System and method for monitoring temperature of converter body based on thermal infrared imager

Abstract

The invention relates to the technical field of thermal image processing, in particular to a system and method for monitoring the temperature of a converter body based on a thermal infrared imager. According to the system for monitoring the temperature of the converter body through the thermal infrared imager, after a collected thermogram is subjected to screening and field angle correction processing, whether the local temperature in the processed thermogram is too high or not, whether the local temperature is uniform or not and the average temperature change trend of the converter wall are analyzed, and the temperature of the converter body is monitored through the thermal infrared imager. Due to the fact that thermogram collection does not involve a large amount of signal modulation and the collection distance is farther than the thermocouple interval, the anti-interference capacity is high, the monitoring precision is higher, and the requirement for precise monitoring of the temperature of the converter wall in the industry is met.

Description

Technical Field

[0001] The present application relates to the technical field of thermal image processing, and particularly to a system and method for monitoring the temperature of a converter furnace body based on an infrared thermal imager. Background Art

[0002] In the field of non-ferrous metal smelting, monitoring the temperature of the converter furnace wall is an important measure in the copper smelting process. Monitoring the furnace wall temperature helps operators understand the thermal state inside the furnace, improve the copper smelting efficiency and quality, protect the refractory materials inside the furnace, and avoid material erosion caused by overheating.

[0003] Traditional converter furnace wall temperature monitoring often uses thermocouples for temperature measurement. Thermocouples are arranged axially with equal density in the circumferential lining of the converter furnace, and radially with equal density at the furnace bottom. Additionally, thermocouples are densely arranged at the trunnion ring part to achieve a relatively comprehensive temperature monitoring of the converter furnace wall.

[0004] However, when converting the voltage signal of the thermocouple into a digital signal of an available temperature reading, a large amount of signal conditioning is required. However, the high-temperature environment around the furnace wall will cause the electric field around it to become scattered and the magnetic field noise to increase, which easily introduces large interference, resulting in a large deviation between the converted temperature indication and the actual value.

[0005] In view of this, there is an urgent need for a converter furnace wall temperature detection system that can adapt to the high-temperature environment with more signal noise to meet the industrial need for accurate monitoring of the converter furnace wall temperature. Summary of the Invention

[0006] The main purpose of the present application is to provide a system for monitoring the temperature of a converter furnace body based on an infrared thermal imager, aiming to solve the problem of how to achieve accurate monitoring of the converter furnace wall temperature in a high-temperature and signal-noise-rich environment.

[0007] To achieve the above purpose, a system provided by the present application includes:

[0008] A thermal image acquisition module, configured to acquire an initial thermal image around the converter furnace wall;

[0009] A thermal image processing module, configured to select, from the initial thermal image, those with a cosine similarity greater than a preset similarity threshold with a standard thermal image as target thermal images, and correct the field of view angle of the target thermal images to a front-view thermal image that conforms to a preset field of view angle;

[0010] A local temperature analysis module of the converter furnace body, configured to determine a furnace wall temperature analysis result based on the front-view thermal image, where the furnace wall temperature analysis result includes a local high-temperature warning result of the converter furnace wall, a local temperature uniformity analysis result, and an analysis result of the average temperature change trend of the furnace wall.

[0011] Optionally, the thermal image processing module includes:

[0012] A thermal image screening unit, configured to select, from the initial thermal images, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as the target thermal images;

[0013] A thermal image tilt correction unit, configured to correct the field of view angle of the target thermal image to a frontal thermal image that meets the preset field of view angle.

[0014] Optionally, the thermal image tilt correction unit includes:

[0015] A scale space construction unit, configured to generate a plurality of Gaussian blurred images by performing Gaussian blur on the target thermal image, and further form a scale space;

[0016] A key point localization unit, configured to find the extreme points in the scale space to locate the key point coordinates;

[0017] A key point direction matching unit, configured to calculate the gradient and direction of the neighborhood of each key point coordinate;

[0018] A descriptor generation unit, configured to divide the neighborhood of each key point coordinate into 16 small regions of 4*4, calculate the direction and magnitude of the gradient in each small region, obtain a gradient histogram corresponding to the number of gradient directions, assign the gradient direction to one of the 8 gradient histograms, and accumulate the corresponding gradient magnitudes to form an 8-dimensional vector, and concatenate the vectors of all sub-regions to form a 128-dimensional descriptor;

[0019] An image transformation unit, configured to construct a transformation model according to the descriptor, and obtain a corrected image using a transformation function according to the transformation model;

[0020] An image fusion unit, configured to decompose the corrected image into multiple frequency layers, then perform image mixing on each frequency layer, generate a weight map according to the values of each pixel point near the stitching line of the obtained mixed image, and mix the images according to the weights corresponding to each pixel in the weight map to generate a stitched frontal thermal image.

[0021] Optionally, the thermal image processing module further includes:

[0022] A thermal image enhancement unit, configured to enhance the thermal imaging data in the frontal thermal image by interpolation.

[0023] Optionally, the local temperature analysis module of the converter body includes:

[0024] A local temperature uniformity analysis unit, configured to determine the uniformity degree of the temperature difference field of the frontal thermal image according to the temperature difference field uniformity coefficient;

[0025] Among them, the calculation expression of the temperature difference field uniformity coefficient is as follows:

[0026]

[0027] Among them, φ is the temperature difference field uniformity coefficient, 0 < φ < 1, T i,j and t i,j respectively represent the temperature distributions of high temperature and low temperature, and M and N respectively represent the numbers of sub-elements along the length and width.

[0028] In addition, to achieve the above object, the present application also provides a method for monitoring the temperature of a converter vessel based on an infrared thermal imager, which is characterized in that it is applied to the system for monitoring the temperature of a converter vessel based on an infrared thermal imager as described above, and the method includes the following steps:

[0029] Collect an initial thermal image around the converter vessel wall;

[0030] Select, from the initial thermal image, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as target thermal images, and correct the field of view angle of the target thermal images to a frontal thermal image that conforms to the preset field of view angle;

[0031] Determine the furnace wall temperature analysis result according to the frontal thermal image, and the furnace wall temperature analysis result includes a local high temperature warning result of the converter furnace wall, a local temperature uniformity analysis result, and a furnace wall average temperature change trend analysis result.

[0032] Optionally, the step of selecting, from the initial thermal image, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as target thermal images, and correcting the field of view angle of the target thermal images to a frontal thermal image that conforms to the preset field of view angle specifically includes:

[0033] Generate a plurality of Gaussian blurred images by performing Gaussian blur on the target thermal image, and further form a scale space;

[0034] Find the extreme points in the scale space to locate the key point coordinates;

[0035] Calculate the gradient and direction of the neighborhood of each key point coordinate;

[0036] Divide the neighborhood of each key point coordinate into 16 small regions of 4*4, calculate the direction and magnitude of the gradient in each small region, obtain a gradient histogram corresponding to the number of gradient directions, assign the gradient direction to one of the 8 gradient histograms, and accumulate the corresponding gradient magnitudes to form an 8-dimensional vector. Concatenate the vectors of all sub-regions to form a 128-dimensional descriptor;

[0037] Construct a transformation model according to the descriptor, and obtain a corrected image using a transformation function according to the transformation model;

[0038] Decompose the corrected image into multiple frequency layers, then perform image blending on each frequency layer, generate a weight map based on the values of each pixel near the stitching line of the obtained blended image, and blend the images according to the weights corresponding to each pixel in the weight map to generate a stitched front-view thermal image.

[0039] Optionally, before the step of analyzing the furnace wall temperature data according to the front-view thermal image, where the furnace wall temperature data includes local high temperature, local temperature uniformity, and the change trend of the average furnace wall temperature of the converter furnace wall, further include:

[0040] Enhance the thermal imaging data in the front-view thermal image through interpolation.

[0041] Optionally, the step of analyzing the furnace wall temperature data according to the front-view thermal image includes:

[0042] Determine the uniformity degree of the temperature difference field of the front-view thermal image according to the temperature difference field uniformity coefficient;

[0043] Among them, the calculation expression of the temperature difference field uniformity coefficient is:

[0044]

[0045] Among them, φ is the temperature difference field uniformity coefficient, 0 < φ < 1, T i,j and t i,j respectively represent the temperature distributions of high temperature and low temperature, and M and N respectively represent the numbers of sub-elements along the length and width.

[0046] In addition, to achieve the above object, the present application also provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements each step of the method for monitoring the temperature of the converter furnace body based on an infrared thermal imager as described in any one of the above.

[0047] The present application at least has the following beneficial effects:

[0048] For the system for monitoring the temperature of the converter furnace body through an infrared thermal imager, after the collected thermal image is screened and corrected for the field of view angle, analyze whether the local temperature in the processed thermal image is too high, whether the local temperature is uniform, and the change trend of the average furnace wall temperature. Since collecting the thermal image does not involve a large amount of signal modulation and the collection distance is relatively far from the thermocouple interval, the anti-interference ability is strong and the monitoring accuracy is higher, thus meeting the industrial demand for accurate monitoring of the converter furnace wall temperature. Description of the Drawings

[0049] Figure 1Schematic diagram of the architecture of the system for monitoring the temperature of the converter furnace body based on an infrared thermal imager according to an embodiment of the present application;

[0050] Figure 2 Schematic diagram of the architecture between the converter furnace wall and the infrared thermal imager according to an embodiment of the present application;

[0051] Figure 3 Schematic flowchart of the method for monitoring the temperature of the converter furnace body based on an infrared thermal imager according to an embodiment of the present application;

[0052] Figure 4 Schematic diagram of the architecture of the hardware operating environment of the computer terminal according to an embodiment of the present application.

[0053] The realization, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0054] To better understand the above technical solutions, the exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be completely conveyed to those skilled in the art.

[0055] First embodiment

[0056] Referring to Figure 1 the schematic diagram of the architecture of the system for monitoring the temperature of the converter furnace body based on an infrared thermal imager shown in

[0057] a thermal image acquisition module 100, configured to acquire an initial thermal image around the converter furnace wall;

[0058] In this embodiment, the system uses multiple infrared thermal imagers as the thermal image acquisition module to acquire and monitor the temperature of the converter furnace body.

[0059] Exemplarily, referring to Figure 2 the schematic diagram of the architecture between the converter furnace wall and the infrared thermal imager shown in

[0060] Optionally, in a specific implementation manner, the number of infrared thermal imagers can be set to 4.

[0061] The thermal image processing module 200 is configured to select, from the initial thermal images, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as the target thermal images, and correct the field of view angle of the target thermal images to a frontal thermal image that meets the preset field of view angle;

[0062] In this embodiment, the cosine similarity is used to compare with the standard thermal image, and when the conditions are met, the thermal image is intercepted as the target thermal image.

[0063] Optionally, the preset similarity threshold can be 0.9.

[0064] Exemplarily, the calculation formula of the cosine similarity is as follows:

[0065]

[0066] Wherein, A·B represents the dot product of the initial thermal image A and the standard thermal image B; ‖A‖ represents the Euclidean norm of the initial thermal image A; ‖B‖ represents the Euclidean norm of the standard thermal image B; i represents the dimension of the vector.

[0067] On the other hand, in order to ensure the accuracy of the subsequent temperature analysis module, the field of view angle of the target thermal image is corrected to a frontal thermal image that meets the preset field of view angle.

[0068] The local temperature analysis module 300 of the converter body is configured to determine the furnace wall temperature analysis result according to the frontal thermal image, and the furnace wall temperature analysis result includes the local high temperature warning result of the converter furnace wall, the local temperature uniformity analysis result, and the furnace wall average temperature change trend analysis result.

[0069] In this embodiment, the infrared thermal imager uses an infrared detector to detect the infrared radiation emitted by an object. The detector converts the infrared radiation into an electrical signal, and the electrical signal is amplified and digitally processed, converted into a digital signal representing the radiation energy, and then sent to the local temperature analysis module of the converter body for analysis. When analyzing, a MATLAB algorithm is used to analyze the excessive temperature in a specific area, the local uniformity of the temperature, and the change trend of the furnace wall average temperature and present it in the form of a chart on a computer terminal.

[0070] Exemplarily, in a specific embodiment, the working process of the system for monitoring the temperature of the converter body based on the infrared thermal imager in this embodiment is as follows:

[0071] First, set the emissivity of the furnace wall material, as well as the ambient temperature and relative humidity on the infrared thermal imager; start the infrared thermal imager to collect the infrared image of the converter furnace wall, ensuring that the received image is clear without distortion or blurring; observe the thermal image, search for temperature anomaly points on the furnace wall, and analyze the hot spots or cooling areas. Use the software tool of the infrared thermal imager to locate the temperature distribution, the highest / lowest temperature points; save the thermal image and related temperature data to the computer terminal. Record the analysis results, including time, environmental parameters, converter operation status, etc. According to the analysis results, analyze the local high temperature, local temperature uniformity, and the change trend of the average furnace wall temperature of the converter furnace wall. Measure the temperature of the furnace body by the local temperature uniformity and analyze the possible thermal stress of the furnace body. If the local high temperature exceeds the empirical threshold, trigger the system alarm.

[0072] In the technical solution provided in this embodiment, for the system that monitors the temperature of the converter furnace body by the infrared thermal imager, after the collected thermal image is screened and the field of view angle is corrected, analyze whether the local temperature in the processed thermal image is too high, whether the local temperature is uniform, and the change trend of the average furnace wall temperature. Since the collection of the thermal image does not involve a large amount of signal modulation and the collection distance is relatively far from the thermocouple interval, the anti-interference ability is strong and the monitoring accuracy is higher, thus meeting the industrial demand for accurate monitoring of the converter furnace wall temperature.

[0073] Second Embodiment

[0074] Based on the first embodiment, in this embodiment, the thermal image processing module includes:

[0075] A thermal image screening unit, configured to select, from the initial thermal images, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as the target thermal images;

[0076] A thermal image tilt correction unit, configured to correct the field of view angle of the target thermal image to a frontal thermal image that conforms to a preset field of view angle.

[0077] Further, the thermal image tilt correction unit includes:

[0078] A scale space construction unit, configured to generate multiple Gaussian blurred images by performing Gaussian blur on the target thermal image, and further form a scale space;

[0079] Specifically, let the scale space L( x,y,σ ) be expressed as:

[0080] L(x, y, σ) = G(x, y, σ) * I(x, y)

[0081] In the formula, G(x, y, σ) is the Gaussian function; I(x, y) is the input image; * represents the convolution operation.

[0082] Among them, the expression of the Gaussian function is:

[0083]

[0084] Multiple Gaussian blurred images are generated through different σ values to form a scale space L(x, y, σ).

[0085] A key point localization unit, used to find the extreme points in the scale space to locate the key point coordinates;

[0086] In the scale space, key points are located by finding extreme points. For each pixel point L(x, y, σ), check the maximum and minimum values in its neighborhood, that is:

[0087] When L(x, y, σ) > L(x', y', σ), take the maximum value;

[0088] When L(x, y, σ) < L(x”, y”, σ), take the minimum value;

[0089] In the formula, (x', y') and (x”, y”) are both pixel points adjacent to (x, y).

[0090] A key point direction matching unit, used to calculate the gradient and direction of the neighborhood of each key point coordinate;

[0091] In order to make the descriptor rotation invariant, SIFT assigns one or more directions to each key point, calculates the gradient and direction of the key point neighborhood. The calculation formulas for the gradient m(x, y) and direction θ(x, y) of the key point neighborhood are as follows:

[0092]

[0093] Among them, I x and I y are the gradients of the key point in the x and y directions;

[0094] A descriptor generation unit, used to divide the neighborhood of each key point coordinate into 16 small regions of 4*4, calculate the direction and magnitude of the gradient in each small region, obtain a gradient histogram corresponding to the number of gradient directions, assign the gradient direction to one of the 8 gradient histograms, and accumulate the corresponding gradient magnitudes to form an 8-dimensional vector, and concatenate the vectors of all sub-regions to form a 128-dimensional descriptor;

[0095] An image transformation unit, used to construct a transformation model according to the descriptor, and according to the transformation model, use a transformation function to obtain a corrected image;

[0096] An image fusion unit, configured to decompose the corrected image into multiple frequency layers, then perform image mixing on each frequency layer, generate a weight map based on the values of each pixel point near the stitching line of the obtained mixed image, and mix the images according to the weights corresponding to each pixel in the weight map to generate a stitched front-facing thermal image.

[0097] The third embodiment

[0098] Based on any one of the embodiments, in this embodiment, the thermal image processing module further includes:

[0099] A thermal image enhancement unit, configured to enhance the thermal imaging data in the front-facing thermal image by an interpolation method.

[0100] Specifically, the interpolation method in this embodiment mainly includes spatial interpolation and temporal interpolation.

[0101] Spatial interpolation is to perform spatial mapping and grid processing on the filtered temperature data according to the spatial positions and measurement point distributions of each monitoring area.

[0102] Optionally, for a regular rectangular monitoring area, a bilinear interpolation algorithm can be used; for an irregular polygonal monitoring area, a Kriging interpolation algorithm can be used; for the case where the temperature data shows an obvious anisotropic distribution, an anisotropic Kriging interpolation algorithm can be used.

[0103] Temporal interpolation is to calculate the temperature value at a certain moment based on the measurement data at adjacent moments when the temperature value at a certain moment needs to be obtained but there is no direct measurement data.

[0104] Optionally, linear interpolation or spline interpolation can be used for temporal interpolation.

[0105] The fourth embodiment

[0106] Based on any one of the embodiments, in this embodiment, the temperature difference field uniformity degree of the front-facing thermal image is determined according to the temperature difference field uniformity coefficient.

[0107] Wherein, the calculation expression of the temperature difference field uniformity coefficient is:

[0108]

[0109] Wherein, φ is the temperature difference field uniformity coefficient, 0 < φ < 1, T i,j and t i,j respectively represent the temperature distributions of high temperature and low temperature, and M and N respectively represent the numbers of sub-elements along the length and width.

[0110] The fifth embodiment

[0111] As an implementation solution, referring to Figure 3, in this embodiment, a method for monitoring the temperature of a converter furnace body based on an infrared thermal imager is provided. This method is applied to the system for monitoring the temperature of a converter furnace body based on an infrared thermal imager in any of the foregoing embodiments. The method includes the following steps:

[0112] S10, Collect an initial thermal image around the converter furnace wall;

[0113] S20, Select, from the initial thermal image, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as target thermal images, and correct the field of view angle of the target thermal images to a frontal thermal image that conforms to the preset field of view angle;

[0114] S30, Determine the furnace wall temperature analysis result according to the frontal thermal image. The furnace wall temperature analysis result includes a local high temperature warning result of the converter furnace wall, a local temperature uniformity analysis result, and a furnace wall average temperature change trend analysis result.

[0115] Further and optionally, the S20 specifically includes:

[0116] S21, Generate multiple Gaussian blurred images by performing Gaussian blur on the target thermal image, and then form a scale space;

[0117] S22, Search for extreme points in the scale space to locate the key point coordinates;

[0118] S23, Calculate the gradient and direction of the neighborhood of each key point coordinate;

[0119] S24, Divide the neighborhood of each key point coordinate into 16 small regions of 4*4, calculate the direction and magnitude of the gradient in each small region to obtain a gradient histogram corresponding to the number of gradient directions, assign the gradient direction to one of 8 gradient histograms, and accumulate the corresponding gradient magnitudes to form an 8-dimensional vector. Concatenate the vectors of all sub-regions to form a 128-dimensional descriptor;

[0120] S25, Construct a transformation model according to the descriptor, and use a transformation function to obtain a corrected image according to the transformation model;

[0121] S26, Decompose the corrected image into multiple frequency layers, then perform image mixing on each frequency layer, generate a weight map according to the value of each pixel point near the stitching line of the obtained mixed image, and mix the images according to the weights corresponding to each pixel in the weight map to generate a stitched frontal thermal image.

[0122] Further and optionally, before the S30, it further includes:

[0123] S40, Enhance the thermal imaging data in the frontal thermal image by interpolation method.

[0124] Further and optionally, S30 specifically includes:

[0125] S31, determining the temperature difference field uniformity degree of the front thermal image according to the temperature difference field uniformity coefficient;

[0126] Wherein, the calculation expression of the temperature difference field uniformity coefficient is:

[0127]

[0128] Wherein, φ is the temperature difference field uniformity coefficient, 0 < φ < 1, T i,j and t i,j respectively represent the temperature distributions of high temperature and low temperature, and M and N respectively represent the numbers of sub-elements along the length and width.

[0129] In addition, as an implementation solution, Figure 4 is a schematic architecture diagram of the hardware operating environment of the computer terminal involved in the solution of the embodiment of the present application.

[0130] As Figure 4 shown, the computer terminal may include: a processor 1001, such as a CPU, a memory 1005, a user interface 1003, a network interface 1004, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the foregoing processor 1001.

[0131] Those skilled in the art can understand that Figure 1 the computer terminal architecture shown in does not constitute a limitation on the computer terminal, and may include more or fewer components than shown, or combine some components, or arrange different components.

[0132] As Figure 1 shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a computer program. Among them, the operating system is a program for managing and controlling the hardware and software resources of the computer terminal, and the operation of the computer program and other software or programs.

[0133] In Figure 1In the computer terminal shown, the user interface 1003 is mainly used to connect to the terminal and communicate with the terminal for data; the network interface 1004 is mainly used to communicate with the background server for data; the processor 1001 can be used to call the computer program stored in the memory 1005.

[0134] In this embodiment, the computer terminal includes: a memory 1005, a processor 1001, and a computer program stored on the memory and executable on the processor, where:

[0135] When the processor 1001 calls the computer program stored in the memory 1005, the following operations are performed:

[0136] Collect an initial thermal image around the converter wall;

[0137] Select, from the initial thermal image, those with a cosine similarity greater than a preset similarity threshold to the standard thermal image as target thermal images, and correct the field of view angle of the target thermal images to a frontal thermal image that meets the preset field of view angle;

[0138] Determine the furnace wall temperature analysis result based on the frontal thermal image, where the furnace wall temperature analysis result includes a local high temperature warning result of the converter wall, a local temperature uniformity analysis result, and a furnace wall average temperature change trend analysis result.

[0139] When the processor 1001 calls the computer program stored in the memory 1005, the following operations are performed:

[0140] Generate a plurality of Gaussian blurred images by performing Gaussian blur on the target thermal image, and further form a scale space;

[0141] Locate the key point coordinates by finding the extreme points in the scale space;

[0142] Calculate the gradient and direction of the neighborhood of each key point coordinate;

[0143] Divide the neighborhood of each key point coordinate into 16 small regions of 4*4, calculate the direction and magnitude of the gradient in each small region to obtain a gradient histogram corresponding to the number of gradient directions, assign the gradient direction to one of the 8 gradient histograms, and accumulate the corresponding gradient magnitudes to form an 8-dimensional vector. Concatenate the vectors of all sub-regions to form a 128-dimensional descriptor;

[0144] Construct a transformation model based on the descriptor, and use a transformation function to obtain a corrected image according to the transformation model;

[0145] Decompose the corrected image into multiple frequency layers, then perform image blending on each frequency layer, generate a weight map based on the values of each pixel point near the splicing line of the obtained blended image, and blend the images according to the weights corresponding to each pixel in the weight map to generate a spliced frontal thermal image.

[0146] When the processor 1001 calls the computer program stored in the memory 1005, it performs the following operations:

[0147] Enhance the thermal imaging data in the frontal thermal image by interpolation.

[0148] When the processor 1001 calls the computer program stored in the memory 1005, it performs the following operations:

[0149] Determine the uniformity degree of the temperature difference field of the frontal thermal image according to the temperature difference field uniformity coefficient;

[0150] Among them, the calculation expression of the temperature difference field uniformity coefficient is:

[0151]

[0152] Among them, φ is the temperature difference field uniformity coefficient, 0 < φ < 1, T i,j and t i,j respectively represent the temperature distributions of high temperature and low temperature, and M and N respectively represent the numbers of sub-elements along the length and width.

[0153] In addition, those of ordinary skill in the art can understand that all or part of the processes in the methods of implementing the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer terminal to implement the process steps of the embodiments of the above methods.

[0154] Therefore, the present application also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements each step of the method for monitoring the temperature of the converter body based on an infrared thermal imager as described in the above embodiments.

[0155] Among them, the computer-readable storage medium can be various computer-readable storage media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disc that can store program codes.

[0156] It should be noted that since the storage medium provided in the embodiments of the present application is the storage medium used to implement the methods of the embodiments of the present application, based on the methods introduced in the embodiments of the present application, those skilled in the art can understand the specific structure and variations of the storage medium, and thus will not be elaborated herein. Any storage medium used in the methods of the embodiments of the present application falls within the scope of protection of the present application.

[0157] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0158] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one or more of the flows Figure 1 or a combination of multiple flows and / or blocks

[0159] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the specified functions in Figure 1 one or more of the flows Figure 1 or a combination of multiple flows and / or blocks

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in Figure 1 one or more of the flows Figure 1 or a combination of multiple flows and / or blocks

[0161] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several devices, several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words may be interpreted as names.

[0162] Although the preferred embodiments of the present application have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0163] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A system for monitoring the temperature of a converter furnace body based on an infrared thermal imager, characterized in that The system includes: A thermal image acquisition module for acquiring an initial thermal image around the converter furnace wall; A thermal image processing module for selecting, from the initial thermal image, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as the target thermal image, and correcting the field of view angle of the target thermal image to a frontal thermal image that conforms to the preset field of view angle; A local temperature analysis module for the converter furnace body, which is used to determine the furnace wall temperature analysis result according to the frontal thermal image, and the furnace wall temperature analysis result includes a local high-temperature warning result for the converter furnace wall, a local temperature uniformity analysis result, and an analysis result of the changing trend of the average furnace wall temperature.

2. The system according to claim 1, wherein The thermal image processing module includes: A thermal image screening unit for selecting, from the initial thermal image, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as the target thermal image; A thermal image tilt correction unit for correcting the field of view angle of the target thermal image to a frontal thermal image that conforms to the preset field of view angle.

3. The system according to claim 2, wherein The thermal image tilt correction unit includes: A scale space construction unit for generating multiple Gaussian blurred images by performing Gaussian blur on the target thermal image, and then forming a scale space; A key point positioning unit for finding the extreme points in the scale space to locate the key point coordinates; A key point direction matching unit for calculating the gradient and direction of the neighborhood of each key point coordinate; A descriptor generation unit for dividing the neighborhood of each key point coordinate into 16 small regions of 4*4, calculating the direction and magnitude of the gradient in each small region, obtaining a gradient histogram corresponding to the number of gradient directions, allocating the gradient direction to one of the 8 gradient histograms, and accumulating the corresponding gradient magnitudes to form an 8-dimensional vector, and concatenating the vectors of all sub-regions to form a 128-dimensional descriptor; An image transformation unit for constructing a transformation model according to the descriptor, and obtaining a corrected image using a transformation function according to the transformation model; An image fusion unit for decomposing the corrected image into multiple frequency layers, then performing image mixing on each frequency layer, generating a weight map according to the values of each pixel point near the splicing line of the obtained mixed image, and mixing the images according to the weights corresponding to each pixel in the weight map to generate a spliced frontal thermal image.

4. The system according to claim 2, wherein The thermal image processing module further includes: A thermal image enhancement unit for enhancing the thermal imaging data in the frontal thermal image by interpolation.

5. The system according to claim 1, wherein The local temperature analysis module for the converter furnace body includes: A local temperature uniformity analysis unit for determining the uniformity degree of the temperature difference field of the frontal thermal image according to the temperature difference field uniformity coefficient; Wherein, the calculation expression of the temperature difference field uniformity coefficient is: where φ is the temperature difference field uniformity coefficient, 0 < φ < 1, T i,j and t i,j represent the temperature distributions of the high temperature and the low temperature respectively, and M and N represent the numbers of sub-elements along the length and the width respectively.

6. A method for monitoring the temperature of a converter furnace body based on an infrared thermal imager, characterized in that, Applied to the system for monitoring the temperature of the converter furnace body based on an infrared thermal imager according to any one of claims 1 to 5, the method includes the following steps: Acquiring an initial thermal image around the converter furnace wall; Selecting, from the initial thermal image, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as the target thermal image, and correcting the field of view angle of the target thermal image to a frontal thermal image that conforms to the preset field of view angle; Determine the analysis result of the furnace wall temperature based on the front-view thermal image, and the analysis result of the furnace wall temperature includes the local high-temperature warning result of the converter furnace wall, the analysis result of the local temperature uniformity, and the analysis result of the changing trend of the average furnace wall temperature.

7. The method according to claim 6, wherein The step of selecting, from the initial thermal images, those with a cosine similarity greater than a preset similarity threshold with the standard thermal image as the target thermal images and correcting the field of view angle of the target thermal images to the front-view thermal image that meets the preset field of view angle specifically includes: Generate a plurality of Gaussian blurred images by performing Gaussian blurring on the target thermal image, thereby forming a scale space; Locate the key point coordinates by finding the extreme points in the scale space; Calculate the gradient and direction of the neighborhood of each key point coordinate; Divide the neighborhood of each key point coordinate into 16 small regions of 4*4, calculate the direction and magnitude of the gradient in each small region, obtain a gradient histogram corresponding to the number of gradient directions, assign the gradient direction to one of the 8 gradient histograms, and accumulate the corresponding gradient magnitudes to form an 8-dimensional vector. Concatenate the vectors of all sub-regions to form a 128-dimensional descriptor; Construct a transformation model according to the descriptor, and use a transformation function to obtain a corrected image according to the transformation model; Decompose the corrected image into multiple frequency layers, then perform image blending on each frequency layer, generate a weight map according to the value of each pixel point near the splicing line of the obtained blended image, and blend the images according to the weight corresponding to each pixel in the weight map to generate a spliced front-view thermal image.

8. The method according to claim 6, wherein Before the step of analyzing the furnace wall temperature data according to the front-view thermal image, where the furnace wall temperature data includes the local high temperature of the converter furnace wall, the local temperature uniformity, and the changing trend of the average furnace wall temperature, it further includes: Enhance the thermal imaging data in the front-view thermal image by interpolation method.

9. The method according to claim 6, characterized in that, The step of analyzing the furnace wall temperature data according to the front-view thermal image includes: Determine the uniformity degree of the temperature difference field of the front-view thermal image according to the temperature difference field uniformity coefficient; Among them, the calculation expression of the temperature difference field uniformity coefficient is: Among them, φ is the uniformity coefficient of the temperature difference field, 0 < φ < 1, T i,j and t i,j represent the temperature distributions of high temperature and low temperature respectively, and M and N represent the numbers of sub-elements along the length and width respectively.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements each step of the method for monitoring the temperature of a converter furnace body based on an infrared thermal imager as described in any one of claims 6-9.

Images