Online monitoring method and device for laser drilling quality of tipping paper

Abstract

The invention belongs to the technical field of tipping paper drilling, and particularly discloses an online monitoring method and device for tipping paper laser drilling quality, and the method comprises the steps: selecting a standard single-hole image corresponding to tipping paper to be detected, and obtaining the standard single-hole image through taking and segmenting a standard single hole; under the same shooting condition, performing roll-by-roll image taking on the to-be-detected tipping paper placed at the paper feeding position of the imaging system to obtain a to-be-detected porous image of each roll of the to-be-detected tipping paper; based on the shape of the standard single hole, identifying a target single hole at a specified position in the single-frame to-be-detected porous image, performing translation transformation on the single-frame to-be-detected porous image based on the target single hole, and aligning different frames of to-be-detected porous images; performing hole-by-hole identification on the to-be-detected multi-hole image, and counting direct evaluation hole parameters based on a hole-by-hole identification result; comparing the hole-by-hole identification result with a standard single-hole image, and counting indirect evaluation hole parameters; and the counted direct evaluation hole parameters and indirect evaluation hole parameters are sent to a laser drilling controller to adjust a drilling strategy.

Description

Technical Field

[0001] The present application belongs to the technical field of tipping paper punching, and more specifically, to an online monitoring method and device for the quality of tipping paper laser punching. Background Art

[0002] Tipping paper pattern holes are holes with specific shapes and arrangements punched on the tipping paper of cigarette filters to improve the air permeability of cigarette tipping paper, thereby reducing the concentration of tar in smoke when smoking. Laser drilling has gradually become the mainstream solution for tipping paper drilling due to its advantages such as cleanliness, reliability, wide range of air permeability of punching results, and high production efficiency.

[0003] Online monitoring of the quality of drilling during the laser drilling process is an important means to improve production efficiency, ensure product quality, reduce production costs, and enhance the level of intelligence. In related technologies, the area of ​​the small holes is calculated by capturing the image of the small holes in the laser drilling of the tipping paper, and then a simple proportional relationship is established with the known air permeability value to complete the air permeability detection of the drilling results. However, this method uses the mapping relationship between the hole area and air permeability of the tipping paper to perform air permeability detection, and can only measure the air permeability of the drilling results as a whole. Summary of the invention

[0004] In view of the above-mentioned defects in the prior art, the present application provides a method and device for online monitoring of the quality of laser punching of tipping paper, aiming to solve the problem of online monitoring of the quality of laser punching of tipping paper.

[0005] In a first aspect, the present application provides an online monitoring method for the laser drilling quality of tipping paper, comprising: Select a standard single-hole image corresponding to the tipping paper to be tested, the standard single-hole image is obtained by taking an image and performing image segmentation on the standard single hole; Under the same shooting conditions, the tipping paper to be tested placed at the paper feeding position of the imaging system is taken up roll by roll, and the porous image to be tested of each roll of the tipping paper to be tested is obtained; Based on the shape of the standard single hole, the target single hole at the specified position in the single frame of the multi-hole image to be tested is identified, and the single frame of the multi-hole image to be tested is translated based on the target single hole, so as to align the multi-hole images in different frames; Perform hole-by-hole identification on the multi-hole images to be tested, and directly evaluate the hole parameters based on the statistics of the hole-by-hole identification results; compare the hole-by-hole identification results with the standard single-hole images, and indirectly evaluate the hole parameters based on statistics; The statistical direct evaluation hole parameters and indirect evaluation hole parameters are sent to the laser drilling controller to adjust the drilling strategy.

[0006] In a second aspect, the present application also provides an online monitoring device for the laser drilling quality of tipping paper, comprising: A standard selection module is used to select a standard single-hole image corresponding to the tipping paper to be tested, and the standard single-hole image is obtained by taking an image and performing image segmentation on the standard single hole; An image acquisition module is used to take images of the tipping paper to be tested placed at the paper feeding position of the imaging system roll by roll under the same shooting conditions, and obtain the porous images to be tested of each roll of the tipping paper to be tested; An image alignment module is used to identify a target single hole at a specified position in the multi-hole image to be tested based on the shape of a standard single hole, and to perform a translation transformation on the multi-hole image to be tested based on the target single hole, so as to align the multi-hole images to be tested in different frames; The hole parameter statistics module includes a first statistics unit and a second statistics unit, wherein the first statistics unit is used to perform hole-by-hole identification on the multi-hole image to be tested, and directly evaluate the hole parameters based on the statistics of the hole-by-hole identification results; the second statistics unit is used to compare the hole-by-hole identification results with the standard single-hole image, and indirectly evaluate the hole parameters based on statistics; The hole parameter sending module is used to send the statistical direct evaluation hole parameters and indirect evaluation hole parameters to the laser drilling controller to adjust the drilling strategy.

[0007] In a third aspect, the present application also provides an electronic device, comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any possible implementation of the first aspect.

[0008] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0009] In a fifth aspect, the present application further provides a computer program product, which, when executed on a processor, enables the processor to execute the method described in the first aspect or any possible implementation manner of the first aspect.

[0010] The online monitoring method and device for the laser drilling quality of tipping paper provided in the present application facilitate the consistency comparison between the multi-hole image to be tested and the standard single-hole image of the tipping paper to be tested by pre-selecting a standard single-hole image, standardizing shooting conditions and automatically aligning each frame of the image; the multi-hole image to be tested is identified and directly measured hole by hole, and the hole-by-hole identification results are compared with the standard single-hole image, and the hole parameters are directly evaluated and indirectly evaluated. The laser drilling quality of the tipping paper is comprehensively monitored online from different dimensions of direct measurement and standard comparison. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 It is a flow chart of an online monitoring method for the laser drilling quality of tipping paper provided in an embodiment of the present application; Figure 2 This is a sample schematic diagram of laser punching of tipping paper provided in an embodiment of the present application; Figure 3 is a schematic diagram of the operation of selecting a standard single hole image provided in an embodiment of the present application; Figure 4 is a schematic diagram of the structure of a standard lighting metering board provided in an embodiment of the present application; Figure 5 is a display schematic diagram of automatic frame alignment provided by an embodiment of the present application; Figure 6 It is a display schematic diagram of the hole line deviation measurement provided in the embodiment of the present application; Figure 7 is a schematic diagram of automatic measurement of hole parameters provided in an embodiment of the present application; Figure 8 It is a structural schematic diagram of an online monitoring device for the laser drilling quality of tipping paper provided in an embodiment of the present application; Fig. 9 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] Figure 1 is a flow chart of an online monitoring method for the laser drilling quality of tipping paper provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises at least the following steps: S101, selecting a standard single-hole image corresponding to the tipping paper to be tested; S102, under the same shooting conditions, taking up images of the tipping paper to be tested placed at the paper feeding position of the imaging system roll by roll, and obtaining a porous image of each roll of the tipping paper to be tested; S103, based on the shape of the standard single hole, identifying the target single hole at the specified position in the single frame of the multi-hole image to be tested, and performing a translation transformation on the single frame of the multi-hole image to be tested based on the target single hole, so as to align the multi-hole images of different frames to be tested; S104, performing hole-by-hole identification on the multi-hole image to be tested, and directly evaluating hole parameters based on the hole-by-hole identification results; comparing the hole-by-hole identification results with the standard single-hole image, and indirectly evaluating the hole parameters based on the statistics; S105 , sending the statistically directly evaluated hole parameters and indirectly evaluated hole parameters to the laser drilling controller to adjust the drilling strategy.

[0015] For S101, a standard single-hole image corresponding to the tipping paper to be tested is pre-selected as a control group for taking images of the tipping paper to be tested during the online monitoring of the laser drilling quality of the tipping paper. This can detect the consistency between the actual graphic holes of the tipping paper and the standard graphic holes in terms of size and shape. At the same time, the pre-selected standard single-hole image remains consistent during the monitoring process, avoiding subjective differences caused by real-time selection by operators during the monitoring process.

[0016] Figure 2 Schematic diagram of a sample of laser punching of tipping paper provided in the embodiment of the present application. Figure 2 As shown, the tipping paper 1 is used as the outer packaging paper of the filter tip of the cigarette. Through laser punching technology, a plurality of evenly arranged graphic holes 2 are punched on the tipping paper 1. The shapes of the graphic holes 2 can be various shapes such as circle, ellipse, star, polygon, etc.

[0017] The standard single hole image is obtained by taking an image and performing image segmentation on the standard single hole. Figure 3 is a schematic diagram of the operation of selecting a standard single hole image provided in an embodiment of the present application, such as Figure 3 As shown, standard single-hole images of different specifications and shapes are pre-saved in the system to serve as a control group when the quality of laser drilling of cork paper is monitored online. The operator selects the standard single-hole image from the database through the mouse icon 3. The standard single-hole image is obtained by taking an image of the standard single hole 4 and performing image segmentation.

[0018] Optionally, a picture of the standard perforated tipping paper that has been certified for quality is taken, and an operator enlarges and manually determines the picture-taking result, selects a standard single hole and performs image segmentation to obtain a standard single hole image and store it in the system.

[0019] Optionally, the perforated tipping paper is imaged, and an operator amplifies and manually determines the image results, selects a standard single hole that meets the quality standards, performs image segmentation, obtains a standard single hole image, and stores it in the system.

[0020] Optionally, the image segmentation adopts minimum circumscribed rectangle segmentation, or outer contour segmentation based on the outer contour of the graphic hole.

[0021] For S102, under the same shooting conditions as the standard single-hole imaging, the tipping paper to be tested placed at the paper feeding position of the imaging system is imaged roll by roll, and the multi-hole images to be tested of each roll of tipping paper to be tested that has completed laser drilling are obtained as the basis for the laser drilling quality inspection of the tipping paper.

[0022] Specifically, the same shooting conditions refer to a series of fixed environments and parameters set for comparative analysis, including the same lighting conditions, the same shooting equipment, the same exposure parameters, the same placement of the object, the same shooting angle and composition, etc.

[0023] In some embodiments, the online monitoring method for the laser drilling quality of tipping paper further includes: Based on the preset transmittance, the standard perforated tipping paper is imaged regularly to obtain a reference image; Performing brightness detection on the reference image, and verifying the attenuation degree of the brightness of the light source based on the brightness detection result; If the brightness of the light source decays, the light source controller is controlled to adjust the brightness of the light source to maintain a preset transmittance.

[0024] Specifically, a high-speed camera is generally set just above the paper feeding position of the imaging device to take images of the tipping paper to be tested. A parallel light source is set just below the paper feeding position. During operation, the parallel light source is used to illuminate the tipping paper to be tested, and at the same time, the high-speed camera is used to capture the porous image of the tipping paper to be tested.

[0025] The online monitoring of the quality of laser drilling of cork paper requires very high precision in the measurement of hole parameters, which largely depends on the accuracy and stability of optical detection equipment. Due to the influence of factors such as aging, poor heat dissipation, and dust pollution during the use of the light source, the brightness of the light source may decay. The attenuation of the light source brightness makes it impossible to meet the high consistency of the light conditions during the monitoring process, resulting in deviations in the measurement results of the hole parameters. Therefore, it is necessary to regularly detect the attenuation degree of the light source brightness and standardize the light source brightness during the monitoring process.

[0026] Figure 4 is a schematic diagram of the structure of a standard lighting metering board provided in an embodiment of the present application, such as Figure 4 As shown, a standard perforated tipping paper that has been certified for quality is placed between two pieces of high-transmittance glass through a glass sample clamp 12 and placed at the paper feeding position of the imaging system. The lighting source is tested and calibrated for stability offline to ensure that each roll of tipping paper to be tested is under the same lighting conditions.

[0027] Specifically, the system presets the transmittance, takes an image of the standard perforated tipping paper placed at the paper feeding position of the imaging system, and obtains the reference image; performs brightness detection on the reference image, compares the brightness detection result with the standard brightness value, and verifies the attenuation degree of the light source; if the difference between the brightness detection result and the standard brightness value exceeds the system error, it means that the light source is attenuated, and the actual transmittance provided by the light source fails to reach the transmittance set by the system, and controls the light source controller to adjust the light source brightness to maintain the preset transmittance. If necessary, replace the light source.

[0028] For S103, based on the shape of the standard single hole, the target single hole at the specified position in the single frame of the multi-hole image to be tested is identified, and the single frame of the multi-hole image to be tested is translated based on the target single hole to align different frames of multi-hole images to be tested.

[0029] Figure 5 is a display schematic diagram of automatic frame alignment provided by an embodiment of the present application, such as Figure 5 As shown, during the laser drilling process of tipping paper, due to the continuity of the production line and the accuracy limitations of the punching equipment, there are differences between the actual punching positions and the standard punching positions on different rolls of tipping paper to be tested, and this difference needs to be detected; at the same time, the image taking speed of the tipping paper to be tested placed at the paper feeding position of the imaging system by the high-speed camera and the roll changing speed of the tipping paper to be tested may not be completely matched, resulting in large differences in the display positions of the graphic holes in different frames of the porous images to be tested. The purpose of frame alignment is to eliminate the display differences so that different frames of the porous images to be tested remain visually approximately consistent, which is convenient for subsequent analysis, processing and quality monitoring.

[0030] Specifically, based on the shape of the standard single hole, the target single hole at the specified position in the single-frame multi-hole image to be tested is identified. Figure 5 For example, the first graphic hole in the first row on the left is identified as the target single hole, and the target single hole of the different frames of the multi-porous images to be tested is displayed at the specified display position (for example, the display position of the first graphic hole in the first row on the left in the first frame of the multi-porous image to be tested) through translation operation, so that the frames of the different frames of the multi-porous images to be tested are aligned, and the different frames of the multi-porous images to be tested are approximately stationary when displayed, which is convenient for hole parameter measurement and process parameter adjustment.

[0031] For S104, the multi-hole image to be tested is identified hole by hole, and the hole parameters are directly evaluated based on the hole by hole identification result statistics; the hole by hole identification result is compared with the standard single hole image, and the hole parameters are indirectly evaluated based on the statistics.

[0032] Directly evaluated pore parameters refer to pore parameters obtained by directly measuring or evaluating the multi-pore image to be tested; indirectly evaluated parameters refer to pore parameters obtained by calculating or evaluating after comparing the multi-pore image to be tested with the standard single-pore image.

[0033] In some embodiments, the hole parameters directly evaluated are hole spacing, hole margin, hole line deviation, etc. The hole spacing, hole margin and hole line deviation can all be used to measure the hole position deviation of the tipping paper laser punching. Accordingly, the hole parameters are directly evaluated based on the hole-by-hole recognition result statistics in S104, specifically including: Determine the centroid coordinates of the graphic holes in the multi-hole image to be tested by a centroid fitting algorithm; The centroid coordinates of the graphic holes are grouped according to the hole lines, and the hole line equation of the corresponding hole line is fitted using each group of centroid coordinates; The hole spacing, hole edge distance or hole line deviation is calculated based on the hole line equation.

[0034] Specifically, the centroid coordinates of all the graphic holes in the porous image to be tested are determined by a centroid fitting algorithm. The centroid coordinates of a single graphic hole can be calculated by all pixel coordinates of the single graphic hole, or, since the graphic holes of the tipping paper generally adopt a regular pattern, the centroid coordinates of a single graphic hole can also be calculated by the pixel coordinates of the outline of the single graphic hole.

[0035] All the graphic holes on the cork paper are arranged regularly, and the centroid coordinates of all the graphic holes in the porous image to be tested are grouped, and each group of coordinates corresponds to a hole line. Figure 2 For example, there are 2 rows and 6 columns of graphic holes regularly arranged on the cork paper. The centroid coordinates of a row of graphic holes correspond to one hole line, and the centroid coordinates of a column of graphic holes correspond to one hole line.

[0036] The hole line equation Fn (n is the hole line number) of the corresponding hole line is fitted using each group of centroid coordinates through the least square method or other fitting algorithms. The hole line equation Fn is used as the measurement basis for directly evaluating hole parameters such as hole spacing, hole margin and hole line deviation.

[0037] In some embodiments, calculating the hole spacing based on the hole line equation includes: The distance between the hole line equations of the parallel hole lines where the adjacent graphic holes are located is determined as the hole spacing between the adjacent graphic holes.

[0038] Specifically, the hole spacing refers to the distance between two adjacent graphic holes on the tipping paper. The accuracy of the hole spacing directly reflects the fineness of the laser drilling of the tipping paper. If there is a large difference between the actual hole spacing and the standard hole spacing, it means that there is a deviation or misalignment when the tipping paper is laser punched; uneven hole spacing will affect the air permeability and overall structure of the tipping paper.

[0039] The hole spacing can be directly calculated by the centroid coordinates of adjacent graphic holes. Considering that there are multiple regularly arranged graphic holes on the tipping paper, it takes multiple calculations to calculate the hole spacing between adjacent holes one by one using the centroid coordinates, and it is difficult to describe the arrangement of the graphic holes of a single roll of tipping paper to be tested as a whole. Therefore, in the embodiment of the present application, the distance between the hole lines is used to measure the hole spacing, and the distance between the hole line equations of the parallel hole lines where the adjacent graphic holes are located is used as the hole spacing between the adjacent graphic holes.

[0040] by Figure 2 For example, the standard hole spacing between adjacent graphic holes in rows is d1, and the standard hole spacing between graphic holes in columns is a. If the error between the distance calculated by the hole line equation of adjacent row hole lines and d1 exceeds the threshold, it is considered that the row arrangement quality of the graphic holes is low, and an out-of-tolerance alarm is issued; if the error between the distance calculated by the hole line equation of adjacent column hole lines and a exceeds the threshold, it is considered that the column arrangement quality of the graphic holes is low, and an out-of-tolerance alarm is issued.

[0041] In some embodiments, calculating the hole margin distance based on the hole line equation includes: The distance between the hole line equation of the edge hole line where the edge graphic hole in the porous image to be tested is located and the straight line equation of the edge of the tipping paper is determined as the hole margin distance.

[0042] The straight line equation of the tipping paper edge is obtained by edge tracking of the porous image to be tested.

[0043] Specifically, in addition to the hole spacing, the hole margin is also an important indicator to measure the quality of laser punching of tipping paper. The hole margin refers to the distance from the graphic hole to the edge of the tipping paper. If the hole margin is too small, it will destroy the structural strength of the tipping paper.

[0044] The edge tracking algorithm can be used to obtain the straight line equation of the tipping paper edge in the porous image to be tested, and the distance between each hole line equation and the straight line equation of the tipping paper edge can be calculated as the hole margin distance between the graphic holes on each hole line and the tipping paper edge to be tested.

[0045] Generally speaking, the edge pattern holes and the hole margins of the tipping paper directly affect the structural strength of the tipping paper. In order to reduce the calculation complexity, only the edge pattern holes and the hole margins of the tipping paper can be calculated.

[0046] It requires multiple calculations to calculate the hole margin of each hole using the centroid coordinates of the edge graphic hole and the straight line equation of the paper edge of the cork paper, and it is difficult to measure the distance deviation between the edge graphic hole and the paper edge as a whole. Therefore, the distance between the hole line equation of the edge hole line where the edge graphic hole in the multi-porous image to be tested is located and the straight line equation of the paper edge is used as the hole margin.

[0047] Furthermore, combined with Figure 5It can be seen that, through the consistent setting of shooting conditions and frame alignment operation, after taking pictures of different rolls of tipping paper to be tested, the paper edge of the tipping paper to be tested should be displayed in the same position, that is, the paper edge straight line equation can be used in the monitoring process of different rolls of tipping paper to be tested without repeated calculation. At the same time, the paper edge straight line equation of the tipping paper in different frames of the porous image to be tested can be regularly calculated by edge tracking to correct the paper edge straight line equation.

[0048] In some embodiments, calculating the hole line deviation based on the hole line equation includes: The hole line equation of the target hole line in the multi-hole image to be tested is compared with the preset standard hole line equation to determine the hole line deviation.

[0049] Specifically, the hole line deviation is used to measure the deviation between the actual position and the standard position of the hole after the tipping paper is punched. The hole line deviation will lead to uneven distribution of the air permeability of the tipping paper. If the deviation is too large, it may destroy the structural integrity of the tipping paper and affect the accuracy of the anti-counterfeiting mark of the tipping paper.

[0050] Since the alignment operation is performed on the porous images to be tested in different frames in S103, each graphic hole in the porous image to be tested is displayed at the standard position or near the standard position. Therefore, the hole line equation of the target hole line can be calculated by the centroid coordinates of the graphic hole, and then the actual hole line equation of the target hole line is compared with the preset standard hole line equation to obtain the hole line deviation. If the hole line deviation exceeds the threshold, an alarm is issued.

[0051] Figure 6 is a schematic diagram showing the hole line deviation measurement provided in the embodiment of the present application, such as Figure 6 As shown, through the frame alignment operation, each graphic hole in the multi-hole image to be tested is displayed at or near the standard position. Figure 6 The middle right side is a schematic diagram of the standard hole line of each target hole line. By comparing the hole line equation of the target hole line with the standard hole line equation of the standard hole line, the occurrence of hole position deviation can be effectively prevented.

[0052] In some embodiments, directly evaluating the hole parameters includes single hole area, multi-hole area and hole number. S104 directly evaluates the hole parameters based on hole-by-hole identification result statistics, specifically including: Based on the hole-by-hole recognition results, single-hole segmentation is performed, and the images of the single holes to be tested are obtained hole by hole and the number of holes is determined; The single hole area in the single hole image to be tested is determined by binarization processing, and the multi-hole area is calculated based on the single hole area statistics.

[0053] Specifically, the size of a single hole area directly affects the air permeability and structural strength of the tipping paper; the size and distribution stability of the multi-porous hole area affect the air permeability stability and the overall strength and wear resistance of the tipping paper; the number and uniform distribution of holes also affect the air permeability of the tipping paper.

[0054] The multi-hole image to be tested is identified hole by hole and single hole segmented, and multiple single hole images to be tested are obtained while the number of holes is determined. Alternatively, the multi-hole image to be tested is identified hole by hole and then single hole regions are marked, and the number of holes is determined and multiple single hole regions are obtained and marked. Then, the area of ​​each single hole is further counted by binarization processing, and the multi-hole area is calculated based on the single hole area. The multi-hole area can be the hole area of ​​the multi-hole in a specified row or column, or the hole area of ​​all holes.

[0055] In some embodiments, the indirect evaluation parameters include the hole shape similarity, and the indirect evaluation hole parameters are statistically evaluated in S104, specifically including: Based on the hole-by-hole recognition results, single-hole segmentation is performed, and images of single-holes to be tested are obtained hole by hole; The SSIM algorithm is used to compare the structural similarity of the single hole image to be tested with the standard single hole image hole by hole, and the hole shape similarity between each graphic hole in the multi-hole image to be tested and the standard single hole is counted.

[0056] Specifically, the hole shape similarity refers to the degree of match between the actual punching situation and the preset standard hole. If the hole shape similarity of a single hole is low, that is, the holes are of different shapes and sizes, the air permeability of the tipping paper will be uneven; if the hole shape of a single hole is irregular or there are defects such as jagged edges, cracks, burrs, etc., the overall structural strength of the tipping paper will decrease.

[0057] The multi-hole images to be tested are identified hole by hole, and single hole segmentation is performed based on the hole-by-hole identification results. The single hole images to be tested can be obtained hole by hole. The single hole images to be tested are compared with the standard single hole images, and the hole shape similarity between the actual single hole and the preset standard single hole can be obtained.

[0058] Optionally, the structural similarity index (SSIM) is used to measure the hole shape similarity between the single hole image to be tested and the standard single hole image. SSIM evaluates the hole shape similarity by comparing the brightness, contrast and structural similarity between the single hole image to be tested and the standard single hole image.

[0059] Assume that the standard single hole image is T, and the size of T is the maximum circumscribed rectangle of the standard single hole; the single hole image to be tested is ti (i is the hole number), and the size of ti is the maximum circumscribed rectangle of the single hole to be tested. The hole shape similarity f between the single hole image to be tested ti and the standard single hole image T is expressed as: f=SSIM(T,ti). In a possible implementation, f>0.95 is considered to be strongly similar to the single hole image to be tested and f<0.9 is considered to be extremely dissimilar to the single hole image to be tested and the standard single hole image.

[0060] Furthermore, the indirect evaluation parameters also include hole incompleteness. The indirect evaluation hole parameters are statistically evaluated in S104, and specifically include: If the hole shape similarity is lower than a preset threshold, it is determined that the single hole is defective; If the hole shape similarity is higher than the preset threshold, the centroid coordinates of the single hole image to be tested and the standard single hole image are aligned, and a polar coordinate system is established with the aligned centroid as the origin; the edge detection algorithm is used to detect the contour to be tested of the single hole image to be tested and the standard contour of the standard single hole image, and the radius deviation of the points on the contour to be tested and the standard contour are compared according to the set interval angle, and whether the single hole is defective is determined based on the radius deviation.

[0061] Specifically, for a single hole to be tested whose hole shape similarity with a standard single hole is lower than a preset threshold, for example, f<0.9, it is considered that the image of the single hole to be tested is extremely dissimilar to the image of the standard single hole, that is, the single hole to be tested has a hole defect.

[0062] For the single hole to be tested whose hole shape similarity with the standard single hole is higher than the preset threshold, for example, f>0.9, it is considered that the hole shape similarity between the single hole image to be tested and the standard single hole image meets the preset condition, but further comparison is required to prevent the occurrence of hole defects such as sawtooth, crack, burr, etc.

[0063] The specific detection of hole defects can be divided into a preparation stage and a comparison stage. In the preparation stage: for the standard single-hole image, the standard contour C and the center of mass coordinates Gc are detected by an edge detection algorithm; for the single-hole image to be tested, the contour c and the center of mass coordinates gc to be tested are detected by an edge detection algorithm; the center of mass of the single-hole image to be tested and the standard single-hole image are aligned. The center of mass alignment can eliminate the deviation caused by translation, making subsequent calculations more accurate; a polar coordinate system is established with the aligned center of mass as the origin, and each point on the contour of the graphic hole can be represented by a radius and an angle; since the contour of the graphic hole is continuous and the calculation is discrete, the contour can be uniformly randomly sampled by setting an interval angle. If the interval angle is too small, the calculation amount will increase, and if it is too large, the deviation calculation will be inaccurate. It is necessary to select a suitable value according to the actual situation, for example, setting it to 1°.

[0064] In the comparison stage: compare the radius deviations of the points on the measured contour c and the points on the standard contour C according to the set interval angle, and determine whether the single hole is defective based on the radius deviation. Specifically, first extract the contour points: extract the points at the corresponding angle θ from the measured contour c and the standard contour C respectively; then calculate the radius deviation: for each sampling angle θ, calculate the distance r1 between the point on the measured contour c and the origin, and calculate the distance r2 between the point on the standard contour C and the origin, and the radius deviation Δr=|r1-r2|. Optionally, in order to make the radius deviation more intuitive and comparable, the radius deviation is normalized, for example, the radius deviation is divided by the radius r2 of the standard contour C at the sampling angle θ to obtain the relative deviation Δr / r2.

[0065] Optionally, the radius deviation or relative deviation at different sampling angles θ is plotted as a curve, so that the radius deviation between the profile to be measured c and the standard profile C can be observed more intuitively.

[0066] Optionally, statistics such as an average value or a maximum value of the radius deviation or the relative deviation at all sampling angles θ are calculated to evaluate the radius deviation between the profile to be measured c and the standard profile C as a whole.

[0067] Optionally, a threshold value is determined for the radius deviation between the calculated contour to be measured c and the standard contour C, and an alarm is issued if the deviation is too large.

[0068] Figure 7 is a schematic diagram of automatic measurement of hole parameters provided in the embodiment of the present application, such as Figure 7 As shown, the standard value, measured value, upper tolerance, lower tolerance, etc. of hole parameters such as single hole area, multi-hole area, hole spacing, hole margin, hole line deviation, hole shape similarity, etc. are displayed in real time and dynamically, and the roll change of the tipping paper to be tested can be automatically identified.

[0069] The online monitoring method for the laser drilling quality of tipping paper provided in the embodiment of the present application facilitates the consistency comparison between the multi-hole image to be tested and the standard single-hole image of the tipping paper to be tested by pre-selecting a standard single-hole image, standardizing the shooting conditions and automatically aligning each frame of the image; the multi-hole image to be tested is identified and directly measured hole by hole, the hole-by-hole identification result is compared with the standard single-hole image, the hole parameters directly evaluated and the hole parameters indirectly evaluated are statistically evaluated, and the laser drilling quality of the tipping paper is comprehensively monitored online from different dimensions of direct measurement and standard comparison; wherein, the directly evaluated hole parameters are hole spacing, hole margin, hole line deviation, single-hole hole area, multi-hole hole area, number of holes, etc., and the indirectly evaluated hole parameters are hole shape similarity, hole incompleteness, etc., and the laser drilling quality of the tipping paper is comprehensively monitored online from different dimensions of details and the whole.

[0070] It should be noted that the online monitoring method for the laser drilling quality of tipping paper provided in the embodiment of the present application is applicable to the prism drilling process for micro-holes and the galvanometer drilling process for large holes.

[0071] Figure 8 is a schematic diagram of the structure of an online monitoring device for the laser drilling quality of tipping paper provided in an embodiment of the present application, such as Figure 8 As shown, the device at least includes: The standard selection module 801 is used to select a standard single hole image corresponding to the tipping paper to be tested, wherein the standard single hole image is obtained by taking an image and performing image segmentation on the standard single hole; The image acquisition module 802 is used to take images of the tipping paper to be tested placed at the paper feeding position of the imaging system roll by roll under the same shooting conditions, and obtain the porous images to be tested of each roll of the tipping paper to be tested; The image alignment module 803 is used to identify the target single hole at the specified position in the single frame of the multi-hole image to be tested based on the shape of the standard single hole, and perform translation transformation on the single frame of the multi-hole image to be tested based on the target single hole, so as to align different frames of multi-hole images to be tested; The hole parameter statistics module 804 includes a first statistics unit and a second statistics unit, wherein the first statistics unit is used to perform hole-by-hole identification on the multi-hole image to be tested, and directly evaluate the hole parameters based on the hole-by-hole identification result statistics; the second statistics unit is used to compare the hole-by-hole identification result with the standard single hole image, and indirectly evaluate the hole parameters based on the statistics; The hole parameter sending module 805 is used to send the statistical direct evaluation hole parameters and indirect evaluation hole parameters to the laser drilling controller to adjust the drilling strategy.

[0072] In some embodiments, the hole parameter directly evaluated is the hole spacing, hole margin distance or hole line deviation, and the first statistical unit is specifically used for: Determine the centroid coordinates of the graphic holes in the multi-hole image to be tested by a centroid fitting algorithm; The centroid coordinates of the graphic holes are grouped according to the hole lines, and the hole line equation of the corresponding hole line is fitted using each group of centroid coordinates; The hole spacing, hole edge distance or hole line deviation is calculated based on the hole line equation.

[0073] In some embodiments, calculating the hole margin distance based on the hole line equation includes: Determine the distance between the hole line equation of the edge hole line where the edge graphic hole in the multi-hole image to be tested is located and the straight line equation of the edge of the tipping paper as the hole margin distance; The straight line equation of the tipping paper edge is obtained by edge tracking of the porous image to be tested.

[0074] In some embodiments, calculating the hole line deviation based on the hole line equation includes: The hole line equation of the target hole line in the multi-hole image to be tested is compared with the preset standard hole line equation to determine the hole line deviation.

[0075] In some embodiments, calculating the hole spacing based on the hole line equation includes: The distance between the hole line equations of the parallel hole lines where the adjacent graphic holes are located is determined as the hole spacing between the adjacent graphic holes.

[0076] In some embodiments, directly evaluating the pore parameters includes single-pore pore area, multi-pore pore area and pore number, and the first statistical unit is specifically used for: Based on the hole-by-hole recognition results, single-hole segmentation is performed, and the images of the single holes to be tested are obtained hole by hole and the number of holes is determined; The single hole area in the single hole image to be tested is determined by binarization processing, and the multi-hole area is calculated based on the single hole area statistics.

[0077] In some embodiments, the indirect evaluation parameter includes hole shape similarity, and the second statistical unit is specifically used for: Based on the hole-by-hole recognition results, single-hole segmentation is performed, and images of single-holes to be tested are obtained hole by hole; The SSIM algorithm is used to compare the structural similarity of the single hole image to be tested with the standard single hole image hole by hole, and the hole shape similarity between each graphic hole in the multi-hole image to be tested and the standard single hole is counted.

[0078] In some embodiments, the indirect evaluation parameter further includes hole defects, and the second statistical unit is further used for: If the hole shape similarity is lower than a preset threshold, it is determined that the single hole is defective; If the hole shape similarity is higher than the preset threshold, the centroid coordinates of the single hole image to be tested and the standard single hole image are aligned, and a polar coordinate system is established with the aligned centroid as the origin; the edge detection algorithm is used to detect the contour to be tested of the single hole image to be tested and the standard contour of the standard single hole image, and the radius deviation of the points on the contour to be tested and the standard contour are compared according to the set interval angle, and whether the single hole is defective is determined based on the radius deviation.

[0079] In some embodiments, the device further includes a brightness calibration module, configured to: Based on the preset transmittance, the standard perforated tipping paper is imaged regularly to obtain a reference image; Performing brightness detection on the reference image, and verifying the attenuation degree of the brightness of the light source based on the brightness detection result; If the brightness of the light source decays, the light source controller is controlled to adjust the brightness of the light source to maintain a preset transmittance.

[0080] It can be understood that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.

[0081] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0082] Based on the method in the above embodiment, an embodiment of the present application provides an electronic device. The device may include: at least one memory for storing programs and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the above embodiment.

[0083] Fig. 9 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Fig. 9 As shown, the electronic device may include: a processor (processor) 901, a communication interface (Communications Interface) 902, a memory (memory) 903 and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904. The processor 901 may call the software instructions in the memory 903 to execute the method described in the above embodiment.

[0084] In addition, the logic instructions in the above-mentioned memory 903 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present application.

[0085] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0086] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0087] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0088] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0089] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0090] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0091] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. An online monitoring method for the laser drilling quality of tipping paper, characterized in that: include: Selecting a standard single-hole image corresponding to the tipping paper to be tested, wherein the standard single-hole image is obtained by taking an image and performing image segmentation on the standard single hole; Under the same shooting conditions, the tipping paper to be tested placed at the paper feeding position of the imaging system is taken up roll by roll, and the porous image to be tested of each roll of the tipping paper to be tested is obtained; Based on the shape of the standard single hole, a target single hole at a specified position in a single frame of the multi-hole image to be tested is identified, and based on the target single hole, the single frame of the multi-hole image to be tested is translated and transformed, so as to align different frames of multi-hole images to be tested; Perform hole-by-hole identification on the multi-hole images to be tested, and directly evaluate the hole parameters based on the statistics of the hole-by-hole identification results; Comparing the hole-by-hole recognition result with the standard single hole image, and statistically indirectly evaluating hole parameters; The statistically evaluated direct hole parameters and the indirect hole parameters are sent to a laser drilling controller to adjust the drilling strategy.

2. The online monitoring method according to claim 1, characterized in that: The directly evaluated hole parameters are hole spacing, hole margin distance or hole line deviation, and the directly evaluated hole parameters based on hole-by-hole recognition result statistics include: Determine the centroid coordinates of the graphic holes in the multi-hole image to be tested by a centroid fitting algorithm; The centroid coordinates of the graphic holes are grouped according to the hole lines, and the hole line equation of the corresponding hole line is fitted using each group of centroid coordinates; The hole spacing, hole edge distance or hole line deviation is calculated based on the hole line equation.

3. The online monitoring method according to claim 2, characterized in that: The hole edge distance is calculated based on the hole line equation, including: Determine the distance between the hole line equation of the edge hole line where the edge graphic hole in the porous image to be tested is located and the straight line equation of the tipping paper edge as the hole margin; The straight line equation of the tipping paper edge is obtained by edge tracking of the porous image to be measured.

4. The online monitoring method according to claim 2, characterized in that: The hole line deviation is calculated based on the hole line equation, including: The hole line equation of the target hole line in the porous image to be tested is compared with the preset standard hole line equation to determine the hole line deviation.

5. The online monitoring method according to claim 2, characterized in that: The hole spacing is calculated based on the hole line equation, including: The distance between the hole line equations of the parallel hole lines where the adjacent graphic holes are located is determined as the hole spacing between the adjacent graphic holes.

6. The online monitoring method according to claim 1, characterized in that: The directly evaluated hole parameters include single hole area, multi-hole area and hole number, and the directly evaluated hole parameters based on hole-by-hole identification result statistics include: Based on the hole-by-hole recognition results, single-hole segmentation is performed, and images of single holes to be tested are obtained hole by hole and the number of holes is determined; The single hole area in the single hole image to be tested is determined by binarization processing, and the multi-hole area is calculated based on the single hole area statistics.

7. The online monitoring method according to claim 1, characterized in that: The indirect evaluation parameters include the hole shape similarity, and the statistical indirect evaluation of the hole parameters includes: Perform single-hole segmentation based on the hole-by-hole recognition results, and obtain single-hole images to be tested hole by hole; The structural similarity between the single hole image to be tested and the standard single hole image is compared hole by hole by hole by the SSIM algorithm, and the hole shape similarity between each graphic hole in the multi-hole image to be tested and the standard single hole is counted.

8. The online monitoring method according to claim 7, characterized in that: The indirect evaluation parameters also include hole defects, and the statistical indirect evaluation of hole parameters also includes: If the hole shape similarity is lower than a preset threshold, it is determined that the single hole is defective; If the hole shape similarity is higher than the preset threshold, the centroid coordinates of the single hole image to be tested and the standard single hole image are aligned, and a polar coordinate system is established with the aligned centroid as the origin; the measured contour of the single hole image to be tested and the standard contour of the standard single hole image are detected by an edge detection algorithm, and the radius deviation of the points on the measured contour and the standard contour are compared according to the set interval angle, and whether the single hole is defective is determined based on the radius deviation.

9. The online monitoring method according to claim 1, characterized in that: The method further comprises: Based on the preset transmittance, the standard perforated tipping paper is imaged regularly to obtain a reference image; Performing brightness detection on the reference image, and verifying the attenuation degree of the brightness of the light source based on the brightness detection result; If the brightness of the light source decays, the light source controller is controlled to adjust the brightness of the light source to maintain the preset transmittance.

10. An online monitoring device for the quality of laser drilling of tipping paper, characterized in that: include: A standard selection module is used to select a standard single-hole image corresponding to the tipping paper to be tested, wherein the standard single-hole image is obtained by taking an image and performing image segmentation on the standard single hole; An image acquisition module is used to take images of the tipping paper to be tested placed at the paper feeding position of the imaging system roll by roll under the same shooting conditions, and obtain the porous images to be tested of each roll of the tipping paper to be tested; An image alignment module is used to identify a target single hole at a specified position in the multi-hole image to be tested based on the shape of the standard single hole, and to perform a translation transformation on the multi-hole image to be tested based on the target single hole, so as to align different frames of multi-hole images to be tested; The hole parameter statistics module includes a first statistics unit and a second statistics unit, wherein the first statistics unit is used to perform hole-by-hole identification on the multi-hole image to be tested, and directly evaluate the hole parameters based on the statistics of the hole-by-hole identification results; the second statistics unit is used to compare the hole-by-hole identification results with the standard single-hole image, and indirectly evaluate the hole parameters based on statistics; The hole parameter sending module is used to send the statistically directly evaluated hole parameters and the indirectly evaluated hole parameters to the laser drilling controller to adjust the drilling strategy.

Images