CN107248157A - A kind of aluminium cell sees the method and its device of fire automatically - Google Patents
A kind of aluminium cell sees the method and its device of fire automatically Download PDFInfo
- Publication number
- CN107248157A CN107248157A CN201710526709.9A CN201710526709A CN107248157A CN 107248157 A CN107248157 A CN 107248157A CN 201710526709 A CN201710526709 A CN 201710526709A CN 107248157 A CN107248157 A CN 107248157A
- Authority
- CN
- China
- Prior art keywords
- pinkeye
- mrow
- msub
- gray level
- functional area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 229910052782 aluminium Inorganic materials 0.000 title claims abstract description 48
- 239000004411 aluminium Substances 0.000 title claims abstract description 42
- AZDRQVAHHNSJOQ-UHFFFAOYSA-N alumane Chemical compound [AlH3] AZDRQVAHHNSJOQ-UHFFFAOYSA-N 0.000 title claims abstract description 31
- 208000031973 Conjunctivitis infective Diseases 0.000 claims abstract description 197
- 201000001028 acute contagious conjunctivitis Diseases 0.000 claims abstract description 197
- 239000011159 matrix material Substances 0.000 claims abstract description 47
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims description 21
- 239000003792 electrolyte Substances 0.000 claims description 18
- 238000005259 measurement Methods 0.000 claims description 18
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 claims description 17
- 238000007667 floating Methods 0.000 claims description 16
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 14
- 229910052799 carbon Inorganic materials 0.000 claims description 14
- 239000002893 slag Substances 0.000 claims description 14
- 239000011244 liquid electrolyte Substances 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 239000000463 material Substances 0.000 claims description 10
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 claims description 10
- 238000009529 body temperature measurement Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 3
- 210000004027 cell Anatomy 0.000 description 43
- 230000006870 function Effects 0.000 description 19
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005868 electrolysis reaction Methods 0.000 description 5
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 4
- 238000005273 aeration Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000004861 thermometry Methods 0.000 description 3
- 206010068052 Mosaicism Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 210000003765 sex chromosome Anatomy 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 208000002925 dental caries Diseases 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000010297 mechanical methods and process Methods 0.000 description 1
- 230000005226 mechanical processes and functions Effects 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000000377 silicon dioxide Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0014—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation from gases, flames
- G01J5/0018—Flames, plasma or welding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Plasma & Fusion (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The invention discloses the method and its device that a kind of aluminium cell sees fire automatically, this method includes：Step 1：The pinkeye image of aluminium cell is obtained, and is converted to pinkeye digital picture；Step 2：Pinkeye digital picture is pre-processed；Step 3：Pretreated pinkeye digital picture is converted into pinkeye gray level image, and builds gray level image matrix；Step 4：Functional regional division is carried out to pinkeye gray level image using the multi-threshold segmentation method of gray value according to the gray level image matrix in step 3；Step 5：The pinkeye information index of functional area described in extraction step 4, pinkeye information index is at least one kind in area, temperature or texture eigenvalue；Step 6：Display pinkeye image and pinkeye information see fire automatically to realize.The present invention can get pinkeye picture by the above method, quickly and accurately get the apparent state of pinkeye and implicit information, and realization sees fiery function automatically to aluminium cell.
Description
Technical field
The method and its device of fire are seen automatically the invention belongs to technical field of aluminum electrolysis, more particularly to a kind of aluminium cell.
Background technology
Modern aluminum tank is one and possesses self-healing electrochemical reactor, should blanking discharge (going out aluminium) again, its
Middle electrolytic cell, which can not be subcooled, to be overheated, and its state is vital to energy consumption and production stability.Modern aluminium electroloysis is equal
By the way of point feeding, after crust-breaking chips is fallen, point feeding device blanking, and the crust position meeting that tup is got through
Formed a hole, hole in addition to having fused electrolyte, also anodic gas burning formed flame and dielectric in carbon
The burning point of slag, and then a similar hole burned with anger is formd, it is referred to as in aluminum i ndustry " pinkeye ".
Electrolytic cell is a closed reaction system, wants to learn the state that it is internal, in addition to conventional tank voltage information,
Pinkeye state is a most intuitively information, and veteran electrolysis work can determine the mistake of electrolytic cell from the state of pinkeye
Temperature, groove stability and current efficiency etc..And the pinkeye of electrolytic cell middle part is typically difficult to be directly observed, but in aluminium inlet
Pinkeye then can conveniently observe.Therefore all the time, have judgement of the operative employee of knowhow for many years to being electrolysed slot status most directly perceived
Mode be to be observed by the state to aluminium inlet charge door pinkeye, by observe flame color, electrolyte roll shape
The information such as state, pinkeye size, indirect discrimination groove condition.
This method needs the prolonged experience accumulation of aluminium electroloysis operative employee and various trials, but inevitably exists artificial
Subjectivity, and lack unified standard, it is difficult to promote and study in depth, therefore often there is certain deviation in actual production.
As can be seen here, in aluminum i ndustry circle, currently for the apparent state of pinkeye and implicit information obtaining means still very
Lack, it is main or to be electrolysed based on the experience of workman, it is necessary to provide a kind of method that can obtain pinkeye status information in fact
And device, to judge the state of electrolytic cell exactly.
The content of the invention
Based on the defect in existing mode, the present invention provides the method and its device that a kind of aluminium cell sees fire automatically, can
To get pinkeye picture, and then the apparent state of pinkeye and implicit information are got, realization sees fiery work(automatically to aluminium cell
Can, overcome and judge to obtain the subjective sex chromosome mosaicism that pinkeye state and implicit information are brought by experience in existing mode.
On the one hand, the invention provides a kind of method that aluminium cell sees fire automatically, methods described includes：
Step 1：The pinkeye image of aluminium cell is obtained, and pinkeye image is converted into pinkeye digitized map by converter
Picture；
Step 2：Pinkeye digital picture is pre-processed, pretreatment includes noise reduction and smooth；
Step 3：Pretreated pinkeye digital picture in step 2 is converted into pinkeye gray level image, and builds gray-scale map
As matrix；
Each element correspondence is each pixel in pinkeye gray level image in gray level image matrix, and the value of each element is
The gray value of each pixel；
Step 4：According to the gray level image matrix in step 3 using the multi-threshold segmentation method of gray value to pinkeye gray-scale map
As carrying out functional regional division；
Step 5：The pinkeye information index of functional area in extraction step 4；
Wherein, the pinkeye information index of functional area is at least one kind in area, temperature or texture eigenvalue；
Step 6：Display pinkeye image and pinkeye information see fire automatically to realize.
By shooting pinkeye image and carrying out image analysis processing, the apparent shape of pinkeye can be quickly and accurately got
State and implicit information, and then realize the automatic function of seeing fire.
Preferably, when the pinkeye information index of the functional area described in the step 4 extracted in step 5 is area, function
The extraction process of the area in region is as follows：
The area of each functional area, each function are calculated using roaming gray level image matrix and pixel statistical method
The area in region is equal to the number of all pixels point in corresponding function region；
Wherein, the areal calculation formula of functional area is as follows：
Wherein, Q is expressed as the area of functional area, and W represents the Breadth Maximum of functional area, and H represents functional area most
Big height, (IMG (x, y) represents the element IMG (x, y) of statistics gray level image matrix quantity to Count, and IMG (x, y) represents ash
Xth row, the element of y row spent in image array.
Wherein, after step 4 carries out functional regional division, each functional area is obtained based on conventional images treatment technology
The Breadth Maximum and maximum height of specific scope and each functional area.
Preferably, the pinkeye information index of the functional area described in the step 4 extracted in step 5 is texture eigenvalue,
The extraction process of the texture eigenvalue of functional area is as follows：
Functional area according to gray level image matrix and the pinkeye gray level image divided obtains the gray scale of functional area
Co-occurrence matrix P (g1,g2)；
Wherein, the calculation of gray level co-occurrence matrixes is as follows：
Wherein, P (g1,g2) represent to occur gray value simultaneously for g1And g2When probability constitute gray level co-occurrence matrixes；
S represents the set of pinkeye gray level image, and " # " represents the element number in set, f (x1,y1) represent gray level image square
Xth in battle array1OK, y1The corresponding gray value g of element of row1, f (x2,y2) represent xth in gray level image matrix2OK, y2Row
The corresponding gray value g of element2；
Gray level co-occurrence matrixes P (g according to functional area1,g2) calculate the texture eigenvalue of functional area, textural characteristics
Including at least category feature in entropy, energy, inverse differential square, contrast；
Wherein, entropy f1Calculation formula it is as follows：
Energy f2Calculation formula it is as follows：
Inverse differential is away from f3Calculation formula it is as follows：
Contrast f4Calculation formula it is as follows：
Wherein, M is the maximum gradation value of pixel in the pinkeye gray level image of the functional area, and N is the functional areas
The minimum gradation value of pixel in the pinkeye gray level image in domain.
Preferably, the multi-threshold segmentation method of gray value is used to fire according to the gray level image matrix in step 3 in step 4
Eye gray level image carries out functional regional division, including：
Divided according to multiple threshold values and obtain several intensity value ranges；
Wherein, one intensity value ranges of each functional area correspondence；
Each corresponding gray value of element falls into corresponding grey scale value scope in the gray level image matrix, then is divided to pair
The functional area answered.
Preferably, multiple threshold values are respectively first threshold, Second Threshold and the 3rd threshold value；
Wherein, the magnitude range 40~50 of first threshold, the magnitude range of Second Threshold are the big of the 70~75, the 3rd threshold value
Small range is 144~150.
The threshold range in each region determines to obtain by substantial amounts of live pinkeye IMAQ analysis, is needed in application process
To be demarcated according to the parameter of camera.
Preferably, functional area is divided into：Liquid electrolyte area, flame zone, floating Tan Zha areas and material area；
Multiple threshold values are respectively first threshold, Second Threshold and the 3rd threshold value；
Each functional area and the relation of three threshold values are as follows：
The corresponding intensity value ranges in liquid electrolyte area are more than 0 and less than first threshold；
The corresponding intensity value ranges of flame zone are more than or equal to first threshold and less than Second Threshold；
It is more than or equal to Second Threshold and less than the 3rd threshold value to float the corresponding intensity value ranges in Tan Zha areas；
The corresponding intensity value ranges in material area are more than or equal to the 3rd threshold value and less than 255.
Preferably, after step 4, this method also includes：
Another pinkeye image at neighbouring sample moment is gathered, and another pinkeye figure is obtained according to the operation of step 1- steps 4
The gray value of pixel in Tan Zha areas is floated as in；
The gray scale of same pixel in Tan Zha areas is floated in floating Tan Zha areas in calculation procedure 5 and in another pinkeye image
The difference of value；
The separating degree of carbon slag and electrolyte in pinkeye is obtained according to the difference of the gray value in floating Tan Zha areas.
Wherein, separating degree is good if the difference of gray value is more than 10, gray value difference be between 5~10 if separating degree one
As, less than 5 separating degrees it is poor.
On the other hand, present invention also offers the device that a kind of aluminium cell sees fire automatically, the device includes：IMAQ
Module, image processing module and Subscriber Interface Module SIM, wherein image processing module include pretreatment module, gray level image and built
Module, function division module and measurement module
The measurement module is at least included in temperature measurement module, pinkeye size measurement module, pinkeye textural characteristics module at least
One module；
Wherein, described image acquisition module, the pinkeye image for obtaining aluminium cell aluminium inlet, and process converter will
The pinkeye image is converted to pinkeye digital picture；
Pretreatment module, for being pre-processed to pinkeye digital picture, pretreatment includes noise reduction and smooth；
Gray level image builds module, for pretreated pinkeye digital picture to be converted into pinkeye gray level image, and structure
Build gray level image matrix；
Each element correspondence is each pixel in pinkeye gray level image in gray level image matrix, and the value of each element is
The gray value of each pixel；
Function division module, for using the multi-threshold segmentation method of gray value according to gray level image matrix to pinkeye gray scale
Image carries out functional regional division；
Measurement module, the pinkeye information index for extracting the functional area；
Wherein, the pinkeye information index of the functional area is at least one kind in area, temperature or texture eigenvalue；
Subscriber Interface Module SIM, fire is seen for showing pinkeye image and pinkeye information automatically to realize.
Preferably, the device also includes protection device and support meanss；
Support meanss include pedestal and support arm, and protection device is arranged on support arm, and support arm is rotated around pedestal；
Image capture module is within protection device.
Support arm is rotated around pedestal, is easy to adjust the relative angle between protection device and electrolytic cell, and then be easy to regulation
The acquisition angles of image capture module.
Preferably, the device is arranged at the center line of electrolytic cell aluminium inlet and at 30~50cm of cell vessel.
The present apparatus is arranged at outside the passageway of electrolytic cell, can protect the harvester, extends the service life of the present apparatus,
It is arranged at simultaneously outside electrolytic cell, is easy to be adjusted the present apparatus.
Beneficial effect：
The method that a kind of aluminium cell that the present invention is provided sees fire automatically, by gathering the pinkeye image of aluminium cell, and
Carry out after image analysis processing, functional regional division has been carried out, while also getting the pinkeye information of each functional area, i.e. face
Product, temperature and texture eigenvalue, therefore the apparent state of pinkeye, such as pinkeye figure can be quickly and accurately got by this way
Picture；And get the implicit information of pinkeye, the functional regional division content of such as pinkeye, the area of functional area, temperature, texture
Characteristic value and difference according to neighbouring sample moment gray value, texture eigenvalue obtain carbon slag separating degree, melt flows state it
Category information, and then fiery function is seen in realization automatically, if application sees fire automatically, can obtain the situation letter in abundant electrolytic cell
Breath.
It is to rely on the artificial mode artificially judged in the prior art, and this method can quickly, accurately and economically
The pinkeye image of aluminium cell is sampled and obtained and pinkeye image is handled and analyzed, therefore compared to existing skill
Art, the testing efficiency of this method is higher, and the accuracy of test result is higher, effectively overcomes the subjectivity existed during artificial judgement
Sex chromosome mosaicism.
In addition, present invention correspondence described method provides the automatic device for seeing fire, the device is arranged at the mistake of aluminium cell
Outside road, the service life of the present apparatus can be extended, be convenient for measuring, while being also convenient for being adjusted the present apparatus, such as module
During damage, module can be changed in time.
Furthermore, protection device is provided with the present apparatus, can further extend the service life of modules in the present apparatus,
Protection device can be rotated around support arm simultaneously, and when promoting to carry out pinkeye IMAQ using the present apparatus, image capture module can
To adjust acquisition angles to optimal acquisition angle.
Brief description of the drawings
Fig. 1 is the indicative flowchart for the method that a kind of aluminium cell provided in an embodiment of the present invention sees fire automatically；
Fig. 2 is the schematic diagram of pinkeye image provided in an embodiment of the present invention；
Fig. 3 is the division schematic diagram of the functional area of pinkeye gray level image provided in an embodiment of the present invention；
Fig. 4 is the schematic diagram in floating Tan Zha areas in pinkeye gray level image provided in an embodiment of the present invention；
Fig. 5 is that a kind of aluminium cell provided in an embodiment of the present invention sees schematic diagram when fiery device is measured automatically；
A kind of aluminium cell that Fig. 6 is provided sees the structural representation of fiery device automatically；
Wherein, description of reference numerals is as follows：
1 protection device, 2 support meanss, 3 image capture modules, 4 image processing modules, 5 Subscriber Interface Module SIMs, 21 pedestals,
22 support arms, 11 shells, 12 inner casings, 13 cooling air channels, 14 suprasil pieces, 15 cavitys, 41 pretreatment modules, 42 gray level images
Build module, 43 function division modules, 44 temperature measurement modules, 45 pinkeye size measurement modules, 46 pinkeye textural characteristics modules, 51 knots
Fruit display module, 52 result memory modules, 53 radio interface modules.
Embodiment
The present invention is described further below in conjunction with the drawings and specific embodiments.
As shown in figure 1, the method that a kind of aluminium cell provided in an embodiment of the present invention sees fire automatically, including：
Step 1：The pinkeye image of aluminium cell is obtained, and pinkeye image is converted into pinkeye digitized map by converter
Picture.
As shown in Fig. 2 the pinkeye image of aluminium cell is gathered in the present embodiment by image acquiring sensor.
Step 2：Pinkeye digital picture is pre-processed, pretreatment includes noise reduction and smooth.
Specifically, the cleaning to image, eliminates the influence of sampling noiset.
Step 3：Pretreated pinkeye digital picture in step 2 is converted into pinkeye gray level image, and builds gray-scale map
As matrix；
Each element correspondence is each pixel in pinkeye gray level image in gray level image matrix, and the value of each element is
The gray value of each pixel.
Specifically, building gray level image matrix, IMG (x, y) represents the member that xth row, y in gray level image matrix are arranged
Element, x, y are zero or positive integer.F (x, the y) gray scales for representing element IMG (x, y) in gray level image matrix in the present embodiment
Value.
Step 4：According to the gray level image matrix in step 3 using the multi-threshold segmentation method of gray value to pinkeye gray-scale map
As carrying out functional regional division.
As shown in figure 3, being preferably by functional regional division in the present embodiment：Liquid electrolyte area, flame zone, floating carbon slag
Area and material area, wherein liquid electrolyte area are referred to as fused electrolyte area, and floating Tan Zha areas are referred to as carbon slag
Scum silica frost area.
Using this method can rapidly to gray level image carry out functional regional division, compared in existing mode rely on people
For the mode of judgement, this method it is more efficient, the degree of accuracy of division result is higher.
The multi-threshold segmentation method of gray value is used to pinkeye gray scale according to the gray level image matrix in step 3 in step 4
Image carries out functional regional division, specifically includes：
Divided according to multiple threshold values and obtain several intensity value ranges；
Wherein, one intensity value ranges of each functional area correspondence；
The corresponding gray value of each element falls into corresponding grey scale value scope in gray level image matrix, then is divided to corresponding
Functional area.
Divided in the present embodiment according to three threshold values and obtain four intensity value ranges, wherein, liquid electrolyte area, flame
Area, floating Tan Zha areas and material area correspond to an intensity value ranges respectively.
When functional area includes liquid electrolyte area, flame zone, floating Tan Zha areas and material area in the present embodiment, three
Individual threshold value is respectively first threshold, Second Threshold and the 3rd threshold value, wherein, the relation of each functional area and three threshold values is such as
Shown in lower：
The corresponding intensity value ranges in liquid electrolyte area are more than 0 and less than first threshold；
The corresponding intensity value ranges of flame zone are more than or equal to first threshold and less than Second Threshold；
It is more than or equal to Second Threshold and less than the 3rd threshold value to float the corresponding intensity value ranges in Tan Zha areas；
The corresponding intensity value ranges in material area are more than or equal to the 3rd threshold value and less than 255.
Preferably, the magnitude range 40~50 of first threshold, the magnitude range of Second Threshold are the 70~75, the 3rd threshold value
Magnitude range is 144~150.
Step 5：The pinkeye information index of functional area in extraction step 4；
Wherein, the pinkeye information index of functional area is at least one kind in area, temperature or texture eigenvalue.
Wherein, the pinkeye information index of each functional area is preferably obtained in the present embodiment includes area and temperature and line
Manage characteristic value, in other feasible embodiments, needed according to real data, can measure acquisition to some or certain it is several
The a certain class of functional area or certain classes of pinkeye information index.
Specifically, when the pinkeye information index of functional area in the step 4 extracted in step 5 is area, functional area
Area extraction process it is as follows：
The area of each functional area, each function are calculated using roaming gray level image matrix and pixel statistical method
The area in region is equal to the number of all pixels point in corresponding function region；
Wherein, the areal calculation formula of functional area is as follows：
Wherein, Q is expressed as the area of functional area, and W represents the Breadth Maximum of functional area, and H represents functional area most
Big height, (IMG (x, y) represents the element IMG (x, y) of statistics gray level image matrix quantity to Count, and IMG (x, y) represents ash
Xth row, the element of y row spent in image array, x, y are zero or positive integer.
For example, the area in liquid electrolyte area is the number of pixel in liquid electrolyte area.
It should be appreciated that the size of functional area can reflect the situation of pinkeye, and then reflect the groove condition of electrolytic cell, example
Size such as flame zone reflects aeration, the category information of bath surface tension force, and the wherein degree of superheat is higher, electrolyte meter
Face tension force is small, and aeration is better, and it is more prosperous that flame burns；The degree of superheat is lower, and bath surface tension force is big, and aeration is poorer, causes
Overall gas pressure is big in electrolyte, and pinkeye does not have flame or outside jet flames.
Specifically, when the pinkeye information index of functional area in the step 4 extracted in step 5 is texture eigenvalue, function
The extraction process of the texture eigenvalue in region is as follows：
Step A：Functional area according to gray level image matrix and the pinkeye gray level image divided obtains functional area
Gray level co-occurrence matrixes；And,
Step B：Gray level co-occurrence matrixes P (g according to functional area1,g2) calculate the texture eigenvalue of functional area, line
Managing feature includes at least category feature in entropy, energy, inverse differential square, contrast.
Wherein, the calculation of gray level co-occurrence matrixes is as follows：
Wherein, P (g1,g2) represent to occur gray value simultaneously for g1And g2When probability constitute gray level co-occurrence matrixes；
S represents the set of pinkeye gray level image, and " # " represents the element number in set, f (x1,y1) represent gray level image square
Xth in battle array1OK, y1The corresponding gray value g of element of row1, f (x2,y2) represent xth in gray level image matrix2OK, y2Row
The corresponding gray value g of element2, wherein x1、x2、y1、y2It is zero or positive integer.
It should be noted that being that the gray scale for calculating the functional area for each functional area is total in certain embodiments
S in raw matrix, above-mentioned formula represents the set of the image in pinkeye gray level image in corresponding function region；In other implementations
Can generate a gray level co-occurrence matrixes for whole pinkeye gray level image matrix, S is then expressed as whole in above-mentioned formula in example
The set of individual pinkeye gray level image, then get correspondence work(according to a gray level co-occurrence matrixes and the functional module divided
The gray level co-occurrence matrixes in energy region, then the calculating of texture eigenvalue is carried out, or according to a gray level co-occurrence matrixes and institute
The functional module of division directly carries out the calculating of the texture eigenvalue in corresponding function region.
Wherein, the calculation formula of entropy is as follows：
The calculation formula of energy is as follows：
Inverse differential away from calculation formula it is as follows：
The calculation formula of contrast is as follows：
Wherein, M is the maximum gradation value of pixel in the pinkeye gray level image in corresponding function region, and N is corresponding function area
The minimum gradation value of pixel in the pinkeye gray level image in domain.
It should be noted that entropy is the randomness metrics that image includes information content.When all values are equal in co-occurrence matrix
Or gray value, when showing the randomness of maximum, entropy is maximum；Therefore entropy indicates the complexity of gradation of image distribution, entropy
Value is bigger, and image is more complicated.
Energy is the quadratic sum of gray level co-occurrence matrixes each element value, is the degree to the grey scale change degree of stability of image texture
Amount, has reacted gradation of image and has been evenly distributed degree and texture fineness degree.Energy value shows that greatly current texture is a kind of rule change
Relatively stable texture.
The value that contrast is generally used for metric matrix is that the number with localized variation in image how be distributed, and has reacted image
Definition and texture the rill depth.The rill of texture is deeper, and contrast is bigger, and effect is clear；Conversely, reduced value is small, then ditch
Line is shallow, and effect is obscured.
Inverse differential away from be generally used for reflect image texture homogeney, measurement image texture localized variation number.Its value
Lack change between different zones that are big then illustrating image texture, it is local highly uniform.
Based on above-mentioned entropy, energy, contrast and inverse differential away from characteristic, calculate functional area in the present embodiment above-mentioned
Texture eigenvalue, can also obtain other implicit informations of pinkeye, such as melt flows state.For example using liquid electrolyte area as
Example, if calculating, to obtain its texture eigenvalue as follows：Entropy is 0.51, and energy is 1.07, and inverse differential square is 0.85, and contrast is
0.62, it can determine whether out the knowledge related to groove condition such as melt crust speed is very fast, electrolyte flow characteristicses are preferable based on these values
Differentiate.Similarly, the texture eigenvalue of flame zone, floating Tan Zha areas and material area is calculated, more and electrolytic cell is equally can obtain
The related information of groove condition.
It should be noted that this method is by substantial amounts of experiment, and to obtaining entropy, energy after experimental data progress Treatment Analysis
Amount, contrast and inverse differential away from numerical value and pinkeye each functional area characteristic relation, and then gather the acquisition of pinkeye image
To after above-mentioned texture eigenvalue, the current characteristic of functional area can be rapidly got.
Wherein, when the pinkeye information index of functional area in the step 4 extracted in step 5 is temperature, the temperature of functional area
The extraction process of degree is as follows：
The temperature for obtaining functional area is calculated according to twocolor thermometry.
Wherein, two-color thermometry is also known as two waveband thermometry or double-colored temperature method, is at two according to heat radiation object
The method that functional relation of the ratio between the spectral radiance under wavelength between temperature carrys out measurement temperature, using double-colored signal contrast
Method can preferably eliminate the influence of environment and emissivity, be effectively improved temperature measurement accuracy, rational two work of selection
Wave band can greatly reduce the measurement error because of caused by the change of testee emissivity.
In the present embodiment, in wavelength X1And λ2Under the image N1 and N2 that collect, its actual thermometric formula is：
T is represented：The temperature of measurement；
C2Represent：Computational constant；
λ1、λ2Represent：The melt incident wavelength selected in thermometric；
K is represented：Equipment constant；
R(T,λ1,λ2) represent：The ratio of gradation of image, can be by being calibrated with thermocouple.
Step 6：Display pinkeye image and pinkeye information see fire automatically to realize.
Wherein pinkeye information at least includes pinkeye information index, the division content of functional area.
Specifically, quickly and accurately getting the apparent state of pinkeye and implicit information by the above method, it is easy to more
Quickly and accurately judge to be electrolysed slot status.
Compared to such scheme, in order to obtain more pinkeye information, further, after step 4, this method is also wrapped
Include：
Another pinkeye image at neighbouring sample moment is gathered, and another pinkeye figure is obtained according to the operation of step 1- steps 4
As in functional area pixel gray value；
With the gray scale of same pixel in same functional area in another pinkeye image in functional area in calculation procedure 5
The difference of value；
The gray-value variation trend of functional area in pinkeye is obtained according to the difference of gray value.
Specifically, exemplified by floating Tan Zha areas, if getting the gray value in the floating Tan Zha areas at two moment of neighbouring sample
Difference, then can draw the separating degree of carbon slag and electrolyte in pinkeye.The schematic diagram in floating Tan Zha areas as shown in Figure 4, it is illustrated that
Middle bright spot is carbon slag.
Wherein, it is previous sampling instant or latter sampling instant that the present invention, which does not limit the neighbouring sample moment,.
As shown in Figure 4 and Figure 5, a kind of aluminium cell sees that the device of fire includes protection device 1, support meanss 2, image automatically
Acquisition module 3, image processing module 4 and Subscriber Interface Module SIM 5.
Wherein, support meanss 2 include pedestal 21 and support arm 22, and protection device 1 is arranged on support arm 22, support arm 22
It can be rotated around pedestal 21, and then the angle between protection device 1 and support arm 22 can be adjusted.
It is preferred that pedestal 21 is moveable, for example pedestal 21 is provided with pulley.Which is easy to measurement, when not measuring, will
It is removed, and it is not influenceed the work of electrolytic cell；Simultaneously in actual mechanical process, whole potroom work area need to only be equipped with one
Playscript with stage directions device is that can obtain the information at all electrolytic cell pinkeye, compared to the device for being fixed on every electrolytic cell progress thermometric, sheet
The cost of device is extremely low.
Protection device 1 includes shell 11 and inner casing 12, and preferably shell 11 and inner casing 12 is made using stainless steel material, thick
Spend for 2mm~3mm.
Cooling air channel 13, the position on shell 11 and inner casing 12 just to pinkeye are formed wherein between shell 11 and inner casing 12
Suprasil piece 14 is equipped with, the normal operation for protecting image capture module 3.
Within the protection device 1 of image capture module 3, specifically, image capture module 3 is located at the cavity 15 of the formation of inner casing 12
It is interior.Preferred image acquisition module 3 is image acquiring sensor in the present embodiment, for example with CCD imaging techniques.
Wherein, image capture module 3 is used for the pinkeye image that aluminium cell aluminium inlet is obtained by sensing technology, and passes through
Pinkeye image is converted to pinkeye digital picture by converter.
Wherein, image capture module 3 is connected with the communication of image processing module 4, image processing module 4 and Subscriber Interface Module SIM
5 communication connections.
Image processing module 4 includes pretreatment module 41, gray level image and builds module 42, function division module 43 and survey
Measure module.
Wherein measurement module at least includes temperature measurement module 44, pinkeye size measurement module 45, pinkeye textural characteristics module 46
In a module.
Wherein, pretreatment module 41 is used to pre-process pinkeye digital picture, and pretreatment includes noise reduction and smooth.Tool
Body, the cleaning to image eliminates the influence of sampling noiset, pre-processed for example with the method for average.
Gray level image builds module 42, for pretreated pinkeye digital picture to be converted into pinkeye gray level image, and
Build gray level image matrix.
Each element correspondence is each pixel in pinkeye gray level image in gray level image matrix, and the value of each element is
The gray value of each pixel.
Function division module 43, for grey to pinkeye using the multi-threshold segmentation method of gray value according to gray level image matrix
Spend image and carry out functional regional division.
Measurement module, the pinkeye information index for abstraction function region.
Wherein, the pinkeye information index of functional area is at least one kind in area, temperature or texture eigenvalue.
Wherein, temperature measurement module 44, the temperature of functional area is obtained for measuring.
Pinkeye size measurement module 45, the size of functional area is obtained for measuring.
Pinkeye textural characteristics module 46, the texture eigenvalue of functional area is obtained for measuring.
In other feasible embodiments, in order to obtain more pinkeye information, pinkeye textural characteristics module 46 is additionally operable to obtain
Take the difference of the gray value of same pixel in the same functional area of adjacent moment, so the gray scale to pixel in functional area
Value changes trend.For example obtain floating the carbon slag in Tan Zha areas and the separating degree of electrolyte.
Subscriber Interface Module SIM 5, fire is seen for showing pinkeye image and pinkeye information automatically to realize.Specifically, user
Interface module 5 includes result display module 51, result memory module 52 and radio interface module 53.
Wherein, result display module 51 is used to show pinkeye image and pinkeye information；As a result memory module 52 is used to deposit
Store up pinkeye image and pinkeye information；Radio interface module 53, for transmitting information, example with external equipment progress wireless connection
Such as with rule in aluminum electrolysis control device wireless connection, pinkeye information transfer is given rule in aluminum electrolysis control device by realization, realizes automatic control and feedback
Function.
It should be noted that the state of pinkeye and the groove condition of electrolytic cell are closely bound up, the present apparatus is for this area to electrolysis
The groove condition of groove carries out judgement and is significant, for example, the relation of the state of pinkeye and groove condition is mainly manifested in：(1) it is fiery
Eye melt region size and shape：Heat channel pinkeye is big, and easily collapses；And cold trap pinkeye is small, shape can shrink；The information
Show on pinkeye image be fused electrolyte region size and situation of change；(2) flame characteristic at pinkeye：The degree of superheat is got over
Height, bath surface tension force is small, and aeration is better, and it is more prosperous that flame burns；The degree of superheat is lower, and bath surface tension force is big, ventilation
Property it is poorer, cause in electrolyte overall gas pressure big, pinkeye does not have flame or outside jet flames；The Informational Expression is in pinkeye figure
As the size of upper as flame zone；(3) electrolyte, pinkeye and carbon slag equitemperature (degree of superheat) information：The degree of superheat is smaller, then
The tension force of bath surface is bigger, and the gas that electrolytic cell is produced is more difficult to give out from electrolyte, so as to cause above and below electrolyte
Jumping frequency rate is high, and amplitude is big；The degree of superheat is bigger, and the tension force of bath surface is smaller, and the gas that electrolytic cell is produced is easier from electricity
Xie Zhizhong gives out, so as to cause that electrolyte bob frequency is low, amplitude is small.(4) pinkeye textural characteristics：Groove condition it is normal or
Partial heat carbon slag separating degree is good, and adrift the carbon slag on electrolyte is in aterrimus, and the groove carbon slag separating degree of groove condition partial heat is poor, adrift
Carbon slag on electrolyte is in dark-grey white.
To sum up, the present invention can quickly, it is accurate and economically aluminium cell aluminium inlet pinkeye image is sampled, go forward side by side
Row analyzing and processing, obtains the implicit pinkeye information of pinkeye image and its institute, manually fire is seen instead of existing with machine vision, can be timely
Pinkeye information is fed back to, to judge in time state in electrolytic bath, therefore a kind of aluminium cell that the present invention is provided is certainly
The dynamic method and its device for seeing fire is significant to the stabilization of electrolytic cell, production energy-saving, efficiently solves aluminium cell condition
A problem being difficult to.
It should be appreciated that these are only presently preferred embodiments of the present invention, it is merely illustrative for the purpose of the present invention, rather than limit
Property processed.Those skilled in the art understands, can carry out many modifications to it in the scope of the claims in the present invention, but
Fall within protection scope of the present invention.Based on the embodiment in the present invention, those of ordinary skill in the art are not making
The every other embodiment obtained under the premise of creative work, belongs to protection scope of the present invention.
Claims (10)
1. a kind of method that aluminium cell sees fire automatically, it is characterised in that methods described includes：
Step 1：The pinkeye image of aluminium cell is obtained, and the pinkeye image is converted into pinkeye digitized map by converter
Picture；
Step 2：The pinkeye digital picture is pre-processed, the pretreatment includes noise reduction and smooth；
Step 3：Pretreated pinkeye digital picture in step 2 is converted into pinkeye gray level image, and builds gray level image square
Battle array；
Each element correspondence is each pixel in pinkeye gray level image in the gray level image matrix, and the value of each element is
The gray value of each pixel；
Step 4：According to the gray level image matrix in step 3 using the multi-threshold segmentation method of gray value to the pinkeye gray-scale map
As carrying out functional regional division；
Step 5：The pinkeye information index of functional area described in extraction step 4；
Wherein, the pinkeye information index of the functional area is at least one kind in area, temperature or texture eigenvalue；
Step 6：Display pinkeye image and pinkeye information see fire automatically to realize, the pinkeye information includes pinkeye information index
With the division information of functional area.
2. according to the method described in claim 1, it is characterised in that：The functional area described in the step 4 extracted in step 5
When pinkeye information index is area, the extraction process of the area of functional area is as follows：
The area of each functional area is calculated using roaming gray level image matrix and pixel statistical method, it is each described
The area of functional area is equal to the number of all pixels point in the correspondence functional area；
Wherein, the areal calculation formula of functional area is as follows：
<mrow>
<mi>Q</mi>
<mo>=</mo>
<msubsup>
<mo>&Sigma;</mo>
<mrow>
<mi>x</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mi>W</mi>
</msubsup>
<msubsup>
<mo>&Sigma;</mo>
<mrow>
<mi>y</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mi>H</mi>
</msubsup>
<mi>C</mi>
<mi>o</mi>
<mi>u</mi>
<mi>n</mi>
<mi>t</mi>
<mrow>
<mo>(</mo>
<mi>I</mi>
<mi>M</mi>
<mi>G</mi>
<mo>(</mo>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
</mrow>
Wherein, Q is expressed as the area of functional area, and W represents the Breadth Maximum of functional area, and H represents that the maximum of functional area is high
Degree, Count (IMG (x, y)) represents the element IMG (x, y) of statistics gray level image matrix quantity, and IMG (x, y) represents gray-scale map
As the xth row in matrix, the element of y row, x, y are zero or positive integer.
3. according to the method described in claim 1, it is characterised in that：The functional area described in the step 4 extracted in step 5
Pinkeye information index is texture eigenvalue, and the extraction process of the texture eigenvalue of functional area is as follows：
Functional area according to the gray level image matrix and the pinkeye gray level image divided obtains functional area
Gray level co-occurrence matrixes P (g1,g2)；
Wherein, the calculation of gray level co-occurrence matrixes is as follows：
Wherein, P (g1,g2) represent to occur gray value simultaneously for g1And g2When probability constitute gray level co-occurrence matrixes；
S represents the set of pinkeye gray level image, and " # " represents the element number in set, f (x1,y1) represent in gray level image matrix
Xth1OK, y1The corresponding gray value g of element of row1, f (x2,y2) represent xth in gray level image matrix2OK, y2The element of row
Corresponding gray value g2；
Gray level co-occurrence matrixes P (g according to functional area1,g2) calculate the texture eigenvalue of the functional area, the texture
Feature at least includes the category feature in entropy, energy, inverse differential square, contrast；
Wherein, entropy f1Calculation formula it is as follows：
<mrow>
<msub>
<mi>f</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mo>-</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>N</mi>
</mrow>
<mrow>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>M</mi>
</mrow>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>N</mi>
</mrow>
<mrow>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>M</mi>
</mrow>
</munderover>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mi>l</mi>
<mi>o</mi>
<mi>g</mi>
<mrow>
<mo>(</mo>
<mi>P</mi>
<mo>(</mo>
<mrow>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>;</mo>
</mrow>
Energy f2Calculation formula it is as follows：
<mrow>
<msub>
<mi>f</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>N</mi>
</mrow>
<mrow>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>M</mi>
</mrow>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>N</mi>
</mrow>
<mrow>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>M</mi>
</mrow>
</munderover>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>;</mo>
</mrow>
Inverse differential is away from f3Calculation formula it is as follows：
<mrow>
<msub>
<mi>f</mi>
<mn>3</mn>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>N</mi>
</mrow>
<mrow>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>M</mi>
</mrow>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>N</mi>
</mrow>
<mrow>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>M</mi>
</mrow>
</munderover>
<mfrac>
<mn>1</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>-</mo>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</mfrac>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mo>;</mo>
</mrow>
Contrast f4Calculation formula it is as follows：
<mrow>
<msub>
<mi>f</mi>
<mn>4</mn>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>N</mi>
</mrow>
<mrow>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>M</mi>
</mrow>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>N</mi>
</mrow>
<mrow>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>M</mi>
</mrow>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>-</mo>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>g</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>g</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mo>;</mo>
</mrow>
Wherein, M is the maximum gradation value of pixel in the pinkeye gray level image of the functional area, and N is the functional area
The minimum gradation value of pixel in pinkeye gray level image.
4. according to the method described in claim 1, it is characterised in that used in step 4 according to the gray level image matrix in step 3
The multi-threshold segmentation method of gray value carries out functional regional division to the pinkeye gray level image, and detailed process is as follows：
Divided according to multiple threshold values and obtain several intensity value ranges；
Wherein, one intensity value ranges of each functional area correspondence；
Each corresponding gray value of element falls into corresponding grey scale value scope in the gray level image matrix, then is divided to corresponding
Functional area.
5. method according to claim 4, it is characterised in that the multiple threshold value is respectively first threshold, Second Threshold
With the 3rd threshold value；
Wherein, the magnitude range 40~50 of first threshold, the magnitude range of Second Threshold are the size model of the 70~75, the 3rd threshold value
Enclose for 144~150.
6. method according to claim 4, it is characterised in that the functional area is divided into：Liquid electrolyte area, fire
Flame area, floating Tan Zha areas and material area, the multiple threshold value is respectively first threshold, Second Threshold and the 3rd threshold value；
Each functional area and the relation of three threshold values are as follows：
The corresponding intensity value ranges in liquid electrolyte area are more than 0 and less than first threshold；
The corresponding intensity value ranges of flame zone are more than or equal to first threshold and less than Second Threshold；
It is more than or equal to Second Threshold and less than the 3rd threshold value to float the corresponding intensity value ranges in Tan Zha areas；
The corresponding intensity value ranges in material area are more than or equal to the 3rd threshold value and less than 255.
7. method according to claim 6, it is characterised in that after step 4, methods described also includes：
Another pinkeye image at neighbouring sample moment is gathered, and another pinkeye figure is obtained according to the operation of step 1- steps 4
The gray value of pixel in Tan Zha areas is floated as in；
The gray scale of same pixel in Tan Zha areas is floated in floating Tan Zha areas in calculation procedure 5 and in another pinkeye image
The difference of value；
The separating degree of carbon slag and electrolyte in the pinkeye is obtained according to the difference of the gray value in floating Tan Zha areas.
8. a kind of aluminium cell sees the device of fire automatically, it is characterised in that described device includes image capture module, image procossing
Module and Subscriber Interface Module SIM, wherein described image processing module include pretreatment module, gray level image and build module, function
Division module and measurement module；
The measurement module at least includes at least one in temperature measurement module, pinkeye size measurement module, pinkeye textural characteristics module
Module；
Wherein, described image acquisition module, the pinkeye image for obtaining aluminium cell aluminium inlet, and will be described by converter
Pinkeye image is converted to pinkeye digital picture；
The pretreatment module, for being pre-processed to the pinkeye digital picture, the pretreatment includes noise reduction and smooth；
The gray level image builds module, for pretreated pinkeye digital picture to be converted into pinkeye gray level image, and structure
Build gray level image matrix；
Each element correspondence is each pixel in pinkeye gray level image in the gray level image matrix, and the value of each element is
The gray value of each pixel；
The function division module, for using the multi-threshold segmentation method of gray value according to gray level image matrix to the pinkeye
Gray level image carries out functional regional division；
The measurement module, the pinkeye information index for extracting the functional area；
Wherein, the pinkeye information index of the functional area is at least one kind in area, temperature or texture eigenvalue；
The Subscriber Interface Module SIM, sees fire, pinkeye information includes automatically for showing pinkeye image and pinkeye information to realize
The division information of pinkeye information index and functional area.
9. device according to claim 8, it is characterised in that described device also includes protection device and support meanss；
The support meanss include pedestal and the support arm on the pedestal, and the protection device is arranged at the support arm
On, the support arm is rotated around the pedestal；
Described image acquisition module is within the protection device.
10. device according to claim 9, it is characterised in that described device is arranged at the center line of electrolytic cell aluminium inlet
And at 30~50cm of cell vessel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710526709.9A CN107248157A (en) | 2017-06-30 | 2017-06-30 | A kind of aluminium cell sees the method and its device of fire automatically |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710526709.9A CN107248157A (en) | 2017-06-30 | 2017-06-30 | A kind of aluminium cell sees the method and its device of fire automatically |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107248157A true CN107248157A (en) | 2017-10-13 |
Family
ID=60014426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710526709.9A Pending CN107248157A (en) | 2017-06-30 | 2017-06-30 | A kind of aluminium cell sees the method and its device of fire automatically |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107248157A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108815853A (en) * | 2018-04-24 | 2018-11-16 | 张霞 | Carrousel seat switching method |
| CN109161932A (en) * | 2018-10-22 | 2019-01-08 | 中南大学 | A kind of extracting method of aluminium cell acute conjunctivitis video behavioral characteristics |
| CN109697433A (en) * | 2019-01-02 | 2019-04-30 | 中南大学 | A kind of aluminium cell degree of superheat state identification method and system based on 3D convolutional neural networks |
| CN111192221A (en) * | 2020-01-07 | 2020-05-22 | 中南大学 | Aluminum electrolysis fire hole image repairing method based on deep convolution generation countermeasure network |
| CN114959797A (en) * | 2022-07-04 | 2022-08-30 | 广东技术师范大学 | Aluminum electrolysis cell condition diagnosis method based on data amplification and SSKELM |
| CN115082734A (en) * | 2022-06-23 | 2022-09-20 | 中南大学 | Aluminum electrolysis cell fire eye video inspection system and superheat degree deep learning identification method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015038012A (en) * | 2013-07-17 | 2015-02-26 | 株式会社トクヤマ | Dry process alumina fine particle and method for producing the same |
| CN104748793A (en) * | 2015-03-19 | 2015-07-01 | 中南大学 | Real-time combined measurement device and method for temperature and flow speed of aluminum electrolytic cell melt |
| CN104751147A (en) * | 2015-04-16 | 2015-07-01 | 成都汇智远景科技有限公司 | Image recognition method |
-
2017
- 2017-06-30 CN CN201710526709.9A patent/CN107248157A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015038012A (en) * | 2013-07-17 | 2015-02-26 | 株式会社トクヤマ | Dry process alumina fine particle and method for producing the same |
| CN104748793A (en) * | 2015-03-19 | 2015-07-01 | 中南大学 | Real-time combined measurement device and method for temperature and flow speed of aluminum electrolytic cell melt |
| CN104751147A (en) * | 2015-04-16 | 2015-07-01 | 成都汇智远景科技有限公司 | Image recognition method |
Non-Patent Citations (2)
| Title |
|---|
| 张创奇 等: "《上插槽炼铝》", 30 September 1998 * |
| 张红亮: "氧化铝回转窑火焰图像识别、检索与聚类研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108815853A (en) * | 2018-04-24 | 2018-11-16 | 张霞 | Carrousel seat switching method |
| CN109161932A (en) * | 2018-10-22 | 2019-01-08 | 中南大学 | A kind of extracting method of aluminium cell acute conjunctivitis video behavioral characteristics |
| CN109697433A (en) * | 2019-01-02 | 2019-04-30 | 中南大学 | A kind of aluminium cell degree of superheat state identification method and system based on 3D convolutional neural networks |
| CN111192221A (en) * | 2020-01-07 | 2020-05-22 | 中南大学 | Aluminum electrolysis fire hole image repairing method based on deep convolution generation countermeasure network |
| CN111192221B (en) * | 2020-01-07 | 2024-04-16 | 中南大学 | Aluminum electrolysis fire hole image repairing method based on deep convolution generation countermeasure network |
| CN115082734A (en) * | 2022-06-23 | 2022-09-20 | 中南大学 | Aluminum electrolysis cell fire eye video inspection system and superheat degree deep learning identification method |
| CN115082734B (en) * | 2022-06-23 | 2023-01-31 | 中南大学 | Aluminum electrolysis cell fire eye video inspection system and superheat degree deep learning identification method |
| CN114959797A (en) * | 2022-07-04 | 2022-08-30 | 广东技术师范大学 | Aluminum electrolysis cell condition diagnosis method based on data amplification and SSKELM |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107248157A (en) | A kind of aluminium cell sees the method and its device of fire automatically | |
| CN111968080B (en) | Method for detecting quality of inside and outside of Feicheng peaches based on hyperspectral and deep learning | |
| CN107144353B (en) | A kind of textile chromatism measurement method based on digital camera | |
| CN103017869B (en) | A kind of water stage measurement system and method based on Digital Image Processing | |
| CN104363815B (en) | Image processing apparatus and image processing method | |
| CN103969168B (en) | A kind of method for quantitatively determining of loose mineral cross-sectional hole rate | |
| CN106228532B (en) | A kind of LCD screen sub-pixel defect inspection method | |
| WO2020207070A1 (en) | Method and system for evaluating shenzhen sea water quality | |
| CN109754019B (en) | Method for continuously monitoring combustion condition of boiler | |
| CN101539528B (en) | Method for detecting lubricating oil water content by utilizing image sensor | |
| CN105445607A (en) | Power equipment fault detection method based on isothermal line drawing | |
| CN109472261A (en) | A kind of quantity of stored grains in granary variation automatic monitoring method based on computer vision | |
| CN104215334A (en) | Real-time online monitoring method of temperature of molten steel in RH refining furnace | |
| CN106483143A (en) | A kind of solar energy photovoltaic panel dust stratification on-Line Monitor Device and its detection method | |
| CN102795627A (en) | Multi-parameter online monitoring and optimizing control device and method of polycrystalline silicon reduction furnace | |
| CN108051442A (en) | A kind of water quality recognition methods and water quality identifying system based on intelligent terminal | |
| CN114419311B (en) | Multi-source information-based passion fruit maturity nondestructive testing method and device | |
| CN109632811A (en) | Structural steel pattern segregation fault detection based on machine vision quantifies ranking method | |
| CN113674280A (en) | Method for measuring temperature of hearth of power station boiler | |
| CN112488997B (en) | Method for detecting and evaluating color reproduction of ancient painting printed matter based on characteristic interpolation | |
| CN210664378U (en) | Customized light source roughness detection device based on red-green chromatic aberration | |
| CN109344892A (en) | A kind of lodging index extracting method based on Multi-source Information Fusion | |
| JP2009536316A (en) | Method and apparatus for measuring the surface quality of a support layer | |
| CN107300360A (en) | A kind of shaft size fast algorithm of detecting of rain fed crops seed three | |
| CN115656202B (en) | Multiband optical detection device for surface state of insulator |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171013 |