CN114018982B - Visual monitoring method for dust deposit of air preheater - Google Patents

Abstract

This application provides a visual monitoring method for dust accumulation in an air preheater, which includes: Step S1: Install two infrared detection imaging devices at both the cold and hot ends of the primary air side of the air preheater; Step S2: Operate the air preheater The state image is preprocessed by median filtering; Step S3: Segment the abnormal area of the preprocessed empty preheater operating state image to obtain the characteristic abnormal area; Step S4: Establish the two-dimensional coordinate system XOZ plane; Step S5: According to The proportional relationship between the fixed position reference window of the infrared detection imaging device and the fan-shaped area is equally divided into multiple concentric arcs on the air preheater operating status image, and the characteristic anomaly is determined based on the proportional relationship between the infrared image and the actual operation of the air preheater. The coordinates of the area. By analyzing the acquired infrared image through median filter preprocessing and improved region growing algorithm, the real-time dust accumulation situation of the air preheater can be obtained by analyzing the acquired infrared image, which improves the accuracy of dust accumulation monitoring of the air preheater. .

Description

A visual monitoring method for dust accumulation in air preheaters

Technical field

The invention relates to the technical field of air preheater monitoring, and in particular to a visual monitoring method for dust accumulation in the air preheater.

Background technique

The air preheater is a heat exchange device that uses boiler exhaust heat to heat the air. It can effectively reduce the boiler exhaust temperature and improve boiler efficiency. At present, rotary air preheaters are widely used in power stations. This type of air preheater is prone to dust accumulation. Especially in recent years, with the completion of the transformation of denitrification systems in various plants, the ammonia hydrogen sulfate produced during the denitrification process has further aggravated this problem. Threaten the safe and economical operation of the unit. At present, there is a lack of direct monitoring methods for the dust accumulation status of the air preheater. The pressure difference between the inlet and outlet of the air preheater is often reflected laterally. However, the pressure difference is greatly affected by the flue gas flow. When the unit is operating under variable operating conditions, the pressure difference will be very large. Fluctuation, unable to show changes in the dust accumulation level of the air preheater.

Since once dust accumulation occurs in the air preheater, the local temperature will be abnormal. At this time, it is particularly important to monitor the overall temperature distribution of the air preheater in real time through an infrared thermal imaging camera.

Contents of the invention

In view of this, the main purpose of the present invention is to solve the problem of being unable to accurately determine changes in the degree of ash accumulation in the air preheater due to large fluctuations in pressure difference when the unit is operating under varying operating conditions.

The present invention provides a visual monitoring method for dust accumulation in an air preheater, which includes: Step S1: Install two infrared detection imaging devices at both the cold and hot ends of the primary air side of the air preheater, wherein the observation area of the infrared detection imaging device is empty The area of the fan-shaped area on the primary wind side of the preheater; Step S2: In response to the real-time acquisition of the air preheater operating status image captured by the infrared detection imaging device, perform median filtering preprocessing on the air preheater operating status image to obtain the preprocessing The preprocessed air preheater operating status image; Step S3: Determine the abnormal area of the preprocessed air preheater operating status image based on the improved region growing algorithm, and segment the abnormal area of the preprocessed air preheater operating status image, So that the characteristic abnormal area is obtained, wherein the characteristic abnormal area is the dust accumulation area of the air preheater with local temperature abnormality; Step S4: Establish a two-dimensional coordinate system XOZ plane, where the X-axis is the centerline direction of the primary fan-shaped area , the Z axis is the direction of the central rotation axis of the air preheater, the origin is the midpoint of the central rotation axis of the air preheater, and the reference point is the installation position of the infrared detection imaging device; Step S5: Reference window and sector based on the fixed position of the infrared detection imaging device The proportional relationship between areas is divided into multiple concentric arcs on the air preheater operating status image, and the coordinates of the characteristic abnormal areas are determined based on the proportional relationship between the infrared image and the actual operation of the air preheater.

In some embodiments of the present invention, determining the abnormal area of the preprocessed empty preheater operating state image based on the improved region growing algorithm includes: traversing the preprocessed empty preheater operating state according to an N×N sliding matrix All areas of the image, and calculate the mean of all pixels in the sliding matrix, and select the center point of the area with the largest mean as the seed point. The expression for calculating the mean of all pixels in the sliding matrix is: , in the formula,/> Think/> is the mean of the matrix of middle pixels,/> is the pixel in the matrix, is the size of the sliding matrix,/> is the coordinate of the intermediate pixel point in the pixel coordinate system; start regional growth based on the determined seed point, and determine whether the absolute value of the difference between the pixel value of a certain pixel in the growing area and the pixel value T of the grown area is less than The first preset threshold K; If the absolute value of the difference between the pixel value of a certain pixel in the growth area and the pixel value T of the grown area is less than the preset threshold K, then continue to grow, otherwise stop growing; at the pixel When growing to the edge of the image, determine whether the pixel gradient amplitude of a certain pixel at the edge of the image is greater than the second preset threshold; if the pixel gradient amplitude of the pixel at the edge of the image is greater than the second preset threshold, Then the pixels at the edge of an image are edge points.

In some embodiments of the present invention, in step S1, the infrared detection imaging device includes an intermediate sleeve, one end of the intermediate sleeve passes through a fixed sleeve and is detachably connected to the end of the fixed sleeve, The other end of the intermediate sleeve is detachably installed with an angle bracket through bolts, wherein a first cavity is provided inside the angle bracket, and the first cavity is connected with the inside of the fixed sleeve; removable The sensor is installed on the angle bracket. The outer wall of the sensor is covered with a cooling jacket. The cooling jacket is clamped on the angle bracket, and a second cavity is provided inside the cooling jacket. , the end of the cooling jacket away from the angle bracket is provided with an opening slot, the opening slot is connected to the first cavity through the second cavity; and a cooling jacket is fixedly installed on the cooling jacket. An infrared lens is located between the opening groove and the sensor, so that the air flow in the opening groove can purge the infrared lens.

In some embodiments of the present invention, in step S1, the infrared detection imaging device further includes a protective hood set on the cooling jacket, and the protective hood is detachably connected to the intermediate sleeve. .

In some embodiments of the present invention, in step S1, the infrared detection imaging device further includes a sensor lead connected to the sensor, and one end of the sensor lead away from the sensor passes through the Wire sleeve.

The invention provides a visual monitoring method for dust accumulation in an air preheater. Four infrared detection imaging devices are respectively installed at the hot and cold ends of the primary air side of the air preheater, two at each end. The purpose is to monitor The entire fan-shaped area on the primary air side at both hot and cold ends of the air preheater. The image data monitored in real time by the infrared thermal imaging camera is transmitted to the computer through the RJ45 twisted pair, and the obtained infrared image is analyzed using median filter preprocessing and improved region growing algorithm on the computer, and the obtained infrared image is analyzed, that is The real-time dust accumulation status of the air preheater can be obtained, which effectively improves the accuracy of dust accumulation monitoring of the air preheater and provides guarantee for the stable operation of the air preheater.

Description of the drawings

Figure 1 is a flow chart of a visual monitoring method for dust accumulation in an air preheater according to an embodiment of the present invention;

Figure 2 is a schematic layout diagram of an infrared thermal imager of a visual monitoring method for dust accumulation in an air preheater according to an embodiment of the present invention;

Figure 3 is a growth criterion flow chart of a visual monitoring method for dust accumulation in an air preheater according to an embodiment of the present invention;

Figure 4 is a schematic diagram of positioning the dust accumulation area of a visual monitoring method for dust accumulation in an air preheater according to an embodiment of the present invention.

Figure 5 is an overall schematic diagram of an infrared detection imaging device according to an embodiment of the present invention;

Figure 6 is a partial schematic diagram of an infrared detection imaging device according to an embodiment of the present invention;

Figure 7 is a partial cross-sectional view of an infrared detection imaging device according to an embodiment of the present invention;

Among them, the above-mentioned drawings include the following reference signs:

1. Angle bracket; 101. First cavity; 2. Protective hood; 3. Sensor; 4. Fixed sleeve; 5. Wire sleeve; 6. Sensor lead; 7. Intermediate sleeve; 8. Cooling jacket ; 801. Second cavity; 802. Open slot; 9. Infrared lens.

Detailed ways

The present application will be further described in detail below in conjunction with the accompanying drawings and examples. It can be understood that the specific embodiments described here are only used to explain the relevant invention, but not to limit the invention. It should also be noted that, for convenience of description, only the parts related to the invention are shown in the drawings. It should be noted that, as long as there is no conflict, the embodiments and features in the embodiments of this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

Please refer to Figure 1, which shows a flow chart of a visual monitoring method for dust accumulation in an air preheater according to the present application.

As shown in Figure 1, in step S1, two infrared detection and imaging devices are installed at both the cold and hot ends of the primary air side of the air preheater. The observation area of the infrared detection and imaging device is the fan-shaped area on the primary air side of the air preheater. area;

In step S2: In response to real-time acquisition of the air preheater operating status image captured by the infrared detection imaging device, perform median filtering preprocessing on the air preheater operating status image to obtain a preprocessed air preheater operating status image. ;

In step S3: Determine the abnormal area of the preprocessed air preheater operating state image based on the improved region growing algorithm, and segment the abnormal area of the preprocessed air preheater operating state image to obtain the characteristic abnormal area, where , the characteristic abnormal area is the dust accumulation area of the air preheater with local temperature abnormality;

In step S4: Establish the two-dimensional coordinate system XOZ plane, in which the X-axis is the centerline direction of the primary fan-shaped area, the Z-axis is the direction of the central axis of the air preheater, and the origin is the midpoint of the central axis of the air preheater. , the reference point is the installation position of the infrared detection imaging device;

In step S5: According to the proportional relationship between the fixed position reference window and the sector area of the infrared detection imaging device, multiple concentric arcs are equally divided on the air preheater operating status image, and based on the infrared image and the actual operation of the air preheater The proportional relationship determines the coordinates of the characteristic abnormal area.

In the method of this embodiment, after automatically selecting the seed point, the acquired operating status image of the air preheater is segmented to obtain the characteristic abnormal area, and the real-time dust accumulation situation of the air preheater can be obtained, which effectively improves the efficiency of the air preheater. The accuracy of dust accumulation monitoring in the preheater provides guarantee for the stable operation of the air preheater, and the radial distance and axial distance between the dust accumulation part and the midpoint of the air preheater are taken into account, thereby simplifying the three-dimensional coordinates into two-dimensional coordinates, and The coordinates of the dust accumulation area are determined using the proportional relationship between the infrared image and the actual operation of the air preheater.

In a specific embodiment, this application provides a visual monitoring method for dust accumulation in an air preheater, including the following steps:

Step 1: Install two infrared detection imaging devices at both the cold and hot ends of the primary air side of the air preheater. The installation position can be determined according to the field of view, focal length and object distance of the thermal imager. The area of the fan-shaped area on the primary wind side of the air preheater is the area that the infrared thermal imaging camera needs to observe, that is, the installation location must ensure that the observation area meets the requirements (as shown in Figure 2).

Step 2: The infrared detection imaging device captures the operating status of the air preheater in real time, transmits the captured infrared image to the computer through the RJ45 twisted pair, and uses the image processing algorithm to process the input infrared image on the computer, as follows:

Step 2.1: Perform median filtering preprocessing on the input infrared image, statistically sort the rectangular windows, and replace the pixel value of the center point of the window with the median gray value of the neighborhood pixels in the window, that is:

In the formula, is the median filter function,/> is the median filter function,/> is the pixel value at the (s,t) position,/> The center point is at (x, y);

Pair size is Rectangular graphics window/> Sort the pixels in and replace the center point with the grayscale value of the median pixel/> pixel value.

Step 2.2: Use the region-based image segmentation algorithm to segment the areas with abnormal characteristics in the infrared image, which are the areas that reflect dust accumulation in the air preheater. Because the temperature distribution of the normal operation of the air preheater is continuous, once dust accumulation occurs, The local temperature will be abnormal, and the area can be segmented using the characteristics of the temperature abnormality.

Step 2.3: When executing the algorithm, first select a pixel point in the area to be grown as a seed point for growth, then grow the area around the seed point according to the predefined growth standards, and combine some features of adjacent pixels with the seed point. Compare the pixels, and if the growth conditions are met, merge them into the area where the seed pixels are located, and use the new pixels as seed points to continue growing. Repeat the above process until no new pixels meet the conditions and stop growing. A growth area is formed (as shown in Figure 3).

When there are multiple abnormal areas, we only need to add a pixel in the area to be grown as a growth seed point. use a The sliding matrix is used to traverse all areas of interest, calculate the mean of all pixels in the sliding matrix, and select the center point of the area with the largest mean as the seed point to realize automatic selection of seed points. The calculation of the regional pixel mean is:

,

In the formula, Think/> is the mean of the matrix of middle pixels,/> is the pixel in the matrix,/> is the size of the sliding matrix,/> is the coordinate of the middle pixel point in the pixel coordinate system;

After the seed point is determined, regional growth begins and regional growth conditions are determined. Suppose the image area of interest is R and the number of pixels is n, then the calculation formula of gray mean m is:

;

The pixels to be determined in the area of interest are Compared with the pixel mean T of the grown area, if the absolute value of the pixel difference is less than the threshold K, the growth condition is met,/> Continue growing as a new seed point, otherwise, stop growing:

When the seed point grows to the edge, the gray value of the edge changes greatly. If it continues to grow according to the growth conditions, it will lead to over-segmentation or wrong segmentation. In order to avoid this situation, this application uses a gradient-based edge detection operator to detect edges. Because the edge gray value changes greatly, the gradient amplitude of the pixel at the edge is larger. If the gradient amplitude is greater than the preset threshold, the point is determined to be an edge point. Among them, the gradient of the pixels in the image is:

;

In the formula, is the pixel point in the infrared image,/> is the directional derivative of the pixel in the x direction,/> is the directional derivative of the pixel point in the y direction,/> ,/> are the unit vectors in the x and y directions respectively.

The magnitude of the gradient is defined as ,Right now:

Then the edge point determination condition is:

In the formula, is the gradient amplitude of the current seed point,/> is the gradient amplitude of the previous seed point,/> is the threshold.

After determining the target area based on the image segmentation algorithm, the dust accumulation area positioning algorithm is then used to determine the exact location of the target area (as shown in Figure 4).

Step 3: The abnormal area segmented from the infrared image can use the midpoint of the central axis of the air preheater as the origin to establish a radial and axial two-dimensional coordinate system XOZ plane, the radial direction is the X-axis direction, and the axial direction is the Z-axis direction, and the center line of the fan-shaped area of the primary air silo is set as the X-axis.

Step 4: Divide multiple concentric arcs equally on the infrared image based on the proportional relationship between the fixed position reference window of the infrared thermal imaging camera and the fan-shaped area. The segmentation of concentric arcs and the determination of the X and Z axes allow the dust accumulation area to only measure the coordinates of the XZ direction of the central axis of rotation, and use the characteristics of the air preheater's own rotation to convert the three-dimensional space coordinates into two-dimensional Plane coordinates.

Step 5: Then use the proportional relationship between the infrared image and the actual operation of the air preheater to determine the coordinates of the dust accumulation area.

Please refer to Figures 5-7, which show the infrared detection imaging device provided by the present application, including: an intermediate sleeve 7, one end of the intermediate sleeve 7 passes through the fixed sleeve 4, and the end of the fixed sleeve 4 is detachable. connection, the other end of the intermediate sleeve 7 is detachably installed with an angle bracket 1 through bolts, wherein a first cavity 101 is provided inside the angle bracket 1, and the first cavity 101 is connected with the inside of the fixed sleeve 4; removable The sensor 3 is installed on the angle bracket 1. The outer wall of the sensor 3 is covered with a cooling jacket 8. The cooling jacket 8 is clamped on the angle bracket 1, and a second cavity 801 is provided inside the cooling jacket 8. The end of the jacket 8 away from the angle bracket 1 is provided with an opening slot 802. The opening slot 802 is connected to the first cavity 101 through the second cavity 801; the infrared lens 9 is fixedly installed on the cooling jacket 8. 9 is located between the opening slot 802 and the sensor 3 so that the air flow in the opening slot 802 can blow the infrared lens 9 .

Applying the technical solution of this embodiment, the sensor 3 is fixedly installed on the angle bracket 1, so that the vertical angle between the sensor 3 and the air preheater wall can be reduced, which facilitates installation, and the sensor 3 installed in the fixed sleeve 4 is rotated. The intermediate sleeve 7 can adjust the visual range of the sensor 3. Moreover, a cooling jacket 8 is set on the outside of the sensor 3. The second cavity 801 in the cooling jacket 8 is connected with the first cavity 101 in the angle bracket 1, so that the air flow can flow through the second cavity 801. To achieve the purpose of cooling the sensor 3.

Among them, by fixing the infrared lens 9 installed on the cooling jacket 8, the sensor 3 can directly measure the external temperature through the infrared lens 9 and be completely isolated from the external air, and the infrared lens 9 is located between the opening groove 802 and the sensor 3. The opening slot 802 extends from the cooling jacket 8. The cooling airflow flows out from the opening slot 802 and finally flows to the outside. The airflow in the opening slot 802 will continuously blow the infrared lens 9 to avoid dust accumulation and achieve self-cleaning.

In some optional embodiments, the device further includes a protective head cover 2 set on the cooling jacket 8 , and the protective head cover 2 is detachably connected to the intermediate sleeve 7 . By providing a protective hood 2, the heat flow can be prevented from directly impacting the sensor 3 and reducing the heat transfer speed.

In some optional embodiments, the device further includes a sensor lead 6 connected to the sensor 3 , and one end of the sensor lead 6 away from the sensor 3 passes through the wire sleeve 5 provided in the intermediate sleeve 7 .

What is described above are only some embodiments of the present invention. For those of ordinary skill in the art, several modifications and improvements can be made without departing from the creative concept of the present invention, and these all belong to the protection scope of the present invention.

Claims (5)

1. A visual monitoring method for dust accumulation in air preheaters, which is characterized by including: Step S1: Install two infrared detection imaging devices at both the cold and hot ends of the primary air side of the air preheater, where the observation area of the infrared detection imaging device is the fan-shaped area of the primary air side of the air preheater; Step S2: In response to real-time acquisition of the air preheater operating status image captured by the infrared detection imaging device, perform median filtering preprocessing on the air preheater operating status image to obtain a preprocessed air preheater operating status image; Step S3: Determine the abnormal area of the preprocessed air preheater operating state image based on the improved region growing algorithm, and segment the abnormal area of the preprocessed air preheater operating state image to obtain the characteristic abnormal area, where The characteristic abnormal area mentioned above is the dust accumulation area of the air preheater with local temperature abnormality; Step S4: Establish the two-dimensional coordinate system XOZ plane, in which the The point is the installation position of the infrared detection imaging device; Step S5: According to the proportional relationship between the fixed position reference window of the infrared detection imaging device and the sector area, divide multiple concentric arcs equally on the air preheater operating status image, and based on the ratio of the infrared image to the actual operation of the air preheater The relationship determines the coordinates of the characteristic anomaly area. 2. A method for visual monitoring of air preheater ash accumulation according to claim 1, characterized in that the abnormal area of the preprocessed air preheater operating status image determined based on the improved region growing algorithm includes: According to an N×N sliding matrix, all areas of the preprocessed empty preheater operating state image are traversed, and the mean value of all pixels in the sliding matrix is calculated, and the center point of the area with the largest mean value is selected as the seed point, where, the sliding matrix is calculated The expression of the mean value of all pixels within is: , In the formula, Think/> is the mean of the matrix of middle pixels,/> is the pixel in the matrix,/> is the size of the sliding matrix,/> is the coordinate of the middle pixel point in the pixel coordinate system; Start region growth based on the determined seed point, and determine whether the absolute value of the difference between the pixel value of a certain pixel in the growth region and the pixel value T of the grown region is less than the first preset threshold K; If the absolute value of the difference between the pixel value of a certain pixel in the growing area and the pixel value T of the already grown area is less than the preset threshold K, then continue growing, otherwise stop growing; When the pixel points grow to the edge of the image, determine whether the pixel gradient amplitude of a certain pixel point at the edge of the image is greater than a second preset threshold; If the pixel gradient amplitude of the pixel at the edge of the image is greater than the second preset threshold, the pixel at the edge of a certain image is an edge point. 3. A visual monitoring method for dust accumulation in air preheaters according to claim 1, characterized in that, in step S1, the infrared detection imaging device includes an intermediate casing (7), and the intermediate casing (7) ) passes through the fixed sleeve (4) and is detachably connected to the end of the fixed sleeve (4), and the other end of the intermediate sleeve (7) is detachably installed with an angle bracket (1) through bolts, Wherein, a first cavity (101) is provided inside the angle bracket (1), and the first cavity (101) is connected with the inside of the fixed sleeve (4); The sensor (3) is removably installed on the angle bracket (1). The outer wall of the sensor (3) is provided with a cooling jacket (8). The cooling jacket (8) is clamped at the angle. A second cavity (801) is provided on the bracket (1) and inside the cooling jacket (8). An open slot is provided at the end of the cooling jacket (8) away from the angle bracket (1). (802), the opening groove (802) communicates with the first cavity (101) through the second cavity (801); and An infrared lens (9) is fixedly installed on the cooling jacket (8). The infrared lens (9) is located between the opening groove (802) and the sensor (3), so that the opening groove (802) The airflow in 802) can purge the infrared lens (9). 4. A visual monitoring method for dust accumulation in an air preheater according to claim 3, characterized in that in step S1, the infrared detection and imaging device further includes a Protective hood (2), the protective hood (2) is detachably connected to the intermediate sleeve (7). 5. A visual monitoring method for dust accumulation in an air preheater according to claim 3, characterized in that in step S1, the infrared detection imaging device further includes a sensor lead (6) connected to the sensor (3) ), one end of the sensor lead (6) away from the sensor (3) passes through the wire sleeve (5) provided in the intermediate sleeve (7).