threshold, standard continuous casting billet image information qualified in flaw detection is obtained, namely the content of the inclusion corresponding to the continuous casting billet image information is low, and large inclusions cannot be formed due to extension in the subsequent rolling process, so that the continuous casting billet image information is qualified in flaw detection. Secondly, if the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold, the continuous casting billet image information is filtered, for example, the contents of Al, Ca, O and Mg in the components of a certain continuous casting billet are high, the elements are unique to the covering slag, the continuous casting billet extends in the subsequent rolling process, a plurality of layers of chain-shaped large inclusions at the center are easily formed, and therefore flaw detection is unqualified, and the continuous casting billet image information is filtered.
Example two
Based on the same inventive concept as the method for improving the continuous casting flaw detection qualification rate in the previous embodiment, the invention also provides a device for improving the continuous casting flaw detection qualification rate, as shown in fig. 2, comprising:
a first obtaining unit 11, configured to obtain image information of a continuous casting slab;
the first input unit 12 is configured to input the image information of the continuous casting slab into a training model, where the training model is obtained by training multiple sets of training data, and each set of training data in the multiple sets includes: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained;
the first output unit 13 is configured to obtain output information of the training model, where the output information includes continuous casting slab central metallographic structure information and inclusion information corresponding to the continuous casting slab image information;
and the second obtaining unit 14 is configured to screen and filter the continuous casting billet image information according to continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information, so as to obtain standard continuous casting billet image information qualified in flaw detection.
Further, the obtaining of the image information of the continuous casting slab in the first obtaining unit includes:
the third obtaining unit is used for obtaining image information of the continuous casting billet to be detected;
and the fourth obtaining unit is used for preprocessing the image information of the continuous casting billet to be detected to obtain the image information of the continuous casting billet, wherein the image information of the continuous casting billet is the same image information with the same size, proportion and pixel.
Further, each of the training data in the plurality of sets in the first input unit includes information identifying a continuous casting billet central metallographic structure label, including:
a fifth obtaining unit, configured to obtain a crack in a central metallographic structure of the continuous casting slab;
the first judging unit is used for judging whether the cracks in the central metallographic structure of the continuous casting slab meet a preset standard image or not;
a sixth obtaining unit, configured to obtain label information for identifying the continuous casting billet central metallographic structure when the crack in the continuous casting billet central metallographic structure does not meet the predetermined standard image;
and the second input unit is used for inputting the label information for identifying the metallographic structure of the continuous casting slab center as first label data into each group of training data.
Further, each of the sets of training data in the first input unit includes preset inclusion index information, including:
a seventh obtaining unit, configured to obtain a component of an inclusion in the continuous casting slab and a content of the component of the inclusion;
an eighth obtaining unit, configured to obtain the preset inclusion index information according to the components of the inclusions and the content of the components of the inclusions;
and the third input unit is used for inputting the preset inclusion index information serving as second label data into each group of training data.
Further, in the second obtaining unit, the continuous casting billet image information is filtered according to the continuous casting billet central metallographic structure information and the inclusion information corresponding to the continuous casting billet image information, and standard continuous casting billet image information qualified in flaw detection is obtained, including:
the second judging unit is used for judging whether the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a preset standard image or not;
a ninth obtaining unit, configured to obtain a predetermined inclusion threshold if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a predetermined standard image;
and the first execution unit is used for filtering the continuous casting billet image information if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information does not accord with a preset standard image.
Further, after the ninth obtaining unit, the method includes:
the third judging unit is used for judging whether the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value;
a tenth obtaining unit, configured to obtain standard continuous casting billet image information that is qualified for flaw detection if inclusion information corresponding to the continuous casting billet image information does not reach a predetermined inclusion threshold;
and the second execution unit is used for filtering the continuous casting billet image information if the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value.
Various modifications and specific examples of the method for improving the continuous casting flaw detection qualification rate in the first embodiment of fig. 1 are also applicable to the apparatus for improving the continuous casting flaw detection qualification rate in the present embodiment, and the implementation method of the apparatus for improving the continuous casting flaw detection qualification rate in the present embodiment is clear to those skilled in the art from the foregoing detailed description of the method for improving the continuous casting flaw detection qualification rate, so for the brevity of the description, detailed description is omitted here.
EXAMPLE III
Based on the same inventive concept as the method for improving the qualification rate of continuous casting flaw detection in the first embodiment, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, realizes the steps of any one of the methods for improving the qualification rate of continuous casting flaw detection described above.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
in the method and the apparatus for improving the yield of continuous casting flaw detection provided by the embodiment of the present specification, the obtained image information of the continuous casting slab is input into a training model, wherein the training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets includes: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained; comparing continuous casting billet image information with continuous casting billet central metallographic structure label information and preset inclusion index information in a training model to obtain output information of the training model, wherein the output information comprises continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information; according to continuous casting billet center metallographic structure information and inclusion information that continuous casting billet image information corresponds, it is right continuous casting billet image information screens and filters, obtains the qualified standard continuous casting billet image information of detecting a flaw, can solve because the continuous casting billet easily appears large-scale inclusion, microcrack in rolling process, and easy aggravation continuous casting billet center segregation and banded structure, leads to detecting a flaw unqualified, and can't discern the technical problem of the qualification rate of detecting a flaw of continuous casting billet fast, reached the qualification rate of detecting a flaw that improves the continuous casting billet, reduce inclusion content, guarantee the internal quality of continuous casting billet, reduction in production cost's technological effect.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present specification have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all changes and modifications that fall within the scope of the specification.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present specification without departing from the spirit and scope of the specification. Thus, if such modifications and variations of the present specification fall within the scope of the claims of the present specification and their equivalents, the specification is intended to include such modifications and variations.
Claims (5)
1. A method for improving the qualification rate of continuous casting flaw detection is characterized by comprising the following steps:
acquiring continuous casting billet image information;
inputting the image information of the continuous casting billet into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained;
acquiring output information of the training model, wherein the output information comprises continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information;
screening and filtering the continuous casting billet image information according to continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information to obtain standard continuous casting billet image information qualified in flaw detection;
each group of training data in the multiple groups comprises identification continuous casting billet center metallographic structure label information, and the identification continuous casting billet center metallographic structure label information comprises the following components: obtaining cracks in the central metallographic structure of the continuous casting billet; judging whether the cracks in the central metallographic structure of the continuous casting billet meet a preset standard image or not; when the cracks in the continuous casting billet central metallographic structure do not accord with the preset standard image, obtaining label information for identifying the continuous casting billet central metallographic structure; taking the label information of the metallographic structure of the center of the identification continuous casting billet as first label data, and inputting the first label data into each group of training data;
each set of training data in the plurality of sets comprises preset inclusion index information, and the method comprises the following steps:
obtaining the components of the inclusions in the continuous casting billet and the contents of the components of the inclusions;
acquiring preset inclusion index information according to the components of the inclusions and the content of the components of the inclusions;
inputting the preset inclusion index information into each group of training data as second label data;
according to continuous casting billet center metallographic structure information and inclusion information that continuous casting billet image information corresponds, right continuous casting billet image information screens and filters, obtains qualified standard continuous casting billet image information of detecting a flaw, includes:
judging whether the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a preset standard image or not;
if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a preset standard image, a preset inclusion threshold value is obtained;
if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information does not accord with a preset standard image, filtering the continuous casting billet image information;
after the predetermined inclusion threshold is obtained, the method comprises the following steps:
judging whether the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value;
if the inclusion information corresponding to the continuous casting billet image information does not reach the preset inclusion threshold value, obtaining standard continuous casting billet image information qualified in flaw detection;
and filtering the continuous casting billet image information if the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value.
2. The method of claim 1, wherein the obtaining slab image information comprises:
acquiring continuous casting billet image information to be detected;
and preprocessing the continuous casting billet image information to be detected to obtain the continuous casting billet image information, wherein the continuous casting billet image information is the same image information with the same size, proportion and pixel.
3. An apparatus for increasing the yield of continuous casting flaw detection, the apparatus comprising:
the first obtaining unit is used for obtaining image information of a continuous casting billet;
the first input unit is used for inputting the image information of the continuous casting billet into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the continuous casting billet image information, the continuous casting billet center metallographic structure label identification information and the preset inclusion index information are obtained;
the first output unit is used for obtaining output information of the training model, wherein the output information comprises continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information;
the second obtaining unit is used for screening and filtering the continuous casting billet image information according to continuous casting billet central metallographic structure information and inclusion information corresponding to the continuous casting billet image information to obtain standard continuous casting billet image information qualified in flaw detection;
each group of training data in the multiple groups comprises identification continuous casting billet center metallographic structure label information, and the identification continuous casting billet center metallographic structure label information comprises the following components: a fifth obtaining unit, configured to obtain a crack in a central metallographic structure of the continuous casting slab; the first judging unit is used for judging whether the cracks in the central metallographic structure of the continuous casting slab meet a preset standard image or not; a sixth obtaining unit, configured to obtain label information for identifying the continuous casting billet central metallographic structure when the crack in the continuous casting billet central metallographic structure does not meet the predetermined standard image; the second input unit is used for inputting the label information for identifying the metallographic structure of the continuous casting slab center as first label data into each group of training data;
each set of training data in the plurality of sets comprises preset inclusion index information, and the method comprises the following steps:
a seventh obtaining unit, configured to obtain a component of an inclusion in the continuous casting slab and a content of the component of the inclusion;
an eighth obtaining unit, configured to obtain the preset inclusion index information according to the components of the inclusions and the content of the components of the inclusions;
the third input unit is used for inputting the preset inclusion index information serving as second label data into each group of training data;
according to continuous casting billet center metallographic structure information and inclusion information that continuous casting billet image information corresponds, right continuous casting billet image information screens and filters, obtains qualified standard continuous casting billet image information of detecting a flaw, includes:
the second judgment unit is used for judging whether the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a preset standard image or not;
a ninth obtaining unit, configured to obtain a predetermined inclusion threshold if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information meets a predetermined standard image;
the first execution unit is used for filtering the continuous casting billet image information if the continuous casting billet central metallographic structure information corresponding to the continuous casting billet image information does not accord with a preset standard image;
after the predetermined inclusion threshold is obtained, the method comprises the following steps:
the third judging unit is used for judging whether the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value;
a tenth obtaining unit, configured to obtain standard continuous casting billet image information that is qualified for flaw detection if inclusion information corresponding to the continuous casting billet image information does not reach a predetermined inclusion threshold;
and the second execution unit is used for filtering the continuous casting billet image information if the inclusion information corresponding to the continuous casting billet image information reaches a preset inclusion threshold value.
4. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1-2.
5. An apparatus for increasing the yield of continuous casting inspection comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to perform the steps of the method of any of claims 1-2.
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 CN110490862A (en) | 2019-11-22 |
| CN110490862B true 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) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102637258A (en) * | 2012-04-01 | 2012-08-15 | 首钢总公司 | Method for creating online surface quality detection system defect library |
| 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 |
| 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 |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2838827B3 (en) * | 2002-04-19 | 2004-04-02 | Central Iron & Steel Res Inst | ANALYSIS METHOD OF STATISTICAL DISTRIBUTION OF ORIGINAL POSITION FOR A METAL |
| 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 |
| 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 |
| CN103245711B (en) * | 2013-04-18 | 2016-10-05 | 沈阳理工大学 | Aluminum liquid non-metallic inclusion online soft sensor device and method based on neutral net |
| 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 |
| 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 |
| CN109856359B (en) * | 2019-01-31 | 2022-03-29 | 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 (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102637258A (en) * | 2012-04-01 | 2012-08-15 | 首钢总公司 | Method for creating online surface quality detection system defect library |
| 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 |
| 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 |
| 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 (1)
| Title |
|---|
| development and application of CISDI online slab quality diagnosis & analysis system;Shuigen wang 等，;《Advanced Materials Research》;20120614;第2012年卷;第647-652页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110490862A (en) | 2019-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110490862B (en) | Method and device for improving continuous casting flaw detection qualification rate | |
| JPS61501174A (en) | Automatic inspection of hot steel slabs | |
| US8913842B2 (en) | Image smoothing method based on content-dependent filtering | |
| JP7355943B2 (en) | Method and system for automatic identification and grading of low acid etching defects using machine vision | |
| JP6208426B2 (en) | Automatic unevenness detection apparatus and automatic unevenness detection method for flat panel display | |
| CN111476759B (en) | Screen surface detection method and device, terminal and storage medium | |
| CN110637227A (en) | Detection parameter determining method and detection device | |
| CN117252864B (en) | Steel production device smoothness detection system based on identification analysis | |
| CN104243967A (en) | Image detection method and device | |
| CN110631475B (en) | On-site target size detection method | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN117115171A (en) | Slight bright point defect detection method applied to subway LCD display screen | |
| CN109272480B (en) | Detection method for boundary of immiscible solution | |
| CN103605973A (en) | Image character detection and identification method | |
| CN106530292A (en) | Strip steel surface defect image rapid identification method based on line scanning camera | |
| CN116381053A (en) | Ultrasonic detection method and system for welding metal materials | |
| JPH04238592A (en) | Automatic bundled bar steel tally device | |
| CN114841971A (en) | Method, system and device for detecting pit defects of metal block | |
| CN114196799A (en) | Method and device for detecting converter slag overflow and computer equipment | |
| Hsu et al. | Vision-based detection of steel billet surface defects via fusion of multiple image features | |
| CN110473148B (en) | Computer quality judging system | |
| CN112967226A (en) | High-reflectivity product detection system, method and medium based on artificial intelligence | |
| CN117607164B (en) | Copper foil defect detection method and device based on time-sharing polishing and virtual stations | |
| CN117274252B (en) | Steel product surface flaw detection system based on identification analysis | |
| CN115661159B (en) | Panel defect enhancement detection method, system, device and medium |
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 |