Control optimization method based on digital slotting machine for paperboard

Abstract

The application discloses a control optimization method based on a paperboard digital intelligent grooving machine, and relates to the technical field of paperboard grooving, solves the problem of long idle stroke distance and frequent repeated movement caused by the optimization of the motion trail without considering the distribution of the actual grooving area, selects a path with the shortest total distance of feature points, reduces invalid travel, and based on single or double confirmation processes of the total number of grooving positions, further optimizes the path planning in each grooving area, and finally forms an optimal path that significantly shortens the movement distance of the grooving machine, improves the overall grooving rate, and is especially suitable for batch processing scenes of multiple grooving areas, and for irregular paperboards or multiple feature points, through the multi-round coincidence verification and path adjustment mechanism, the adaptability of the equipment to complex processing scenes is enhanced, and the fault tolerance and stability of the system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of paperboard slotting, in particular to a control optimization method based on a paperboard digital intelligent slotting machine. BACKGROUND

[0002] In the field of paper box production and processing, the paperboard slotting process is a core link that determines the quality of paper box forming and the subsequent assembly efficiency, and its processing precision directly affects the folding flatness, sealing performance and structural strength of the paper box. With the rapid growth of demand for customized, small-batch and multi-specification paper boxes in the packaging industry, the control mode of traditional paperboard slotting machines gradually exposes many technical bottlenecks, making it difficult to adapt to modern production needs.

[0003] Traditional slotting machines rely on manual experience for operation, and workers need to manually adjust the cutter position, feed speed and other parameters according to the size and material of the paperboard, and calibrate the slotting position by eye observation or simple measuring tools. Not only is the operation process tedious and labor costs high, but it is also easy to cause problems such as slotting position deviation and inconsistent groove depth due to human judgment deviation.

[0004] At the same time, traditional equipment lacks precise recognition ability of paperboard surface features and cannot automatically adapt to the processing characteristics of different types of paperboard. In terms of path planning, traditional slotting machines mostly use fixed path mode and do not optimize the motion trajectory in combination with the distribution of the actual slotting area, resulting in long cutter idle distance and frequent repeated motion. Not only does this increase equipment energy consumption and mechanical wear and tear, but it also prolongs the processing cycle of single paperboard, especially in batch processing scenarios with multiple slotting areas, the efficiency shortcoming is more prominent.

[0005] In addition, the control system of traditional equipment is mostly in independent operation mode, lacks linkage with digital systems, and cannot realize real-time storage, analysis and tracing of processing data. When slotting quality problems occur, it is difficult to quickly locate the root cause, and subsequent process optimization lacks data support. Therefore, developing a slotting machine control method that can realize accurate paperboard recognition, automatic parameter matching and intelligent path optimization has become a key requirement to solve current industry pain points and improve paper box processing automation level and product quality. SUMMARY

[0006] In view of the deficiencies of the prior art, the present application provides a control optimization method based on a paperboard digital intelligent slotting machine, which solves the problem of long cutter idle distance and frequent repeated motion caused by not optimizing the motion trajectory in combination with the distribution of the actual slotting area.

[0007] To achieve the above purpose, the present application is implemented by the following technical scheme: a control optimization method based on a paperboard digital intelligent slotting machine, comprising the following steps:

[0008] Step one, get the surface image of the need to slot paperboard, according to the edge profile of the surface image, confirm the midpoint of the slot paperboard, and then according to the profile characteristics of the edge profile, confirm the calibration characteristics of the current slot paperboard, the specific way is:

[0009] When the slot paperboard is placed in the processing area, the surface image of the slot paperboard is obtained, and the surface image is processed by gray scale, the gray image associated with the surface image is confirmed, the RGB value associated with different pixel points in the surface image is marked as R i , G i and B i in turn, wherein i represents different pixel points, and HD i =0.299×R i +0.587×G i +0.114×B i is adopted to confirm the gray value HD i associated with the corresponding pixel point, and different gray values associated with different pixel points are generated to belong to the gray image associated with the surface image.

[0010] The comprehensive gradient associated with different gray points in the gray image is confirmed by using Sobel algorithm, the vertical gradient and horizontal gradient associated with the corresponding gray point are confirmed according to the different gray values of different gray points, and then: The comprehensive gradient associated with the corresponding gray point is confirmed, the gray point with comprehensive gradient satisfying comprehensive gradient≥Y1 is marked as gradient point, otherwise, no mark is made, wherein Y1 is a preset value.

[0011] The adjacent gradient points of the gray image are confirmed in turn, and the adjacent gradient points are connected to confirm the gradient contour line, whether the gradient contour line is closed is identified, if closed, it is recorded as the edge profile of the current slot paperboard, otherwise, stop until the edge profile is determined.

[0012] The two-dimensional coordinates associated with different profile points on the edge profile are confirmed by combining the edge profile with the two-dimensional coordinate system, and the two-dimensional coordinates associated with several profile points are processed by mean value to confirm the mean value coordinates, and the point with the mean value coordinates is recorded as the midpoint of the slot paperboard.

[0013] According to the midpoint confirmed inside the slot paperboard, the straight line distance between different profile points and the midpoint on the edge profile is confirmed, from the confirmed several groups of straight line distance, the maximum value is selected, and the profile point associated with the maximum value is recorded as the feature point; If there are multiple groups of maximum values, a group of profile points is randomly selected as the feature point, and a group of calibration inner lines is generated with the midpoint as the starting point and the feature point as the ending point, and the generated calibration inner line is taken as the calibration characteristics of the current slot paperboard.

[0014] Step 2: Based on the calibration characteristics confirmed by the current slotted cardboard, extract the preset standard template from the cloud database, compare the standard template with the current slotted cardboard, confirm and record the associated slotting positions on the surface of the current slotted cardboard. The specific method is as follows:

[0015] Let L be the bus length associated with the calibration feature, and let Q be the preset feature line length within different preset standard templates. k Where k represents different standard templates, and Q is determined from several Qk. k =L is the standard template, and this standard template is denoted as the undetermined template. If Q does not exist... k The standard template for =L will directly generate and display error signals;

[0016] The grayscale image associated with the slotted cardboard is compared with the standard template: the calibration features of the grayscale image are made to coincide with the preset features associated with the standard template. After the coincidence process is completed, it is confirmed whether the grayscale image is completely coincident with the standard template. If it coincides, the current processing process is completed. If it does not coincide, it is sequentially compared with other preset features in the grayscale image until the grayscale image is completely coincident with the standard template.

[0017] Based on the pre-set slotting positions in the standard template, they are simultaneously marked in the grayscale image of the current slotted cardboard.

[0018] Step 3: Based on the recorded slotting positions on the surface of the slotted cardboard, locate the slotting area and perform path analysis to select the initial optimal path. Then, based on the total number of slotting areas, perform path analysis on the internal slotting paths associated with each slotting area to confirm the optimal path and execute it. The specific method for selecting the initial optimal path is as follows:

[0019] And the slotted cardboard records several slotted positions, confirms the slotted area associated with each different slotted position, determines the center point associated with each slotted area and records it as a feature point, and then performs several selection processes from the marked feature points: randomly selects a set of feature points as the initial point, and then randomly selects other feature points in sequence until all feature points have been selected, and connects the sequentially selected feature points according to the step-by-step selection process to generate a driving path, and records the bus length of the driving path corresponding to the current selection process as ZS. q Where q represents different selection processes, and ZS represents different total threads associated with several selection processes. q In the middle, select the minimum value ZS q min, and set the minimum value ZS q The selection process associated with min is called the determining process, and the driving path associated with the determining process is called the initial optimal path.

[0020] The specific way of confirming the optimal path is:

[0021] According to the confirmed initial optimal path, the associated slotting positions are sorted according to the driving process of the path, the slotting position sequence is confirmed, the specific total number ZZ of the slotting positions in the slotting position sequence is identified, if ZZ is even, a single confirmation process is performed, and if ZZ is odd, a double confirmation process is performed.

[0022] Single confirmation process: from the confirmed slotting position sequence, starting from the first slotting position, two groups of adjacent slotting positions are recorded as unit sets, the area profiles of the two slotting regions in the unit set are confirmed, the two profile points closest in straight line distance on the two confirmed area profiles are confirmed, the two profile points are recorded as the slotting starting points of the corresponding slotting positions, and the slotting paths of the corresponding slotting regions are generated in the clockwise direction according to the slotting starting points. The slotting paths recorded in the determination process are sorted in sequence according to the sorting method of the slotting position sequence to generate the optimal path.

[0023] The double confirmation process includes: generating the slotting paths associated with different slotting positions in the slotting position sequence according to the slotting path confirmation method of the single confirmation process, recording the straight line distance of the two closest profile points in the unit set, and summing up the recorded several groups of straight line distances to confirm the total distance, which is recorded as the single feature.

[0024] From the second group of slotting positions, two groups of adjacent slotting positions are recorded as unit sets, and the same way of confirming the slotting path of the slotting region is used to confirm the slotting paths associated with different slotting regions, and the same confirmation method of the total distance of the single feature is used to confirm the total distance associated with the current processing process, which is recorded as the double feature.

[0025] From the single feature or the double feature, the minimum value is selected, the processing process associated with the minimum value is recorded as the determination process, and the slotting paths recorded in the determination process are sorted in sequence according to the sorting method of the slotting position sequence to generate the optimal path.

[0026] The present application provides a control optimization method based on a paperboard digital intelligent slotting machine. Compared with the prior art, the following beneficial effects are achieved:

[0027] The present application realizes accurate positioning of different types and sizes of paperboards by surface image analysis and grayscale processing, combined with Sobel algorithm to extract edge profiles and determine midpoint and calibration features, laying a high-precision foundation for subsequent determination of slotting positions. The calibration feature and the standard template comparison mechanism can effectively adapt to the characteristics of various paperboards, ensuring the accuracy of the slotting position marking and greatly reducing the positioning deviation caused by the difference in paperboard specifications.

[0028] In terms of efficiency improvement, the path optimization strategy shows obvious advantages; the initial optimal path reduces invalid travel by selecting the path with the shortest total distance of feature points; and the single or double confirmation process based on the total number of slotting positions further optimizes the path planning within each slotting area, significantly shortening the movement distance of the slotting machine and improving the overall slotting rate, especially suitable for batch processing scenarios with multiple slotting areas;

[0029] In terms of intelligence and adaptability, the method introduces a cloud database to store standard templates, combines image recognition and automatic comparison technology to reduce manual intervention and achieve automatic processing of the slotting process; for irregular paperboards or multiple feature points, the multi-round coincidence verification and path adjustment mechanism enhances the device's adaptability to complex processing scenarios and improves the system's fault tolerance and stability. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 The figure is a flowchart of the method of the present application. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0032] Please refer to Figure 1 The present application provides a control optimization method based on a paperboard digital intelligent slotting machine, comprising the following steps:

[0033] Step one, obtain the surface image of the paperboard to be slotted, confirm the midpoint of the slotted paperboard according to the edge profile of the surface image, and then confirm the calibration features of the current slotted paperboard according to the profile features of the edge profile. Specifically, for different types and sizes of paperboards, first, image acquisition is needed, then feature analysis and verification of the obtained image is performed to identify some paperboard features of this type of paperboard, and then a pre-set standard template is combined to effectively confirm the specific slotting position of the corresponding paperboard, thereby quickly and effectively determining the slotting opening and completing the slotting process of the corresponding slotted paperboard.

[0034] The specific way to confirm the midpoint of the slotted paperboard is as follows:

[0035] When the slotted paperboard is placed in the processing area, the surface image of the slotted paperboard is obtained, and then the surface image is subjected to grayscale processing, the grayscale image associated with the surface image is confirmed, and the RGB values associated with different pixel points in the surface image are sequentially marked as Ri , G i , and B i , wherein i represents different pixel points, and then HD i = 0.299 * R i + 0.587 * G i + 0.114 * B i is adopted to confirm the gray value HD i associated with the corresponding pixel points, and according to different gray values associated with different pixel points, a gray image belonging to the surface image is generated;

[0036] The comprehensive gradient associated with different gray points in the gray image is confirmed by using the Sobel algorithm, the vertical gradient and the horizontal gradient associated with the corresponding gray points are confirmed according to different gray values of different gray points, and then HD = 0.299 * R + 0.587 * G

[0037] + 0.114 * B is adopted to confirm the comprehensive gradient associated with the corresponding gray points, the gray points with a comprehensive gradient satisfying comprehensive gradient >= Y1 are marked as gradient points, and otherwise, no marking is performed, wherein Y1 is a preset value, and the specific value is determined by an operator according to experience;

[0038] The adjacent gradient points around the gray image are confirmed in sequence, and the adjacent gradient points are connected to confirm the gradient contour line, whether the gradient contour line is closed is identified, if the gradient contour line is closed, the edge contour of the current slotted paperboard is recorded, otherwise, the process is stopped until the edge contour is determined;

[0039] The two-dimensional coordinates associated with different contour points on the edge contour are confirmed by combining the edge contour with the two-dimensional coordinate system, the two-dimensional coordinates associated with a plurality of contour points are processed by using the mean value, the mean value coordinates are confirmed, and the point with the mean value coordinates is recorded as the midpoint of the slotted paperboard;

[0040] Specifically, in the specific slotted processing process, the gray feature associated with the paperboard is confirmed according to the overall surface image of the corresponding paperboard, so as to identify the edge contour existing around the corresponding paperboard, and the slotted feature of the current paperboard is confirmed according to the edge contour, which is convenient for subsequent comparison and verification, and quickly realizes the slotted processing process of the slotted paperboard;

[0041] Step two, according to the calibration feature confirmed by the current slotted paperboard, extract the preset standard template from the cloud database, compare the standard template with the current slotted paperboard, confirm the slotted position associated with the surface of the current slotted paperboard and record it;

[0042] Among them, the specific way of detailed confirmation of the slotted position is:

[0043] The bus length associated with the calibration feature is denoted as L, and the feature line length preset in different preset standard templates is denoted as Q k Where k represents different standard templates, Q is confirmed from several Qk k =L standard template, this standard template is denoted as the undetermined template, if there is no Q k =L standard template, then an error signal is generated directly, in actual operation, the relevant management personnel need to preset the standard template in advance, according to the corresponding processing paperboard associated with the processing scene, preset the corresponding template associated with different processing paperboard in advance, and the corresponding slotted position is preset in the standard template, which is convenient for subsequent comparison process to confirm the corresponding slotted position on the corresponding paperboard;

[0044] Compare the gray image associated with the slotted paperboard with the standard template: make the calibration feature of the gray image coincide with the preset feature (that is, a group of feature lines associated with the corresponding feature line length) associated with the standard template. After completing the coincidence processing, it is confirmed whether the gray image coincides with the standard template completely (in the coincidence process, scaling processing will be performed, and the size of the corresponding gray image contour will be adjusted to the preset size of the standard template). If it coincides, the current processing process is completed, if it does not coincide, it will be coincided with other preset features in the gray image in turn, until the gray image and the standard template completely coincide. Stop, why there are other preset features, is that there are multiple maximum values of the corresponding contour points, for example, irregular paperboard, its periphery may have multiple farthest points, then after randomly selecting a farthest point, it cannot reach the coincidence state, then the farthest point selected and the farthest point on the corresponding template do not coincide, it needs to be processed again, execute several coincidence processing processes to confirm the complete coincidence processing process.

[0045] According to the preset slotted position in the standard template, the gray image of the current slotted paperboard is marked synchronously, specifically, in the actual processing process, through the corresponding coincidence processing process, the slotted paperboard of the corresponding standard template can be effectively marked in the corresponding gray image, which is convenient for subsequent execution of the corresponding slotted process;

[0046] Step three, according to the current slotting paperboard surface recorded slotting position, locking slotting area, and path analysis, select the initial optimal path, and based on the total number of slotting area, the internal slotting path associated with each slotting area is analyzed, and the optimal path is confirmed and executed;

[0047] Wherein, the specific way of selecting the initial optimal path is:

[0048] And the slotting paperboard records several slotting positions, confirms the slotting area associated with each different slotting position (which can be directly extracted from the standard template), determines the center point associated with each slotting area, and marks it as a feature point. Then, from the marked several feature points, several selection processes are performed: a group of feature points are randomly selected as initial points, and other feature points are randomly selected in turn. After all the feature points are selected, the selected feature points are connected according to the step-by-step selection process, and a driving path is generated. The total length of the driving path corresponding to the current selection process is recorded as ZS q , where q represents different selection processes, and the total length ZS q of several selection processes associated with different selection processes is selected as the minimum value ZS q min , and the selection process associated with the minimum value ZS q min is recorded as the determination process, and the driving path associated with the determination process is recorded as the initial optimal path.

[0049] Specifically, the initial optimal path is the path corresponding to the minimum distance traveled by the slotting machine when all feature points are selected and confirmed in the path confirmation process. In the determination state of the initial optimal path, the subsequent slotting path is analyzed and processed again to determine the optimal path and execute the slotting process of the corresponding slotting paperboard.

[0050] The specific way of confirming the optimal path is:

[0051] According to the confirmed initial optimal path, the slotting positions associated with the driving process of the path are sorted in turn to confirm the slotting position sequence, identify the specific total number ZZ of slotting positions in the slotting position sequence, and if ZZ is even, a single confirmation process is performed, and if ZZ is odd, a double confirmation process is performed.

[0052] Single confirmation process: from the confirmed slotting position sequence, the first slotting position is taken as the starting point, and two adjacent groups of slotting positions are recorded as a unit set (each unit set includes two groups of slotting positions), the region profiles of the two slotting regions in the unit set are confirmed, and the two profile points closest in straight line distance on the two confirmed region profiles are recorded as the slotting starting points of the corresponding slotting positions, and the slotting paths of the corresponding slotting regions are generated in the slotting regions according to the clockwise direction according to the slotting starting points, and the slotting paths recorded in the determination process are sorted in sequence according to the sorting method of the slotting position sequence to generate an optimal path, the slotting starting point of which is not only the starting point but also the ending point;

[0053] Double confirmation process: according to the slotting path confirmation method of the single confirmation process, the slotting paths associated with different slotting positions in the slotting position sequence are generated, the straight line distances of the two closest profile points in the corresponding unit set are recorded, and the sum of the recorded several groups of straight line distances is calculated to obtain the total distance, which is recorded as the single feature;

[0054] Then, from the second group of slotting positions, two adjacent groups of slotting positions are recorded as a unit set, and the slotting paths associated with different slotting regions are confirmed in the same way as described above, and the total distance associated with the current processing process is confirmed in the same way as the single feature total distance, which is recorded as the double feature;

[0055] From the single feature or the double feature, the minimum value is selected, and the processing process associated with the minimum value is recorded as the determination process, and the slotting paths recorded in the determination process are sorted in sequence according to the sorting method of the slotting position sequence to generate an optimal path;

[0056] The optimal path is the shortest path associated with the corresponding slotting machine during the slotting process, and when the corresponding slotting process is performed according to the shortest path, the slotting speed is the fastest, and the distance traveled by the corresponding slotting head is the shortest, which not only ensures the normal slotting process of the paperboard, but also ensures the specific efficiency of the slotting.

[0057] Some data in the above formula are dimensionless numerical calculations, and the contents not described in detail in the specification are all prior art known to those skilled in the art.

[0058] The above embodiments are only used to illustrate the technical method of the present application and are not limiting, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. A method for optimizing the control of a digital slotter based on cardboard, characterized in that, The method comprises the following steps: Step one, obtaining the surface image of the paperboard to be slotted, confirming the midpoint of the slotted paperboard according to the edge profile of the surface image, and confirming the calibration feature of the current slotted paperboard according to the profile feature of the edge profile; Step two, extracting a preset standard template from a cloud database according to the calibration feature of the current slotted paperboard, comparing the standard template with the current slotted paperboard, confirming the slotting position associated with the surface of the current slotted paperboard and recording the slotting position; Step three, locking the slotting area according to the recorded slotting position of the surface of the current slotted paperboard, performing path analysis, selecting an initial optimal path, and performing path analysis on the internal slotting path associated with each slotting area based on the total number of slotting areas to confirm an optimal path and execute the optimal path; The specific way of confirming the optimal path is: According to the confirmed initial optimal path, the slotting positions associated with the path in sequence are sorted according to the driving process of the path to confirm the slotting position sequence, identify the specific total number ZZ of slotting positions in the slotting position sequence, if ZZ is even, a single confirmation process is performed, and if ZZ is odd, a double confirmation process is performed; The single confirmation process: from the first slotting position in the confirmed slotting position sequence, two groups of slotting positions adjacent in sequence are recorded as unit sets, the region profiles of the two slotting regions in the unit set are confirmed, the two profile points closest in straight line distance on the two confirmed region profiles are confirmed, the two profile points are recorded as the slotting starting points of the corresponding slotting positions, and the slotting path of the corresponding slotting region is generated in the slotting region according to the slotting starting points in the clockwise direction. The slotting paths recorded in the single confirmation process are sorted in sequence according to the sorting method of the slotting position sequence to generate an optimal path; The double confirmation process includes: generating the slotting paths associated with different slotting positions in the slotting position sequence according to the slotting path confirmation method of the single confirmation process, recording the straight line distance of the two closest profile points in the unit set, summing the recorded several groups of straight line distances to confirm the total distance, and recording the total distance as the single feature; From the second group of slotting positions, two groups of slotting positions adjacent in sequence are recorded as unit sets, and the same way of confirming the slotting path of the slotting region is used to confirm the slotting paths associated with different slotting regions, and the same confirmation method of the total distance of the single feature is used to confirm the total distance associated with the current processing process, which is recorded as the double feature; From the single feature or the double feature, the minimum value is selected, the processing process associated with the minimum value is recorded as the double confirmation process, and the slotting paths recorded in the double confirmation process are sorted in sequence according to the sorting method of the slotting position sequence to generate an optimal path.

2. The control optimization method of the paperboard digital smart grooving machine based on the paperboard digital smart grooving machine according to claim 1, characterized in that, In step one, the specific way of confirming the calibration feature of the current slotted paperboard is: When the slotted paperboard is placed in the processing area, the surface image of the slotted paperboard is acquired, the surface image is subjected to grayscale processing, the grayscale image associated with the surface image is confirmed, the RGB values associated with different pixel points in the surface image are sequentially marked as R i , G i and B i , wherein i represents different pixel points, and the HD i =0.299×R i +0.587×G i +0.114×B i of the corresponding pixel point is confirmed, and the grayscale value HD i associated with different pixel points is generated to generate the grayscale image associated with the surface image. The Sobel algorithm is used to confirm the comprehensive gradient associated with different gray points in the gray image. According to different gray values of different gray points, the vertical gradient and the horizontal gradient associated with the corresponding gray points are confirmed. Then, the comprehensive gradient associated with the corresponding gray points is confirmed. The gray points with a comprehensive gradient satisfying comprehensive gradient >= Y1 are marked as gradient points, otherwise, no marking is performed, wherein Y1 is a preset value. The adjacent gradient points around the gray image are confirmed in sequence, and the adjacent gradient points are connected to confirm the gradient contour line. It is identified whether the gradient contour line is closed. If it is closed, it is recorded as the edge contour of the current slotted paperboard, otherwise, the process is stopped until the edge contour is determined. The edge contour and the two-dimensional coordinate system are combined to confirm the two-dimensional coordinates associated with different contour points on the edge contour. The two-dimensional coordinates associated with a plurality of contour points are processed by averaging to confirm the average coordinates, and the point with the average coordinates is recorded as the midpoint of the slotted paperboard. According to the midpoint confirmed inside the slotted paperboard, the straight line distance associated between different contour points and the midpoint on the edge contour is confirmed. From the confirmed plurality of groups of straight line distances, the maximum value is selected, and the contour point associated with the maximum value is recorded as the first feature point.

3. The control optimization method of the paperboard digital smart grooving machine based on the paperboard digital smart grooving machine according to claim 2, characterized in that, If there are multiple maximum values, a group of contour points is randomly selected as the feature point. With the midpoint as the starting point and the feature point as the ending point, a group of calibration inner lines is generated, and the generated calibration inner lines are used as the calibration features of the current slotted paperboard.

4. The control optimization method of the paperboard digital smart grooving machine based on the paperboard digital smart grooving machine according to claim 3, characterized in that, In step two, the specific way of detailed confirmation of the slotting position is: Let the bus length associated with the calibration feature be denoted as L, and let the feature line length preset in the different preset standard templates be denoted as Q k wherein k represents different standard templates, and Q is confirmed from several Qk k =L. The standard template is denoted as a to-be-determined template. The gray image associated with the slotted paperboard is compared with the standard template: the calibration features of the gray image are overlapped with the preset features associated with the standard template. After the overlapping process is completed, it is confirmed whether the gray image is completely overlapped with the standard template. If it is overlapped, the current processing process is completed, if it is not overlapped, the other preset features in the gray image are overlapped in sequence until the gray image is completely overlapped with the standard template. According to the preset slotting position in the standard template, the gray image of the current slotted paperboard is marked synchronously.

5. The control optimization method of the paperboard digital smart grooving machine based on the paperboard digital smart grooving machine according to claim 4, characterized in that, If there is no standard template for Q k =L, an error signal is generated directly.

6. The control optimization method of the paperboard digital smart grooving machine based on the paperboard digital smart grooving machine according to claim 1, characterized in that, In step three, the specific way of selecting the initial optimal path is: According to a plurality of slotting positions recorded by the slotted paperboard, a slotting area associated with each different slotting position is confirmed, a center point associated with each slotting area is determined, and is marked as a second feature point. Then, a plurality of selection processes are performed from the plurality of marked second feature points: a group of second feature points are randomly selected as initial points, and other second feature points are randomly selected in turn until all second feature points are selected. Then, according to a step-by-step selection process, the second feature points selected in turn are connected, a driving path is generated, and the total bus length of the driving path corresponding to the current selection process is marked as ZS q , wherein q represents different selection processes, and the different total bus lengths ZS q are associated with a plurality of selection processes. Then, the minimum value ZS q min is selected, and the selection process associated with the minimum value ZS q min is marked as a determination process. The driving path associated with the determination process is marked as an initial optimal path.

Images