Converter lining thickness determination method and device, electronic equipment and storage medium

Abstract

The application discloses a converter lining thickness determination method and device, electronic equipment and storage medium. The specific scheme is: after the current furnace smelting is completed, the smelting parameters and infrared images of the target converter are obtained, wherein the infrared images are the images of the local area of the target converter;According to the infrared image, the target lining temperature of the target converter is determined, and according to the target lining temperature and the smelting parameters, the predicted lining spalling amount corresponding to the target converter under the current furnace is determined;According to the initial lining thickness information and the predicted lining spalling amount, the target lining thickness corresponding to the target converter is determined;Wherein, the initial lining thickness information is the lining thickness parameter determined before the target converter smelts in the current furnace. The application improves the efficiency and accuracy of determining the lining thickness of the converter.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method, apparatus, electronic device, and storage medium for determining the thickness of a converter lining. Background Technology

[0002] A converter generally refers to a tiltable cylindrical oxygen-blown steelmaking vessel. The furnace lining of a converter is typically made of magnesia-carbon bricks. However, during the smelting process of the molten iron in the converter, the addition of scrap steel and molten iron, the slag erosion during oxygen blowing, and the thermal radiation of the molten steel all cause wear or erosion to the converter lining. Over time, this can lead to the lining burning through, threatening the safety of on-site personnel.

[0003] Currently, the main method for detecting converter lining thickness involves using a 3D laser scanner to emit a laser signal and a laser receiver to receive the reflected laser signal. The thickness is determined by the time interval between the emitted and received signals. However, there are locations in the converter lining where laser measurement is inconvenient. For these locations, manual measurement is typically used. However, manual measurement is not only time-consuming and labor-intensive but also cannot guarantee the accuracy of the results. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for determining the thickness of a converter lining, which accurately and quickly determines the lining thickness of a target converter.

[0005] According to one aspect of the present invention, a method for determining the thickness of a converter lining is provided, the method comprising:

[0006] After the current furnace smelting is completed, the smelting parameters and infrared images of the target converter are obtained, where the infrared images are images of a local area of ​​the target converter.

[0007] Based on the infrared image, the target lining temperature of the target converter is determined, and based on the target lining temperature and smelting parameters, the predicted lining spalling amount of the target converter in the current heat is determined.

[0008] Based on the initial furnace lining thickness information and the predicted furnace lining spalling amount, the target furnace lining thickness corresponding to the target converter is determined;

[0009] The initial furnace lining thickness information refers to the furnace lining thickness parameters determined for the target converter before the current furnace smelting.

[0010] According to another aspect of the present invention, a converter lining thickness determining device is provided, the device comprising:

[0011] The data acquisition module is used to acquire the smelting parameters and infrared images of the target converter after the current smelting is completed. The infrared images are images of a local area of ​​the target converter.

[0012] The spalling amount determination module is used to determine the target furnace lining temperature of the target converter based on infrared images, and to determine the predicted spalling amount of the target converter in the current furnace cycle based on the target furnace lining temperature and smelting parameters.

[0013] The furnace lining thickness determination module is used to determine the target furnace lining thickness corresponding to the target converter based on the initial furnace lining thickness information and the predicted furnace lining spalling amount.

[0014] The initial furnace lining thickness information refers to the furnace lining thickness parameters determined for the target converter before the current furnace smelting.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory that is communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the converter lining thickness determination method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the converter lining thickness determination method of any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, characterized in that, when executed by a processor, the computer program implements a converter lining thickness determination method as described in any embodiment of the present invention.

[0021] The technical solution of this invention provides data support for determining the furnace lining thickness of the target converter by acquiring the smelting parameters and infrared images of the target converter after the current furnace smelting is completed. Based on the infrared image, the target furnace lining temperature of the target converter is determined. And based on the target furnace lining temperature and smelting parameters, the predicted furnace lining spalling amount of the target converter in the current furnace is determined, so as to determine the furnace lining thickness of the target converter after the completion of the current furnace smelting based on the predicted furnace lining spalling amount. Based on the furnace lining thickness parameters determined before the current furnace smelting and the predicted furnace lining spalling amount, the target furnace lining thickness of the target converter is determined. This invention solves the problems of incomplete measurement caused by laser measurement of furnace lining thickness in the prior art and the low efficiency and accuracy caused by manual measurement of furnace lining thickness. By quickly and accurately determining the target furnace lining thickness of the target converter through infrared images and smelting parameters, it not only improves the efficiency and accuracy of determining the furnace lining thickness, but also effectively avoids the furnace lining being burned through, ensuring the safety of on-site personnel.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for determining the thickness of a converter lining provided in an embodiment of the present invention;

[0025] Figure 2 This is an example diagram of the original infrared image provided in an embodiment of the present invention;

[0026] Figure 3 This is an example image of the original grayscale image provided in an embodiment of the present invention;

[0027] Figure 4 This is an example diagram of the processing of a denoised grayscale image using a preset gradient operator provided in an embodiment of the present invention;

[0028] Figure 5 This is an example diagram of a local area provided in an embodiment of the present invention;

[0029] Figure 6 This is a flowchart of a method for determining the thickness of a converter lining provided in an embodiment of the present invention;

[0030] Figure 7 This is an example diagram of training a furnace lining spalling prediction model provided in an embodiment of the present invention;

[0031] Figure 8 This is a line graph of the prediction error provided in an embodiment of the present invention;

[0032] Figure 9 This is a line graph showing the actual furnace lining spalling amount and the theoretical furnace lining spalling amount corresponding to the spalling thickness provided in the embodiments of the present invention;

[0033] Figure 10 This is a schematic diagram of a converter lining thickness determination device provided in an embodiment of the present invention;

[0034] Figure 11 This is a schematic diagram of the structure of an electronic device for implementing the converter lining thickness determination method of this invention. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0037] Example 1

[0038] Figure 1This is a flowchart of a method for determining the thickness of a converter lining according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the target lining thickness of the target converter is determined after the current furnace smelting is completed, using infrared images and the smelting parameters of the current furnace. This method can be executed by a converter lining thickness determining device, which can be implemented in hardware and / or software. This converter lining thickness determining device can be configured in electronic devices such as mobile phones, computers, or servers. Figure 1 As shown, the method includes:

[0039] S110. After the current furnace smelting is completed, acquire the smelting parameters and infrared image of the target converter, wherein the infrared image is an image of a local area of ​​the target converter.

[0040] A converter generally refers to a tiltable cylindrical oxygen-blown steelmaking vessel. The converter lining is typically made of magnesia-carbon bricks. During the converter smelting process, the lining is subject to impact or erosion, leading to lining spalling and, over time, potentially burn-through. To avoid this, the converter lining thickness can be determined to assess the risk of burn-through. The converter whose lining thickness needs to be determined can be used as a target converter.

[0041] The smelting parameters of the target converter can be understood as the smelting data of the target converter during the current heat smelting process. Optionally, the smelting parameters may include at least two of the following: furnace melt temperature after the current heat smelting, oxygen blowing duration during the current heat smelting process, oxygen flow rate during the current heat smelting process, total iron content (TFe) in the slag after the current heat smelting, magnesium oxide (MgO) content in the slag after the current heat smelting, and furnace lining life parameters of the target converter. The furnace lining life parameter can be determined by the following function.

[0042]

[0043] in, N represents the furnace lining life parameter of the target converter. i N represents the number of furnace cycles that have been completed in the target converter. n N represents the heat number corresponding to the last lining replacement / maintenance of the target converter. p This indicates the converter lining replacement cycle, i.e., how many heats are required to replace the target converter lining.

[0044] The infrared image of the target converter is an infrared image of a local area within the target converter. Optionally, the local area can be a region of the target converter with a relatively thin furnace lining. The local area can be determined by edge detection from the complete infrared image corresponding to the target converter.

[0045] Specifically, after the current heat of smelting in the target converter is completed, a complete infrared image of the target converter is acquired using infrared thermal imaging equipment, or an infrared video frame corresponding to the moment of completion of smelting in the target converter is acquired using infrared thermal imaging equipment. The complete infrared image or infrared video frame is processed into grayscale to perform edge detection and determine the local area of ​​the target converter. The infrared image corresponding to the local area is determined based on the complete infrared image or infrared video frame. Furthermore, the smelting parameters during the current heat of smelting are obtained from the corresponding database, and the amount of lining spalling in the target converter during the current heat of smelting is determined by using the smelting parameters and the infrared image.

[0046] In this embodiment of the invention, the method for obtaining the infrared image of the target converter may be as follows: obtaining the original infrared image of the target converter, performing grayscale processing on the original infrared image to determine the original grayscale image corresponding to the original infrared image; performing Gaussian filtering on the original grayscale image to obtain a denoised grayscale image, and processing the denoised grayscale image based on a preset gradient operator to determine at least one selectable edge pixel in the denoised grayscale image; determining at least one target edge pixel and a local region corresponding to the at least one target edge pixel based on the pixel value corresponding to the at least one selectable edge pixel and a preset pixel range; and determining the infrared image of the target converter based on the original infrared image and the local region.

[0047] The original infrared image can be understood as the complete infrared image corresponding to the target converter. Optionally, the original infrared image can be an infrared image of the target converter taken by an infrared thermal imager deployed in front of the target converter, or an infrared video frame corresponding to the moment when the current furnace smelting of the target converter is completed. For example, the original infrared image can be as follows: Figure 2 As shown. The original grayscale image can be obtained by grayscale processing of the original infrared image. For example, the original grayscale image can be as follows: Figure 3 As shown. Gaussian filtering can be based on Gaussian high-frequency filtering, applying a weighted average to each pixel in the original grayscale image to achieve denoising. The denoised grayscale image can be understood as the image obtained after denoising the original grayscale image. A preset gradient operator can be used to determine the direction and magnitude of pixel intensity changes in the denoised grayscale image to identify edge pixels to be selected. Edge pixels to be selected can be understood as pixels that may be at the edges of regions in the denoised grayscale image. Optionally, the preset gradient operator can be a Sobel gradient operator or a Canny operator. The preset pixel range can be a pre-set standard range of pixel values ​​in a local region. Target edge pixels can be edge pixels whose pixel values ​​satisfy the preset pixel range. The local region can be the furnace lining region corresponding to at least one target edge pixel. The local region is typically a region where the target converter lining is relatively thin.

[0048] Specifically, an infrared thermal imager is used to acquire images of the target converter, obtaining its original infrared image. The original infrared image is then processed using a grayscale conversion function to obtain the original grayscale image. Optionally, the grayscale conversion function can be expressed as follows:

[0049] Gray(i,j)=0.299×R(i,j)+0.587×G(i,j)+0.114×B(i,j)

[0050] Here, Gray(i,j) represents the grayscale value of the pixel at coordinate (i,j), R(i,j) represents the red channel value of the pixel at coordinate (i,j) in the original infrared image, G(i,j) represents the green channel value of the pixel at coordinate (i,j) in the original infrared image, and B(i,j) represents the blue channel value of the pixel at coordinate (i,j) in the original infrared image. Gaussian filtering is applied to the original grayscale image to remove noise, resulting in a denoised grayscale image. The denoised grayscale image is then processed according to a preset gradient operator; that is, the grayscale value of each pixel in the denoised grayscale image is compared with the grayscale values ​​of its neighboring pixels. If the grayscale value of a pixel is greater than the grayscale values ​​of all its neighboring pixels, that pixel is determined as a candidate edge pixel. Based on this, at least one candidate edge pixel is obtained. Based on the pixel value of at least one candidate edge pixel and a preset pixel range, candidate edge pixels whose pixel values ​​belong to the preset pixel range are selected as target edge pixels, thus obtaining at least one target edge pixel and a local region corresponding to the at least one target edge pixel. Based on the original infrared image and the local region, an infrared image of the local region is obtained, i.e., the infrared image of the target converter.

[0051] For example, an infrared thermal imager can be used to acquire the original infrared image of the target converter, or an infrared thermal imager can be used to acquire a video stream of the target converter after smelting is completed, and the video frame of the target converter at the moment of smelting completion can be used as the original infrared image. See also Figure 2 The original infrared image may contain 30,700 pixels. The original infrared image is then processed to grayscale using a grayscale conversion function to obtain the original grayscale image. See [link to relevant documentation]. Figure 3 A two-dimensional discrete Fourier transform is performed on each pixel in the original grayscale image to obtain the Fourier spectrum corresponding to the original grayscale image. The function of the two-dimensional discrete Fourier transform can be expressed as follows:

[0052]

[0053] Where f(x,y) represents the gray value of the pixel at coordinates (x,y) in the original grayscale image, (u,v) represents the coordinates corresponding to the pixel at coordinates (x,y) in the Fourier spectrum, M represents the number of horizontal pixels in the original grayscale image, N represents the number of vertical pixels in the original image, and -j is the imaginary number representing the transformation direction.

[0054] A Fourier spectrum is a type of colored image, but it differs from a normal colored image in that it uses color variations to reflect the structural complexity, image details, and noise in a grayscale image. The closer the color is to yellow, the more concentrated the image information in that area; conversely, a more pronounced yellow area indicates more noise (i.e., invalid image data). To improve the accuracy of subsequent processing, Gaussian high-frequency filtering (GFR) can be used in the OpenCV component of the AWT package in Java to process the Fourier spectrum corresponding to the original grayscale image, removing noise and obtaining a denoised Fourier spectrum. Then, a two-dimensional discrete Fourier transform is used to convert the denoised Fourier spectrum into a grayscale image, resulting in a denoised grayscale image.

[0055] Taking the Canny operator as the preset gradient operator as an example, the denoised grayscale image is processed using the Canny operator. Specifically, the grayscale value of each pixel in the denoised grayscale image is compared with the grayscale values ​​of its neighboring pixels. If the grayscale value of a pixel is greater than the grayscale values ​​of all its surrounding pixels, that pixel is selected as an edge pixel to be considered. For example, see... Figure 4 The central red area represents the current pixel block in the denoised grayscale image, and the eight arrows surrounding it represent the eight directions of the pixel gradient after discretization. By traversing and calculating, the maximum value of the pixel gradient is determined at point A. The gradient at point A is retained, and a vertical line is drawn along the direction at point A with point A as the foot of the perpendicular, which is the boundary.

[0056] By processing the denoised grayscale image using the aforementioned preset gradient operator, the direction and magnitude of pixel gradient changes in the denoised grayscale image can be determined, resulting in a gradient magnitude image. A dual-threshold method is then used to process the gradient magnitude image to identify local regions. Specifically, after performing non-maximum suppression on the gradient magnitude image, pixels with gradient values ​​greater than the preset maximum gradient value, or gradient values ​​greater than the preset maximum gradient value but less than the preset minimum gradient value, are identified using preset maximum and minimum gradient values. These pixels are then designated as target edge pixels. Local regions are determined using these target edge pixels. It should be noted that there can be one or more local regions. Figure 2 By performing the above processing on the original infrared image, it can be determined that... Figure 5The local area is shown in the red box. Based on this local area and the original infrared image, the infrared image of the target converter can be determined.

[0057] S120. Based on the infrared image, determine the target lining temperature of the target converter, and based on the target lining temperature and smelting parameters, determine the predicted lining spalling amount corresponding to the target converter in the current heat.

[0058] The target furnace lining temperature can be understood as the average furnace lining temperature corresponding to a local area. Optionally, the target furnace lining temperature can be determined based on the temperature value of each pixel in the local area and the number of pixels. The predicted furnace lining spalling amount can be understood as the target converter furnace lining spalling amount during the current furnace smelting process.

[0059] Specifically, the grayscale image corresponding to the infrared image of a local area is determined. Based on this grayscale image and the correspondence between grayscale values ​​and temperature values, the temperature value to be processed for each pixel in the local area is determined. Based on the temperature value to be processed for each pixel and the number of pixels in the local area, the average temperature, i.e., the target lining temperature of the target converter, is determined. The smelting parameters of the target converter in the current heat cycle are obtained from the relevant database. Based on the smelting parameters and the target lining temperature, the predicted lining spalling amount corresponding to the target converter in the current heat cycle is determined.

[0060] In this embodiment of the invention, the method for determining the target furnace lining temperature may be as follows: based on the highest and lowest temperature values ​​in the original infrared image, and the maximum and minimum grayscale values ​​in the original grayscale image, determine the conversion parameters to be used; determine the grayscale image to be processed corresponding to the infrared image, and determine the temperature value to be processed for each pixel according to the grayscale value to be processed, the maximum grayscale value, and the conversion parameters to be used for each pixel in the grayscale image to be processed; and determine the target furnace lining temperature of the target converter based on the number of pixels in the local area and the temperature value to be processed for each pixel.

[0061] The highest temperature value can be the temperature value corresponding to the pixel with the highest radiation intensity in the region corresponding to the target converter in the original infrared image. Similarly, the lowest temperature value can be the temperature value corresponding to the pixel with the lowest radiation intensity in the region corresponding to the target converter in the original infrared image. The maximum grayscale value can be understood as the highest grayscale value in the original grayscale image. The minimum grayscale value can be the lowest grayscale value in the original grayscale image. The conversion parameters to be used can be determined based on the highest temperature value, lowest temperature value, maximum grayscale value, and minimum grayscale value. The conversion between grayscale values ​​and temperature values ​​can be achieved through the conversion parameters to be used. Optionally, the conversion parameters to be used can be determined by the following function.

[0062]

[0063] Among them, T max The highest temperature value, T min Y is the lowest temperature value. max For the maximum grayscale value, Y min The minimum grayscale value is denoted by k, which represents the conversion parameter to be used.

[0064] The grayscale image to be processed can be obtained by grayscale processing of an infrared image, or it can be determined when defining a local region based on the original grayscale image. The grayscale value of each pixel in the grayscale image to be processed is used as the grayscale value to be processed. The temperature value to be processed can be understood as the temperature value obtained after converting the grayscale value to be processed. The target furnace lining temperature can be the average temperature determined based on the number of pixels corresponding to the local region and the temperature value to be processed for each pixel. Optionally, the function for determining the temperature value to be processed can be as follows.

[0065] T (i，j) =(Y (i,j) -Y max )×k+Y max

[0066] Among them, T (i，j) Y represents the temperature value to be processed for the pixel with pixel coordinates (i,j). (i,j) Y represents the grayscale value to be processed for the pixel with pixel coordinates (i,j). max The maximum grayscale value is represented by k, which represents the conversion parameter to be used.

[0067] Specifically, the original infrared image is analyzed to determine the highest and lowest temperature values ​​corresponding to the target converter area within the original infrared image. The temperature difference between the highest and lowest temperatures is then determined. Based on the maximum and minimum grayscale values ​​in the original grayscale image, the grayscale difference between the maximum and minimum grayscale values ​​is determined. The ratio of the temperature difference to the grayscale difference is used as the conversion parameter. The corresponding grayscale image to be processed is determined, and based on the conversion parameter and the maximum grayscale value, the grayscale value corresponding to each pixel in the grayscale image is converted to determine the temperature value to be processed for each pixel. Based on the number of pixels in a local area of ​​the grayscale image and the temperature value to be processed for each pixel, the average temperature is determined and used as the target furnace lining temperature for the target converter.

[0068] S130. Based on the initial furnace lining thickness information and the predicted furnace lining spalling amount, determine the target furnace lining thickness corresponding to the target converter.

[0069] The initial lining thickness information refers to the lining thickness parameters determined for the target converter before the current heat. The lining thickness parameters can be understood as the thickness of the target converter before the current heat. The target lining thickness can be understood as the thickness of the lining after the current heat. The target lining thickness can be used to determine whether the target converter is at risk of burn-through.

[0070] Specifically, the initial lining thickness information of the target converter before the current heat is obtained. The difference between the initial lining thickness information and the predicted lining spalling amount is then calculated to obtain the target lining thickness corresponding to the target converter.

[0071] In this embodiment of the invention, the target furnace lining thickness can be determined by: subtracting the initial furnace lining thickness information from the predicted furnace lining spalling amount to obtain the target furnace lining thickness corresponding to the target converter, so that when the target furnace lining thickness does not reach the preset furnace lining thickness threshold, an early warning message is generated and an early warning is issued based on the target furnace lining thickness.

[0072] The preset furnace lining thickness threshold can be a pre-set standard value for the target converter lining thickness. The warning message can be used to alert relevant personnel that the target converter lining thickness has not reached the preset threshold, requiring replacement or repair of the target converter lining.

[0073] Specifically, the initial lining thickness information of the target converter before the current heat smelting is obtained. The difference between the initial lining thickness information and the predicted lining spalling amount is determined, and this difference is used as the target lining thickness. If the target lining thickness does not reach the preset lining thickness threshold, it indicates that the lining of the target converter is at risk of being burned through. In this case, an early warning message can be generated based on the target lining thickness, and warning processing can be performed.

[0074] For example, the preset lining thickness threshold can be 60% of the original lining thickness of the target converter, where the original lining thickness can be understood as the thickness of a brand new, unrefined lining. After determining the target lining thickness based on the difference between the initial lining thickness information and the predicted lining spalling amount, it is then determined whether the target lining thickness exceeds 60% of the original lining thickness. If so, no warning action is required. If not, a warning message is generated based on the target lining thickness, and the warning action is initiated so that relevant personnel can promptly repair or replace the lining of the target converter to prevent burn-through and leakage.

[0075] The technical solution of this embodiment acquires the smelting parameters and infrared images of the target converter after the current heat smelting is completed, providing data support for subsequently determining the furnace lining thickness of the target converter. Based on the infrared image, the target furnace lining temperature of the target converter is determined. And based on the target furnace lining temperature and smelting parameters, the predicted furnace lining spalling amount of the target converter in the current heat is determined, so as to determine the furnace lining thickness of the target converter after the completion of the current heat smelting based on the predicted furnace lining spalling amount. Based on the furnace lining thickness parameters determined before the current heat smelting and the predicted furnace lining spalling amount, the target furnace lining thickness of the target converter is determined. This invention solves the problems of incomplete measurement caused by laser measurement of furnace lining thickness in the prior art and the low efficiency and accuracy caused by manual measurement of furnace lining thickness. By quickly and accurately determining the target furnace lining thickness of the target converter through infrared images and smelting parameters, it not only improves the efficiency and accuracy of determining the furnace lining thickness, but also effectively avoids the furnace lining being burned through, ensuring the safety of on-site personnel.

[0076] Example 2

[0077] Figure 6 This is a flowchart of a method for determining converter lining thickness according to Embodiment 2 of the present invention. This embodiment is a refinement of the step "determining the predicted lining spalling amount corresponding to the target converter in the current heat cycle based on the target lining temperature and smelting parameters" in the above embodiment. For specific implementation details, please refer to the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiment will not be repeated here. Figure 6 As shown, the method includes:

[0078] S210. After the current furnace smelting is completed, acquire the smelting parameters and infrared image of the target converter, wherein the infrared image is an image of a local area of ​​the target converter.

[0079] S220. Based on the infrared image, determine the target furnace lining temperature of the target converter, and process the smelting parameters based on multiple common factors to determine multiple input parameters corresponding to the smelting parameters.

[0080] The common factor determination function can be a function based on factor analysis and historical smelting parameters, used to characterize the correlation between smelting parameters. The input parameters can be common factor parameters obtained by substituting the smelting parameters into the common factor determination function.

[0081] Specifically, the grayscale image corresponding to the infrared image of a local area is determined. Based on this grayscale image and the conversion parameters to be used between grayscale values ​​and temperature values, the temperature value to be processed for each pixel in the local area is determined. Based on the temperature value to be processed for each pixel and the number of pixels in the local area, the average temperature, i.e., the target furnace lining temperature of the target converter, is determined. The smelting parameters are processed separately using multiple common factorization functions to determine multiple input parameters corresponding to the smelting parameters. Based on these input parameters and the target furnace lining thickness, the predicted furnace lining spalling amount is determined.

[0082] In this embodiment of the invention, before processing the smelting parameters based on multiple common factor determination functions, common factor determination functions can be obtained first. The determination of common factor determination functions can be achieved by: obtaining historical smelting parameters of the target converter in at least two dimensions under historical furnace cycles, wherein the at least two dimensions include at least two of the following: furnace liquid temperature, smelting time after filling with a preset gas, flow rate of the preset gas, proportion of a preset component in the slag, and usage time of the target converter; performing dimensionality reduction processing on the historical smelting parameters in at least two dimensions based on factor analysis, so that multiple common factor determination functions are obtained when the cumulative contribution rate corresponding to the factor analysis meets a preset condition.

[0083] Here, "historical furnace runs" can be understood as the historical furnace runs of the target converter's current furnace run. "Historical smelting parameters" refers to the smelting parameters during the historical furnace runs. These historical smelting parameters can include smelting parameters across at least two dimensions. These at least two dimensions include: furnace melt temperature, smelting time after filling with a preset gas, preset gas flow rate, preset component ratio in the slag, and the target converter's usage time.

[0084] Historical smelting parameters under the furnace melt temperature dimension can be the furnace melt temperature after the completion of a historical heat. The preset gas can be oxygen. Historical smelting parameters under the smelting time dimension after filling the preset gas can be the oxygen blowing time during the historical heat. Historical smelting parameters under the preset gas flow rate dimension can be understood as the oxygen flow rate during the historical heat. Historical smelting parameters under the preset component ratio dimension in the slag can be the total iron content, magnesium oxide content, and slag basicity in the slag after the completion of a historical heat. Historical smelting parameters under the target converter usage time dimension can be the lining life parameters of the target converter corresponding to the historical heat. The lining life parameters can be used to characterize the duration the target converter can be used after the current heat.

[0085] Factor analysis can reduce historical smelting parameters across at least two dimensions to a few common factor parameters, which can then be used to characterize the relationships between these parameters. The cumulative contribution rate can be used to characterize the representativeness of the common factor parameters extracted based on factor analysis for the historical smelting parameters across at least two dimensions. In other words, the higher the cumulative contribution rate, the stronger the representativeness of the corresponding common factor parameter. The preset condition can be a pre-set numerical condition that the cumulative contribution rate needs to reach. Optionally, the preset condition can be a cumulative contribution rate greater than 90%.

[0086] Specifically, historical smelting parameters of the target converter in the current heat are obtained from multiple historical heats. These historical smelting parameters include at least two of the following dimensions: molten metal temperature, smelting time after filling with a preset gas, flow rate of the preset gas, proportion of a preset component in the slag, and usage duration of the target converter. Factor analysis is used to perform dimensionality reduction on these historical smelting parameters in at least two of the above dimensions. To prevent excessive feature loss, multiple common factor determination functions can be obtained when the cumulative contribution rate corresponding to the factor analysis meets a preset condition. These common factor determination functions are then used to process the smelting parameters of the target converter in the current heat, yielding the corresponding common factor parameters, i.e., the input parameters.

[0087] For example, the historical smelting parameters under the dimension of furnace liquid temperature are taken as the endpoint temperature, the historical smelting parameters under the dimension of smelting time after filling the preset gas are taken as the blowing time, the historical smelting parameters under the dimension of preset gas flow rate are taken as the oxygen flow rate, the historical smelting parameters under the dimension of preset component ratio in slag are taken as TFe in slag, MgO in slag and slag basicity, and the historical smelting parameters under the dimension of target converter service life are taken as the furnace lining life parameters.

[0088] The raw smelting parameters for heats 269 to 1169 were obtained. Data preprocessing was performed on the raw smelting parameters to obtain historical smelting parameters for 500 heats. These historical smelting parameters include the endpoint temperature, blowing time, oxygen flow rate, TFe in slag, MgO in slag, slag basicity, and furnace lining life parameters for each historical heat. Table 1 below shows the information for these historical smelting parameters.

[0089] Table 1 Information on Historical Smelting Parameters

[0090]

[0091] Factor analysis was used to standardize the seven historical smelting parameters from the aforementioned 500 heats, and the correlation coefficient matrix corresponding to these parameters was determined. The correlation coefficient matrix was then processed to determine the common factor variables and their corresponding coefficients. When the cumulative contribution rate exceeded 90%, three common factor determination functions were obtained. For example, the common factor determination functions can be shown in Table 2 below.

[0092]

[0093]

[0094] Based on this, the smelting parameters of the current furnace of the target converter can be substituted into the above common factor determination function to obtain the common factor parameters F1, F2 and F3 corresponding to the smelting parameters of the current furnace, which are the parameters to be input.

[0095] S230. Input the parameters to be input and the target furnace lining temperature into the pre-trained furnace lining spalling prediction model to determine the predicted furnace lining spalling amount corresponding to the target converter in the current furnace cycle.

[0096] Among them, the furnace lining spalling prediction model can be a pre-trained model used to predict the furnace lining spalling amount of the target converter during the current furnace smelting process.

[0097] Specifically, based on the pre-trained furnace lining spalling prediction model, the input target furnace lining temperature and the parameters to be input are processed to obtain the predicted furnace lining spalling amount corresponding to the target converter in the current furnace cycle. Based on the predicted furnace lining spalling amount, the target furnace lining thickness of the target converter after the current furnace lining smelting is completed is determined.

[0098] In this embodiment of the invention, before processing the input parameters and target furnace lining temperature based on the pre-trained furnace lining spalling prediction model, the furnace lining spalling prediction model can be constructed and trained first. The furnace lining spalling prediction model is determined based on the particle swarm optimization algorithm and the backpropagation algorithm. The initial model parameters of the furnace lining spalling prediction model are obtained after updating and iterating the original model parameters based on the particle swarm optimization algorithm. The training method of the furnace lining spalling prediction model can be as follows: obtain multiple training samples, wherein the training samples include sample furnace lining temperatures, sample input parameters, and theoretical furnace lining spalling amounts corresponding to the sample furnace lining temperatures and sample input parameters; input the sample furnace lining temperatures and sample input parameters from the training samples into the furnace lining spalling prediction model to be trained to obtain the actual furnace lining spalling amounts; determine the loss value based on the theoretical furnace lining spalling amounts and the actual furnace lining spalling amounts; and correct the initial model parameters of the furnace lining spalling prediction model to be trained based on the loss value to obtain the trained furnace lining spalling prediction model.

[0099] Particle swarm optimization (PSO) is a swarm intelligence-based optimization algorithm. In PSO, each potential solution is abstracted as a "particle," which navigates through a high-dimensional solution space, seeking the optimal solution through information sharing and collaborative cooperation. In this embodiment of the invention, PSO is used to adjust and optimize the original model parameters of a furnace lining spalling prediction model. Backpropagation can be used to adjust the weights and biases of the furnace lining spalling prediction model to make its output closer to the theoretical furnace lining spalling amount. The furnace lining spalling prediction model to be trained can be a neural network model determined based on PSO and backpropagation. The original model parameters can be understood as the default parameters of the furnace lining spalling prediction model to be trained. The initial model parameters can be the model parameters obtained after optimizing and adjusting the original model parameters based on PSO.

[0100] The sample furnace lining temperature can be the average furnace lining temperature of a local area corresponding to a historical furnace run. The sample input parameters can be common factor parameters determined based on historical smelting parameters from previous furnace runs. The theoretical furnace lining spalling amount can be determined based on the furnace lining thickness information before and after smelting in previous furnace runs. The actual furnace lining spalling amount can be the furnace lining spalling amount predicted by the furnace lining spalling amount prediction model to be trained. The loss value can be understood as the difference between the actual furnace lining spalling amount and the theoretical furnace lining spalling amount.

[0101] Specifically, before training the furnace lining spalling prediction model based on training samples, multiple training samples can be obtained first to train the model. To improve the accuracy of the furnace lining spalling prediction model, as many and rich training samples as possible can be obtained. Sample furnace lining temperatures and sample input parameters corresponding to multiple historical furnace runs are obtained, and the theoretical furnace lining spalling amounts corresponding to the historical furnace runs are determined. The sample furnace lining temperatures and sample input parameters from the training samples are input into the furnace lining spalling prediction model to obtain the actual furnace lining spalling amount. A loss value is determined based on the actual and theoretical furnace lining spalling amounts, and this loss value is used to correct the model parameters of the furnace lining spalling prediction model. When correcting the model parameters in the furnace lining spalling prediction model using the loss value, the convergence of the loss function can be used as a training objective, such as whether the training error is less than a preset error, whether the error change tends to stabilize, or whether the current number of iterations is equal to a preset number. If the convergence condition is met, such as the training error of the loss function being less than a preset error, or the error trend stabilizing, it indicates that the training of the furnace lining spalling prediction model is complete, and iterative training can be stopped. If the convergence condition has not been met, other training samples can be obtained to continue training the furnace lining spalling prediction model until the training error of the loss function is within a preset range. When the training error of the loss function converges, the successfully trained furnace lining spalling prediction model is obtained.

[0102] For example, a PSO-BP model is determined based on the Particle Swarm Optimization (PSO) algorithm and the Backpropagation Algorithm (BP), and this PSO-BP model is used as the furnace lining spalling prediction model to be trained. The trained furnace lining spalling prediction model is obtained through forward iteration using the PSO algorithm and backpropagation training using the backpropagation algorithm. In the trained furnace lining spalling prediction model, the BP neural network contains a three-layer structure: an input layer, a hidden layer, and an output layer. The hidden layer has 9 nodes, the activation function is the Sigmoid activation function, and the PSO optimization parameters are selected as follows: Particle Swarm Optimization parameter 50, learning factor 1.5, and inertia weight 0.8.

[0103] See the examples above. Figure 7This paper uses the PSO-BP model as the model to predict furnace lining spalling for illustration. The PSO-BP model can be determined using MATLAB programming. 490 training samples and 10 test samples are set up. Before training the PSO-BP model, it can be determined based on the particle swarm optimization algorithm and backpropagation algorithm. The original model parameters are then optimized using the PSO algorithm to obtain the initial model parameters. That is, the optimization objective of the PSO algorithm is the hyperparameters of the BP neural network, and the input is the training samples.

[0104] Specifically, this can be done by setting particle swarm parameters and initializing particle position and velocity information. The fitness of each particle is calculated, which is the distance of each particle's position from the target. The individual optimal fitness of each particle and the population optimal fitness of the entire particle swarm are determined. Based on the individual optimal fitness and the population optimal fitness, the velocity and position information of each particle are updated, and the fitness of each particle is recalculated. The individual optimal fitness and the population optimal fitness are then updated. This process is repeated until a preset error condition is met, at which point the initial model parameters are output.

[0105] The PSO-BP model, based on the initial model parameters, processes the training samples to determine the loss value, and then updates the initial model parameters based on the loss value. If the detection reaches the convergence condition, i.e., the loss function converges, the trained furnace lining spalling prediction model is obtained.

[0106] For example, in the process of training a furnace lining spalling prediction model, the prediction error is as follows: Figure 8 As shown. The prediction error can be understood as the difference between the actual furnace lining spalling amount and the theoretical furnace lining spalling amount. The spalling thickness corresponding to the actual furnace lining spalling amount and the theoretical furnace lining spalling amount is shown in the figure. Figure 9 As shown. Figure 9 In the above, the actual value is the spalling thickness corresponding to the theoretically predicted spalling amount. The predicted value is the spalling thickness corresponding to the actual furnace lining spalling amount. The prediction error range is concentrated in [-0.6, 0.27]. Setting the theoretical error to ±0.3mm, the prediction accuracy of the furnace lining spalling amount prediction model to be trained is 88%.

[0107] S240. Based on the initial furnace lining thickness information and the predicted furnace lining spalling amount, determine the target furnace lining thickness corresponding to the target converter.

[0108] The initial furnace lining thickness information refers to the furnace lining thickness parameters determined for the target converter before the current furnace smelting.

[0109] The technical solution of this embodiment acquires the smelting parameters and infrared image of the target converter after the current heat smelting is completed, providing data support for subsequently determining the furnace lining thickness of the target converter. Based on the infrared image, the target furnace lining temperature of the target converter is determined. The smelting parameters are processed based on multiple common factor determination functions to determine multiple input parameters corresponding to the smelting parameters. These input parameters and the target furnace lining temperature are input into a pre-trained furnace lining spalling prediction model to determine the predicted furnace lining spalling amount of the target converter in the current heat. The furnace lining thickness of the target converter after the completion of the current heat smelting is determined based on the predicted furnace lining spalling amount. Finally, based on the furnace lining thickness parameters determined before the current heat smelting and the predicted furnace lining spalling amount, the target furnace lining thickness of the target converter is determined. This invention solves the problems of incomplete measurement caused by laser measurement of furnace lining thickness and low efficiency and accuracy caused by manual measurement of furnace lining thickness in the prior art. By processing infrared images and input parameters through a furnace lining spalling prediction model, it realizes continuous prediction of the target converter furnace lining thickness in a non-contact manner. This not only improves the efficiency and accuracy of determining the furnace lining thickness, but also effectively avoids the situation where the target converter furnace lining is burned through, ensuring the safety of on-site personnel.

[0110] Example 3

[0111] Figure 10 This is a schematic diagram of a converter lining thickness determination device provided in Embodiment 3 of the present invention. Figure 10 As shown, the device includes: a data acquisition module 310, a spalling amount determination module 320, and a furnace lining thickness determination module 330.

[0112] The data acquisition module 310 is used to acquire the smelting parameters and infrared image of the target converter after the current smelting is completed, wherein the infrared image is an image of a local area of ​​the target converter; the spalling amount determination module 320 is used to determine the target furnace lining temperature of the target converter based on the infrared image, and to determine the predicted furnace lining spalling amount of the target converter in the current smelting based on the target furnace lining temperature and smelting parameters; the furnace lining thickness determination module 330 is used to determine the target furnace lining thickness of the target converter based on the initial furnace lining thickness information and the predicted furnace lining spalling amount; wherein the initial furnace lining thickness information is the furnace lining thickness parameter determined before the current smelting of the target converter.

[0113] The technical solution of this embodiment acquires the smelting parameters and infrared images of the target converter after the current heat smelting is completed, providing data support for subsequently determining the furnace lining thickness of the target converter. Based on the infrared image, the target furnace lining temperature of the target converter is determined. And based on the target furnace lining temperature and smelting parameters, the predicted furnace lining spalling amount of the target converter in the current heat is determined, so as to determine the furnace lining thickness of the target converter after the completion of the current heat smelting based on the predicted furnace lining spalling amount. Based on the furnace lining thickness parameters determined before the current heat smelting and the predicted furnace lining spalling amount, the target furnace lining thickness of the target converter is determined. This invention solves the problems of incomplete measurement caused by laser measurement of furnace lining thickness in the prior art and the low efficiency and accuracy caused by manual measurement of furnace lining thickness. By quickly and accurately determining the target furnace lining thickness of the target converter through infrared images and smelting parameters, it not only improves the efficiency and accuracy of determining the furnace lining thickness, but also effectively avoids the furnace lining being burned through, ensuring the safety of on-site personnel.

[0114] Based on the above embodiments, optionally, the data acquisition module includes an image acquisition unit, used to acquire the original infrared image of the target converter, and perform grayscale processing on the original infrared image to determine the original grayscale image corresponding to the original infrared image; perform Gaussian filtering on the original grayscale image to obtain a denoised grayscale image, and process the denoised grayscale image based on a preset gradient operator to determine at least one selectable edge pixel in the denoised grayscale image; determine at least one target edge pixel and a local region corresponding to the at least one target edge pixel based on the pixel value corresponding to the at least one selectable edge pixel and a preset pixel range; and determine the infrared image of the target converter based on the original infrared image and the local region.

[0115] Optionally, the peeling amount determination module includes a furnace lining temperature determination unit, used to determine the conversion parameters to be used based on the highest and lowest temperature values ​​in the original infrared image and the maximum and minimum grayscale values ​​in the original grayscale image; determine the grayscale image to be processed corresponding to the infrared image, and determine the temperature value to be processed for each pixel based on the grayscale value to be processed, the maximum grayscale value, and the conversion parameters to be used for each pixel in the grayscale image to be processed; and determine the target furnace lining temperature of the target converter based on the number of pixels in the local area and the temperature value to be processed for each pixel.

[0116] Optionally, the spalling amount determination module includes a predicted furnace lining spalling amount determination unit, which includes: a parameter determination subunit, used to process the smelting parameters based on multiple common factor determination functions to determine multiple parameters to be input corresponding to the smelting parameters; and a model processing subunit, used to input the parameters to be input and the target furnace lining temperature into a pre-trained furnace lining spalling amount prediction model to determine the predicted furnace lining spalling amount corresponding to the target converter in the current heat.

[0117] Optionally, the unit for predicting furnace lining spalling further includes: a common factor determination function determination subunit, used to obtain historical smelting parameters of the target converter in at least two dimensions under historical furnace cycles, wherein the at least two dimensions include at least two of the following: furnace liquid temperature dimension, smelting time dimension after filling with preset gas dimension, preset gas flow rate dimension, preset component ratio dimension in slag dimension, and target converter usage time dimension; and to perform data dimensionality reduction processing on the historical smelting parameters in at least two dimensions based on factor analysis method, so as to obtain multiple common factor determination functions when the cumulative contribution rate corresponding to the factor analysis method meets the preset conditions.

[0118] Optionally, the furnace lining spalling prediction model is determined based on the particle swarm optimization algorithm and the backpropagation algorithm. The initial model parameters of the furnace lining spalling prediction model are obtained by updating and iterating the original model parameters based on the particle swarm optimization algorithm. The furnace lining spalling prediction unit also includes: a model training subunit, used to acquire multiple training samples, wherein the training samples include sample furnace lining temperature, sample input parameters, and theoretical furnace lining spalling corresponding to the sample furnace lining temperature and sample input parameters; inputting the sample furnace lining temperature and sample input parameters from the training samples into the furnace lining spalling prediction model to be trained to obtain the actual furnace lining spalling; determining the loss value based on the theoretical furnace lining spalling and the actual furnace lining spalling; and correcting the initial model parameters of the furnace lining spalling prediction model to be trained based on the loss value to obtain the trained furnace lining spalling prediction model.

[0119] Optionally, a furnace lining thickness determination module is used to perform subtraction processing on the initial furnace lining thickness information and the predicted furnace lining spalling amount to obtain the target furnace lining thickness corresponding to the target converter, so that when the target furnace lining thickness does not reach the preset furnace lining thickness threshold, an early warning message is generated and an early warning processing is performed based on the target furnace lining thickness.

[0120] The converter lining thickness determination device provided in the embodiments of the present invention can execute the converter lining thickness determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0121] Example 4

[0122] Figure 11This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0123] like Figure 11 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0124] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0125] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the converter lining thickness determination method.

[0126] In some embodiments, the converter lining thickness determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the converter lining thickness determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the converter lining thickness determination method by any other suitable means (e.g., by means of firmware).

[0127] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] The computer program for implementing the converter lining thickness determination method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0129] Example 5

[0130] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a method for determining the thickness of a converter lining, the method comprising:

[0131] After the current heat smelting is completed, the smelting parameters and infrared images of the target converter are acquired, where the infrared images are images of a local area of ​​the target converter; based on the infrared images, the target lining temperature of the target converter is determined, and based on the target lining temperature and smelting parameters, the predicted lining spalling amount corresponding to the target converter in the current heat is determined; based on the initial lining thickness information and the predicted lining spalling amount, the target lining thickness corresponding to the target converter is determined; where the initial lining thickness information is the lining thickness parameter determined before the current heat smelting of the target converter.

[0132] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0134] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0135] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0136] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0137] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining the thickness of a converter lining, characterized in that, include: After the current furnace smelting is completed, the smelting parameters and infrared image of the target converter are obtained, wherein the infrared image is an image of a local area of ​​the target converter; Based on the infrared image, the target furnace lining temperature of the target converter is determined, and based on the target furnace lining temperature and the smelting parameters, the predicted furnace lining spalling amount corresponding to the target converter in the current furnace cycle is determined. The target furnace lining thickness is determined based on the initial furnace lining thickness information and the predicted furnace lining spalling amount; Wherein, the initial furnace lining thickness information is the furnace lining thickness parameter determined by the target converter before the current furnace smelting; The step of determining the predicted lining spalling amount of the target converter in the current heat cycle based on the target lining temperature and the smelting parameters includes: The smelting parameters are processed based on multiple common factor determination functions to determine multiple input parameters corresponding to the smelting parameters; the input parameters and the target furnace lining temperature are input into a pre-trained furnace lining spalling prediction model to determine the predicted furnace lining spalling amount corresponding to the target converter in the current furnace cycle. Before processing the smelting parameters based on a function that determines multiple common factors, the method further includes: The historical smelting parameters of the target converter under at least two dimensions in historical furnace cycles are obtained. The at least two dimensions include at least two of the following: furnace liquid temperature, smelting time after filling with a preset gas, flow rate of the preset gas, proportion of a preset component in the slag, and usage time of the target converter. The historical smelting parameters under the at least two dimensions are subjected to dimensionality reduction processing based on factor analysis to obtain multiple common factor determination functions when the cumulative contribution rate corresponding to the factor analysis meets a preset condition. The furnace lining spalling prediction model is determined based on particle swarm optimization and backpropagation algorithms. The initial model parameters of the furnace lining spalling prediction model are obtained by updating and iteratively processing the original model parameters using particle swarm optimization. The method further includes: Multiple training samples are obtained, including sample furnace lining temperatures, sample input parameters, and theoretical furnace lining spalling amounts corresponding to the sample furnace lining temperatures and sample input parameters. The sample furnace lining temperatures and sample input parameters from the training samples are input into the furnace lining spalling amount prediction model to be trained to obtain the actual furnace lining spalling amount. Based on the theoretical furnace lining spalling amount and the actual furnace lining spalling amount, a loss value is determined. Based on the loss value, the initial model parameters of the furnace lining spalling amount prediction model to be trained are corrected to obtain a trained furnace lining spalling amount prediction model.

2. The method according to claim 1, characterized in that, Acquire infrared images of the target converter, including: Acquire the original infrared image of the target converter, and perform grayscale processing on the original infrared image to determine the original grayscale image corresponding to the original infrared image; The original grayscale image is subjected to Gaussian filtering to obtain a denoised grayscale image, and the denoised grayscale image is processed based on a preset gradient operator to determine at least one edge pixel to be selected in the denoised grayscale image. Based on the pixel value corresponding to the at least one edge pixel to be selected and the preset pixel range, at least one target edge pixel and a local region corresponding to the at least one target edge pixel are determined; Based on the original infrared image and the local region, the infrared image of the target converter is determined.

3. The method according to claim 1, characterized in that, Determining the target furnace lining temperature of the target converter based on the infrared image includes: Based on the highest and lowest temperature values ​​in the original infrared image, and the maximum and minimum grayscale values ​​in the original grayscale image, determine the conversion parameters to be used; Determine the grayscale image to be processed corresponding to the infrared image, and determine the temperature value to be processed for each pixel based on the grayscale value to be processed for each pixel in the grayscale image to be processed, the maximum grayscale value, and the conversion parameters to be used; The target furnace lining temperature of the target converter is determined based on the number of pixels in the local area and the temperature value to be processed for each pixel.

4. The method according to claim 1, characterized in that, Determining the target lining thickness corresponding to the target converter based on the initial lining thickness information and the predicted lining spalling amount includes: The initial furnace lining thickness information and the predicted furnace lining spalling amount are subtracted to obtain the target furnace lining thickness corresponding to the target converter. When the target furnace lining thickness does not reach the preset furnace lining thickness threshold, an early warning message is generated and an early warning is issued based on the target furnace lining thickness.

5. A device for determining the thickness of a converter lining, characterized in that, include: The data acquisition module is used to acquire the smelting parameters and infrared image of the target converter after the current smelting is completed, wherein the infrared image is an image of a local area of ​​the target converter; The spalling amount determination module is used to determine the target furnace lining temperature of the target converter based on the infrared image, and to determine the predicted furnace lining spalling amount of the target converter in the current furnace cycle based on the target furnace lining temperature and the smelting parameters. The furnace lining thickness determination module is used to determine the target furnace lining thickness corresponding to the target converter based on the initial furnace lining thickness information and the predicted furnace lining spalling amount. Wherein, the initial furnace lining thickness information is the furnace lining thickness parameter determined by the target converter before the current furnace smelting; The spalling amount determination module includes a furnace lining spalling amount prediction unit, which includes: a parameter determination subunit, used to process the smelting parameters based on multiple common factor determination functions to determine multiple input parameters corresponding to the smelting parameters; and a model processing subunit, used to input the input parameters and the target furnace lining temperature into a pre-trained furnace lining spalling amount prediction model to determine the predicted furnace lining spalling amount corresponding to the target converter in the current heat. The unit for predicting furnace lining spalling further includes a common factor determination function determination subunit, used to obtain historical smelting parameters of the target converter in at least two dimensions under historical furnace cycles, wherein the at least two dimensions include at least two of the following: furnace liquid temperature dimension, smelting time dimension after filling with preset gas dimension, flow rate dimension of preset gas dimension, proportion of preset components in slag dimension, and usage time dimension of the target converter dimension; and performs data dimensionality reduction processing on the historical smelting parameters in the at least two dimensions based on factor analysis method, so as to obtain multiple common factor determination functions when the cumulative contribution rate corresponding to the factor analysis method meets the preset conditions. The furnace lining spalling prediction model is determined based on the particle swarm optimization algorithm and the backpropagation algorithm. The initial model parameters of the furnace lining spalling prediction model are obtained by updating and iterating the original model parameters based on the particle swarm optimization algorithm. The furnace lining spalling prediction unit further includes: a model training subunit, used to acquire multiple training samples, wherein the training samples include sample furnace lining temperature, sample input parameters, and theoretical furnace lining spalling corresponding to the sample furnace lining temperature and the sample input parameters; inputting the sample furnace lining temperature and sample input parameters from the training samples into the furnace lining spalling prediction model to be trained to obtain the actual furnace lining spalling; determining the loss value based on the theoretical furnace lining spalling and the actual furnace lining spalling; and correcting the initial model parameters of the furnace lining spalling prediction model to be trained based on the loss value to obtain the trained furnace lining spalling prediction model.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the converter lining thickness determination method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method for determining the converter lining thickness as described in any one of claims 1-4.

Images