Bag leakage positioning detection method suitable for bag type dust removal system and related equipment

Abstract

The invention relates to the technical field of cloth bag dust removal positioning, in particular to a bag leakage positioning detection method suitable for a bag type dust removal system and related equipment, and the method comprises the following steps: obtaining a dust concentration distribution matrix; grading each data point of the matrix to obtain a grade matrix; marking the uniform area, and obtaining a reset matrix; clustering all data in the reset matrix to obtain a dust cluster; obtaining a dust accumulation factor of each data point in the dust cluster; obtaining a dust deposition index of each uniform area; obtaining a damage confidence coefficient of each uniform region; and mapping the matrix coordinates corresponding to the mass center of each uniform area, and positioning the leakage bag in combination with the damage confidence. The invention aims to improve the accuracy of leaked bag positioning.

Description

Technical Field

[0001] The present application relates to the technical field of bag dust removal positioning, and in particular to a bag leak positioning detection method and related equipment applicable to a bag dust removal system. Background Art

[0002] Bag dust removal technology has evolved from the initial hanging bag to the modern large-scale pulse back-blowing bag dust collector, witnessing the progress and innovation of industrial dust removal technology, and can meet the stringent requirements of industrial smoke and dust emissions. Especially in the steel, cement and other industries, bag dust removal technology has achieved ultra-low emission targets, playing an important role in environmental protection and industrial sustainable development. Once the filter bag is damaged, it will directly affect the dust removal efficiency and emission quality, resulting in failure to meet environmental protection standards. Therefore, timely and accurate detection and positioning of leaking bags is crucial to ensuring dust removal effects, extending equipment life, and maintaining environmental quality.

[0003] The leaky bag positioning technology can be achieved by directly measuring the dust concentration, using a dust concentration sensor to monitor the dust content in the dust box. This method is sensitive to changes in dust, but because the mobility and distribution of dust in the dust box may be uneven, the concentration data detected by the sensor may fluctuate, thus affecting the positioning accuracy. Summary of the invention

[0004] In view of the above, it is necessary to provide a bag leakage positioning detection method and related equipment suitable for a bag dust removal system to solve the above problems.

[0005] The first aspect of the present application provides a bag leakage positioning detection method applicable to a bag dust removal system, the method comprising: The dust concentrations at all preset positions in the dust removal box form a dust concentration distribution matrix; Analyze the numerical distribution of all data points in the dust concentration distribution matrix, classify each data point in the matrix, and obtain a grade matrix; preset a sliding window, and based on the degree of data dispersion in the window when the sliding window moves in the grade matrix, mark the uniform area and obtain a reset matrix; Cluster all data in the reset matrix to obtain dust clusters; obtain the dust accumulation factor of each data point in the dust cluster based on the distribution difference of dust concentration between each data point in the dust cluster and all data points, combined with the randomness of the data point in the preset neighborhood window; Analyze the difference in dust concentration distribution between each uniform area and the dust cluster, and the chaotic characteristics of dust concentration in each uniform area, and obtain the dust deposition index of each uniform area; analyze the distance between each uniform area and all data points in the dust cluster, and combine the dust accumulation factor and the dust deposition index to obtain the damage confidence of each uniform area; The matrix coordinates corresponding to the centroid of each uniform area are mapped, and the leaking bag is located in combination with the damage confidence.

[0006] The specific process of classifying each element of the matrix is ​​as follows: The negative correlation mapping result of the extreme value of all data points in the dust concentration distribution matrix is ​​used as the step size of the grade division; the minimum data point of the dust concentration distribution matrix is ​​used as the starting value of the grade division to obtain the grade division interval, and the corresponding concentration level is assigned to each data point in the matrix; The matrix consisting of the concentration levels of all data points is used as the level matrix.

[0007] The process of marking the uniform area is specifically as follows: Calculate the standard deviation of all data in the sliding window each time it moves in the rank matrix, and filter all areas where the standard deviation is equal to 0 to obtain uniform areas.

[0008] The reset matrix is ​​specifically a dust concentration distribution matrix in which the data points at the corresponding positions of the uniform area are 0.

[0009] The specific process of clustering all the data in the reset matrix to obtain dust clusters is as follows: A preset number of clusters are obtained; the dust concentration mean of all data points in each cluster is calculated and recorded as the dust concentration within the cluster; and the cluster with the largest dust concentration within the cluster is taken as the dust cluster.

[0010] The dust accumulation factor of each data point in the dust cluster includes: Calculate the dust concentration average of all data points in the dust cluster; compare the dust concentration of each data point in the dust cluster with the dust concentration average to obtain the concentration ratio of each data point in the dust cluster; The grayscale run matrix algorithm is used to obtain the run entropy of each data point in the neighborhood window; Based on the concentration ratio and the run entropy, a dust accumulation factor of each data point in the dust cluster is obtained; wherein the dust accumulation factor is positively correlated with the concentration ratio and negatively correlated with the run entropy.

[0011] The dust deposition index of each uniform area is obtained as follows: The difference between the mean dust concentration in each uniform area and the mean dust concentration in the dust cluster is calculated; the maximum value between the difference and 0 is obtained; the maximum value corresponding to each uniform area is merged with the dust concentration entropy value of all data points in the area to obtain the dust deposition index of each uniform area.

[0012] The formula for obtaining the damage confidence of each uniform area is: ; represents the damage confidence of the i-th uniform area; represents the shortest Euclidean distance between the kth data point and the ith uniform region in the dust cluster, and e represents a natural constant; Indicates the dust accumulation degree of the kth data point in the dust cluster; represents the dust deposition index of the ith uniform area; K represents the total number of data points in the dust cluster.

[0013] The specific process of locating the leaking bag is as follows: Obtain the area corresponding to the dust distribution matrix, recorded as the distribution area; calculate the average coordinates of all data points in each uniform area in the distribution area to obtain the coordinates of the center of the area; Obtaining the proportional position of the regional center of each uniform region in the dust concentration distribution matrix, wherein the abscissa of the proportional position is the ratio of the abscissa of the regional center to the matrix width, and the ordinate is the ratio of the ordinate of the regional center to the matrix length; According to the proportional position, the center of each uniform area is mapped to the actual dust removal box position. If the center of the area falls into the filter bag position, the corresponding uniform area is marked and recorded as the marked area. When the damage confidence of the marked area is greater than a preset damage threshold, the area center corresponding to the marked area is determined to be the location of the damaged filter bag.

[0014] In the second aspect, an embodiment of the present application also provides a bag leakage positioning detection device suitable for a bag dust removal system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above methods are implemented.

[0015] In the above scheme, the dust concentrations of all preset positions in the dust collection box are combined into a dust concentration distribution matrix, which can comprehensively reflect the spatial distribution of dust concentration inside the dust collection box, and help to identify possible bag leakage areas by comparing the dust concentration changes at different positions in the future; obtaining the grade matrix, marking the uniform area, and obtaining the reset matrix are helpful to divide the dust concentration grades, obtain the filter bag area with uniform concentration distribution, and separate the area with uniform dust concentration distribution, and analyze the area with uneven dust concentration distribution, that is, the non-filter bag area; clustering all the data in the reset matrix to obtain dust clusters, and obtain the dust accumulation factor of each data point in the dust cluster. The beneficial effect is that the clustering method reflects the distribution characteristics of dust concentration. The dust deposition index and damage confidence of each uniform area are obtained, and its beneficial effect lies in the complexity and uniformity of the dust distribution inside the filter bag and the retrograde analysis. The chaotic characteristic analysis of the dust concentration in the area with uniform dust distribution reflects the characteristics of the dust distribution inside the filter bag, eliminates the influence of non-damaged filter bags, reflects the possibility of filter bag damage, and solves the problem of accuracy of filter bag damage detection. By mapping the matrix coordinates corresponding to the centroid of each uniform area and combining the damage confidence, the leaking bag is located, and the rapid positioning and alarm of the substantially damaged filter bag is realized, thereby improving the accuracy of leaking bag detection and positioning, and enhancing the automation level of broken bag positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a method for detecting bag leakage in a bag-type dust removal system provided in accordance with an embodiment of the present application; Figure 2 A cross-sectional view of a dust removal box provided in one embodiment of the present application, wherein 1 is a pulse dust removal device, 2 is an air inlet, 3 is a dust removal box, 4 is a data acquisition device, 5 is an air outlet, 6 is a filter bag, 7 is a partition, and arrows are air flow directions; Figure 3 A flowchart for obtaining damage confidence provided in one embodiment of the present application. DETAILED DESCRIPTION

[0017] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0019] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of protection of the present application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0021] The following is a detailed description of the specific scheme of the bag leakage positioning detection method and related equipment applicable to the bag dust removal system provided by the present application in conjunction with the accompanying drawings.

[0022] See also Figure 1 , which shows a flowchart of a method for detecting bag leakage positioning in a bag dust removal system provided by an embodiment of the present application, the method comprising the following steps: The first step: The dust concentrations at all preset locations in the dust removal box are combined into a dust concentration distribution matrix.

[0023] In order to accurately locate the leaking bag in the bag dust collector, laser dust concentration sensors are evenly installed above the dust box. Specifically, in this embodiment, a laser dust concentration sensor is installed every d meters horizontally and vertically on the top of the dust box to form a sensor matrix. The value of d is 0.1, and the implementer can adjust the interval of the installed sensors according to the actual situation. The laser dust concentration sensor mainly monitors the dust concentration in the air through the principle of light scattering. The sensor installation method in this embodiment is mainly significant in detecting dust particles from under the sensor. Since the change of dust concentration will occur on a smaller spatial scale in a closed system such as a bag dust collector, the distribution of dust may be uneven. Therefore, a denser sensor layout helps to capture these local changes, thereby locating the leaking bag more accurately.

[0024] The dust box is divided into two parts, the lower part, by the partition with filter bags installed. The lower part is the area where the dust-containing gas enters the dust collector and before it contacts the filter bags. Dust particles are captured by the filter bags in this part, and the clean gas enters the upper box through the filter bags. The upper part is the area where the clean gas after being filtered by the filter bags is located. After being purified by the filter bags, the gas will enter the upper box and then be discharged through the exhaust duct. The specific cross-sectional diagram of the dust box is shown as follows: Figure 2 As shown, Figure 2 It includes a pulse dust cleaning device 1, an air inlet 2, a dust removal box 3, a data acquisition device 4, an air outlet 5, a filter bag 6, and a partition 7. The arrows in the figure indicate the air flow direction.

[0025] The dust concentration is obtained using a dust concentration sensor. The obtained dust concentration is considered to be the average dust concentration within the monitoring range of the sensor. The dust concentrations detected by all sensors are linearly normalized and sorted according to the position order of the sensors to obtain a dust concentration distribution matrix.

[0026] The second step: Analyze the numerical distribution of all data points in the dust concentration distribution matrix, classify each data point in the matrix, and obtain a grade matrix; preset a sliding window, mark the uniform area based on the degree of data discreteness in the window when the sliding window moves in the grade matrix, and obtain a reset matrix.

[0027] Above the dust removal box, if the filter bag is not damaged, there should be no dust distribution in the upper box, that is, the dust concentration collected by all laser dust concentration sensors is 0. After the filter bag is damaged, dust particles will enter the upper box. Due to the fluidity of dust particles, each laser dust concentration sensor may collect dust concentration.

[0028] Since the laser dust concentration sensor is installed above the box, and the laser dust concentration sensor measures the gas concentration by emitting a laser beam of a specific wavelength and detecting its scattering or absorption in the air. When the laser beam passes through the gas, specific gas molecules will absorb or scatter the laser, changing the intensity or frequency of the beam. Since the laser has good penetration and directionality, it can detect the concentration data at a long distance below. If the filter bag is damaged, the dust will flow irregularly above the box because of its fluidity.

[0029] In order to analyze whether the concentration detection position is above the bag, the range of all data in the dust concentration distribution matrix is ​​calculated, and the dust concentration is graded using the reciprocal of the range as the step length. Specifically, the data points whose concentration is from the minimum value to the minimum value plus one step length have a concentration grade of 1, and the data points whose concentration is from the minimum value plus one step length to the minimum value plus two steps have a concentration grade of 2, and so on. All data points in the concentration distribution matrix are graded, and using the reciprocal of the range as the step length helps to more finely distinguish the dust concentration differences in different areas, so as to improve the sensitivity to changes in dust concentration, and the grades are used instead of the original data to obtain the grade matrix.

[0030] Assume that the cross-sectional diameter of the filter bag opening of the bag filter to be tested parallel to the top of the dust collector box is D, then the side length of the construction is A square sliding window, is a rounding function. It should be noted that, in this embodiment: , the sliding step of the sliding window in this embodiment is 1. It should be noted that the sliding step needs to be smaller than the side length of the sliding window, so that the subsequent acquisition of uniform areas is more accurate. The sliding window traverses the level matrix, and calculates the standard deviation of all data in the window each time the sliding window moves, and selects areas with a standard deviation of 0. The area with a standard deviation of 0 represents that the dust concentration of all data points in the area belongs to the same level. All areas with a standard deviation of 0 are recorded as uniform areas. It should be understood that the size of the uniform area is greater than or equal to the size of the sliding window. According to the position of the data point in the uniform area, the dust concentration of the data point at the corresponding position in the dust concentration distribution matrix is ​​defined as 0, and a reset matrix is ​​obtained to remove areas with uniform dust concentration distribution.

[0031] The movement and sedimentation of dust particles are affected by their particle size. Larger dust particles will settle quickly after being ejected from the orifice, while smaller particles may continue to be suspended in the air. Therefore, when the filter bag leaks, the larger dust particles will quickly settle near the leaking filter bag and will not enter the filter bag or be discharged.

[0032] The third step: cluster all the data in the reset matrix to obtain dust clusters; based on the distribution difference of dust concentration between each data point in the dust cluster and all data points, combined with the randomness of the data points in the preset neighborhood window, the dust accumulation factor of each data point in the dust cluster is obtained.

[0033] When there is no leakage in the filter bag, the data points in the dust concentration distribution matrix should all be 0. If there is a leakage in the filter bag, there are three areas in the dust concentration distribution matrix, namely, non-uniform areas with less dust content, non-uniform areas with dust deposition, and uniform areas. Based on this, the reset matrix is ​​used as input, the K-means clustering algorithm is used, the K value is set to 3, and three clusters are output, representing the three areas respectively. In the three areas, the more dust particles, the higher the dust concentration. Therefore, the dust concentration value in the non-uniform area with dust deposition is generally greater than that in another non-uniform area. Calculate the mean dust concentration within each cluster, and sort the mean in ascending order. The cluster with the largest mean is recorded as the dust cluster.

[0034] The ratio of the dust concentration of each data point in the dust cluster to the average dust concentration in the dust cluster is taken as the concentration ratio, denoted as a; and each data point in the dust cluster is taken as the center to create a A neighborhood window, in this embodiment, N is taken as 5, and the data points in the window are taken as input. The grayscale run matrix algorithm is used to output the run entropy in the neighborhood window of each data point, which is recorded as b.

[0035] Calculate the dust accumulation factor A for each data point in the dust cluster. The specific calculation formula is: Specifically, a represents the intensity of each data point in the dust cluster relative to the average dust concentration of the entire dust cluster. The larger the value of a, the higher the average dust concentration of the data point relative to the dust cluster. At this time, the possibility that the data point represents dust accumulation is higher, and the A value is larger; b quantifies the randomness and complexity of the dust concentration distribution in the neighborhood window of the data point. The smaller its value is, the more uniform the dust concentration distribution in the window is. At this time, the possibility that the data point is caused by dust deposition is greater, and the A value is larger.

[0036] It should be understood that the dust accumulation factor describes the degree of accumulation of each data point in the dust cluster caused by dust deposition. The larger the value, the higher the possibility that the data point belongs to dust deposition, thereby quantitatively evaluating the dust accumulation.

[0037] The fourth step: Analyze the difference in dust concentration distribution between each uniform area and the dust cluster, and the chaotic characteristics of dust concentration in each uniform area, and obtain the dust deposition index of each uniform area.

[0038] Since the leaking filter bag allows dust to pass through, there is sedimentation and accumulation of large-size dust inside it, resulting in a higher dust concentration. The local accumulation caused by dust penetration makes the dust concentration distribution in the leakage area more uneven. In order to analyze the characteristics of increased dust concentration caused by the sedimentation of dust particles in all filter bags, the dust deposition index of each uniform area is obtained based on the difference characteristics of the dust concentration distribution in each uniform area and the dust cluster, combined with the degree of chaos of the dust concentration distribution in each uniform area: the difference c between the mean dust concentration in each uniform area and the mean dust concentration in the dust cluster is calculated, and the dust concentration entropy value d of all data points in each uniform area is calculated. The dust deposition index of each uniform area is recorded as B, and its formula form is: ; Among them, max() represents the maximum value function.

[0039] It should be understood that c reflects the degree of deviation of the dust concentration inside the uniform area from the average level of the dust cluster. When its value is greater than 0, it means that there are data points inside the uniform area that are greater than the dust concentration in the dust cluster, that is, the dust concentration in the uniform area is greater than the dust concentration in the dust cluster; d is used to quantify the degree of disorder of the distribution of data points in the uniform area. The larger the d value, the more obvious the dust sedimentation phenomenon in the uniform area, the higher the possibility of damage, and the larger B; similarly, when c is less than 0, it means that the dust sedimentation phenomenon in the uniform area is less obvious, and there is almost no possibility of damage. At this time, B takes a value of 0. The dust deposition index is used to describe the possibility of damage to the uniform area. The larger its value, the more significant the difference between the dust sedimentation and dust concentration changes in the area and the normal situation, that is, the higher the possibility of damage to the uniform area.

[0040] Due to the dynamic influence of dust flow and deposition, dust flow will also occur above the filter bag mouth that has not been damaged, resulting in changes in dust concentration and irregular dust concentration distribution in the dust concentration distribution matrix. Since the dust accumulation factor can quantitatively evaluate the degree of accumulation of dust settling around the uniform area, and the dust deposition index can reflect the complexity of dust distribution inside the uniform area, the combination of the two can comprehensively evaluate whether there is damage to the bag in the uniform area and make an assessment of the dust concentration detection. Analyze the distance between each uniform area and all data points in the dust cluster, and combine the dust accumulation factor and the dust deposition index to obtain the damage confidence of each uniform area. The specific calculation relationship is: ; represents the damage confidence of the i-th uniform area; It represents the shortest Euclidean distance between the kth data point and the ith uniform area in the dust cluster, which measures the spatial relationship between the data point k and the uniform area. The larger the value, the farther the data point k is from the selected uniform area. Its negative exponential function The closer it is to 0, the smaller the weight given to data points that are farther away from the selected uniform area; Indicates the dust accumulation degree of the kth data point in the dust cluster. The larger its value is, the higher the possibility that the data point represents dust accumulation is. and The product of is summed up, and the summed result represents the weight factor of dust accumulation around the uniform area. The larger the summed result, the heavier the dust accumulation around the selected uniform area, and the higher the damage confidence of the selected uniform area. It represents the dust deposition index of the ith uniform area. It characterizes the possibility of damage to the selected uniform area through the dust distribution inside the uniform area. The larger the value, the higher the possibility of bag damage in the uniform area. K represents the total number of data points in the dust cluster.

[0041] The damage confidence is used to describe the possibility of damage in a uniform area. The larger the value, the higher the possibility of damage in the uniform area. The flow chart for obtaining the damage confidence is as follows: Figure 3 shown.

[0042] The fifth step is to map the matrix coordinates corresponding to the centroid of each uniform area, and locate the leaking bag in combination with the damage confidence.

[0043] In order to determine whether the uniform area belongs to the real filter bag area, the proportional position in the dust concentration distribution matrix is ​​calculated according to the regional center of each uniform area, that is, the average value of the coordinates of all data points in the uniform area in the corresponding area of ​​the dust concentration distribution matrix. The horizontal coordinate of the proportional position is the ratio of the horizontal coordinate of the regional center to the matrix width, and the vertical coordinate is the ratio of the vertical coordinate of the regional center to the matrix length; according to the proportional position, the position in the matrix is ​​mapped to the actual filter bag position to determine whether the center falls on the actual filter bag. If so, the uniform area is marked, if not, no operation is performed. Based on the above method, all uniform areas are traversed to obtain all marked uniform areas and record them as marked areas.

[0044] Based on the damage confidence of all marked areas, the damage threshold is set to 0.8. When the damage confidence of the marked area is greater than the damage threshold, it is determined that the filter bag in the marked area is actually damaged. At this time, the filter bag with actual damage is located according to the proportional position of the center point of the marked area that exceeds the threshold, and the sound and light alarm is controlled to sound an alarm to remind the operator how to check and replace it.

[0045] Based on the same inventive concept as the above method, an embodiment of the present application also provides a bag leakage positioning detection device suitable for a bag dust removal system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned bag leakage positioning detection methods suitable for a bag dust removal system are implemented.

[0046] In summary, the embodiment of the present application forms a dust concentration distribution matrix with the dust concentrations of all preset positions in the dust collector, which can comprehensively reflect the spatial distribution of the dust concentration inside the dust collector, and help to identify possible bag leakage areas by comparing the dust concentration changes at different positions in the future; obtaining a grade matrix, marking uniform areas, and obtaining a reset matrix are helpful to divide the dust concentration grades, obtain filter bag areas with uniform concentration distribution, and separate areas with uniform dust concentration distribution, and analyze areas with uneven dust concentration distribution, i.e., non-filter bag areas; clustering all data in the reset matrix to obtain dust clusters, and obtaining the dust accumulation factor of each data point in the dust cluster, and its beneficial effect is that the clustering method reflects the classification of dust concentration. The dust distribution characteristics are used to solve the problem of dust distribution and sedimentation in non-filter bag areas; further, the dust deposition index and damage confidence of each uniform area are obtained, and its beneficial effect lies in the complexity and uniformity of the dust distribution inside the filter bag and the retrograde analysis. The chaotic characteristics of dust concentration in the dust distribution uniform area are analyzed to reflect the characteristics of dust distribution inside the filter bag, eliminate the influence of non-damaged filter bags, reflect the possibility of filter bag damage, and solve the problem of accuracy of filter bag damage detection. By mapping the matrix coordinates corresponding to the centroid of each uniform area and combining the damage confidence, the leaking bag is located, and the rapid positioning and alarm of the substantially damaged filter bag is realized, the accuracy of leaking bag detection and positioning is improved, and the automation level of broken bag positioning is enhanced.

[0047] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two continuous operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0048] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; the technical solutions recorded in the above embodiments are modified, or some of the technical features are replaced by equivalents, which does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A bag leak detection method applicable to a bag dust removal system, characterized in that: The method comprises the following steps: The dust concentrations at all preset positions in the dust removal box form a dust concentration distribution matrix; Analyze the numerical distribution of all data points in the dust concentration distribution matrix, classify each data point in the matrix, and obtain a grade matrix; preset a sliding window, and based on the degree of data dispersion in the window when the sliding window moves in the grade matrix, mark the uniform area and obtain a reset matrix; Cluster all data in the reset matrix to obtain dust clusters; obtain the dust accumulation factor of each data point in the dust cluster based on the distribution difference of dust concentration between each data point in the dust cluster and all data points, combined with the randomness of the data point in the preset neighborhood window; Analyze the difference in dust concentration distribution between each uniform area and the dust cluster, and the chaotic characteristics of dust concentration in each uniform area, and obtain the dust deposition index of each uniform area; analyze the distance between each uniform area and all data points in the dust cluster, and combine the dust accumulation factor and the dust deposition index to obtain the damage confidence of each uniform area; The coordinates of the center of each uniform area in the corresponding area of ​​the dust concentration distribution matrix are mapped, and the leaking bag is located in combination with the damage confidence.

2. The bag leak detection method for bag dust removal system according to claim 1, characterized in that: The specific process of classifying each element of the matrix is ​​as follows: The negative correlation mapping result of the extreme value of all data points in the dust concentration distribution matrix is ​​used as the step size of the grade division; the minimum data point of the dust concentration distribution matrix is ​​used as the starting value of the grade division to obtain the grade division interval, and the corresponding concentration level is assigned to each data point in the matrix; The matrix consisting of the concentration levels of all data points is used as the level matrix.

3. The bag leak detection method for bag dust removal system according to claim 1, characterized in that: The process of marking the uniform area is specifically as follows: Calculate the standard deviation of all data in the sliding window each time it moves in the rank matrix, and filter all areas where the standard deviation is equal to 0 to obtain uniform areas.

4. The bag leak detection method for bag dust removal system according to claim 1, characterized in that: The reset matrix is ​​specifically a dust concentration distribution matrix in which the data points at the corresponding positions of the uniform area are 0.

5. The bag leak detection method applicable to the bag dust removal system according to claim 1, characterized in that: The specific process of clustering all the data in the reset matrix to obtain dust clusters is as follows: A preset number of clusters are obtained; the dust concentration mean of all data points in each cluster is calculated and recorded as the dust concentration within the cluster; and the cluster with the largest dust concentration within the cluster is taken as the dust cluster.

6. The bag leak detection method applicable to the bag dust removal system according to claim 1, characterized in that: The dust accumulation factor of each data point in the dust cluster includes: Calculate the dust concentration average of all data points in the dust cluster; compare the dust concentration of each data point in the dust cluster with the dust concentration average to obtain the concentration ratio of each data point in the dust cluster; The grayscale run matrix algorithm is used to obtain the run entropy of each data point in the neighborhood window; Based on the concentration ratio and the run entropy, a dust accumulation factor of each data point in the dust cluster is obtained; wherein the dust accumulation factor is positively correlated with the concentration ratio and negatively correlated with the run entropy.

7. The bag leak detection method applicable to the bag dust removal system according to claim 1, characterized in that: The dust deposition index of each uniform area is obtained as follows: The difference between the mean dust concentration in each uniform area and the mean dust concentration in the dust cluster is calculated; the maximum value between the difference and 0 is obtained; the maximum value corresponding to each uniform area is merged with the dust concentration entropy value of all data points in the area to obtain the dust deposition index of each uniform area.

8. The bag leak detection method applicable to a bag dust removal system according to claim 1, characterized in that: The formula for obtaining the damage confidence of each uniform area is: ; represents the damage confidence of the i-th uniform area; represents the shortest Euclidean distance between the kth data point and the ith uniform region in the dust cluster, and e represents a natural constant; Indicates the dust accumulation degree of the kth data point in the dust cluster; represents the dust deposition index of the ith uniform area; K represents the total number of data points in the dust cluster.

9. The bag leak detection method applicable to a bag dust removal system according to claim 1, characterized in that: The specific process of positioning the leaking bag is as follows: Obtain the area corresponding to the dust distribution matrix, recorded as the distribution area; calculate the average coordinates of all data points in each uniform area in the distribution area to obtain the coordinates of the center of the area; Obtaining the proportional position of the regional center of each uniform region in the dust concentration distribution matrix, wherein the abscissa of the proportional position is the ratio of the abscissa of the regional center to the matrix width, and the ordinate is the ratio of the ordinate of the regional center to the matrix length; According to the proportional position, the center of each uniform area is mapped to the actual dust removal box position. If the center of the area falls into the filter bag position, the corresponding uniform area is marked and recorded as the marked area. When the damage confidence of the marked area is greater than a preset damage threshold, the area center corresponding to the marked area is determined to be the location of the damaged filter bag.

10. A bag leak detection device for a bag dust removal system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images