CN110705539A - Image acquisition method and system for improving low-power center segregation rating precision of continuous casting billet - Google Patents
Image acquisition method and system for improving low-power center segregation rating precision of continuous casting billet Download PDFInfo
- Publication number
- CN110705539A CN110705539A CN201911101671.6A CN201911101671A CN110705539A CN 110705539 A CN110705539 A CN 110705539A CN 201911101671 A CN201911101671 A CN 201911101671A CN 110705539 A CN110705539 A CN 110705539A
- Authority
- CN
- China
- Prior art keywords
- continuous casting
- casting billet
- computer
- center segregation
- low
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an image acquisition method and system for improving low power center segregation rating precision of a continuous casting billet, and belongs to the technical field of automation. The implementation steps are as follows: 1. fixing the pickled continuous casting billet on a continuous casting billet clamping device, controlling a continuous casting billet angle rotating device to reach a specified angle through a computer, controlling a camera to collect a picture, and sending the collected picture to the computer; 2. repeating the process of the step 1 for 2 times, and taking 3-angle low-magnification pictures; 3. the computer carries out brightness adjustment, contrast adjustment, noise addition, blurring and sharpening on the collected 3 pictures and stores the pictures; 4. manually grading and classifying the stored photos at a low magnification level; 5. and using the classified data for training input of the continuous casting billet low-power center segregation grade automatic rating model. The method can rapidly increase the quantity of the low-magnification photos of the continuous casting billet, so that the trained model is more robust, and the identification precision of the model is improved.
Description
Technical Field
The invention belongs to the technical field of automation, and relates to an image acquisition method and system for improving low-power center segregation rating precision of a continuous casting billet.
Background
In the continuous casting production process, quality problems such as center segregation, corner cracks and the like may occur to the continuous casting billet under the influence of production conditions, and in order to ensure the product quality, the produced casting billet needs to be tracked and monitored. The detection method of the center segregation of the casting blank is to observe the macroscopic picture of the acid-etched continuous casting blank and judge the category and the grade of the center segregation. The conventional inspection and rating method for the low-magnification defects of the casting blank mainly comprises a manual rating mode and a computer image automatic rating mode.
And in the manual rating mode, the low-power sample picture of the casting blank is compared with a national standard YB/T4002-2013 & lt & gt continuous casting square billet low-power structure defect rating picture, and the category and the grade of the center segregation are given. The grading method has the inevitable defects of influence of artificial subjective factors, grading delay and the like.
The computer image automatic rating mode is the most rapidly developed continuous casting slab defect assessment method at present, an image recognition model is trained mostly by adopting a deep learning method, the center segregation of the continuous casting slab is represented as scattered points or discontinuous lines on the low power of the continuous casting slab, the size is small, and the geometric characteristics are not obvious, so that in order to achieve reasonable recognition accuracy, the sample data required for training is huge, each plant is limited by production, and the number of accumulated low power images is not enough to support the training of the model.
Therefore, the invention provides a method for solving the problem of low precision of automatic model evaluation of the low power center segregation level of the continuous casting billet caused by insufficient sample data, which can rapidly increase the number of low power photos of the continuous casting billet, so that a trained model is more robust, and the identification precision of the model is improved.
Disclosure of Invention
In view of the above, the present invention provides an image acquisition method and system for improving the low power center segregation rating accuracy of a continuous casting slab.
In order to achieve the purpose, the invention provides the following technical scheme:
the image acquisition method for improving the low-power center segregation rating precision of the continuous casting billet comprises the following steps of:
s1: fixing a pickled continuous casting billet on a continuous casting billet clamping device;
s2: the computer controls the angle rotating device of the continuous casting billet to drive the continuous casting billet to reach a specified angle;
s3: the computer controls the camera to collect the photos and sends the collected photos to the computer;
s4: repeating the processes of S2-S3 for 2 times, and taking 3-angle low-magnification photos;
s5: processing the image of the picture 1 acquired in the step S4, sequentially adjusting brightness, contrast, noise, image blurring and image sharpening, and storing the processed 5 pictures;
s6: repeating S5, and performing image processing on all the photos acquired in S4;
s7: manually grading and classifying the original photos stored in the S4 and the processed photos stored in the S6 in a low-magnification level, and obtaining 18 photos in total for each cast billet;
s8: and using the classified data for training input of the continuous casting billet low-power center segregation grade automatic rating model.
The image acquisition system for improving the low-power center segregation rating precision of the continuous casting billet comprises a continuous casting billet clamping device, a continuous casting billet angle rotating device, a camera and a computer;
the continuous casting billet clamping device is connected with the continuous casting billet angle rotating device;
the continuous casting billet angle rotating device is connected with a computer;
the continuous casting billet clamping device is used for fixing the position of a continuous casting billet, the continuous casting billet clamping device is positioned above the continuous casting billet angle rotating device and moves along with the continuous casting billet angle rotating device, and the angle of the continuous casting billet angle rotating device is controlled by a computer;
the camera is in signal connection with the computer.
Optionally, the camera is used for shooting images, and the action is controlled by a computer.
Optionally, the actions of the continuous casting angular rotation device and the camera are controlled by the same computer, and the computer coordinates the action relationship between the continuous casting angular rotation device and the camera, so that the camera is started to take a picture after the continuous casting angular rotation device reaches a specified angle and is still, and the steps are sequentially repeated for 3 times.
Optionally, the computer performs brightness, contrast, noise, blur, and sharpening on each image in sequence to obtain 5 processed images.
Optionally, the pictures processed by the computer are subjected to low power level classification and classification manually, and then are used for training an automatic rating model of the low power center segregation level of the continuous casting billet.
The invention has the beneficial effects that: the method can rapidly increase the quantity of the low-magnification photos of the continuous casting billet, so that the trained model is more robust, and the identification precision of the model is improved.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a flow chart of the implementation of the present invention;
FIG. 2 is a connection diagram of the control system of the present invention;
FIG. 3 is a schematic diagram of a system apparatus; (a) a first orientation angle state; (b) a second positioning angle state; (c) the third positioning angle state.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and examples may be combined with each other without conflict.
Wherein the showings are for the purpose of illustrating the invention only and not for the purpose of limiting the same, and in which there is shown by way of illustration only and not in the drawings in which there is no intention to limit the invention thereto; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", "front", "rear", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not an indication or suggestion that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes, and are not to be construed as limiting the present invention, and the specific meaning of the terms may be understood by those skilled in the art according to specific situations.
Referring to fig. 1-2, an image acquisition method and system for improving the accuracy of low-power center segregation rating of a continuous casting slab, comprising the following steps:
1. fixing a pickled continuous casting billet on a continuous casting billet clamping device;
2. the computer controls the angle rotating device of the continuous casting billet to drive the continuous casting billet to reach a specified angle;
3. the computer controls the camera to collect the photos and sends the collected photos to the computer;
4. repeating the processes of 2 and 3 for 2 times, and taking 3-angle low-magnification pictures;
5. processing the image 1 acquired in the step 4, sequentially adjusting brightness, contrast, noise, image blurring and image sharpening, and storing 5 processed images;
6. repeating the step 5, and carrying out image processing on all the photos collected in the step 4;
7. manually grading and classifying the original photos stored in the step 4 and the processed photos stored in the step 6 at a low-magnification level, and obtaining 18 photos in total for each cast billet;
8. and using the classified data for training input of the continuous casting billet low-power center segregation grade automatic rating model.
Taking the implementation of a billet caster as an example, the production parameters are as follows:
steel grade: HRB400
The tundish temperature is as follows: 1538 deg.C
Section: 160mm by 160mm
Blank drawing speed: 2.7m/min
The method comprises the following steps of (1) taking a low-power sample for producing a casting blank, carrying out acid pickling processing, and then carrying out image processing by adopting the method: FIG. 3 is a schematic diagram of a system apparatus; (a) a first orientation angle state; (b) a second positioning angle state; (c) the third positioning angle state.
The method is adopted to photograph and process the annual macroscopic samples of a certain factory, and the training of the central segregation image recognition model is carried out, wherein the training result is as follows:
| not using the invention | By adopting the invention | |
| Number of pictures | 483 | 2898 |
| Accuracy of model identification | 78％ | 94％ |
According to the embodiment, the method can improve the low-power center segregation recognition rate of the continuous casting billet.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.
Claims (6)
1. The image acquisition method for improving the low-power center segregation rating precision of the continuous casting billet is characterized by comprising the following steps of: the method comprises the following steps:
s1: fixing a pickled continuous casting billet on a continuous casting billet clamping device;
s2: the computer controls the angle rotating device of the continuous casting billet to drive the continuous casting billet to reach a specified angle;
s3: the computer controls the camera to collect the photos and sends the collected photos to the computer;
s4: repeating the processes of S2-S3 for 2 times, and taking 3-angle low-magnification photos;
s5: processing the image of the picture 1 acquired in the step S4, sequentially adjusting brightness, contrast, noise, image blurring and image sharpening, and storing the processed 5 pictures;
s6: repeating S5, and performing image processing on all the photos acquired in S4;
s7: manually grading and classifying the original photos stored in the S4 and the processed photos stored in the S6 in a low-magnification level, and obtaining 18 photos in total for each cast billet;
s8: and using the classified data for training input of the continuous casting billet low-power center segregation grade automatic rating model.
2. Improve image acquisition system of continuous casting billet low power center segregation rating precision, its characterized in that: the device comprises a continuous casting billet clamping device, a continuous casting billet angle rotating device, a camera and a computer;
the continuous casting billet clamping device is connected with the continuous casting billet angle rotating device;
the continuous casting billet angle rotating device is connected with a computer;
the continuous casting billet clamping device is used for fixing the position of a continuous casting billet, the continuous casting billet clamping device is positioned above the continuous casting billet angle rotating device and moves along with the continuous casting billet angle rotating device, and the angle of the continuous casting billet angle rotating device is controlled by a computer;
the camera is in signal connection with the computer.
3. The image acquisition system for improving the low power center segregation rating precision of the continuous casting slab as claimed in claim 2, wherein: the camera is used for shooting images, and the action is controlled by a computer.
4. The image acquisition system for improving the low power center segregation rating precision of the continuous casting slab as claimed in claim 2, wherein: the action of the angle rotating device of the continuous casting billet and the action of the camera are controlled by the same computer, and the computer coordinates the action relationship of the angle rotating device and the camera, so that the camera is started to shoot a picture after the angle reaches the specified angle and the angle reaches the rest, and the operation is circulated for 3 times in sequence.
5. The image acquisition system for improving the low power center segregation rating precision of the continuous casting slab as claimed in claim 2, wherein: and the computer carries out brightness, contrast, noise, blurring and sharpening processing on each picture in sequence to obtain 5 processed pictures.
6. The image acquisition system for improving the low power center segregation rating precision of the continuous casting slab as claimed in claim 2, wherein: and the pictures processed by the computer are manually classified in a low power level mode and then used for training an automatic grading model of the low power center segregation level of the continuous casting billet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911101671.6A CN110705539A (en) | 2019-11-12 | 2019-11-12 | Image acquisition method and system for improving low-power center segregation rating precision of continuous casting billet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911101671.6A CN110705539A (en) | 2019-11-12 | 2019-11-12 | Image acquisition method and system for improving low-power center segregation rating precision of continuous casting billet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110705539A true CN110705539A (en) | 2020-01-17 |
Family
ID=69205054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911101671.6A Pending CN110705539A (en) | 2019-11-12 | 2019-11-12 | Image acquisition method and system for improving low-power center segregation rating precision of continuous casting billet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705539A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111899230A (en) * | 2020-07-15 | 2020-11-06 | 重庆大学 | Quality quantification and automatic multi-stage judgment method based on three-dimensional characteristics of steel casting billet macrostructure |
| CN114113106A (en) * | 2021-11-12 | 2022-03-01 | 中冶赛迪技术研究中心有限公司 | Method and system for automatically grading low-power structure quality of continuous casting billet |
-
2019
- 2019-11-12 CN CN201911101671.6A patent/CN110705539A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111899230A (en) * | 2020-07-15 | 2020-11-06 | 重庆大学 | Quality quantification and automatic multi-stage judgment method based on three-dimensional characteristics of steel casting billet macrostructure |
| CN111899230B (en) * | 2020-07-15 | 2023-11-17 | 重庆大学 | Quality quantification and automatic multi-stage judgment method based on three-dimensional characteristics of steel casting blank macrostructure |
| CN114113106A (en) * | 2021-11-12 | 2022-03-01 | 中冶赛迪技术研究中心有限公司 | Method and system for automatically grading low-power structure quality of continuous casting billet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Surface defects detection based on adaptive multiscale image collection and convolutional neural networks | |
| CN108827181B (en) | Vision-based plate surface detection method | |
| CN109632808B (en) | Edge defect detection method and device, electronic equipment and storage medium | |
| CN110705539A (en) | Image acquisition method and system for improving low-power center segregation rating precision of continuous casting billet | |
| CN110544231B (en) | Lithium battery electrode surface defect detection method based on background standardization and centralized compensation algorithm | |
| JP7355943B2 (en) | Method and system for automatic identification and grading of low acid etching defects using machine vision | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN108802051B (en) | System and method for detecting bubble and crease defects of linear circuit of flexible IC substrate | |
| CN113066088A (en) | Detection method, detection device and storage medium in industrial detection | |
| CN112529893A (en) | Hub surface flaw online detection method and system based on deep neural network | |
| CN115423755A (en) | Wafer micromachining structure defect detection method and device, equipment and medium thereof | |
| CN108416790B (en) | Method for detecting breakage rate of workpiece | |
| CN210721503U (en) | Image acquisition system for improving low-power center segregation rating precision of continuous casting billet | |
| CN115984360B (en) | Method and system for calculating length of dry beach based on image processing | |
| CN117475205A (en) | Defect type identification method, defect type identification device, control device and storage medium | |
| CN112763496A (en) | Mobile phone battery surface defect detection device and detection method thereof | |
| CN115963397B (en) | Rapid online detection method and device for surface defects of inner contour of motor stator | |
| CN116754567A (en) | Periodic defect detection method, device and equipment for copper foil material | |
| CN105354848A (en) | Optimization method of Cognex surface quality detection system of hot galvanizing production line | |
| CN113888504A (en) | mesh component detection method, device and storage medium | |
| CN115861220A (en) | Cold-rolled strip steel surface defect detection method and system based on improved SSD algorithm | |
| CN115330705A (en) | Skin paint surface defect detection method based on adaptive weighting template NCC | |
| CN114742770A (en) | Electrolytic copper plate copper nodule defect detection method, training method and system | |
| CN114219802A (en) | Skin connecting hole position detection method based on image processing | |
| CN106355562A (en) | Denoising method for steel rail detection images, based on machine vision |
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 |