CN115393308A - Method and device for detecting scratch defects on surface of strip steel, medium and electronic equipment - Google Patents
Method and device for detecting scratch defects on surface of strip steel, medium and electronic equipment Download PDFInfo
- Publication number
- CN115393308A CN115393308A CN202211002895.3A CN202211002895A CN115393308A CN 115393308 A CN115393308 A CN 115393308A CN 202211002895 A CN202211002895 A CN 202211002895A CN 115393308 A CN115393308 A CN 115393308A
- Authority
- CN
- China
- Prior art keywords
- strip steel
- scratch
- defect
- detected
- steel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06T2207/30136—Metal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to the technical field of surface detection of hot-rolled strip steel, and discloses a method, a device, a medium and electronic equipment for detecting surface scratch defects of strip steel. The method comprises the following steps: constructing an initial classifier for detecting scratch defects on the surface of the strip steel; acquiring a strip steel surface image sample set with scratch defects, and training the initial classifier based on the strip steel surface image sample set to obtain a target classifier; acquiring a steel coil to be detected, and acquiring a strip steel surface image of the steel coil to be detected; and detecting the surface image of the strip steel through the target classifier so as to identify the scratch defect of the strip steel surface in the steel coil to be detected. The technical scheme that this application provided can automatic identification the fish tail defect that exists on belted steel surface, avoids appearing the problem of careless omission because of artificial looking over.
Description
Technical Field
The application relates to the technical field of surface detection of hot-rolled strip steel, and discloses a method, a device, a medium and electronic equipment for detecting surface scratch defects of strip steel.
Background
The scratch on the surface of the hot-rolled strip steel is a common hot-rolling quality defect and mainly appears as a dark linear defect, and basically occurs on the lower surface of the strip steel according to the production characteristics of a hot-rolling process. Once scratch defects occur on commercial materials and acid-pickled plate products, if the scratch defects are not discovered and processed in time, the problem of batch quality is caused. Generally, after the scratch defect occurs, the scratch defect needs to be cut off or degraded, so that the product cashing and production cost is seriously influenced, and the economic loss is huge. If scratch omission flows into downstream processes or clients, quality objections can be caused, client trust can be lost, and client resources are lost, so that identification and control of scratch defects are emphasized by various hot rolling mills.
At present, a plurality of hot rolling plants apply a surface quality detection system, the classification rate of defects can be improved by scientifically optimizing the system, field quality personnel can obtain the surface quality information of steel coils by checking the defect pictures, coils with scratch defects can be closed, and the manual checking does not avoid omission, so that the technical problem to be solved urgently at present is how to enable the system to automatically identify the scratch defects on the surfaces of strip steels.
Disclosure of Invention
The embodiment of the application provides a method, a device, a medium and electronic equipment for detecting scratch defects on the surface of strip steel. The scratch defect on the surface of the strip steel can be automatically identified, and the problem of omission caused by manual checking is avoided.
Other features and advantages of the present application will be apparent from the following detailed description, or may be learned by practice of the application.
According to a first aspect of the embodiments of the present application, there is provided a method for detecting a scratch defect on a surface of a strip steel, the method including: constructing an initial classifier for detecting scratch defects on the surface of the strip steel; acquiring a strip steel surface image sample set with scratch defects, and training the initial classifier based on the strip steel surface image sample set to obtain a target classifier; acquiring a steel coil to be detected, and acquiring a strip steel surface image of the steel coil to be detected; and detecting the surface image of the strip steel through the target classifier so as to identify the scratch defect of the strip steel surface in the steel coil to be detected.
In an embodiment of the application, based on the foregoing scheme, the training the initial classifier based on the strip steel surface image sample set to obtain a target classifier includes: selecting a strip steel surface image sample subset from the strip steel surface image sample set, and training the initial classifier based on the strip steel surface image sample subset to obtain an intermediate classifier; acquiring a test steel coil, and identifying the scratch defect of the steel surface in the test steel coil through the intermediate classifier; determining the accuracy of the intermediate classifier for identifying the scratch defects on the surface of the strip steel in the test steel coil; and if the accuracy is lower than an accuracy threshold, selecting a new strip steel surface image sample subset from the strip steel surface image sample set, and returning to the step of training the initial classifier based on the strip steel surface image sample subset until the accuracy is higher than or equal to the accuracy threshold, and taking the intermediate classifier as the target classifier.
In an embodiment of the application, based on the foregoing solution, after the target classifier detects the image of the strip steel surface to identify the scratch defect on the strip steel surface in the steel coil to be detected, the method further includes: constructing a scratch defect expert detection module; and qualitatively detecting the scratch defects on the surface of the strip steel in the steel coil to be detected through the scratch defect expert detection module so as to identify the actual scratch defects on the surface of the strip steel in the steel coil to be detected.
In an embodiment of this application, based on the foregoing scheme, through scratch defect expert detection module is right detect the scratch defect on strip steel surface in the coil of strip that awaits measuring qualitatively, include: and determining the scratch defect of the non-lower surface in the steel coil to be detected as a non-scratch defect.
In an embodiment of this application, based on the foregoing scheme, through scratch defect expert detection module is right detect the scratch defect on strip steel surface in the coil of strip that awaits measuring qualitatively, include: and determining a plurality of scratch defects in the preset surface area of the steel coil to be detected as a scratch defect.
In an embodiment of the application, based on the foregoing solution, after identifying the actual scratch defect on the surface of the steel strip in the steel coil to be detected, the method further includes: counting the number of actual scratch defects on the strip steel surface in the steel coil to be detected; and if the actual number of the scratch defects exceeds the number threshold, triggering a surface defect early warning prompt aiming at the steel coil to be detected.
In an embodiment of the application, based on the foregoing solution, after identifying the actual scratch defect on the surface of the steel strip in the steel coil to be detected, the method further includes: counting the total length of the actual scratch defects on the strip steel surface in the steel coil to be detected; and if the total length of the actual scratch defects exceeds a length threshold, triggering a surface defect early warning prompt aiming at the steel coil to be detected.
According to a second aspect of the embodiments of the present application, there is provided an apparatus for detecting scratch defects on a surface of a strip steel, the apparatus comprising: the construction unit is used for constructing an initial classifier for detecting scratch defects on the surface of the strip steel; the acquisition unit is used for acquiring a strip steel surface image sample set with scratch defects, and training the initial classifier based on the strip steel surface image sample set to obtain a target classifier; the device comprises a collecting unit, a judging unit and a judging unit, wherein the collecting unit is used for acquiring a steel coil to be detected and collecting a strip steel surface image of the steel coil to be detected; and the identification unit is used for detecting the image on the surface of the strip steel through the target classifier so as to identify the scratch defect of the surface of the strip steel in the steel coil to be detected.
According to a third aspect of the embodiments of the present application, there is provided a computer-readable storage medium having at least one program code stored therein, where the at least one program code is loaded and executed by a processor to implement the method for detecting a scratch defect on a strip steel surface according to any of the embodiments.
According to a fourth aspect of the embodiments of the present application, there is provided an electronic device, which includes one or more processors and one or more memories, where at least one program code is stored in the one or more memories, and the at least one program code is loaded by and executed by the one or more processors to implement the method for detecting scratch defects on a surface of a strip steel according to any one of the embodiments.
In the technical scheme that this application provided, be used for detecting the initial classifier of belted steel surface fish tail defect through the construction, acquire the belted steel surface image sample set that has the fish tail defect, and based on belted steel surface image sample set training initial classifier obtains the target classifier, acquires and waits to detect the coil of strip, and gathers the belted steel surface image of waiting to detect the coil of strip, through target classifier is right belted steel surface image detects, with discernment the fish tail defect on belted steel surface in waiting to detect the coil of strip. The user can let the sorter automatic identification belted steel surface's fish tail defect, avoids appearing the problem of careless omission because of artificial looking over.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
FIG. 1 is a flow chart of a method for detecting scratch defects on a strip steel surface in the embodiment of the application;
FIG. 2 is a detailed flowchart illustrating training of the initial classifier based on the strip steel surface image sample set to obtain a target classifier in the embodiment of the present application;
FIG. 3 is a block diagram of a device for detecting scratch defects on the surface of a strip steel in the embodiment of the application;
FIG. 4 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the application.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
It should be noted that: reference herein to "a plurality" means two or more. "and/or" describe the association relationship of the associated objects, meaning that there may be three relationships, e.g., A and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
It is noted that the terms first, second and the like in the description and claims of the present application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the objects so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in other sequences than those illustrated or described herein.
The implementation details of the technical solution of the embodiment of the present application are set forth in detail below:
FIG. 1 shows a flowchart of a method for detecting scratch defects on a strip steel surface in an embodiment of the present application.
As shown in fig. 1, the method for detecting scratch defects on the surface of a strip steel at least includes steps 110 to 170.
The following will describe steps 110 to 170 shown in fig. 1 in detail:
in step 110, an initial classifier for detecting scratch defects on the surface of the strip steel is constructed.
In the application, the initial classifier has a learning function, and can be trained and learned through some samples or reference data.
With continued reference to fig. 1, in step 130, a sample set of images of the strip surface with scratch defects is obtained, and training the initial classifier based on the strip steel surface image sample set to obtain a target classifier.
In the application, the strip steel surface image sample set with scratch defects comprises a large number of typical scratch defect images, based on the strip steel surface image sample set, an initial classifier can be trained and learned, and a target classifier is obtained after training.
With continued reference to fig. 1, in step 150, a steel coil to be detected is obtained, and a strip steel surface image of the steel coil to be detected is acquired.
With continued reference to fig. 1, in step 170, the target classifier is used to detect the image of the strip steel surface so as to identify the scratch defect on the strip steel surface in the steel coil to be detected.
In this application, through the target classifier who obtains after the training detects the belted steel surface image of treating the detection coil of strip, discerns treat the fish tail defect on belted steel surface in the coil of strip, and show the fish tail defect takes place the law at belted steel length direction and width direction's fish tail defect for quick locking fish tail defect takes place the position, based on the fish tail defect takes place the position locking and solves the fish tail defect and takes place the reason.
In one embodiment of step 130 shown in fig. 1, training the initial classifier based on the strip surface image sample set to obtain a target classifier may be performed according to the steps shown in fig. 2.
Referring to fig. 2, a detailed flowchart of training the initial classifier based on the strip steel surface image sample set to obtain a target classifier in the embodiment of the present application is shown. Specifically, the method comprises steps 210 to 270:
in step 210, a strip steel surface image sample subset is selected from the strip steel surface image sample set, and the initial classifier is trained based on the strip steel surface image sample subset, resulting in an intermediate classifier.
In the method, a strip steel surface image sample subset is selected from a strip steel surface image sample set, the number of images of the strip steel surface image sample subset is not limited, 80 to 100 strip steel surface images with scratch defects can be selected as the strip steel surface image sample subset, and an initial classifier is trained and learned based on the strip steel surface image sample subset to obtain an intermediate classifier.
With continued reference to fig. 2, in step 230, a test steel coil is obtained, and the scratch defect on the surface of the strip steel in the test steel coil is identified through the intermediate classifier.
In the application, the number of the test steel coil can be 20 coils or 30 coils, the limitation is not made, and the scratch defect on the surface of the strip steel in the test steel coil is identified through the intermediate classifier.
With continued reference to fig. 2, in step 250, the accuracy with which the intermediate classifier identifies scratch defects on the strip steel surface in the test steel coil is determined.
In this application, confirm intermediate classifier identifies the rate of accuracy of belted steel surface fish tail defect in the test coil of strip, the value of rate of accuracy is intermediate classifier recognizes the number of belted steel surface fish tail defect in the test coil of strip with the ratio of the actual number of belted steel surface fish tail defect in the test coil of strip. For example, if the number of scratch defects on the surface of the strip steel in the test steel coil is 80 and the actual number of scratch defects on the surface of the strip steel in the test steel coil is 100, the accuracy is 80%; or, the intermediate classifier identifies that the number of the scratch defects on the surface of the strip steel in the test steel coil is 80, the actual number of the scratch defects on the surface of the strip steel in the test steel coil is 60, and the accuracy is 75%.
With continued reference to fig. 2, in step 270, if the accuracy is lower than the accuracy threshold, a new subset of strip steel surface image samples is selected from the strip steel surface image sample set, and the step of training the initial classifier based on the subset of strip steel surface image samples is performed again until the accuracy is higher than or equal to the accuracy threshold, and the intermediate classifier is used as the target classifier.
In the application, the accuracy threshold can be limited as required, and the larger the accuracy threshold is, the better the classification effect of the trained target classifier is.
In the application, the accuracy of the scratch defect on the surface of the strip steel in the test steel coil is identified by the intermediate classifier is lower than the accuracy threshold, then a new strip steel surface image sample subset is selected from the strip steel surface image sample set, a certain number of strip steel surface images can be added on the basis of the original strip steel surface image sample subset, or a proper number of strip steel surface images are selected again from the strip steel surface image sample set to form a new strip steel surface image sample subset except the original strip steel surface image sample subset, and the step of training the initial classifier based on the strip steel surface image sample subset is returned to be executed until the accuracy is higher than or equal to the accuracy threshold, and the intermediate classifier is used as the target classifier.
In an embodiment of the present application, after the image of the strip steel surface is detected by the target classifier to identify the scratch defect on the strip steel surface in the steel coil to be detected, the method further includes: constructing a scratch defect expert detection module; and qualitatively detecting the scratch defects on the surface of the strip steel in the steel coil to be detected through the scratch defect expert detection module so as to identify the actual scratch defects on the surface of the strip steel in the steel coil to be detected.
In this application, constitute fish tail defect expert detection module, fish tail defect expert detection module includes fish tail defect expert rule, fish tail defect expert detection module application fish tail defect expert rule is right it carries out qualitative detection to wait to detect the fish tail defect on belted steel surface in the coil of strip, with discerning wait to detect the actual fish tail defect on belted steel surface in the coil of strip.
In an embodiment of the present application, the qualitative detection of the scratch defect on the strip steel surface in the steel coil to be detected by the scratch defect expert detection module includes: and determining the scratch defect of the non-lower surface in the steel coil to be detected as a non-scratch defect.
In this application, fish tail defect expert detection module application fish tail defect expert rule is right wait to detect the fish tail defect on strip steel surface in the coil of strip and carry out qualitative detection, will wait to detect the fish tail defect of non-lower surface in the coil of strip and be qualitative for non-fish tail defect, because only the strip steel lower surface just can appear the fish tail defect by the fish tail in the strip steel production process, appear the defect of similar fish tail defect at strip steel upper surface or side, then be because the non-fish tail defect that other reasons caused. For example, a defect like a scratch defect appears at the edge portion of the upper surface, which is actually a fine line defect at the edge portion due to an excessive rolling reduction at the time of rolling.
In an embodiment of the present application, the qualitative detection of the scratch defect on the strip steel surface in the steel coil to be detected by the scratch defect expert detection module includes: and determining a plurality of scratch defects in the preset surface area of the steel coil to be detected as a scratch defect.
In this application, fish tail defect expert detection module application fish tail defect expert rule is right it carries out qualitative detection to wait to detect the fish tail defect on belted steel surface in the coil of strip, will wait to detect a plurality of fish tail defects in the coil of strip in the predetermined surface area qualitatively for a fish tail defect, the length of the fish tail defect after the combination is for the length of a plurality of fish tail defects before the combination with. For example, the predetermined surface area is 180cm 2 In an area of 180cm 2 And if 3 scratch defects appear on the surface of the strip steel, and the lengths of the scratch defects are respectively 5cm, 10cm and 15cm, combining the 3 scratch defects into one scratch defect, wherein the length of the combined scratch defect is 30cm.
In an embodiment of the present application, after identifying the actual scratch defect on the surface of the steel strip in the steel coil to be detected, the method further includes: counting the number of actual scratch defects on the strip steel surface in the steel coil to be detected; and if the actual number of the scratch defects exceeds the number threshold, triggering a surface defect early warning prompt aiming at the steel coil to be detected.
In this application, treat the fish tail defect that detects the strip steel surface in the coil of strip through fish tail defect expert detection module and carry out qualitative detection, discern the actual fish tail defect on strip steel surface in treating the coil of strip, make statistics of treat the actual fish tail defect number on strip steel surface in the coil of strip, make statistics of when actually fish tail defect number, not including the number statistics of the fish tail defect in belted steel head and the afterbody 3m, and judge whether actual fish tail defect number exceeds the number threshold value, the number threshold value is set for according to the demand, can be 5, also can be 10, if actually fish tail defect number exceeds the number threshold value, then trigger to treat the surface defect early warning suggestion of coil of strip, the surface defect early warning suggestion is used for reminding operating personnel that there is the fish tail defect to take place, the surface defect early warning suggestion can be the sound prompt, also can show different colours and remind.
In an embodiment of the present application, after identifying the actual scratch defect on the surface of the steel strip in the steel coil to be detected, the method further includes: counting the total length of the actual scratch defects on the strip steel surface in the steel coil to be detected; and if the total length of the actual scratch defects exceeds a length threshold, triggering a surface defect early warning prompt aiming at the steel coil to be detected.
In this application, treat the fish tail defect that detects belted steel surface in the coil of strip through fish tail defect expert detection module and carry out qualitative detection, discern and wait to detect the actual fish tail defect on belted steel surface in the coil of strip, make up the actual fish tail defect total length that detects belted steel surface in the coil of strip, make up when actual fish tail defect total length, do not including the length statistics of the fish tail defect in belted steel head and the afterbody 3m, and judge whether actual fish tail defect total length exceeds the length threshold value, the length threshold value sets for according to the demand, can be 5 meters, also can be 10 meters, if actual fish tail defect total length exceeds the length threshold value, then triggers to wait to detect the surface defect early warning suggestion of coil of strip, the surface defect early warning suggestion is used for reminding operating personnel has the fish tail defect to take place, the surface defect early warning suggestion can be the sound prompt, also can show different colours and remind.
The following describes embodiments of the apparatus of the present application, which may be used to perform the method for detecting scratch defects on the surface of a strip steel according to the first aspect of the above embodiments of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the method for detecting scratch defects on the surface of a strip steel of the first aspect of the present application.
FIG. 3 shows a block diagram of a device for detecting scratch defects on the surface of a strip steel in the embodiment of the application.
As shown in fig. 3, the device 300 for detecting scratch defects on the surface of a strip steel in the embodiment of the present application includes: the device comprises a construction unit 301, an acquisition unit 302, a collection unit 303 and an identification unit 304.
The construction unit 301 is used for constructing an initial classifier for detecting scratch defects on the surface of the strip steel; the obtaining unit 302 is configured to obtain a strip steel surface image sample set with a scratch defect, and train the initial classifier based on the strip steel surface image sample set to obtain a target classifier; the acquisition unit 303 is used for acquiring a steel coil to be detected and acquiring a strip steel surface image of the steel coil to be detected; and the identification unit 304 is used for detecting the image of the surface of the strip steel through the target classifier so as to identify the scratch defect of the surface of the strip steel in the steel coil to be detected.
In some embodiments of the present application, based on the foregoing solution, the obtaining unit 302 is configured to: selecting a strip steel surface image sample subset from the strip steel surface image sample set, and training the initial classifier based on the strip steel surface image sample subset to obtain an intermediate classifier; acquiring a test steel coil, and identifying the scratch defect of the strip steel surface in the test steel coil through the intermediate classifier; determining the accuracy of the intermediate classifier for identifying the scratch defects on the surface of the strip steel in the test steel coil; and if the accuracy is lower than an accuracy threshold, selecting a new strip steel surface image sample subset from the strip steel surface image sample set, and returning to the step of training the initial classifier based on the strip steel surface image sample subset until the accuracy is higher than or equal to the accuracy threshold, and taking the intermediate classifier as the target classifier.
In some embodiments of the present application, based on the foregoing solution, the apparatus further comprises a discriminating unit configured to construct a scratch defect expert detection module; and qualitatively detecting the scratch defects on the surface of the strip steel in the steel coil to be detected through the scratch defect expert detection module so as to identify the actual scratch defects on the surface of the strip steel in the steel coil to be detected.
In some embodiments of the present application, based on the foregoing scheme, the discriminating unit is configured to: and determining the scratch defect of the non-lower surface in the steel coil to be detected as a non-scratch defect.
In some embodiments of the present application, based on the foregoing solution, the identifying unit is further configured to: and determining a plurality of scratch defects in the preset surface area of the steel coil to be detected as a scratch defect.
In some embodiments of the application, based on the foregoing scheme, the device further includes a first triggering unit, configured to count the number of actual scratch defects on the steel surface in the steel coil to be detected; and if the actual number of the scratch defects exceeds the number threshold, triggering a surface defect early warning prompt aiming at the steel coil to be detected.
In some embodiments of the present application, based on the foregoing solution, the apparatus further includes a second triggering unit, configured to count a total actual length of the scratch defect on the steel surface in the steel coil to be detected; and if the total length of the actual scratch defects exceeds a length threshold, triggering a surface defect early warning prompt aiming at the steel coil to be detected.
The present application provides a computer program product comprising computer instructions stored in a computer readable storage medium and adapted to be read and executed by a processor to cause a computer apparatus having the processor to perform the method for detecting scratch defects on a strip steel surface as described in the above embodiments.
The present application also provides a computer readable medium, which may be embodied in an electronic device; or may be present alone without being incorporated into the electronic device. The computer readable storage medium has at least one program code stored therein, and the at least one program code is loaded and executed by a processor to implement the method for detecting scratch defects on a strip steel surface described in the above embodiments.
In order that those skilled in the art will more readily understand the present application, it is described below in terms of a specific embodiment.
The method specifically comprises the following steps:
1500 coils of steel are selected for testing on a first steel moving production line, wherein the 1500 coils of steel comprise 500 coils of cold rolling materials, 500 coils of pickled plates and 500 coils of takeout coils.
Step 1, constructing an initial classifier for detecting scratch defects on the surface of strip steel;
step 2, acquiring a strip steel surface image sample set with scratch defects, selecting a strip steel surface image sample subset from the strip steel surface image sample set, wherein the number of images of the strip steel surface image sample subset is 100, training an initial classifier based on the strip steel surface image sample subset to obtain an intermediate classifier, testing the intermediate classifier by using 20 test steel coils, the identification accuracy is lower than 90%, increasing the number of images of the strip steel surface image sample subset until the identification accuracy of the intermediate classifier is higher than or equal to 90%, the number of images of the strip steel surface image sample subset is 125, the identification accuracy of the intermediate classifier is 92%, and taking the intermediate classifier with the identification accuracy of 92% as a target classifier;
step 3, constructing a scratch defect expert detection module, wherein the scratch defect expert detection module comprises a scratch defect expert rule, and the scratch defect expert detection module carries out qualitative detection on the scratch defect of the strip steel surface in the steel coil to be detected by using the scratch defect expert rule so as to identify the actual scratch defect of the strip steel surface in the steel coil to be detected;
step 4, counting the number of actual scratch defects on the surface of the strip steel in the steel coil to be detected, when counting the number of the actual scratch defects, not counting the number of the scratch defects in 3m of the head and the tail of the strip steel, judging whether the number of the actual scratch defects exceeds 10, if the number of the actual scratch defects exceeds 10, triggering a surface defect early warning prompt aiming at the steel coil to be detected, displaying green on an operation page, and reminding field workers to stop the machine for inspection;
step 5, counting the total actual length of the scratch defects on the surface of the strip steel in the steel coil to be detected, when the total actual length of the scratch defects is counted, not counting the lengths of the scratch defects within 3m of the head and the tail of the strip steel, judging whether the total actual length of the scratch defects exceeds 10 m, if the total actual length of the scratch defects exceeds 10 m, triggering a surface defect early warning prompt aiming at the steel coil to be detected, displaying green on an operation page, and reminding field workers to perform shutdown inspection;
and 6, displaying the distribution rules of the scratch defects on the surface of the strip steel in the length direction and the width direction so as to quickly lock the scratch defect occurrence positions, and locking and solving the scratch defect occurrence reasons based on the scratch defect occurrence positions.
The test results obtained by the method are shown in table 1, and the alarm accuracy can reach 91.93% through verification and confirmation.
| Steel grade | Number of test rolls | Number of coils with scratch defect | Number of alarm coils for scratch defect | Rate of accuracy of alarm |
| Cold rolling material | 500 | 287 | 263 | 91.64％ |
| Pickling plate | 500 | 306 | 285 | 93.14％ |
| Takeout roll | 500 | 188 | 170 | 90.43％ |
| Total up to | 1500 | 781 | 718 | 91.93％ |
TABLE 1
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
through optimizing and improving the classification accuracy of the scratch defects of the classifier, the scratch defects on the surface of the strip steel in the steel coil to be detected can be more accurately identified.
And triggering a surface defect early warning prompt aiming at the steel coil to be detected when the scratch defect of the surface of the strip steel in the steel coil to be detected reaches a set condition, and prompting a worker to carry out detection and maintenance.
Through showing the distribution rule of the scratch defects fast, finding out the fault equipment causing the scratch defects fast, solving the problem causing the scratch defects fast and avoiding causing further loss.
FIG. 4 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.
It should be noted that the computer system 400 of the electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiments.
As shown in fig. 4, the computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for system operation are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An Input/Output (I/O) interface 405 is also connected to the bus 404.
The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a Display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as needed, so that a computer program read out therefrom is mounted in the storage section 408 as needed.
In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411. The computer program executes various functions defined in the system of the present application when executed by a Central Processing Unit (CPU) 401.
It should be noted that the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, and may also be implemented by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains.
Furthermore, the above-described figures are merely schematic illustrations of processes involved in methods according to exemplary embodiments of the present application, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
It will be understood that the present application is not limited to the precise arrangements that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. The method for detecting the scratch defects on the surface of the strip steel is characterized by comprising the following steps:
constructing an initial classifier for detecting scratch defects on the surface of the strip steel;
acquiring a strip steel surface image sample set with scratch defects, and training the initial classifier based on the strip steel surface image sample set to obtain a target classifier;
acquiring a steel coil to be detected, and acquiring a strip steel surface image of the steel coil to be detected;
and detecting the surface image of the strip steel through the target classifier so as to identify the scratch defect of the strip steel surface in the steel coil to be detected.
2. The method of claim 1, wherein training the initial classifier based on the strip steel surface image sample set to obtain a target classifier comprises:
selecting a strip steel surface image sample subset from the strip steel surface image sample set, and training the initial classifier based on the strip steel surface image sample subset to obtain an intermediate classifier;
acquiring a test steel coil, and identifying the scratch defect of the steel surface in the test steel coil through the intermediate classifier;
determining the accuracy of the intermediate classifier for identifying the scratch defects on the surface of the strip steel in the test steel coil;
and if the accuracy is lower than an accuracy threshold, selecting a new strip steel surface image sample subset from the strip steel surface image sample set, and returning to the step of training the initial classifier based on the strip steel surface image sample subset until the accuracy is higher than or equal to the accuracy threshold, and taking the intermediate classifier as the target classifier.
3. The method according to claim 1, wherein after the image of the strip surface is detected by the object classifier to identify the scratch defect of the strip surface in the coil to be detected, the method further comprises:
constructing a scratch defect expert detection module;
and qualitatively detecting the scratch defects on the surface of the strip steel in the steel coil to be detected through the scratch defect expert detection module so as to identify the actual scratch defects on the surface of the strip steel in the steel coil to be detected.
4. The method according to claim 3, wherein the qualitative detection of the scratch defect on the strip steel surface in the steel coil to be detected by the scratch defect expert detection module comprises:
and determining the scratch defect of the non-lower surface in the steel coil to be detected as a non-scratch defect.
5. The method according to claim 3, wherein the qualitative detection of the scratch defect on the strip steel surface in the steel coil to be detected by the scratch defect expert detection module comprises:
and determining a plurality of scratch defects in the preset surface area of the steel coil to be detected as a scratch defect.
6. The method according to claim 3, characterized in that after identifying the actual scratch defect of the strip surface in the coils to be detected, the method further comprises:
counting the number of actual scratch defects on the strip steel surface in the steel coil to be detected;
and if the actual number of the scratch defects exceeds the number threshold, triggering a surface defect early warning prompt aiming at the steel coil to be detected.
7. The method according to claim 3, characterized in that after identifying the actual scratch defect of the strip surface in the coils to be detected, the method further comprises:
counting the total length of the actual scratch defects on the strip steel surface in the steel coil to be detected;
and if the total length of the actual scratch defects exceeds a length threshold, triggering a surface defect early warning prompt aiming at the steel coil to be detected.
8. The utility model provides a detection apparatus for belted steel surface fish tail defect, its characterized in that, the device includes:
the construction unit is used for constructing an initial classifier for detecting the scratch defects on the surface of the strip steel;
the acquisition unit is used for acquiring a strip steel surface image sample set with scratch defects, and training the initial classifier based on the strip steel surface image sample set to obtain a target classifier;
the acquisition unit is used for acquiring a steel coil to be detected and acquiring a strip steel surface image of the steel coil to be detected;
and the identification unit is used for detecting the image on the surface of the strip steel through the target classifier so as to identify the scratch defect of the surface of the strip steel in the steel coil to be detected.
9. A computer-readable storage medium having at least one program code stored therein, the at least one program code being loaded and executed by a processor to implement the method of detecting scratch defects on a strip steel surface according to any one of claims 1 to 7.
10. An electronic device, comprising one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded by the one or more processors and executed to implement the method for detecting scratch defects on a strip steel surface according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211002895.3A CN115393308A (en) | 2022-08-19 | 2022-08-19 | Method and device for detecting scratch defects on surface of strip steel, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211002895.3A CN115393308A (en) | 2022-08-19 | 2022-08-19 | Method and device for detecting scratch defects on surface of strip steel, medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115393308A true CN115393308A (en) | 2022-11-25 |
Family
ID=84120379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211002895.3A Pending CN115393308A (en) | 2022-08-19 | 2022-08-19 | Method and device for detecting scratch defects on surface of strip steel, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115393308A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI814677B (en) * | 2023-02-10 | 2023-09-01 | 中國鋼鐵股份有限公司 | Defect detection method and defect detection system using the same |
-
2022
- 2022-08-19 CN CN202211002895.3A patent/CN115393308A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI814677B (en) * | 2023-02-10 | 2023-09-01 | 中國鋼鐵股份有限公司 | Defect detection method and defect detection system using the same |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105975980A (en) | Method of monitoring image mark quality and apparatus thereof | |
| CN111126759B (en) | Electric energy meter state evaluation method based on abnormal event fault correlation degree | |
| CN108304816B (en) | Identity recognition method and device, storage medium and electronic equipment | |
| CN107679046A (en) | A kind of detection method and device of fraudulent user | |
| CN115293463B (en) | Glass lens processing supervision method and system based on cutting quality prediction | |
| CN115393308A (en) | Method and device for detecting scratch defects on surface of strip steel, medium and electronic equipment | |
| CN104903262A (en) | System for managing production of glass substrates and method for managing production of glass substrates | |
| CN107610119A (en) | The accurate detection method of steel strip surface defect decomposed based on histogram | |
| CN115100188A (en) | Steel plate surface quality automatic grading and judging method for hierarchical defect analysis | |
| CN110992323A (en) | Steel strip detection method and device based on image processing and steel clamping detection method | |
| CN114020598A (en) | Method, device and equipment for detecting abnormity of time series data | |
| CN109102486B (en) | Surface defect detection method and device based on machine learning | |
| CN110394432B (en) | Method and device for inspecting continuous casting protection pouring | |
| CN117372377A (en) | Broken line detection method and device for monocrystalline silicon ridge line and electronic equipment | |
| CN110610344A (en) | Method, device and equipment for improving auditing speed of automatic auditing system | |
| CN113361729B (en) | Risk assessment method, device, terminal and storage medium based on maintenance plan | |
| CN112732773B (en) | Method and system for checking uniqueness of relay protection defect data | |
| CN113435464B (en) | Abnormal data detection method and device, electronic equipment and computer storage medium | |
| CN114429556A (en) | Picture auditing method and device | |
| CN114137635A (en) | Method, device and equipment for testing detection efficiency of security check machine and storage medium | |
| CN113792090A (en) | Steel rolling data monitoring method, system, medium and electronic terminal | |
| CN112685610A (en) | False registration account identification method and related device | |
| DE102020205120A1 (en) | Method for operating a metal strip processing system and a metal strip processing system | |
| CN114199879B (en) | Identification method for aggregated defects on surface of cold-rolled strip steel | |
| CN104376212B (en) | The method and device of assessment operation accuracy |
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 |