CN112828275B - Automatic slag skimming method, device and system - Google Patents
Automatic slag skimming method, device and system Download PDFInfo
- Publication number
- CN112828275B CN112828275B CN202011625432.3A CN202011625432A CN112828275B CN 112828275 B CN112828275 B CN 112828275B CN 202011625432 A CN202011625432 A CN 202011625432A CN 112828275 B CN112828275 B CN 112828275B
- Authority
- CN
- China
- Prior art keywords
- slag
- image
- iron ladle
- data
- plate
- 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
- 239000002893 slag Substances 0.000 title claims abstract description 280
- 238000000034 method Methods 0.000 title claims abstract description 85
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims abstract description 336
- 229910052742 iron Inorganic materials 0.000 claims abstract description 168
- 239000002699 waste material Substances 0.000 claims abstract description 93
- 230000008569 process Effects 0.000 claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 claims abstract description 15
- 238000006477 desulfuration reaction Methods 0.000 claims abstract description 10
- 230000023556 desulfurization Effects 0.000 claims abstract description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 30
- 239000007788 liquid Substances 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000007726 management method Methods 0.000 claims description 9
- 230000005855 radiation Effects 0.000 claims description 7
- 230000003628 erosive effect Effects 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims 2
- 238000005260 corrosion Methods 0.000 claims 1
- 230000007797 corrosion Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 description 23
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000004048 modification Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 239000000779 smoke Substances 0.000 description 5
- 238000009628 steelmaking Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000003756 stirring Methods 0.000 description 2
- 238000005211 surface analysis Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- BRPQOXSCLDDYGP-UHFFFAOYSA-N calcium oxide Chemical compound [O-2].[Ca+2] BRPQOXSCLDDYGP-UHFFFAOYSA-N 0.000 description 1
- ODINCKMPIJJUCX-UHFFFAOYSA-N calcium oxide Inorganic materials [Ca]=O ODINCKMPIJJUCX-UHFFFAOYSA-N 0.000 description 1
- 239000000292 calcium oxide Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 239000011819 refractory material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22D—CASTING OF METALS; CASTING OF OTHER SUBSTANCES BY THE SAME PROCESSES OR DEVICES
- B22D43/00—Mechanical cleaning, e.g. skimming of molten metals
- B22D43/005—Removing slag from a molten metal surface
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C1/00—Refining of pig-iron; Cast iron
- C21C1/02—Dephosphorising or desulfurising
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C7/00—Treating molten ferrous alloys, e.g. steel, not covered by groups C21C1/00 - C21C5/00
- C21C7/04—Removing impurities by adding a treating agent
- C21C7/064—Dephosphorising; Desulfurising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- Y02P10/00—Technologies related to metal processing
- Y02P10/20—Recycling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Carbon Steel Or Casting Steel Manufacturing (AREA)
Abstract
The invention discloses an automatic slag skimming method, a device and a system, which are applied to a KR method desulfurization production line and comprise the following steps: acquiring an iron ladle opening image, and processing the iron ladle opening image to obtain iron ladle data; controlling the iron ladle to tip based on the iron ladle data; acquiring an iron ladle opening image after rollover control, and processing the iron ladle opening image after rollover control to obtain waste residue data; controlling slag skimming equipment to execute a slag skimming procedure based on the waste residue data and the length data of the slag skimming plate; and acquiring a slag-off plate image in the process of executing the slag-off procedure, and updating the length data of the slag-off plate according to the slag-off plate image.
Description
Technical Field
The invention relates to the field of steelmaking, in particular to an automatic slag skimming method, device and system.
Background
The desulfurization and slagging-off are used as important preorders in steel making, and the slagging-off effect has great influence on the subsequent steel making effect. The original slag raking work is mainly finished in a manual remote control mode, and the iron ladle tipping, the slag raking machine action and the slag raking plate state judgment in the whole slag raking process are finished through human eye judgment by utilizing video monitoring. Currently, in the field of automated skimming, there have been several attempts including infrared detection and traditional CV image analysis to automatically skive slag.
However, in the first aspect, the existing automatic slag skimming technologies mainly aim at the processing of slag surface analysis, and the processing effect is greatly influenced by the environment in the scene. On the other hand, the slag surface analysis is only one ring in automatic slag skimming. The existing intelligent desulfurization system needs a set of more complete automatic slag skimming auxiliary system to cover all processes of tipping, skimming, plate changing and the like in the slag skimming process.
Disclosure of Invention
The embodiment of the application provides an automatic slag-raking method, device and system, solves the technical problems of poor automatic slag-raking effect and single function in the prior art, and achieves the technical effects of efficient automatic slag-raking and perfect function.
In a first aspect, the present application provides the following technical solutions through an embodiment of the present application:
an automatic slag skimming method is applied to a KR method desulfurization production line and comprises the following steps:
acquiring an iron ladle opening image, and processing the iron ladle opening image to obtain iron ladle data;
controlling the iron ladle to tip based on the iron ladle data;
acquiring an iron ladle opening image after rollover control, and processing the iron ladle opening image after rollover control to obtain waste residue data;
controlling slag skimming equipment to execute a slag skimming procedure based on the waste residue data and the length data of the slag skimming plate; and acquiring a slag-off plate image in the process of executing the slag-off procedure, and updating the length data of the slag-off plate according to the slag-off plate image.
In one embodiment, the obtaining an image of a ladle opening and processing the image of the ladle opening to obtain ladle data includes:
acquiring two images of the ladle opening from two different directions, wherein the two images are total images;
firstly, carrying out radiation transformation and perspective transformation on the two images to obtain a processed complete image, and then processing the complete image to obtain the data of the iron ladle.
In one embodiment, the processing the packet edge image to obtain the data of the iron packet includes:
analyzing the texture of the middle part of the image of the region by using a convolutional neural network model to obtain iron ladle data; the convolutional neural network model is a U-shaped network model.
In one embodiment, the acquiring an iron ladle opening image after rollover control, and processing the iron ladle opening image after rollover control to obtain waste slag data includes:
respectively acquiring two iron ladle opening images after rollover control from two directions, wherein the number of the images is four;
and combining the four images into two spliced images, and processing the two spliced images to obtain waste residue data.
In one embodiment, the processing the tipping-controlled ladle opening image to obtain the slag data includes:
analyzing the iron ladle opening image subjected to rollover control by using a convolutional neural network model to obtain waste residue data; the convolutional neural network model is a U-shaped network model.
In one embodiment, said updating said slag skimming plate length data according to said slag skimming plate image comprises:
firstly, identifying the slag skimming plate image by using a convolutional neural network model to obtain current slag skimming plate length data, updating the slag skimming plate length data based on the current slag skimming plate length data, and then determining whether to replace the slag skimming plate based on the slag skimming plate length data by using plate replacing equipment.
In one embodiment, the controlling the slag-raking device to perform the slag-raking process based on the slag data and the length data of the slag-raking plate includes:
dividing molten iron into a plurality of regions with the same width based on the whole occupation ratio of the waste residues, wherein the higher the whole occupation ratio of the waste residues is, the fewer the divided regions are;
determining the slag skimming priority of each area based on the following formula:
wherein, a w To take off the slag priority, r w For each area of the waste residue proportion,
skimming the weight for each zone;
selecting a for each round of slag removing equipment w The highest one is subjected to slagging-off.
In one embodiment, each round of slag-raking equipment selects a w Slagging off in the highest zone, comprising:
based on the a w Determining the initial point of the automatic control slag raking arm movement in the current round at the waste slag position farthest from the slag raking arm in the highest area; and determining the slag skimming depth based on the length data and the waste slag thickness of the slag skimming plate.
In a second aspect, the present application provides the following technical solutions according to an embodiment of the present application:
an automatic slag raking device, comprising:
the first acquisition processing unit is used for acquiring an iron ladle opening image and processing the iron ladle opening image to obtain iron ladle data;
the first control unit is used for carrying out tipping control on the iron ladle based on the iron ladle data;
the second acquisition processing unit is used for acquiring the iron ladle opening image after the tipping control and processing the iron ladle opening image after the tipping control to obtain waste residue data;
the second control unit is used for controlling the slag skimming equipment to execute a slag skimming procedure based on the waste slag data and the length data of the slag skimming plate; and acquiring a slag-off plate image in the process of executing the slag-off procedure, and updating the length data of the slag-off plate according to the slag-off plate image.
In one embodiment, the first acquisition processing unit is further configured to:
acquiring two images of the ladle opening from two different directions, wherein the two images are total images;
firstly, carrying out radiation transformation and perspective transformation on the two images to obtain a processed complete image, and then processing the complete image to obtain the data of the iron ladle.
In one embodiment, the first obtaining processing unit is further configured to:
analyzing the texture of the middle part of the image of the region by using a convolutional neural network model to obtain iron ladle data; the convolutional neural network model is a U-shaped network model.
In one embodiment, the second acquisition processing unit is further configured to:
respectively acquiring two iron ladle opening images after rollover control from two directions, wherein the number of the images is four;
and combining the four images into two spliced images, and processing the two spliced images to obtain waste residue data.
In one embodiment, the second acquisition processing unit is further configured to:
analyzing the iron ladle opening image subjected to rollover control by using a convolutional neural network model to obtain waste residue data; the convolutional neural network model is a U-shaped network model.
In one embodiment, the second control unit is further configured to:
firstly, identifying the slag skimming plate image by using a convolutional neural network model to obtain current slag skimming plate length data, updating the slag skimming plate length data based on the current slag skimming plate length data, and then determining whether to replace the slag skimming plate based on the slag skimming plate length data by using plate replacing equipment.
In one embodiment, the second control unit is further configured to:
dividing molten iron into a plurality of regions with the same width based on the whole occupation ratio of the waste residues, wherein the higher the whole occupation ratio of the waste residues is, the fewer the divided regions are;
determining the slag skimming priority of each area based on the following formula:
wherein, a w To take off the slag priority, r w For each area of the waste residue proportion,
skimming the weight for each zone;
selecting a for each round of slag removing equipment w The highest one is subjected to slagging-off.
In one embodiment, the second control unit is further configured to:
based on the a w Determining the initial point of the automatic control slag raking arm movement in the current round at the waste slag position farthest from the slag raking arm in the highest area; and determining the slag skimming depth based on the length data and the waste slag thickness of the slag skimming plate.
In a third aspect, the present application provides the following technical solutions through an embodiment of the present application:
an automatic slag skimming system comprising:
the system comprises two industrial cameras, a monitoring camera, a client viewing terminal, a programmable logic controller and a production system, wherein the two industrial cameras, the monitoring camera and the programmable logic controller are respectively connected with the client viewing terminal, and the programmable logic controller is connected with the production system;
the two industrial cameras are arranged on the oblique upper position of the iron ladle, positioned on the left side and the right side of the slag removing arm and used for shooting the opening of the iron ladle; the monitoring camera is used for shooting the slag raking plate; the client checking terminal is internally provided with a management platform and an image processing module, the image processing module is used for processing images and videos, analyzing the slag surface of the iron ladle, analyzing the erosion of the slag skimming plate, judging whether the slag skimming plate is replaced, controlling the tilting of the iron ladle and planning a slag skimming path, and the management platform is used for result display and system management; the programmable logic controller is used for receiving the signal of the image processing module and controlling the production system based on the signal.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the embodiment of the application provides the automatic slag-raking method, the device and the system, before the automatic slag-raking of the slag-raking equipment, the iron ladle is tilted to a proper angle through the tilting equipment, so that the slag-raking of the slag-raking equipment can be facilitated; the slag removing equipment is controlled through the waste slag data of the iron ladle and the length data of the slag removing plate, so that the slag removing precision and efficiency can be improved; the plate replacing equipment can automatically replace and replace the slag removing plate through the length data of the slag removing plate. Therefore, the technical problems of poor automatic slag skimming effect and single function of the slag skimming system in the prior art are solved, and the technical effects of high efficiency and more perfect slag skimming system are realized.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a flow chart of an automatic slag-raking method in the embodiment of the invention;
FIG. 2 is a diagram of a U-shaped network model-neural network structure according to an embodiment of the present invention;
FIG. 3 is a diagram of the slag surface of the ladle in three parts according to the embodiment of the invention;
FIG. 4 is a diagram of five divided iron ladle slag surfaces in an embodiment of the invention;
FIG. 5 is a diagram illustrating the influence of a bell-shaped curve on slag skimming according to an embodiment of the present invention;
FIG. 6 is a structural diagram of an automatic slag removing device in the embodiment of the invention;
fig. 7 is a structural diagram of an automatic slag raking system in the embodiment of the invention.
Detailed Description
The embodiment of the application provides an automatic slag-raking method, device and system, solves the technical problems of poor automatic slag-raking effect and single function in the prior art, and achieves the technical effects of efficient automatic slag-raking and perfect function.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
an automatic slag skimming method is applied to a KR method desulfurization production line and comprises the following steps:
acquiring an iron ladle opening image, and processing the iron ladle opening image to obtain iron ladle data;
controlling the iron ladle to tip based on the iron ladle data;
acquiring an iron ladle opening image after rollover control, and processing the iron ladle opening image after rollover control to obtain waste residue data;
controlling slag skimming equipment to execute a slag skimming procedure based on the waste residue data and the length data of the slag skimming plate; and acquiring a slag-off plate image in the process of executing the slag-off procedure, and updating the length data of the slag-off plate according to the slag-off plate image.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
First, it is stated that the term "and/or" appearing herein is merely one type of associative relationship that describes an associated object, meaning that three types of 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
Specifically, as shown in fig. 1, an embodiment of the present application provides an automatic slag skimming method, which is applied to a KR desulfurization production line, and includes:
and S101, acquiring an iron ladle opening image, and processing the iron ladle opening image to obtain iron ladle data.
In the specific implementation process, the KR method desulfurization is to immerse a baked cross-shaped stirring head which is cast with refractory materials into an iron ladle molten pool for a certain depth, add a weighed desulfurizer onto the surface of molten iron by virtue of a vortex generated by rotation of the stirring head, and roll the weighed desulfurizer into the molten iron by virtue of the vortex to enable calcium oxide-based desulfurization powder to be fully contacted and reacted with the molten iron, so as to achieve the purpose of desulfurization. The iron ladle is similar to a container for containing water, and the iron ladle contains molten iron. And when the molten iron liquid level is closer to the ladle opening, the brighter the edge of the molten iron liquid level is. Therefore, the distance between the molten iron liquid level in the ladle and the ladle opening, namely the ladle data can be obtained by analyzing the brightness of the image of the edge below the ladle opening. When the edge of the molten iron liquid surface is close to the ladle opening, molten iron is highlighted and exposed, and the ladle opening lined by the highlight can show special grains similar to lava. With this feature, the rollover to position timing can be estimated. Of course, the ladle data may also be grains of lava in the image of the edge below the ladle opening.
And S102, performing tipping control on the iron ladle based on the iron ladle data.
In the specific implementation process, the iron ladle is subjected to real-time tipping control based on the texture of the lava in the image and whether the time of tipping in place is estimated based on the appearance of the highlight. And if special grains similar to lava appear below the iron ladle image, stopping tipping the iron ladle. And if the highlight appears below the iron ladle image, performing reverse tipping on the iron ladle, wherein the reverse tipping time can be set to be different based on different tipping equipment.
Of course, a threshold brightness interval can be set, and the iron ladle can be subjected to real-time tipping control by comparing the molten iron liquid level brightness with the threshold brightness interval. When the brightness of the liquid level of the molten iron is lower than the threshold brightness interval, tipping the iron ladle; when the liquid level brightness of the molten iron is within the threshold brightness interval, stopping overturning the iron ladle; and when the brightness of the molten iron liquid level exceeds the threshold brightness interval, determining that molten iron overflows from the iron ladle, and performing reverse tipping on the iron ladle until the brightness of the molten iron liquid level is within the threshold brightness interval.
And S103, acquiring an iron ladle opening image after rollover control, and processing the iron ladle opening image after rollover control to obtain waste residue data.
In the specific implementation process, the waste slag can float in different areas of the molten iron liquid level, and the area where the waste slag is located in the obtained ladle opening image is dark. Therefore, the distribution map of the waste residue can be obtained based on the brightness of the pixel points in the image, and the thickness of the waste residue in the current area can be obtained based on the depth of the pixel point color in the waste residue area.
Of course, in addition to obtaining the waste residue data (the proportion of the waste residue and the thickness of the waste residue) based on the brightness and darkness of the image pixels, the waste residue data can also be obtained based on the obtained image lines. For example, the molten iron level has grains similar to lava, and the area with slag has grains that do not appear because the slag blocks the grains. Therefore, the waste residue area can be judged by the existence of the texture similar to the lava, and the proportion of the waste residue can be obtained.
Step S104, controlling slag skimming equipment to execute a slag skimming procedure based on the waste residue data and the length data of the slag skimming plate; and acquiring a slag-off plate image in the process of executing the slag-off procedure, and updating the length data of the slag-off plate according to the slag-off plate image.
In a specific implementation process, the waste residue data includes: the distribution of the waste slag in the iron ladle and the thickness of the waste slag in different areas in the iron ladle, and the length data of the slag skimming plate is the length of the slag skimming plate. Therefore, the slag removing equipment can be controlled to carry out the slag removing process based on the waste slag data and the length data of the slag removing plate. The length of the slag skimming plate is changed due to the erosion of molten iron to the slag skimming plate in the slag skimming process. Therefore, the image of the slag raking plate can be collected through the monitoring camera, the length of the current slag raking plate can be obtained through analyzing and collecting the image of the slag raking plate, and the length data of the slag raking plate can be updated.
As an alternative embodiment, step S101 further includes:
acquiring two images of the ladle opening from two different directions, wherein the two images are total images;
firstly, carrying out radiation transformation and perspective transformation on the two images to obtain a processed complete image, and then processing the complete image to obtain the data of the iron ladle.
In the specific implementation process, due to the problem of the installation angle of the industrial camera, the obliquely shot image is slightly deformed, the slag raking arm can also shield partial images, and the obtained iron ladle data are distorted. Therefore, two images of the ladle opening can be obtained from two different directions, and the two images are total; the two images are subjected to radiation transformation and perspective transformation to obtain a processed complete image, and then the deformed image can be corrected and a part of image shielded by the slag removing arm can be supplemented, so that the obtained iron ladle data are accurate. The two directions can be the left side and the right side of the slag removing arm, so that the obtained image is shielded to the minimum degree, and certainly, the optimal angles of shooting the iron ladle by different slag removing facility cameras can be different, so that the two directions can be other directions. Furthermore, the installation position of the camera can be adjusted according to the layout of the field facility, and this embodiment is not particularly limited.
As an alternative embodiment, step S101 further includes:
analyzing the texture of the middle part of the image of the region by using a convolutional neural network model to obtain iron ladle data; the convolutional neural network model is a U-shaped network model. Of course, the convolutional neural network model may also be an annular network model, a pyramid structure model, or the like, and this embodiment is not particularly limited.
As an alternative embodiment, step S103 further includes:
analyzing the iron ladle opening image subjected to rollover control by using a convolutional neural network model to obtain waste residue data; the convolution neural network model is a U-shaped network model. Of course, the convolutional neural network model may also be an annular network model or a pyramid structure model, and the like, and this embodiment is not particularly limited.
As an alternative embodiment, step S104 further includes:
firstly, identifying the slag skimming plate image by using a convolutional neural network model to obtain current slag skimming plate length data, updating the slag skimming plate length data based on the current slag skimming plate length data, and then determining whether to replace the slag skimming plate based on the slag skimming plate length data by using plate replacing equipment.
In a specific implementation process, a machine vision technology is developed into a plurality of deep learning methods mainly based on a convolutional neural network by utilizing a plurality of general image processing algorithms from a traditional CV (constant-volume) mode; the neural network method often shows better adaptability to specific scenes, and due to the characteristics of universal fitting and local optimization, the neural network model can give a good result in a single scene. The convolutional neural network model used in steps S101 and S103 of the present embodiment is shown in fig. 2.
Specifically, in this embodiment, the U-type network model used in step S101 and step S103 is shown in fig. 2, data in each processing unit represents the number and size of output images, the processing unit on the left of the U-type network model processes images of original large pixels to obtain images with a large number of small pixel features, and the processing unit on the right restores the images with a large number of small pixel features into classified images with a small number of large pixel features. Then, one high-pixel image is input, sequentially processed by the processing unit in the U-shaped network model, and two images with pixels close to the input image are output. Each pixel of the input image is a color pixel, each pixel of the output image represents the classification of this pixel in its corresponding original image, and the pixel value of each pixel is its classification number.
For example, the top left corner of the figure is 1x1324 2 Represents the input-sheet 1324 2 Pixel-sized image twice processed through the first layer resulting in 64 1316 2 The image with the pixel size is processed by the processing units of the next layers to obtain 1024 images with 64 images 2 An image of pixels; the 1024 images are processed by the right processing unit to obtain 64 images 904 2 Pixel-sized image, and finally 2 of said 904 2 Pixel-sized images.
As an alternative embodiment, step S103 further includes:
respectively acquiring two iron ladle opening images after rollover control from two directions, wherein the number of the images is four;
and combining the four images into two spliced images, and processing the two spliced images to obtain waste residue data.
In a specific implementation process, molten iron is subjected to smoke generation in a slag removing process, the influence of smoke is considered, and before the spliced images are processed to obtain waste residue data, smoke generation areas of the two spliced images need to be eliminated.
Specifically, two images of the ladle mouth after tipping control are obtained from the left side and the right side of the slag removing arm respectively, and the total number of the images is four. Combining two corresponding left and right images in the four images into one image to obtain two spliced images, and performing smoke abatement on the two spliced images. Of course, four images can be obtained from any four directions, and any two images selected from the four images are combined into one image. The smoke area of the image may be eliminated before or after the stitching of the two images.
As an alternative embodiment, step S104 further includes:
dividing molten iron into a plurality of regions with the same width based on the whole occupation ratio of the waste residues, wherein the higher the whole occupation ratio of the waste residues is, the fewer the divided regions are;
determining the slag skimming priority of each area based on the following formula:
wherein, a w To take off the slag priority, r w For each area of the waste residue proportion,
skimming the slag weight for each area;
selecting a for each round of slag removing equipment w The highest one is subjected to slagging-off.
In the specific implementation process, in order to ensure the slag skimming effect, the slag skimming is required to be carried out in the area with the most slag each time, so that the molten iron can be divided into a plurality of areas with the same width based on the whole proportion of the slag, and the more the whole proportion of the slag isHigh, the fewer the number of divided regions. The minimum value of the divided area number is 3, and the maximum value is the pixel width wd of the slag removing plate on the image b And the pixel width wd of the slag removing area s Is determined to be greater than or equal to
Is the first odd number of.
Specifically, according to the size of the slag removing plate and the size of the iron ladle adopted in actual production, the maximum number of blocks can be determined to be 7 based on the pixel width of the slag removing plate and the pixel width of a slag removing area. Therefore, the number of divided areas can be set to three number levels, 3 blocks, 5 blocks, and 7 blocks, respectively. Two thresholds are set for dividing in three different levels, so that a user can set two thresholds (two liquid level integral slag ratio) in the system to guide the system to divide the number of zones transversely when the slag skimming is carried out. As shown in fig. 3 and 4, if there is more slag on the molten iron surface, the molten iron surface is divided into 3 regions, if there is medium bright slag on the molten iron surface, the molten iron surface is divided into 5 regions, and if there is less slag on the molten iron surface, the molten iron surface is divided into 7 regions. In the figure, black areas represent waste areas, and white areas represent bright areas (areas without waste).
In the specific implementation process, because the molten iron is a fluid, the liquid level of the molten iron flows in the slag-raking process, the influence of slag-raking on the periphery is large relative to the middle area, and the slag-raking effect is relatively good. The slag raking effect is distributed according to the probability of the bell-shaped curve which is just too distributed, and the higher the probability of the corresponding bell-shaped curve of the slag raking area is, the better the slag raking effect of the slag raking area is. Therefore, in the embodiment, the probability of the median curve corresponding to each interval is used as the slag-off weight of each region. By the formula
Determining the slag-off priority of each area; wherein, a w To take off the slag priority, r w For each area of the waste residue proportion,
and (4) slagging-off weight for each area. Lifting deviceFor example, as shown in fig. 5, a bell curve influence diagram on slag skimming corresponding to fig. 4 can be obtained. Wherein, the curve in the graph is a probability curve of a bell-shaped curve, and the slag removing weights of 5 areas in the graph 4 are obtained based on the curve and sequentially comprise: 0.3, 0.45, 0.67, 0.45 and 0.3; the ratio of the waste residues in each area is calculated based on the graph of 4 as follows: 70%, 65%, 40%, 43% and 55%; multiplying the slag proportion of each area by the corresponding slag removing weight to obtain slag removing priorities of 5 areas, wherein the slag removing priorities are as follows: 21%, 29.25%, 26.8%, 19.35% and 16.5%.
As an alternative embodiment, step S104 further includes:
based on the a w Determining the initial point of the automatic control slag raking arm movement in the current round at the waste slag position farthest from the slag raking arm in the highest area; and determining the slag skimming depth based on the length data and the waste slag thickness of the slag skimming plate.
In the specific implementation process, after determining which area to carry out slag skimming, slag skimming control is required to be carried out on the slag skimming equipment. The slag skimming starting point can be determined by positioning the slag points in the iron ladle image through an xyz three-dimensional coordinate, wherein x is the horizontal coordinate of the slag pixel point, y is the vertical coordinate of the slag pixel point, and z is the depth coordinate of the slag pixel point.
Specifically, the point with the largest y value in all the waste residue pixels is selected as the initial point of the slag skimming of the current round, and the point with the smallest y value in all the waste residue pixels can also be selected as the final point of the slag skimming of the current round. Based on different requirements of users, different threshold values can be set, if the y values of a plurality of waste residue pixels are all the minimum value or the maximum value and the number of the pixels exceeds the threshold value number, the middle point of the pixels is taken as the x value of the target slag raking position, otherwise, the x value far away from the horizontal central line of the whole ladle opening area is taken as the x value of slag raking.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
the embodiment of the application provides the automatic slag-raking method, the iron ladle is tilted to a proper angle through the tilting equipment, and the slag of the slag-raking equipment can be conveniently raked; the slag removing equipment is controlled through the waste slag data of the iron ladle and the length data of the slag removing plate, so that the slag removing precision and efficiency can be improved; the plate replacing equipment can automatically replace and replace the slag removing plate through the length data of the slag removing plate. Therefore, the technical problems of poor automatic slag skimming effect and single function of the slag skimming system in the prior art are solved, and the technical effects of high efficiency and more perfect slag skimming system are realized.
Example two
Based on the same inventive concept, as shown in fig. 6, the present embodiment provides an automatic slag raking device 600, including:
the first obtaining and processing unit 610 is configured to obtain an image of a ladle opening of a ladle, and process the image of the ladle opening to obtain ladle data;
a first control unit 620, configured to perform tipping control on the ladle based on the ladle data;
the second obtaining and processing unit 630 is configured to obtain an iron ladle opening image after rollover control, and process the iron ladle opening image after rollover control to obtain waste residue data;
the second control unit 640 is used for controlling the slag removing equipment to execute a slag removing process based on the waste slag data and the length data of the slag removing plate; and acquiring a slag-off plate image in the process of executing the slag-off procedure, and updating the length data of the slag-off plate according to the slag-off plate image.
Since the automatic slag raking device described in this embodiment is a device used for implementing the automatic slag raking method in the embodiment of the present invention, based on the automatic slag raking method described in the embodiment of the present invention, a person skilled in the art can understand a specific implementation manner and various variations of the automatic slag raking device in this embodiment, so that a detailed description of how the automatic slag raking device implements the method in the embodiment of the present invention is not provided here. As long as the device adopted by the automatic slag-raking method in the embodiment of the invention is implemented by persons skilled in the art, the automatic slag-raking method belongs to the protection scope of the invention.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
the embodiment of the application provides the automatic slag raking device, the iron ladle is tilted to a proper angle through the tilting equipment, and the slag raking of the slag raking equipment can be facilitated; the slag removing equipment is controlled through the waste slag data of the iron ladle and the length data of the slag removing plate, so that the slag removing precision and efficiency can be improved; the plate replacing equipment can automatically replace and replace the slag removing plate through the length data of the slag removing plate. Therefore, the technical problems of poor automatic slag skimming effect and single function of the slag skimming system in the prior art are solved, and the technical effects of high efficiency and more perfect slag skimming system are realized.
EXAMPLE III
Based on the same inventive concept, as shown in fig. 7, the present embodiment provides an automatic slag-off system, including:
the system comprises two industrial cameras, a monitoring camera, a client viewing terminal, a programmable logic controller and a production system, wherein the two industrial cameras, the monitoring camera and the programmable logic controller are respectively connected with the client viewing terminal, and the programmable logic controller is connected with the production system;
the two industrial cameras are arranged on the oblique upper position of the iron ladle, positioned on the left side and the right side of the slag removing arm and used for shooting the opening of the iron ladle; the monitoring camera is used for shooting the slag raking plate; the client checking terminal is internally provided with a management platform and an image processing module, the image processing module is used for processing images and videos, analyzing the slag surface of the iron ladle, analyzing the erosion of the slag skimming plate, judging whether the slag skimming plate is replaced, controlling the tilting of the iron ladle and planning a slag skimming path, and the management platform is used for result display and system management; the programmable logic controller is used for receiving the signal of the image processing module and controlling the production system based on the signal.
Since the automatic slag-raking system described in this embodiment is a system used for implementing the automatic slag-raking method in the embodiment of the present invention, based on the automatic slag-raking method described in the embodiment of the present invention, a person skilled in the art can understand a specific implementation manner and various variations of the automatic slag-raking system in this embodiment, so that a detailed description of how the automatic slag-raking system implements the method in the embodiment of the present invention is omitted here. The system adopted by the automatic slag-raking method in the embodiment of the invention is all within the protection scope of the invention as long as the person skilled in the art implements the system.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
the embodiment of the application provides the automatic slag raking system, the iron ladle is tilted to a proper angle through the tilting equipment, and the slag raking of the slag raking equipment can be facilitated; the slag removing equipment is controlled through the waste slag data of the iron ladle and the length data of the slag removing plate, so that the slag removing precision and efficiency can be improved; the plate replacing equipment can automatically replace and replace the slag removing plate through the length data of the slag removing plate. Therefore, the technical problems of poor automatic slag skimming effect and single function of the slag skimming system in the prior art are solved, and the technical effects of high efficiency and more perfect slag skimming system are realized.
While preferred embodiments of the present invention 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 such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (6)
1. An automatic slag skimming method is characterized by being applied to a KR method desulfurization production line and comprising the following steps:
acquiring an iron ladle opening image, and processing the iron ladle opening image to obtain iron ladle data;
controlling the iron ladle to tip based on the iron ladle data;
acquiring an iron ladle opening image after rollover control, and processing the iron ladle opening image after rollover control to obtain waste residue data;
controlling slag skimming equipment to execute a slag skimming procedure based on the waste residue data and the length data of the slag skimming plate; acquiring a slag-off plate image in the process of executing the slag-off procedure, and updating the length data of the slag-off plate according to the slag-off plate image;
the acquiring of the image of the iron ladle opening, and the processing of the image of the iron ladle opening to obtain the iron ladle data comprise:
acquiring two images of the ladle opening from two different directions, wherein the two images are total images;
firstly, performing radiation transformation and perspective transformation on the two images to obtain a processed complete image, and then processing the complete image to obtain iron ladle data;
analyzing the texture of the middle part of the image of the region by using a convolutional neural network model to obtain iron ladle data; the convolutional neural network model is a U-shaped network model;
the processing of the ladle opening image after the tipping control to obtain waste residue data comprises the following steps:
analyzing the iron ladle opening image subjected to rollover control by using a convolutional neural network model to obtain waste residue data; the convolutional neural network model is a U-shaped network model;
the step of controlling slag skimming equipment to execute a slag skimming procedure based on the waste residue data and the length data of the slag skimming plate comprises the following steps:
dividing molten iron into a plurality of regions with the same width based on the whole occupation ratio of the waste residues, wherein the higher the whole occupation ratio of the waste residues is, the fewer the divided regions are;
the method comprises the following steps of dividing molten iron into a plurality of regions with the same width based on the integral proportion of waste residues, wherein the higher the integral proportion of the waste residues is, the fewer the divided regions are, and the method comprises the following steps:
according to the size of the slag removing plate and the size of the iron ladle, the number of divided areas is set to three number levels of 3 blocks, 5 blocks and 7 blocks based on the pixel width of the slag removing plate and the pixel width of the slag removing area, and the divided areas are divided by setting two threshold values;
the threshold value is the ratio of the whole waste residues of the two liquid levels;
determining the slag skimming priority of each area based on the following formula:
wherein,
to take off the slag priority, r w For each area of the waste residue proportion,
skimming the weight for each zone;
selection of each round of slag removing equipment
The highest one is subjected to slagging-off.
2. The method of claim 1, wherein the obtaining of the tipping-controlled taphole image and the processing of the tipping-controlled taphole image to obtain the slag data comprises:
respectively acquiring two iron ladle opening images after rollover control from two directions, wherein the number of the images is four;
and combining the four images into two spliced images, and processing the two spliced images to obtain waste residue data.
3. The method of claim 1, wherein said updating said slag plate length data based on said slag plate image comprises:
firstly, identifying the slag skimming plate image by using a convolutional neural network model to obtain current slag skimming plate length data, updating the slag skimming plate length data based on the current slag skimming plate length data, and then determining whether to replace the slag skimming plate based on the slag skimming plate length data by using plate replacing equipment.
4. The method of claim 1, wherein each round of slag removal equipment is selectedSlagging off in the highest zone, comprising:
based on theDetermining the initial point of the automatic control slag raking arm movement in the current round at the waste slag position farthest from the slag raking arm in the highest area; and determining the slag skimming depth based on the length data and the waste slag thickness of the slag skimming plate.
5. An automatic slag raking device is characterized by comprising:
the first acquisition processing unit is used for acquiring an iron ladle opening image and processing the iron ladle opening image to obtain iron ladle data;
the first control unit is used for carrying out tipping control on the iron ladle based on the iron ladle data;
the second acquisition processing unit is used for acquiring the iron ladle opening image after the tipping control and processing the iron ladle opening image after the tipping control to obtain waste residue data;
the second control unit is used for controlling the slag skimming equipment to execute a slag skimming procedure based on the waste slag data and the length data of the slag skimming plate; acquiring a slag-off plate image in the process of executing the slag-off procedure, and updating the length data of the slag-off plate according to the slag-off plate image;
the acquiring of the image of the iron ladle opening, and the processing of the image of the iron ladle opening to obtain the iron ladle data comprise:
acquiring two images of the ladle opening from two different directions, wherein the two images are total images;
firstly, performing radiation transformation and perspective transformation on the two images to obtain a processed complete image, and then processing the complete image to obtain iron ladle data;
analyzing the texture of the middle part of the image of the region by using a convolutional neural network model to obtain iron ladle data; the convolutional neural network model is a U-shaped network model;
the processing of the iron ladle opening image after the tipping control to obtain waste residue data comprises the following steps:
analyzing the iron ladle opening image subjected to tipping control by using a convolutional neural network model to obtain waste residue data; the convolutional neural network model is a U-shaped network model;
the step of controlling slag skimming equipment to execute a slag skimming procedure based on the waste residue data and the length data of the slag skimming plate comprises the following steps:
dividing molten iron into a plurality of regions with the same width based on the whole occupation ratio of the waste residues, wherein the higher the whole occupation ratio of the waste residues is, the fewer the divided regions are;
the method comprises the following steps of dividing molten iron into a plurality of regions with the same width based on the integral proportion of waste residues, wherein the higher the integral proportion of the waste residues is, the fewer the divided regions are, and the method comprises the following steps:
according to the size of the slag removing plate and the size of the iron ladle, the number of divided areas is set to three number levels of 3 blocks, 5 blocks and 7 blocks based on the pixel width of the slag removing plate and the pixel width of the slag removing area, and the divided areas are divided by setting two threshold values;
the threshold value is the ratio of the whole waste residues of the two liquid levels;
determining the slag skimming priority of each area based on the following formula:
wherein,to take off the slag priority, r w For each area of the waste residue proportion,skimming the weight for each zone;
selection of each round of slag removing equipmentThe highest one is subjected to slagging-off.
6. An automatic slag skimming system, comprising:
the system comprises two industrial cameras, a monitoring camera, a client viewing terminal, a programmable logic controller and a production system, wherein the two industrial cameras, the monitoring camera and the programmable logic controller are respectively connected with the client viewing terminal, and the programmable logic controller is connected with the production system;
the two industrial cameras are arranged on the oblique upper position of the iron ladle, positioned on the left side and the right side of the slag removing arm and used for shooting the opening of the iron ladle; the monitoring camera is used for shooting the slag raking plate; the client checking terminal is internally provided with a management platform and an image processing module, the image processing module is used for processing images and videos, analyzing the slag surface of the iron ladle, analyzing the erosion of the slag skimming plate, judging whether the slag skimming plate is replaced, controlling the tilting of the iron ladle and planning a slag skimming path, and the management platform is used for result display and system management; the programmable logic controller is used for receiving the signal of the image processing module and controlling the production system based on the signal;
the shooting iron ladle opening comprises:
acquiring two images of the ladle opening from two different directions, wherein the two images are total images;
the image processing module is used for image and video processing, analysis of the slag surface of the iron ladle, corrosion analysis of the slag skimming plate, judgment of whether the slag skimming plate is replaced, iron ladle rollover control and slag skimming path planning, and comprises the following components:
firstly, performing radiation transformation and perspective transformation on the two images to obtain a processed complete image, and then processing the complete image to obtain iron ladle data;
analyzing the texture of the middle part of the image of the region by using a convolutional neural network model to obtain iron ladle data; the convolution neural network model is a U-shaped network model;
analyzing the iron ladle opening image subjected to rollover control by using a convolutional neural network model to obtain waste residue data; the convolutional neural network model is a U-shaped network model;
dividing molten iron into a plurality of regions with the same width based on the whole occupation ratio of the waste residues, wherein the higher the whole occupation ratio of the waste residues is, the fewer the divided regions are;
the method comprises the following steps of dividing molten iron into a plurality of regions with the same width based on the integral proportion of waste residues, wherein the higher the integral proportion of the waste residues is, the fewer the divided regions are, and the method comprises the following steps:
according to the size of the slag removing plate and the size of the iron ladle, the number of divided areas is set to three number levels of 3 blocks, 5 blocks and 7 blocks based on the pixel width of the slag removing plate and the pixel width of the slag removing area, and the divided areas are divided by setting two threshold values;
the threshold value is the ratio of the whole waste residues of the two liquid levels;
determining the slag skimming priority of each area based on the following formula:
wherein,to take off the slag priority, r w For each area of the waste residue proportion,skimming the weight for each zone;
selection of each round of slag removing equipmentThe highest one is subjected to slagging-off.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011625432.3A CN112828275B (en) | 2020-12-30 | 2020-12-30 | Automatic slag skimming method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011625432.3A CN112828275B (en) | 2020-12-30 | 2020-12-30 | Automatic slag skimming method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112828275A CN112828275A (en) | 2021-05-25 |
| CN112828275B true CN112828275B (en) | 2022-08-09 |
Family
ID=75924443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011625432.3A Active CN112828275B (en) | 2020-12-30 | 2020-12-30 | Automatic slag skimming method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112828275B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113528750A (en) * | 2021-07-27 | 2021-10-22 | 湖南福华信息工程有限公司 | Automatic slag skimming system |
| CN115156518B (en) * | 2022-07-12 | 2024-03-08 | 哈尔滨工业大学 | Automatic molten steel slag removing device, method, fault processing device, loss degree obtaining method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105353654A (en) * | 2015-09-29 | 2016-02-24 | 田陆 | System and method of detection and control of melted iron drossing on the basis of image processing |
| WO2018105652A1 (en) * | 2016-12-06 | 2018-06-14 | 新日鐵住金株式会社 | Method for evaluating volume of slag on surface of molten metal |
| CN108311688A (en) * | 2018-04-17 | 2018-07-24 | 上海曙佳科技发展有限公司 | Intelligent mucking machine |
| CN109521730A (en) * | 2017-09-20 | 2019-03-26 | 上海梅山钢铁股份有限公司 | The on-line calculation method of the top of the slag in a kind of ladle |
| CN110666150A (en) * | 2019-10-09 | 2020-01-10 | 长沙有色冶金设计研究院有限公司 | Metal ingot casting slag skimming system and method |
| CN111349753A (en) * | 2020-05-08 | 2020-06-30 | 衡阳镭目科技有限责任公司 | Hot metal ladle slag-raking control system, slag-raking machine and automatic slag-raking control method for hot metal ladle |
| CN112091206A (en) * | 2019-05-31 | 2020-12-18 | 宝山钢铁股份有限公司 | Safe and reliable molten iron pretreatment automatic slag skimming method and system |
-
2020
- 2020-12-30 CN CN202011625432.3A patent/CN112828275B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105353654A (en) * | 2015-09-29 | 2016-02-24 | 田陆 | System and method of detection and control of melted iron drossing on the basis of image processing |
| WO2018105652A1 (en) * | 2016-12-06 | 2018-06-14 | 新日鐵住金株式会社 | Method for evaluating volume of slag on surface of molten metal |
| CN109521730A (en) * | 2017-09-20 | 2019-03-26 | 上海梅山钢铁股份有限公司 | The on-line calculation method of the top of the slag in a kind of ladle |
| CN108311688A (en) * | 2018-04-17 | 2018-07-24 | 上海曙佳科技发展有限公司 | Intelligent mucking machine |
| CN112091206A (en) * | 2019-05-31 | 2020-12-18 | 宝山钢铁股份有限公司 | Safe and reliable molten iron pretreatment automatic slag skimming method and system |
| CN110666150A (en) * | 2019-10-09 | 2020-01-10 | 长沙有色冶金设计研究院有限公司 | Metal ingot casting slag skimming system and method |
| CN111349753A (en) * | 2020-05-08 | 2020-06-30 | 衡阳镭目科技有限责任公司 | Hot metal ladle slag-raking control system, slag-raking machine and automatic slag-raking control method for hot metal ladle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112828275A (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112828275B (en) | Automatic slag skimming method, device and system | |
| EP0578508A2 (en) | Video camera with colour-based target tracking system | |
| CN100553301C (en) | The modification method of brightness | |
| EP1895469A2 (en) | Image display apparatus, image display method, and image display program | |
| CN110781944B (en) | Automatic molten iron slag-off control method based on deep learning | |
| CN105554364A (en) | Image processing method and terminal | |
| CN112150421B (en) | Ladle slag removing path determining method and device and slag removing machine | |
| CN106683100A (en) | Image segmentation and defogging method and terminal | |
| CN110196252B (en) | Groove defect detection algorithm and device | |
| JP2009293993A (en) | Method and apparatus for evaluating degree of corrosion and program | |
| CN110751669A (en) | Novel CBOCP online infrared converter tapping steel flow automatic detection and tracking method and system | |
| CN113592868B (en) | Method for detecting black and gray of glass fiber cloth cover | |
| CN107749986A (en) | Instructional video generation method, device, storage medium and computer equipment | |
| CN102724541B (en) | Intelligent diagnosis and recovery method for monitoring images | |
| KR20240019361A (en) | Methods, measuring devices, welding systems, and programs for measuring the behavior of welding phenomena | |
| JP2020063898A (en) | Slag amount measurement device and slag amount measurement method | |
| CN113411510B (en) | Camera automatic exposure algorithm based on image quality evaluation and red hot forging | |
| CN112200755B (en) | Image defogging method | |
| CN113063474A (en) | Slag liquid level real-time detection method, device, equipment and storage medium | |
| CN113052816A (en) | Furnace mouth image identification method, device, equipment and storage medium | |
| CN113052828A (en) | Ladle slag line slagging cleaning time prediction method and system based on artificial intelligence | |
| CN110136104A (en) | Image processing method, system and medium based on unmanned aerial vehicle station | |
| JPH08106534A (en) | Movable object detector | |
| CN108830834B (en) | Automatic extraction method for video defect information of cable climbing robot | |
| CN113469980B (en) | Flange identification method based on image processing |
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 |