CN111583231B - Method and system for detecting opening of metallurgical tank - Google Patents

Method and system for detecting opening of metallurgical tank Download PDF

Info

Publication number
CN111583231B
CN111583231B CN202010384588.0A CN202010384588A CN111583231B CN 111583231 B CN111583231 B CN 111583231B CN 202010384588 A CN202010384588 A CN 202010384588A CN 111583231 B CN111583231 B CN 111583231B
Authority
CN
China
Prior art keywords
area
tank
analysis unit
tank opening
edge
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
Application number
CN202010384588.0A
Other languages
Chinese (zh)
Other versions
CN111583231A (en
Inventor
田陆
田立
谢卫东
肖小文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hengyang Ramon Science & Technology Co ltd
Original Assignee
Hengyang Ramon Science & Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hengyang Ramon Science & Technology Co ltd filed Critical Hengyang Ramon Science & Technology Co ltd
Priority to CN202010384588.0A priority Critical patent/CN111583231B/en
Publication of CN111583231A publication Critical patent/CN111583231A/en
Application granted granted Critical
Publication of CN111583231B publication Critical patent/CN111583231B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/20—Metals
    • G01N33/204—Structure thereof, e.g. crystal structure
    • G01N33/2045—Defects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30136—Metal
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P10/00—Technologies related to metal processing
    • Y02P10/20—Recycling

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medicinal Chemistry (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Food Science & Technology (AREA)
  • Multimedia (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
  • Measurement Of Levels Of Liquids Or Fluent Solid Materials (AREA)

Abstract

The invention provides a method and a system for detecting a gap of a metallurgical tank, wherein an image acquisition module is used for acquiring a tank opening edge image of the metallurgical tank in the metallurgical process in real time, and then an image processing module is used for analyzing and processing the tank opening edge image to detect a position area of the gap of the metallurgical tank from the tank opening edge image, so that an optimal endpoint of a slag-removing path planning in a slag-removing process is determined, slag-removing efficiency is improved, and loss of metal liquid in the slag-removing process is reduced. The position of the notch is judged through multiple times of calculation and comparison, and the judgment accuracy is high.

Description

Method and system for detecting opening of metallurgical tank
Technical Field
The invention belongs to the field of ferrous metallurgy, and particularly relates to a method and a system for detecting a notch of a metallurgical tank.
Background
In the field of iron and steel smelting, some impurity residues may exist in the molten metal in the smelting pot, and if the residues are brought into the next converter process, the purity of metallurgy can be affected, so that the quality of a terminal product is reduced. Therefore, before transferring the molten metal to the converter, a slag skimming process is required to remove impurity slag from the molten metal.
At present, the automatic slag removing process is already automated, and in the automatic slag removing process, a slag removing path is usually planned according to a gap of a smelting pot, because the gap is generally used as an endpoint reference of the slag removing path. However, during the slagging-off process, the edges of the smelting pot may accumulate and bind some metal slag, resulting in an uncertain position of the gap, which may result in inefficient slagging-off and unstable slagging-off process.
Disclosure of Invention
In view of the above, the invention provides a method and a system for detecting a gap of a metallurgical tank, which are used for solving the problems of low slag removal efficiency and unstable slag removal process caused by the fact that the slag removal path planning is not optimized due to the uncertainty of the position of the gap in the prior art.
A method for detecting the opening of a metallurgical tank comprises the following steps:
step S1, acquiring an image of the edge of the mouth of the metallurgical tank,
step S2, identifying the edge point of the tank opening of the metallurgical tank from the image of the edge of the tank opening,
step S3, an analysis area is defined according to the edge points of the edge tank opening,
step S4, dividing the analysis area into a plurality of analysis unit areas,
step S5, calculating the duration time that the number of the bright spots in each analysis unit area is larger than a first threshold value and the percentage of the number of the bright spots, wherein the bright spots are pixel spots with gray values larger than a second threshold value,
step S6 of comparing said duration of each of said analysis unit areas with said percentage of the number of bright spots,
step S7: and (5) circularly executing the steps S5 to S6 for a plurality of times, and judging the analysis unit area with the longest continuous occurrence duration and the largest number percentage of the bright spots as the area where the notch is located.
Preferably, the step S2 includes:
defining an identification area in the can rim image according to the imaging position of the can rim in the can rim image,
vertically traversing the pixel points in the identification area, taking two adjacent pixel points as judgment base points,
and when the gray value of the upper pixel point in the adjacent two image points is not smaller than a third threshold value and the gray value of the lower pixel point in the adjacent two pixel points is smaller than the third threshold value, acquiring the upper pixel point in the adjacent two pixel points as the tank opening edge point.
Preferably, the step S3 includes:
fitting a can rim curve according to the recognized can rim point, translating the can rim curve toward the direction of the inner wall of the can rim toward the outer wall of the can rim by a first distance and a second distance respectively to obtain a first expansion curve and a second expansion curve respectively,
the area between the first extension curve and the second extension curve is defined as the analysis area.
Preferably, the step S4 includes:
dividing the tank opening edge curve equally according to the length to obtain each first dividing point on the tank opening edge curve,
making the shortest distance straight line to the first expansion curve by the first dividing points, and extending the shortest distance straight line to at least the second expansion curve,
and taking the analysis area between two adjacent shortest distance straight lines in the shortest distance straight lines extending respectively as one analysis unit area.
Preferably, the step S5 includes:
sequentially calculating the change of the number of the bright spots in each analysis unit area, starting timing when the number of the bright spots in the analysis unit area currently subjected to the calculation exceeds the first threshold value, and stopping timing until the calculation action of the analysis unit area currently subjected to the calculation is finished, thereby obtaining the duration.
Preferably, the bright point number percentage is a percentage of the total number of bright points in the corresponding analysis unit area to the total number of pixel points.
Preferably, after the steps S1 to S6 are sequentially performed five times, the analysis unit area where the duration is longest and the number percentage of the bright spots is largest is determined as the area where the notch is located.
Preferably, the can mouth edge points are fitted to the can mouth edge curve using a least squares method.
A system for detecting a breach of a metallurgical vessel, comprising: an image acquisition module, a signal transmission module and an image processing module,
the image acquisition module is fixedly arranged at a preset position above the tank opening of the metallurgical tank to acquire the edge image of the tank opening of the metallurgical tank,
the signal transmission module transmits the tank opening edge image to the image processing module,
wherein the image processing module comprises an edge point identification module, an analysis area demarcation module, an analysis area segmentation module and a calculation and processing module,
the edge point identification module is used for identifying the edge point of the tank opening of the metallurgical tank from the tank opening edge image and storing the position coordinate information of the edge point of the tank opening,
the analysis zone defining module defines an analysis zone below the edge of the tank opening according to the edge point of the tank opening, the analysis zone comprises a position area where the opening is positioned,
the analysis area dividing module is used for dividing the analysis area into a plurality of analysis unit areas,
the computing and processing module is respectively used for executing the following instructions:
calculating the duration time when the number of the bright spots in each analysis unit area is larger than a first threshold value and the percentage of the number of the bright spots, wherein the bright spots are pixel spots with gray values larger than a second threshold value,
comparing the duration of each of the analysis unit areas with the bright spot number percentage,
and sequentially executing the calculating step and the comparing step for a plurality of times, and judging the analysis unit area with the longest duration and the largest number percentage of the bright spots as the area where the notch is positioned.
Preferably, the gap detection system further comprises a cooling protection module for protecting the image acquisition module.
In the method and the system for detecting the tank opening of the metallurgical tank, provided by the invention, the image acquisition module is used for acquiring the tank opening edge image of the metallurgical tank in the metallurgical process in real time, and then the image processing module is used for analyzing and processing the tank opening edge image to detect the position area of the opening of the metallurgical tank, so that the optimal endpoint of the slag removing path planning in the slag removing process is determined, the slag removing efficiency is improved, and the loss of metal liquid in the slag removing process is reduced. The position of the notch is judged through multiple times of calculation and comparison, and the judgment accuracy is high.
Drawings
FIG. 1 is a flow chart of a method for detecting a notch according to the present invention,
FIG. 2 is a simplified schematic illustration of a can end rim image provided in accordance with the present invention;
FIG. 3 is a schematic illustration of an analysis region of a can end edge image provided in accordance with the method of the present invention;
fig. 4 is a schematic view of the area division of an analysis unit of a can end edge image according to the method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure. In addition, the term "…" in the description of the present invention refers to only technical terms or features in the present invention.
It is known that the position of the opening of the metallurgical tank is always lower than the other part of the tank, so that when the metal liquid in the metallurgical tank comes out of the metallurgical tank, more molten iron and slag always come out of the position of the opening, namely the metal slag in the metal liquid or the metal liquid firstly appears in the position of the opening compared with the other part of the tank, and finally disappears from the position of the opening compared with the other part of the tank. During a metallurgical process, the metal liquid in a metallurgical vessel typically has an ultra-high temperature, and thus in the image of the rim of the vessel opening taken from above the metallurgical vessel, the location of the metal liquid is in bright areas relative to the location areas of other parts in the rim image, which are relatively dark areas. Thus, during the metallurgical process, the position of the tank opening is earliest bright and finally darkly compared with the position of other parts of the tank opening edge as can be seen from the image change of the tank opening edge of the metallurgical tank acquired in real time.
Based on the above analysis characteristics of the tank opening, the invention provides a method for detecting the tank opening of a metallurgical tank, as shown in a tank opening detection flow chart provided by the method according to the invention shown in fig. 1, the method mainly comprises the following steps:
step S1: and acquiring an image of the edge of the mouth of the metallurgical tank.
Metallurgical tanks are devices used in metallurgical processes for collecting and transporting molten metal, such as hot metal tanks, etc. Specifically, the can opening edge image can be acquired through an image acquisition device, and the image acquisition device can be a high-precision camera device, such as an infrared camera or a thermal imager. The image acquisition device is fixedly arranged above the metallurgical tank so as to ensure that the edge of the metallurgical tank can be fully acquired by the image acquisition device. The image acquisition device acquires the tank opening edge image in real time according to a preset frequency and transmits the image to the industrial personal computer through a signal transmission module such as Ethernet.
A simplified schematic of the rim image of the mouth is shown in fig. 2, fig. 2 only showing the mouth rim portion of the metallurgical vessel in the rim image of the mouth, while the high Wen Gaoliang metal liquid located in the metallurgical vessel is not shown. As shown in fig. 2, 11 is the rim of the opening, 111 is the gap, 112 is the inner wall (the wall in contact with the molten metal) of the metallurgical vessel, 113 is the outer wall of the metallurgical vessel, and it is apparent that the inner wall surface 112 of the location area of the gap 111 is lower than the inner wall surface of the other portion of the rim 11 except for the gap, so that the molten metal in the metallurgical vessel will first appear at the inner wall 112 surface of the location area of the gap 111 and disappear from there at the latest when the molten metal is transferred into the metallurgical vessel. Therefore, in the can edge image acquired in real time, the area of the notch 111 is first bright and finally dark, so the number of bright spots in the area of the notch 111 should be the largest relative to other positions, and the duration of the bright spots should be the longest.
In addition, since the temperature of the metal liquid in the metallurgical tank is very high during the metallurgical process, for example, the temperature of molten iron is up to 1270-1350 ℃, the image acquisition device can be externally provided with a cooling protection device to protect the image acquisition device when acquiring the tank opening edge image during the metallurgical process through the image acquisition device.
Step S2: and identifying the tank mouth edge point of the metallurgical tank from the tank mouth edge image.
The method comprises the steps of dividing a fixed area containing the can edge into an identification area at an imaging position in the can edge image, and identifying the can edge point in the identification area. Specifically, the step of identifying the edge point of the can opening is as follows: and traversing pixel points in the identification area vertically, taking two adjacent pixel points as judging reference points, wherein the upper pixel point in the two adjacent pixel points is called an upper pixel point, the lower pixel point in the two adjacent pixel points is called a lower pixel point, and judging the upper pixel point as the tank edge point when the gray value of the upper pixel point is not less than a preset tank edge gray threshold value and the gray value of the lower pixel point is less than the tank edge gray threshold value, and acquiring and storing the position information (such as coordinate position) of the tank edge point.
Step S3: and dividing an analysis area according to the edge points of the edge tank opening.
Specifically, fig. 3 is a schematic structural diagram of the analysis region, and the step of defining the analysis region may further include:
step S31: and fitting a can mouth edge curve Ls according to the can mouth edge points.
Specifically, the quadratic function arc fitting may be fitted by least squares, specifically using least squares to fit the quadratic function f (x) =ax 2 And +bx+c, and solving the values of a, b and c according to the coordinates of the tank opening edge points, so as to fit and obtain an arc tank opening edge curve Ls.
Step S32: the can end edge curve Ls is shifted by a first preset distance in the direction from the inner wall 112 to the outer wall 113 to obtain a first extension curve Le1, wherein the first preset distance is set according to the fact that the first extension curve Le1 does not exceed the can end edge.
Step S33: translating the tank opening edge curve Ls towards the direction from the inner wall 112 to the outer wall 113 by a second preset distance to obtain a second expansion curve Le2, and demarcating the area between the first expansion curve Le1 and the second expansion curve Le2 as the analysis area, wherein the setting of the second preset distance is set according to the fluctuation interference condition of the metal liquid at the tank opening edge of the metallurgical tank so as to ensure that the analysis area is not influenced by the fluctuation interference.
The time sequence for obtaining the first extension curve Le1 and the second extension curve Le2 may not be limited.
And S4, dividing the analysis area into a plurality of analysis unit areas.
As shown in fig. 4, which is a schematic structural diagram of the analysis unit area division, the specific steps of dividing the analysis area into a plurality of analysis unit areas may include:
step S41, dividing the can edge curve equally according to the length to obtain each first division point on the can edge curve, such as a round dot Ja on the can edge curve Ls in FIG. 4. For simplicity of drawing, only one first division point Ja is labeled in fig. 4.
Step S42: and respectively making a shortest distance straight line to the first expansion curve Le1 by each first partition point Ja, and extending each shortest distance straight line to at least the second expansion curve Le2 to obtain each extended shortest distance straight line Ld. The intersection point of each extended shortest distance straight line Ld and the first extension curve Le1, for example, the triangle point Jb in fig. 4 is each second division point on the first extension curve Le 1. The intersection point of each extended shortest distance straight line Ld and the second extension curve Le2, such as the star point Jc in fig. 4, is each third division point on the second extension curve Le 2. For simplicity of drawing, only one second division point Jb and one corresponding third division point Jc are labeled in fig. 4.
Step S43: and taking the analysis area between two adjacent extended shortest distance straight lines Ld as one analysis unit area.
It should be noted that, when the first dividing point Ja is set, setting needs to be performed according to the position of the opening, so that the finally divided analysis unit area at least includes a part of the tank opening position area.
And S5, calculating the duration time when the number of the bright spots in each analysis unit area is larger than a preset number threshold value and the number percentage of the bright spots.
Specifically, the change of the number of the bright spots in each analysis unit area is sequentially calculated, when the number of the bright spots in the analysis unit area currently being calculated exceeds 20% of the total number of the points in the preset number threshold analysis unit area, timing is started, and timing is stopped until the calculation action of the analysis unit area currently being calculated is ended, so that the duration time is obtained. Furthermore, before calculating the change in the number of bright spots, it is also necessary to judge the bright spots in each of the analysis unit areas. Specifically, the gray value of each pixel in the analysis unit area can be compared with a preset brightness threshold to determine which pixels are bright spots, and when the gray value of the pixel currently being compared is greater than the preset brightness threshold, the pixel currently being compared is determined to be one bright spot, wherein the preset brightness threshold is obtained by performing image dynamic threshold segmentation calculation in the analysis area. Wherein the preset number value is set according to the total number of pixel points in the analysis unit area so that the number of bright points in the analysis unit area exceeds 20% or more of the total number of bright points in the analysis unit area.
In addition, calculating the change of the number of the bright spots in each analysis unit area further comprises further calculating the total number of the bright spots in the analysis unit area and the average number of the bright spots calculated for a plurality of times when the calculated number of the bright spots in a certain analysis unit area exceeds the preset number threshold, and comparing the total number of the bright spots in the analysis unit area with the total number of the pixel spots in the analysis unit area to obtain the bright spot percentage of the analysis unit area.
Step S6: comparing the duration of each of the analysis unit areas with the bright point quantity percentage. And obtaining an analysis unit area with the maximum duration time and the maximum number percentage of the bright spots after each comparison operation, and taking the analysis unit area as a position area of the undetermined opening.
Step S7: and (3) circularly executing the steps S5 to S6 for a plurality of times, and judging the analysis unit area with the longest duration and the largest number percentage of the bright spots as the area where the notch is located.
Since it is difficult to truly determine the position of the opening by one calculation and comparison, it is necessary to perform steps S5 to S6 a plurality of times to obtain a plurality of calculations and comparisons, so that it is possible to determine that the analysis unit region where the duration is longest and the number of bright spots is greatest is determined as the region where the opening is located. For example, after the calculation and comparison are performed five times, if the duration and the bright point percentage in the i-th analysis unit area of the plurality of analysis unit areas are each maximum four times in succession, it may be determined that the i-th analysis unit area is the area where the notch is located. And the position information of the notch can be further obtained by obtaining the position information of the ith analysis unit area. Specifically, four vertexes of each analysis unit area may be two adjacent second division points Jb and two corresponding third division points Jc, and coordinates of the four vertexes may be obtained by corresponding coordinates of the first division points and the edge curve Lc, so that position information of the opening may be obtained according to the coordinate calculation of the four vertexes.
Furthermore, the invention also provides a system for detecting the opening, which is realized by the method for detecting the opening, and specifically comprises the following steps: the system comprises an image acquisition module, a signal transmission module and an image processing module. The image acquisition module includes an image acquisition device in step S1, and the signal transmission module is, for example, an ethernet in step S1, configured to transmit the acquired can edge image to the image processing module, where the image processing module may be an image processing algorithm running in the industrial personal computer, and may specifically include: the device comprises an edge point identification module, an analysis area demarcation module, an analysis area segmentation module and a calculation and processing module. The edge point identification module is used for identifying a tank opening edge point of the metallurgical tank from the tank opening edge image and storing position coordinate information of the tank opening edge point, the analysis area demarcation module is used for demarcating an analysis area below the tank opening edge according to the tank opening edge point, the analysis area comprises a position area where the opening is located, the analysis area segmentation module is used for dividing the analysis area into a plurality of analysis unit areas, and the calculation and processing module is used for executing the following instructions:
calculating duration time when the number of bright spots in each analysis unit area is larger than a first threshold value and the percentage of the number of the bright spots, wherein the bright spots are pixel spots with gray values larger than a second threshold value;
comparing the duration of each of the analysis cell areas with the bright spot quantity percentage;
and sequentially executing the calculating step and the comparing step for a plurality of times, and judging the analysis unit area with the longest duration and the largest number percentage of the bright spots as the area where the notch is positioned.
Furthermore, since the metal liquid in the metallurgical tank has a very high temperature in the metallurgical process, the detection system may further comprise a cooling protection module, such as a cooling protection device arranged outside the image acquisition device.
In the method and the system for detecting the mouth of the metallurgical tank, provided by the invention, the image acquisition module is used for acquiring the mouth edge image of the metallurgical tank in the metallurgical process in real time, and then the image processing module is used for analyzing and processing the mouth edge image so as to detect the position area of the opening of the metallurgical tank, thereby determining the optimal endpoint of slag-removing path planning in the slag-removing process, improving the slag-removing efficiency and reducing the loss of metal liquid in the slag-removing process. The position of the notch is judged through multiple times of calculation and comparison, and the judgment accuracy is high.
Embodiments in accordance with the present invention, as described above, are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention and various modifications as are suited to the particular use contemplated. The invention is limited only by the claims and the full scope and equivalents thereof.

Claims (10)

1. A method for detecting a gap in a metallurgical vessel, comprising:
step S1, acquiring a changed tank opening edge image of the metallurgical tank in the metallurgical process in real time,
step S2, identifying the edge point of the tank opening of the metallurgical tank from the image of the edge of the tank opening,
step S3, an analysis area is defined according to the edge points of the edge tank opening,
step S4, dividing the analysis area into a plurality of analysis unit areas,
step S5, calculating the duration time that the number of the bright spots in each analysis unit area is larger than a first threshold value and the percentage of the number of the bright spots, wherein the bright spots are pixel spots with gray values larger than a second threshold value,
step S6 of comparing said duration of each of said analysis unit areas with said percentage of the number of bright spots,
step S7: and (5) circularly executing the steps S5 to S6 for a plurality of times, and judging the analysis unit area with the longest continuous occurrence duration and the largest number percentage of the bright spots as the area where the notch is located.
2. The method of detecting a notch according to claim 1, wherein the step S2 includes:
defining an identification area in the can rim image according to the imaging position of the can rim in the can rim image,
vertically traversing the pixel points in the identification area, taking two adjacent pixel points as judgment base points,
and when the gray value of the upper pixel point of the two adjacent pixel points is not smaller than a third threshold value and the gray value of the lower pixel point of the two adjacent pixel points is smaller than the third threshold value, acquiring the upper pixel point of the two adjacent pixel points as the tank opening edge point.
3. The method of detecting a notch according to claim 1, wherein the step S3 includes:
fitting a can rim curve according to the recognized can rim point, translating the can rim curve toward the direction of the inner wall of the can rim toward the outer wall of the can rim by a first distance and a second distance respectively to obtain a first expansion curve and a second expansion curve respectively,
the area between the first extension curve and the second extension curve is defined as the analysis area.
4. A method of detecting a gap as claimed in claim 3, wherein said step S4 comprises:
dividing the tank opening edge curve equally according to the length to obtain each first dividing point on the tank opening edge curve,
making the shortest distance straight line to the first expansion curve by the first dividing points, and extending the shortest distance straight line to at least the second expansion curve,
and taking the analysis area between two adjacent shortest distance straight lines in the shortest distance straight lines extending respectively as one analysis unit area.
5. The method of detecting a notch according to claim 1, wherein the step S5 includes:
sequentially calculating the change of the number of the bright spots in each analysis unit area, starting timing when the number of the bright spots in the analysis unit area currently subjected to the calculation exceeds the first threshold value, and stopping timing until the calculation action of the analysis unit area currently subjected to the calculation is finished, thereby obtaining the duration.
6. The method of claim 5, wherein the percentage of the number of bright spots is a percentage of the total number of bright spots in the corresponding analysis unit area to the total number of pixels.
7. The method according to claim 1, wherein after the steps S1 to S6 are sequentially performed five times, the analysis unit area having the longest duration and the largest number percentage of bright spots is determined as the area where the notch is located.
8. A method of detecting a gap as claimed in claim 3 wherein the tank opening edge points are fitted to the tank opening edge curve using a least squares method.
9. A metallurgical tank breach detection system comprising: an image acquisition module, a signal transmission module and an image processing module,
the image acquisition module is fixedly arranged at a preset position above the tank opening of the metallurgical tank to acquire the changed tank opening edge image of the metallurgical tank in the metallurgical process in real time,
the signal transmission module transmits the tank opening edge image to the image processing module,
wherein the image processing module comprises an edge point identification module, an analysis area demarcation module, an analysis area segmentation module and a calculation and processing module,
the edge point identification module is used for identifying the edge point of the tank opening of the metallurgical tank from the tank opening edge image and storing the position coordinate information of the edge point of the tank opening,
the analysis zone defining module defines an analysis zone below the edge of the tank opening according to the edge point of the tank opening, the analysis zone comprises a position area where the opening is positioned,
the analysis area dividing module is used for dividing the analysis area into a plurality of analysis unit areas,
the computing and processing module is respectively used for executing the following instructions:
calculating the duration time when the number of the bright spots in each analysis unit area is larger than a first threshold value and the percentage of the number of the bright spots, wherein the bright spots are pixel spots with gray values larger than a second threshold value,
comparing the duration of each of the analysis unit areas with the bright spot number percentage,
and sequentially executing the calculating step and the comparing step for a plurality of times, and judging the analysis unit area with the longest duration and the largest number percentage of the bright spots as the area where the notch is positioned.
10. The breach detection system of claim 9, further comprising a cooling protection module for protecting said image acquisition module.
CN202010384588.0A 2020-05-08 2020-05-08 Method and system for detecting opening of metallurgical tank Active CN111583231B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010384588.0A CN111583231B (en) 2020-05-08 2020-05-08 Method and system for detecting opening of metallurgical tank

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010384588.0A CN111583231B (en) 2020-05-08 2020-05-08 Method and system for detecting opening of metallurgical tank

Publications (2)

Publication Number Publication Date
CN111583231A CN111583231A (en) 2020-08-25
CN111583231B true CN111583231B (en) 2023-06-13

Family

ID=72112063

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010384588.0A Active CN111583231B (en) 2020-05-08 2020-05-08 Method and system for detecting opening of metallurgical tank

Country Status (1)

Country Link
CN (1) CN111583231B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5629706A (en) * 1993-02-03 1997-05-13 Baaaath; Lars Method for simultaneously measuring the positions of more than one surface in metallurgic processes
US6197086B1 (en) * 1997-11-13 2001-03-06 Bethlehem Steel Corporation System and method for minimizing slag carryover during the production of steel
CN108389179A (en) * 2018-01-15 2018-08-10 湖南大学 A kind of cover detection method of surface flaw based on machine vision
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

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5629706A (en) * 1993-02-03 1997-05-13 Baaaath; Lars Method for simultaneously measuring the positions of more than one surface in metallurgic processes
US6197086B1 (en) * 1997-11-13 2001-03-06 Bethlehem Steel Corporation System and method for minimizing slag carryover during the production of steel
CN108389179A (en) * 2018-01-15 2018-08-10 湖南大学 A kind of cover detection method of surface flaw based on machine vision
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

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Marcella Grosso,Clara J. Pacheco.Eddy current and inspection of coatings for storage tanks.J MATER RES TECHNOL.2018,356-360. *
仇进，梁少林，字发国.铁合金冶炼渣罐的改进应用.第23届全国铁合金学术研讨会论文集.2014,486-489. *
肖海忠，武文秀.金川11 m3 钢渣罐的设计开发与制造.包钢科技.2018,第44卷(第44期),67-70. *

Also Published As

Publication number Publication date
CN111583231A (en) 2020-08-25

Similar Documents

Publication Publication Date Title
Li et al. A local annular contrast based real-time inspection algorithm for steel bar surface defects
JP6414102B2 (en) Refining furnace discharge flow determination apparatus, refining furnace discharge flow determination method, and molten metal refining method
CN105160683B (en) A kind of molten iron drossing measurement and control system and its method based on manual intervention
CN105562643B (en) A kind of Crystallizer bleed-out processing method
WO2021208324A1 (en) Image-based temperature measurement and sampling gun placing position intelligent detection method and system
EP3118612A1 (en) Steel-pipe surface inspection method, surface inspection device, manufacturing system, defect generation-location specifying method, and manufacturing method
CN107730521B (en) Method for rapidly detecting ridge type edge in image
CN110747306A (en) Method, device and equipment for controlling slag overflow in converter tapping process and storage medium
CN111583231B (en) Method and system for detecting opening of metallurgical tank
CN110751669A (en) Novel CBOCP online infrared converter tapping steel flow automatic detection and tracking method and system
CN112200823A (en) Hot-rolled plate blank head warping characteristic detection method based on machine vision
CN110918973B (en) Crystallizer thermal image abnormal region marking method based on run
EP1018633A2 (en) Bar angle measurement system
JP5482615B2 (en) Blowing control method in converter
JP2010051997A (en) Spot welding gun management apparatus
JP5959319B2 (en) Symbol identification method and symbol identification device
CN110310239B (en) Image processing method for eliminating illumination influence based on characteristic value fitting
JP6052238B2 (en) Correction method and determination method of time-series two-dimensional distribution data
CN112361985B (en) Machine vision-based blank curvature detection method
RU2722957C1 (en) Method of controlling process of high-frequency welding of pipes and device for implementation thereof
CN113112427A (en) Method, device and equipment for monitoring molten iron transportation and storage medium
CN113781506A (en) Strip steel offset detection method and system
CN111079735A (en) Method and device for recognizing end face characters of casting blank
JP6010972B2 (en) Metal adhesion measurement method and metal adhesion measurement device
JP2941511B2 (en) Method for detecting boil in mold

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