Industrial furnace thermal efficiency dynamic optimization control method, equipment and medium

Abstract

The invention discloses an industrial furnace thermal efficiency dynamic optimization control method and device and a medium, relates to the field of industrial furnaces, and solves the problem that local abnormity of an industrial furnace cannot be recognized and adjusted. The method comprises the steps that infrared surface images of the industrial furnace in work at multiple visual angles are collected; analyzing the temperature distribution condition of the outer surface of the industrial furnace based on the infrared surface image, and dividing the industrial furnace into a plurality of industrial furnace sub-regions; the industrial furnace sub-regions are clustered based on the similarity and the position relation between the corresponding industrial furnace sub-regions of the industrial furnace, and updated industrial furnace sub-regions are obtained; calculating the heat efficiency of the updated industrial furnace sub-region, and judging the heat efficiency state of the corresponding industrial furnace sub-region based on the heat efficiency; and identifying the heat efficiency abnormal sub-region, and dynamically adjusting the combustion state of the heat efficiency abnormal sub-region through a control variable method until the heat efficiency of the sub-region reaches a heat efficiency threshold value, thereby realizing accurate sensing and dynamic compensation of the local heat efficiency of the industrial furnace.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial furnaces, and in particular relates to a method, equipment and medium for dynamically optimizing the thermal efficiency of an industrial furnace. Background Art

[0002] An industrial furnace is a closed device used to heat metal, glass, ceramics, or other materials for industrial operations such as melting, sintering, heat treatment, and drying. It generates a high-temperature environment through fuel combustion or electrical energy conversion, causing the material to undergo physical or chemical changes at a controlled temperature. It is widely used in industries such as metallurgy, chemicals, building materials, and machinery manufacturing. The core of an industrial furnace is to convert fuel or electrical energy into heat energy, achieving process goals such as metal smelting, ceramic sintering, glass melting, and steel heat treatment in a high-temperature environment. Therefore, precise control of parameters such as temperature curves, oxidation / reduction, and pressure is required to ensure the quality of processed products. However, currently, when confirming the thermal efficiency of industrial furnaces, the overall combustion thermal efficiency of the industrial furnace is calculated, rather than first dividing the industrial furnace into regions and then determining the thermal efficiency of each region and making adjustments. As a result, traditional methods have poor local perception of the industrial furnace, and over-compensation and under-compensation are common during adjustments. To this end, the present invention proposes a method, equipment and medium for dynamically optimizing the thermal efficiency of an industrial furnace. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, device and medium for dynamically optimizing the thermal efficiency of an industrial furnace to solve the problems raised in the above background technology.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: A method for dynamically optimizing the thermal efficiency of an industrial furnace, the method comprising: Step S1, collecting infrared surface images of a working industrial furnace at multiple viewing angles using an infrared collection device; Step S2, analyzing the outer surface temperature distribution of the industrial furnace based on the infrared surface image, and dividing the industrial furnace into a plurality of industrial furnace areas; Step S3, clustering the industrial furnace regions based on the similarity and position relationship between the corresponding industrial furnace regions to obtain updated industrial furnace regions; Step S4, calculating the updated thermal efficiency of the industrial furnace area, and determining the thermal efficiency state of the corresponding industrial furnace area based on the thermal efficiency; Step S5: identifying the abnormal thermal efficiency sub-region, and dynamically adjusting the combustion state of the abnormal thermal efficiency sub-region by using a control variable method until the thermal efficiency of the abnormal thermal efficiency sub-region reaches a thermal efficiency threshold.

[0005] Furthermore, step S2 includes the following sub-steps: Step S21, obtaining infrared surface images of the working industrial furnace at multiple viewing angles, stitching the infrared surface images at multiple viewing angles to obtain a stitched infrared image; identifying pixel values of all pixels in the stitched infrared image, and identifying real-time temperature values corresponding to the pixel values of the pixels by a table lookup method; Step S22: Read the number of burners connected to the industrial furnace and the connection position of each burner, and set initial division intervals on both sides of the connection position with the connection position as the center to obtain the combustion radiation area of the corresponding burner; Step S23: identifying two adjacent combustion radiation areas based on the stitched infrared image. If there is a blank area between the adjacent combustion radiation areas, the corresponding blank area is recorded as an independent combustion area. If there is no blank area between the adjacent combustion radiation areas, no operation is performed. Step S24, constructing an industrial furnace area corresponding to the combustion radiation area; Step S25: According to step S24, obtain the industrial furnace areas corresponding to all independent combustion areas; Step S26: Summarize the combustion radiation area and the combustion independent area to obtain the industrial furnace area corresponding to the industrial furnace.

[0006] Furthermore, the construction process of the combustion radiation area corresponding to the industrial furnace area is as follows: Step S241: Select any pixel at the bottom of the combustion radiation area as the first pixel of the industrial furnace area, and add any pixel adjacent to the selected pixel to the industrial furnace area; Step S242: Calculate the average of the real-time temperature values corresponding to all pixels in the industrial furnace area, and record it as the average temperature of the sub-area corresponding to the industrial furnace area; and calculate the standard deviation of the temperature values corresponding to all pixels in the corresponding industrial furnace area based on the average temperature of the sub-area. Step S243: The sub-region average temperature minus the standard deviation is used as the left endpoint, and the sub-region average temperature plus the standard deviation is used as the right endpoint to obtain the screening interval; Step S244: If the temperature values of all pixels in the industrial furnace area are within the screening interval, the adjacent pixel last added to the industrial furnace area is deemed qualified. If the temperature value of any pixel in the industrial furnace area is outside the screening range, the adjacent pixel added to the industrial furnace area is deemed unqualified and the corresponding adjacent pixel is removed; Step S245: When all adjacent pixel points are unqualified, an industrial furnace area in the combustion radiation area is obtained, and similarly, all industrial furnace areas in the combustion radiation area are obtained.

[0007] Furthermore, step S3 includes the following sub-steps: Step S31: Acquire the industrial furnace area, and then read the average temperature of the sub-area of each industrial furnace area, and use the sub-area average temperature as the characteristic value TZi of the corresponding industrial furnace area; where i is the number of the different industrial furnace areas, i=1, 1, ..., z, and z is a positive integer; Step S32: Calculate the similarity XSij of the corresponding feature values of any two industrial furnace regions using a similarity function. The similarity function is as follows: ; In the formula, e is a natural constant, j is the number of another industrial furnace area, TZj is the eigenvalue of another industrial furnace area, ||TZi-TZj|| represents the calculation of the Euclidean distance between TZi and TZj; σ is the Gaussian kernel.

[0008] Furthermore, the step S3 further includes the following sub-steps: Step S33: Consider the numbers of the industrial furnace regions as vertices, and the similarities of the corresponding eigenvalues of the multiple industrial furnace regions as the weights of the edges to obtain a similarity matrix XS, and construct an adjacency matrix LJ corresponding to the similarity matrix based on the similarity matrix; Step S34: Calculate the degree matrix D corresponding to the adjacency matrix using the formula. The calculation formula for each element in the degree matrix is as follows: ; Where Dii represents the degree of vertex i, when i≠j, Dij=0; LJij is the element in the adjacency matrix LJ, i represents the number of rows in the adjacency matrix, and j represents the number of columns in the adjacency matrix; Step S35: Calculate the Laplacian matrix LP using the adjacency matrix and the degree matrix.

[0009] Furthermore, the step S3 further includes: Step S36, calculating the Laplace eigenvalues LTZ and the Laplace eigenvectors LXL of the Laplace matrix; arranging the first k Laplace eigenvectors into a characteristic matrix U; Step S37, normalizing each row in the feature matrix to obtain a normalized feature matrix GU; The unitization process is as follows: ; Where Unm represents any element in the feature matrix, n is the number of rows in the feature matrix, m is the number of columns in the feature matrix, the upper limit of n is p, and the upper limit of m is k; Step S38: Consider each row in the normalized feature matrix as an embedding of an element in a k-dimensional space, and consider the nth row of data as a normalized vector, thereby obtaining p normalized vectors; and cluster the p normalized vectors into k clusters using a K-means clustering algorithm. Step S39: For any industrial furnace area, if different industrial furnace areas are located in the same cluster and the corresponding different industrial furnace areas are adjacent, the corresponding different industrial furnace areas are regarded as the same industrial furnace area, the corresponding industrial furnace areas are connected and the industrial furnace areas are updated; otherwise, no operation is performed.

[0010] Furthermore, step S4 includes the following sub-steps: Step S41, measuring the sub-region areas MJc of different industrial furnace regions, where c is the updated number of the industrial furnace region, c=1, 2, ..., x; Step S42, reading the material types of different industrial furnace areas according to the design drawing of the industrial furnace, and reading the corresponding thermal conductivity RDc based on the material type; Step S43: Add and average the real-time temperature values corresponding to all pixels in the updated industrial furnace area to obtain the sub-area average temperature PJWc.

[0011] Furthermore, the step S4 further includes the following sub-steps: Step S44, calculate the heat loss JRSc of the sub-area of the industrial furnace area using the formula, the specific formula is as follows: JRSc=RDc×MJc×(PJWc-HW); where HW is the ambient temperature; Step S45, calculating the sub-region thermal efficiency RXLc of the industrial furnace region by the formula, the specific formula is as follows: RXLc = 1 - JRSc ÷ SRXc; SRXc is the input thermal efficiency, calculated by multiplying the mass of fuel added to the corresponding burner in the industrial furnace area by the lower heating value of the corresponding fuel. The lower heating value is the heat released when the water vapor in the combustion products remains in a gaseous state after the fuel is completely burned. It is often used to reflect the actual heat available for the equipment. Step S46: The thermal efficiency of the sub-region of the industrial furnace region is compared with the thermal efficiency threshold. If the thermal efficiency of the sub-region is greater than or equal to the thermal efficiency threshold, no operation is performed; if the thermal efficiency of the sub-region is less than the thermal efficiency threshold, the corresponding industrial furnace region is marked as a sub-region with abnormal thermal efficiency. Step S47: Identify abnormal conditions in all industrial furnace areas, summarize abnormal thermal efficiency sub-areas, and send them to a storage terminal for storage.

[0012] A computer device, comprising: a memory storing a computer program; The processor is communicatively connected to the memory, and when the computer program is executed by the processor, the above method is implemented.

[0013] A computer-readable storage medium stores a computer program, which implements the above method when executed by a processor.

[0014] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention first uses infrared acquisition equipment to collect infrared surface images of a working industrial furnace from multiple viewing angles. Based on the infrared surface images, the outer surface temperature distribution of the industrial furnace is analyzed and the industrial furnace is divided into multiple industrial furnace regions. Furthermore, the industrial furnace regions are clustered based on the similarity and positional relationship between the corresponding industrial furnace regions to obtain updated industrial furnace regions. The present invention achieves the construction of industrial furnace regions. 2. The present invention first calculates the thermal efficiency of the updated industrial furnace area, and determines the thermal efficiency status of the corresponding industrial furnace area based on the thermal efficiency; finally, the abnormal thermal efficiency sub-area is identified through the thermal efficiency status, and the combustion state of the abnormal thermal efficiency sub-area is dynamically adjusted through the control variable method until the thermal efficiency of the sub-area of the abnormal thermal efficiency sub-area reaches the thermal efficiency threshold; the present invention realizes accurate perception and dynamic compensation of the local thermal efficiency of the industrial furnace. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0016] Figure 1 is a block diagram of the overall system of the present invention; Figure 2 An approximate outer surface image of the industrial furnace of the present invention; Figure 3 A schematic diagram of the combustion radiation area in the present invention; Figure 4 Schematic diagram of the undirected graph corresponding to the adjacency matrix in the present invention; Figure 5 The present invention is a schematic structural diagram of a computer device. DETAILED DESCRIPTION

[0017] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] Example 1, please refer to Figures 1-4As shown, the technical solution provided by the present invention is: a method for dynamically optimizing the thermal efficiency of an industrial furnace, which collects infrared images of a working industrial furnace, divides the industrial furnace into multiple different industrial furnace areas based on the infrared images, identifies the real-time thermal efficiency corresponding to different industrial furnace areas, and dynamically adjusts the industrial furnace areas with low real-time thermal efficiency to optimize the thermal efficiency of the industrial furnace; In this embodiment, the dynamic optimization control method for the thermal efficiency of an industrial furnace is as follows: Step S1: collecting infrared surface images of the working industrial furnace from multiple viewing angles using an infrared collection device; wherein the infrared collection device may be an infrared camera: The industrial furnace is approximately regarded as a cylinder, and multiple viewing angles do not include the bottom and top surfaces; Step S2, analyzing the outer surface temperature distribution of the industrial furnace based on the infrared surface image, and dividing the industrial furnace into a plurality of industrial furnace areas; In the present invention, step S2 includes the following sub-steps: Step S21, obtaining infrared surface images of the working industrial furnace at multiple viewing angles, stitching the infrared surface images at multiple viewing angles to obtain a stitched infrared image; identifying pixel values of all pixels in the stitched infrared image, and identifying real-time temperature values corresponding to the pixel values of the pixels by a table lookup method; Step S22, as Figure 2-Figure 3 As shown, the number of burners connected to the industrial furnace and the connection position of each burner are read, and with the connection position as the center, initial division intervals are set on both sides of the connection position to obtain the combustion radiation area of the corresponding burner; Step S23: identifying two adjacent combustion radiation areas based on the stitched infrared image. If there is a blank area between the adjacent combustion radiation areas, the corresponding blank area is recorded as an independent combustion area. If there is no blank area between the adjacent combustion radiation areas, no operation is performed. Step S24: construct the industrial furnace area corresponding to the combustion radiation area. The construction process is as follows: Step S241: Select any pixel at the bottom of the combustion radiation area as the first pixel of the industrial furnace area, and add any pixel adjacent to the selected pixel to the industrial furnace area; Step S242: Calculate the average of the real-time temperature values corresponding to all pixels in the industrial furnace area, and record it as the average temperature of the sub-area corresponding to the industrial furnace area; and calculate the standard deviation of the temperature values corresponding to all pixels in the corresponding industrial furnace area based on the average temperature of the sub-area. Step S243: The sub-region average temperature minus the standard deviation is used as the left endpoint, and the sub-region average temperature plus the standard deviation is used as the right endpoint to obtain the screening interval; Step S244: If the temperature values of all pixels in the industrial furnace area are within the screening interval, the adjacent pixel last added to the industrial furnace area is deemed qualified. If the temperature value of any pixel in the industrial furnace area is outside the screening range, the adjacent pixel added to the industrial furnace area is deemed unqualified and the corresponding adjacent pixel is removed; Step S245: When all adjacent pixels are unqualified, an industrial furnace area in the combustion radiation area is obtained, and similarly, all industrial furnace areas in the combustion radiation area are obtained; Step S25: According to step S24, obtain the industrial furnace areas corresponding to all independent combustion areas; Step S26: Summarize the combustion radiation area and the combustion independent area to obtain the industrial furnace area corresponding to the industrial furnace.

[0019] Step S3, clustering the industrial furnace regions based on the similarity and position relationship between the corresponding industrial furnace regions to obtain updated industrial furnace regions; In the present invention, the updating process is specifically as follows: Step S31: Acquire the industrial furnace area, and then read the average temperature of the sub-area of each industrial furnace area, and use the sub-area average temperature as the characteristic value TZi of the corresponding industrial furnace area; where i is the number of the different industrial furnace areas, i=1, 1, ..., z, and z is a positive integer; Step S32: Calculate the similarity XSij of the corresponding feature values of any two industrial furnace regions using a similarity function. The similarity function is as follows: ; In the formula, e is a natural constant, j is the number of another industrial furnace area, TZj is the characteristic value of another industrial furnace area, ||TZi-TZj|| represents the calculation of the Euclidean distance between TZi and TZj; σ is the Gaussian kernel, specifically a constant; In step S33, the numbers of the industrial furnace regions are considered as vertices, and the similarities of the corresponding eigenvalues of multiple industrial furnace regions are considered as edge weights to obtain a similarity matrix XS. Based on the similarity matrix, an adjacency matrix LJ corresponding to the similarity matrix (i.e., an edge weight matrix of an undirected graph) is constructed. A graph is a data structure and model, and the simplest and most effective way to store a graph in a computer is as a matrix. Optionally, the adjacency matrix can be constructed as follows: (1) K-nearest neighbor method: only retain the top K edges with the greatest similarity for each vertex; (2) ϵ-neighborhood method: If XSij>ϵ, then keep the edge; where ϵ is a constant (3) Full connection method: LJ=XS (all vertices are connected to each other); It should be noted that the adjacency matrix LJ is a symmetric matrix, that is, the element LJij=LJji in the adjacency matrix; Step S34: Calculate the degree matrix D corresponding to the adjacency matrix using the formula. The calculation formula for each element in the degree matrix is as follows: ; Where Dii represents the degree of vertex i (i.e. the sum of the weights of the edges connected to vertex i); Wherein, the degree matrix is a diagonal matrix, so when i≠j, Dij=0; LJij is the element in the adjacency matrix LJ, i represents the number of rows in the adjacency matrix, and j represents the number of columns in the adjacency matrix; For example, Figure 4 As shown, 1, 2, 3, 4, and 5 are the five vertices of the undirected graph corresponding to the adjacency matrix. The weights of the edges connecting the five vertices are all 1, so the form of converting them into a matrix is: ; D11 represents the degree of vertex 1, adding the elements of the first row in the adjacency matrix LJ, that is: D1=D11+D12+D13+D14+D15=0+1+0+1+0=2; Step S35: Calculate the Laplace matrix LP using the adjacency matrix and the degree matrix. The optional Laplace matrix calculation method is: Unnormalized Laplace matrix: LP1=D-LJ; Symmetrically normalized Laplacian matrix: ;Where I is the identity matrix and × is the matrix multiplication operation; Normalized Laplace matrix of random walk: LP3=D -1 ×LP1=ID -1 ×LJ; Step S36, calculating the Laplace eigenvalues LTZ and the Laplace eigenvectors LXL of the Laplace matrix; arranging the first k Laplace eigenvectors into a characteristic matrix U; Among them, the Laplace eigenvalue LTZ and the Laplace eigenvector LXL can be obtained by solving the characteristic equation: LP1×LXL=LTZ×LXL; which is equivalent to solving det(LP1-LTZ×I)=0; where det represents the determinant operation; It should be noted that LP2 and LP3 need to skip the smallest zero eigenvalue; Step S37, normalizing each row in the feature matrix to obtain a normalized feature matrix GU; The unitization process is as follows: ; Where Unm represents any element in the feature matrix, n is the number of rows in the feature matrix, m is the number of columns in the feature matrix, the upper limit of n is p, and the upper limit of m is k; Step S38: Consider each row in the normalized feature matrix as the embedding of an element point in the k-dimensional space, and consider the nth row of data as a normalized vector, thereby obtaining p normalized vectors; and use the K-means clustering algorithm to cluster the p normalized vectors into k clusters. For example, if the normalized feature matrix is 2*3, two normalized vectors are obtained, and each normalized vector is regarded as the unit vector of a certain element point in three-dimensional space; Step S39: For any industrial furnace area, if different industrial furnace areas are located in the same cluster and the corresponding different industrial furnace areas are adjacent, the corresponding different industrial furnace areas are regarded as the same industrial furnace area, the corresponding industrial furnace areas are connected and the industrial furnace areas are updated; otherwise, no operation is performed.

[0020] Step S4, calculating the updated thermal efficiency of the industrial furnace area, and determining the thermal efficiency state of the corresponding industrial furnace area based on the thermal efficiency; In this embodiment, step S4 includes the following sub-steps: Step S41, measuring the sub-region areas MJc of different industrial furnace regions, where c is the updated number of the industrial furnace region, c=1, 2, ..., x; Step S42, reading the material types of different industrial furnace areas according to the design drawing of the industrial furnace, and reading the corresponding thermal conductivity RDc based on the material type; Exemplary material types for industrial furnace areas include: high-alumina refractory bricks, magnesia bricks, and ceramic fiber felt; Among them, the thermal conductivity of high alumina refractory bricks is 1.5-2.5 (W / (m·K)); the thermal conductivity of magnesia bricks is 3.0-5.0 (W / (m·K)); the thermal conductivity of ceramic fiber felt is 0.05~0.15 (W / (m·K)); Step S43, adding and averaging the updated real-time temperature values corresponding to all pixels in the industrial furnace area to obtain the sub-area average temperature PJWc; Step S44, calculate the heat loss JRSc of the sub-area of the industrial furnace area using the formula, the specific formula is as follows: JRSc=RDc×MJc×(PJWc-HW); where HW is the ambient temperature; Step S45, calculating the sub-region thermal efficiency RXLc of the industrial furnace region by the formula, the specific formula is as follows: RXLc = 1 - JRSc ÷ SRXc; SRXc is the input thermal efficiency, calculated by multiplying the mass of fuel added to the corresponding burner in the industrial furnace area by the lower heating value of the corresponding fuel. The lower heating value is the heat released when the water vapor in the combustion products remains in a gaseous state after the fuel is completely burned. It is often used to reflect the actual heat available for the equipment. Step S46: The thermal efficiency of the sub-region of the industrial furnace region is compared with the thermal efficiency threshold. If the thermal efficiency of the sub-region is greater than or equal to the thermal efficiency threshold, no operation is performed; if the thermal efficiency of the sub-region is less than the thermal efficiency threshold, the corresponding industrial furnace region is marked as a sub-region with abnormal thermal efficiency. Step S47, identifying abnormal conditions in all industrial furnace areas, summarizing abnormal thermal efficiency sub-areas and sending them to a storage terminal for storage; Step S5, identifying the abnormal thermal efficiency sub-region, and dynamically adjusting the combustion state of the abnormal thermal efficiency sub-region by using a control variable method until the thermal efficiency of the sub-region of the abnormal thermal efficiency sub-region reaches a thermal efficiency threshold; Specifically, the adjustment measures of the control variable method include: increasing the burner output corresponding to the sub-area with abnormal thermal efficiency and adjusting the gas / air ratio; increasing the thickness of the insulation layer in the sub-area with abnormal thermal efficiency and repairing the furnace wall; adjusting the opening of the primary air / secondary air valve corresponding to the sub-area with abnormal thermal efficiency, etc.

[0021] In this application, if a corresponding calculation formula appears, the above calculation formula is dimensionless and its numerical calculation is performed. The weight coefficient, proportional coefficient and other coefficients in the formula are set to a result value obtained by quantifying each parameter. Regarding the size of the weight coefficient and the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the result value, it is acceptable.

[0022] Example 2, Figure 5The present invention is a schematic diagram of the structure of a computer device, which may include: a processor, a communications interface, a memory, and a communications bus, wherein the processor, the communications interface, and the memory communicate with each other via the communications bus. The processor may call logic instructions in the memory to execute a method for dynamically optimizing the thermal efficiency of an industrial furnace. The method includes: using an infrared acquisition device to collect infrared surface images of a working industrial furnace from multiple viewing angles; analyzing the temperature distribution of the outer surface of the industrial furnace based on the infrared surface images and dividing the industrial furnace into multiple industrial furnace regions; clustering the industrial furnace regions based on the similarity and positional relationship between corresponding industrial furnace regions to obtain updated industrial furnace regions; calculating the thermal efficiency of the updated industrial furnace regions and determining the thermal efficiency status of the corresponding industrial furnace regions based on the thermal efficiency; identifying sub-regions with abnormal thermal efficiency and dynamically adjusting the combustion status of the sub-regions with abnormal thermal efficiency using a control variable method until the thermal efficiency of the sub-regions with abnormal thermal efficiency reaches a thermal efficiency threshold.

[0023] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0024] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a dynamic optimization control method for the thermal efficiency of an industrial furnace provided by the above methods, the method including: collecting infrared surface images of a working industrial furnace at multiple perspectives through infrared acquisition equipment; analyzing the outer surface temperature distribution of the industrial furnace based on the infrared surface image, and dividing the industrial furnace into multiple industrial furnace areas; clustering the industrial furnace areas based on the similarity and position relationship between the corresponding industrial furnace areas of the industrial furnace to obtain updated industrial furnace areas; calculating the thermal efficiency of the updated industrial furnace area, and judging the thermal efficiency status of the corresponding industrial furnace area based on the thermal efficiency; identifying abnormal thermal efficiency sub-areas, and dynamically adjusting the combustion status of the abnormal thermal efficiency sub-areas through the control variable method until the sub-area thermal efficiency of the abnormal thermal efficiency sub-area reaches the thermal efficiency threshold.

[0025] On the other hand, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned method for dynamic optimization control of the thermal efficiency of an industrial furnace, the method comprising: collecting infrared surface images of a working industrial furnace at multiple perspectives through infrared acquisition equipment; analyzing the outer surface temperature distribution of the industrial furnace based on the infrared surface image, and dividing the industrial furnace into multiple industrial furnace areas; clustering the industrial furnace areas based on the similarity and position relationship between the corresponding industrial furnace areas of the industrial furnace to obtain updated industrial furnace areas; calculating the thermal efficiency of the updated industrial furnace area, and judging the thermal efficiency status of the corresponding industrial furnace area based on the thermal efficiency; identifying abnormal thermal efficiency sub-areas, and dynamically adjusting the combustion status of the abnormal thermal efficiency sub-areas through the control variable method until the sub-area thermal efficiency of the abnormal thermal efficiency sub-area reaches the thermal efficiency threshold.

[0026] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0027] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0028] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for dynamic optimization control of thermal efficiency of an industrial furnace, characterized in that: Methods include: Step S1, collecting infrared surface images of a working industrial furnace at multiple viewing angles using an infrared collection device; Step S2, analyzing the temperature distribution of the outer surface of the industrial furnace based on the infrared surface image, and dividing the industrial furnace into a plurality of industrial furnace areas; Step S3, clustering the industrial furnace regions based on the similarity and position relationship between the corresponding industrial furnace regions to obtain updated industrial furnace regions; Step S4, calculating the updated thermal efficiency of the industrial furnace area, and determining the thermal efficiency state of the corresponding industrial furnace area based on the thermal efficiency; Step S5: identifying the abnormal thermal efficiency sub-region, and dynamically adjusting the combustion state of the abnormal thermal efficiency sub-region by using a control variable method until the thermal efficiency of the abnormal thermal efficiency sub-region reaches a thermal efficiency threshold.

2. The method for dynamic optimization control of thermal efficiency of an industrial furnace according to claim 1, characterized in that: The step S2 includes the following sub-steps: Step S21, obtaining infrared surface images of the working industrial furnace at multiple viewing angles, stitching the infrared surface images at multiple viewing angles to obtain a stitched infrared image; identifying pixel values of all pixels in the stitched infrared image, and identifying real-time temperature values corresponding to the pixel values of the pixels by a table lookup method; Step S22: Read the number of burners connected to the industrial furnace and the connection position of each burner, and set initial division intervals on both sides of the connection position with the connection position as the center to obtain the combustion radiation area of the corresponding burner; Step S23: identifying two adjacent combustion radiation areas based on the stitched infrared image. If there is a blank area between the adjacent combustion radiation areas, the corresponding blank area is recorded as an independent combustion area. If there is no blank area between the adjacent combustion radiation areas, no operation is performed. Step S24, constructing an industrial furnace area corresponding to the combustion radiation area; Step S25: According to step S24, obtain the industrial furnace areas corresponding to all independent combustion areas; Step S26: Summarize the combustion radiation area and the combustion independent area to obtain the industrial furnace area corresponding to the industrial furnace.

3. The method for dynamic optimization control of thermal efficiency of an industrial furnace according to claim 1, characterized in that: The construction process of the combustion radiation area corresponding to the industrial furnace area is as follows: Step S241: Select any pixel at the bottom of the combustion radiation area as the first pixel of the industrial furnace area, and add any pixel adjacent to the selected pixel to the industrial furnace area; Step S242: Calculate the average of the real-time temperature values corresponding to all pixels in the industrial furnace area, and record it as the average temperature of the sub-area corresponding to the industrial furnace area; and calculate the standard deviation of the temperature values corresponding to all pixels in the corresponding industrial furnace area based on the average temperature of the sub-area. Step S243: The sub-region average temperature minus the standard deviation is used as the left endpoint, and the sub-region average temperature plus the standard deviation is used as the right endpoint to obtain the screening interval; Step S244: If the temperature values of all pixels in the industrial furnace area are within the screening interval, the adjacent pixel last added to the industrial furnace area is deemed qualified. If the temperature value of any pixel in the industrial furnace area is outside the screening range, the adjacent pixel added to the industrial furnace area is deemed unqualified and the corresponding adjacent pixel is removed; Step S245: When all adjacent pixel points are unqualified, an industrial furnace area in the combustion radiation area is obtained, and similarly, all industrial furnace areas in the combustion radiation area are obtained.

4. The method for dynamic optimization control of thermal efficiency of an industrial furnace according to claim 1, characterized in that: The step S3 includes the following sub-steps: Step S31: Acquire the industrial furnace area, and then read the average temperature of the sub-area of each industrial furnace area, and use the sub-area average temperature as the characteristic value TZi of the corresponding industrial furnace area; where i is the number of the different industrial furnace areas, i=1, 1, ..., z, and z is a positive integer; Step S32: Calculate the similarity XSij of the corresponding feature values of any two industrial furnace regions using a similarity function. The similarity function is as follows: ; In the formula, e is a natural constant, j is the number of another industrial furnace area, TZj is the eigenvalue of another industrial furnace area, ||TZi-TZj|| represents the calculation of the Euclidean distance between TZi and TZj; σ is the Gaussian kernel.

5. The method for dynamic optimization control of thermal efficiency of an industrial furnace according to claim 4, characterized in that: The step S3 further includes the following sub-steps: Step S33: Consider the numbers of the industrial furnace regions as vertices, and the similarities of the corresponding eigenvalues of the multiple industrial furnace regions as the weights of the edges to obtain a similarity matrix XS, and construct an adjacency matrix LJ corresponding to the similarity matrix based on the similarity matrix; Step S34: Calculate the degree matrix D corresponding to the adjacency matrix using the formula. The calculation formula for each element in the degree matrix is as follows: ; Where Dii represents the degree of vertex i, when i≠j, Dij=0; LJij is the element in the adjacency matrix LJ, i represents the number of rows in the adjacency matrix, and j represents the number of columns in the adjacency matrix; Step S35: Calculate the Laplacian matrix LP using the adjacency matrix and the degree matrix.

6. The method for dynamic optimization control of thermal efficiency of an industrial furnace according to claim 5, characterized in that: The step S3 further includes: Step S36, calculating the Laplace eigenvalues LTZ and the Laplace eigenvectors LXL of the Laplace matrix; arranging the first k Laplace eigenvectors into a characteristic matrix U; Step S37, normalizing each row in the feature matrix to obtain a normalized feature matrix GU; The unitization process is as follows: ; Where Unm represents any element in the feature matrix, n is the number of rows in the feature matrix, m is the number of columns in the feature matrix, the upper limit of n is p, and the upper limit of m is k; Step S38: Consider each row in the normalized feature matrix as the embedding of an element point in the k-dimensional space, and consider the nth row of data as a normalized vector, thereby obtaining p normalized vectors; and use the K-means clustering algorithm to cluster the p normalized vectors into k clusters. Step S39: For any industrial furnace area, if different industrial furnace areas are located in the same cluster and the corresponding different industrial furnace areas are adjacent, the corresponding different industrial furnace areas are regarded as the same industrial furnace area, the corresponding industrial furnace areas are connected and the industrial furnace areas are updated; otherwise, no operation is performed.

7. The method for dynamic optimization control of thermal efficiency of an industrial furnace according to claim 1, characterized in that: The step S4 includes the following sub-steps: Step S41, measuring the sub-region areas MJc of different industrial furnace regions, where c is the updated number of the industrial furnace region, c=1, 2, ..., x; Step S42, reading the material types of different industrial furnace areas according to the design drawing of the industrial furnace, and reading the corresponding thermal conductivity RDc based on the material type; Step S43: Add and average the real-time temperature values corresponding to all pixels in the updated industrial furnace area to obtain the sub-area average temperature PJWc.

8. The method for dynamic optimization control of thermal efficiency of an industrial furnace according to claim 7, characterized in that: The step S4 further includes the following sub-steps: Step S44, calculate the heat loss JRSc of the sub-area of the industrial furnace area using the formula, the specific formula is as follows: JRSc=RDc×MJc×(PJWc-HW); where HW is the ambient temperature; Step S45, calculating the sub-region thermal efficiency RXLc of the industrial furnace region by the formula, the specific formula is as follows: RXLc=1-JRSc÷SRXc; SRXc is the input thermal efficiency, which is obtained by multiplying the mass of fuel added to the corresponding burner in the industrial furnace area by the lower heating value of the corresponding fuel; Step S46: The thermal efficiency of the sub-region of the industrial furnace region is compared with the thermal efficiency threshold. If the thermal efficiency of the sub-region is greater than or equal to the thermal efficiency threshold, no operation is performed; if the thermal efficiency of the sub-region is less than the thermal efficiency threshold, the corresponding industrial furnace region is marked as a sub-region with abnormal thermal efficiency. Step S47: Identify abnormal conditions in all industrial furnace areas, summarize abnormal thermal efficiency sub-areas, and send them to a storage terminal for storage.

9. A computer device, characterized in that: The computer device comprises: a memory storing a computer program; A processor is communicatively connected to the memory, and when the computer program is executed by the processor, the method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images