A method for monitoring blockage of air preheater

By analyzing the grayscale change curve and fluctuation difference in the air preamper tube sheet image, adjusting the grayscale value to enhance contrast, and using the Otsu threshold method to divide the deformation area, solving the inaccurate detection of tiny deformation of the air preamper tube sheet in the existing technology. The problem of this achieves more accurate blockage monitoring.

CN118864455BActive Publication Date: 2024-11-29DEQING JINYE ELECTRIC POWER TECH CO LTD +1
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411337182.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-25
Publication Date
2024-11-29
Estimated Expiration
2044-09-25

AI Technical Summary

Technical Problem

The slight deformation of the pipe sheet in the air preloader equipment leads to less obvious grayscale changes. The existing Otsu threshold method cannot accurately segment the deformation area, resulting in inaccurate detection and may lead to blockage of the air preloader.

Method used

By collecting the tube slice images, the grayscale change curve of each row of pixel points is obtained, the curve periodicity is analyzed, the fluctuation difference and abnormality degree is calculated, the grayscale value is adjusted, the image contrast is enhanced, and the deformation area is finally divided using the Otsu threshold method.

Benefits of technology

It realizes accurate identification of the deformation area of ​​the air preloader pipe sheet, improves the accuracy of clogging monitoring, prevents the air preloader equipment from overheating or overcooling, and extends the service life of the equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118864455B_ABST
    Figure CN118864455B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of image processing technology, and more specifically, to a blockage monitoring method for an air preheater, the method comprising: obtaining a plurality of grayscale change curves according to each row of pixel points in a tube segment image, obtaining a fluctuation difference amount of each pixel point in the tube segment image according to the periodicity of the grayscale change curve where each pixel point in the tube segment image is located; obtaining the abnormality degree of each pixel point in the tube segment image according to the difference in fluctuation difference amount between each pixel point in the tube segment image and other pixel points in its column; obtaining the deformation degree of each pixel point in the tube segment image according to the difference in abnormality degree between surrounding pixel points of each pixel point in the tube segment image; adjusting the grayscale value of each pixel point according to the deformation degree of each pixel point to obtain an enhanced tube segment image, segmenting the enhanced tube segment image, and identifying a deformation area. The present invention can accurately identify the deformation area and prevent the air preheater from being blocked.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology and more specifically to a method for monitoring the blockage of an air preheater. Background Art

[0002] The air preheater is an important equipment in thermal power plants and other industrial boiler systems. It is used to increase the temperature of the boiler inlet air, thereby improving combustion efficiency and energy-saving performance. However, blockage caused by deformation of the tube segments in the air preheater equipment may cause overheating or overcooling of the air preheater, affecting its normal operation and even causing damage to the equipment. Therefore, by real-time identification of the tube segment deformation area in the air preheater equipment, blockage of the air preheater can be prevented. When the tube segment deformation area in the air preheater equipment is found, the staff is notified to take timely measures to avoid subsequent serious failures of the equipment.

[0003] The patent application document with the publication number CN113870182A currently discloses an Otsu thresholding method with a mask. First, the number of masks and the number of permeable areas in the masks are determined, and a template of equal size is made according to the original image. The shielding area and the permeable area in the template are filled with grayscale shielding factors and permeability factors respectively; then the Hadamard product of the image and the mask is used as the target area to be extracted; then, the maximum between-class variance in the target area is calculated to obtain the threshold of the target area thresholding operation; finally, the threshold is binarized with the obtained threshold.

[0004] When there is a slight deformation of the tube segment in the air preheater equipment, the grayscale change of the deformation area is not obvious, and the grayscale of the deformation area is random. Therefore, the Otsu threshold segmentation method in the above method cannot accurately segment the deformation area, resulting in inaccurate detection of air preheater tube segment defects, which may cause subsequent blockage of the air preheater. Summary of the invention

[0005] In order to solve the problem that the grayscale change of the deformation area generated when there is a slight deformation of the tube segment in the air preheater equipment is not obvious, and the deformation area cannot be accurately segmented using the Otsu threshold method, the present invention proposes a blockage monitoring method for the air preheater, which includes the following steps:

[0006] Collect the pipe segment image; obtain each grayscale change curve according to the grayscale value of each row of pixels in the pipe segment image; obtain the period of each grayscale change curve and segment each grayscale change curve to obtain each band of each grayscale change curve; obtain the fluctuation difference of each pixel in the pipe segment image ; Represents the fluctuation difference of the i-th pixel in the segment image; Represents the number of bands where the grayscale value of the i-th pixel and the corresponding position of the grayscale change curve of other bands are consistent; Represents the DTW distance between the band of the grayscale change curve where the i-th pixel is located and the j-th band except this band; Represents the number of bands of the grayscale change curve where the i-th pixel is located; Represents the gray value of the i-th pixel; Represents the grayscale value corresponding to the target serial number in the jth band outside the band on the grayscale change curve where the i-th pixel is located; || represents the absolute value symbol; obtain the abnormality degree of each pixel point, and the abnormality degree is the sum of the differences between the fluctuation difference amount of each pixel point and the fluctuation difference amount of other pixels in its column;

[0007] The deformation degree of each pixel is obtained, and the deformation degree is positively correlated with the abnormality degree of each pixel; the gray value of each pixel is adjusted according to the deformation degree of each pixel to obtain an enhanced pipe segment image; and the enhanced pipe segment image is threshold segmented to identify the deformation area.

[0008] The innovation of the present invention lies in that according to the characteristics of the change in the grayscale change curve of each row of pixels caused by the deformation of the pipe segment in the pipe segment image, the deformation degree of each pixel is obtained and the grayscale value of each pixel is adjusted, so that there is a significant difference in the grayscale value between the deformed area and the normal area. Finally, the Otsu threshold segmentation method is used to segment it to obtain the prepared deformation area, thereby preventing subsequent air preheater blockage.

[0009] Preferably, the obtaining of each grayscale change curve includes:

[0010] A two-dimensional coordinate system is constructed with the grayscale value of the pixel as the vertical axis and the pixel serial number as the horizontal axis. Taking any row of pixels in the tube image as an example, the row of pixels is input into the two-dimensional coordinate system in order from left to right to draw a grayscale change curve, and several grayscale change curves are obtained.

[0011] This facilitates the subsequent analysis of the periodicity of the grayscale change curve and obtains the fluctuation difference of each pixel in the pipe segment image.

[0012] Preferably, the step of obtaining the period of each grayscale change curve and segmenting each grayscale change curve to obtain each band of each grayscale change curve includes:

[0013] Taking any grayscale change curve as an example, Fourier transform is performed on the grayscale change curve, the inverse of the frequency with the largest amplitude in the frequency domain is taken as the period, and the grayscale change curve is divided according to the period to obtain various bands of the grayscale change curve.

[0014] Preferably, the number of fluctuations of the grayscale value of the pixel point and the corresponding position of other bands of the grayscale change curve where the pixel point is located is consistent includes:

[0015] The serial number in the band of the grayscale change curve where the i-th pixel in the pipe image is located is recorded as the target serial number, and the number of bands whose grayscale values ​​corresponding to the target serial number in other bands other than the band on the grayscale change curve where the i-th pixel is located are consistent with the grayscale value of the i-th pixel is recorded as the number of bands whose grayscale values ​​at the corresponding positions of the i-th pixel and other bands of the grayscale change curve are consistent.

[0016] Preferably, obtaining the abnormality degree of each pixel point includes:

[0017] ;

[0018] In the formula, Represents the abnormality degree of the i-th pixel in the pipe segment image; Represents the fluctuation difference of the i-th pixel in the segment image; Represents the number of pixels in the column where the i-th pixel is located in the tube image except the i-th pixel. The fluctuation difference of each pixel; Represents the number of pixels in the column where the i-th pixel in the tube image is located, except for the i-th pixel; || represents the absolute value symbol.

[0019] The sum of the differences between the fluctuation difference of each pixel and the fluctuation difference of other pixels in its column is taken as the abnormality degree of each pixel. The characteristic that the deformed pixel has a larger fluctuation difference than other normal pixels in its column is taken into consideration, making the abnormality degree of each pixel more accurate.

[0020] Preferably, obtaining the deformation degree of each pixel point includes:

[0021] Get the target position of each reference row of the i-th pixel;

[0022] ;

[0023] In the formula, Represents the deformation degree of the i-th pixel in the pipe segment image; Represents the abnormality degree of the i-th pixel in the pipe segment image; Represents the number of all reference rows for the i-th pixel in the tube segment image; Represents the abnormality degree of the left adjacent pixel of the target position in the kth reference row of the i-th pixel; Represents the abnormality degree of the right adjacent pixel of the target position in the kth reference row of the i-th pixel.

[0024] The larger the deformation degree, the more likely the pixel is a deformed area. Its grayscale value needs to be increased to form a contrast with the normal area.

[0025] Preferably, obtaining the target position of each reference row of the i-th pixel point includes:

[0026] The row where the i-th pixel is located, as well as the row before and after the row, are all used as reference rows for the i-th pixel; the position of the i-th pixel in the row is recorded as the target position of the row where the i-th pixel is located, and based on the target position of the row where the i-th pixel is located, the target position of each reference row of the i-th pixel is obtained.

[0027] Preferably, the obtaining of the enhanced segment image includes:

[0028] The product of the deformation degree and the gray value of each pixel in the pipe segment area is used as the updated gray value of each pixel to obtain the enhanced pipe segment image.

[0029] The grayscale value difference between the deformed area and the normal area in the enhanced segment image is large, and the precise deformed area can be segmented later.

[0030] The present invention has the following beneficial effects: according to the characteristic of periodic change of the grayscale change curve of each row of pixels caused by deformation of the pipe segment in the pipe segment image, the present invention obtains the fluctuation difference value of each pixel point, and then obtains the abnormality degree of each pixel point according to the sum of the difference between the fluctuation difference amount of each pixel point and the fluctuation difference amounts of other pixels points in its column, taking into account the characteristic that the fluctuation difference amount of the deformed pixel point is larger than that of other normal pixels in its column, so that the abnormality degree of each pixel point is more accurate, and finally, the deformation degree of each pixel point is obtained according to the abnormality degree to adjust the grayscale value of each pixel point, so that there is a significant difference in the grayscale value between the deformed area and the normal area, and finally, the prepared deformation area can be obtained after segmenting it using the Otsu threshold segmentation method, thereby preventing subsequent air preheater from being blocked. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0032] Figure 1 It is a flow chart of the steps of a method for monitoring blockage of an air preheater according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0034] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0035] See also Figure 1 , which shows a flow chart of the steps of a method for monitoring blockage of an air preheater provided by an embodiment of the present invention, the method comprising the following steps:

[0036] S001. Collect segment images.

[0037] It should be noted that the purpose of the present invention is to identify the deformation area of ​​the tube segment in the air preheater, so as to prevent the subsequent blockage of the air preheater, so it is necessary to collect the tube segment image.

[0038] In an embodiment of the present invention, a high-definition camera is used to photograph the segments in the air preheater to obtain an RGB image of the segment. To facilitate subsequent analysis, the RGB image of the segment is grayed to obtain an image of the segment.

[0039] S002. Obtain a plurality of grayscale change curves, and obtain the fluctuation difference of each pixel point in the pipe segment image according to the periodicity of the grayscale change curve where each pixel point in the pipe segment image is located.

[0040] It should be noted that it is known that the intervals between all adjacent tube segments are fixed, and the edge curvature of the tube segment is certain. Therefore, when the tube segment is not deformed, the grayscale fluctuation of each row of pixels in the tube segment image presents a fixed periodicity. If the tube segment is deformed, the pixels in the deformed area of ​​the tube segment image will affect the grayscale fluctuation period of each row of pixels in the tube segment image. Therefore, in the present invention, each grayscale change curve is first drawn according to the grayscale value of each row of pixels in the tube segment image, and then the periodicity of each grayscale change curve is analyzed to find the pixels that affect the periodicity of the grayscale change curve, that is, the pixels in the deformation area.

[0041] In the embodiment of the present invention, a two-dimensional coordinate system is constructed with the grayscale value of the pixel as the vertical axis and the serial number of the pixel as the horizontal axis. Taking any row of pixels in the tube slice image as an example, the row of pixels is input into the two-dimensional coordinate system in order from left to right to draw a grayscale change curve, and several grayscale change curves are obtained. It should be noted that each pixel in the tube slice image corresponds to a grayscale change curve.

[0042] In an embodiment of the present invention, taking any grayscale change curve as an example, Fourier transform is performed on the grayscale change curve, the inverse of the frequency with the largest amplitude in the frequency domain is taken as the period, and the grayscale change curve is divided according to the period to obtain each band of the grayscale change curve.

[0043] The serial number in the band of the grayscale change curve where the i-th pixel in the pipe image is located is recorded as the target serial number, and the number of bands whose grayscale values ​​corresponding to the target serial number in other bands other than the band on the grayscale change curve where the i-th pixel is located are consistent with the grayscale value of the i-th pixel is recorded as the number of bands whose grayscale values ​​at the corresponding positions of the i-th pixel and other bands of the grayscale change curve are consistent.

[0044] The DTW algorithm is used to obtain the DTW distance between the band of the grayscale change curve where the i-th pixel point in the pipe image is located and the j-th band excluding this band.

[0045] Get the fluctuation difference of each pixel in the pipe segment image:

[0046] ;

[0047] In the formula, Represents the fluctuation difference of the i-th pixel in the segment image; Represents the number of bands where the grayscale value of the i-th pixel and the corresponding position of the grayscale change curve of other bands are consistent; Represents the DTW distance between the band of the grayscale change curve where the i-th pixel point in the pipe image is located and the j-th band except this band; Represents the number of bands of the grayscale change curve where the i-th pixel in the pipe segment image is located; Represents the gray value of the i-th pixel; Represents the grayscale value corresponding to the target number in the jth band outside the band on the grayscale change curve where the i-th pixel is located; || represents the absolute value symbol; The approximate relationship between the band of the grayscale change curve where the i-th pixel is located and all bands except this band is larger, indicating that the similarity is greater. The greater the difference between the grayscale value of the i-th pixel in the tube image and the grayscale value of the corresponding position of other bands of the grayscale change curve where it is located, the greater the fluctuation difference of the i-th pixel is, and the more abnormal the i-th pixel is. The larger the value of is, the larger the number of bands whose grayscale values ​​of the i-th pixel are consistent with the grayscale values ​​of the corresponding positions of other bands of its grayscale change curve is, which means that the fluctuation difference of the i-th pixel is smaller and the i-th pixel is less abnormal.

[0048] S003. Obtain the degree of abnormality of each pixel in the tube slice image according to the difference in fluctuation difference between each pixel in the tube slice image and other pixel points in its column; obtain the degree of deformation of each pixel in the tube slice image according to the difference in abnormality between the surrounding pixel points of each pixel in the tube slice image.

[0049] It should be noted that when the pipe segment has not been deformed, the fluctuation difference of a single column of pixels in the pipe segment image is approximately the same. When the pipe segment has been deformed, the fluctuation difference of a single column of pixels in the pipe segment image is different. Therefore, when the fluctuation difference of each pixel in the pipe segment image is larger than that of all the pixels in its column, it means that the degree of abnormality of the pixel is greater.

[0050] In the embodiment of the present invention, the abnormality degree of each pixel in the pipe segment image is obtained:

[0051] ;

[0052] In the formula, Represents the abnormality degree of the i-th pixel in the pipe segment image; Represents the fluctuation difference of the i-th pixel in the segment image; Represents the number of pixels in the column where the i-th pixel is located in the tube image except the i-th pixel. The fluctuation difference of each pixel; represents the number of pixels other than the i-th pixel in the column where the i-th pixel is located in the tube image; || represents the absolute value symbol, The larger the value is, the more abnormal the i-th pixel in the tube image is.

[0053] It should be noted that when the segment is not deformed, the grayscale changes of each row of pixels in the segment image are periodic. When the segment is deformed, since the segment material is tough and thin, the pixels in the deformed area in the segment image will not exist alone, but will be linked with the pixels in the nearby area to form a deformation area. Therefore, the deformation degree of each pixel in the segment image is obtained based on the difference in the degree of abnormality between the surrounding pixels of each pixel in the segment image.

[0054] In an embodiment of the present invention, the row where the i-th pixel is located and the row before and after the row are all used as reference rows for the i-th pixel; the position of the i-th pixel in the row is recorded as the target position of the row where the i-th pixel is located, and based on the target position of the row where the i-th pixel is located, the target position of each reference row of the i-th pixel is obtained. It should be noted that the target position of each reference row of the i-th pixel is on the same column as the target position of the row where the i-th pixel is located.

[0055] Get the deformation degree of each pixel in the tube segment image:

[0056] ;

[0057] In the formula, Represents the deformation degree of the i-th pixel in the pipe segment image; Represents the abnormality degree of the i-th pixel in the pipe segment image; Represents the number of all reference rows for the i-th pixel in the tube segment image; Represents the abnormality degree of the left adjacent pixel of the target position in the kth reference row of the i-th pixel; Represents the abnormality degree of the right adjacent pixel of the target position in the kth reference row of the i-th pixel;

[0058] S004. Adjust the gray value of each pixel according to the deformation degree of each pixel to obtain an enhanced pipe segment image, and segment the enhanced pipe segment image to identify the deformation area.

[0059] It should be noted that after obtaining the deformation degree of each pixel, the grayscale value of each pixel needs to be adjusted according to the deformation degree of each pixel to enhance the contrast between the deformed area and the normal area in the pipe segment image, so as to facilitate the subsequent use of threshold segmentation to obtain the deformed area.

[0060] In an embodiment of the present invention, the product of the deformation degree and the grayscale value of each pixel point in the pipe segment area is used as the updated grayscale value of each pixel point to obtain an enhanced pipe segment image. The enhanced pipe segment image is segmented using the Otsu threshold segmentation method to obtain the deformation area, and relevant personnel are notified to handle it to prevent blockage of the air preheater in subsequent use.

[0061] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring blockage of an air preheater, characterized in that: include: Collect segment images; According to the gray value of each row of pixels in the pipe slice image, each gray change curve is obtained; the period of each gray change curve is obtained to segment each gray change curve to obtain each band of each gray change curve; the fluctuation difference of each pixel in the pipe slice image is obtained ; Represents the fluctuation difference of the i-th pixel in the segment image; Represents the number of bands where the grayscale value of the i-th pixel and the corresponding position of the grayscale change curve of other bands are consistent; Represents the DTW distance between the band of the grayscale change curve where the i-th pixel is located and the j-th band except this band; Represents the number of bands of the grayscale change curve where the i-th pixel is located; Represents the gray value of the i-th pixel; Represents the grayscale value corresponding to the target serial number in the jth band outside the band on the grayscale change curve where the i-th pixel is located; || represents the absolute value symbol; obtain the abnormality degree of each pixel point, and the abnormality degree is the sum of the differences between the fluctuation difference amount of each pixel point and the fluctuation difference amount of other pixels in its column; Obtaining the deformation degree of each pixel point, wherein the deformation degree is positively correlated with the abnormality degree of each pixel point; The gray value of each pixel is adjusted according to the deformation degree of each pixel to obtain an enhanced segment image; Perform threshold segmentation on the enhanced segment image to identify the deformation area.

2. The method for monitoring blockage of an air preheater according to claim 1, characterized in that: The obtaining of each grayscale change curve comprises: A two-dimensional coordinate system is constructed with the grayscale value of the pixel as the vertical axis and the pixel serial number as the horizontal axis. Taking any row of pixels in the tube image as an example, the row of pixels is input into the two-dimensional coordinate system in order from left to right to draw a grayscale change curve, and several grayscale change curves are obtained.

3. The method for monitoring blockage of an air preheater according to claim 1, characterized in that: The step of obtaining the period of each grayscale change curve and segmenting each grayscale change curve to obtain each band of each grayscale change curve includes: Taking any grayscale change curve as an example, Fourier transform is performed on the grayscale change curve, the inverse of the frequency with the largest amplitude in the frequency domain is taken as the period, and the grayscale change curve is divided according to the period to obtain various bands of the grayscale change curve.

4. The method for monitoring blockage of an air preheater according to claim 1, characterized in that: The number of fluctuations of the grayscale value of the pixel point and the corresponding position of the grayscale change curve in other bands thereof is consistent, including: The serial number in the band of the grayscale change curve where the i-th pixel in the pipe image is located is recorded as the target serial number, and the number of bands whose grayscale values ​​corresponding to the target serial number in other bands other than the band on the grayscale change curve where the i-th pixel is located are consistent with the grayscale value of the i-th pixel is recorded as the number of bands whose grayscale values ​​at the corresponding positions of the i-th pixel and other bands of the grayscale change curve are consistent.

5. The method for monitoring blockage of an air preheater according to claim 3, characterized in that: The obtaining of the abnormality degree of each pixel point includes: ; In the formula, Represents the abnormality degree of the i-th pixel in the pipe segment image; Represents the fluctuation difference of the i-th pixel in the segment image; Represents the number of pixels in the column where the i-th pixel is located in the tube image except the i-th pixel. The fluctuation difference of each pixel; Represents the number of pixels in the column where the i-th pixel in the tube image is located, except for the i-th pixel; || represents the absolute value symbol.

6. The method for monitoring blockage of an air preheater according to claim 1, characterized in that: The step of obtaining the deformation degree of each pixel point includes: Get the target position of each reference row of the i-th pixel; ; In the formula, Represents the deformation degree of the i-th pixel in the pipe segment image; Represents the abnormality degree of the i-th pixel in the pipe segment image; Represents the number of all reference rows for the i-th pixel in the tube segment image; Represents the abnormality degree of the left adjacent pixel of the target position in the kth reference row of the i-th pixel; Represents the abnormality degree of the right adjacent pixel of the target position in the kth reference row of the i-th pixel.

7. The method for monitoring blockage of an air preheater according to claim 6, characterized in that: The step of obtaining the target position of each reference row of the i-th pixel point includes: The row where the i-th pixel is located, as well as the row before and after the row, are all used as reference rows for the i-th pixel; the position of the i-th pixel in the row is recorded as the target position of the row where the i-th pixel is located, and based on the target position of the row where the i-th pixel is located, the target position of each reference row of the i-th pixel is obtained.

8. The method for monitoring blockage of an air preheater according to claim 1, characterized in that: The step of acquiring the enhanced segment image comprises: The product of the deformation degree and the gray value of each pixel in the pipe segment area is used as the updated gray value of each pixel to obtain the enhanced pipe segment image.

Citation Information

Patent Citations

  • Otsu thresholding method with mask

    CN113870182A

  • Tunnel surrounding rock deformation monitoring method

    CN117190900A

  • Traffic engineering road condition visual detection method and system

    CN118015002A