CN115786614B - Method and device for measuring thickness of blast furnace lining - Google Patents
Method and device for measuring thickness of blast furnace lining Download PDFInfo
- Publication number
- CN115786614B CN115786614B CN202211486492.0A CN202211486492A CN115786614B CN 115786614 B CN115786614 B CN 115786614B CN 202211486492 A CN202211486492 A CN 202211486492A CN 115786614 B CN115786614 B CN 115786614B
- Authority
- CN
- China
- Prior art keywords
- image
- temperature
- processed image
- region
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000001914 filtration Methods 0.000 claims abstract description 38
- 238000003709 image segmentation Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims description 46
- 238000006243 chemical reaction Methods 0.000 claims description 23
- 230000003628 erosive effect Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 10
- 230000002093 peripheral effect Effects 0.000 claims description 10
- 239000011449 brick Substances 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 239000000428 dust Substances 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 14
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 8
- 238000000691 measurement method Methods 0.000 description 8
- 230000007547 defect Effects 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 239000006002 Pepper Substances 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 235000002566 Capsicum Nutrition 0.000 description 4
- 241000722363 Piper Species 0.000 description 4
- 235000016761 Piper aduncum Nutrition 0.000 description 4
- 235000017804 Piper guineense Nutrition 0.000 description 4
- 235000008184 Piper nigrum Nutrition 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 229910052742 iron Inorganic materials 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 150000003839 salts Chemical class 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000002035 prolonged effect Effects 0.000 description 3
- 235000001674 Agaricus brunnescens Nutrition 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 238000009529 body temperature measurement Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 239000002893 slag Substances 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Radiation Pyrometers (AREA)
Abstract
The invention discloses a method and a device for measuring the thickness of a blast furnace lining, wherein the method comprises the steps of obtaining a thermal infrared image of a region to be measured when a blast furnace runs, carrying out filtering treatment on the thermal infrared image to obtain a first treatment image so as to inhibit various dust, equipment thermal noise and other various interferences in the blast furnace measuring environment, taking gray features or texture features of the first treatment image as image features, carrying out image segmentation on the first treatment image to obtain a second treatment image, and obtaining temperature field information of the region to be measured according to the gray value of a pixel on the second treatment image and a preset corresponding relation according to the gray value of a target position on the second treatment image.
Description
Technical Field
The application relates to the technical field of blast furnace lining thickness measurement, in particular to a method and a device for measuring the thickness of a blast furnace lining.
Background
In the production of blast furnaces, a large number of large blast furnaces at home and abroad have the phenomenon of excessively fast erosion of furnace hearth and furnace lining, thereby bringing serious threat to the production safety of the blast furnaces and causing huge loss and negative influence to enterprises and society. If the thickness change of the furnace hearth lining in the blast furnace can be monitored in real time in the production process, the erosion degree of the furnace hearth lining can be accurately mastered, the operation strategy can be timely adjusted or effective furnace protection measures can be adopted, the continuous deterioration of the furnace condition is avoided, and the service life of the blast furnace is prolonged. For ironmaking workers, the development and application of the hearth lining thickness detection technology are significant, but because the blast furnace is a closed container for continuous production, the lining is always in an internal environment with high temperature, high pressure and multiple smoke dust, and especially the hearth part is in a high-temperature molten slag iron environment for a long time, the detection of the residual thickness of the lining is very difficult. The existing measuring method is mostly based on the related physical parameters of the furnace lining, and utilizes a mathematical model or algorithm to indirectly infer the residual thickness of the furnace lining, so that the accuracy of measuring the thickness of the furnace lining of the blast furnace is insufficient.
Therefore, how to improve the accuracy of the thickness measurement of the blast furnace lining is a technical problem to be solved at present.
Disclosure of Invention
The method and the device for measuring the thickness of the blast furnace lining can improve the accuracy of measuring the thickness of the blast furnace lining.
The embodiment of the invention provides the following scheme:
in a first aspect, an embodiment of the present invention provides a method for measuring a thickness of a lining of a blast furnace, the method including:
acquiring a thermal infrared image of a region to be measured when the blast furnace operates;
filtering the thermal infrared image to obtain a first processed image;
Image segmentation is carried out on the first processed image according to image characteristics to obtain a second processed image, wherein the image characteristics at least comprise gray level characteristics or texture characteristics of the first processed image;
obtaining temperature field information of the region to be detected according to the gray value of the target position on the second processing image and a preset corresponding relation, wherein the preset corresponding relation is the corresponding relation between the temperature value and the gray value;
and determining the thickness of the furnace lining of the region to be detected according to the temperature field information.
In an alternative embodiment, the filtering the thermal infrared image to obtain a first processed image includes:
acquiring a first pixel window with a preset specification, wherein the first pixel window comprises at least 3 pixel points;
Performing median filtering processing on the thermal infrared image according to the first pixel window so as to update the pixel gray value of the thermal infrared image;
and outputting an updating result of the thermal infrared image to obtain the first processed image.
In an alternative embodiment, after the outputting the updated result of the thermal infrared image to obtain the first processed image, the method further includes:
Acquiring a plurality of first processing images output by a preset duration;
obtaining gray average values of the same pixel areas of the plurality of first processed images according to the plurality of first processed images;
and updating the gray value of the corresponding pixel area according to the gray average value until the gray value of all the pixel areas is updated, so as to obtain the updated first processed image.
In an alternative embodiment, after the gray value update of all the pixel areas is completed, the method further includes:
Dividing the updated first processed image into a plurality of second pixel windows with preset specifications;
Obtaining a weight gray value of each pixel point according to a preset weight coefficient and the gray value of each pixel point in the second pixel window;
And determining the gray level value of the second pixel window according to the weight gray level value positioned at the center of the second pixel window so as to update the first processed image again.
In an alternative embodiment, the image segmentation of the first processed image according to the image features to obtain a second processed image includes:
acquiring a histogram of the first processed image corresponding to the gray feature;
Determining a first sample center of the first processed image according to the gray upper limit value of the histogram;
Obtaining a second sample center according to the first sample center and a preset sample center distance;
performing fuzzy clustering processing on the first processed image according to the first sample center and the second sample center, and updating a clustering center to perform iterative computation;
And outputting the first processed image of the image segmentation when the clustering result reaches a preset target so as to obtain the second processed image.
In an alternative embodiment, the determining the thickness of the furnace lining of the region to be measured according to the temperature field information includes:
Obtaining furnace shell temperatures of a plurality of target positions according to the temperature field information, wherein the target positions are erosion line intersection point positions of hearth brick liners in the blast furnace;
Inputting a plurality of furnace shell temperatures into a preset temperature calculation model to obtain a temperature conversion coefficient of each target position, wherein the temperature conversion coefficient is used for representing a temperature change proportion when the radial distance from the target position to the blast furnace is increased;
Obtaining a target isothermal curve of the blast furnace in a target direction according to the temperature of each furnace shell and the corresponding temperature conversion coefficient;
Obtaining a peripheral curve of the region to be detected according to the region parameters of the region to be detected and the outer diameter of the blast furnace, wherein the region parameters are central angles or region arc lengths of the region to be detected;
and determining the thickness of the furnace lining according to the interval distance between the target isothermal curve and the peripheral curve.
In an alternative embodiment, the obtaining the target isothermal curve of the blast furnace in the target direction according to the furnace shell temperature and the corresponding temperature conversion coefficient includes:
Obtaining a target position of each target temperature in the target direction according to each furnace shell temperature and the temperature conversion coefficient;
and obtaining the target isothermal curves according to the fitting curves of the target positions based on the adjacent relation.
In a second aspect, an embodiment of the present invention further provides a device for measuring a thickness of a lining of a blast furnace, the device including:
The acquisition module is used for acquiring a thermal infrared image of a region to be detected when the blast furnace operates;
The first obtaining module is used for carrying out filtering processing on the thermal infrared image to obtain a first processed image;
the second obtaining module is used for carrying out image segmentation on the first processed image according to image characteristics to obtain a second processed image, wherein the image characteristics at least comprise gray characteristics or texture characteristics of the first processed image;
The third obtaining module is used for obtaining the temperature field information of the region to be detected according to the gray value of the target position on the second processing image and a preset corresponding relation, wherein the preset corresponding relation is the corresponding relation between the temperature value and the gray value;
and the determining module is used for determining the thickness of the furnace lining of the region to be detected according to the temperature field information.
In a third aspect, embodiments of the present invention also provide an electronic device comprising a processor and a memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the electronic device to perform the steps of the method of any one of the first aspects.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements the steps of the method according to any of the first aspects.
Compared with the prior art, the method and the device for measuring the thickness of the blast furnace lining have the following advantages:
According to the measuring method, the thermal infrared image of the region to be measured is obtained when the blast furnace runs, the thermal infrared image is subjected to filtering treatment to obtain the first treatment image, so that various kinds of interference such as dust, equipment thermal noise and the like in the blast furnace measuring environment are restrained, the gray level characteristic or texture characteristic of the first treatment image is used as the image characteristic, the first treatment image is subjected to image segmentation to obtain the second treatment image, the gray level value of the pixel on the second treatment image has a corresponding relation with the temperature value, the temperature field information of the region to be measured is obtained according to the gray level value of the target position on the second treatment image and the preset corresponding relation, and the temperature field information of the region to be measured can represent the temperature distribution characteristic of the region to be measured due to image segmentation and gray level value conversion, so that the thickness of a furnace lining of the region to be measured can be accurately determined according to the temperature field information, and the accuracy of measuring the thickness of the furnace lining of the blast furnace is improved. The method can analyze the thickness of the lining and the defect position in the blast furnace through the thermal infrared image, so that the severity degree of the defect and the size of the defect area can be accurately measured, an operator can improve the operation method, a maintenance and construction scheme can be formulated, grouting lining construction can be guided, and the service life of the blast furnace lining can be prolonged. In addition, the maintenance construction quality of the blast furnace can be checked by adopting the thermal infrared image, so that the safe and reliable operation of the equipment after the recovery is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required for the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present description, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for measuring the thickness of a blast furnace lining provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of an infrared thermal imager according to an embodiment of the present invention;
FIG. 3 is a data flow diagram of a furnace lining thickness measurement provided by an embodiment of the present invention;
FIG. 4 is an original schematic view of a thermal infrared image according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a thermal infrared image according to an embodiment of the present invention after median filtering;
FIG. 6 is a schematic diagram of a thermal infrared image according to an embodiment of the present invention after mean filtering;
FIG. 7 is a schematic diagram of a weighted filtered thermal infrared image according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a thermal infrared image according to an embodiment of the present invention after image segmentation;
FIG. 9 is a schematic diagram of temperature field information of a region to be measured according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a target isothermal curve provided by an embodiment of the present invention;
FIG. 11 is a schematic structural view of a device for measuring thickness of a blast furnace lining according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the embodiments of the present invention.
At present, researchers at home and abroad successively develop various blast furnace lining thickness measurement technologies, and although certain effects are achieved, a universally applicable method is not formed yet. Common blast furnace lining thickness measuring methods can be largely classified into direct measurement methods and indirect measurement methods. The direct measurement method mainly includes a multi-head thermocouple method, a resistance method, a capacitance method, an ultrasonic method and an electromagnetic wave method, and is mainly characterized in that a sensor is embedded in a furnace lining in advance, the sensor and the furnace lining are corroded synchronously in the production process, and the residual thickness of the furnace lining can be judged by measuring the residual length of the sensor. The indirect measurement method mainly comprises a model inference method, a heat flow detection method and an impact echo method, and is mainly characterized in that the residual thickness of the furnace lining is indirectly inferred by utilizing a mathematical model or algorithm based on detected relevant physical parameters of the furnace lining.
In the blast furnace lining thickness measuring method, except for an impact echo method, a thermocouple or a special sensor is embedded in a furnace lining to collect data, but in actual production application, a large number of thermocouples fail within a few years of blast furnace production, so that a plurality of dead zones exist in furnace lining temperature measurement, and the accuracy of a model inference method is particularly influenced; in addition, the service life of the sensor cannot be guaranteed due to the severe environment of the blast furnace, and once damaged, the sensor cannot be repaired, so that the detection is difficult. The lining erosion is gradually serious in Gao Lusheng postpartum period, and the thickness monitoring is more meaningful, but the thickness is often undetectable due to the damage of a thermocouple and a sensor. In addition, the hearth area where the high temperature molten liquid slag iron is present is also limited to sensors that use some metallic materials. Although the impact echo method has the advantages of convenient test and low test cost, the test precision is low, the hearth environment is complex, the water pipes are dense, and the impact echo method is difficult to test. Therefore, the method can not accurately measure the thickness of the furnace lining in the long-term running process of the blast furnace, and the defects of the prior measuring scheme are unavoidable. The measuring method provided by the embodiment of the invention is specifically described below to accurately measure the thickness of the furnace lining of the blast furnace.
Referring to fig. 1, an embodiment of the present invention provides a method for measuring a thickness of a lining of a blast furnace, the method including:
s11, acquiring a thermal infrared image of a region to be measured when the blast furnace operates.
Specifically, the thermal infrared image is an image formed by receiving and recording thermal radiation energy emitted by a blast furnace during operation by a thermal infrared imager (or thermal infrared scanner). Referring to fig. 2, when the blast furnace 1 is in operation, the heat of the molten steel in the blast furnace can be radiated outwards through the furnace lining, so that the molten steel can be received by the thermal infrared imager 2, the thermal infrared imager 2 comprises a lens 3, a grating 4 and a detector 5, and the infrared rays of the region to be detected on the blast furnace sequentially pass through the lens 3 and the grating 4 and then are imaged by a photosensitive element on the detector 5 to output a thermal infrared image 6. The suitable thermal infrared imager can be selected according to the temperature fluctuation range of the temperature of the blast furnace shell, the resolution can be 384 multiplied by 288, and the thermal infrared imager is preferably an online temperature measurement type. Referring to fig. 3, the thermal infrared imager may form a thermal image of the surface of an object by receiving infrared rays emitted from the blast furnace, and output the thermal image to an image acquisition card of the processing terminal for image processing, where the area to be detected may be any area needing to be monitored on the periphery of the blast furnace, for example, a lower portion of the furnace body, a waist area or a lower portion of the hearth iron notch. The main area affecting the life of the blast furnace is the mushroom erosion area below the hearth tap hole, so that the mushroom erosion area below the tap hole is subjected to infrared thermal imaging, and other parts can also be subjected to infrared thermal imaging. And (3) installing the thermal infrared imager on the side surface of the region to be detected to obtain a thermal infrared image of the region to be detected, and entering step S12 after obtaining the thermal infrared image.
S12, filtering the thermal infrared image to obtain a first processed image.
Specifically, because the environment is bad when the blast furnace runs, various interference factors such as more dust, equipment thermal noise and the like exist, the thermal infrared image is filtered, and the influence of the interference factors on a measurement result can be restrained. The filtering mode can adopt a nonlinear filter for processing, so that the first processed image is clearer and sharper; of course, other smoothing filtering methods may be used to perform the processing, and the quality of the obtained first processed image may be higher, which is not particularly limited herein.
In practical application, referring to fig. 4, the original state of the thermal infrared image has more noise due to pulse interference, and the partial filtering mode cannot be effectively suppressed. Based on this, in a specific embodiment, filtering the thermal infrared image to obtain a first processed image includes:
Acquiring a first pixel window with a preset specification, wherein the first pixel window comprises at least 3 pixel points; performing median filtering processing on the thermal infrared image according to the first pixel window so as to update the pixel gray value of the thermal infrared image; and outputting an updating result of the thermal infrared image to obtain a first processed image.
Specifically, the preset specification of the first pixel window may be determined according to the requirement of actual median filtering, for example, the number of pixels of the first pixel window is set to be 3×3; of course, other specifications are also possible. When the median filtering is performed, the pixel points in the first pixel window can be arranged in a descending order or an ascending order, the intermediate value of an arrangement array is determined, the gray value of the central pixel point of the first pixel window is updated to the intermediate value, the gray values of all the pixel points of the thermal infrared image are updated accordingly, and the updating result of the thermal infrared image is determined to be the first processed image. The median filtering can effectively inhibit impulse interference-level salt-pepper noise, and can effectively protect edges from blurring while inhibiting random noise. Taking median filtering of the target pixel f (x, y) as an example, 8 adjacent pixel values of the input f (x, y) are arranged from small to large, and are denoted as x0, x1, x2, …, x7, an intermediate value m (x, y) = (x3+x4)/2 is calculated, and an output pixel value g (x, y) is:
g (x, y) =f (x, y) -m (x, y) to update the gray value of the target pixel, and the median filtering process result can refer to fig. 5.
In a specific embodiment, after outputting the updated result of the thermal infrared image to obtain the first processed image, the method further includes:
acquiring a plurality of first processing images output by a preset duration; according to the plurality of first processed images, gray average values of the same pixel areas of the plurality of first processed images are obtained; and updating the gray values of the corresponding pixel areas according to the gray average value until the gray value updating of all the pixel areas is completed, so as to obtain an updated first processed image.
Specifically, the thermal infrared images are shot and output based on a preset acquisition frequency on the thermal infrared imager, the preset time length can be set according to measurement requirements, for example, 5s, a plurality of first processing images output by the preset time length represent processing results of the thermal infrared images after median filtering, and the average filtering effect is better when the number of the first processing images is larger. The pixel area can be a pixel point or an area formed by a plurality of pixel points, the gray average value represents the gray average value of a plurality of first processing images in the same pixel area, the gray average value is used for replacing the gray value of the corresponding pixel area, the gray value of the pixel area can be determined more accurately, the gray values of all the pixel areas are updated and replaced accordingly, an updated first processing image is obtained, and the Gaussian noise in the image is well inhibited in the mean filtering mode.
For example, the median filter image F (x, y) is an n×n pixel point matrix, and the G (x, y) is an image after the mean processing, where the gray value of each pixel point in the image is determined by the mean value of the pixel gray values in the pixel region included in the pixel point (x, y), that is, the image may be subjected to the mean smoothing process by the following formula.
Where x, y=0, 1,2, …, N-1, s is the set of pixels (x, y) in the pixel area [ except for the pixel (x, y), M is the total number of pixels in the pixel area, the upper bound in the summation formula is determined by the number of the first processed images output by the preset duration, and the processing result of the average filtering can refer to fig. 6.
In practical application, although the mean filtering has a good suppression effect on Gaussian noise, salt and pepper noise still exists in the updated first processed image. Based on this, in a specific embodiment, after the gray value update of all the pixel areas is completed, the method further includes:
Dividing the updated first processed image into a plurality of second pixel windows with preset specifications; obtaining a weight gray value of each pixel point according to a preset weight coefficient and the gray value of each pixel point in the second pixel window; and determining the gray level value of the second pixel window according to the weight gray level value positioned at the center of the second pixel window so as to update the first processed image again.
Specifically, the preset specification and the preset weight coefficient of the second pixel window can be determined according to experience of a technician, or can be determined according to a calibration experiment, and the salt and pepper noise can be effectively suppressed. After the mean value filtering is finished, the weighted average filtering is adopted to inhibit impulse interference and salt and pepper noise existing in the image, so that the image noise is inhibited and the edge of the image is kept clear through filtering in two aspects of time and space scale.
Taking the example of setting a3×3 matrix for the number of pixels in the second pixel window, and setting the gray value of the second pixel window F (i, j) to be F (i, j), the gray value composition of the second pixel window is:
the weight matrix is as follows:
Where w (i, j) =1/2 (i.e. 0.5).
The other pixels of the weight matrix are:
wherein m and n are-1, 0 and 1 respectively, and 0 cannot be taken at the same time.
Multiplying the weights at the corresponding positions of each pixel point of the second pixel window, namely updating the first processed image G (i, j) again to be:
The impulse interference and the salt and pepper noise existing in the image are suppressed by adopting weighted average filtering, so that the image noise is suppressed and the edge of the image is kept clear by filtering in two aspects of time and space, the processing result of the weighted average filtering can be seen in fig. 7, and the step S13 is carried out after the first processing image is obtained by filtering the thermal infrared image.
S13, performing image segmentation on the first processed image according to image features to obtain a second processed image, wherein the image features at least comprise gray features or texture features of the first processed image.
In particular, the image segmentation is to divide the first processed image into a plurality of specific regions with unique properties, and the image features may be gray features or texture features. Thus, image segmentation may be performed based on a gray threshold, dividing pixels greater than the gray threshold into regions having target features, and dividing pixels not greater than the gray threshold into other regions to divide regions having high temperature point features; of course, the picture division may be performed based on other modes, so that the pixels in the same region satisfy the homogeneity, and the properties of the pixels in different regions are different from each other. The filtered first processed image is converted into a more abstract, compact form by image segmentation, providing conditions for further analysis.
In a specific embodiment, image segmentation is performed on the first processed image according to the image characteristics to obtain a second processed image, including:
Acquiring a histogram of gray features corresponding to the first processed image; determining a first sample center of the first processed image according to the gray upper limit value of the histogram; obtaining a second sample center according to the first sample center and a preset sample center distance; performing fuzzy clustering processing on the first processed image according to the first sample center and the second sample center, and updating the clustering center to perform iterative computation; and outputting the first processed image of the image segmentation when the clustering result reaches a preset target so as to obtain a second processed image.
Specifically, the histogram of the gray features characterizes the gray distribution condition of each pixel point on the first processed image, the first sample center of the first processed image can be determined through the gray upper limit value of the histogram, and different temperatures can correspond to different gray values for imaging when thermal infrared imaging is performed, so that the first sample center characterizes the initial sample center of the low-temperature region pixel point, the sample center distance can be set through a formula or a distance value, the first sample center is taken as the center, the sample center distance can be added to determine the second sample center, the second sample center characterizes the initial sample center of the high-temperature region pixel point, fuzzy clustering FCM (Fuzzy C-Mean) processing is performed according to the first sample center, and the clustering center is determined again for iterative calculation. The preset target may be that the number of iterative computations reaches a set number of times threshold, or that the clustered target pixels (or Wen Xiangsu points) reach a set number of thresholds, and then the first processed image of image segmentation is output to obtain a second processed image, where the purpose of fuzzy clustering processing is to segment the first processed image into Gao Wenxiang pixel areas representing high temperature.
Let the histogram { p t } (t=0, 1, …, 255) of the gray scale features (or sample sets) be given by the distance expression of each sample from the center of a known clustered sample: d tt′ = |t-t '| and the initial histogram p t and the iteratively calculated histogram p' t are not equal to 0, the steps of fuzzy clustering are as follows:
step one, taking the maximum pixel gray value of a histogram of gray features as a first sample center t 1';
Step two, determining a sample farthest from t 1 'as a first sample center t 2' according to the given distance expression;
Step three, calculating the distance d i1、di2 between each sample and t 1 ' and t 2 ' one by one, determining d i＝max{min(di1、di2), determining t 3 ' by the maximum value d max of each sample distance, and carrying out clustering calculation in an iterative manner;
And step four, if the required number C of the cluster centers (namely the number of the high Wen Xiangsu points) is reached, ending the searching process, otherwise, calculating the distance between the rest samples and the found cluster centers, and determining a new cluster center according to the same minimum and maximum criterion.
The first processed image is subjected to fuzzy clustering, that is, the image is divided into a high-temperature region representing a high-temperature feature and a low-temperature region representing a low-temperature feature, referring to fig. 8, a region with a lower gray value is a high-temperature region, and a region with a higher gray value is a low-temperature region, so as to obtain a second processed image, and step S14 is performed after the second processed image is obtained.
S14, obtaining temperature field information of the region to be detected according to the gray value of the target position on the second processed image and a preset corresponding relation, wherein the preset corresponding relation is the corresponding relation between the temperature value and the gray value.
Specifically, the target position may be a preset position of the thickness of the furnace lining to be measured on the blast furnace, or may be a position point of a molten iron solidification line in the furnace, or an intersection point position of erosion lines of brick lining of a hearth in the blast furnace. The temperature value has a corresponding relation with the gray value, and the gray value is smaller when the temperature value is larger; on the contrary, the gray values are larger when the temperature values are smaller, a preset corresponding relation is constructed according to the gray values, the corresponding temperature values are determined in the preset corresponding relation based on the gray values of a plurality of target positions on the second processed image, and then the temperature field information of the region to be detected can be obtained, and the step S15 is carried out after the temperature field information is obtained.
S15, determining the thickness of the furnace lining of the region to be detected according to the temperature field information.
Specifically, referring to fig. 9, the temperature field information characterizes the temperature distribution condition of the region to be measured, and when the thickness of the furnace lining is determined through the temperature field information, the corresponding relationship between the temperature and the thickness of the furnace lining can be constructed based on experiments, so as to determine the thickness of the furnace lining.
In a specific embodiment, determining the thickness of the furnace lining of the region to be measured according to the temperature field information comprises:
obtaining furnace shell temperatures of a plurality of target positions according to the temperature field information, wherein the target positions are erosion line intersection point positions of hearth brick liners in the blast furnace; inputting a plurality of furnace shell temperatures into a preset temperature calculation model to obtain a temperature conversion coefficient of each target position, wherein the temperature conversion coefficient is used for representing the temperature change proportion when the radial distance from the target position to the blast furnace is increased; obtaining a target isothermal curve of the blast furnace in a target direction according to the temperature of each furnace shell and the corresponding temperature conversion coefficient; obtaining a peripheral curve of the region to be measured according to the region parameters of the region to be measured and the outer diameter of the blast furnace, wherein the region parameters are the central angle or the region arc length of the region to be measured; and determining the thickness of the furnace lining according to the interval distance between the target isothermal curve and the peripheral curve.
Specifically, referring to fig. 9 and 10, in a blast furnace, a hearth lining is built by refractory bricks, a masonry gap exists between adjacent refractory bricks to form an erosion line 7, the erosion line 7 comprises an erosion warp and an erosion weft, an intersection point of the erosion line is a target position 8, the furnace shell temperature of the position can be determined through a gray value of the target position 8 and a preset corresponding relation, the furnace shell temperature comprises a first temperature region 9, a first temperature region 10 and a third temperature region 11, and the temperature sequentially decreases from the first temperature region 9, the first temperature region 10 and the third temperature region 11.
The temperature calculation model may be a finite element calculation model including a temperature interpolation function, and assuming that the furnace shell temperature Ti on a certain unit is a linear function of the position coordinates x and r, that is, t=a1+a2x+a3r, where a1, a2, a3 are constants to be determined, the constants to be determined may be determined from the furnace shell temperature.
From the above equation, a1, a2, a3 can be obtained by matrix inversion
Obtaining the temperature conversion coefficient kij of each target position, and obtaining the temperature (pi is converted value) in the furnace of the target position
Solving the equation set can obtain the hearth temperature distribution in the target direction, the target direction can be the erosion warp direction or the erosion weft direction, the target isothermal curve in the target direction is obtained through each furnace shell temperature and the corresponding temperature conversion coefficient, the target isothermal curve represents the fitting curve of the same temperature points in the furnace, the temperature value of the target isothermal curve can be set to 1150 ℃, the position of the 1150 ℃ isothermal line is obtained, the outer diameter of the blast furnace is known, the peripheral curve can be obtained through the central angle or the regional arc length of the region to be detected, the interval distance between the target isothermal curve and the peripheral curve is the thickness of the furnace lining, and the erosion condition of the hearth can be predicted according to the target isothermal curve, so that the residual thickness of the hearth is obtained. The thermal transmission calculation shows that the thickness of the carbon brick at the local part is 700-800mm, and the carbon brick belongs to the safety range.
In a specific embodiment, obtaining a target isothermal curve of the blast furnace in a target direction according to the furnace shell temperature and a corresponding temperature conversion coefficient comprises:
Obtaining a target position of each target temperature in a target direction according to the temperature of each furnace shell and the temperature conversion coefficient; and obtaining a target isothermal curve according to the fitting curves of the plurality of target positions based on the adjacent relation.
Specifically, referring to fig. 10, the furnace shell temperature of the target position O 1-O7 may be obtained according to a preset corresponding relationship, the target position P 1-P7 of each target temperature in the target direction is obtained through a temperature conversion coefficient and each furnace shell temperature, a fitting curve is generated based on the adjacent relationship of the plurality of target positions P 1-P7, so as to obtain a target isothermal curve L, and when the target direction is the direction of the erosion warp, the thickness of the cross section furnace lining of the blast furnace in the target position may be obtained.
Based on the same inventive concept as the measuring method, the embodiment of the invention also provides a measuring device for the thickness of a blast furnace lining, referring to fig. 11, the device comprises:
the acquisition module 101 is used for acquiring a thermal infrared image of a region to be measured when the blast furnace runs;
The first obtaining module 102 is configured to perform filtering processing on the thermal infrared image to obtain a first processed image;
A second obtaining module 103, configured to perform image segmentation on the first processed image according to image features, to obtain a second processed image, where the image features at least include gray features or texture features of the first processed image;
a third obtaining module 104, configured to obtain temperature field information of the area to be measured according to a gray value of the target position on the second processed image and a preset corresponding relationship, where the preset corresponding relationship is a corresponding relationship between a temperature value and a gray value;
and the determining module 105 is used for determining the thickness of the furnace lining of the region to be detected according to the temperature field information.
In an alternative embodiment, the first obtaining module includes:
The first acquisition sub-module is used for acquiring a first pixel window with preset specification, wherein the first pixel window comprises not less than 3 pixel points;
The first updating sub-module is used for carrying out median filtering processing on the thermal infrared image according to the first pixel window so as to update the pixel gray value of the thermal infrared image;
and the first output sub-module is used for outputting the updating result of the thermal infrared image so as to obtain the first processed image.
In an alternative embodiment, the first obtaining module further includes:
the second acquisition sub-module is used for acquiring a plurality of first processed images output by a preset duration;
The first obtaining submodule is used for obtaining the gray average value of the same pixel area of the plurality of first processed images according to the plurality of first processed images;
And the second obtaining submodule is used for updating the gray values corresponding to the pixel areas according to the gray average value until the gray value updating of all the pixel areas is completed so as to obtain the updated first processed image.
In an alternative embodiment, the first obtaining module further includes:
The dividing sub-module is used for dividing the updated first processing image into a plurality of second pixel windows with preset specifications;
a third obtaining sub-module, configured to obtain a weight gray value of each pixel point according to a preset weight coefficient and a gray value of each pixel point in the second pixel window;
And the second updating sub-module is used for determining the gray value of the second pixel window according to the weight gray value positioned at the center of the second pixel window so as to update the first processed image again.
In an alternative embodiment, the second obtaining module obtains a second processed image, including:
a third obtaining sub-module, configured to obtain a histogram of the first processed image corresponding to the gray feature;
A first determining sub-module, configured to determine a first sample center of the first processed image according to a gray upper limit value of the histogram;
a fourth obtaining sub-module, configured to obtain a second sample center according to the first sample center and a preset sample center distance;
the second updating sub-module is used for carrying out fuzzy clustering processing on the first processed image according to the first sample center and the second sample center, and updating a clustering center to carry out iterative computation;
And a fifth obtaining sub-module, configured to output the first processed image of the image segmentation when the clustering result reaches a preset target, so as to obtain the second processed image.
In an alternative embodiment, the determining module includes:
A sixth obtaining submodule, configured to obtain furnace shell temperatures of a plurality of target positions according to the temperature field information, where the target positions are erosion line intersection positions of hearth bricks in the blast furnace;
A seventh obtaining submodule, configured to input a plurality of furnace shell temperatures into a preset temperature calculation model, and obtain a temperature conversion coefficient of each target position, where the temperature conversion coefficient is used to characterize a temperature change ratio when a radial distance from the target position to the blast furnace increases;
an eighth obtaining submodule, configured to obtain a target isothermal curve of the blast furnace in a target direction according to each furnace shell temperature and the corresponding temperature conversion coefficient;
A ninth obtaining submodule, configured to obtain a peripheral curve of the region to be measured according to a region parameter of the region to be measured and an outer diameter of the blast furnace, where the region parameter is a central angle or a region arc length of the region to be measured;
and the second determination submodule is used for determining the thickness of the furnace lining according to the interval distance between the target isothermal curve and the peripheral curve.
In an alternative embodiment, the eighth obtaining sub-module includes:
A first obtaining unit configured to obtain a target position of each target temperature in the target direction based on each of the furnace shell temperatures and the temperature conversion coefficients;
And the second obtaining unit is used for obtaining the target isothermal curves according to a plurality of fitting curves of the target positions based on adjacent relations.
Based on the same inventive concept as the measurement method, an embodiment of the invention also provides an electronic device comprising a processor and a memory coupled to the processor, the memory storing instructions which, when executed by the processor, cause the electronic device to perform the steps of any one of the measurement methods.
Based on the same inventive concept as the measurement method, the embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements the steps of any one of the measurement methods.
The technical scheme provided by the embodiment of the invention has at least the following technical effects or advantages:
The method comprises the steps of obtaining a thermal infrared image of a region to be measured when a blast furnace runs, performing filtering processing on the thermal infrared image to obtain a first processing image so as to inhibit various kinds of interference such as dust, equipment thermal noise and the like in a blast furnace measuring environment, taking gray level characteristics or texture characteristics of the first processing image as image characteristics, performing image segmentation on the first processing image to obtain a second processing image, and obtaining temperature field information of the region to be measured according to a corresponding relation between gray level values of pixels on the second processing image and temperature values and a preset corresponding relation according to gray level values of target positions on the second processing image. The method can analyze the thickness of the lining and the defect position in the blast furnace through the thermal infrared image, so that the severity degree of the defect and the size of the defect area can be accurately measured, an operator can improve the operation method, a maintenance and construction scheme can be formulated, grouting lining construction can be guided, and the service life of the blast furnace lining can be prolonged. In addition, the maintenance construction quality of the blast furnace can be checked by adopting the thermal infrared image, so that the safe and reliable operation of the equipment after the recovery is ensured.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (modules, systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. A method for measuring the thickness of a blast furnace lining, the method comprising:
acquiring a thermal infrared image of a region to be measured when the blast furnace operates;
filtering the thermal infrared image to obtain a first processed image;
Image segmentation is carried out on the first processed image according to image characteristics to obtain a second processed image, wherein the image characteristics at least comprise gray level characteristics or texture characteristics of the first processed image;
Obtaining temperature field information of the region to be detected according to a gray value of a target position on the second processing image and a preset corresponding relation, wherein the preset corresponding relation is a corresponding relation between the temperature value and the gray value, and the target position is an erosion line intersection point position of a hearth brick lining in the blast furnace;
Determining the thickness of a furnace lining of the region to be detected according to the temperature field information;
the filtering processing is performed on the thermal infrared image to obtain a first processed image, including:
acquiring a first pixel window with a preset specification, wherein the first pixel window comprises at least 3 pixel points;
Performing median filtering processing on the thermal infrared image according to the first pixel window so as to update the pixel gray value of the thermal infrared image;
Outputting an update result of the thermal infrared image to obtain the first processed image;
the image segmentation is carried out on the first processed image according to the image characteristics to obtain a second processed image, and the method comprises the following steps:
acquiring a histogram of the first processed image corresponding to the gray feature;
Determining a first sample center of the first processed image according to the gray upper limit value of the histogram;
Obtaining a second sample center according to the first sample center and a preset sample center distance;
performing fuzzy clustering processing on the first processed image according to the first sample center and the second sample center, and updating a clustering center to perform iterative computation;
Outputting the first processed image of image segmentation when the clustering result reaches a preset target to obtain the second processed image, wherein the preset target is that the number of iterative computation reaches a set number threshold or the clustered target pixel points reach a set number threshold.
2. The method according to claim 1, wherein after the outputting of the updated result of the thermal infrared image to obtain the first processed image, the method further comprises:
Acquiring a plurality of first processing images output by a preset duration;
obtaining gray average values of the same pixel areas of the plurality of first processed images according to the plurality of first processed images;
and updating the gray value of the corresponding pixel area according to the gray average value until the gray value of all the pixel areas is updated, so as to obtain the updated first processed image.
3. The method for measuring thickness of a blast furnace lining according to claim 2, wherein after the gray value update of all the pixel areas is completed, the method further comprises:
Dividing the updated first processed image into a plurality of second pixel windows with preset specifications;
Obtaining a weight gray value of each pixel point according to a preset weight coefficient and the gray value of each pixel point in the second pixel window;
And determining the gray level value of the second pixel window according to the weight gray level value positioned at the center of the second pixel window so as to update the first processed image again.
4. The method for measuring the thickness of a furnace lining according to claim 1, wherein the determining the thickness of the furnace lining of the region to be measured according to the temperature field information comprises:
Obtaining furnace shell temperatures of a plurality of target positions according to the temperature field information;
Inputting a plurality of furnace shell temperatures into a preset temperature calculation model to obtain a temperature conversion coefficient of each target position, wherein the temperature conversion coefficient is used for representing a temperature change proportion when the radial distance from the target position to the blast furnace is increased;
Obtaining a target isothermal curve of the blast furnace in a target direction according to the temperature of each furnace shell and the corresponding temperature conversion coefficient;
Obtaining a peripheral curve of the region to be detected according to the region parameters of the region to be detected and the outer diameter of the blast furnace, wherein the region parameters are central angles or region arc lengths of the region to be detected;
and determining the thickness of the furnace lining according to the interval distance between the target isothermal curve and the peripheral curve.
5. The method according to claim 4, wherein the obtaining a target isothermal curve of the blast furnace in a target direction according to the furnace shell temperature and the corresponding temperature conversion coefficient comprises:
Obtaining a target position of each target temperature in the target direction according to each furnace shell temperature and the temperature conversion coefficient;
and obtaining the target isothermal curves according to the fitting curves of the target positions based on the adjacent relation.
6. A device for measuring the thickness of a blast furnace lining, characterized in that the device is a device corresponding to the measuring method of any one of claims 1-5, the device comprising:
The acquisition module is used for acquiring a thermal infrared image of a region to be detected when the blast furnace operates;
The first obtaining module is used for carrying out filtering processing on the thermal infrared image to obtain a first processed image;
the second obtaining module is used for carrying out image segmentation on the first processed image according to image characteristics to obtain a second processed image, wherein the image characteristics at least comprise gray characteristics or texture characteristics of the first processed image;
The third obtaining module is used for obtaining the temperature field information of the region to be detected according to the gray value of the target position on the second processing image and a preset corresponding relation, wherein the preset corresponding relation is the corresponding relation between the temperature value and the gray value;
and the determining module is used for determining the thickness of the furnace lining of the region to be detected according to the temperature field information.
7. An electronic device comprising a processor and a memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the electronic device to perform the steps of the method of any of claims 1-5.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211486492.0A CN115786614B (en) | 2022-11-24 | 2022-11-24 | Method and device for measuring thickness of blast furnace lining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211486492.0A CN115786614B (en) | 2022-11-24 | 2022-11-24 | Method and device for measuring thickness of blast furnace lining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115786614A CN115786614A (en) | 2023-03-14 |
| CN115786614B true CN115786614B (en) | 2024-06-25 |
Family
ID=85441313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211486492.0A Active CN115786614B (en) | 2022-11-24 | 2022-11-24 | Method and device for measuring thickness of blast furnace lining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115786614B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270237A (en) * | 2020-10-22 | 2021-01-26 | 中冶南方工程技术有限公司 | Blast furnace gas flow state identification method, system and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927347B (en) * | 2021-02-01 | 2022-05-20 | 中南大学 | Visualization method and system for temperature field data of blast furnace reflow zone |
-
2022
- 2022-11-24 CN CN202211486492.0A patent/CN115786614B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270237A (en) * | 2020-10-22 | 2021-01-26 | 中冶南方工程技术有限公司 | Blast furnace gas flow state identification method, system and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于神经网络的铜转炉内壁蚀损红外检测方法;刘飞飞等;红外技术;第30卷(第12期);697-701 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115786614A (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108998608B (en) | A kind of blast furnace iron notch molten iron temperature measurement method and system based on infrared machine vision | |
| CN102547365B (en) | Black edge detection method and device for video image | |
| Khanzadeh et al. | A methodology for predicting porosity from thermal imaging of melt pools in additive manufacturing thin wall sections | |
| JP7027536B2 (en) | Analysis system and analysis method | |
| EP3229156B1 (en) | Predicting cracking in cooled metal or alloy components | |
| CN117235672B (en) | Comprehensive pipe gallery fault diagnosis method and device based on multi-source data | |
| CN109493292B (en) | Enhancement processing method and device based on infrared temperature measurement image of power equipment | |
| CN104778361A (en) | Improved method for predicting hot-metal silicon content by EMD-Elman (empirical mode decomposition-Elman) neural network | |
| CN111830084B (en) | Furnace lining refractory material damage detection method | |
| WO2020241888A1 (en) | Model for predicting occurrence of corrosion under heat insulating material, and plant maintenance support device | |
| CN115786614B (en) | Method and device for measuring thickness of blast furnace lining | |
| CN114778684A (en) | Steel pipe performance evaluation method and system based on service scene | |
| CN115759409A (en) | Water gate deformation prediction method for optimizing LSTM (least Square TM) model by multi-time mode attention mechanism | |
| CN117520103B (en) | Temperature monitoring method for data center machine room based on thermal imaging | |
| CN111238927A (en) | Fatigue durability evaluation method and device, electronic equipment and computer readable medium | |
| Chen et al. | Edge and texture detection of metal image under high temperature and dynamic solidification condition | |
| CN110989856B (en) | Coordinate prediction method, device, equipment and storable medium | |
| JP7305509B2 (en) | Information processing device, its control method, program, and storage medium | |
| JP2019204351A (en) | Estimation device, estimation system, estimation method, and program | |
| CN118090078B (en) | Leakage online monitoring method for closed circulation water cooling system | |
| CN117358892B (en) | Deformation monitoring and early warning method and system for crystallizer copper pipe | |
| CN113649422A (en) | Hot image-based rough rolling billet quality detection system and method | |
| Gong et al. | Online Measurement Method of Molten Iron Temperature After Blast Furnace Skimmer Based on Infrared Vision | |
| CN112381792B (en) | Intelligent imaging on-line detection method for radar wave-absorbing coating/electromagnetic shielding film damage based on deep learning | |
| Han et al. | Infrared simulation of 4-bar target for the static performance evaluation of thermal imaging system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |