A test paper rotary machine glue spraying control method, process, system, product and medium

Abstract

The application provides a printing plate rotary press glue spraying control method, process, system, product and medium, and relates to the technical field of glue spraying image equipment. A basic data set is established by acquiring continuous multiple frames of image data and extracting edge contour points and glue line feature points in the image data. The motion trajectory is obtained by calculating the displacement vector of the edge contour points and the glue line feature points between adjacent image data, and the vibration component is separated by performing spectrum analysis on the edge trajectory and the glue line trajectory. Then, the geometric constraint relationship of the booklet edge contour maintained in the deformation process is used, and a detection area is constructed according to the processed edge contour points and the corresponding processed glue line feature points. The change relationship between the edge trajectory and the processed edge contour points is adjusted to the detection area, so that the real-time self-adaptation of the detection area to the product deformation is realized. Through the optimization strategy combined with the physical characteristics, the stability of the detection reference and the accuracy of the glue line detection are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of glue spraying image equipment, and particularly relates to a glue spraying control method, process, system, product and medium for a booklet rotary machine. BACKGROUND

[0002] With the continuous improvement of the quality requirements of teaching materials and teaching aids in the education field, the quality control of the back glue process becomes particularly important in the production process of the booklet rotary machine for folding single A4 paper into multi-page booklet products. Due to the production efficiency requirements, the equipment usually needs to run at a high speed of 300-600 pages per minute.

[0003] At present, the quality control of the back glue of the booklet rotary machine mainly adopts a visual detection technology based on a preset reference point. The technology collects the back image of the product by installing an industrial camera on the production line, and extracts features based on the pre-calibrated image reference point. The system judges whether the position and shape of the glue line meet the requirements according to the corresponding relationship between the extracted features and the preset reference point, so as to evaluate the quality state of the glue line.

[0004] However, in the glue spraying process of the booklet rotary machine, the arc surface of the booklet back spine will be dynamically deformed due to the vibration of the equipment, and the displacement between the pages will occur under the action of the vibration due to the laminated folding structure (because the size of the booklet product is small, this misalignment phenomenon is more prominent). Due to the superposition of these two unstable factors, the system preset reference point cannot accurately reflect the actual detection reference, resulting in a deviation between the feature extraction result and the true state, and affecting the reliability of the detection result. SUMMARY

[0005] The present application provides a glue spraying control method, process, system, product and medium for a booklet rotary machine, which is used to improve the reliability of the detection result.

[0006] In a first aspect, the application provides a glue spraying control method for a book block rotary machine, comprising: acquiring continuous multiple frames of image data, the image data comprising a glue line spraying area of a folded back of a product; extracting edge contour points and glue line feature points in the image data; composing an edge contour point sequence and a glue line feature point sequence; calculating displacement vectors of the edge contour points between adjacent image data based on the edge contour point sequence to generate an edge trajectory; calculating displacement vectors of the glue line feature points between adjacent image data based on the glue line feature point sequence to generate a glue line trajectory; performing spectral analysis on the edge trajectory and the glue line trajectory respectively, separating out vibration components based on a preset frequency threshold to obtain processed edge contour points and processed glue line feature points; constructing a detection area according to the processed edge contour points and corresponding processed glue line feature points; adjusting the detection area according to a change relationship between the edge trajectory and the processed edge contour points to obtain a dynamic detection area adjusted over time; and performing integrity detection on the glue line feature points in the dynamic detection area, and outputting a glue line quality state evaluation result according to the integrity detection result.

[0007] By adopting the above technical solution, a basic data set is established by acquiring continuous multiple frames of image data and extracting edge contour points and glue line feature points in the image data. Because glue line deformation has continuity, while device vibration and page displacement exhibit jumping changes. Based on this characteristic, motion trajectories are obtained by calculating displacement vectors of the edge contour points and the glue line feature points between adjacent image data, and spectral analysis is performed on the edge trajectory and the glue line trajectory to separate out vibration components. Then, a detection area is constructed according to the processed edge contour points and corresponding processed glue line feature points by using the geometric constraint relationship maintained by the booklet edge contour in the deformation process. The detection area is adjusted according to a change relationship between the edge trajectory and the processed edge contour points to realize real-time self-adaptation of the detection area to product deformation. By combining an optimization strategy of physical characteristics, the stability of the detection reference and the accuracy of glue line detection are ensured.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of adjusting the detection area according to a change relationship between the edge trajectory and the processed edge contour points to obtain a dynamic detection area adjusted over time, the method further comprises: determining a fitting plane according to depth information of the edge contour points in the same image data; determining a transformation matrix of the fitting plane and a reference plane where the dynamic detection area is located; changing the dynamic detection area from the reference plane to the fitting plane according to the transformation matrix; projecting the dynamic detection area in the fitting plane from the fitting plane to the reference plane to obtain an optimized detection area; and performing integrity detection on the glue line feature points in the optimized detection area, and outputting a glue line quality state evaluation result according to the integrity detection result.

[0009] By adopting the technical scheme, the fitting plane is determined according to the depth information of the edge contour points, and a transformation relationship with the reference plane is established, so that accurate conversion of the detection region between different planes is realized. The dynamic detection region in the reference plane is converted to the fitting plane which is more suitable for the actual product surface, and then is projected back to the reference plane to obtain an optimized detection region, so that the detection region can be more accurately fitted to the actual product form. The region optimization method based on three-dimensional space effectively solves the detection deviation problem caused by the deformation of the product surface.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the step of determining the fitting plane according to the depth information of the edge contour points in the same image data specifically comprises: calculating the distance between all edge contour points and the plane in depth according to the depth information of the edge contour points; adjusting the plane to minimize the sum of the distances to obtain the fitting plane.

[0011] By adopting the technical scheme, when the fitting plane is determined, the distance of all edge contour points to the plane is calculated and minimized, so that the optimal fitting of the actual surface form of the product is realized. The fitting plane can be ensured to be most suitable for the actual surface state of the product, and a reliable spatial reference is provided for the subsequent detection region optimization.

[0012] In combination with some embodiments of the first aspect, in some embodiments, before the step of determining the fitting plane according to the depth information of the edge contour points in the same image data, the method further comprises: tracking the displacement change of the edge contour points between adjacent frame image data; calculating a scale factor of the feature points based on a preset actual size of the edge contour; constructing a fundamental matrix according to the displacement change, combining with a camera parameter decomposition to obtain a relative motion matrix, and applying the scale factor to the relative motion matrix to obtain a motion matrix; obtaining the depth information of the edge contour points by triangulation.

[0013] By adopting the technical scheme, the fundamental data is obtained by tracking the displacement change of the edge contour points, and the scale factor is calculated based on the preset actual size, so that the proportional accuracy of the depth calculation is ensured. The relative motion matrix is obtained by constructing the fundamental matrix and combining with the camera parameter decomposition, and then the scale factor is applied to obtain the motion matrix of the true scale, and finally the accurate depth information is obtained by triangulation, so as to provide reliable three-dimensional space data for the construction of the fitting plane.

[0014] With reference to some embodiments of the first aspect, in some embodiments, the steps of performing spectrum analysis on the edge track and the glue line track respectively, and separating out the vibration component based on a preset frequency threshold to obtain the processed edge contour points and the processed glue line feature points specifically include: performing sliding window segmentation processing on the edge track and the glue line track respectively to obtain a plurality of edge track data segments and glue line track data segments; performing Fourier transform on the edge track data segments and the glue line track data segments respectively to obtain corresponding frequency amplitude spectra; determining the edge track data segment or the glue line track data segment with a frequency amplitude spectrum higher than the preset frequency threshold as the vibration component; removing the vibration component, and merging the edge track data segments and the glue line track data segments after removing the vibration component to obtain the processed edge contour points and the processed glue line feature points.

[0015] By adopting the above technical solution, the sliding window segmentation processing method is adopted, which not only ensures the continuity of the data, but also improves the accuracy of the spectrum analysis. The track data is converted to the frequency domain through Fourier transform, the vibration component is accurately identified and separated according to the preset threshold, and the vibration interference is effectively suppressed by merging the processed data segments, so that the subsequent detection process can be based on stable feature points.

[0016] With reference to some embodiments of the first aspect, in some embodiments, the step of outputting the glue line quality state evaluation result according to the integrity detection result specifically includes: dividing the products into different grades according to the integrity detection result; and performing a glue supplementing action on the products with a grade within a glue line missing threshold range.

[0017] By adopting the above technical solution, the products are divided into different grades based on the integrity detection result, and the glue supplementing operation is performed on the products with the glue line missing within the threshold range, so that the closed-loop management of detection and control is realized. This grading processing and timely remediation method not only ensures the product quality, but also avoids unnecessary scrapping, thereby improving the production efficiency.

[0018] In a second aspect, the application provides a glue spraying control process of a book block rotary machine, comprising: mixing colored glue; feeding the colored glue into a glue gun, and initializing the glue gun, a visual detection device, and a conveying device; conveying the folded product to the glue spraying range of the glue gun by the conveying device; starting the glue gun to spray the colored glue to the fold of the product; starting the visual detection device to detect the integrity of the glue line; causing the visual detection device to perform the method of the first aspect; if the integrity detection result is that the glue line is complete, pressing and bonding the fold of the product; if the integrity detection result is that the glue line is incomplete, determining the product as a defective product by the visual detection device, and sending the information of the defective product to a host; controlling a picking mechanism to move the defective product away from the conveying device by the host; classifying the glue line quality state evaluation result of the defective product; performing a glue supplementing action on the product within the glue line loss threshold range; starting the visual detection device to detect the integrity of the glue line of the defective product after the glue supplementing action; if the integrity detection result is that the glue line is complete, moving the defective product to a finished product conveying line by the picking mechanism again; if the integrity detection result is that the glue line is incomplete, performing waste treatment.

[0019] In a third aspect, the application provides a glue spraying control system of a book block rotary machine, comprising: one or more processors and a memory; the memory is coupled with the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprising computer instructions, and the one or more processors are configured to invoke the computer instructions to cause the glue spraying control system of the book block rotary machine to perform the method of the first aspect.

[0020] In a fourth aspect, the application provides a computer program product comprising instructions, which, when executed on a glue spraying control system of a book block rotary machine, cause the glue spraying control system of the book block rotary machine to perform the method of the first aspect.

[0021] In a fifth aspect, the application provides a computer-readable storage medium comprising instructions, which, when executed on a glue spraying control system of a book block rotary machine, cause the glue spraying control system of the book block rotary machine to perform the method of the first aspect.

[0022] The one or more technical solutions provided in the embodiments of the application have at least the following technical effects or advantages:

[0023] 1. By acquiring continuous multi-frame image data and extracting edge contour points and glue line feature points in the image data to establish a basic data set. Because the glue line deformation has continuity, while the device vibration and page displacement show a jump change. Based on this characteristic, the motion trajectory is obtained by calculating the displacement vector of the edge contour points and the glue line feature points between adjacent image data, and the vibration component is separated by performing spectral analysis on the edge trajectory and the glue line trajectory. Then, according to the geometric constraint relationship that the booklet edge contour remains during the deformation process, the detection area is constructed according to the processing edge contour points and the corresponding processing glue line feature points. By adjusting the change relationship between the edge trajectory and the processing edge contour points to the detection area, the real-time self-adaptation of the detection area to the product deformation is realized. By combining the optimization strategy of physical characteristics, the stability of the detection reference and the accuracy of the glue line detection are ensured.

[0024] 2. The depth information of the edge contour points is used to determine the fitting plane and establish the transformation relationship with the reference plane, so that the accurate conversion of the detection area between different planes is realized. The dynamic detection area in the reference plane is converted to the fitting plane which is more consistent with the actual product surface, and then projected back to the reference plane to obtain the optimized detection area, so that the detection area can more accurately conform to the actual shape of the product. This three-dimensional space-based area optimization method effectively solves the detection deviation problem caused by product surface deformation.

[0025] 3. When determining the fitting plane, the distances of all edge contour points to the plane are calculated and minimized to realize the optimal fitting of the actual surface shape of the product. It ensures that the fitting plane can conform to the actual surface state of the product to the greatest extent, and provides a reliable spatial reference for the subsequent detection area optimization. BRIEF DESCRIPTION OF DRAWINGS

[0026] Figure 1 is a flowchart of the web offset press glue spraying control method in the embodiment of the application;

[0027] Figure 2 is another flowchart of the web offset press glue spraying control method in the embodiment of the application;

[0028] Figure 3 is Figure 2 another flowchart before step S201 of

[0029] Figure 4 is an exemplary hardware structure schematic diagram of the web offset press glue spraying control system in the embodiment of the application. DETAILED DESCRIPTION

[0030] The terminology used in the following description of the embodiments herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the description of the embodiments and the appended claims herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It also will be understood that the terms and / or phrases used herein are for the purpose of describing particular embodiments and are not intended to be limiting, but are meant to include any or all combinations of one or more of the listed items.

[0031] Hereinafter, the terms first, second, etc. are used only for the purpose of description and are not to be construed as implying or suggesting relative importance or a specific number of technical features indicated. Thus, the features defined with first, second, etc. can explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, the meaning of plural is two or more, unless otherwise specified.

[0032] In the process of making A4 paper booklet products, glue spraying needs to be performed at the folding part to ensure product quality. Due to the small size of the product and the narrow folding area, a small glue spraying gun nozzle is required to achieve precise spraying. However, such a small nozzle is prone to clogging, causing glue spraying to be interrupted or uneven. Especially in the continuous production process, the nozzle may gradually clog due to glue solidification or impurity accumulation, causing glue line breakage, insufficient glue amount, and other quality defects, which seriously affect the binding firmness of the product.

[0033] Based on the above problems, the present application provides a glue spraying process for a title book rotary machine, comprising:

[0034] Harmonizing colored glue;

[0035] A specific proportion of pigment is added to the conventional white glue to make the glue present a color that is easy for the visual system to recognize, improving the accuracy of visual detection.

[0036] The colored glue is added to the glue gun, and the glue gun, visual detection equipment, and conveying equipment are initialized.

[0037] The folded product is transported by the conveying equipment to the glue spraying range of the glue gun; ensure that each equipment is in normal working condition.

[0038] The folded product is stably conveyed to the glue spraying station of the glue gun by the clamping device of the conveying equipment. The design of the clamping device ensures that the product maintains the correct posture during transportation, preventing deviation or deformation.

[0039] Start the glue gun to spray colored glue to the folding part of the product;

[0040] The spraying parameters (such as pressure, speed, etc.) of the glue gun are pre-set according to the characteristics of the product.

[0041] The visual detection device detects the integrity of the glue line; so that the visual detection device executes a kind of title book rotary machine glue spraying control method;

[0042] If the integrity detection result is that the glue line is complete, the crease of the compression product is bonded;

[0043] If the integrity detection result is that the glue line is not complete, the visual detection device determines the product as a defective product, and sends the information of the defective product to the host computer;

[0044] The host computer controls the picking mechanism to move the defective product from the conveying device;

[0045] The glue line quality state evaluation result of the defective product is divided;

[0046] The product within the glue line loss threshold range is executed to supplement glue action;

[0047] The visual detection device detects the integrity of the glue line after the glue is supplemented;

[0048] If the integrity detection result is that the glue line is complete, it is moved to the finished product conveying line again by the picking mechanism;

[0049] If the integrity detection result is that the glue line is not complete, it is discarded.

[0050] As can be seen, by adding a specific pigment to the glue for dyeing, the sprayed glue line has clear visual characteristics. During the glue spraying process, the visual detection system monitors the glue line state in real time, and once the glue line width is detected to be abnormal or the spraying area deviates from the preset range, the system immediately alarms. The nozzle clogging problem can be found in time and cleaned, effectively preventing the production of batch defective products and improving production efficiency.

[0051] S101, acquire continuous multiple frames of image data, and the image data includes the glue line spraying area of the folded back of the product;

[0052] Among them, the continuous multiple frames of image data refer to a series of image sequences collected by an industrial camera at continuous time points, and each frame of image represents the state information of the product at a certain moment. The folded back of the product represents the back ridge part formed after the booklet product is folded, which is the target area for glue spraying.

[0053] S102, extract edge contour points and glue line feature points in the image data;Form edge contour point sequence and glue line feature point sequence;

[0054] Among them, the edge contour point refers to the characteristic pixel point of the edge of the folded back of the product, which is used to represent the contour shape and spatial position of the product in the image. The glue line feature point represents the key point on the glue spraying line, which is used to describe the shape and distribution characteristics of the glue line.

[0055] Specifically, preprocessing is performed on each frame of image, including image enhancement, noise suppression and contrast adjustment, to improve the accuracy of feature extraction. Then, for the edge region of the product, an edge detection algorithm is used to extract contour feature points, and key points on the glue line are extracted using the color feature of the colored glue. For each feature point, the system records its two-dimensional coordinate information and related attributes (such as gray value, gradient direction, etc.). Finally, the same type of feature points are organized into a sequence according to spatial position or time sequence, and the correlation between feature points is established.

[0056] S103, based on the edge contour point sequence, calculating the displacement vector of the edge contour point between adjacent image data, generating the edge trajectory;

[0057] Specifically, the system establishes a matching relationship between the corresponding edge contour points in the adjacent two frames of image, ensuring that the same physical point is tracked. Then, the spatial position difference between each pair of matched points is calculated to obtain the displacement vector in the two-dimensional plane. These displacement vectors not only contain displacement size and direction information, but also reflect the deformation characteristics of the product during movement. By connecting the time-continuous displacement vectors, a trajectory curve describing the motion law of the edge is formed.

[0058] S104, based on the glue line feature point sequence, calculating the displacement vector of the glue line feature point between adjacent image data, generating the glue line trajectory;

[0059] Specifically, the corresponding relationship of the feature points in adjacent frames of glue line is established, ensuring that the same physical location feature point is tracked. The position offset between the corresponding feature points is calculated to obtain the displacement vector reflecting the local deformation of the glue line. These displacement vectors not only contain the motion information of the glue line, but also reflect the deformation characteristics in the glue spraying process. By time sequence correlation and spatial connection of the displacement vectors, a continuous trajectory describing the dynamic behavior of the glue line is constructed.

[0060] S105, respectively performing spectral analysis on the edge trajectory and the glue line trajectory, separating out the vibration component based on a preset frequency threshold, obtaining the processed edge contour points and the processed glue line feature points;

[0061] This step is performed after obtaining the motion trajectory, and is used to eliminate the interference caused by environmental vibration and device jitter. Specifically, the system first performs Fourier transform on the edge trajectory and the glue line trajectory, converting the time-domain motion signal into frequency-domain representation. Then, the spectral characteristics are analyzed to identify the low-frequency component belonging to normal motion and the high-frequency component caused by vibration. Based on the pre-set frequency threshold, the system filters out the vibration component higher than the threshold, and retains the low-frequency signal reflecting the actual motion characteristics. Finally, the processed signal is converted back to the time domain through inverse transform, and the feature point position with vibration influence eliminated is obtained.

[0062] In some specific embodiments, after continuous sampling of the X, Y coordinate data of the edge trajectory and the glue line trajectory, the edge trajectory and the glue line trajectory are segmented, which can be preset length, or preset adjacent segment overlap rate. The FFT calculation is performed on each data segment, the preset frequency threshold is set as the cutoff frequency, the low frequency band basic motion trajectory is reserved, and the high frequency band vibration component is filtered out. In reconstruction, the components above the preset frequency threshold in the frequency domain data are set to 0, the complete amplitude inside the preset frequency threshold is reserved, and then IFFT calculation is performed. The reconstructed data segments are smoothly transitioned in the overlapping area.

[0063] In other specific embodiments, step S105 specifically comprises:

[0064] S1051, respectively, the edge trajectory and the glue line trajectory are subjected to sliding window segmentation processing to obtain a plurality of edge trajectory data segments and glue line trajectory data segments;

[0065] Wherein, the sliding window refers to a fixed length data segment moving in time series, which is used to divide the continuous signal into local intervals. The segmentation processing means that the continuous trajectory data is divided into a plurality of overlapping data segments.

[0066] Specifically, the system first determines the size of the sliding window, which needs to consider the balance between the periodic characteristics of the signal and the calculation efficiency. Then, set the overlap rate of the window, usually choose about 50% overlap to ensure the continuity of the data. For each sliding position, the system extracts the trajectory data in the current window, and applies the window function to reduce the spectral leakage.

[0067] In some specific embodiments, first, a fixed window length is set, which is used as the basis to accurately define the scope of data processing. Then, calculate the window overlap parameter to ensure that the connection between different windows and the data coverage meet the expected requirements, so as to realize more reasonable data processing layout. Subsequently, the window function is used for weighting operation, which highlights the importance of certain parts of the data, and also helps to improve the overall characteristics of the data, making it more conducive to subsequent analysis and processing.

[0068] In addition, adaptive window method can also be selected to further optimize the whole process, so that it can dynamically adjust the window related parameters according to the characteristics of the actual data, better adapt to different data situations, and enhance the flexibility and adaptability of data processing.

[0069] S1052, respectively, the edge trajectory data segment and the glue line trajectory data segment are subjected to Fourier transform to obtain the corresponding frequency amplitude spectrum;

[0070] Wherein, the Fourier transform refers to a mathematical method of converting time domain signal into frequency domain representation, which is used to analyze the frequency composition of the signal.

[0071] Specifically, the system first preprocesses each data segment, including mean removal and trend elimination, to reduce the direct current component and low-frequency interference in spectral analysis. Then, the Fast Fourier Transform (FFT) is applied to the processed data segment to convert the time-domain data into a complex frequency spectrum representation.

[0072] S1053, determine the edge trajectory data segment or the glue line trajectory data segment with a frequency amplitude spectrum higher than a preset frequency threshold as a vibration component;

[0073] Specifically, the system analyzes the spectral characteristics of each data segment to detect frequency components exceeding the threshold. The system needs to consider the effects of spectral leakage and noise, and for the data segments identified as vibration components, the system also needs to record their characteristic parameters to provide a basis for subsequent signal reconstruction.

[0074] S1054, remove the vibration component, and merge the edge contour point and the glue line feature point after removing the vibration component to obtain a processed edge contour point and a processed glue line feature point.

[0075] Specifically, the system designs a frequency domain filter to suppress or remove the identified vibration frequency components. The filtered spectrum is inverse transformed to restore the time-domain signal. Considering the boundary effect caused by the segmentation processing, the system needs to perform smooth transition processing in the overlapping area of the data segments. Finally, the processed data segments are recombined in chronological order to construct a complete motion trajectory. During the merging process, the continuity and smoothness of the trajectory need to be ensured.

[0076] As can be seen, the sliding window segmentation processing method not only ensures the continuity of the data, but also improves the accuracy of the spectral analysis. By converting the trajectory data to the frequency domain through Fourier transform, the vibration components are accurately identified and separated according to the preset threshold, and then the processed data segments are merged to effectively suppress the vibration interference, so that the subsequent detection process can be based on stable feature points.

[0077] S106, construct a detection region according to the processed edge contour point and the corresponding processed glue line feature point;

[0078] Specifically, the system first establishes the spatial mapping relationship between the processed edge contour point and the glue line feature point to determine their relative positions. Then, based on the distribution characteristics of these feature points, an envelope region is constructed as the detection range. This detection region needs to completely cover the glue line distribution area.

[0079] In some specific embodiments, the approximate range contour formed by the glue line feature points is outlined for the convex hull boundary of the glue line feature points; a minimum circumscribed rectangle is constructed according to the determined convex hull boundary to simplify the shape representation of the region, which is more consistent with the actual glue segment.

[0080] Calculate the vertical distance di of the processing edge contour point to the four edges of the detection area; find the shortest distance dmin corresponding edge as the reference edge L; record the projection point Qi of the contour point on the reference edge; use the distance si from the starting point of the reference edge to the projection point to represent the position; establish the mapping relationship: Mi=(L, si, dmin).

[0081] S107, adjust the change relationship between the edge trajectory and the processing edge contour point to the detection area, and obtain a dynamic detection area adjusted over time;

[0082] Specifically, the system compares the position deviation between the edge trajectory and the processed contour point in real time, calculates the deformation degree and displacement trend between them. Based on these change characteristics, the system dynamically updates the shape and position parameters of the detection area, so that the detection area can adapt to the product movement and deformation.

[0083] According to the change relationship between the edge trajectory and the processed edge contour point, the projection point Qi is modified according to the mapping relationship, and then the transition projection point is smoothed, and a new detection area, i.e. a dynamic detection area, is obtained.

[0084] For example: the displacement vector of the edge trajectory is Δv=(Δx, Δy), Δx is the difference between the edge trajectory and the processed edge contour point in the x-axis, and Δy is the difference between the edge trajectory and the processed edge contour point in the y-axis; the projection point Qi is displaced according to the same displacement vector Δv.

[0085] S108, integrity detection is performed on the glue line feature points in the dynamic detection area, and a glue line quality state evaluation result is output according to the integrity detection result.

[0086] Specifically, the shape features of the glue line in the dynamic detection area are extracted, including width, continuity, edge smoothness and other parameters. Then, these features are compared with the preset quality standard, and the overall quality score is calculated through the set scoring mechanism. Finally, the quality level or specific defect description is output according to the score, providing decision basis for production control.

[0087] It can be seen that the basic data set is established by acquiring continuous multiple frame image data and extracting edge contour points and glue line feature points in the image data. Because the glue line deformation has continuity, while the device vibration and page displacement show a jump change. Based on this characteristic, the motion trajectory is obtained by calculating the displacement vector of the edge contour points and the glue line feature points between adjacent image data, and the vibration component is separated by performing spectrum analysis on the edge trajectory and the glue line trajectory. Then, according to the processing edge contour points and the corresponding processing glue line feature points, the detection area is constructed by using the geometric constraint relationship of the booklet edge contour maintained in the deformation process. By adjusting the change relationship between the edge trajectory and the processing edge contour points, the detection area realizes real-time self-adaptation to product deformation. Through the optimization strategy combined with the physical characteristics, the stability of the detection reference and the accuracy of the glue line detection are ensured.

[0088] In some specific embodiments, step S108 specifically comprises:

[0089] S1081, dividing the products into different grades according to the integrity detection result;

[0090] Specifically, based on the indicators obtained by detection, such as glue line continuity, uniformity, width consistency, etc., then compared with multiple grade intervals and corresponding quality standards, the quality grade to which the product belongs is determined.

[0091] S1082, performing a glue supplement action on the product whose grade is within the threshold range of glue line missing.

[0092] Specifically, the system first evaluates the specific situation of glue line missing, including missing position, range and degree. Then, the evaluation result is compared with the preset repairable threshold to determine whether the glue supplement condition is met. For the products that meet the condition, the system needs to generate detailed glue supplement instructions, including glue supplement position, amount and speed parameters, etc. This process needs to consider the state of the original glue line to ensure that the glue supplement can be perfectly integrated with the original glue line after the glue supplement. The system also needs to monitor the glue supplement process in real time to ensure the remedial effect.

[0093] It can be seen that the products are classified based on the integrity detection result, and the glue supplement operation is performed on the products whose glue line is missing within the threshold range, realizing closed-loop management of detection and control. This grading processing and timely remediation method not only ensures product quality, but also avoids unnecessary scrapping, improving production efficiency.

[0094] However, in the actual production process, the arc surface of the booklet back spine will produce dynamic deformation due to device vibration, and the inter-page displacement will occur under the action of the laminated folding structure, and irregular deformation will often occur on the side surface of the product. In this case, if the vertical reference surface is still used for detection, the detection accuracy will be affected.

[0095] Therefore, in some preferred embodiments, after step S107, there is further comprising:

[0096] S201, determining a fitting plane according to the depth information of the edge contour points in the same image data;

[0097] Wherein, the depth information refers to the Z-axis coordinate value of the point in the three-dimensional space, which is used to represent the spatial position information of the object surface. The fitting plane represents the best matching space plane calculated by mathematical method, which is used to approximately describe the actual deformed surface.

[0098] Specifically, the least square method or other optimization algorithm is used to calculate the parameter equation of the best fitting plane, including the normal vector and intercept of the plane. This fitting plane needs to be closest to the actual product surface to the greatest extent, while having sufficient smoothness to eliminate the influence of local noise.

[0099] In some specific embodiments:

[0100] Step S201 specifically includes: S2011, calculating the distance of all edge contour points in depth from the plane according to the depth information of the edge contour points;

[0101] Specifically, an initial plane equation is established, and the plane where the center of gravity of the point cloud is usually selected as the starting plane. Then, for each edge contour point, the signed distance from the current plane is calculated, and the sign of the distance indicates whether the point is on the positive side or negative side of the plane. These distance values will be an important basis for subsequent plane optimization.

[0102] S2012, adjusting the plane to minimize the sum of distances to obtain the fitting plane.

[0103] Specifically, the system first constructs a least square optimization objective function, taking the sum of the squares of the distances of all points from the plane as the optimization index. Then, through iterative optimization algorithm, the normal vector and intercept parameters of the plane are continuously adjusted to gradually reduce the value of the objective function.

[0104] As can be seen, in determining the fitting plane, by calculating the distance of all edge contour points from the plane and minimizing it, the optimal fitting of the actual surface morphology of the product is achieved. It ensures that the fitting plane can best fit the actual surface state of the product, providing a reliable spatial reference for subsequent detection area optimization.

[0105] In some embodiments, before step S201, there is further comprising:

[0106] S301, tracking the displacement change of the edge contour points between adjacent frame image data;

[0107] Specifically, edge contour feature points are extracted from each frame of image to ensure the stability and recognizability of the feature points. The correspondence of the feature points between adjacent frames is established, which needs to consider the local appearance features and spatial distribution constraints of the feature points. Meanwhile, the motion trajectory of each feature point needs to be recorded, including the displacement direction and amplitude information. These displacement information will provide an important basis for subsequent motion estimation and depth calculation.

[0108] S302, calculating a scale factor of the feature points based on a preset edge contour actual size;

[0109] The preset edge contour actual size refers to the real measurement value of the product edge contour in the physical space, which is used to provide an absolute scale reference. The scale factor represents the scale coefficient from the image space to the physical space, which is used to convert the relative motion into actual motion. The actual size represents the real length unit in the physical world. The preset is used to represent the standard value known or measured in advance.

[0110] This step is executed after completing the feature point tracking, which is used to solve the scale uncertainty problem in motion recovery. Specifically, the system first acquires the standard physical size information of the product edge contour. Then, the pixel distance between the corresponding feature points is measured in the image space, and the correspondence between the image space and the physical space is established. The system needs to consider the imaging characteristics of the camera and the influence of the perspective effect, and select appropriate feature point pairs to calculate the scale factor. At the same time, it also needs to handle the measurement error and uncertainty, and improve the accuracy of scale estimation through statistical analysis of multiple measurement data.

[0111] S303, constructing a fundamental matrix according to the displacement change, decomposing a relative motion matrix combined with camera parameters, and applying the scale factor to the relative motion matrix to obtain a motion matrix;

[0112] The fundamental matrix refers to a 3x3 matrix describing the epipolar geometry relationship between two images, which is used to represent the algebraic constraints of camera motion. The camera parameters represent the internal imaging characteristics of the camera, including focal length, principal point, and distortion coefficient, etc. The relative motion matrix refers to the rotation and translation matrix describing the change of camera pose. The motion matrix is used to represent the camera motion transformation with actual scale. The construction represents the process of establishing a matrix model by mathematical method. The decomposition refers to the process of decomposing the fundamental matrix into camera motion parameters. The application is used to represent the operation of integrating the scale information into the motion estimation.

[0113] Specifically, the system first constructs the essential matrix from the matched feature points, which requires at least 8 pairs of corresponding points, and usually more points are used to improve stability. Then, the essential matrix is decomposed into a rotation matrix and a translation vector by combining the known camera intrinsic parameters. This process may produce multiple solutions, and the correct solution needs to be selected through geometric constraints. Finally, the scale factor calculated earlier is applied to the translation vector to obtain the motion matrix reflecting the actual scale of the motion.

[0114] In some specific embodiments, the essential matrix E is constructed: the essential matrix is constructed using the displacement change information; decomposition is performed in combination with the camera intrinsic parameters K; and a relative motion matrix is obtained, which includes a rotation matrix R and a unit translation vector t.

[0115] Calculate the real scale: measure the projected size L_image of the edge profile in the image; obtain the actual size L_real of the edge profile; calculate the scale factor: s = L_real / L_image;

[0116] Obtain the real-scale motion matrix: apply the scale factor to the translation vector: T = s*t; and construct the complete camera motion matrix [R|T].

[0117] S304, the depth information of the edge profile points is obtained by triangulation.

[0118] Specifically, the system first establishes the projection equation of the feature points in the two images, which includes the camera's intrinsic and extrinsic parameters and the image coordinates of the feature points. Then, based on the known camera motion and intrinsic parameters, a least squares optimization problem is constructed to solve the three-dimensional coordinates of the feature points.

[0119] As can be seen, by tracking the displacement change of the edge profile points to obtain the basic data, combining the pre-set actual size to calculate the scale factor, the proportional accuracy of the depth calculation is ensured. By constructing the essential matrix and combining the camera parameter decomposition to obtain the relative motion matrix, and then applying the scale factor to obtain the real-scale motion matrix, the accurate depth information is finally obtained through triangulation, which provides reliable three-dimensional spatial data for the construction of the fitting plane.

[0120] S202, determine the transformation matrix of the fitting plane and the reference plane where the dynamic detection area is located;

[0121] Specifically, the system first determines the parametric equation of the reference plane, and usually selects a plane parallel to the image plane as the reference. Then, the geometric relationship between the fitting plane and the reference plane is analyzed, including the angle between the normal vectors of the two planes and the relative position offset. Based on these geometric relationships, a transformation matrix containing rotation and translation components is constructed.

[0122] S203, change the dynamic detection area from the reference plane to the fitting plane according to the transformation matrix;

[0123] It should be noted that the change here and the projection below are not the same, specifically, the change here essentially refers to the transformation of the plane, that is, it involves the change operation of the plane in space or a certain set of situations. And the dynamic detection area related to it will be closely related to the transformation plane, and will change accordingly with the transformation plane, and there is such a cooperative change relationship between the two.

[0124] Specifically, it is to accurately transfer the dynamic detection area originally on the reference plane to the fitting plane according to the set transformation matrix, so as to complete the change from one plane to another, so as to meet the specific requirements of the subsequent related processing or analysis for the plane position and the like.

[0125] S204, projecting the dynamic detection area in the fitting plane from the fitting plane to the reference plane to obtain an optimized detection area;

[0126] It should be noted that projection is a specific geometric mapping operation. Specifically, it is to make the graphics, areas (such as dynamic detection areas) in a plane (such as the fitting plane mentioned here) in the existing space or set situation, according to the corresponding projection rules (such as orthographic projection, oblique projection and different projection methods, each with its specific projection direction and angle requirements), make it on another plane (such as the reference plane) Corresponding image, that is, the shape, position and other information contained in the dynamic detection area on the fitting plane is transferred to the reference plane by projection, thereby generating a new area (such as the optimized detection area here) that meets the specific requirements.

[0127] Unlike the change mentioned above, the change focuses on the transformation of the entire plane itself and the synchronous change of the related area, which is a whole change operation of the plane position, state and the like; while the projection focuses on mapping the elements in one plane to another plane according to specific rules, and emphasizes the transfer and presentation process of the graphic information from one plane to another plane, and the two have different operation connotations and purposes.

[0128] More accurate is that the rules applied are different, one is the transformation matrix, and the other is the orthographic projection method.

[0129] It needs to be understood that, at the beginning, the dynamic detection area is above the reference plane, however, as mentioned above, the reference plane is not the most ideal plane that is most suitable for subsequent operations. In view of this, the method of copying the reference plane is adopted, and then the azimuth angle of the copied plane is changed, so as to make it better meet the requirements of subsequent data processing, detection and the like by changing the azimuth angle. The dynamic detection area closely related thereto will also change accordingly due to the cooperative relationship with the copied plane. However, in actual observation, the work needs to be carried out from the specific angle of the reference plane. Therefore, in order to keep the original observation angle and make good use of the advantages brought by the plane after the change of the azimuth angle, the dynamic detection area that has changed in the process of changing the copied plane needs to be projected back to the reference plane through the projection operation, so that the familiar reference plane angle can be used to watch and process the related content, and the optimization effect brought by the change of the azimuth angle of the plane can be used to better complete the whole process.

[0130] S108 is replaced by S205, integrity detection is performed on the glue line feature points in the optimized detection area, and a glue line quality state evaluation result is output according to the integrity detection result.

[0131] It can be seen that the fitting plane is determined through the depth information of the edge contour points, and the transformation relationship with the reference plane is established, so that the accurate conversion of the detection area between different planes is realized. The dynamic detection area in the reference plane is converted to the fitting plane that is more suitable for the actual product surface, and then projected back to the reference plane to obtain the optimized detection area, so that the detection area can be more accurately fitted to the actual shape of the product. This region optimization method based on three-dimensional space effectively solves the detection deviation problem caused by the deformation of the product surface.

[0132] The following describes an example test form rotary press glue spraying control system 400 provided by an embodiment of the present application. Figure 4 is an example hardware structure schematic diagram of the test form rotary press glue spraying control system 400 provided by an embodiment of the present application.

[0133] In some embodiments, the web press glue spraying control system 400 is a computer device or includes a computer device in the web press glue spraying control system 400. The computer device includes a processor, a memory and a network interface connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store data. The network interface of the computer device is configured to communicate with other terminals or servers outside through a network connection. In some embodiments, the network interface can be a wired network interface, and in some embodiments, the network interface can also be a wireless network interface. The computer program is executed by the processor to implement the method in the embodiments of the present application.

[0134] Those skilled in the art can understand that, Figure 4 The structure shown in the above-mentioned embodiments is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0135] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit the technical solutions thereof. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features thereof. Such modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0136] In the above-described embodiments, according to the context, the term "when" can be interpreted as meaning "if" or "after" or "in response to determining" or "in response to detecting". Similarly, according to the context, the phrase "when it is determined that" or "if it is detected that" can be interpreted as meaning "if it is determined that" or "in response to determining that" or "when it is detected that" or "in response to detecting that".

[0137] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk) and the like.

[0138] Those of ordinary skill in the art understand that all or part of the processes in the above embodiments can be implemented by a computer program to instruct the relevant hardware, which can be stored in a computer readable storage medium. The program can include the processes of the above method embodiments when executed. The aforementioned storage medium includes ROM or random access memory (RAM), magnetic disk or optical disk, and various media that can store program codes.

Claims

1. A method of controlling glue spraying of a sheet-fed rotary machine, characterized by, The method comprises the following steps: acquiring continuous multi-frame image data, wherein the image data comprises a glue line spraying area of a product folding back; extracting edge contour points and glue line feature points in the image data; composing an edge contour point sequence and a glue line feature point sequence; calculating displacement vectors of the edge contour points between adjacent image data based on the edge contour point sequence to generate an edge trajectory; calculating displacement vectors of the glue line feature points between adjacent image data based on the glue line feature point sequence to generate a glue line trajectory; respectively performing spectral analysis on the edge trajectory and the glue line trajectory, separating out vibration components based on a preset frequency threshold to obtain processed edge contour points and processed glue line feature points; wherein the edge trajectory and the glue line trajectory are respectively subjected to sliding window segmentation processing to obtain a plurality of edge trajectory data segments and glue line trajectory data segments; respectively performing Fourier transform on the edge trajectory data segments and the glue line trajectory data segments to obtain corresponding frequency amplitude spectra; determining the edge trajectory data segments or the glue line trajectory data segments with a frequency amplitude spectrum higher than the preset frequency threshold as vibration components; removing the vibration components, and merging the edge trajectory data segments and the glue line trajectory data segments after removing the vibration components to obtain the processed edge contour points and the processed glue line feature points; constructing a detection area according to the processed edge contour points and corresponding processed glue line feature points; adjusting the detection area according to the change relationship between the edge trajectory and the processed edge contour points to obtain a dynamic detection area adjusted over time; determining a fitting plane according to the depth information of the edge contour points in the same image data; determining a transformation matrix of the fitting plane and a reference plane where the dynamic detection area is located; changing the dynamic detection area from the reference plane to the fitting plane according to the transformation matrix; projecting the dynamic detection area in the fitting plane from the fitting plane to the reference plane to obtain an optimized detection area; performing integrity detection on the glue line feature points inside the dynamic detection area, and outputting a glue line quality state evaluation result according to the integrity detection result.

2. The method of claim 1, wherein, The step of determining a fitting plane according to the depth information of the edge contour points in the same image data specifically comprises: calculating the distance between all the edge contour points and a plane in depth according to the depth information of the edge contour points; adjusting the plane to make the sum of distances minimum to obtain the fitting plane.

3. The method of claim 1, wherein, Before the step of determining a fitting plane according to the depth information of the edge contour points in the same image data, the method further comprises: tracking the displacement change of the edge contour points between adjacent frames of the image data; calculating a scale factor of feature points based on a preset edge contour actual size; constructing a fundamental matrix according to the displacement change, combining camera parameters to obtain a relative motion matrix, and applying the scale factor to the relative motion matrix to obtain a motion matrix; obtaining the depth information of the edge contour points through triangulation.

4. The method of claim 1, wherein, The step of outputting a glue line quality state evaluation result according to the integrity detection result specifically comprises: According to the integrity detection result, the products are divided into different grades; The products with the grade within the glue line missing threshold range are executed with the glue supplementing action.

5. A glue jet process for a sheet-fed rotary press, characterized in that The method comprises: Harmonizing colored glue; The colored glue is added into a glue gun, and the glue gun, visual detection equipment and conveying equipment are initialized; The folded product is clamped and transported by the conveying equipment to the glue spraying range of the glue gun; The colored glue is sprayed to the fold of the product by starting the glue gun; The visual detection equipment is started to detect the integrity of the glue line, so that the visual detection equipment executes the method according to any one of claims 1-4; If the integrity detection result is that the glue line is complete, the fold of the product is compressed and bonded; If the integrity detection result is that the glue line is not complete, the visual detection equipment determines the product as a defective product, and sends the information of the defective product to a host computer; The host computer controls a picking mechanism to move the defective product from the conveying equipment; The glue line quality state evaluation result of the defective product is divided; The product with the grade within the glue line missing threshold range is executed with the glue supplementing action; The visual detection equipment is started to detect the integrity of the glue line of the defective product after the glue supplementing action; If the integrity detection result is that the glue line is complete, the picking mechanism is moved to a finished product conveying line again; If the integrity detection result is that the glue line is not complete, the defective product is discarded.

6. A glue spraying control system for a sheet-fed rotary machine, characterized by The glue spraying control system of the proof rounder comprises one or more processors and memories; the memories are coupled with the one or more processors, the memories are used to store computer program codes, the computer program codes comprise computer instructions, and the one or more processors call the computer instructions to make the glue spraying control system of the proof rounder execute the method according to any one of claims 1-4.

7. A computer program product comprising instructions, characterized in that, When the computer program product runs on the glue spraying control system of the proof rounder, the glue spraying control system of the proof rounder executes the method according to any one of claims 1-4.

8. A computer-readable storage medium comprising instructions, characterized in that, When the instructions run on the glue spraying control system of the proof rounder, the glue spraying control system of the proof rounder executes the method according to any one of claims 1-4.

Images