Waste gas leakage detection method for bag-type dust collector

Abstract

The invention relates to the technical field of image processing, in particular to an exhaust gas leakage detection method for a bag-type dust collector, which comprises the following steps: continuously acquiring multiple frames of images of a pattern plate plane, calculating local information entropy of each bag area in each frame of image, and calculating the local information entropy of each bag area in each frame of image; determining a local information entropy sequence of each cloth bag region according to a plurality of reference images of the current frame image, and obtaining entropy change stability through a first-order difference sequence of the local information entropy sequence; calculating the vector convergence degree of each cloth bag by using the gradient of the local information entropy of each cloth bag region in the reference image and combining the space vectors of each cloth bag region and the adjacent cloth bag region; the leakage possibility degree of each cloth bag area is obtained by integrating the local information entropy, the entropy change stability and the vector convergence degree of each cloth bag area, the cloth bag with leakage is determined according to the leakage possibility degree, and the accuracy of waste gas leakage detection of the bag-type dust collector is improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an exhaust gas leakage detection method for a bag filter. Background Art

[0002] In the field of industrial waste gas purification, bag dust collectors play a vital role in reducing dust emissions, protecting the ecological environment, and ensuring human health due to their excellent performance in efficiently capturing solid particles.

[0003] Implementing exhaust gas leakage detection on bag dust collector is a key link to ensure its stable and efficient operation. Once exhaust gas leaks, a large amount of dust will escape, which will not only significantly reduce the dust removal efficiency of the dust collector, but also increase the risk of environmental pollution.

[0004] At present, using image processing technology to locate the bag where exhaust gas leaks in bag filters has become an important detection method used in the industry. The existing detection scheme mainly analyzes the changes in the local information entropy of the bag area in multiple consecutive frames of images, and determines the bag area where exhaust gas leaks exist based on the size of the difference in local information entropy.

[0005] However, in actual working conditions, when the exhaust gas leaks and escapes too quickly, the exhaust gas diffuses rapidly in a short period of time, causing significant changes in the image features within large areas of the bag filter. This makes it difficult for the detection algorithm based on local information entropy changes to accurately distinguish which changes are due to the real leakage source and which changes are "pseudo-leakages" caused by exhaust gas diffusion. Large areas of the bag filter will be misjudged as leakage areas, reducing the accuracy of exhaust gas leakage detection and affecting the dust removal effect of the bag filter. Summary of the invention

[0006] In order to solve the problem that the existing exhaust gas leakage detection method of the bag dust collector is prone to misjudgment, which reduces the accuracy of the exhaust gas leakage detection. The present invention proposes an exhaust gas leakage detection method for the bag dust collector, comprising: Continuously collect multiple frames of images of the flower plate plane of the bag filter, wherein the flower plate plane includes multiple bag areas, and calculate the local information entropy of each bag area in each frame image; take any frame image as the current frame image, and determine the local information entropy sequence of each bag area of ​​the current frame image according to multiple reference images of the current frame image; The entropy change stability of each bag region is determined according to the first-order difference sequence of the local information entropy sequence of each bag region; the degree of vector convergence is calculated according to the gradient of the local information entropy of each bag region in each reference image and the spatial vector of each bag region and the adjacent bag region: , For the The degree of vector convergence in the bag area, For the The first The adjacent bag area is in the The gradient of the local information entropy of the reference image, For the The bag area and The space vector of adjacent bag regions, For the The total number of adjacent bag areas of a bag area, is the total number of reference images, To find the model length, To find the absolute value, is the natural exponential function, is the normalization function; The product of the local information entropy, entropy change stability and vector convergence degree of each bag area is taken as the possible leakage degree of each bag area, and exhaust gas leakage detection is performed according to the possible leakage degree.

[0007] The above technical solution establishes the time series data of the bag area state by calculating the local information entropy of multiple frames of images, which can be used to analyze the dynamic changes of the state of the bag area over time. Compared with a single frame image, it can more comprehensively understand the changes in each bag area. After selecting the current frame image, the local information entropy sequence of each bag area is determined in combination with multiple reference images. By analyzing the sequence changes, the change trend of the local information entropy of the bag area can be obtained. By analyzing the change trend, the abnormal entropy value fluctuation caused by exhaust gas leakage can be more accurately identified, and the pseudo-leakage characteristics caused by exhaust gas diffusion can be misjudged as real leakage. And further, the change rate of the local information entropy sequence is reflected by the first-order difference sequence, and the stability of the entropy change can accurately measure whether the change of the local information entropy of the bag area is stable. The gradient of the local information entropy reflects the change direction and degree of the local information entropy of the bag area, and the spatial vector reflects the spatial position relationship between the bag areas. The degree of vector convergence can be calculated by combining the two, and the mutual relationship between the bag areas can be comprehensively considered from the spatial correlation dimension and the time correlation dimension, which can accurately reflect whether the exhaust gas flow and information change between adjacent bag areas are regular, and thus more accurately locate the leakage source. Furthermore, the combination of the above three key indicators can comprehensively and comprehensively evaluate the possibility of exhaust gas leakage in the bag area, avoid the misjudgment problem caused by exhaust gas diffusion, and improve the accuracy of exhaust gas leakage detection.

[0008] Furthermore, the entropy change stability of each bag area is determined based on the following formula: ; In the formula, For the The entropy change stability of the bag region, For the The first-order difference sequence of the local information entropy of the bag region values, For the The number corresponding to the first time the value of the first-order difference sequence of the local information entropy of the bag region is greater than 0 except for the starting position, is the total number of reference images, is the total number of bag areas, is the linear normalization function, is the multiplication symbol, is the absolute value symbol.

[0009] The above technical scheme can capture the starting point of the change in the local information entropy of the bag area and the subsequent change trend by processing the first-order difference sequence of the local information entropy, and then calculate the entropy change stability of each bag area, which can accurately quantify the change trend of the local information entropy of each bag area in multiple consecutive frames of images.

[0010] Furthermore, the gradient of the local information entropy of each bag region in each reference image is determined based on the following method: Obtain the local information entropy of each bag region and its adjacent bag regions in each reference image; In each reference image: The direction of the gradient of the local information entropy of each bag area is: the center of the bag area points to the adjacent bag area with the largest local information entropy; The value of the gradient of the local information entropy of each bag area is: the normalized value of the difference between the information entropy of the bag area and the information entropy of the adjacent bag area with the maximum local information entropy.

[0011] The above technical solution determines the gradient based on the local information entropy of each bag area and its adjacent bag areas, fully considering the mutual correlation between bag areas, and can more comprehensively capture the information transfer and interaction between bag areas, so as to more accurately evaluate the status of a single bag area. The change in information entropy of adjacent bag areas can reflect the diffusion path and scope of influence, which helps to distinguish the real leakage source from the area affected by the diffusion.

[0012] Furthermore, the space vectors of each bag area and the adjacent bag areas are determined based on the following method: For each bag area and any of its adjacent bag areas, the direction of the space vector is: the center of the adjacent bag area points to the center of the bag area; the value of the space vector is: the normalized value of the Euclidean distance between the center of the adjacent bag area and the center of the bag area.

[0013] The above technical solution clearly constructs the spatial position association between bag areas, can intuitively display the relative positions between bag areas, and provide a basis for the subsequent analysis of the interaction between bag areas. When studying the exhaust gas diffusion path, the spatial vector direction can help determine which adjacent areas the exhaust gas may flow from to the target bag area, which helps to understand the flow pattern of the gas in the entire system. And through the numerical value of the spatial vector, the quantification of the spatial distance between bag areas is realized. The spatial distance will affect the diffusion speed and degree of exhaust gas between bags. When judging the scope of exhaust gas leakage, the quantified spatial vector value can be used as an important reference. Adjacent bag areas with a closer distance are more susceptible to the leakage of exhaust gas, and the normalized value can more accurately measure the potential degree of this impact.

[0014] Furthermore, the method for obtaining the local information entropy of each bag area in each frame of image is:

[0015] In the formula, For the The bag area is in The local information entropy in the frame image, For the The first The gray value is The probability of appearing in the bag area is For the The total number of grayscale value types of the frame image.

[0016] The above technical solution quantifies the degree of disorder of the grayscale information in the bag area through the information entropy formula to obtain the local information entropy. Exhaust gas leakage may be a dynamically changing process. By continuously collecting multiple frames of images and calculating the local information entropy of the bag area in each frame, the changing trend of the local information entropy over time can be observed.

[0017] Furthermore, each bag area and adjacent bag areas are determined based on the following method: For each bag area, the distance between the center of the bag area and the centers of other bag areas is calculated, and other bag areas whose distances are less than or equal to a preset distance threshold are taken as adjacent bag areas of the bag area.

[0018] Furthermore, the method for obtaining the multiple bag areas is: using the Hough circle detection method or the row-column segmentation method to divide the flower plate plane of the bag filter into multiple bag areas.

[0019] Furthermore, the method for exhaust gas leakage detection according to the possible degree of leakage is: If the possibility of leakage in a certain bag area is greater than the preset possibility of leakage threshold, the bag corresponding to the bag area is a bag with exhaust gas leakage; if the possibility of leakage in a certain bag area is not greater than the preset possibility of leakage threshold, the bag corresponding to the bag area is a bag with no exhaust gas leakage.

[0020] Furthermore, before calculating the local information entropy of each bag region in each frame of image, the following operations are performed: all the acquired multiple frames of images are converted into grayscale images.

[0021] Furthermore, the multiple reference images of the current frame image are: the current frame image and the total number of reference images before it. Frame image, is the default value.

[0022] The present invention has the following effects: The present invention continuously collects multiple frames of images, calculates the local information entropy of each bag area, and makes a comprehensive judgment based on multiple indicators such as entropy change stability and vector convergence degree. It not only considers the change of local information entropy of each bag area from the time dimension, but also combines the spatial correlation between each bag area and its adjacent bag areas from the spatial dimension. Finally, the possible leakage degree of each bag area is obtained, and the bag with leakage is determined based on the accurate possible leakage degree, which reduces the possibility of misjudgment when the exhaust gas diffuses rapidly, improves the accuracy and reliability of exhaust gas leakage detection, and ensures the dust removal effect of the bag dust collector. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic flow chart of the method of the present invention; Figure 2 It is a schematic structural diagram of the bag dust collector of the present invention; Figure 3 It is a schematic diagram of the flower plate plane of the bag filter of the present invention. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0025] like Figure 1 As shown in, the present invention provides a method for detecting exhaust gas leakage for a bag filter, comprising steps S1 to S6: S1: Collect multiple frames of images of the bag filter, each frame of the image includes multiple bag areas.

[0026] Since the bag filter adopts an external filtration dust removal structure that blows air from bottom to top, the bags all have round bag openings. The specific structure is as follows Figure 2As shown in the figure, the exhaust gas enters the bag filter from the bottom and then escapes upwards, passes through the bag filter, and is then discharged. The top of the bag filter is the flower plate plane. In this step, an industrial camera is installed in the center of the top of the bag filter to ensure that the shooting angle is perpendicular to the flower plate plane of the bag filter and all bag openings on the flower plate plane are fully photographed. The bag openings on the flower plate plane are arranged as shown in the figure. Figure 3 As shown in , in order to accurately obtain and analyze the exhaust gas leakage situation of each bag, it is necessary to accurately divide each bag area on the flower plate plane.

[0027] Therefore, multiple frames of images of the flower plate plane of the bag filter are continuously collected, and each frame of the image is Figure 3 As shown in , it contains multiple bag areas (the area where the bag mouth of each bag is located). In multiple frames of images, the size and size of each bag area are fixed. This is because the inherent structure of the flower plate plane of the bag filter will not change. In order to reduce the computational complexity, each frame of the image is grayed out, and then all the bag areas in each frame of the image are accurately divided.

[0028] In one embodiment, the flower plate plane of the bag filter is divided into a plurality of bag areas using a Hough circle detection method or a row-column segmentation method.

[0029] For the Hough circle detection method, the specific implementation process is as follows: First, use the Hough circle detection algorithm to accurately identify the bag openings of all bags on the flower plate plane of the bag filter. For each circle corresponding to the detected bag opening, extract its center coordinates, which will be used as the center of each bag area to be divided later, and then decide whether to select a square frame or a circular frame to delineate the bag area. If there are high requirements for calculation efficiency and shape regularity, the square frame may have more advantages in subsequent calculations; if more attention is paid to the fit with the actual shape of the bag, choose a circular frame.

[0030] In this step, a circular frame is selected to delineate the bag area. For each center, start from a small initial radius of 1, and gradually increase the radius by a step size of 1 each time to expand. Check whether the expanded circular frame overlaps with other circular frames until the largest non-overlapping radius is found. After obtaining the preliminary circular frame of each bag area based on each center and the largest non-overlapping radius, perform statistical analysis on the size of each circular frame and calculate the average radius of all circular frames. For circular frames whose sizes deviate from the average value, adjust them according to the difference in size and average radius, while ensuring that the adjusted circular frame still does not overlap with other circular frames, and treat each adjusted circular frame as a bag area. According to this method, the flower plate plane of the bag filter in each frame image is divided into multiple bag areas.

[0031] For the row-column partitioning method, the specific implementation process is as follows: An edge detection algorithm is used to perform edge detection on each frame of image, identify the edge of each bag opening in each frame of image, and further enhance the outline of the bag opening through morphological operations (such as dilation and erosion) to facilitate accurate identification of the position of the bag opening and obtain the center coordinates of the closed area surrounded by the edge of each bag opening. These center coordinates represent the position of each bag opening in the image.

[0032] Analyze the center coordinates of all identified pockets. First, sort the center coordinates of all pockets by the horizontal coordinate (horizontal direction), and group pockets with similar horizontal coordinates into the same row. For each row, calculate the Euclidean distance between the center coordinates of adjacent pockets, count these distance values, and take the distance value with the highest frequency as the row spacing of the row. This is because the bags are usually evenly arranged on the flower board, and the row spacing is relatively consistent. Similarly, sort the center coordinates of all pockets by the vertical coordinate (vertical direction), divide into columns, and calculate the column spacing.

[0033] According to the calculated row spacing and column spacing, the center coordinates of the first bag opening in the first row are taken as the starting point, and horizontal lines are fitted through the starting point and subsequent equally spaced points along the horizontal direction with the row spacing as the interval. These horizontal lines cover the horizontal range of the entire image, and the drawing of the row dividing lines is completed. Similarly, the center coordinates of the first bag opening in the first column are taken as the starting point, and vertical lines are fitted along the vertical direction with the column spacing as the interval, covering the vertical range of the entire image, and the drawing of the column dividing lines is completed. Since the drawn horizontal dividing lines and vertical dividing lines intersect with each other to form grid areas, each grid area is a bag area. According to this method, the flower plate plane of the bag dust collector in each frame image is divided into multiple bag areas.

[0034] S2: Obtain the local information entropy sequence of each bag area in the current frame image.

[0035] Under normal circumstances, the grayscale of all bag areas is relatively uniform and stable, and the local information entropy calculated based on the grayscale value of the pixel points in each bag area is stable. When exhaust gas leaks in a bag area, the exhaust gas will cause the local information entropy of the bag area to increase. Therefore, analyzing the changes in the local information entropy of each bag area in continuous frame images is of great significance for exhaust gas leakage detection.

[0036] In one embodiment, the local information entropy of each bag region in each frame of the image is calculated according to the information entropy calculation formula:

[0037] In this formula, For the The bag area is in The local information entropy in the frame image, For the The first The gray value is The probability of appearing in the bag area is For the The total number of grayscale value types of the frame image.

[0038] Take any frame image as the current frame image, after obtaining the local information entropy of each bag area in each frame image, in order to more accurately analyze the change trend of the local information entropy of each bag area in the time dimension entropy, the current frame image and its previous total frame image, as the reference image of the current frame image (including the current frame image itself), is the default value, and the empirical value is 10. If the image before the current frame is insufficient Frame, postpone the current frame image frame by frame until it meets When the current frame is set, the current frame image is reset and the current frame image is determined in the same way. A reference image.

[0039] In one embodiment, the method for obtaining the local information entropy sequence of each bag area in the current frame image is as follows: obtaining the bag area There are 10 local information entropies in all reference images of the current frame image, which form a local information entropy sequence in chronological order. The local information entropy sequence is used as the bag area in the current frame image. The local information entropy sequence.

[0040] S3: Determine the entropy change stability of each bag region in the current frame image.

[0041] In the current frame image, it is important to determine the entropy change stability of each bag area. When the exhaust gas escapes too quickly, a special situation will occur: if a bag has an exhaust gas leak, the nearby bags without exhaust gas leaks will be affected by the bag, causing the local information entropy of the nearby bags without exhaust gas leaks to increase, and then be mistakenly identified as having exhaust gas leaks.

[0042] For bags with real exhaust gas leakage, the local information entropy will maintain a stable high level after increasing. However, for bags without exhaust gas leakage, the local information entropy is slightly lower than that of bags with exhaust gas leakage, and the changes are unstable because the exhaust gas is continuously diluted after escaping.

[0043] Based on the above analysis, by calculating the entropy change stability of each bag area in the current frame image, we can deeply analyze the change of local information entropy of each bag area. Entropy change stability can be used as a key indicator to reflect the possibility of exhaust gas leakage in the bag area. Specifically: When the entropy change stability of a bag area is low, it means that the change of its local information entropy is unstable, and it is very likely that it is affected by the diffusion of the surrounding bag areas with exhaust gas leakage, not that there is leakage itself; when the entropy change stability of a bag area is high, it means that the change of its local information entropy is relatively stable and at a high level, then the possibility of exhaust gas leakage in the bag area is high.

[0044] In one embodiment, the entropy change stability of each bag area in the current frame image is obtained based on the local information entropy sequence of each bag area. Specifically, the first-order difference sequence of the local information entropy sequence of each bag area is first obtained. The first-order difference sequence is a sequence obtained by subtracting the former from the latter of every two adjacent local information entropies in the original sequence. For example, the local information entropy sequence of a bag area is: 2.5, 2.7, 2.6, 2.8, 2.9, then the first-order difference sequence is 0.2, -0.1, 0.2, 0.1. Then record the sequence number corresponding to the value when the value greater than 0 appears for the first time in the first-order difference sequence except for the starting position, and the value corresponds to two consecutive frame images in the original sequence.

[0045] For example, in the first-order difference sequence 0.2, -0.1, 0.2, 0.1, when a value greater than 0 appears for the first time except at the starting position, the corresponding serial number is 2, which is the serial number of -0.1 in the first-order difference sequence. -0.1 is calculated from the two local information entropies of 2.6 and 2.7.

[0046] When a value greater than 0 appears for the first time in the first-order difference sequence of a bag area except for the starting position, the entropy of the bag area increases in two consecutive frame images (corresponding to the appearance of a value greater than 0). The local information entropy of the bag area shows a significant difference in these two consecutive frame images, and it can be determined that the entropy change stability of the bag area is low.

[0047] In one embodiment, the entropy change stability of each bag region is determined based on the following formula:

[0048] In this formula, For the The entropy change stability of the bag region, For the The first-order difference sequence of the local information entropy of the bag region values, For the The number corresponding to the first time the value of the first-order difference sequence of the local information entropy of the bag region is greater than 0 except for the starting position, which marks the first The starting point where the local information entropy of the bag area begins to show an upward trend, that is, the starting point of entropy increase. This starting point is crucial for analyzing the change of the local information entropy of the bag area. is the total number of reference images of the current frame image, is the total number of bag areas, is a linear normalization function, The value of is mapped to between 0 and 1. is the multiplication symbol, is the absolute value symbol.

[0049] In this formula, is the first The absolute entropy change stability of the bag area. It is The first-order difference sequence of the local information entropy of the bag region is The absolute values ​​of all the values ​​are then multiplied together to comprehensively consider the cumulative effect of the entropy change in the bag area during this period. The use of absolute values ​​ensures that whether the entropy change is positive or negative, it can be reasonably included in the calculation, reflecting the overall situation of the magnitude of the entropy change. If the local information entropy of the bag area changes more dramatically during this period, then the multiplication result will be larger, otherwise it will be smaller. It reflects the starting point of entropy increase. To The time span of the reference image. This time span, combined with the cumulative effect of local information entropy, jointly affects the stability of absolute entropy change. A longer time span and a larger cumulative entropy change will increase the value of the stability of absolute entropy change, which means that the entropy change of the bag area during this period is more complicated and may be in an unstable state; conversely, a shorter time span or a smaller cumulative entropy change indicates that the bag entropy change is relatively stable.

[0050] In this formula, It represents the mean value of the absolute entropy change stability of all bag regions in the current frame image. This mean value is used as a reference benchmark to measure the The difference between the absolute entropy change stability of each bag area and the overall level.

[0051] The whole formula is the first The difference between the absolute entropy change stability of the bag image and the mean absolute entropy change stability of all bag regions, if The absolute entropy change stability of the bag area is much higher than the mean. The larger the difference, The larger the value, the more prominent the entropy change in the bag area is in the overall situation, and the more likely it is to be in a relatively unstable state, which means that the bag area is more likely to have exhaust gas leakage, and vice versa.

[0052] S4: Calculate the vector convergence degree of each bag area in the current frame image.

[0053] Since the local information entropy of the bag area reflects the disorder of the grayscale information in the bag area, when the bag is intact and the exhaust gas is stably diluted, the gas distribution is relatively more regular and orderly, and the local information entropy of the bag area corresponding to the intact bag is lower. However, the gas flow and mixing inside the bag with exhaust gas leakage are more complicated and chaotic, so the local information entropy of the bag area corresponding to the bag with exhaust gas leakage is higher.

[0054] In the current frame image, when the exhaust gas escapes to the intact bags, the dilution rate of the exhaust gas will remain stable. In this case, the overall entropy change stability of all bag areas in the entire dust collector is still at a high level. However, the local information entropy of the bag areas corresponding to the intact bags is slightly lower than the local information entropy of the bag areas corresponding to the bags with exhaust gas leaks. If we rely on the size of the local information entropy, it is difficult to accurately distinguish between intact bags and bags with exhaust gas leaks.

[0055] Therefore, this step sets the following judgment method: During the operation of the bag filter, the state of the bag can be judged based on the gradient characteristics of the local information entropy around it. When a bag leaks, it acts as a leakage source, and the exhaust gas in the bag will gradually escape to the surrounding adjacent bags. From the opposite perspective, the exhaust gas converges from the surrounding adjacent bags to the bag where the leakage source is located. Therefore, it can be observed from the continuous frame images that if the gradient of the local information entropy of the adjacent bag areas around a bag area presents a highly ordered and regular distribution, specifically, the gradient of the local information entropy of the surrounding adjacent bag areas converges toward the center of the bag area, indicating that the bag corresponding to the bag area is very likely to be the source of the leakage. Because of this regular convergence trend, it means that the process of exhaust gas diffusion from the leaking bag to the surrounding area presents a specific pattern. In this specific bag area, the gradient value of its local information entropy is greater than that of the surrounding bag area, highlighting the characteristic changes caused by the diffusion of exhaust gas generated in the bag area.

[0056] On the contrary, if in continuous frame images, the gradient of the local information entropy of adjacent bag areas around a certain bag area presents a disorderly distribution state with no regular pattern to follow, or although there is a divergent trend, it does not converge regularly towards the center of a specific bag area, but diverges randomly to the surroundings without obvious regular changes, then the bag corresponding to the bag area is more likely to be a bag without leakage, indicating that the flow of exhaust gas between these bags is in a normal, disordered state and not affected by bag leakage.

[0057] Therefore, this step determines the gradient of the local information entropy of each bag area in each reference image of the current frame image, as well as the spatial vector of each bag area and its adjacent bag areas, and determines the degree of vector convergence of each bag area based on the gradient and the spatial vector.

[0058] In one embodiment, the method for determining the adjacent bag areas of each bag area is as follows: Set the distance threshold to 200 (empirical value). For each bag area, calculate the Euclidean distance between the center of other bag areas and the center of this bag area, and take other bag areas with a Euclidean distance less than or equal to 200 as all adjacent bag areas of this bag area.

[0059] In one embodiment, the method for determining the gradient of the local information entropy of each bag region in each reference image of the current frame image is: Obtain the local information entropy of each bag region and its adjacent bag regions in each reference image; In each reference image, the direction of the gradient of the local information entropy of each bag area is: the center of the bag area points to the adjacent bag area with the largest local information entropy; the value of the gradient of the local information entropy of each bag area is: the normalized value of the difference between the information entropy of the bag area and the information entropy of the adjacent bag area with the largest local information entropy. In this way, the gradient of the local information entropy of each bag area in each reference image of the current frame image is obtained, and the gradient is a vector.

[0060] In one embodiment, the space vectors of each bag area and its adjacent bag areas are determined as follows: For each bag area and any of its adjacent bag areas, the direction of the space vector is: the center of the adjacent bag area points to the center of the bag area; the value of the space vector is: the normalized value of the Euclidean distance between the center of the adjacent bag area and the center of the bag area. The bag area and its The direction of the space vector of the adjacent bag area is: The center of the adjacent bag area points to the The center of the bag area, the size of the space vector is The center of the Budai area and its The normalized value of the Euclidean distance between the centers of adjacent bag regions.

[0061] In one embodiment, the vector convergence degree of each bag region is calculated based on the following formula:

[0062] In this formula, For the The degree of vector convergence in the bag area, For the The first The adjacent bag area is in the The gradient of the local information entropy of the reference image, For the The bag area and The space vector of adjacent bag regions, For the The total number of adjacent bag areas of a bag area, is the total number of reference images, To find the model length, To find the absolute value, is the natural exponential function, is the normalization function.

[0063] In this formula, for and The greater the consistency of the directions of these two vectors (gradient and space vector are both vectors), the closer the direction of the local information entropy gradient is to the direction of the space vector, which means that the The bag area and its The higher the consistency of the direction of the exhaust gas state change trend in the adjacent bag area and the spatial position, the more regular it is, indicating that the The adjacent bag areas around the first bag area show an orderly convergence state in direction. The larger the bag area, the more likely the bag corresponding to it is the leak source.

[0064] In this formula, for and The numerical difference between these two vectors is smaller, indicating that The bags corresponding to the bag areas are more likely to leak.

[0065] When the bag leaks exhaust gas, the gradient of the local information entropy and the spatial vector are not only regular in direction, but also in value. This close correlation is consistent with the physical process of exhaust gas diffusion when the bag leaks, that is, the exhaust gas changes the local information entropy rapidly in the limited space around the leaking bag, so that the gradient value representing the change of the exhaust gas state tends to match the vector value representing the spatial position. Therefore, through The negative exponential function in Reverse weighting can highlight the impact of the matching degree of numerical differences on the degree of vector convergence. Specifically, the smaller the numerical difference, the more the two vectors match in numerical terms, and the more regularity the vectors of the bag area and its surrounding adjacent bag areas show in numerical terms, indicating that the bag is more likely to be a leaking bag.

[0066] In summary, in a continuous multi-frame image, if the In all the adjacent bag areas of a bag area, the more adjacent bag areas there are, the greater the gradient direction and (the The higher the consistency of the direction of the space vector of the first bag area with those of the adjacent bag areas, and the lower the difference in the value of the gradient direction and the space vector, the The higher the degree of vector convergence in the bag area, the greater the vector convergence in the bag area.

[0067] S5: Comprehensively evaluate the possible degree of leakage of each bag area in the current frame image.

[0068] The possible degree of leakage of each bag area in the current frame image is determined by the local information entropy, entropy change stability and vector convergence degree of each bag area. If the local information entropy, entropy change stability and vector convergence degree of a bag area are higher, the possibility of exhaust gas leakage in the bag area is higher.

[0069] Therefore, the product of the local information entropy, entropy change stability and vector convergence degree of each bag area is used as the possible leakage degree of each bag area. The leakage degree of each bag area may satisfy the following relationship:

[0070] In the formula, The current frame image The possible extent of leakage in each bag area, The current frame image The local information entropy of the bag region (linearly normalized value), The current frame image The entropy change stability of the bag region, The current frame image The degree of vector convergence in the bag area.

[0071] S6: Perform exhaust gas leakage detection based on the possible degree of leakage in each bag area.

[0072] Set the threshold of the possible degree of leakage to (Experience value), if the leakage probability of a bag area in the current frame image is greater than 0.5, the bag area has exhaust gas leakage; if the leakage probability of a bag area is not greater than 0.5, the bag area has no exhaust gas leakage. Further, the bag area with exhaust gas leakage is marked to remind maintenance personnel to check the bag filter in time, and replace the bag with exhaust gas leakage in time according to the mark.

[0073] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for detecting exhaust gas leakage for a bag filter, characterized in that: include: Continuously collect multiple frames of images of the flower plate plane of the bag filter, wherein the flower plate plane includes multiple bag areas, and calculate the local information entropy of each bag area in each frame of the image; Taking any frame image as the current frame image, determining the local information entropy sequence of each bag area of ​​the current frame image according to multiple reference images of the current frame image; The entropy change stability of each bag region is determined according to the first-order difference sequence of the local information entropy sequence of each bag region; the degree of vector convergence is calculated according to the gradient of the local information entropy of each bag region in each reference image and the spatial vector of each bag region and the adjacent bag region: , For the The degree of vector convergence in the bag area, For the The first The adjacent bag area is in The gradient of the local information entropy of the reference image, For the The bag area and The space vector of adjacent bag regions, For the The total number of adjacent bag areas of a bag area, is the total number of reference images, To find the model length, To find the absolute value, is the natural exponential function, is the normalization function; The product of the local information entropy, entropy change stability and vector convergence degree of each bag area is taken as the possible leakage degree of each bag area, and exhaust gas leakage detection is performed according to the possible leakage degree.

2. The method for detecting exhaust gas leakage for bag filter according to claim 1, characterized in that: The entropy stability of each bag area is determined based on the following formula: ； In the formula, For the The entropy change stability of the bag region, For the The first-order difference sequence of the local information entropy of the bag region values, For the The number corresponding to the first time the value of the first-order difference sequence of the local information entropy of the bag region is greater than 0 except for the starting position, is the total number of reference images, is the total number of bag areas, is the linear normalization function, is the multiplication symbol, is the absolute value symbol.

3. The method for detecting exhaust gas leakage for bag filter according to claim 1, characterized in that: The gradient of the local information entropy of each bag region in each reference image is determined as follows: Obtain the local information entropy of each bag region and its adjacent bag regions in each reference image; In each reference image: The direction of the gradient of the local information entropy of each bag area is: the center of the bag area points to the adjacent bag area with the largest local information entropy; The value of the gradient of the local information entropy of each bag area is: the normalized value of the difference between the information entropy of the bag area and the information entropy of the adjacent bag area with the maximum local information entropy.

4. The method for detecting exhaust gas leakage for bag filter according to claim 1, characterized in that: The space vectors of each bag area and the adjacent bag areas are determined based on the following method: For each bag area and any of its adjacent bag areas, the direction of the space vector is: the center of the adjacent bag area points to the center of the bag area; the value of the space vector is: the normalized value of the Euclidean distance between the center of the adjacent bag area and the center of the bag area.

5. The method for detecting exhaust gas leakage for bag filter according to claim 1, characterized in that: The method for obtaining the local information entropy of each bag area in each frame image is: ; In the formula, For the The bag area is in The local information entropy in the frame image, For the The first The gray value is The probability of appearing in the bag area is For the The total number of grayscale value types of the frame image.

6. The method for detecting exhaust gas leakage for bag filter according to claim 1, characterized in that: Each bag area and its adjacent bag areas are determined based on the following method: For each bag area, the distance between the center of the bag area and the centers of other bag areas is calculated, and other bag areas whose distances are less than or equal to a preset distance threshold are taken as adjacent bag areas of the bag area.

7. The method for detecting exhaust gas leakage for bag filter according to claim 1, characterized in that: The method for obtaining multiple bag areas is: using the Hough circle detection method or the row-column segmentation method to divide the flower plate plane of the bag filter into multiple bag areas.

8. The method for detecting exhaust gas leakage for bag filter according to claim 1, characterized in that: The methods for exhaust gas leak detection according to the possible degree of leakage are: If the possibility of leakage in a certain bag area is greater than the preset possibility of leakage threshold, the bag corresponding to the bag area is a bag with exhaust gas leakage; if the possibility of leakage in a certain bag area is not greater than the preset possibility of leakage threshold, the bag corresponding to the bag area is a bag with no exhaust gas leakage.

9. The method for detecting exhaust gas leakage for bag filter according to claim 1, characterized in that: Before calculating the local information entropy of each bag region in each frame of image, the following operations are performed: all the acquired multiple frames of images are converted into grayscale images.

10. The method for detecting exhaust gas leakage for bag filter according to claim 1, characterized in that: The multiple reference images of the current frame image are: the current frame image and the total number of images before it Frame image, is the default value.

Images