Automatic cleaning method and system for sulfuric acid absorption tower

Abstract

The invention relates to the technical field of sulfuric acid absorption towers, and discloses an automatic cleaning method and system for a sulfuric acid absorption tower, a plurality of to-be-analyzed images of the sulfuric acid absorption tower are obtained, the plurality of to-be-analyzed images are respectively preprocessed, to-be-detected images are determined, and reference images corresponding to the to-be-detected images are obtained; acquiring data information corresponding to the to-be-detected image, and performing graying processing on the to-be-detected image according to the data information to obtain a corresponding graying processing image; determining a reference gray level image of the reference image, and calculating a correlation degree between the reference gray level image and the graying processing image; whether foreign matters exist in the sulfuric acid absorption tower or not is judged based on the correlation degree, if yes, a cleaning instruction of the cleaning device is set according to the correlation degree, intelligent detection of the foreign matters in the sulfuric acid absorption tower can be achieved, errors caused by manual participation are avoided, the foreign matter detection precision and real-time performance are improved, and process blockage caused by accumulation of a large number of foreign matters is avoided; and the purity is influenced.

Description

Technical Field

[0001] The invention relates to the technical field of sulfuric acid absorption towers, and in particular to an automatic cleaning method and system for sulfuric acid absorption towers. Background Art

[0002] Absorption tower is a device for realizing absorption operation, which is divided into three categories according to the contact form between gas and liquid. The first category is plate tower, bubbling absorption tower, stirring bubbling absorption tower in which gas is dispersed in liquid phase in the form of bubbles; the second category is ejector, venturi, spray tower in which liquid is dispersed in gas phase in the form of droplets; the third category is packed absorption tower and falling film absorption tower in which liquid contacts gas phase in film-like motion. The flow mode of gas and liquid in the tower can be countercurrent or cocurrent. Countercurrent operation is usually adopted, and the absorbent is added from the top of the tower to flow from top to bottom, contacting with gas flowing from bottom to top, and the liquid that absorbs the absorbent is discharged from the bottom of the tower, and the purified gas is discharged from the top of the tower.

[0003] The absorption tower is composed of a shell, fillers, filler supports, liquid distributors, intermediate supports and redistributors, gas and liquid inlet and outlet pipes and other components. The tower shell is mostly made of metal materials, but can also be made of plastic. After the absorption tower has been running for a long time, large slag will appear and it is easy to scale. After long-term operation, this slag will be mixed in the liquid, affecting the quality of the liquid. In the subsequent use of the purified liquid, it is easy to cause process blockage and affect the purity. However, the existing technology can only provide staff with detection of foreign matter such as large slag and scaling, which is inefficient. Summary of the invention

[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an automatic cleaning method and system for a sulfuric acid absorption tower, aiming to solve the problems in the prior art that it is impossible to accurately detect large slag, scaling and other foreign matter appearing in the absorption tower, and it is impossible to provide reliable support for automatic cleaning. The existing manual detection method is not timely and has low efficiency. After long-term operation, such slag will be mixed in the liquid, affecting the quality of the liquid, easily causing process blockage, and affecting the purity.

[0005] In order to achieve the above object, the present invention provides an automatic cleaning method for a sulfuric acid absorption tower, comprising:

[0006] Acquire multiple images to be analyzed of the sulfuric acid absorption tower, pre-process the multiple images to be analyzed respectively, determine an image to be detected, and acquire a reference image corresponding to the image to be detected;

[0007] Acquire data information corresponding to the image to be detected, and perform grayscale processing on the image to be detected according to the data information to obtain a corresponding grayscale processed image;

[0008] Determining a reference grayscale image of the reference image, and calculating a correlation degree between the reference grayscale image and the grayscale processed image;

[0009] Based on the correlation degree, it is determined whether there are foreign objects in the sulfuric acid absorption tower. If so, a cleaning instruction for a cleaning device is set according to the correlation degree.

[0010] Further, when acquiring a plurality of images to be analyzed of the sulfuric acid absorption tower, preprocessing the plurality of images to be analyzed respectively, determining an image to be detected, and acquiring a reference image corresponding to the image to be detected, the method includes:

[0011] Performing image difference preprocessing on the image to be analyzed, and performing image segmentation on the image to be analyzed based on a preset segmentation algorithm to obtain a plurality of segmented images;

[0012] Perform convolution operation on the image pixel values ​​of each segmented image according to the convolutional neural network, and obtain the convolution value;

[0013] Classifying the segmented image according to the relationship between the convolution value and a preset convolution value;

[0014] When the convolution value is greater than or equal to the preset convolution value, a set of images to be analyzed is generated according to the corresponding segmented images;

[0015] Obtaining the confidences of all segmented images in the image set to be analyzed, sorting all segmented images based on the confidence values, and taking the segmented image corresponding to the maximum confidence as the image to be detected;

[0016] When the convolution value is less than the preset convolution value, a set of images not to be analyzed is generated according to the corresponding segmented images.

[0017] Furthermore, when obtaining data information corresponding to the image to be detected and graying the image to be detected according to the data information to obtain a corresponding graying processed image, it includes:

[0018] Divide the image to be detected into multiple sub-images, obtain the image area of ​​each sub-image, and obtain the total area of ​​the image to be detected;

[0019] Calculate the image area ratio of each sub-image according to the image area of ​​each sub-image and the total area of ​​the image to be detected;

[0020] According to the image area ratio, the red channel grayscale conversion coefficient, the green channel conversion coefficient and the blue channel conversion coefficient of the sub-image are set;

[0021] Obtaining the image entropy value of each sub-image respectively, and correcting the red channel grayscale conversion coefficient, the green channel conversion coefficient and the blue channel conversion coefficient of the sub-image according to the image entropy value, to obtain the target red channel grayscale conversion coefficient, the target green channel conversion coefficient and the target blue channel conversion coefficient;

[0022] The sub-image is gray-scaled based on a target red channel grayscale conversion coefficient, a target green channel grayscale conversion coefficient, and a target blue channel grayscale conversion coefficient to obtain a corresponding gray-scaled image.

[0023] Furthermore, when determining a reference grayscale image of the reference image and calculating the degree of association between the reference grayscale image and the grayscale processed image, it includes:

[0024] Extracting pixel points of the grayscale processed image and determining first pixel information corresponding to each pixel point;

[0025] constructing a first pixel information value sequence according to the first pixel information, and calculating a first difference influence value Y1 of the grayscale processed image according to the first pixel information value sequence;

[0026] Extracting pixel points of the reference grayscale image and determining second pixel information corresponding to each pixel point;

[0027] constructing a second pixel information value sequence according to the second pixel information, and calculating a second difference influence value Y2 of the reference grayscale image according to the second pixel information value sequence;

[0028] The degree of association between the reference grayscale image and the grayscale processed image is calculated according to the first difference influence value Y1 and the second difference influence value Y2.

[0029] Further, when calculating the first difference influence value Y1 of the grayscale processed image according to the first pixel information value sequence, it includes:

[0030] Determine a comparison pixel information value sequence corresponding to the first pixel information value sequence;

[0031] Divide the pixel information of the first pixel information value sequence that is smaller than the comparison pixel information value sequence into a first pixel information set;

[0032] Divide the pixel information in the first pixel information value sequence that is equal to the comparison pixel information value sequence into a second pixel information set;

[0033] Divide the pixel information of the first pixel information value sequence that is greater than the comparison pixel information value sequence into a third pixel information set;

[0034] Calculate a first difference influence value Y1 of the grayscale processed image according to the first pixel information set, the second pixel information set and the third pixel information set;

[0035] The first difference influence value Y1 of the grayscale processed image is calculated according to the following formula:

[0036]

[0037] Wherein, n is the number of pixel information in the first pixel information set, bi is the i-th pixel information in the first pixel information set, e is the average value of the pixel information in the first pixel information set, m is the number of pixel information in the third pixel information set, fj is the j-th pixel information in the third pixel information set, d is the average value of the pixel information in the third pixel information set, and h is the correction coefficient of the first difference influence value;

[0038] The method for determining the correction coefficient h of the first difference influence value includes:

[0039] Counting the number q of pixel information in the second pixel information set;

[0040] If q≥m+n, set the correction factor h to 1;

[0041] If q<m+n, then determine the quantity ratio q / m+n;

[0042] Setting a preset quantity ratio, setting a first preset correction coefficient, a second preset correction coefficient and a third preset correction coefficient;

[0043] When the quantity ratio q / m+n is less than the preset quantity ratio, the first preset correction coefficient is used as the correction coefficient of the first difference influence value;

[0044] When the quantity ratio q / m+n=the preset quantity ratio, the second preset correction coefficient is used as the correction coefficient of the first difference influence value;

[0045] When the quantity ratio q / m+n>the preset quantity ratio, the third preset correction coefficient is used as the correction coefficient of the first difference influence value.

[0046] Further, when calculating the correlation degree between the reference grayscale image and the grayscale processed image according to the first difference influence value Y1 and the second difference influence value Y2, it includes:

[0047] Calculating an absolute value of a difference between the first difference impact value Y1 and the second difference impact value Y2;

[0048] A corresponding weight is determined, and a product value of the weight and the absolute value of the difference is used as the degree of association between the reference grayscale image and the grayscale processed image.

[0049] Further, when judging whether there is foreign matter in the sulfuric acid absorption tower based on the correlation degree, it includes:

[0050] Obtaining a preset correlation degree, and judging whether there is foreign matter in the sulfuric acid absorption tower according to the relationship between the preset correlation degree and the correlation degree;

[0051] When the correlation degree is less than the preset correlation degree, it is determined that there is no foreign matter in the sulfuric acid absorption tower;

[0052] When the correlation degree is greater than or equal to the preset correlation degree, it is determined that foreign matter exists in the sulfuric acid absorption tower.

[0053] In order to achieve the above object, the present invention also provides an automatic cleaning system for a sulfuric acid absorption tower, comprising:

[0054] The first module is used to obtain a plurality of images to be analyzed of the sulfuric acid absorption tower, pre-process the plurality of images to be analyzed respectively, determine an image to be detected, and obtain a reference image corresponding to the image to be detected;

[0055] The second module is used to obtain data information corresponding to the image to be detected, and grayscale the image to be detected according to the data information to obtain a corresponding grayscale processed image;

[0056] A third module is used to determine a reference grayscale image of the reference image, and calculate the degree of association between the reference grayscale image and the grayscale processed image;

[0057] The fourth module is used to determine whether there are foreign objects in the sulfuric acid absorption tower based on the correlation degree, and if so, set a cleaning instruction for the cleaning device according to the correlation degree.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The invention discloses an automatic cleaning method and system for a sulfuric acid absorption tower. The method comprises the following steps: obtaining a plurality of images to be analyzed of the sulfuric acid absorption tower, pre-processing the plurality of images to be analyzed respectively, determining an image to be detected, and obtaining a reference image corresponding to the image to be detected; obtaining data information corresponding to the image to be detected, and gray-scaling the image to be detected respectively according to the data information to obtain a corresponding gray-scaling processed image; determining a reference gray-scale image of the reference image, and calculating the degree of correlation between the reference gray-scale image and the gray-scaling processed image; judging whether there are foreign matters in the sulfuric acid absorption tower based on the degree of correlation, and if so, setting a cleaning instruction of a cleaning device according to the degree of correlation, so as to realize intelligent detection of foreign matters in the sulfuric acid absorption tower, avoid errors existing in manual participation, improve the accuracy and real-time performance of foreign matter detection, and avoid the phenomenon that a large amount of foreign matters are accumulated, causing process blockage and affecting purity. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0061] Figure 1 A schematic flow chart of an automatic cleaning method for a sulfuric acid absorption tower in an embodiment of the present invention is shown;

[0062] Figure 2 The schematic diagram of the structure of the automatic cleaning system for the sulfuric acid absorption tower in the embodiment of the present invention is shown. DETAILED DESCRIPTION

[0063] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0064] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0065] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0066] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0067] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0068] like Figure 1 As shown, an embodiment of the present invention discloses an automatic cleaning method for a sulfuric acid absorption tower, comprising:

[0069] S110: acquiring a plurality of images to be analyzed of the sulfuric acid absorption tower, preprocessing the plurality of images to be analyzed respectively, determining an image to be detected, and acquiring a reference image corresponding to the image to be detected;

[0070] In some embodiments of the present application, when acquiring multiple images to be analyzed of a sulfuric acid absorption tower, preprocessing the multiple images to be analyzed respectively, determining an image to be detected, and acquiring a reference image corresponding to the image to be detected, the method includes:

[0071] Performing image difference preprocessing on the image to be analyzed, and performing image segmentation on the image to be analyzed based on a preset segmentation algorithm to obtain a plurality of segmented images;

[0072] Perform convolution operation on the image pixel values ​​of each segmented image according to the convolutional neural network, and obtain the convolution value;

[0073] Classifying the segmented image according to the relationship between the convolution value and a preset convolution value;

[0074] When the convolution value is greater than or equal to the preset convolution value, a set of images to be analyzed is generated according to the corresponding segmented images;

[0075] Obtaining the confidences of all segmented images in the image set to be analyzed, sorting all segmented images based on the confidence values, and taking the segmented image corresponding to the maximum confidence as the image to be detected;

[0076] When the convolution value is less than the preset convolution value, a set of images not to be analyzed is generated according to the corresponding segmented images.

[0077] In this embodiment, the preset convolution value can be set according to actual conditions and is not specifically limited here.

[0078] In this embodiment, the confidences of all segmented images in the image set to be analyzed may be determined based on a pre-trained confidence model.

[0079] The beneficial effect of the above technical solution is that the present invention determines the image to be detected according to the convolution value and the confidence level, and can provide a basis for judging whether there are foreign objects in the sulfuric acid absorption tower, thereby ensuring the accuracy of the judgment.

[0080] S120: Acquire data information corresponding to the image to be detected, and perform grayscale processing on the image to be detected according to the data information to obtain a corresponding grayscale processed image;

[0081] In some embodiments of the present application, when acquiring data information corresponding to the image to be detected, and gray-scaling the image to be detected according to the data information, to obtain a corresponding gray-scale processed image, the method includes:

[0082] Divide the image to be detected into multiple sub-images, obtain the image area of ​​each sub-image, and obtain the total area of ​​the image to be detected;

[0083] Calculate the image area ratio of each sub-image according to the image area of ​​each sub-image and the total area of ​​the image to be detected;

[0084] According to the image area ratio, the red channel grayscale conversion coefficient, the green channel conversion coefficient and the blue channel conversion coefficient of the sub-image are set;

[0085] Obtaining the image entropy value of each sub-image respectively, and correcting the red channel grayscale conversion coefficient, the green channel conversion coefficient and the blue channel conversion coefficient of the sub-image according to the image entropy value, to obtain the target red channel grayscale conversion coefficient, the target green channel conversion coefficient and the target blue channel conversion coefficient;

[0086] The sub-image is gray-scaled based on a target red channel grayscale conversion coefficient, a target green channel grayscale conversion coefficient, and a target blue channel grayscale conversion coefficient to obtain a corresponding gray-scaled image.

[0087] In this embodiment, the red channel grayscale conversion coefficient, the green channel conversion coefficient, and the blue channel conversion coefficient of the sub-image are set based on the area ratio-conversion coefficient mapping table.

[0088] In this embodiment, the corresponding correction coefficient is determined according to the image entropy value-correction coefficient mapping table, and the product value of the correction coefficient and the red channel grayscale conversion coefficient, the green channel conversion coefficient and the blue channel conversion coefficient is used as the target red channel grayscale conversion coefficient, the target green channel conversion coefficient and the target blue channel conversion coefficient.

[0089] The beneficial effect of the above technical solution is: the present invention performs grayscale processing on the sub-image based on the target red channel grayscale conversion coefficient, the target green channel conversion coefficient and the target blue channel conversion coefficient to obtain the corresponding grayscale processed image, which effectively ensures the accuracy of grayscale conversion and avoids errors caused by manual calculation.

[0090] S130: Determine a reference grayscale image of the reference image, and calculate a correlation degree between the reference grayscale image and the grayscale processed image;

[0091] In some embodiments of the present application, when determining a reference grayscale image of the reference image and calculating the degree of association between the reference grayscale image and the grayscale processed image, the method includes:

[0092] Extracting pixel points of the grayscale processed image and determining first pixel information corresponding to each pixel point;

[0093] constructing a first pixel information value sequence according to the first pixel information, and calculating a first difference influence value Y1 of the grayscale processed image according to the first pixel information value sequence;

[0094] Extracting pixel points of the reference grayscale image and determining second pixel information corresponding to each pixel point;

[0095] constructing a second pixel information value sequence according to the second pixel information, and calculating a second difference influence value Y2 of the reference grayscale image according to the second pixel information value sequence;

[0096] The degree of association between the reference grayscale image and the grayscale processed image is calculated according to the first difference influence value Y1 and the second difference influence value Y2.

[0097] When calculating the first difference influence value Y1 of the grayscale processed image according to the first pixel information value sequence, it includes:

[0098] Determine a comparison pixel information value sequence corresponding to the first pixel information value sequence;

[0099] Divide the pixel information of the first pixel information value sequence that is smaller than the comparison pixel information value sequence into a first pixel information set;

[0100] Divide the pixel information in the first pixel information value sequence that is equal to the comparison pixel information value sequence into a second pixel information set;

[0101] Divide the pixel information of the first pixel information value sequence that is greater than the comparison pixel information value sequence into a third pixel information set;

[0102] Calculate a first difference influence value Y1 of the grayscale processed image according to the first pixel information set, the second pixel information set and the third pixel information set;

[0103] The first difference influence value Y1 of the grayscale processed image is calculated according to the following formula:

[0104]

[0105] Wherein, n is the number of pixel information in the first pixel information set, bi is the i-th pixel information in the first pixel information set, e is the average value of the pixel information in the first pixel information set, m is the number of pixel information in the third pixel information set, fj is the j-th pixel information in the third pixel information set, d is the average value of the pixel information in the third pixel information set, and h is the correction coefficient of the first difference influence value;

[0106] The method for determining the correction coefficient h of the first difference influence value includes:

[0107] Counting the number q of pixel information in the second pixel information set;

[0108] If q≥m+n, set the correction factor h to 1;

[0109] If q<m+n, then determine the quantity ratio q / m+n;

[0110] Setting a preset quantity ratio, setting a first preset correction coefficient, a second preset correction coefficient and a third preset correction coefficient;

[0111] When the quantity ratio q / m+n is less than the preset quantity ratio, the first preset correction coefficient is used as the correction coefficient of the first difference influence value;

[0112] When the quantity ratio q / m+n=the preset quantity ratio, the second preset correction coefficient is used as the correction coefficient of the first difference influence value;

[0113] When the quantity ratio q / m+n>the preset quantity ratio, the third preset correction coefficient is used as the correction coefficient of the first difference influence value.

[0114] In this embodiment, the preset quantity ratio is a fixed value, preferably 7.

[0115] In this embodiment, the first preset correction coefficient, the second preset correction coefficient and the third preset correction coefficient are fixed values, where the first preset correction coefficient is preferably 0.85, the second preset correction coefficient is preferably 1, and the third preset correction coefficient is preferably 1.25.

[0116] The beneficial effect of the above technical solution is that the present invention realizes the accurate calculation of the first difference influence value Y1, and at the same time, by determining the correction coefficient, it also ensures the dynamic adjustment of the first difference influence value Y1, thereby avoiding the singleness of the calculation process.

[0117] In some embodiments of the present application, when calculating the degree of association between the reference grayscale image and the grayscale processed image according to the first difference influence value Y1 and the second difference influence value Y2, the method includes:

[0118] Calculating an absolute value of a difference between the first difference impact value Y1 and the second difference impact value Y2;

[0119] A corresponding weight is determined, and a product value of the weight and the absolute value of the difference is used as the degree of association between the reference grayscale image and the grayscale processed image.

[0120] The beneficial effect of the above technical solution is: the present invention calculates the absolute value of the difference between the first difference influence value Y1 and the second difference influence value Y2, and uses the product value of the weight and the absolute value of the difference as the degree of correlation between the reference grayscale image and the grayscale processed image, thereby providing reliable judgment data for whether there are foreign matter in the sulfuric acid absorption tower, and ensuring the judgment accuracy and convenience.

[0121] S140: Determine whether there are foreign objects in the sulfuric acid absorption tower based on the correlation degree, and if so, set a cleaning instruction for the cleaning device according to the correlation degree.

[0122] In some embodiments of the present application, when judging whether there is foreign matter in the sulfuric acid absorption tower based on the correlation degree, it includes:

[0123] Obtaining a preset correlation degree, and judging whether there is foreign matter in the sulfuric acid absorption tower according to the relationship between the preset correlation degree and the correlation degree;

[0124] When the correlation degree is less than the preset correlation degree, it is determined that there is no foreign matter in the sulfuric acid absorption tower;

[0125] When the correlation degree is greater than or equal to the preset correlation degree, it is determined that foreign matter exists in the sulfuric acid absorption tower.

[0126] In this embodiment, the preset correlation degree is a fixed value, preferably 5 here.

[0127] The beneficial effects of the above technical solution are: it can realize intelligent detection of foreign matter in the sulfuric acid absorption tower, avoid errors caused by human participation, improve the accuracy and real-time performance of foreign matter detection, and avoid the accumulation of large amounts of foreign matter, which may cause process blockage and affect purity.

[0128] In order to further explain the technical idea of ​​the present invention, the technical solution of the present invention is now described in combination with specific application scenarios.

[0129] Correspondingly, such as Figure 2 As shown, the present application also provides an automatic cleaning system for a sulfuric acid absorption tower, comprising:

[0130] The first module is used to obtain a plurality of images to be analyzed of the sulfuric acid absorption tower, pre-process the plurality of images to be analyzed respectively, determine an image to be detected, and obtain a reference image corresponding to the image to be detected;

[0131] The second module is used to obtain data information corresponding to the image to be detected, and grayscale the image to be detected according to the data information to obtain a corresponding grayscale processed image;

[0132] A third module is used to determine a reference grayscale image of the reference image, and calculate the degree of association between the reference grayscale image and the grayscale processed image;

[0133] The fourth module is used to determine whether there are foreign objects in the sulfuric acid absorption tower based on the correlation degree, and if so, set a cleaning instruction for the cleaning device according to the correlation degree.

[0134] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0135] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed by the present invention may be used in combination with each other in any manner, and the fact that these combinations are not fully described in this specification is only for the sake of omitting space and saving resources.

[0136] Those skilled in the art can understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An automatic cleaning method for a sulfuric acid absorption tower, characterized in that: include: Acquire multiple images to be analyzed of the sulfuric acid absorption tower, pre-process the multiple images to be analyzed respectively, determine an image to be detected, and acquire a reference image corresponding to the image to be detected; Acquire data information corresponding to the image to be detected, and perform grayscale processing on the image to be detected according to the data information to obtain a corresponding grayscale processed image; Determining a reference grayscale image of the reference image, and calculating a correlation degree between the reference grayscale image and the grayscale processed image; Based on the correlation degree, it is determined whether there are foreign objects in the sulfuric acid absorption tower. If so, a cleaning instruction for a cleaning device is set according to the correlation degree.

2. The automatic cleaning method for a sulfuric acid absorption tower according to claim 1, characterized in that: When a plurality of images to be analyzed of a sulfuric acid absorption tower are obtained, the plurality of images to be analyzed are preprocessed respectively, an image to be detected is determined, and a reference image corresponding to the image to be detected is obtained, including: Performing image difference preprocessing on the image to be analyzed, and performing image segmentation on the image to be analyzed based on a preset segmentation algorithm to obtain a plurality of segmented images; Perform convolution operation on the image pixel values ​​of each segmented image according to the convolutional neural network, and obtain the convolution value; Classifying the segmented image according to the relationship between the convolution value and a preset convolution value; When the convolution value is greater than or equal to the preset convolution value, a set of images to be analyzed is generated according to the corresponding segmented images; Obtaining the confidences of all segmented images in the image set to be analyzed, sorting all segmented images based on the confidence values, and taking the segmented image corresponding to the maximum confidence as the image to be detected; When the convolution value is less than the preset convolution value, a set of images not to be analyzed is generated according to the corresponding segmented images.

3. The automatic cleaning method for a sulfuric acid absorption tower according to claim 1, characterized in that: When acquiring data information corresponding to the image to be detected and performing grayscale processing on the image to be detected according to the data information to obtain a corresponding grayscale processed image, the method includes: Divide the image to be detected into multiple sub-images, obtain the image area of ​​each sub-image, and obtain the total area of ​​the image to be detected; Calculate the image area ratio of each sub-image according to the image area of ​​each sub-image and the total area of ​​the image to be detected; According to the image area ratio, the red channel grayscale conversion coefficient, the green channel conversion coefficient and the blue channel conversion coefficient of the sub-image are set; Obtaining the image entropy value of each sub-image respectively, and correcting the red channel grayscale conversion coefficient, the green channel conversion coefficient and the blue channel conversion coefficient of the sub-image according to the image entropy value, to obtain the target red channel grayscale conversion coefficient, the target green channel conversion coefficient and the target blue channel conversion coefficient; The sub-image is gray-scaled based on a target red channel grayscale conversion coefficient, a target green channel grayscale conversion coefficient, and a target blue channel grayscale conversion coefficient to obtain a corresponding gray-scaled image.

4. The automatic cleaning method for a sulfuric acid absorption tower according to claim 1, characterized in that: When determining a reference grayscale image of the reference image and calculating the degree of association between the reference grayscale image and the grayscale processed image, it includes: Extracting pixel points of the grayscale processed image and determining first pixel information corresponding to each pixel point; constructing a first pixel information value sequence according to the first pixel information, and calculating a first difference influence value Y1 of the grayscale processed image according to the first pixel information value sequence; Extracting pixel points of the reference grayscale image and determining second pixel information corresponding to each pixel point; constructing a second pixel information value sequence according to the second pixel information, and calculating a second difference influence value Y2 of the reference grayscale image according to the second pixel information value sequence; The degree of association between the reference grayscale image and the grayscale processed image is calculated according to the first difference influence value Y1 and the second difference influence value Y2.

5. The automatic cleaning method for a sulfuric acid absorption tower according to claim 4, characterized in that: When calculating the first difference influence value Y1 of the grayscale processed image according to the first pixel information value sequence, it includes: Determine a comparison pixel information value sequence corresponding to the first pixel information value sequence; Divide the pixel information of the first pixel information value sequence that is smaller than the comparison pixel information value sequence into a first pixel information set; Divide the pixel information in the first pixel information value sequence that is equal to the comparison pixel information value sequence into a second pixel information set; Divide the pixel information of the first pixel information value sequence that is greater than the comparison pixel information value sequence into a third pixel information set; Calculate a first difference influence value Y1 of the grayscale processed image according to the first pixel information set, the second pixel information set and the third pixel information set; The first difference influence value Y1 of the grayscale processed image is calculated according to the following formula: Wherein, n is the number of pixel information in the first pixel information set, bi is the i-th pixel information in the first pixel information set, e is the average value of the pixel information in the first pixel information set, m is the number of pixel information in the third pixel information set, fj is the j-th pixel information in the third pixel information set, d is the average value of the pixel information in the third pixel information set, and h is the correction coefficient of the first difference influence value; The method for determining the correction coefficient h of the first difference influence value includes: Counting the number q of pixel information in the second pixel information set; If q≥m+n, set the correction factor h to 1; If q<m+n, then determine the quantity ratio q / m+n; Setting a preset quantity ratio, setting a first preset correction coefficient, a second preset correction coefficient and a third preset correction coefficient; When the quantity ratio q / m+n is less than the preset quantity ratio, the first preset correction coefficient is used as the correction coefficient of the first difference influence value; When the quantity ratio q / m+n=the preset quantity ratio, the second preset correction coefficient is used as the correction coefficient of the first difference influence value; When the quantity ratio q / m+n>the preset quantity ratio, the third preset correction coefficient is used as the correction coefficient of the first difference influence value.

6. The automatic cleaning method for a sulfuric acid absorption tower according to claim 1, characterized in that: When calculating the degree of association between the reference grayscale image and the grayscale processed image according to the first difference influence value Y1 and the second difference influence value Y2, the method includes: Calculating an absolute value of a difference between the first difference impact value Y1 and the second difference impact value Y2; A corresponding weight is determined, and a product value of the weight and the absolute value of the difference is used as the degree of association between the reference grayscale image and the grayscale processed image.

7. The automatic cleaning method for a sulfuric acid absorption tower according to claim 1, characterized in that: When judging whether there is foreign matter in the sulfuric acid absorption tower based on the correlation degree, the method includes: Obtaining a preset correlation degree, and judging whether there is foreign matter in the sulfuric acid absorption tower according to the relationship between the preset correlation degree and the correlation degree; When the correlation degree is less than the preset correlation degree, it is determined that there is no foreign matter in the sulfuric acid absorption tower; When the correlation degree is greater than or equal to the preset correlation degree, it is determined that foreign matter exists in the sulfuric acid absorption tower.

8. An automatic cleaning system for a sulfuric acid absorption tower, applied to the automatic cleaning method for a sulfuric acid absorption tower according to any one of claims 1 to 7, characterized in that: include: The first module is used to obtain a plurality of images to be analyzed of the sulfuric acid absorption tower, pre-process the plurality of images to be analyzed respectively, determine an image to be detected, and obtain a reference image corresponding to the image to be detected; The second module is used to obtain data information corresponding to the image to be detected, and grayscale the image to be detected according to the data information to obtain a corresponding grayscale processed image; A third module is used to determine a reference grayscale image of the reference image, and calculate the degree of association between the reference grayscale image and the grayscale processed image; The fourth module is used to determine whether there are foreign objects in the sulfuric acid absorption tower based on the correlation degree, and if so, set a cleaning instruction for the cleaning device according to the correlation degree.

Images