CN113034480A - Blast furnace damage analysis method based on artificial intelligence and image processing - Google Patents
Blast furnace damage analysis method based on artificial intelligence and image processing Download PDFInfo
- Publication number
- CN113034480A CN113034480A CN202110356247.7A CN202110356247A CN113034480A CN 113034480 A CN113034480 A CN 113034480A CN 202110356247 A CN202110356247 A CN 202110356247A CN 113034480 A CN113034480 A CN 113034480A
- Authority
- CN
- China
- Prior art keywords
- furnace
- blast furnace
- degree
- crack
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 title claims abstract description 25
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 18
- 239000003034 coal gas Substances 0.000 claims abstract description 22
- 230000007797 corrosion Effects 0.000 claims abstract description 22
- 238000005260 corrosion Methods 0.000 claims abstract description 22
- 230000008447 perception Effects 0.000 claims abstract description 15
- 238000009826 distribution Methods 0.000 claims abstract description 14
- 230000007547 defect Effects 0.000 claims abstract description 12
- 238000005516 engineering process Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 24
- 230000003628 erosive effect Effects 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 11
- 210000001015 abdomen Anatomy 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 abstract description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 6
- 238000003723 Smelting Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 229910052742 iron Inorganic materials 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013021 overheating Methods 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 229910001018 Cast iron Inorganic materials 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000009991 scouring Methods 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000009628 steelmaking Methods 0.000 description 1
- 238000005211 surface analysis Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21B—MANUFACTURE OF IRON OR STEEL
- C21B7/00—Blast furnaces
- C21B7/24—Test rods or other checking devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a blast furnace damage analysis method based on artificial intelligence and image processing, which solves the problem that the damage degree of a blast furnace still needs to be intelligently identified in the prior art. The invention comprises the following steps: a plurality of high-temperature-resistant CCD cameras are arranged at the furnace mouth and beside the furnace to acquire furnace surface images; sending an infrared image acquired by an infrared camera into a trained semantic perception network to acquire an edge gas flow area in the furnace; extracting temperature distribution characteristic data of edge coal gas flow to analyze the corrosion and damage condition of the furnace lining; extracting the surface characteristics of the furnace shell to compensate the characteristic data of the edge coal gas flow, and analyzing the degree of the corrosion loss of the furnace lining by fusing various characteristics; extracting a furnace body surface crack characteristic vector through an image processing technology; and (4) constructing a blast furnace damage degree analysis model by combining the blast furnace lining corrosion damage degree and the blast furnace surface crack degree characteristics. The technology is used for analyzing the damage degree of the blast furnace by constructing a mathematical model according to the damage degree of the blast furnace and combining furnace lining, furnace shell and furnace body surface defect characteristics.
Description
Technical Field
The invention relates to the field of artificial intelligence computer vision processing, in particular to a blast furnace damage analysis method based on artificial intelligence and image processing.
Background
The damage degree of the blast furnace is mainly embodied in the damage conditions of a furnace lining, a furnace body, a furnace shell, a furnace hearth and the like, if the blast furnace with larger damage degree is not maintained or reconstructed in time, serious safety accidents can be caused, and the quality of blast furnace smelting products is reduced. At present, for the analysis of the damage degree and the service life of the blast furnace, the use condition of the blast furnace is analyzed mainly by observing the furnace condition by an operator and monitoring the reaction condition of the burden distribution minerals in a blast furnace hearth, and the damage degree of the blast furnace is further evaluated. The method has low accuracy, no real-time performance, manpower waste and lower working efficiency. Blast furnace iron making is the basic guarantee of steel making, cast iron and other processes of iron and steel enterprises, the quality of blast furnace operation directly relates to the benefits of the enterprises, and whether the blast furnace can operate with high efficiency and long service life is more and more emphasized by the iron and steel enterprises of various countries.
Disclosure of Invention
The invention overcomes the problem that the damage degree of the blast furnace still needs to be intelligently identified in the prior art, and provides the blast furnace damage analysis method based on artificial intelligence and image processing, which has low maintenance cost and high intelligent identification degree.
The technical scheme of the invention is to provide a blast furnace damage analysis method based on artificial intelligence and image processing, which comprises the following steps: comprises the following steps:
firstly, mounting a high-temperature-resistant infrared camera at a furnace mouth to acquire an image in a furnace, and mounting a plurality of high-temperature-resistant CCD cameras beside a blast furnace to acquire a furnace surface image;
sending the infrared image acquired by the infrared camera into a trained semantic perception network to acquire an edge gas flow area in the furnace;
extracting temperature distribution characteristic data of edge coal gas flow to analyze the corrosion and damage condition of the furnace lining;
extracting the surface characteristics of the furnace shell to compensate the characteristic data of the edge coal gas flow, and analyzing the degree of the corrosion loss of the furnace lining by fusing various characteristics;
extracting a furnace body surface crack characteristic vector through an image processing technology;
and step six, constructing a blast furnace damage degree analysis model by combining the blast furnace lining corrosion damage degree and the blast furnace surface crack degree characteristics.
Preferably, in the first step, the furnace mouth high-temperature resistant infrared camera is positioned beside the furnace mouth and used for collecting infrared image data in the furnace; and meanwhile, a plurality of industrial CCD cameras are arranged around the blast furnace, the height of each camera is positioned in the middle of the furnace body, the position of each camera is adjusted and fixed, and a partial overlapping area exists in the shooting range between every two adjacent cameras.
Preferably, in the second step, a semantic perception network is adopted to perform segmentation detection on the infrared image in the furnace, firstly, label data are manually made, pixels in the edge gas flow area are marked as 1, pixels in other areas are marked as 0, and marking of the pixels is required to be performed according to manual experience; and then inputting the image data and the label data into a network model, and performing iterative training on the network by adopting a cross entropy loss function.
Preferably, after the in-furnace semantic perception effect graph is obtained in the third step, the graph is used as a mask to obtain an IR image of the edge gas flow, so as to obtain the temperature distribution condition of the edge gas flow, and calculate the average value of the temperature distribution of the edge gas flow region
The characteristic data is used for analyzing the corrosion degree of the blast furnace lining.
Preferably, after the image collected by the camera is denoised and the blurring is eliminated in the fourth step, the ROI region 1 is set as the furnace body furnace belly part in the image for each frame of image, and the furnace belly redness of the furnace body is used as the characteristic data of the analysis of the furnace lining erosion degree; the specific process for evaluating the furnace belly redness is as follows: firstly, channel separation is carried out on the extracted ROI 1, R channel of the ROI 1 is obtained, and the channel component is calculated and recorded as RnAnd representing the R channel component value of the ROI area 1 in the image of the nth frame, constructing an evaluation model of the redness of the blast furnace shell, and analyzing the redness degree of the blast furnace shell:
wherein N is the selected number of frames, RnRepresentsThe R channel component value of ROI region 1 in the image of the nth frame,
representing the furnace shell redness degree, wherein the larger the R channel component mean value of the ROI area 1 in the furnace shell image is, the higher the redness degree of the furnace shell is considered to be; analyzing and estimating the erosion degree of the blast furnace lining based on the characteristic data, constructing a lining erosion degree analysis model, and obtaining the erosion condition of the blast furnace lining, wherein the function expression of the blast furnace erosion degree analysis model is as follows:
in the formula, K is a model adjustable parameter, K is set to be 10, and C is the erosion degree of a furnace lining in the furnace.
Preferably, in the fifth step, the RGB image of the furnace body surface after pretreatment is firstly segmented, the pixel threshold segmentation method is used to segment the defect region, and then the crack proportion characteristic, the crack propagation characteristic and the crack width characteristic in the crack defect degree of the blast furnace body are evaluated:
the crack proportion characteristic acquisition process comprises the following steps: acquiring the width and the area of the crack in the image according to the crack segmentation binary image, and recording as wm、smAcquiring the minimum external rectangle of the crack region in an image processing mode, and recording the length and the width of the minimum external rectangle as Lm、WmAnd constructing a crack ratio calculation model for calculating the crack ratio in the image:
the crack expansibility characteristic analysis model expression is as follows:
in the formula taumIs the propagation of the mth crack; according to the width characteristic, the crack ratio characteristic and the propagation of the blast furnace surface cracksCharacteristic features, construction
The crack severity estimation model has the specific function expression as follows:
in the formula, DmFor the severity of the mth crack, for the overall analysis of the crack severity index of the blast furnace surface, summing all cracks to obtain a final model for determining the severity index of the crack of the whole blast furnace surface:
wherein m represents the number of cracks, D is the index of the severity of the cracks on the surface of the whole blast furnace shell, and the larger the judgment function value is, the more serious the cracks on the surface of the blast furnace are.
Preferably, in the sixth step, the degree of corrosion damage of the blast furnace lining and the severity of cracks on the blast furnace surface are combined, and the model for analyzing the degree of damage of the blast furnace is constructed by:
in the formula, the weight values of alpha and beta are alpha + beta equal to 1, the distributor of the weight values can select the weight values by self, the invention is set as that alpha is 0.5 and beta is 0.5, delta represents the damage degree index of the blast furnace body, the larger the model function value is, the higher the damage degree of the blast furnace body is, and the preset degree threshold value delta of the damage degree of the blast furnace body is setTWhen the damage degree index of the blast furnace body is higher than the set degree threshold value, namely delta>δTAnd the damage degree of the blast furnace body is considered to be larger, and the system gives out corresponding early warning and maintenance prompts.
Compared with the prior art, the blast furnace damage analysis method based on artificial intelligence and image processing has the following advantages: the method adopts an artificial intelligence method, analyzes the blast furnace damage degree evaluation index through the blast furnace body and the conditions in the blast furnace, is convenient for the smelting plant operators to control the state of the blast furnace in real time, and avoids the safety accidents caused by the condition of the blast furnace. The damage degree of the blast furnace body is mainly analyzed through the self condition of the blast furnace body, and the mechanical scouring action of furnace burden and the like is not considered.
And aiming at the damage degree of the blast furnace, a mathematical model is constructed by combining the characteristics of the furnace lining, the furnace shell and the surface defects of the furnace body, and the damage degree of the blast furnace is analyzed based on the model. The blast furnace damage degree monitoring system can reliably monitor the blast furnace damage degree in real time, greatly reduce overhaul investment, improve economic benefits, assist the blast furnace operation and maintenance, facilitate workers to know the blast furnace damage degree in real time, take effective measures in time, effectively improve the blast furnace production efficiency and prolong the service life of the blast furnace.
Drawings
FIG. 1 is a system flow diagram of the present invention.
Detailed Description
The blast furnace damage analysis method based on artificial intelligence and image processing is further explained with reference to the accompanying drawings and the detailed implementation mode: for a better understanding of the following description with reference to the embodiments and the accompanying drawings, reference is made to fig. 1.
Firstly, a high-temperature-resistant infrared camera is installed at a furnace mouth to acquire images in a furnace, and a plurality of high-temperature-resistant CCD cameras are arranged beside a blast furnace and used for acquiring images of a blast furnace surface.
The furnace interior image is collected through the high-temperature resistant infrared camera at the furnace mouth, the camera is located beside the furnace mouth, the position of the camera is adjusted before image collection, so that the complete furnace interior image can be shot, and the camera is fixed after the position of the camera is adjusted and is used for collecting furnace interior infrared image data. Simultaneously arrange a plurality of industry CCD cameras around the blast furnace, the camera height is located the furnace body in the middle of, adjusts and fixes the camera position, guarantees that the camera can not appear the shake phenomenon at the acquisition in-process, and shoots the scope between the adjacent camera and have a small amount of coincidence region to gather complete furnace body surface image.
And step two, sending the infrared image acquired by the infrared camera into a trained semantic perception network to acquire the edge gas flow area in the furnace. In order to identify the coal gas flow area at the inner edge of the furnace and detect the distribution condition of the coal gas flow area, a semantic perception network is adopted to carry out segmentation detection on the infrared image in the furnace.
For training of the semantic perception network, firstly, label data are made manually, pixels of an edge gas flow area are marked as 1, pixels of other areas are marked as 0, and marking of the pixels needs to be carried out according to manual experience. And then inputting the image data and the label data into a network model, and performing iterative training on the network by adopting a cross entropy loss function.
Therefore, the trained semantic perception network can obtain the perception map of the edge gas flow area from the infrared image in the furnace.
And step three, firstly, extracting the edge coal gas flow area in the furnace, and obtaining the temperature distribution characteristics of the edge coal gas flow for a subsequent system to analyze the corrosion and damage condition of the furnace lining.
The distribution state of the edge coal gas flow directly influences the service condition of the furnace lining on the inner side of the blast furnace, and when the edge coal gas flow in the furnace is excessively developed, the surface temperature of the furnace lining is increased, the local overheating damage of the furnace lining is caused, and the corrosion of the furnace lining and the metal penetration are aggravated. Therefore, the erosion degree of the blast furnace lining is analyzed through the development and distribution of the coal gas flow at the edge of the furnace.
And after the in-furnace semantic perception effect graph is obtained, the in-furnace semantic perception effect graph is used as a mask, the IR image of the edge coal gas flow is obtained on the basis of the mask, and the temperature distribution condition of the edge coal gas flow is further obtained. Calculating the mean value of the temperature distribution of the edge gas flow area
And the corrosion degree of the blast furnace lining is used as a characteristic for analyzing the corrosion degree of the blast furnace lining.
Step four: in order to improve the system accuracy, the surface characteristics of the blast furnace shell are extracted, and the erosion degree of the furnace lining in the blast furnace is further analyzed according to the redness of the furnace surface.
Because the reaction process in the furnace is complex, and the boundary of the edge coal gas flow and the central coal gas flow in the furnace is not obvious enough, the extraction of the edge coal gas flow area is easy to cause errors, so that the erosion degree of the furnace lining cannot be accurately judged only by the development state of the edge coal gas flow, and the furnace lining in the furnace is further analyzed by combining the condition of the furnace shell for improving the accuracy of detecting the erosion degree of the furnace lining by a system.
The method comprises the steps of firstly adopting a plurality of high-temperature-resistant industrial cameras to collect images on the surface of a furnace body, adjusting the positions of the cameras by the aid of the cameras, so that the height of the furnace body and the height of the cameras are roughly consistent, considering that the smelting environment of a blast furnace is severe and a large amount of smoke exists, the images are subjected to noise, and the images collected by the cameras are subjected to denoising and fuzzy elimination. There are many specific methods for denoising and eliminating image blur, and the implementer can select them by himself without making a description.
After the images are preprocessed, setting an ROI (region of interest) region 1 for each frame of image, considering that the furnace body surface furnace belly can generate redness in different degrees due to different conditions of the inner lining of the blast furnace in the use process of the blast furnace, wherein the ROI region 1 is the furnace body furnace belly part in the images, and the redness of the furnace body furnace belly is used as characteristic data for analyzing the erosion degree of the lining.
The specific process of the furnace belly redness evaluation is as follows: firstly, channel separation is carried out on the extracted ROI 1, R channel of the ROI 1 is obtained, and the channel component is calculated and recorded as RnAnd representing the R channel component value of the ROI area 1 in the image of the nth frame, constructing an evaluation model of the redness of the blast furnace shell, and analyzing the redness degree of the blast furnace shell:
wherein N is the selected number of frames, RnAn R-channel component value representing the ROI area 1 in the image of the nth frame,
representing the degree of furnace shell redness, the larger the average value of the R channel component of ROI region 1 in the furnace shell image is, the higher the degree of furnace shell redness is considered.
And obtaining the furnace shell redness and the temperature average value of the coal gas flow at the edge of the furnace, analyzing and estimating the corrosion degree of the blast furnace lining based on the characteristic data, and constructing a lining corrosion degree analysis model to obtain the corrosion condition of the blast furnace lining. The blast furnace erosion degree analysis model function expression is as follows:
in the formula, K is a model adjustable parameter, K is set to be 10, and C is the erosion degree of a furnace lining in the furnace.
Step five: the surface condition of the furnace body is also an important characteristic for reflecting the damage degree of the blast furnace, an industrial camera is adopted to shoot the blast furnace surface image, the surface crack characteristic of the furnace body is extracted through an image processing technology, and the crack severity index of the blast furnace surface is analyzed for subsequent analysis of the final damage condition of the blast furnace.
The main objective is the damage degree of analysis blast furnace, and blast furnace damages mainly to be reflected in the blast furnace stove and the damage of blast furnace table, consequently, for comprehensive analysis blast furnace damage condition, will judge the analysis to the blast furnace table condition.
The blast furnace surface analysis mainly analyzes the crack phenomenon of the blast furnace surface. In the using process of the blast furnace, the blast furnace surface has defects of cracking, cracks and the like due to operations such as high-temperature smelting and the like, and in order to analyze the condition of the blast furnace surface, the RGB image of the pretreated furnace body surface is firstly segmented, and the defect area is segmented for subsequent crack degree analysis. The crack region is segmented into a pixel threshold segmentation method, a pixel threshold is set for a blast furnace surface image, the crack region is segmented based on the pixel threshold, an image segmentation algorithm is mature and is a conventional technology, and a concrete segmentation method is selected by an implementer and is not in a protection range and is not described in detail.
Thus, the crack area of each furnace surface can be obtained.
In order to evaluate the degree of the blast furnace body crack defects, the blast furnace body defect characteristics are extracted and are used for analyzing and judging the severity of the blast furnace cracks subsequently. The blast furnace surface defect characteristics mainly include: crack aspect ratio characteristics, crack propagation characteristics, and crack width characteristics.
The crack proportion characteristic acquisition process specifically comprises the following steps: acquiring the width and the area of the crack in the image according to the crack segmentation binary image, and recording as wm、sm. The crack width is used as a width characteristic of the crack. Acquiring a minimum external rectangle of the crack region in an image processing mode, and recording the length and the width of the minimum external rectangle as Lm、WmAnd constructing a crack ratio calculation model for calculating the crack ratio in the image:
the specific analysis process of the crack expansibility characteristic is as follows: in order to reflect the crack grade of the blast furnace body and accurately analyze the severity of the blast furnace cracks, a crack expansibility characteristic analysis model is constructed, and the possibility that the blast furnace cracks expand to the periphery is analyzed, wherein the furnace surface crack expansibility characteristic analysis model expression is as follows:
in the formula taumThe propagation of the mth crack.
And finally, evaluating and analyzing the severity of the cracks according to the width characteristics (namely the width of the cracks), the crack proportion characteristics and the expansibility characteristics of the cracks on the blast furnace surface. Constructing a crack severity estimation model, wherein a specific function expression is as follows:
in the formula, DmFor the severity of the mth crack, for the overall analysis of the crack severity index of the blast furnace surface, summing all cracks to obtain a final model for determining the severity index of the crack of the whole blast furnace surface:
wherein m represents the number of cracks, and D is the severity index of the cracks on the surface of the whole blast furnace shell. The larger the judgment function value is, the more serious the blast furnace surface cracks are considered to be.
Therefore, the method can obtain the degree of corrosion damage of the lining in the blast furnace and the severity of surface cracks of the blast furnace body.
Step six: and (3) establishing a blast furnace damage degree analysis model by combining the corrosion damage degree of the blast furnace lining and the crack severity degree of the blast furnace surface, and evaluating the overall damage degree of the blast furnace based on the model.
And finally, analyzing and judging the damage degree of the whole blast furnace body based on the conditions of the blast furnace lining and the furnace surface so that the working personnel can master the use condition of the blast furnace in real time. The blast furnace body damage degree analysis model is as follows:
in the formula, the weight values α and β are set to α + β equal to 1, the operator can select the weight values by himself, α is 0.5, β is 0.5, δ represents the index of the damage degree of the blast furnace body, and the larger the model function value is, the higher the damage degree of the blast furnace body is.
So far, the implementer can master the condition of the blast furnace body in real time based on the system, and in order to avoid the problems of safety problem and product quality reduction and the like in the smelting process caused by overlarge damage degree of the blast furnace body, a preset degree threshold value delta of the damage degree of the blast furnace body is used for solving the problems of the safety problem and the product quality reduction and the likeT. When the damage degree index of the blast furnace body is higher than the set degree threshold value, namely delta>δTThe damage degree of the blast furnace body is considered to be large, the system gives out corresponding early warning prompts to prompt maintenance personnel to detect and maintain the blast furnace condition as soon as possible, and blast furnace parts are replaced as necessary to prevent safety accidents and other problems caused by the overhigh damage degree of the blast furnace.
In summary, the present invention provides a blast furnace damage analysis system based on artificial intelligence and image processing. The method comprises the steps of firstly, acquiring an image in the furnace through a high-temperature-resistant industrial camera at a furnace mouth, and filtering the image, wherein the erosion of furnace lining slag and metal penetration are aggravated when the edge coal gas flow in the furnace is developed excessively, and the furnace lining is easy to burn through due to local overheating, so that the method analyzes the erosion degree of the furnace lining by combining the characteristic vector of the edge coal gas flow in the furnace and the reddening degree characteristic of a furnace shell. Meanwhile, a multi-camera is adopted outside the blast furnace to acquire blast furnace surface images, RGB (red, green and blue) images of the furnace surface are processed, the surface defect characteristics of the furnace body are extracted, and the crack degree of the furnace body is analyzed. A mathematical model is constructed based on the furnace surface crack degree characteristics and the furnace lining corrosion degree, the damage degree of the blast furnace is detected in real time, data analysis is provided for operation and maintenance of the blast furnace, so that workers are prompted to detect corresponding detection and maintenance of the blast furnace in time, and the service life of the blast furnace is prolonged.
Claims (7)
1. A blast furnace damage analysis method based on artificial intelligence and image processing is characterized in that: comprises the following steps:
firstly, mounting a high-temperature-resistant infrared camera at a furnace mouth to acquire an image in a furnace, and mounting a plurality of high-temperature-resistant CCD cameras beside a blast furnace to acquire a furnace surface image;
sending the infrared image acquired by the infrared camera into a trained semantic perception network to acquire an edge gas flow area in the furnace;
extracting temperature distribution characteristic data of edge coal gas flow to analyze the corrosion and damage condition of the furnace lining;
extracting the surface characteristics of the furnace shell to compensate the characteristic data of the edge coal gas flow, and analyzing the degree of the corrosion loss of the furnace lining by fusing various characteristics;
extracting a furnace body surface crack characteristic vector through an image processing technology;
and step six, constructing a blast furnace damage degree analysis model by combining the blast furnace lining corrosion damage degree and the blast furnace surface crack degree characteristics.
2. The blast furnace damage analysis method based on artificial intelligence and image processing as claimed in claim 1, wherein: in the first step, a furnace mouth high-temperature resistant infrared camera is positioned beside the furnace mouth to acquire furnace infrared image data; and meanwhile, a plurality of industrial CCD cameras are arranged around the blast furnace, the height of each camera is positioned in the middle of the furnace body, the position of each camera is adjusted and fixed, and a partial overlapping area exists in the shooting range between every two adjacent cameras.
3. The blast furnace damage analysis method based on artificial intelligence and image processing as claimed in claim 1, wherein: in the second step, a semantic perception network is adopted to carry out segmentation detection on the infrared image in the furnace, firstly, label data are made manually, pixels in the edge gas flow area are marked as 1, pixels in other areas are marked as 0, and marking of the pixels is carried out according to manual experience; and then inputting the image data and the label data into a network model, and performing iterative training on the network by adopting a cross entropy loss function.
4. The blast furnace damage analysis method based on artificial intelligence and image processing as claimed in claim 1, wherein: after the in-furnace semantic perception effect image is obtained in the third step, the in-furnace semantic perception effect image is used as a mask to obtain an IR image of the edge gas flow, the temperature distribution condition of the edge gas flow is obtained, and the temperature distribution mean value of the edge gas flow area is calculated
The characteristic data is used for analyzing the corrosion degree of the blast furnace lining.
5. The blast furnace damage analysis method based on artificial intelligence and image processing as claimed in claim 1, wherein: in the fourth step, after the image collected by the camera is denoised and the fuzzy processing is eliminated, an ROI (region of interest) region 1 is set as a furnace body furnace belly part in the image for each frame of image, and the furnace belly redness of the furnace body is used as characteristic data for analyzing the erosion degree of the furnace lining; the specific process for evaluating the furnace belly redness is as follows: firstly, channel separation is carried out on the extracted ROI 1, R channel of the ROI 1 is obtained, and the channel component is calculated and recorded as RnRepresenting the R channel component value of ROI area 1 in the nth frame image, constructing the blast furnaceEvaluation model of shell redness the degree of redness of the blast furnace shell was analyzed:
wherein N is the selected number of frames, RnAn R-channel component value representing the ROI area 1 in the image of the nth frame,
representing the furnace shell redness degree, wherein the larger the R channel component mean value of the ROI area 1 in the furnace shell image is, the higher the redness degree of the furnace shell is considered to be; analyzing and estimating the erosion degree of the blast furnace lining based on the characteristic data, constructing a lining erosion degree analysis model, and obtaining the erosion condition of the blast furnace lining, wherein the function expression of the blast furnace erosion degree analysis model is as follows:
in the formula, K is a model adjustable parameter, K is set to be 10, and C is the erosion degree of a furnace lining in the furnace.
6. The blast furnace damage analysis method based on artificial intelligence and image processing as claimed in claim 1, wherein: in the fifth step, the RGB image on the surface of the furnace body after pretreatment is firstly segmented, the defect area is segmented by using a pixel threshold segmentation method, and then the crack occupation ratio characteristic, the crack propagation characteristic and the crack width characteristic in the crack defect degree of the blast furnace body are evaluated:
the crack proportion characteristic acquisition process comprises the following steps: acquiring the width and the area of the crack in the image according to the crack segmentation binary image, and recording as wm、smAcquiring the minimum external rectangle of the crack region in an image processing mode, and recording the length and the width of the minimum external rectangle as Lm、WmAnd constructing a crack ratio calculation model for calculating the crack ratio in the image:
the crack expansibility characteristic analysis model expression is as follows:
in the formula taumIs the propagation of the mth crack; according to the width characteristic, the crack proportion characteristic and the expansibility characteristic of the blast furnace surface cracks, a crack severity estimation model is constructed, and the specific function expression is as follows:
in the formula, DmFor the severity of the mth crack, for the overall analysis of the crack severity index of the blast furnace surface, summing all cracks to obtain a final model for determining the severity index of the crack of the whole blast furnace surface:
wherein m represents the number of cracks, D is the index of the severity of the cracks on the surface of the whole blast furnace shell, and the larger the judgment function value is, the more serious the cracks on the surface of the blast furnace are.
7. The blast furnace damage analysis method based on artificial intelligence and image processing as claimed in claim 1, wherein: combining the erosion degree of the blast furnace lining and the severity degree of the blast furnace surface cracks in the sixth step, constructing a blast furnace damage degree analysis model as follows:
in the formula, the weight values of alpha and beta are alpha + beta equal to 1, the distributor of the weight values can select the weight values by self, the invention is set as that alpha is 0.5 and beta is 0.5, delta represents the damage degree index of the blast furnace body, the larger the model function value is, the higher the damage degree of the blast furnace body is, and the preset degree threshold value delta of the damage degree of the blast furnace body is setTWhen the damage degree index of the blast furnace body is higher than the set degree threshold value, namely delta>δTAnd the damage degree of the blast furnace body is considered to be larger, and the system gives out corresponding early warning and maintenance prompts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110356247.7A CN113034480B (en) | 2021-04-01 | 2021-04-01 | Blast furnace damage analysis method based on artificial intelligence and image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110356247.7A CN113034480B (en) | 2021-04-01 | 2021-04-01 | Blast furnace damage analysis method based on artificial intelligence and image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113034480A true CN113034480A (en) | 2021-06-25 |
| CN113034480B CN113034480B (en) | 2023-12-19 |
Family
ID=76454048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110356247.7A Active CN113034480B (en) | 2021-04-01 | 2021-04-01 | Blast furnace damage analysis method based on artificial intelligence and image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034480B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657193A (en) * | 2021-07-27 | 2021-11-16 | 中铁工程装备集团有限公司 | Segment damage detection method and system based on computer vision and shield machine |
| CN114507760A (en) * | 2022-02-28 | 2022-05-17 | 马鞍山钢铁股份有限公司 | Method and system for detecting damage condition of blast furnace lining |
| CN114998326A (en) * | 2022-07-19 | 2022-09-02 | 江苏瑞立环保工程股份有限公司 | Method and system for detecting distribution condition of gas flow based on artificial intelligence |
| WO2024070150A1 (en) * | 2022-09-27 | 2024-04-04 | Ｊｆｅスチール株式会社 | Gutter management system and gutter management method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0674977A1 (en) * | 1994-03-29 | 1995-10-04 | General Electric Company | Maintenance system |
| CN107749058A (en) * | 2017-10-23 | 2018-03-02 | 中南大学 | A kind of machine vision detection method and system of boiler tubing surface defect |
| JP2018148201A (en) * | 2017-03-03 | 2018-09-20 | 株式会社Ｓｃｒｅｅｎホールディングス | Heat treatment method and heat treatment apparatus |
| CN108998608A (en) * | 2018-07-24 | 2018-12-14 | 中南大学 | A kind of blast furnace iron notch molten iron temperature measurement method and system based on infrared machine vision |
| US20190156483A1 (en) * | 2016-07-25 | 2019-05-23 | Olympus Corporation | Image processing apparatus and image processing method |
| CN109852748A (en) * | 2019-02-27 | 2019-06-07 | 内蒙古科技大学 | Monitor the Gas Flow development process of blast furnace material distribution period and prediction gas utilization rate method |
| CN110762540A (en) * | 2019-10-22 | 2020-02-07 | 华南理工大学 | Combustion decision method and automatic combustion control method and system for garbage incinerator |
| CN112200782A (en) * | 2020-09-30 | 2021-01-08 | 邵传宏 | Photovoltaic cell panel damage risk degree detection method based on artificial intelligence |
-
2021
- 2021-04-01 CN CN202110356247.7A patent/CN113034480B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0674977A1 (en) * | 1994-03-29 | 1995-10-04 | General Electric Company | Maintenance system |
| US20190156483A1 (en) * | 2016-07-25 | 2019-05-23 | Olympus Corporation | Image processing apparatus and image processing method |
| JP2018148201A (en) * | 2017-03-03 | 2018-09-20 | 株式会社Ｓｃｒｅｅｎホールディングス | Heat treatment method and heat treatment apparatus |
| CN107749058A (en) * | 2017-10-23 | 2018-03-02 | 中南大学 | A kind of machine vision detection method and system of boiler tubing surface defect |
| CN108998608A (en) * | 2018-07-24 | 2018-12-14 | 中南大学 | A kind of blast furnace iron notch molten iron temperature measurement method and system based on infrared machine vision |
| CN109852748A (en) * | 2019-02-27 | 2019-06-07 | 内蒙古科技大学 | Monitor the Gas Flow development process of blast furnace material distribution period and prediction gas utilization rate method |
| CN110762540A (en) * | 2019-10-22 | 2020-02-07 | 华南理工大学 | Combustion decision method and automatic combustion control method and system for garbage incinerator |
| CN112200782A (en) * | 2020-09-30 | 2021-01-08 | 邵传宏 | Photovoltaic cell panel damage risk degree detection method based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 匡以顺: "基于红外热图像信息的铜转炉炉衬蚀损状态在线测量系统研究", 《中国优秀硕士学位论文全文数据库》, no. 09, pages 21 - 55 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657193A (en) * | 2021-07-27 | 2021-11-16 | 中铁工程装备集团有限公司 | Segment damage detection method and system based on computer vision and shield machine |
| CN114507760A (en) * | 2022-02-28 | 2022-05-17 | 马鞍山钢铁股份有限公司 | Method and system for detecting damage condition of blast furnace lining |
| CN114998326A (en) * | 2022-07-19 | 2022-09-02 | 江苏瑞立环保工程股份有限公司 | Method and system for detecting distribution condition of gas flow based on artificial intelligence |
| CN114998326B (en) * | 2022-07-19 | 2023-03-07 | 江苏瑞立环保工程股份有限公司 | Method and system for detecting distribution condition of gas flow based on artificial intelligence |
| WO2024070150A1 (en) * | 2022-09-27 | 2024-04-04 | Ｊｆｅスチール株式会社 | Gutter management system and gutter management method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113034480B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113034480A (en) | Blast furnace damage analysis method based on artificial intelligence and image processing | |
| WO2020098299A1 (en) | Method and system for detecting flow rate of high-temperature molten fluid | |
| CN106991668B (en) | Evaluation method for pictures shot by skynet camera | |
| CN110544261B (en) | Method for detecting coal injection state of blast furnace tuyere based on image processing | |
| CN105678295A (en) | Method for real-time monitoring gas heating furnace flame on the basis of ROI average image analysis | |
| CN107782733A (en) | Image recognition the cannot-harm-detection device and method of cracks of metal surface | |
| CN110493574B (en) | Security monitoring visualization system based on streaming media and AI technology | |
| CN109035249B (en) | Pipeline fault parallel global threshold detection method based on image processing | |
| JP2012202858A (en) | Closure crack detection method of concrete surface | |
| CN106934801A (en) | A kind of fluorescentmagnetic particle(powder) defect inspection method based on Laws texture filterings | |
| Diaz et al. | Rust detection using image processing via Matlab | |
| CN113155839A (en) | Steel plate outer surface defect online detection method based on machine vision | |
| CN113702391B (en) | Method and device for compositely detecting defects on surface and near surface of steel billet | |
| CN112508944A (en) | Leakage detection method applied to underground water supply pipeline of coal mine | |
| CN110184401A (en) | Tap cinder iron state online test method | |
| Li et al. | Detection algorithm of defects on polyethylene gas pipe using image recognition | |
| CN110363749B (en) | Evaluation method for rusting degree of vibration damper based on image processing | |
| CN113177605A (en) | Scrap steel carriage grade judgment method based on video monitoring | |
| CN114332081B (en) | Textile surface abnormity determination method based on image processing | |
| CN117235672B (en) | Comprehensive pipe gallery fault diagnosis method and device based on multi-source data | |
| CN115861294B (en) | Concrete production abnormality detection method and device based on computer vision | |
| CN116402827B (en) | Image processing-based cable clamp plate defect detection method and device for coal mining machine | |
| CN111626104A (en) | Cable hidden danger point detection method and device based on unmanned aerial vehicle infrared thermal imagery | |
| CN116681664A (en) | Detection method and device for operation of stamping equipment | |
| CN105354848A (en) | Optimization method of Cognex surface quality detection system of hot galvanizing production line |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231123 Address after: Unit 1104-B, No. 78, Lane 1688, Guoquan North Road, Yangpu District, Shanghai, 200082 Applicant after: Aide Linker (Shanghai) Digital Technology Co.,Ltd. Address before: 710075 10612, unit 1, building 6, Qidi Science Park, No.65, Keji 2nd Road, high tech Zone, Xi'an City, Shaanxi Province Applicant before: Xi'an Daofa Digital Information Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |