Method for detecting flatness of refractory material on kiln car based on image analysis

Abstract

The invention relates to the technical field of flatness detection, and discloses a method for detecting the flatness of a refractory material on a kiln car based on image analysis, which is used for detecting the flatness of the refractory material on the kiln car based on image analysis, and comprises the following steps: firstly, obtaining the size of the refractory material, and selecting a proper camera according to the size of the refractory material; the method comprises the following steps: determining a proper acquisition distance and a proper acquisition angle, extracting edge image information and surface image information of a refractory material, evaluating the edge flatness of the refractory material based on the edge image information of the refractory material, and evaluating the surface flatness of the refractory material based on the surface image information of the refractory material. The method not only can reduce manual intervention, improve the detection speed and reduce the detection cost, but also can adapt to different refractory material types and complex detection environments, and has higher universality and practicability.

Description

Technical Field

[0001] The invention relates to the technical field of flatness detection, and in particular to a method for detecting the flatness of refractory materials on a kiln car based on image analysis. Background Art

[0002] Refractory bricks for kiln cars are mainly used for the inner cladding of high-temperature devices such as kilns, furnaces, and furnaces. These high-temperature devices play an important role in industrial production, such as steel smelting, ceramic production, cement manufacturing, and glass manufacturing. Refractory bricks can withstand high temperatures and maintain structural stability, thereby effectively protecting the refractory layer of high-temperature devices and ensuring the smooth progress of the production process. The flatness of refractory bricks is an important quality indicator, which directly affects the use effect of refractory bricks and the stability of kiln cars.

[0003] Traditional methods for detecting the flatness of refractory materials on kiln cars usually rely on manual detection, which is not only cumbersome to operate, but also easily affected by human factors, resulting in inaccurate detection results. Therefore, the present invention proposes a method for detecting the flatness of refractory materials on kiln cars based on image analysis. Summary of the invention

[0004] The purpose of the present invention is to provide a method for detecting the flatness of refractory materials on a kiln car based on image analysis to solve the above technical problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A method for detecting the flatness of refractory materials on a kiln car based on image analysis, the method comprising the following steps: Step S1, obtaining size information of the refractory material, formulating a detection strategy according to the size information of the refractory material, and obtaining image information of the refractory material according to the detection strategy; Step S2, preprocessing the collected image, including steps such as denoising, smoothing and enhancement, to improve image quality and reduce the impact of noise and interference information on the detection results; Step S3, extracting edge image information of the refractory material, analyzing the edge image of the refractory material, and evaluating the edge flatness of the refractory material; Step S4, extracting surface image information of the refractory material, analyzing the surface image of the refractory material, and evaluating the surface flatness of the refractory material; Step S5: evaluating the overall flatness of the refractory material according to the edge flatness and surface flatness of the refractory material.

[0006] As a further description of the solution of the present invention, the detection strategy in step S1 is: Select the camera according to the size information of the refractory material, and determine the appropriate acquisition distance and angle according to the size of the object and the focal length of the camera to ensure that the edge image and surface image of the refractory material can be clearly captured.

[0007] As a further description of the solution of the present invention, the specific process of step S3 includes: Extract the complete edge image of the refractory material, convert the image into grayscale, and extract the defective area in the image according to the grayscale value; Extract defect area images and number all defect areas, which are numbered 1, 2, ..., k in sequence; Extract the length and depth of all defect areas.

[0008] As a further description of the solution of the present invention, the specific process of step S3 also includes: Get the length of the i-th defect area , get the depth of the i-th defect area , where i belongs to k; pass Calculate the construction coefficient of the i-th defect area , the construction coefficient of the i-th defect area Substitute the following formula to calculate the edge flatness evaluation index of refractory materials ; ; In the formula, is the defect area construction coefficient threshold, is the difference reference value, is the weight coefficient, and Depends on the defect location. When the corner is missing , when the edge is missing ,and ; The refractory edge flatness evaluation index The trained refractory material edge flatness evaluation model is input, and the refractory material edge flatness score A is output.

[0009] As a further description of the solution of the present invention, the working process of step S4 includes: Extract the complete surface image of the refractory material, convert the image into grayscale, and extract the flat area and non-flat area in the image according to the grayscale value; Extract the uneven area image and number all uneven areas, which are numbered 1, 2, ..., x in sequence; Extract the perimeter and area of ​​all non-flat areas.

[0010] As a further description of the solution of the present invention, the working process of step S4 also includes: Get the perimeter of the yth non-flat area , get the area of ​​the yth non-flat region Get the depth of the y-th non-flat area , where y belongs to x; The construction coefficient of the yth uneven area is calculated by the following formula : ; In the formula, and are weight coefficients, y belongs to x; The construction coefficient of the yth non-flat area The first threshold value with the preset By comparison, if the construction coefficient of the yth non-flat area Greater than the preset first construction threshold , it means that the yth non-flat area is a crack; The construction coefficient of the yth non-flat area The second threshold value with the preset By comparison, if the construction coefficient of the yth non-flat area Greater than the preset second construction threshold , it means that the yth non-flat area is a bulge; The construction coefficients of x non-flat areas are calculated in sequence to determine the shapes of all non-flat areas.

[0011] As a further description of the solution of the present invention, the working process of step S4 also includes: Get the number of all cracks n and all bulges m in the uneven area, and calculate the area of ​​all cracks , all bulge areas , the refractory surface flatness evaluation index is calculated by the following formula : ; In the formula, and are weight coefficients, is the surface area of ​​the uneven area, is the surface area of ​​the refractory material; Refractory surface flatness evaluation index The trained refractory surface flatness evaluation model is input, and the refractory surface flatness score B is output.

[0012] As a further description of the solution of the present invention, the working process of step S5 includes: The mathematical calculation model of the overall flatness of refractory materials is constructed, and the expression is: ; The overall flatness of the refractory material Overall flatness threshold with preset refractory material Make comparisons; If the overall flatness of the refractory material Greater than or equal to the overall flatness threshold of the refractory material preset by the system , then the flatness of the refractory material is judged to be qualified; Otherwise, the flatness of the refractory material is judged to be unqualified.

[0013] Beneficial effects of the present invention: 1. The present invention detects the flatness of refractory materials on a kiln car based on image analysis. First, the size of the refractory materials is obtained, and a suitable camera is selected according to the size of the refractory materials, and a suitable acquisition distance and acquisition angle are determined. Then, the edge image information and the surface image information of the refractory materials are extracted, and the edge flatness of the refractory materials is evaluated based on the edge image information of the refractory materials. The surface flatness of the refractory materials is evaluated based on the surface image information of the refractory materials. This can not only reduce manual intervention, improve detection speed, and reduce detection costs, but also adapt to different types of refractory materials and complex detection environments, and has high versatility and practicality. 2. The present invention provides a method for detecting the edge flatness of a refractory material. First, a complete edge image of the refractory material is extracted, and the defect area image in the complete edge image is processed, and all defect areas are numbered, and the length and depth of each defect area are obtained. The structural coefficient of each defect area is calculated by a formula, and then the edge flatness evaluation index of the refractory material is calculated based on the structural coefficient of each defect area. Finally, the refractory material edge flatness evaluation index is input into a trained refractory material edge flatness evaluation model, and the refractory material edge flatness score is obtained as an output; 3. The present invention provides a method for detecting the surface flatness of a refractory material. First, extract the image of a non-flat area, number all the non-flat areas, obtain the perimeter of each non-flat area, obtain the area of ​​each non-flat area, obtain the depth of each non-flat area, calculate the structural coefficient of all the non-flat areas by a formula, compare the structural coefficient of all the non-flat areas with a preset first structural threshold, if the structural coefficient of the non-flat area is greater than the preset first structural threshold, it means that the current non-flat area is a crack; compare the structural coefficient of all the non-flat areas with a preset second structural threshold, if the structural coefficient of the non-flat area is greater than the preset second structural threshold, it means that the current non-flat area is a bulge, then calculate the refractory surface flatness evaluation index based on the number and area of ​​cracks and bulges, input the refractory surface flatness evaluation index into the trained refractory surface flatness evaluation model, and output the refractory surface flatness score; 4. The present invention provides a method for detecting the overall flatness of refractory materials. Based on the edge flatness score and the surface flatness score, a mathematical calculation model for the overall flatness of refractory materials is constructed, and the overall flatness of the refractory materials is compared with a preset overall flatness threshold of the refractory materials. If the overall flatness of the refractory materials is greater than or equal to the overall flatness threshold of the refractory materials preset by the system, the flatness of the refractory materials is judged to be qualified; otherwise, the flatness of the refractory materials is judged to be unqualified. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below in conjunction with the accompanying drawings.

[0015] Figure 1 It is a partial flow chart of the method for detecting the flatness of refractory materials on a kiln car based on image analysis provided by the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] See also Figure 1 The present invention is a method for detecting the flatness of refractory materials on a kiln car based on image analysis, and the method comprises the following steps: Step S1, obtaining size information of the refractory material, formulating a detection strategy according to the size information of the refractory material, and obtaining image information of the refractory material according to the detection strategy; Step S2, preprocessing the collected image, including steps such as denoising, smoothing and enhancement, to improve image quality and reduce the impact of noise and interference information on the detection results; Step S3, extracting edge image information of the refractory material, analyzing the edge image of the refractory material, and evaluating the edge flatness of the refractory material; Step S4, extracting surface image information of the refractory material, analyzing the surface image of the refractory material, and evaluating the surface flatness of the refractory material; Step S5: evaluating the overall flatness of the refractory material according to the edge flatness and surface flatness of the refractory material.

[0018] Through the above technical scheme, the present invention detects the flatness of the refractory material on the kiln car based on image analysis. First, the size of the refractory material is obtained, and a suitable camera is selected according to the size of the refractory material, and a suitable acquisition distance and acquisition angle are determined. Then, the edge image information of the refractory material and the surface image information of the refractory material are extracted, and the edge flatness of the refractory material is evaluated based on the edge image information of the refractory material. The surface flatness of the refractory material is evaluated based on the surface image information of the refractory material. This can not only reduce manual intervention, improve detection speed, and reduce detection costs, but also can adapt to different types of refractory materials and complex detection environments, and has high versatility and practicality.

[0019] The detection strategy in step S1 is: Select the camera according to the size information of the refractory material, and determine the appropriate acquisition distance and angle according to the size of the object and the focal length of the camera to ensure that the edge image and surface image of the refractory material can be clearly captured.

[0020] The specific process of step S3 includes: Extract the complete edge image of the refractory material, convert the image into grayscale, and extract the defective area in the image according to the grayscale value; Extract defect area images and number all defect areas, which are numbered 1, 2, ..., k in sequence; Extract the length and depth of all defect areas.

[0021] The specific process of step S3 also includes: Get the length of the i-th defect area , get the depth of the i-th defect area , where i belongs to k; pass Calculate the construction coefficient of the i-th defect area , the construction coefficient of the i-th defect area Substitute the following formula to calculate the edge flatness evaluation index of refractory materials : ; In the formula, is the defect area construction coefficient threshold, is the difference reference value, is the weight coefficient, and Depends on the defect location. When the corner is missing , when the edge is missing ,and ; The refractory edge flatness evaluation index The trained refractory material edge flatness evaluation model is input, and the refractory material edge flatness score A is output.

[0022] Through the above technical scheme, this embodiment provides a method for detecting the edge flatness of refractory materials. First, a complete edge image of the refractory material is extracted, the defect area image in the complete edge image is processed, and all defect areas are numbered to obtain the length and depth of each defect area. The structural coefficient of each defect area is calculated by a formula, and then the edge flatness evaluation index of the refractory material is calculated based on the structural coefficient of each defect area. Finally, the refractory material edge flatness evaluation index is input into the trained refractory material edge flatness evaluation model, and the refractory material edge flatness score is output.

[0023] It should be noted that the difference reference value , weight coefficient For experience value.

[0024] The working process of step S4 includes: Extract the complete surface image of the refractory material, convert the image into grayscale, and extract the flat area and non-flat area in the image according to the grayscale value; Extract the uneven area image and number all uneven areas, which are numbered 1, 2, ..., x in sequence; Extract the perimeter and area of ​​all non-flat areas.

[0025] The working process of step S4 also includes: Get the perimeter of the yth non-flat area , get the area of ​​the yth non-flat region , get the depth of the yth non-flat area , where y belongs to x; The construction coefficient of the yth uneven area is calculated by the following formula : ; In the formula, and are weight coefficients, y belongs to x; The construction coefficient of the yth non-flat area The first threshold value with the preset By comparison, if the construction coefficient of the yth non-flat area Greater than the preset first construction threshold , it means that the yth non-flat area is a crack; The construction coefficient of the yth non-flat area The second threshold value is constructed with the preset By comparison, if the construction coefficient of the yth non-flat area Greater than the preset second construction threshold , it means that the yth non-flat area is a bulge; The construction coefficients of x non-flat areas are calculated in sequence to determine the shapes of all non-flat areas.

[0026] The working process of step S4 also includes: Get the number of all cracks n and all bulges m in the uneven area, and calculate the area of ​​all cracks , all bulge areas , the refractory surface flatness evaluation index is calculated by the following formula : ; In the formula, and are weight coefficients, is the surface area of ​​the uneven area, is the surface area of ​​the refractory material; Refractory surface flatness evaluation index The trained refractory surface flatness evaluation model is input, and the refractory surface flatness score B is output.

[0027] Through the above technical scheme, this embodiment provides a method for detecting the surface flatness of refractory materials. First, extract the image of the non-flat area, number all the non-flat areas, obtain the perimeter of each non-flat area, obtain the area of ​​each non-flat area, obtain the depth of each non-flat area, calculate the structural coefficient of all non-flat areas through a formula, compare the structural coefficient of all non-flat areas with a preset first structural threshold, if the structural coefficient of the non-flat area is greater than the preset first structural threshold, it means that the current non-flat area is a crack; compare the structural coefficient of all non-flat areas with a preset second structural threshold, if the structural coefficient of the non-flat area is greater than the preset second structural threshold, it means that the current non-flat area is a bulge, and then calculate the refractory surface flatness evaluation index based on the number and area of ​​cracks and bulges, input the refractory surface flatness evaluation index into the trained refractory surface flatness evaluation model, and output the refractory surface flatness score.

[0028] It should be noted that the weight coefficient and For experience value.

[0029] The working process of step S5 includes: The mathematical calculation model of the overall flatness of refractory materials is constructed, and the expression is: The overall flatness of the refractory material Overall flatness threshold with preset refractory material Make comparisons; If the overall flatness of the refractory material Greater than or equal to the overall flatness threshold of the refractory material preset by the system , then the flatness of the refractory material is judged to be qualified; Otherwise, the flatness of the refractory material is judged to be unqualified.

[0030] Through the above technical scheme, this embodiment provides a method for detecting the overall flatness of refractory materials. Based on the edge flatness score and the surface flatness score, a mathematical calculation model for the overall flatness of the refractory material is constructed, and the overall flatness of the refractory material is compared with a preset overall flatness threshold of the refractory material; if the overall flatness of the refractory material is greater than or equal to the overall flatness threshold of the refractory material preset by the system, the flatness of the refractory material is judged to be qualified; otherwise, the flatness of the refractory material is judged to be unqualified.

[0031] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for detecting the flatness of refractory materials on a kiln car based on image analysis, characterized in that: The method comprises the following steps: Step S1, obtaining size information of the refractory material, formulating a detection strategy according to the size information of the refractory material, and obtaining image information of the refractory material according to the detection strategy; Step S2, preprocessing the collected image, including steps such as denoising, smoothing and enhancement, to improve image quality and reduce the impact of noise and interference information on the detection results; Step S3, extracting edge image information of the refractory material, analyzing the edge image of the refractory material, and evaluating the edge flatness of the refractory material; Step S4, extracting surface image information of the refractory material, analyzing the surface image of the refractory material, and evaluating the surface flatness of the refractory material; Step S5: evaluating the overall flatness of the refractory material according to the edge flatness and surface flatness of the refractory material.

2. The method for detecting the flatness of refractory materials on a kiln car based on image analysis according to claim 1 is characterized in that: The detection strategy in step S1 is: Select the camera according to the size information of the refractory material, and determine the appropriate acquisition distance and angle according to the size of the object and the focal length of the camera to ensure that the edge image and surface image of the refractory material can be clearly captured.

3. The method for detecting the flatness of refractory materials on a kiln car based on image analysis according to claim 1 is characterized in that: The specific process of step S3 includes: Extract the complete edge image of the refractory material, convert the image into grayscale, and extract the defective area in the image according to the grayscale value; Extract defect area images and number all defect areas, which are numbered 1, 2, ..., k in sequence; Extract the length and depth of all defect areas.

4. The method for detecting the flatness of refractory materials on a kiln car based on image analysis according to claim 3 is characterized in that: The specific process of step S3 also includes: Get the length of the i-th defect area , get the depth of the i-th defect area , where i belongs to k; pass Calculate the construction coefficient of the i-th defect area , the construction coefficient of the i-th defect area Substitute the following formula to calculate the edge flatness evaluation index of refractory materials : ; In the formula, is the defect area construction coefficient threshold, is the difference reference value, is the weight coefficient, and Depends on the defect location. When the corner is missing , when the edge is missing ,and ; The refractory edge flatness evaluation index The trained refractory material edge flatness evaluation model is input, and the refractory material edge flatness score A is output.

5. The method for detecting the flatness of refractory materials on a kiln car based on image analysis according to claim 1 is characterized in that: The working process of step S4 includes: Extract the complete surface image of the refractory material, convert the image into grayscale, and extract the flat area and non-flat area in the image according to the grayscale value; Extract the uneven area image and number all uneven areas, which are numbered 1, 2, ..., x in sequence; Extract the perimeter and area of ​​all non-flat areas.

6. The method for detecting the flatness of refractory materials on a kiln car based on image analysis according to claim 5 is characterized in that: The working process of step S4 also includes: Get the perimeter of the yth non-flat area , get the area of ​​the yth non-flat region Get the depth of the y-th non-flat area , where y belongs to x; The construction coefficient of the yth uneven area is calculated by the following formula : ; In the formula, and are weight coefficients, y belongs to x; The construction coefficient of the yth non-flat area The first threshold value with the preset By comparison, if the construction coefficient of the yth non-flat area Greater than the preset first construction threshold , it means that the yth non-flat area is a crack; The construction coefficient of the yth non-flat area The second threshold value is constructed with the preset By comparison, if the construction coefficient of the yth non-flat area Greater than the preset second construction threshold , it means that the yth non-flat area is a bulge; The construction coefficients of x non-flat areas are calculated in sequence to determine the shapes of all non-flat areas.

7. The method for detecting the flatness of refractory materials on a kiln car based on image analysis according to claim 6 is characterized in that: The working process of step S4 also includes: Get the number of all cracks n and all bulges m in the uneven area, and calculate the area of ​​all cracks , all bulge areas , the refractory surface flatness evaluation index is calculated by the following formula : ; In the formula, and are weight coefficients, is the surface area of ​​the uneven area, is the surface area of ​​the refractory material; Refractory surface flatness evaluation index The trained refractory surface flatness evaluation model is input, and the refractory surface flatness score B is output.

8. According to the method for detecting the flatness of refractory materials on a kiln car based on image analysis according to claim 1, it is characterized in that: The working process of step S5 includes: The mathematical calculation model of the overall flatness of refractory materials is constructed, and the expression is: ; The overall flatness of the refractory material Overall flatness threshold with preset refractory material Make comparisons; If the overall flatness of the refractory material Greater than or equal to the overall flatness threshold of the refractory material preset by the system , then the flatness of the refractory material is judged to be qualified; Otherwise, the flatness of the refractory material is judged to be unqualified.

Images