A box accumulating conveyor device and method for a fully automatic box pasting machine

Abstract

The application provides a box accumulation conveying device and method for a fully automatic box pasting machine, edge features of each paper box are extracted from depth images of different perspectives of the paper boxes on the accumulation conveying chain; displacement deviation gradients of each group of adjacent paper boxes in the conveying process are determined according to the edge features of each group of adjacent paper boxes, cumulative position deviations of each paper box when reaching the storage area are predicted based on all the displacement deviation gradients; an adjustable range of the best compensation angle of the guide roller for dynamically pre-adjusting each paper box is obtained through all the edge features; the queue interval between each paper box in the conveying process is cooperatively adjusted based on all the cumulative position deviations and the adjustable range of the best compensation angle, and a cooperative queue of the paper boxes in the conveying process is obtained, and the paper boxes on the production line are conveyed according to the cooperative queue. By adopting the scheme, group posture cooperative control can be realized to reduce the chain deviation caused by single-point adjustment of the paper boxes on the accumulation conveying chain.

Description

Technical Field

[0001] The present application relates to the technical field of box accumulation and conveying, and more specifically, to a box accumulation and conveying device and method for a fully automatic box gluing machine. Background Art

[0002] Accumulated box conveying is a key technology used in fully automatic carton gluers for precise stacking and orderly transportation of cartons. Its core goal is to ensure that cartons arrive accurately at the storage area in a preset posture and position through dynamic perception, prediction and collaborative control during long-distance, high-speed transportation.

[0003] With the increasing demand for automation in the packaging industry, fully automatic carton gluers face higher precision requirements in the carton forming, stacking and conveying links. Traditional conveying systems rely on mechanical guide devices with fixed parameters. During long-distance conveying, cartons are prone to cumulative displacement errors and posture deflections due to speed fluctuations of the accumulation conveyor chain, differences in vibration characteristics, and interactions between multiple cartons. In existing technologies, a single perspective is usually used to detect the position of the cartons and single-point adjustments are made to the cartons, but it is difficult to dynamically predict the misalignment trend of the cartons under complex working conditions; the correction angle of the guide roller is mostly based on a preset threshold, and there is a lack of real-time analysis of the spatial correlation between cartons. This leads to a high misalignment rate of carton stacking in the storage area and frequent secondary adjustments, which seriously affect the production cycle and packaging quality. Therefore, how to achieve group posture collaborative control to reduce the chain deviation caused by single-point adjustment of cartons on the accumulation conveyor chain has become a problem facing the industry. Summary of the Invention

[0004] The present application provides a box-accumulating conveying device and method for a fully automatic box-gluing machine, which can realize group posture collaborative control to reduce the chain deviation caused by single-point adjustment of the paper boxes on the accumulation-type conveying chain.

[0005] In a first aspect, the present application provides a carton conveying method for a production line, wherein the production line includes a carton accumulating conveying device for a fully automatic box gluer, a long-distance accumulation conveyor chain, and a guide roller, the method comprising the following steps:

[0006] Collect depth images of cartons on a power-and-free conveyor chain from different angles;

[0007] Extract edge features of each carton from all depth images;

[0008] determining a displacement deviation gradient of each group of adjacent cartons during conveyance based on edge features of each group of adjacent cartons and the conveying speed of the power-and-free conveyor chain, and predicting a cumulative position deviation of each cartons upon arrival at a storage area based on all displacement deviation gradients and the vibration characteristics of the power-and-free conveyor chain;

[0009] Perform multi-angle correlation constraints on the posture angles of each carton on the conveyor line through all edge features to obtain the adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each carton;

[0010] Based on all the accumulated position deviations and the adjustable range of the optimal compensation angle, the queue intervals between the cartons during the conveying process are coordinated to obtain a coordinated queue of the cartons during the conveying process, and then the cartons on the production line are conveyed according to the coordinated queue.

[0011] In some embodiments, extracting edge features of each carton from all depth images specifically includes:

[0012] Grayscale all depth images to obtain multiple grayscale images;

[0013] Perform edge detection on each grayscale image to obtain the edge features of each paper box.

[0014] In some embodiments, determining the displacement deviation gradient of each group of adjacent cartons during the conveying process according to the edge features of each group of adjacent cartons and the conveying speed of the accumulation conveyor chain specifically includes:

[0015] Obtaining a conveying speed of the power-and-free conveyor chain;

[0016] Determine the center representative point of each carton based on all edge features;

[0017] A group of adjacent paper boxes are selected as selected adjacent paper boxes, and a distance between the selected adjacent paper boxes is determined based on a central representative point corresponding to each paper box in the selected adjacent paper boxes;

[0018] Determining the displacement deviation gradient of selected adjacent cartons during the conveying process based on the distance and the conveying speed;

[0019] Continue to determine the displacement deviation gradients of the remaining adjacent cartons during the conveying process.

[0020] In some embodiments, predicting the cumulative position deviation of each carton when it arrives at the storage area based on all displacement deviation gradients and the vibration characteristics of the power-and-free conveyor chain specifically includes:

[0021] determining a vibration characteristic of the power and free conveyor chain;

[0022] Selecting a carton as a selected carton and determining an estimated time for the selected carton to arrive at the storage area;

[0023] determining a position influence characteristic of the selected carton based on the estimated time and the vibration characteristic;

[0024] determining the cumulative position deviation of the selected carton when it arrives at the storage area by using the respective displacement deviation gradients corresponding to the selected carton and the position influence characteristics;

[0025] Continue to determine the cumulative position deviation of the remaining cartons as they arrive at the storage area.

[0026] In some embodiments, multi-angle association constraints are applied to the posture angles of each carton on the conveyor line through all edge features, and the adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each carton is obtained, specifically including:

[0027] Selecting a paper box as a selected paper box, and generating point cloud data of the selected paper box according to edge features of the selected paper box;

[0028] Determine the posture deviation angle of the selected paper box through the point cloud data;

[0029] Continue to determine the posture deviation angles of the remaining cartons;

[0030] Obtaining the posture angle of each carton on the conveyor line;

[0031] The multi-angle correlation of the posture angles of each carton is performed through all posture deviation angles to obtain the multi-angle correlation information of the cartons on the accumulation conveyor chain;

[0032] Determining angle adjustment information of the guide roller;

[0033] The adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each paper box is determined according to the multi-angle association information and the angle adjustment information.

[0034] In some embodiments, based on all accumulated position deviations and the adjustable range of the optimal compensation angle, the queue intervals between the cartons during the conveying process are collaboratively adjusted to obtain the collaborative queue of the cartons during the conveying process, specifically including:

[0035] Determine the collaborative analysis amount of each carton when it is arranged in the conveying process based on all the accumulated position deviations;

[0036] Determining the degree of coupling between the orientations of adjacent cartons during the arrangement process through all the coordinated analysis quantities and the adjustable range of the optimal compensation angle;

[0037] Determine a coupling degree threshold between adjacent cartons;

[0038] Extracting the coupling degrees between the adjacent paper box orientations that are lower than the coupling degree threshold;

[0039] According to the extracted coupling degree, the orientation of the corresponding adjacent carton is adjusted to obtain the arrangement result of the extracted coupling degree on the corresponding adjacent carton.

[0040] The orientation of the corresponding adjacent carton of the unextracted coupling degree is kept unchanged to obtain the arrangement result of the unextracted coupling degree on the corresponding adjacent carton.

[0041] The above two arrangement results are used as the cooperative queue of the carton in the conveying process.

[0042] In some embodiments, the accumulation and conveying chain includes a loading area, a conveying area, an unloading area, a tensioning area, a monitoring area, a turning area, and a buffer area.

[0043] In a second aspect, the application provides an accumulation and conveying device for a full-automatic carton box filling machine, which comprises a carton conveying unit, and the carton conveying unit comprises:

[0044] A collection module is configured to collect depth images of the carton from different angles on the accumulation and conveying chain.

[0045] A processing module is configured to extract edge features of each carton from all the depth images.

[0046] The processing module is further configured to determine displacement deviation gradients of each group of adjacent cartons in the conveying process according to the edge features of each group of adjacent cartons and the conveying speed of the accumulation and conveying chain, and predict cumulative position deviations of each carton when reaching the storage area based on all the displacement deviation gradients and vibration characteristics of the accumulation and conveying chain.

[0047] The processing module is further configured to perform multi-angle correlation constraint on the posture angle of each carton on the conveying line through all the edge features to obtain an adjustable range of the best compensation angle of the guide roller for dynamic pre-adjustment of each carton.

[0048] An execution module is configured to cooperatively adjust the queue interval between each carton in the conveying process based on all the cumulative position deviations and the adjustable range of the best compensation angle to obtain a cooperative queue of the carton in the conveying process, and then convey the carton on the production line according to the cooperative queue.

[0049] In a third aspect, the application provides a computer device, which comprises a memory and a processor, the memory stores a code, and the processor is configured to acquire the code and execute the above-mentioned carton conveying method for a production line.

[0050] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which implements the above-mentioned carton conveying method for a production line when executed by a processor.

[0051] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0052] In the box-accumulating conveying device and method for a fully automatic box gluer provided in the present application, first, depth images of cartons on an accumulating conveyor chain at different viewing angles are collected; edge features of each carton are extracted from all depth images; the displacement deviation gradient of each group of adjacent cartons during the conveying process is determined based on the edge features of each group of adjacent cartons and the conveying speed of the accumulating conveyor chain, and the cumulative position deviation of each carton when it arrives at the storage area is predicted based on all displacement deviation gradients and the vibration characteristics of the accumulating conveyor chain; multi-angle correlation constraints are performed on the posture angles of each carton on the conveyor line through all edge features to obtain the adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each carton; the queue intervals between each carton during the conveying process are coordinated and adjusted based on all cumulative position deviations and the adjustable range of the optimal compensation angle to obtain a coordinated queue of the cartons during the conveying process, and then the cartons on the production line are conveyed according to the coordinated queue.

[0053] It can be seen that in the process of accumulating boxes, the present application first establishes a three-dimensional edge feature model of the carton contour through feature fusion processing of multi-source depth images, effectively eliminating the feature extraction error caused by occlusion or overlap, and then determines the displacement deviation gradient according to the edge features and conveying speed of each group of adjacent cartons, and predicts the cumulative position deviation based on the vibration characteristics, thereby realizing distributed perception and collaborative prediction of the displacement deviation of the carton group during the conveying process, breaking through the limitations of traditional single-point adjustment and effectively avoiding the chain position interference caused by local adjustment; then, the carton posture angle is multi-angle associated with the edge feature to obtain the adjustable range of the optimal compensation angle of the guide roller, and the multi-angle associated constraint is used to dynamically optimize the compensation angle of the guide roller so that the compensation action simultaneously meets the current carton correction requirements and the position constraints of adjacent cartons; then, the queue interval is collaboratively adjusted based on the cumulative position deviation and the optimal compensation angle to form a collaborative queue, and distributed collaborative optimization of the carton queue is realized, thereby improving the overall conveying stability and effectively avoiding the chain reaction deviation caused by single-point adjustment; finally, the cartons on the production line are conveyed according to the collaborative queue to complete the conveying of the cartons on the accumulation conveyor chain. By adopting the above scheme, group posture collaborative control can be achieved to reduce the chain deviation caused by single-point adjustment of the carton on the accumulation and release conveyor chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1is an exemplary flow chart of a carton conveying method for a production line according to some embodiments of the present application;

[0055] Figure 2 1. It is a structural diagram of a power-and-free conveyor chain from different perspectives according to some embodiments of the present application;

[0056] Figure 3 is an exemplary flow chart of determining a displacement deviation gradient according to some embodiments of the present application;

[0057] Figure 4 is a structural schematic diagram of a carton conveying unit according to some embodiments of the present application;

[0058] Figure 5 It is a structural schematic diagram of a computer device for implementing a carton conveying method for a production line according to some embodiments of the present application. DETAILED DESCRIPTION

[0059] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0060] refer to Figure 1 This figure is an exemplary flow chart of a carton conveying method for a production line according to some embodiments of the present application. In this embodiment, the production line includes a carton accumulating conveying device for a fully automatic box gluer, a long-distance accumulation conveyor chain, and a guide roller. The carton conveying method 100 for the production line mainly includes the following steps:

[0061] In step 101, depth images of cartons on a power-and-free conveyor chain at different viewing angles are collected.

[0062] The depth image represents a depth image of the cartons on the accumulation conveyor chain in the detection area, and can be used to determine the geometric shapes of the cartons on the accumulation conveyor chain in the detection area.

[0063] In specific implementation, collection nodes are arranged at different perspectives in the detection area of ​​the accumulation and release conveyor chain, and depth images of the perspective corresponding to each collection node are collected at the collection node. The specific collection equipment can be, for example, a charge coupled device camera, a complementary metal oxide semiconductor camera, a 3D camera, etc., which is not specifically limited here. In other embodiments, other collection methods can also be used, which are not limited here.

[0064] It should be noted that the detection area in this application refers to the area on the accumulation conveyor chain for detecting the state of the carton. In some embodiments, reference Figure 2 As shown, this figure is a structural diagram of different perspectives on the accumulation and release conveyor chain in some embodiments of the present application, such as Figure 2The different view angles include a top view angle (e.g., installed vertically above the detection area), a side view angle (e.g., symmetrically installed on both sides of the detection area, horizontally or slightly inclined to the plane of the detection area), a front and rear view angle (e.g., installed at the beginning and end of the detection area, facing the direction of movement of the carton), and an oblique view angle (e.g., installed on a support or gantry at an angle of 45°-60° to the detection area).

[0065] In step 102, edge features of each carton are extracted from all depth images.

[0066] In some embodiments, the edge features of each carton can be extracted from all depth images by the following steps:

[0067] Grayscale processing is performed on all depth images to obtain a plurality of grayscale images.

[0068] Edge detection is performed on each grayscale image to obtain the edge features of each carton.

[0069] In a specific implementation, grayscale processing can be performed on all depth images to obtain a plurality of grayscale images by the following method: first, a denoising and smoothing preprocessing operation is performed on each depth image by a filtering method (e.g., bilateral filtering, guided filtering) in the prior art to improve image quality and reduce noise interference, and then each preprocessed depth image is converted into a grayscale image by a linear normalization method, thereby obtaining a plurality of grayscale images, which can be used for edge detection of the cartons on the accumulation and conveying chain; edge detection can be performed on each grayscale image to obtain the edge features of each carton by the following method: an edge detection algorithm is used to detect the edges of the cartons in each grayscale image, and the regions with obvious grayscale changes in the grayscale image are detected, thereby determining the edge positions of each carton in each grayscale image; a multi-view edge point clustering method (e.g., DBSCAN, Euclidean clustering) in the prior art is used to merge the edge points of the overlapping regions of the same carton at different edge positions, thereby obtaining the three-dimensional edges of each carton; the edge contour of the carton is extracted from the three-dimensional edges, and the edge contour of each carton is taken as the edge feature of the corresponding carton; in other embodiments, other methods can also be used to determine the edge features, which are not limited here.

[0070] It should be noted that the edge features in the present application represent the features of the edge contour of the carton on the accumulation and conveying chain, which can be used to distinguish the cartons on the accumulation and conveying chain.

[0071] In step 103, the displacement deviation gradient of each group of adjacent cartons during the conveying process is determined according to the edge characteristics of each group of adjacent cartons and the conveying speed of the accumulation conveyor chain, and the cumulative position deviation of each carton when it arrives at the storage area is predicted based on all the displacement deviation gradients and the vibration characteristics of the accumulation conveyor chain.

[0072] In some embodiments, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart for determining the displacement deviation gradient in some embodiments of the present application. In this embodiment, the displacement deviation gradient of each group of adjacent cartons during the conveying process is determined based on the edge features of each group of adjacent cartons and the conveying speed of the accumulation conveyor chain. The following steps can be used to achieve this:

[0073] First, in step 1031, the conveying speed of the power-and-free conveyor chain is obtained;

[0074] Next, in step 1032 , the center representative point of each carton is determined based on all edge features;

[0075] Then, in step 1033, a group of adjacent paper boxes are selected as selected adjacent paper boxes, and the distance between the selected adjacent paper boxes is determined based on the central representative points corresponding to the respective paper boxes in the selected adjacent paper boxes;

[0076] Thus, in step 1034, the displacement deviation gradient of the selected adjacent cartons during the conveying process is determined by the distance and the conveying speed;

[0077] Finally, in step 1035 , the displacement deviation gradients of the remaining adjacent cartons during the conveying process are further determined.

[0078] In specific implementation, the conveying speed of the accumulating conveyor chain can be obtained in the following manner, namely: collecting the conveying speed of the accumulating conveyor chain from the database of the fully automatic box gluer, wherein the conveying speed represents the speed of the accumulating conveyor chain when conveying cartons, and the conveying speed includes the speed of each area on the accumulating conveyor chain, each area including the loading area, conveying area, unloading area, tensioning area, monitoring area, turning area, and buffer area. Since the functions of each area are different, the transmission speed of each area is different; in other embodiments, other methods can also be used to determine, which is not limited here.

[0079] In specific implementation, the following method can be used to determine the center representative point of each paper box based on all edge features, namely: select a paper box as the selected paper box, and calculate the center point of the selected paper box based on the average of polygon vertices. The steps are: first, polygon approximation is performed on all edge points based on the edge features of the selected paper box to obtain the coordinates of each vertex, and then the average of all vertex coordinates is used as the center point, and the center point is used as the center representative point of the selected paper box, and the center representative points of the remaining paper boxes are continued to be determined, wherein the center representative point represents the representative point of the center position of the paper box; in other embodiments, other determinations can also be used, which are not limited here.

[0080] In specific implementation, the distance between selected adjacent paper boxes is determined based on the central representative points corresponding to each paper box in the selected adjacent paper boxes, which can be achieved in the following manner, namely: the distance between the selected adjacent paper boxes is calculated by combining the Euclidean distance in the prior art with the coordinates of the central representative points corresponding to each paper box in the selected adjacent paper boxes; the displacement deviation gradient of the displacement deviation of the selected adjacent paper boxes during the conveying process is determined by the distance and the conveying speed, which can be achieved in the following manner, namely: the displacement deviation represents the degree of deviation of the distance between adjacent paper boxes during the movement on the accumulation conveyor chain, and a displacement deviation gradient model of the displacement deviation is constructed based on the speed change, taking into account the influence of the conveying speed of the accumulation conveyor chain on the distance between paper boxes. A relationship model between phase difference and speed change is established. When the speed of the accumulation conveyor chain changes, the spacing between the cartons will also change accordingly, thereby generating a phase difference. Therefore, the relationship model is constructed using the phase difference change data of the historical cartons on the accumulation conveyor chain during the conveying process, and the model is optimized by the cross-validation method. The optimized model is used as a displacement deviation gradient model, and the current distance between the selected adjacent cartons and the conveying speed of the accumulation conveyor chain are input into the displacement deviation gradient model. The displacement deviation gradient of the selected adjacent cartons during the conveying process is calculated through the displacement deviation gradient model. In some embodiments, other methods can also be used for determination, which are not limited here.

[0081] It should be noted that the displacement deviation gradient in this application represents the gradient of change in the displacement deviation between adjacent cartons during the conveying process, which can be used to adjust the position of cartons on the accumulation conveyor chain, thereby reducing the accumulation of cartons on the accumulation conveyor chain.

[0082] In some embodiments, the following steps may be used to predict the cumulative position deviation of each carton when it arrives at the storage area based on all displacement deviation gradients and the vibration characteristics of the power-and-free conveyor chain:

[0083] determining a vibration characteristic of the power and free conveyor chain;

[0084] Selecting a carton as a selected carton and determining an estimated time for the selected carton to arrive at the storage area;

[0085] determining a position influence characteristic of the selected carton based on the estimated time and the vibration characteristic;

[0086] determining the cumulative position deviation of the selected carton when it arrives at the storage area by using the respective displacement deviation gradients corresponding to the selected carton and the position influence characteristics;

[0087] Continue to determine the cumulative position deviation of the remaining cartons as they arrive at the storage area.

[0088] In specific implementation, the vibration characteristics of the accumulation conveyor chain can be determined in the following manner, namely: the vibration frequency of each area on the accumulation conveyor chain is collected by a vibration sensor, and the set of all vibration frequencies is used as a vibration characteristic, wherein the vibration characteristic represents the characteristic of the vibration frequency on the accumulation conveyor chain; the estimated time for the selected carton to arrive at the storage area can be determined in the following manner, namely: the time for each historical carton to arrive at the storage area is extracted from the time recorder of the full-automatic box gluer, and the average time of all times is used as the estimated time for the selected carton to arrive at the storage area, wherein the estimated time represents the estimated time for the carton to arrive at the storage area from the starting end of the accumulation conveyor chain; the position of the selected carton is determined according to the estimated time and the vibration characteristic. The position influence feature can be realized in the following manner, namely: the weight of the selected carton is collected by a weight sensor, the variance of all vibration frequencies in the vibration feature is calculated to obtain the degree of vibration fluctuation on the accumulation type conveyor chain, the variance is divided by the weight, indicating that the vibration feature is standardized to the frequency fluctuation under unit weight, the value obtained by the division is multiplied by the expected time, the multiplied value is subjected to a natural exponential operation to simulate the nonlinear growth or attenuation of the vibration of the carton during the transportation process, and the inverse of the value obtained by the natural exponential operation is used as the characterization value of the position influence feature of the selected carton, wherein the position influence feature represents the characteristics of the degree of influence of time and the friction of the accumulation type conveyor chain on the position of the carton; in other embodiments, other methods can also be used for determination, which are not limited here.

[0089] In specific implementation, the cumulative position deviation of the selected paper box when it arrives at the storage area is determined by selecting the corresponding displacement deviation gradients and the position influence characteristics of the paper box, which can be achieved in the following manner, namely: based on Newtonian mechanics, the relationship between phase difference and displacement is derived, a cumulative position deviation model is initialized, and a cumulative position deviation model is constructed through a machine learning algorithm (such as linear regression, neural network), and the relationship between phase difference and displacement is used to train the cumulative position deviation model, and the weight coefficients A and B are determined, and the cumulative position deviation model is optimized through a cross-validation method. The structure of this model is: cumulative position deviation = phase difference * A + position influence characteristic * B, and the corresponding displacement deviation gradients and position influence characteristics of the selected paper box are input into the cumulative position deviation model, and the cumulative position deviation of the selected paper box when it arrives at the storage area is output through the cumulative position deviation model; in other embodiments, other methods can also be used for determination, which are not limited here.

[0090] It should be noted that the cumulative position deviation in this application represents the parameter value of the degree of deviation of the position of the carton on the accumulation conveyor chain, which can be used to make overall adjustments to the carton on the accumulation conveyor chain, thereby reducing interference between the carton on the accumulation conveyor chain.

[0091] In step 104, multi-angle correlation constraints are performed on the posture angles of each carton on the conveyor line through all edge features to obtain the adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each carton.

[0092] In some embodiments, multi-angle association constraints are applied to the posture angles of each carton on the conveyor line through all edge features to obtain the adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each carton. The following steps can be used:

[0093] Selecting a paper box as a selected paper box, and generating point cloud data of the selected paper box according to edge features of the selected paper box;

[0094] Determine the posture deviation angle of the selected paper box through the point cloud data;

[0095] Continue to determine the posture deviation angles of the remaining cartons;

[0096] Obtaining the posture angle of each carton on the conveyor line;

[0097] The multi-angle correlation of the posture angles of each carton is performed through all posture deviation angles to obtain the multi-angle correlation information of the cartons on the accumulation conveyor chain;

[0098] Determining angle adjustment information of the guide roller;

[0099] The adjustable range of the optimal compensation angle of the guiding roller pair for dynamically pre-adjusting each carton is determined according to the multi-angle correlation information and the angle adjustment information.

[0100] In a specific implementation, the point cloud data of the selected carton can be generated according to the edge feature of the selected carton in the following manner: the 3D edge point coordinates of the edge feature of the selected carton in the 3D space corresponding to the depth image are calculated by triangulation in the prior art, and the 3D edge point coordinates of the selected carton are generated into 3D edge points of the carton by SFM (Structure from Motion), and all 3D point clouds are generated according to the 3D edge points by using multi-view stereo, and all 3D point clouds are used as the point cloud data of the selected carton, wherein the point cloud data represents the data of the three-dimensional points of the edge of the carton on the accumulation type conveying chain, and can be used to represent the spatial set structure of the carton; the attitude offset angle of the selected carton can be determined in the following manner: the point cloud data is matched with the pre-established three-dimensional model of the carton, the alignment of the point cloud can be performed by using the iterative closest point algorithm, and the current attitude angle of the carton after the matching of the point cloud is calculated by Euler angle, the target attitude is obtained from the database of the full-automatic carton pasting machine, and the difference between the current attitude angle and the attitude angle of the target attitude is used as the attitude offset angle of the selected carton, wherein the attitude offset angle represents the offset degree of the angle between the current carton and the target carton attitude angle, and can be used to analyze the correction of the attitude of the carton; in other embodiments, other manners can also be used to determine, which are not limited here.

[0101] In a specific implementation, the attitude angle of each carton on the conveying line can be obtained in the following manner: the edge feature of each carton is obtained, the four corner points of each carton are located by combining the edge feature with a corner point detection method (such as Harris corner point detection and Shi-Tomasi algorithm), the accumulation type conveying chain is used as a reference surface, and the attitude angle of the corresponding carton is calculated based on an attitude calculation method (such as Perspective-n-Point) combined with the coordinates of the four corner points of each carton, wherein the attitude angle represents the angle of the attitude of the carton relative to the accumulation type conveying chain; in other embodiments, other manners can also be used to determine, which are not limited here.

[0102] In specific implementation, multi-angle association is performed on the posture angles of each carton through all posture offset angles, and the multi-angle association information of the carton on the accumulation conveyor chain is obtained. This can be achieved in the following way, namely: a group of adjacent carton boxes are selected as selected adjacent carton boxes, and the difference between the posture angle corresponding to the first carton in the selected adjacent carton boxes and the posture angle corresponding to the second carton is used as the first angle, and the difference between the posture offset angle corresponding to the first carton in the selected adjacent carton boxes and the posture offset angle corresponding to the second carton is used as the second angle, and the vector composed of the first angle and the second angle is used as the multi-angle association vector between adjacent carton boxes, and the multi-angle association vectors between the remaining adjacent carton boxes are continued to be determined, and the set of all multi-angle association vectors is used as the multi-angle association information of the carton on the accumulation conveyor chain, wherein the multi-angle association information represents information on the association between multiple angles of the carton on the accumulation conveyor chain; in other embodiments, other methods can also be used for determination, which is not limited here.

[0103] In specific implementation, the angle adjustment information of the guide roller can be determined in the following manner, namely: the guide roller is a roller used to adjust the direction and angle of the paper box on the accumulation conveyor chain, the position and angle of the guide roller on the accumulation conveyor chain are collected by a position sensor and an angle sensor, the geometric relationship between the guide roller and related components is analyzed by a geometric analysis method in combination with the position and angle, and the angle adjustment amount that the guide roller needs to be adjusted is determined, and the set of the angle adjustment amount and the current angle is used as the angle adjustment information of the guide roller, wherein the angle adjustment information represents the information that the guide roller adjusts the direction of the paper box on the accumulation conveyor chain; in other embodiments, other methods can also be used to determine, which are not limited here.

[0104] In specific implementation, the following method can be used to determine the adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each paper box based on the multi-angle association information and the angle adjustment information, namely: constructing an angle constraint model based on a machine learning library (such as random forest, neural network), training the angle constraint model through the angle adjustment data of the guide roller and each historical paper box, and optimizing the angle constraint model through a cross-validation method, using the association information and adjustment information as input features of the association model, using the adjustable range of the optimal compensation angle as output features of the association model, inputting the multi-angle association information and the angle adjustment information into the association model to update the association information and adjustment information, and outputting the adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each paper box through the association model; in other embodiments, other methods can also be used for determination, which are not limited here.

[0105] It should be noted that the adjustable range in this application represents the adjustment range within which the guide roller can efficiently correct the angle of each paper box when adjusting the angle of each paper box. It can be used to control the angle correction of all paper boxes on the accumulation conveyor chain by the guide roller, thereby reducing the angle rotation rate of the guide roller to achieve low-power control of the guide roller angle.

[0106] In step 105, based on all accumulated position deviations and the adjustable range of the optimal compensation angle, the queue intervals between the cartons during the conveying process are collaboratively adjusted to obtain a collaborative queue of the cartons during the conveying process, and then the cartons on the production line are conveyed according to the collaborative queue.

[0107] In some embodiments, based on all accumulated position deviations and the adjustable range of the optimal compensation angle, the queue intervals between the cartons during the conveying process are collaboratively adjusted to obtain a collaborative queue of cartons during the conveying process. This can be achieved by the following steps:

[0108] Determine the collaborative analysis amount of each carton when it is arranged in the conveying process based on all the accumulated position deviations;

[0109] Determining the degree of coupling between the orientations of adjacent cartons during the arrangement process through all the coordinated analysis quantities and the adjustable range of the optimal compensation angle;

[0110] Determining a coupling degree threshold between adjacent cartons;

[0111] Extracting the coupling degrees between the adjacent paper box orientations that are lower than the coupling degree threshold;

[0112] Adjusting the positions of the adjacent paper boxes corresponding to the extracted coupling degree pairs to obtain arrangement results of the adjacent paper boxes corresponding to the extracted coupling degree pairs;

[0113] The positions of the adjacent paper boxes corresponding to the unextracted coupling degrees are kept unchanged, and the arrangement results of the adjacent paper boxes corresponding to the unextracted coupling degree pairs are obtained;

[0114] The above two arrangement results are used as the collaborative queues of the cartons during the transportation process.

[0115] In specific implementation, the collaborative analysis amount of each carton when it is arranged in the conveying process according to all the accumulated position deviations can be achieved in the following way, that is: according to the kinematic and dynamic characteristics of the carton during the conveying process, a mathematical relationship model between the carton arrangement and the accumulated position deviation is established, and the motion trajectory and force conditions of each carton on the conveying equipment are analyzed through this mathematical relationship model in combination with all the accumulated position deviations, so as to derive the collaborative analysis amount corresponding to each carton, wherein the collaborative analysis amount represents the parameter value of the adjustment degree of each carton on the accumulation conveyor chain when performing collaborative analysis; the adjacent carton positions in the arrangement process are determined by all the collaborative analysis amounts and the adjustable range of the optimal compensation angle. The coupling degree between the orientations of the cartons can be achieved in the following manner, namely: based on the coupling coordination degree model, the coupling degree of the cartons is defined as the degree of matching between the collaborative analysis quantity and the ideal adjustment quantity under the adjustable range of the optimal compensation angle, and a specific mathematical method (such as weighted summation, multivariate regression) is used as the calculation formula for the matching degree, a group of adjacent cartons are selected as selected adjacent cartons, the mean of the two collaborative analysis quantities corresponding to the selected adjacent cartons and the adjustable range of the optimal compensation angle are input into the calculation formula, and the value calculated by the calculation formula is used as the coupling degree between the orientations of the adjacent cartons, and the coupling degree between the remaining adjacent cartons orientations is continued to be determined; in other embodiments, other methods can also be adopted for determination, which are not limited here.

[0116] It should be noted that the coupling degree in this application represents the parameter value of the coupling degree between the orientations of two cartons in the orientation arrangement during the process of conveying cartons by the accumulation type conveyor chain, which can be used to arrange the cartons on the accumulation type conveyor chain to obtain an orientation arrangement with better coordination effect.

[0117] In specific implementation, determining the coupling degree threshold between adjacent paper boxes can be achieved in the following manner, namely: if the coupling degree between adjacent paper boxes is low, a large amount of stacking misalignment will occur when the adjacent paper boxes are transported to the storage area, and coupling degree data between adjacent paper boxes with low historical misalignment are extracted from the full-automatic box gluer, and the average of all coupling degrees in the coupling degree data is used as the coupling degree threshold between adjacent paper boxes. When the coupling degree of the orientations between adjacent paper boxes during the transportation process reaches the coupling degree threshold, the misalignment of the adjacent paper boxes when transported to the storage area is low, and thus there is no need for secondary stacking; adjusting the orientations of the corresponding adjacent paper boxes according to each extracted coupling degree pair to obtain the arrangement results of the corresponding adjacent paper boxes for each extracted coupling degree pair can be achieved in the following manner, namely: adjusting the orientations of the corresponding adjacent paper boxes for each extracted coupling degree pair by means of a guide roller until the coupling degree between each adjacent paper box is greater than the coupling degree threshold, then there is no need to adjust the orientations of the adjacent paper boxes, and the orientation arrangement of each paper box obtained after the adjustment is used as the arrangement result of the corresponding adjacent paper boxes for each coupling degree pair that has not been extracted.

[0118] In a specific implementation, the paper box on the production line is transported according to the coordinated queue in the following manner: the coordinated queue is transported to a control system of the production line, the control parameters of the production line are adjusted through an adjustment model of the control system, and the paper box transportation process of the production line is controlled through the adjusted control parameters; in other embodiments, other manners can also be used for control, which is not limited here.

[0119] In addition, another aspect of the present application, in some embodiments, the present application provides a paper box conveying device for a full-automatic cartoning machine, which comprises a paper box conveying unit, referring to Figure 4 The figure is a structural schematic diagram of a paper box conveying unit according to some embodiments of the present application, which comprises a collection module 401, a processing module 402 and an execution module 403, which are described as follows:

[0120] The collection module 401 is mainly used for collecting depth images of different angles of the paper boxes on the accumulation type conveying chain in the present application;

[0121] The processing module 402 is used for extracting edge features of each paper box from all the depth images in the present application;

[0122] It should be noted that the processing module 402 is also used for determining displacement deviation gradients of each group of adjacent paper boxes in the conveying process according to the edge features of each group of adjacent paper boxes and the conveying speed of the accumulation type conveying chain, and predicting cumulative position deviations of each paper box when reaching the storage area based on all the displacement deviation gradients and the vibration characteristics of the accumulation type conveying chain;

[0123] In addition, it should be noted that the processing module 402 is also used for performing multi-angle correlation constraint on the posture angles of each paper box on the conveying line through all the edge features, and obtaining an adjustable range of the best compensation angle of the guide roller for dynamic pre-adjustment of each paper box;

[0124] The execution module 403 is mainly used for cooperatively adjusting the queue interval between each paper box in the conveying process based on all the cumulative position deviations and the adjustable range of the best compensation angle, obtaining the coordinated queue of the paper boxes in the conveying process, and then transporting the paper boxes on the production line according to the coordinated queue.

[0125] In addition, the present application also provides a computer device, which comprises a memory and a processor, the memory stores a code, and the processor is configured to acquire the code and execute the above-mentioned paper box conveying method for the production line.

[0126] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing a carton conveying method for a production line according to some embodiments of the present application. The carton conveying method for a production line in the above embodiment can be achieved by Figure 5 The computer device 500 shown in FIG. 5 is implemented as shown in FIG. 5 . The computer device 500 includes at least one processor 501 , a communication bus 502 , a memory 503 , and at least one communication interface 504 .

[0127] The processor 501 may be a general-purpose central processing unit (CPU) or an application specific integrated circuit (ASIC).

[0128] The communication bus 502 may be used to transmit information between the aforementioned components.

[0129] The memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD ROM) or other optical disc storage, an optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory 503 may be independent and connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0130] The memory 503 is used to store program code for executing the solution of the present application, and is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The method used in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0131] The communication interface 504 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0132] In a specific implementation, as an example, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0133] The aforementioned computer device can be a general-purpose computer device or a dedicated computer device. In a specific implementation, the computer device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of this application do not limit the type of computer device.

[0134] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned carton conveying method for a production line.

[0135] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0136] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A carton conveying method for a production line, wherein the production line comprises a carton accumulating conveying device for a fully automatic box gluer, a long-distance accumulation conveying chain and a guide roller, characterized in that: The method comprises the following steps: Collect depth images of cartons on a power-and-free conveyor chain from different angles; Extract edge features of each carton from all depth images; determining a displacement deviation gradient of each group of adjacent cartons during conveyance based on edge features of each group of adjacent cartons and the conveying speed of the power-and-free conveyor chain, and predicting a cumulative position deviation of each cartons upon arrival at a storage area based on all displacement deviation gradients and the vibration characteristics of the power-and-free conveyor chain; By using all edge features, multi-angle correlation constraints are applied to the posture angles of each carton on the conveyor line to obtain the adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each carton; Based on all accumulated position deviations and the adjustable range of the optimal compensation angle, the queue intervals between the cartons during the conveying process are coordinated to obtain a coordinated queue of the cartons during the conveying process, and then the cartons on the production line are conveyed according to the coordinated queue; The step of determining the displacement deviation gradient of each group of adjacent cartons during the conveying process according to the edge features of each group of adjacent cartons and the conveying speed of the accumulation conveyor chain specifically includes: Obtaining a conveying speed of the power-and-free conveyor chain; Determine the center representative point of each carton based on all edge features; A group of adjacent paper boxes are selected as selected adjacent paper boxes, and a distance between the selected adjacent paper boxes is determined based on a central representative point corresponding to each paper box in the selected adjacent paper boxes; Determining the displacement deviation gradient of selected adjacent cartons during the conveying process based on the distance and the conveying speed; Continue to determine the displacement deviation gradients of the remaining adjacent cartons during the conveying process; The method of predicting the cumulative position deviation of each carton when it arrives at the storage area based on all displacement deviation gradients and the vibration characteristics of the power-and-free conveyor chain specifically includes: determining a vibration characteristic of the power and free conveyor chain; Selecting a carton as a selected carton and determining an estimated time for the selected carton to arrive at the storage area; determining a position influence characteristic of the selected carton based on the estimated time and the vibration characteristic; determining the cumulative position deviation of the selected carton when it arrives at the storage area by using the respective displacement deviation gradients corresponding to the selected carton and the position influence characteristics; Continue to determine the cumulative position deviation of the remaining cartons when they arrive at the storage area; Among them, multi-angle correlation constraints are performed on the posture angles of each carton on the conveyor line through all edge features, and the adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each carton is obtained, specifically including: Selecting a paper box as a selected paper box, and generating point cloud data of the selected paper box according to edge features of the selected paper box; Determine the posture deviation angle of the selected paper box through the point cloud data; Continue to determine the posture deviation angles of the remaining cartons; Obtaining the posture angle of each carton on the conveyor line; The multi-angle correlation of the posture angles of each carton is performed through all posture deviation angles to obtain the multi-angle correlation information of the cartons on the accumulation conveyor chain; Determining angle adjustment information of the guide roller; Determining an adjustable range of an optimal compensation angle when the guide roller dynamically pre-adjusts each paper box according to the multi-angle association information and the angle adjustment information; The coordinated adjustment of the queue intervals between the cartons during the conveying process is performed based on all accumulated position deviations and the adjustable range of the optimal compensation angle, and the coordinated queue of the cartons during the conveying process is obtained, specifically including: Determine the collaborative analysis amount of each carton when it is arranged in the conveying process based on all the accumulated position deviations; Determining the degree of coupling between the orientations of adjacent cartons during the arrangement process through all the coordinated analysis quantities and the adjustable range of the optimal compensation angle; Determine a coupling degree threshold between adjacent cartons; Extracting the coupling degrees between the adjacent paper box orientations that are lower than the coupling degree threshold; Adjusting the positions of the adjacent paper boxes corresponding to the extracted coupling degree pairs to obtain arrangement results of the adjacent paper boxes corresponding to the extracted coupling degree pairs; The positions of the adjacent paper boxes corresponding to the unextracted coupling degrees are kept unchanged, and the arrangement results of the adjacent paper boxes corresponding to the unextracted coupling degree pairs are obtained; The above two arrangement results are used as the collaborative queues of the cartons during the transportation process.

2. The method according to claim 1, wherein Extracting edge features of each carton from all depth images specifically includes: Grayscale all depth images to obtain multiple grayscale images; Perform edge detection on each grayscale image to obtain the edge features of each paper box.

3. The method according to claim 1, wherein The accumulation and release conveyor chain includes a loading area, a conveying area, an unloading area, a tensioning area, a monitoring area, a turning area, and a buffer area.

4. A box stacking and conveying device for a fully automatic box gluer, which uses the method according to any one of claims 1 to 3 to convey cartons, and the box stacking and conveying device includes a carton conveying unit, characterized in that: The carton conveying unit comprises: The acquisition module is used to collect depth images of cartons on the accumulation conveyor chain from different perspectives; A processing module is used to extract edge features of each carton from all depth images; The processing module is further configured to determine a displacement deviation gradient of each group of adjacent cartons during conveyance based on edge features of each group of adjacent cartons and a conveying speed of the power-and-free conveyor chain, and to predict a cumulative position deviation of each cartons upon arrival at a storage area based on all displacement deviation gradients and vibration characteristics of the power-and-free conveyor chain; The processing module is further configured to perform multi-angle correlation constraints on the posture angles of each carton on the conveyor line through all edge features, thereby obtaining an adjustable range of the optimal compensation angle when the guide roller dynamically pre-adjusts each carton; The execution module is used to coordinately adjust the queue intervals between each carton during the conveying process based on all accumulated position deviations and the adjustable range of the optimal compensation angle, obtain a coordinated queue of the cartons during the conveying process, and then convey the cartons on the production line according to the coordinated queue.

5. A computer device, characterized in that: The computer device includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the carton conveying method for a production line according to any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the carton conveying method for a production line according to any one of claims 1 to 3 is implemented.

Images