CN103571994B - Infrared steel slag detection method of converter - Google Patents
Infrared steel slag detection method of converter Download PDFInfo
- Publication number
- CN103571994B CN103571994B CN201210270634.XA CN201210270634A CN103571994B CN 103571994 B CN103571994 B CN 103571994B CN 201210270634 A CN201210270634 A CN 201210270634A CN 103571994 B CN103571994 B CN 103571994B
- Authority
- CN
- China
- Prior art keywords
- slag
- converter
- steel
- infrared
- image
- 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
Landscapes
- Carbon Steel Or Casting Steel Manufacturing (AREA)
Abstract
The invention discloses an infrared steel slag detection method of a converter. The infrared steel slag detection method comprises the following steps: a first step of putting an infrared steel slag detection device of the converter into working after detecting a steel tapping starting signal in a production process of the converter; a second step of measuring a converter image in real time through an infrared camera after the device is put into working, and processing the image via an industrial computer, wherein the processing steps comprises the specific steps of dividing the image which contains steel slag, molten steel and background; processing an image pixel by using a histogram technology, finding a suitable threshold value and dividing the steel slag and the molten steel by using the threshold value; subsequently, calculating a steel slag percent content which is a percentage of a steel slag area in a steel flow area, wherein corresponding to a digital image, the steel slag area is a sum of steel slag pixels, and the steel flow area is a sum of steel flow pixels; and a third step of judging whether exceeding a set steel slag alarm limit value according to the steel slag percent content, and outputting an alarm signal and stopping pouring if exceeding the limit value.
Description
Technical field
The present invention relates to a kind of bessemer furnace slag detection method.
Background technology
In STEELMAKING PRODUCTION, from ladle, flow out the quality of excessive slag on steel has bad impact.Too much slag can reduce the purity of steel, accelerates the erosion of resistance to material, reduces the work-ing life of equipment.In order to improve the quality of molten steel, fall in the process of molten steel in converter, operator need to observe the changing conditions of molten steel always, when the molten steel brightness of pouring out increases, prove to occur slag.Adopt different process for making, environmental aspect is around different, except the molten steel of fusing, also can produce a large amount of suspensions and flue gas.In this case, the naked eyes of operator are just difficult to, accurately according to the change of molten steel brightness, judge the appearance of slag, even under clean environment, also only have the experienced operator of minority to be separated the brightness region of molten steel and slag exactly.Therefore, this process is decided by the skills and experience of operator to a great extent.
Through retrieval analysis, the domestic and international relevant report for converter molten steel Lower proterozoic group mainly describes relevant device use experience at the scene and effect at present, and the method and apparatus about bessemer furnace slag detection does not have relevant report.
Summary of the invention
The object of the present invention is to provide the infrared slag detection method of a kind of converter, the method can realize measuring the slag situation in converter tapping process.
For achieving the above object, present invention employs following technical scheme:
The infrared slag detection method of a kind of converter,
The first step, by the tapping commencing signal in monitoring converter production process, if this signal do not detected, represent that converter does not also start cast, the infrared slag means of detection of converter keeps waiting status; After this signal being detected, represent that converter starts tapping, the infrared slag means of detection of converter is devoted oneself to work;
The infrared slag means of detection of described converter comprises infrared CCD camera, light end emitter, optical cable, light end receiving apparatus, central control cabinet; Infrared CCD camera is the thermal imaging system for detecting converter ir radiation, infrared CCD camera exports electrical signal and converts the electrical signal to optical signal by light end emitter, again by optical cable transmission to light end receiving apparatus, then input to central control cabinet after converting electrical signal to; Described central control cabinet comprises industrial computer, image pick-up card, data collecting card and control card, image pick-up card gathers infrared image, data collecting card collecting temperature, industrial computer carries out identification to slag after processing the data that image pick-up card and data collecting card input and judges, is exported control outside execution unit by control card;
Second step, after the infrared slag means of detection of converter is devoted oneself to work, infrared CCD camera measures converter image in real time, and industrial computer processes image, and its treatment step is:
2.1 Image process
Three kinds of objects are comprised: slag, molten steel and background in the image collected, histogram technology is adopted to process to the pixel of image, find suitable threshold value, slag and molten steel is divided by this threshold value, interior of articles and outside plurality point of destination is corresponded to histogram two spikes of the obvious image of background contrast, two peak-to-peak paddy to correspond near object edge relatively minority point of destination, can utilize gray threshold
t 1 the area of object is calculated:
Wherein:
tbe threshold value, namely paddy is low;
dit is gray level;
In above formula
dalong
tarrive
∞integration can obtain two threshold values, the threshold value of background and steel stream
t 1 ; The threshold value of slag and molten steel
t 2 ;
Definition set:
for slag pixel subset;
for molten steel pixel subset;
for the steel stream set of pixels collected;
for background pixel collection;
it is the set of pixels of a two field picture;
First, in the set of pixels intersection of the image collected, background and steel stream two subsets are marked off:
Secondly, from steel adfluxion is closed, slag and molten steel two subsets are marked off:
2.2 slag degrees calculate
Slag degree is exactly the per-cent that slag area accounts for steel flow area in steel flow area, and corresponding to digital picture, slag area is exactly slag pixel count summation, and steel flow area is exactly steel stream pixel count summation;
Close in steel adfluxion
middle sum of all pixels is
q; In slag set
middle sum of all pixels is
m, in molten steel set
middle sum of all pixels is
n, closed by steel adfluxion and define:
obtain:
；
Definition slag degree is
:
After being partitioned into slag subset, molten steel subset, count sum of all pixels in slag subset respectively
mwith sum of all pixels in molten steel subset
n, substitute into above formula calculating and just obtain slag degree;
3rd step, the slag alarm limits exceeding setting is judged whether according to slag degree value, after slag content exceedes alarm limits, industrial computer output alarm signal is also exported by control card and controls execution unit and stop cast, enters the first step and continues to wait for that converter is opened and water signal; When slag content does not exceed alarm limits, continue according to second step work.
Molten steel and slag, by Real-time Collection converter infrared image, are separated by the method for Iamge Segmentation by the present invention from image background, then know by statistics the calculating that method for distinguishing realizes slag degree, finally realize the detection to slag.Method of the present invention is verified through onsite application, and its accuracy of detection is high, and slag recognition accuracy reaches 99%, reliable.
Accompanying drawing explanation
Fig. 1 is converter of the present invention infrared slag means of detection structural representation;
Fig. 2 is converter of the present invention infrared slag detection method schema;
Fig. 3 is converter infrared image original graph;
Fig. 4 is the binary map that converter infrared image isolates molten steel;
Fig. 5 is the binary map that converter infrared image isolates slag;
In figure: 1 infrared CCD camera, 2 light end emitter, 3 optical cables, 4 light end receiving apparatuss, 5 central control cabinets; 5-1 industrial computer, 5-2 image pick-up card, 5-3 data collecting card, 5-4 control card.
Embodiment
Below in conjunction with the drawings and specific embodiments, the invention will be further described.
See Fig. 1, the infrared slag means of detection of a kind of converter, comprises infrared CCD camera 1, light end emitter 2, optical cable 3, light end receiving apparatus 4, central control cabinet 5; Described infrared CCD camera 1 is the thermal imaging system for detecting converter ir radiation, and its Main Function is that ir radiation converter sent is converted to electrical signal through probe unit.
Described infrared CCD camera 1 exports electrical signal and converts the electrical signal to optical signal by light end emitter 2, then is transferred to light end receiving apparatus 4 by optical cable 3, then inputs to central control cabinet 5 after converting electrical signal to.Light end emitter 2, optical cable 3 and light end receiving apparatus 4 are a kind of photoelectric signal transformation and transmitting device.Because the interfering source at converter producing scene is a lot, effectively can eliminate on-the-spot interference so converter picture signal is converted to optical signal to transmit, improve the stability of signal.
Described central control cabinet 5 comprises industrial computer 5-1, image pick-up card 5-2, data collecting card 5-3 and control card 5-4, image pick-up card 5-2 gathers infrared image, data collecting card 5-3 collecting temperature, carry out identification to slag after industrial computer 5-1 processes the data that image pick-up card 5-2 and data collecting card 5-3 inputs to judge, output alarm signal, and export the outside execution unit of control by control card 5-4.
The infrared slag detection method of a kind of converter, converter infrared slag means of detection basis is carried out, the steps include: see Fig. 2,
The first step, by the tapping commencing signal in monitoring converter production process, if this signal do not detected, represent that converter does not also start cast, the infrared slag means of detection of converter keeps waiting status; After this signal being detected, represent that converter starts tapping, the infrared slag means of detection of converter is devoted oneself to work;
Second step, after the infrared slag means of detection of converter is devoted oneself to work, infrared CCD camera 1 measures converter image in real time, and industrial computer 5-1 processes image, and adopt the method for statistical-simulation spectrometry to carry out, its treatment step is:
2.1 Image process
Detect each object in this step, and their image is separated with all the other scenery.Three kinds of objects are comprised: slag, molten steel and background in the image collected, slag because radiant ratio is different, has stronger contrast gradient from molten steel, but the edge of slag and molten steel image is not precipitous, therefore, the boundary alignment overall dimensions chosen extracting object of gray threshold has a great impact.Adopt histogram technology to process to the pixel of image, suitable threshold value can be found, divide slag and molten steel by this threshold value.Correspond to interior of articles and outside plurality point of destination with histogram two spikes of the obvious image of background contrast, two peak-to-peak paddy to correspond near object edge relatively minority point of destination, can utilize gray threshold
tthe area of object is calculated:
Wherein:
tbe threshold value, namely paddy is low;
dit is gray level;
The threshold value corresponding to histogram the lowest point can be found from calculation result above, this threshold value from
tbe increased to
time, the area calculated only has minimizing slightly.Find suitable threshold value
tafter, just can use threshold value
tdivide slag and molten steel.In above formula
dalong
tarrive
∞integration can obtain two threshold values, the threshold value of background and steel stream
t 1 ; The threshold value of slag and molten steel
t 2 .
Definition set:
for slag pixel subset;
for molten steel pixel subset;
for the steel stream set of pixels collected;
for background pixel collection;
it is the set of pixels of a two field picture;
First, in the pixel set I of the image collected, background pixel set B and steel stream pixel set M two subsets are marked off:
Secondly, from steel adfluxion is closed, slag and molten steel two subsets are marked off:
2.2 slag degrees calculate
Slag degree is exactly the per-cent that slag area accounts for steel flow area in steel flow area, and corresponding to digital picture, slag area is exactly slag pixel count summation, and steel flow area is exactly steel stream pixel count summation;
Close in steel adfluxion
middle sum of all pixels is
q; In slag set
middle sum of all pixels is
m, in molten steel set
middle sum of all pixels is
n, closed by steel adfluxion and define:
middle sum of all pixels is
obtain:
；
Definition slag degree is
:
After being partitioned into slag subset, molten steel subset, count sum of all pixels in slag subset respectively
mwith sum of all pixels in molten steel subset
n, substitute into above formula calculating and just obtain slag degree.
3rd step, the slag alarm limits exceeding setting is judged whether according to slag degree value, after slag content exceedes alarm limits, industrial computer 5-1 output alarm signal is also exported by control card 5-4 and controls execution unit and stop cast, enters the first step and continues to wait for that converter is opened and watered signal; When slag content does not exceed alarm limits, continue according to second step work.
After the infrared slag means of detection of converter puts into operation, the limit value (i.e. slag alarm limits) of slag degree is a variable, and it is determined according to technological process needs by process engineer.
Embodiment
The infrared slag detection method of a kind of converter, the infrared slag means of detection of converter is formed sees Fig. 1.
The first step, after the infrared slag means of detection of converter runs and starts, central control cabinet passes through data collecting card, tapping commencing signal in continuous detection converter production process, if this signal do not detected, represent that converter does not also start cast, central control cabinet sends instruction, make the infrared slag means of detection of converter keep waiting status, continue to detect tapping commencing signal; After this signal being detected, represent that converter starts tapping, central control cabinet sends instruction, the infrared slag means of detection of converter is started, enters second step work.
Second step, after the infrared slag means of detection of converter is devoted oneself to work, first by image pick-up card, gather the steel flow infrared image flowed out from converter, obtain the infrared original image of converter as shown in Figure 3, after obtaining view data, by the method for Iamge Segmentation, separating background image from original image, extract the bianry image comprising molten steel, as shown in Figure 4, white is molten steel region, so just can know molten steel regional location in the picture; Use the same method the bianry image extracting from original image and comprise slag, as shown in Figure 5.
After obtaining molten steel and slag region respectively, realized the calculating of slag degree by statistical computation area separately, the area of molten steel and slag is that the quantity by calculating respective pixel realizes, and closes in steel adfluxion
middle sum of all pixels is
q; In slag set
middle sum of all pixels is
m, in molten steel set
middle sum of all pixels is
n, closed by steel adfluxion and define:
middle sum of all pixels is
obtain:
；
Definition slag degree is
:
Count sum of all pixels in slag subset respectively
mwith sum of all pixels in molten steel subset
n, substitute into above formula calculating and just obtain slag degree.
3rd step, after obtaining slag degree, the slag alarm limit according to the setting of converter producing processing requirement judges whether to overflow.After slag content exceedes alarm limit, converter infrared slag means of detection output alarm also stops cast, enters the first step and continues to wait for that converter is opened and water signal; When slag content does not exceed alarm limit, continue according to second step work.
These are only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention, therefore, all any amendments done within the spirit and principles in the present invention, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (1)
1. the infrared slag detection method of converter, is characterized in that:
The first step, by the tapping commencing signal in monitoring converter production process, if this signal do not detected, represent that converter does not also start cast, the infrared slag means of detection of converter keeps waiting status; After this signal being detected, represent that converter starts tapping, the infrared slag means of detection of converter is devoted oneself to work;
The infrared slag means of detection of described converter comprises infrared CCD camera (1), light end emitter (2), optical cable (3), light end receiving apparatus (4), central control cabinet (5); Infrared CCD camera (1) is the thermal imaging system for detecting converter ir radiation, infrared CCD camera (1) exports electrical signal and converts the electrical signal to optical signal by light end emitter (2), be transferred to light end receiving apparatus (4) by optical cable (3) again, then after converting electrical signal to, input to central control cabinet (5); Described central control cabinet (5) comprises industrial computer (5-1), image pick-up card (5-2), data collecting card (5-3) and control card (5-4), image pick-up card (5-2) gathers infrared image, data collecting card (5-3) collecting temperature, carry out identification to slag after industrial computer (5-1) processes the data that image pick-up card (5-2) and data collecting card (5-3) input to judge, exported by control card (5-4) and control outside execution unit;
Second step, after the infrared slag means of detection of converter is devoted oneself to work, infrared CCD camera (1) measures converter image in real time, and industrial computer (5-1) processes image, and its treatment step is:
2.1 Image process
Three kinds of objects are comprised: slag, molten steel and background in the image collected, histogram technology is adopted to process to the pixel of image, find suitable threshold value, slag and molten steel is divided by this threshold value, interior of articles and outside plurality point of destination is corresponded to histogram two spikes of the obvious image of background contrast, two peak-to-peak paddy to correspond near object edge relatively minority point of destination, utilize following formula to calculate:
Wherein: T is threshold value, and namely paddy is low; D is gray level;
D in above formula can obtain two threshold values along T to ∞ integration, the threshold value T of background and steel stream
1; The threshold value T of slag and molten steel
2;
Definition set:
S (s
1, s
2..., s
m) be slag pixel subset;
L (l
1, l
2..., l
n) be molten steel pixel subset;
M (m
1, m
2, m
q) steel stream set of pixels for collecting;
B (b
1, b
2..., b
l) be background pixel collection;
I (i
1, i
2... i
x) be the set of pixels of a two field picture;
First, in the set of pixels intersection of the image collected, background and steel stream two subsets are marked off:
Secondly, from steel adfluxion is closed, slag and molten steel two subsets are marked off:
2.2 slag degrees calculate
Slag degree is exactly the per-cent that slag area accounts for steel flow area in steel flow area, and corresponding to digital picture, slag area is exactly slag pixel count summation, and steel flow area is exactly steel stream pixel count summation;
M (m is closed in steel adfluxion
1, m
2, m
q) in sum of all pixels be q; At slag S set (s
1, s
2..., s
m) in sum of all pixels be m, at molten steel set L (l
1, l
2..., l
n) in sum of all pixels be n, by steel adfluxion close define: M (m
1, m
2, m
q) obtain:
q＝n+m；
Definition slag degree is ξ:
After being partitioned into slag subset, molten steel subset, to count in slag subset sum of all pixels n in sum of all pixels m and molten steel subset respectively, substitute into above formula and calculate and just obtain slag degree;
3rd step, the slag alarm limits exceeding setting is judged whether according to slag degree value, after slag content exceedes alarm limits, industrial computer (5-1) output alarm signal is also exported by control card (5-4) and controls execution unit and stop cast, enters the first step and continues to wait for that converter is opened and watered signal; When slag content does not exceed alarm limits, continue according to second step work.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210270634.XA CN103571994B (en) | 2012-08-01 | 2012-08-01 | Infrared steel slag detection method of converter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210270634.XA CN103571994B (en) | 2012-08-01 | 2012-08-01 | Infrared steel slag detection method of converter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103571994A CN103571994A (en) | 2014-02-12 |
| CN103571994B true CN103571994B (en) | 2015-06-17 |
Family
ID=50044702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210270634.XA Active CN103571994B (en) | 2012-08-01 | 2012-08-01 | Infrared steel slag detection method of converter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103571994B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104232837B (en) * | 2014-09-24 | 2016-08-24 | 杭州谱诚泰迪实业有限公司 | A kind of converter/electric furnace steel tapping monitoring device and control method |
| CN105160683B (en) * | 2015-09-29 | 2019-01-15 | 田陆 | A kind of molten iron drossing measurement and control system and its method based on manual intervention |
| CN105353654B (en) * | 2015-09-29 | 2019-02-26 | 田陆 | A kind of molten iron drossing measurement and control system and its method based on image procossing |
| CN105954285A (en) * | 2016-05-23 | 2016-09-21 | 中国石油大学(华东) | Method for fast determining solid contents of catalytic cracking slurry |
| KR102135754B1 (en) * | 2018-08-13 | 2020-07-20 | 주식회사 포스코 | Refining apparatus and method |
| CN112950586A (en) * | 2021-03-02 | 2021-06-11 | 攀钢集团攀枝花钢铁研究院有限公司 | LF furnace steel slag infrared identification method and system |
| CN113881827A (en) * | 2021-09-15 | 2022-01-04 | 北京首钢股份有限公司 | Control method and device for ladle refining furnace |
| CN117636354B (en) * | 2024-01-25 | 2024-04-09 | 内蒙古鑫元硅材料科技有限公司 | Intelligent identification method for silicon slag in silicon water casting process |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201288203Y (en) * | 2008-11-04 | 2009-08-12 | 福建三钢闽光股份有限公司 | Slag discharge detecting device of revolving furnace |
| CN201330260Y (en) * | 2009-01-06 | 2009-10-21 | 冶金自动化研究设计院 | Slag-roughing detection device in converter tapping process based on emissivity factor monitoring |
| CN101818228A (en) * | 2010-03-22 | 2010-09-01 | 马鞍山钢铁股份有限公司 | Control system and control method for tapping and slagging of converter |
| CN102181598A (en) * | 2011-03-04 | 2011-09-14 | 浙江大学 | Prejudgment and control method of tapping and slagging of converter based on thermal image |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60143B2 (en) * | 1976-11-17 | 1985-01-05 | 住友金属工業株式会社 | Molten steel outflow automatic control device and its signal discrimination device |
| JP2003183720A (en) * | 2001-12-20 | 2003-07-03 | Jfe Engineering Kk | Method and device for detecting slag |
-
2012
- 2012-08-01 CN CN201210270634.XA patent/CN103571994B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201288203Y (en) * | 2008-11-04 | 2009-08-12 | 福建三钢闽光股份有限公司 | Slag discharge detecting device of revolving furnace |
| CN201330260Y (en) * | 2009-01-06 | 2009-10-21 | 冶金自动化研究设计院 | Slag-roughing detection device in converter tapping process based on emissivity factor monitoring |
| CN101818228A (en) * | 2010-03-22 | 2010-09-01 | 马鞍山钢铁股份有限公司 | Control system and control method for tapping and slagging of converter |
| CN102181598A (en) * | 2011-03-04 | 2011-09-14 | 浙江大学 | Prejudgment and control method of tapping and slagging of converter based on thermal image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103571994A (en) | 2014-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103571994B (en) | Infrared steel slag detection method of converter | |
| WO2020098299A1 (en) | Method and system for detecting flow rate of high-temperature molten fluid | |
| CN105956618B (en) | Converter steelmaking blowing state identification system and method based on image dynamic and static characteristics | |
| CN101916364B (en) | Adaptive dial digital identification method | |
| CN101907453B (en) | Online measurement method and device of dimensions of massive agricultural products based on machine vision | |
| CN108109137A (en) | The Machine Vision Inspecting System and method of vehicle part | |
| CN107063946A (en) | Video green-ball particle instrument and its green-ball particle diameter condition detection method | |
| CN104331521A (en) | Automatic power transformation equipment abnormity identification method based on image processing | |
| CN110309973B (en) | Converter splash prediction method and system based on video intelligent algorithm | |
| CN101398392A (en) | Cotton impurity high speed real-time detection method based on HSI color space | |
| CN104504707B (en) | A kind of foreign matter occlusion detection method of monitoring camera video pictures | |
| CN111126206B (en) | Smelting state detection system and method based on deep learning | |
| CN102034098A (en) | Automatic bolt sorting system and automatic bolt sorting method | |
| CN108182682A (en) | A kind of detection method based on Computer Image Processing and pattern-recognition | |
| CN110218824A (en) | A kind of blast furnace slag centrifugal granulation droplet measurement system and method based on image recognition | |
| Zhang et al. | Detection method for pulverized coal injection and particles in the tuyere raceway using image processing | |
| CN103177445A (en) | Outdoor tomato identification method based on subsection threshold image segmentation and light spot identification | |
| CN114529839A (en) | Unmanned aerial vehicle routing inspection-oriented power transmission line hardware anomaly detection method and system | |
| CN104392213A (en) | Image information state recognizing system applicable to melting process | |
| CN110751669A (en) | Novel CBOCP online infrared converter tapping steel flow automatic detection and tracking method and system | |
| CN113063474A (en) | Slag liquid level real-time detection method, device, equipment and storage medium | |
| CN101930540A (en) | Video-based multi-feature fusion flame detecting device and method | |
| JP5786803B2 (en) | Blast furnace outlet diameter measuring method, blast furnace outlet diameter measuring system, and computer program | |
| CN206951597U (en) | A kind of Blueberry hierarchical detection system based on machine vision | |
| CN100487437C (en) | Flue gas discharge continuous monitoring system based on image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |