Automatic tipping paper printing control method based on image detection

Abstract

The invention discloses an automatic control method for tipping paper printing based on image detection, and relates to the technical field of tipping paper printing, and the method specifically comprises the following steps: obtaining surface feature information of each sub-region in a wrinkling region in a tipping paper printing process in real time, and analyzing the surface feature information after obtaining, respectively generating a light intensity anomaly index and a tension instability index of each sub-region; and constructing a wrinkling influence evaluation model for the light intensity anomaly index and the tension instability index of each generated sub-region, respectively generating a comprehensive evaluation coefficient of each sub-region, performing analysis after generation, and evaluating the influence degree of each sub-region in the wrinkling region on the generated printing alignment parameter. And dividing each sub-region in the wrinkling region into a non-influence region, a low-influence region and a high-influence region according to an evaluation result. According to the invention, the problem of insufficient characteristic identification and evaluation of the wrinkling area is solved, and intelligent improvement of printing alignment precision and finished product quality is realized.

Description

Technical Field

[0001] The invention relates to the technical field of tipping paper printing, and in particular to an automatic control method for tipping paper printing based on image detection. Background Art

[0002] Tipping paper printing is an important process used in industries such as cigarettes and food packaging. It involves printing multiple rolls of tipping paper continuously and efficiently, and ensuring that the patterns are aligned and the colors are consistent to meet the aesthetic and functional requirements of product packaging. Traditional tipping paper printing often relies on manual monitoring and adjustment, which is not only prone to printing quality problems due to human errors, such as pattern offset and color misalignment, but also reduces production efficiency and cannot meet the needs of modern industry for high precision and high production capacity. Therefore, it is particularly important to automate the printing of tipping paper. Through automation technology, the printing process can be monitored in real time, and process parameters can be accurately adjusted to improve production efficiency and printing quality. Image detection-based automated control is the key technology, because image detection can capture and analyze subtle changes in the pattern on the surface of the tipping paper in real time, and use this data for rapid feedback and dynamic adjustment, which can not only significantly improve the pattern alignment accuracy and color consistency, but also reduce downtime adjustment time, optimize the use of production resources, and ultimately achieve a high-quality, high-efficiency intelligent printing process to meet the development needs of industrialized intelligent manufacturing.

[0003] The existing automatic control technology for tipping paper printing based on image detection realizes efficient automatic control by constructing a closed-loop control system including image acquisition, image processing and execution control. First, a high-precision industrial camera or sensor is installed in the printing equipment to collect the pattern image of the tipping paper in real time and transmit it to the image processing module for analysis; then, the image processing module detects and compares the key features in the image, such as pattern alignment, color uniformity and edge clarity, through computer vision technology, and compares the detection results with the preset standard template; if deviation is found, the system will generate adjustment instructions through algorithms and send them to actuators, such as servo motors, ink path controllers or tension regulators, to quickly adjust printing parameters to ensure the printing accuracy of the tipping paper. The whole process is characterized by real-time and high precision, and can be continuously monitored and dynamically adjusted to avoid human intervention, improve production efficiency, reduce defective rates, and meet the industrial needs of high-quality and large-scale printing. This technology can not only improve the process stability of tipping paper printing, but also lay the foundation for further intelligence and automation.

[0004] The prior art has the following deficiencies: During the printing process of tipping paper, when the paper is slightly wrinkled due to improper tension control, these wrinkles will change the shape and reflection characteristics of the paper surface, causing the pattern features collected by the image detection system to be distorted or blurred. Since the light reflection characteristics of the wrinkled area are significantly different from those of the normal flat area, the existing tipping paper printing automation control technology based on image detection cannot accurately identify and evaluate the characteristic changes in these areas, resulting in significant deviations in the printing alignment parameters generated by the system. This deviation further leads to incomplete or repeated ghosting problems of the printed pattern, which directly affects the appearance quality of the tipping paper. At the same time, the system may mistakenly trigger a shutdown alarm or erroneous correction operation due to the inability to correctly identify the wrinkled area, which increases manual intervention and downtime in the production process, significantly increases production costs and reduces production efficiency.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide an automatic control method for tipping paper printing based on image detection to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: an automatic control method for printing tipping paper based on image detection, which specifically comprises the following steps: During the printing process of tipping paper, whether the tipping paper is wrinkled is detected in real time. When wrinkling is detected, the wrinkled area on the tipping paper is determined and marked by image detection technology, and evenly divided into several sub-areas; Real-time acquisition of surface feature information of each sub-region in the wrinkled area during the printing process of the tipping paper, and analysis after acquisition to generate the light intensity anomaly index and tension instability index of each sub-region respectively; A wrinkle impact assessment model is constructed for the light intensity anomaly index and tension instability index of each sub-region, and a comprehensive assessment coefficient of each sub-region is generated respectively. After the generation, an analysis is performed to assess the degree of influence of each sub-region in the wrinkle region on the generated printing alignment parameters, and each sub-region in the wrinkle region is divided into a non-influence region, a low-influence region and a high-influence region according to the assessment results; According to the division results of each sub-area in the wrinkled area, different printing control measures are respectively applied to the unaffected area, the low-affected area and the high-affected area; The status changes of each sub-area in the wrinkling area are continuously monitored, and the corresponding printing control measures are dynamically adjusted according to the real-time monitoring results to ensure the alignment accuracy and finished product quality of the tipping paper printing process.

[0008] Preferably, the surface feature information of each sub-region in the wrinkled region during the printing process of the tipping paper is acquired in real time, and analyzed after acquisition to generate the light intensity abnormality index and the tension instability index of each sub-region respectively, which specifically includes the following steps: Real-time acquisition of surface feature information of each sub-area in the wrinkled area during the printing process of the tipping paper, and pre-processing after acquisition; Extracting the light intensity distribution information and edge texture dynamic information from the surface characteristic information of each pre-processed sub-area during the printing process of the tipping paper; The extracted light intensity distribution information and edge texture dynamic information are analyzed to generate the light intensity anomaly index and tension instability index of each sub-region respectively.

[0009] Preferably, the logic for obtaining the light intensity anomaly index of each sub-region is as follows: The light intensity distribution information of each pre-processed sub-region in the surface feature information of the tipping paper printing process is extracted, specifically including the light intensity change rate of each sub-region in the wrinkled area at different times during a period of time during the tipping paper printing process, the average gray value and gray standard deviation of the image pixels of each sub-region, and the average gray value of the image pixels of the area other than the wrinkled area on the tipping paper at different times during the period of time, and they are calibrated as , , and , Indicates that during the printing process of the tipping paper In the wrinkle area The rate of change of light intensity in each sub-region, Indicates that during the printing process of the tipping paper In the wrinkle area The average gray value of the image pixels in the sub-regions, Indicates that during the printing process of the tipping paper In the wrinkle area The grayscale standard deviation of the image pixels in the sub-regions, Indicates that during this time period The average gray value of the image pixels in the area other than the wrinkled area on the tipping paper at the moment, , , and are all positive integers; Calculate the light intensity anomaly index of each sub-area. The specific calculation formula is as follows:

[0010] In the formula, For the The light intensity anomaly index of each sub-area.

[0011] Preferably, the logic for obtaining the tension instability index of each sub-region is as follows: The edge texture dynamic information of each preprocessed sub-region in the surface feature information of the tipping paper printing process is extracted, specifically including the ratio of image edge pixels of each sub-region in the wrinkled area at different times during a period of time in the tipping paper printing process, the average change rate of the edge angle and the standard deviation of the gray value of the image edge pixels, and they are calibrated as , and , Indicates that during the printing process of the tipping paper In the wrinkle area The ratio of image edge pixels in the sub-region to the total pixels, Indicates that during the printing process of the tipping paper In the wrinkle area The average rate of change of the edge angle of each sub-region is Indicates that during the printing process of the tipping paper In the wrinkle area The standard deviation of the grayscale values ​​of the edge pixels of the image in the sub-regions, , , and are all positive integers; Calculate the tension instability index of each sub-area. The specific calculation formula is as follows:

[0012] In the formula, For the The tension instability index of each sub-region.

[0013] Preferably, the light intensity anomaly index of each sub-area is generated and tension instability index A wrinkling impact assessment model was constructed, and the comprehensive assessment coefficients of each sub-area were generated by weighted summation. The specific calculation formula is as follows:

[0014] In the formula, For the The comprehensive evaluation coefficient of each sub-region is and are the light intensity anomaly index of each sub-area and tension instability index The non-zero weight coefficient of .

[0015] Preferably, a preset comprehensive evaluation coefficient threshold interval is determined , and after determination, the comprehensive evaluation coefficients of each sub-region generated A comparison is performed, and the influence of each sub-area in the wrinkled area on the generated printing alignment parameters is evaluated according to the comparison results. According to the evaluation results, each sub-area in the wrinkled area is divided into a non-influence area, a low-influence area, and a high-influence area. The specific comparison analysis and division are as follows: like , the sub-region in the wrinkled region has no influence on the generated printing alignment parameters, and the sub-region is divided into a non-influence region; like , the influence degree of the sub-region in the wrinkled region on the generation of printing alignment parameters is low, and the sub-region is divided into a low-influence region; like The influence degree of this sub-region in the wrinkled region on the generation of printing alignment parameters is high, and the sub-region is divided into a high-influence region.

[0016] Preferably, according to the division results of each sub-area in the wrinkled area, different printing control measures are respectively performed on the unaffected area, the low-impact area and the high-impact area, specifically: For the sub-areas divided into unaffected areas, the printing control measures adopted are: maintain the existing printing alignment parameter settings without additional dynamic adjustments, give priority to ensuring the continuity and efficiency of the overall printing process, and monitor the status of the area in real time to prevent the hidden impact of potential changes on printing quality; For the sub-areas classified as low-impact areas, the printing control measures adopted are: dynamically adjusting the printing alignment parameters, using compensation algorithms to correct the slight deviations caused by wrinkling to ensure the accuracy of the printed pattern, and regularly evaluating the compensation effect to ensure that the adjustment of the printing alignment parameters is consistent with the stability of the overall system operation; For the sub-areas classified as high-impact areas, the printing control measures taken are: suspending the printing operation in the area, triggering the system's automatic tension adjustment function to eliminate wrinkling, and at the same time sending an alarm to the operator to notify him to perform manual inspection and maintenance. After the wrinkling phenomenon is alleviated, the printing parameters are recalibrated and the printing process is resumed.

[0017] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention detects the occurrence of wrinkling during the printing process of the tipping paper in real time, accurately marks the wrinkling area and its sub-areas, and quantitatively analyzes the optical and mechanical properties of each sub-area in combination with the light intensity anomaly index and the tension instability index, thereby significantly improving the system's ability to identify and evaluate changes in the characteristics of the wrinkling area. With the help of a comprehensive evaluation coefficient and a wrinkling impact evaluation model, it is possible to accurately evaluate the degree of influence of each sub-area in the wrinkling area on the printing alignment parameters, and dynamically divide them into non-influence areas, low-influence areas, and high-influence areas to ensure the pertinence and accuracy of printing control measures. The present invention realizes intelligent monitoring and processing of the entire process of the wrinkling phenomenon of the tipping paper, effectively solves the problem of deviation in the printing alignment parameters caused by wrinkling, and ensures high alignment accuracy and finished product quality during the printing process of the tipping paper.

[0018] 2. The present invention uses the light intensity anomaly index and the tension instability index to independently quantify the optical and mechanical properties of the wrinkling area, and constructs a wrinkling impact assessment model through comprehensive evaluation coefficients, thereby achieving a comprehensive assessment and accurate classification of complex wrinkling phenomena. Through real-time monitoring and dynamic adjustment of printing control measures, the present invention can respond quickly according to changes in the wrinkling area, avoiding the problem of false alarms or insufficient adjustments caused by traditional methods due to the inability to accurately identify wrinkling characteristics. At the same time, the classification processing strategy significantly reduces production interference and scrap rates, greatly improves production efficiency while improving printing quality, reduces the need for manual intervention, and significantly reduces overall production costs.

[0019] 3. The present invention has important application value in the process of tipping paper printing. Its intelligent monitoring and control capabilities are applicable to a variety of printing scenarios, including high-precision packaging printing and label printing, and are particularly suitable for printing quality requirements that require high alignment accuracy. In addition, the present invention uses software to achieve intelligent control of the entire process, has good scalability, can flexibly adjust parameters for different tipping paper materials, wrinkling characteristics and production conditions, and has strong adaptability. Overall, the present invention solves the pain points of insufficient wrinkle area identification and evaluation capabilities in the prior art, and at the same time achieves efficient and stable printing control through precise dynamic adjustment strategies, providing a new path for the intelligent development of tipping paper printing. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0021] Figure 1 The figure is a flow chart of the automatic control method for tipping paper printing based on image detection of the present invention. DETAILED DESCRIPTION

[0022] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0023] The present invention provides Figure 1 The automatic control method for tipping paper printing based on image detection shown in the figure specifically comprises the following steps: During the printing process of tipping paper, whether the tipping paper is wrinkled is detected in real time. When wrinkling is detected, the wrinkled area on the tipping paper is determined and marked by image detection technology, and evenly divided into several sub-areas; During the printing process of tipping paper, industrial cameras can be used to collect high-resolution images of the paper surface in real time, and combined with tension sensors to collect paper tension fluctuation data, the wrinkling phenomenon can be detected comprehensively. First, the collected images are preprocessed (such as grayscale and denoising) through image processing algorithms, and edge detection technology is used to detect whether the continuity of the pattern is destroyed, so as to determine whether there is edge breakage or shape deformation caused by wrinkling. At the same time, the light intensity distribution in the image is analyzed to see if there is abnormal reflection caused by wrinkles (such as sudden brightness changes or irregular light spots). In addition, combined with the tension fluctuation data collected by the tension sensor, the tension anomaly that may cause wrinkling is identified by calculating its fluctuation amplitude and change rate. These detection results are processed in real time by software algorithms. When the feature data exceeds the set threshold, it is determined that the paper has wrinkled.

[0024] After wrinkling of the tipping paper is detected, the wrinkled area is accurately marked using image segmentation technology. The boundaries of the abnormal light intensity area in the image are extracted through the region growing method or the threshold-based segmentation algorithm to determine the specific range of the wrinkled area. Subsequently, a rectangular or polygonal marking box is drawn by the software to clearly mark the area on the image and provide regional coordinates for subsequent analysis. Furthermore, the marked wrinkled area is evenly divided into several sub-areas, for example, into an n×n grid, and each sub-area is used as an independent unit for subsequent feature extraction and evaluation. This division method ensures that the degree of impact on each area can be quantified separately, which is convenient for subsequent classification and targeted processing.

[0025] By detecting and dividing the wrinkling area in real time, the problem of inaccurate printing alignment parameters caused by wrinkling can be effectively solved. Since the wrinkling phenomenon is localized, the degree of influence of different areas on the printing process may vary. Unified treatment may lead to the risk of over-adjustment or neglect of key areas. Therefore, by dividing the sub-areas, the characteristics of each sub-area can be independently analyzed and classified, and its degree of influence can be accurately quantified. This method not only improves the accuracy of detection, but also provides data support for subsequent dynamic compensation and adjustment, ensuring that the adjustment of printing alignment parameters is more scientific, significantly improving printing quality and production efficiency.

[0026] Real-time acquisition of surface feature information of each sub-region in the wrinkled area during the printing process of the tipping paper, and analysis after acquisition to generate the light intensity anomaly index and tension instability index of each sub-region respectively; In this embodiment, the surface feature information of each sub-region in the wrinkled region during the printing process of the tipping paper is obtained in real time, and analyzed after acquisition to generate the light intensity abnormality index and the tension instability index of each sub-region respectively, which specifically includes the following steps: Real-time acquisition of surface feature information of each sub-area in the wrinkled area during the printing process of the tipping paper, and pre-processing after acquisition; Real-time acquisition of surface feature information of each sub-area in the wrinkled area during the printing process of the tipping paper can be achieved by using an industrial camera installed on the printing equipment to collect high-resolution images of the tipping paper surface in real time. The specific acquisition method includes: setting the camera's acquisition frequency and exposure parameters to adapt to the paper movement speed to ensure that the image is clear and free of motion blur; using software to segment the image and extract the image data of each sub-area according to the sub-area division rules; synchronously collecting the light intensity distribution data of each sub-area through a light intensity sensor; combining the image data collected by the industrial camera and the real-time sensor data to generate the surface feature information of each sub-area. All acquisition processes are coordinated by the control system to ensure the real-time and consistency of the data.

[0027] Preprocessing is performed to improve data quality, reduce noise interference in subsequent analysis, and standardize the characteristic information of each sub-region for comparison and calculation. The preprocessing steps include the following: first, remove random noise in the image through filtering algorithms (such as median filtering or Gaussian filtering) to ensure the smoothness of light intensity distribution; second, use normalization algorithms to map grayscale values ​​or light intensity values ​​to a fixed range to eliminate the impact of differences in acquisition conditions; finally, use geometric correction techniques (such as projection transformation) to correct the position and angle of the sub-region image to ensure that the image features of each sub-region are consistent in subsequent calculations. Preprocessing is automatically completed through software algorithms, which can improve the accuracy and reliability of subsequent parameter calculations.

[0028] Extracting the light intensity distribution information and edge texture dynamic information from the surface characteristic information of each pre-processed sub-area during the printing process of the tipping paper; Extracting the intensity distribution information and edge texture dynamic information of each pre-processed sub-region can be achieved through image processing and analysis technology. The specific method is: first, perform grayscale histogram analysis on the pre-processed sub-region image, calculate the average grayscale value and standard deviation of the pixel, which are used to characterize the intensity distribution information, and use the Sobel operator to calculate the intensity gradient of each pixel, and obtain the intensity change rate to fully describe the intensity distribution characteristics; then, extract the edge features in the sub-region through edge detection algorithms (such as Canny edge detection), further use Hough transform to detect the angle change of the edge, and calculate the texture direction consistency of the sub-region through the gray level co-occurrence matrix (GLCM) to fully extract the edge texture dynamic information. All feature data are automatically extracted and summarized by the software algorithm to generate the intensity distribution information and edge texture dynamic information of each sub-region to provide support for subsequent analysis.

[0029] The extracted light intensity distribution information and edge texture dynamic information are analyzed to generate the light intensity anomaly index and tension instability index of each sub-region respectively.

[0030] In this embodiment, the logic for obtaining the light intensity anomaly index of each sub-area is as follows: The light intensity distribution information of each pre-processed sub-region in the surface feature information of the tipping paper printing process is extracted, specifically including the light intensity change rate of each sub-region in the wrinkled area at different times during a period of time during the tipping paper printing process, the average gray value and gray standard deviation of the image pixels of each sub-region, and the average gray value of the image pixels of the area other than the wrinkled area on the tipping paper at different times during the period of time, and they are calibrated as , , and , Indicates that during the printing process of the tipping paper In the wrinkle area The rate of change of light intensity in each sub-region, Indicates that during the printing process of the tipping paper In the wrinkle area The average gray value of the image pixels in the sub-regions, Indicates that during the printing process of the tipping paper In the wrinkle area The grayscale standard deviation of the image pixels in the sub-regions, Indicates that during this time period The average gray value of the image pixels in the area other than the wrinkled area on the tipping paper at the moment, , , and are all positive integers; During the printing process of tipping paper, the change rate of illumination intensity of each sub-region in the wrinkled area, the average grayscale value of image pixels, the grayscale standard deviation, and the average grayscale value of image pixels in the area other than the wrinkled area on the tipping paper can be obtained in real time through industrial cameras and image processing algorithms. The specific method is as follows: First, the high-resolution image data of the surface of the tipping paper is collected by an industrial camera. The image acquisition frequency needs to be synchronized with the paper movement speed to ensure that the image is clear and free of motion blur. Then, each frame of the image is divided into regions to separate the wrinkled area and the area other than the wrinkled area, and the image pixel data of each sub-region is calculated: the gradient value of the pixels in each sub-region is calculated using the Sobel operator to quantify the spatial change rate of illumination intensity, thereby obtaining the change rate of illumination intensity (for example, the change rate of the sub-region where the light reflection changes dramatically due to wrinkling will be higher); the pixel value of each sub-region is averaged to obtain the average grayscale value of the sub-region, which is used to reflect the overall level of light intensity; the discrete degree of grayscale distribution is calculated by the standard deviation formula to obtain the grayscale standard deviation, and quantify the uniformity of light intensity distribution. At the same time, the same method is used to calculate the average grayscale value of the area other than the wrinkled area as the reference data of the normal area. The acquisition of these data is automatically completed by the software algorithm, which analyzes each frame of the image in real time and combines the results of regional division to ensure that the data of all sub-areas and reference areas are accurately collected and updated during the dynamic printing process, providing support for subsequent calculations and analysis.

[0031] Calculate the light intensity anomaly index of each sub-area. The specific calculation formula is as follows:

[0032] In the formula, For the The light intensity anomaly index of each sub-area.

[0033] Light intensity anomaly index The calculation formula comprehensively quantifies the abnormality of light intensity in the sub-area by integrating three types of data: the rate of change of light intensity, the difference between the average grayscale value and the reference grayscale value, and the grayscale standard deviation. The calculation logic is as follows: The first part of the formula Reflects the rate of change of light intensity The impact of the anomaly index is to highlight the significance of the area with drastic light intensity changes through exponential calculation, and to use Normalize the data to avoid excessive gradient changes that lead to unbalanced calculation results; the second part of the formula The average gray value of the sub-region is quantified ( ) and the gray value of the reference area ( ) and the grayscale standard deviation ( ) as a normalization factor to balance the differences in characteristics between regions, and at the same time compress the extreme value range through logarithmic operation to make the calculation result more robust. The accumulated average of each moment comprehensively reflects the dynamic characteristics of the sub-region light intensity anomaly over time, thereby ensuring that the calculation results are both locally sensitive and representative of the overall trend, providing a reliable basis for the subsequent evaluation of the impact of printing alignment parameters.

[0034] No. Light intensity anomaly index of sub-areas The size of directly reflects the degree of abnormality of the light intensity distribution in the sub-region, and this degree of abnormality is the core indicator for evaluating the degree of influence of each sub-region in the wrinkled area on the generation of printing alignment parameters. Specifically, the larger the light intensity abnormality index, the more drastic the light intensity change in the sub-region (quantified by the rate of change of light intensity), the greater the difference in light intensity from the normal area (quantified by the difference between the average grayscale value and the reference value), and the more uneven the light intensity distribution (reflected by the grayscale standard deviation). These characteristics make it difficult for the image detection system to accurately capture the pattern details or edge information of the area, which directly affects the calculation accuracy of the printing alignment parameters. Therefore, the light intensity abnormality index can be used to measure the interference intensity of each sub-region on the printing alignment parameters. The larger the index, the higher the degree of influence of the sub-region on the printing alignment parameters, thereby providing a quantitative basis for subsequent classification processing and control decisions.

[0035] In this embodiment, the logic for obtaining the tension instability index of each sub-region is as follows: The edge texture dynamic information of each preprocessed sub-region in the surface feature information of the tipping paper printing process is extracted, specifically including the ratio of image edge pixels of each sub-region in the wrinkled area at different times during a period of time in the tipping paper printing process, the average change rate of the edge angle and the standard deviation of the gray value of the image edge pixels, and they are calibrated as , and , Indicates that during the printing process of the tipping paper In the wrinkle area The ratio of image edge pixels in the sub-region to the total pixels, Indicates that during the printing process of the tipping paper In the wrinkle area The average rate of change of the edge angle of each sub-region is Indicates that during the printing process of the tipping paper In the wrinkle area The standard deviation of the grayscale values ​​of the edge pixels of the image in the sub-regions, , , and are all positive integers; In the process of printing the tipping paper, the ratio of the image edge pixels to the total pixels, the average change rate of the edge angle, and the standard deviation of the grayscale value of the image edge pixels in each sub-area can be obtained in real time through industrial cameras and image processing algorithms. The specific acquisition method is as follows: First, the high-resolution image of the tipping paper surface is collected in real time by the industrial camera, and each frame of the image is preprocessed (including denoising and grayscale) to ensure data quality. Then, the edge pixels of each sub-area are extracted using an edge detection algorithm (such as Canny edge detection), and the ratio of the number of edge pixels to the total number of pixels is calculated by counting the ratio of the number of edge pixels to the total number of pixels. Subsequently, the line segment or curve features are extracted from the edge pixels using Hough transform, and the directional changes of these features at different times are calculated to obtain the average change rate of the edge angle, reflecting the dynamic characteristics of the edge. In addition, the grayscale value data of the edge pixels of each sub-area are extracted, and the discrete degree of the grayscale distribution is quantified by calculating the standard deviation of the grayscale value, so as to obtain the uniformity and stability of the edge grayscale in the sub-area. The entire data acquisition process is implemented through software, which automatically analyzes and calculates each frame of the image in real time, thereby efficiently collecting relevant data of each sub-area over a period of time, providing accurate support for the subsequent calculation of the tension instability index.

[0036] Calculate the tension instability index of each sub-area. The specific calculation formula is as follows:

[0037] In the formula, For the The tension instability index of each sub-region.

[0038] Tension instability index The calculation formula combines three types of data: edge pixel density, edge angle change rate, and edge gray value standard deviation of the sub-region, and comprehensively quantifies the dynamic impact of tension fluctuations on the sub-region. The first part of the formula Emphasize edge gray value standard deviation The sensitivity to tension fluctuations is amplified by exponential operation, and the contribution of gray value distribution anomalies to the index is amplified by Normalization balances the differences between data and avoids instability caused by extreme values. Part 2 The edge density is quantified ( ) and the edge angle change rate ( ), using logarithmic operations to compress extreme values, while highlighting the contribution of marginal distribution and areas with drastic dynamic changes to the index. The formula further reflects the temporal dynamic characteristics of tension fluctuations, making the result both locally sensitive and able to reflect the overall trend, providing a reliable basis for evaluating the stability of printing alignment parameters.

[0039] No. Tension instability index of sub-region The size of directly reflects the instability of the sub-region caused by tension fluctuations, which is closely related to "evaluating the influence of each sub-region in the wrinkling area on the generation of printing alignment parameters". Specifically, The larger the value is, the more abnormal the edge features of the sub-region are (uneven distribution of grayscale values ​​of edge pixels, high standard deviation), the more unstable the edge shape is (large angle change rate), and the more complex the edge feature density is (high edge pixel ratio). These abnormalities will make it difficult for the image detection system to accurately capture key features or generate stable alignment parameters in the sub-region, directly affecting the accuracy and reliability of alignment adjustment during printing. The size of can be used to quantify the degree of disturbance of each sub-region on the printing alignment parameters, thereby providing a quantitative basis for subsequent classification processing and compensation strategies.

[0040] A wrinkle impact assessment model is constructed for the light intensity anomaly index and tension instability index of each sub-region, and a comprehensive assessment coefficient of each sub-region is generated respectively. After the generation, an analysis is performed to assess the degree of influence of each sub-region in the wrinkle region on the generated printing alignment parameters, and each sub-region in the wrinkle region is divided into a non-influence region, a low-influence region and a high-influence region according to the assessment results; In this embodiment, the light intensity abnormality index of each sub-area is generated. and tension instability index A wrinkling impact assessment model was constructed, and the comprehensive assessment coefficients of each sub-area were generated by weighted summation. The specific calculation formula is as follows:

[0041] In the formula, For the The comprehensive evaluation coefficient of each sub-region is and are the light intensity anomaly index of each sub-area and tension instability index The non-zero weight coefficient of .

[0042] Comprehensive evaluation coefficient The generation of wrinkling impact assessment model is carried out by using the light intensity anomaly index and tension instability index The specific implementation method is: first, the weighted sum of each sub-area and Data is input into the evaluation model, and the model evaluates the data according to the defined weighted formula. Calculate the comprehensive evaluation coefficient for each sub-region, where and is a non-zero weight coefficient used to adjust the relative impact of the two indices on the evaluation results. and satisfy , ensuring that the evaluation coefficient results are reasonably distributed within the contribution range of the two indices. By adjusting the weight value, different priorities can be flexibly assigned to the light intensity anomaly index and the tension instability index according to actual needs. For example, in a scenario where edge stability is more important, a larger In the scene where the light intensity is more important, you can increase The evaluation model is automatically processed by software to ensure calculation efficiency and accuracy, and provide a quantitative basis for subsequent sub-area classification and control decisions.

[0043] In this embodiment, the preset comprehensive evaluation coefficient threshold interval is determined , and after determination, the comprehensive evaluation coefficients of each sub-region generated A comparison is performed, and the influence of each sub-area in the wrinkled area on the generated printing alignment parameters is evaluated according to the comparison results. According to the evaluation results, each sub-area in the wrinkled area is divided into a non-influence area, a low-influence area, and a high-influence area. The specific comparison analysis and division are as follows: like , the sub-region in the wrinkled region has no influence on the generated printing alignment parameters, and the sub-region is divided into a non-influence region; This situation means that the combined influence of the light intensity anomaly index and the tension instability index in this sub-area is low, and the light intensity distribution and edge characteristics in the sub-area are basically stable, which will not cause interference or error in generating printing alignment parameters. This sub-area is in a normal state and does not require additional correction or compensation measures. In terms of impact, the existence of such areas indicates that the wrinkling phenomenon has a limited impact on the printing process, which helps to reduce unnecessary processing pressure on the system and improve overall printing efficiency.

[0044] like , the influence degree of the sub-region in the wrinkled region on the generation of printing alignment parameters is low, and the sub-region is divided into a low-influence region; This situation indicates that the light intensity anomaly index and tension instability index of the sub-area have a certain influence on the printing alignment parameters, but the degree is low and it is a slight interference. There may be slight light intensity changes or edge instability in the sub-area, but it has not yet reached the level of seriously affecting the printing accuracy. In terms of influence, such areas require the system to dynamically adjust the printing parameters for slight compensation to ensure the stability of the printing alignment and reduce the quality degradation problem that may be caused by the accumulation of interference.

[0045] like The influence degree of this sub-region in the wrinkled region on the generation of printing alignment parameters is high, and the sub-region is divided into a high-influence region.

[0046] This situation indicates that the combined influence of the light intensity anomaly index and the tension instability index in this sub-area is large, and the light intensity distribution and edge characteristics of the sub-area have changed significantly, which may lead to serious errors in the printing alignment parameters. The wrinkling phenomenon in such areas is significant, which will significantly interfere with the normal operation of the printing process. In terms of impact, the system needs to take mandatory measures for such areas, such as pausing printing, triggering the tension adjustment program, or notifying manual intervention, to avoid the generation of large quantities of waste or equipment failures due to serious interference.

[0047] Determining the pre-set threshold interval of the comprehensive evaluation coefficient can be achieved through a statistical method based on historical data analysis and experimental results, as follows: First, collect the wrinkle area data of multiple printing batches during the printing process of the tipping paper, obtain the light intensity abnormality index and tension instability index of each sub-area, and calculate the comprehensive evaluation coefficient. Then, classify these data according to the degree of influence, for example, determine which sub-areas have no influence, slight influence, and severe influence on the printing alignment parameters through manual inspection or standardized testing, and mark each type of data with corresponding labels. Next, use statistical analysis methods (such as quantile analysis or clustering algorithms) to perform distribution analysis on the comprehensive evaluation coefficient data of different categories to determine the minimum and maximum values ​​of the threshold interval, for example, use the highest value of the non-influence area as the lower limit of the threshold interval, and use the highest value of the low-influence area as the upper limit of the threshold interval. Finally, dynamically adjust the threshold interval in combination with real-time data to ensure applicability under different production environments and paper conditions. The entire process can be completed automatically through software to improve the accuracy and efficiency of threshold setting.

[0048] According to the division results of each sub-area in the wrinkled area, different printing control measures are respectively applied to the unaffected area, the low-affected area and the high-affected area; In this embodiment, according to the division results of each sub-area in the wrinkled area, different printing control measures are respectively performed on the unaffected area, the low-impact area and the high-impact area, specifically: For the sub-areas divided into unaffected areas, the printing control measures adopted are: maintain the existing printing alignment parameter settings without additional dynamic adjustments, give priority to ensuring the continuity and efficiency of the overall printing process, and monitor the status of the area in real time to prevent the hidden impact of potential changes on printing quality; For sub-areas of the unaffected area, specific control can be achieved by maintaining the existing printing alignment parameter settings. The specific implementation method is: after the software system of the printing equipment identifies the unaffected area in the comprehensive evaluation coefficient comparison results, it marks the sub-area as not requiring adjustment and keeps its current printing parameters unchanged, such as printing alignment parameters, pressure settings, and speed. In order to prevent potential state changes, the system will continuously monitor the image features of the area through an industrial camera, and periodically collect new light intensity distribution information and edge texture dynamic information, and calculate a comprehensive evaluation coefficient to ensure the stability of the state of the area. The reason for doing this is that the unaffected area has no substantial impact on the printing alignment parameters. Maintaining the status quo can avoid unnecessary adjustments and maximize printing efficiency. At the same time, real-time monitoring provides early warnings for potential abnormalities.

[0049] For the sub-areas classified as low-impact areas, the printing control measures adopted are: dynamically adjusting the printing alignment parameters, using compensation algorithms to correct the slight deviations caused by wrinkling to ensure the accuracy of the printed pattern, and regularly evaluating the compensation effect to ensure that the adjustment of the printing alignment parameters is consistent with the stability of the overall system operation; For sub-areas of the low-impact area, specific control can be achieved by dynamically adjusting the printing alignment parameters. The specific method is: in the sub-areas of the low-impact area, the system calls the compensation algorithm to fine-tune the current printing alignment parameters according to the size of the comprehensive evaluation coefficient and the specific values ​​of the light intensity anomaly index and the tension instability index, such as adjusting the position or pressure of the print head to offset the slight deviation caused by wrinkling. At the same time, the software will evaluate the compensation effect based on the feature information collected in real time during the printing process, and dynamically optimize the compensation strategy by comparing the changes in the compensated comprehensive evaluation coefficient and the set threshold range. The reason for this is that the sub-areas of the low-impact area have a certain impact on the printing accuracy. Through small adjustments, the printing quality can be effectively improved while maintaining the overall stability of the system operation.

[0050] For the sub-areas classified as high-impact areas, the printing control measures taken are: suspending the printing operation in the area, triggering the system's automatic tension adjustment function to eliminate wrinkling, and at the same time sending an alarm to the operator to notify him to perform manual inspection and maintenance. After the wrinkling phenomenon is alleviated, the printing parameters are recalibrated and the printing process is resumed.

[0051] For sub-areas of the high-impact area, specific control can be achieved by pausing the printing job and triggering the tension adjustment function. The specific method is: when a sub-area is identified as a high-impact area, the system immediately stops printing in the range of the sub-area, and starts the automatic tension adjustment program through the control algorithm, such as adjusting the tension of the paper roll or the feeding speed to eliminate wrinkling. In addition, the system will send an alarm message to the operator to notify him to check the physical condition of the area and perform maintenance. After the wrinkling phenomenon is eliminated, the system re-collects data and calibrates the printing alignment parameters, and then gradually resumes the printing job. The reason for this is that high-impact areas will significantly interfere with the printing process and may cause quality problems. Suspending the process can avoid the generation of waste products, and the combination of tension adjustment and manual intervention can fundamentally solve the problem and ensure the stability of subsequent production.

[0052] The status changes of each sub-area in the wrinkling area are continuously monitored, and the corresponding printing control measures are dynamically adjusted according to the real-time monitoring results to ensure the alignment accuracy and finished product quality of the tipping paper printing process.

[0053] Continuously monitoring the state changes of each sub-area in the wrinkled area can be achieved by real-time image data acquisition by industrial cameras and dynamic analysis combined with software algorithms. The specific method is as follows: First, during the printing process, the industrial camera continuously acquires high-resolution images of the surface of the tipping paper at the set sampling frequency. The system software processes each frame of the image, including grayscale, denoising and area segmentation, extracts the light intensity distribution information and edge texture dynamic information of each sub-area in real time, and calculates the light intensity anomaly index and tension instability index. Then, based on these two indexes, the comprehensive evaluation coefficient is updated and compared with the preset threshold interval to evaluate whether the degree of influence of each sub-area has changed. The system dynamically adjusts the classification status of the non-impact area, low-impact area and high-impact area according to the new division results, and triggers corresponding printing control measures (such as maintaining the status quo, fine-tuning parameters or suspending operations). This process is automatically completed by the software algorithm to ensure that state changes can be identified and processed in a timely manner.

[0054] The reason for this is that the state of the wrinkled area may change dynamically over time or with production conditions (such as tension fluctuations, changes in paper humidity), and these changes may directly affect the accuracy of the printing alignment parameters and the quality of the finished product. By continuously monitoring and analyzing the state of each sub-area in real time, it can be ensured that the system always maintains high-precision printing alignment and finished product quality throughout the printing process, while effectively reducing quality problems and production losses caused by undetected changes. In addition, dynamically adjusting the corresponding printing control measures can also improve the flexibility and robustness of the system, enabling it to quickly adapt to changes in production conditions, thereby ensuring the stability and efficiency of the entire production process.

[0055] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0056] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. 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 by wired or wireless (such as infrared, wireless, microwave, etc.). 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 or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0057] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0058] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0059] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0060] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0061] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0062] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The automatic control method for tipping paper printing based on image detection is characterized in that: The specific steps include: During the printing process of tipping paper, whether the tipping paper is wrinkled is detected in real time. When wrinkling is detected, the wrinkled area on the tipping paper is determined and marked by image detection technology, and evenly divided into several sub-areas; Real-time acquisition of surface feature information of each sub-region in the wrinkled area during the printing process of the tipping paper, and analysis after acquisition to generate the light intensity anomaly index and tension instability index of each sub-region respectively; A wrinkle impact assessment model is constructed for the light intensity anomaly index and tension instability index of each sub-region, and a comprehensive assessment coefficient of each sub-region is generated respectively. After the generation, an analysis is performed to assess the degree of influence of each sub-region in the wrinkle region on the generated printing alignment parameters, and each sub-region in the wrinkle region is divided into a non-influence region, a low-influence region and a high-influence region according to the assessment results; According to the division results of each sub-area in the wrinkled area, different printing control measures are respectively applied to the unaffected area, the low-affected area and the high-affected area; The status changes of each sub-area in the wrinkling area are continuously monitored, and the corresponding printing control measures are dynamically adjusted according to the real-time monitoring results to ensure the alignment accuracy and finished product quality of the tipping paper printing process.

2. The tipping paper printing automation control method based on image detection according to claim 1, characterized in that: The surface feature information of each sub-region in the wrinkled region during the printing process of the tipping paper is obtained in real time, and analyzed after acquisition to generate the light intensity abnormality index and tension instability index of each sub-region respectively, which specifically includes the following steps: Real-time acquisition of surface feature information of each sub-area in the wrinkled area during the printing process of the tipping paper, and pre-processing after acquisition; Extracting the light intensity distribution information and edge texture dynamic information from the surface characteristic information of each pre-processed sub-area during the printing process of the tipping paper; The extracted light intensity distribution information and edge texture dynamic information are analyzed to generate the light intensity anomaly index and tension instability index of each sub-region respectively.

3. The tipping paper printing automation control method based on image detection according to claim 2, characterized in that: The logic for obtaining the light intensity anomaly index of each sub-area is as follows: The light intensity distribution information of each pre-processed sub-region in the surface feature information of the tipping paper printing process is extracted, specifically including the light intensity change rate of each sub-region in the wrinkled area at different times during a period of time during the tipping paper printing process, the average gray value and gray standard deviation of the image pixels of each sub-region, and the average gray value of the image pixels of the area other than the wrinkled area on the tipping paper at different times during the period of time, and they are calibrated as , , and , Indicates that during the printing process of the tipping paper In the wrinkle area The rate of change of light intensity in each sub-region, Indicates that during the printing process of the tipping paper In the wrinkle area The average gray value of the image pixels in the sub-regions, Indicates that during the printing process of the tipping paper In the wrinkle area The grayscale standard deviation of the image pixels in the sub-regions, Indicates that during this time period The average gray value of the image pixels in the area other than the wrinkled area on the tipping paper at the moment, , , and All are positive integers; Calculate the light intensity anomaly index of each sub-area. The specific calculation formula is as follows: In the formula, For the The light intensity anomaly index of each sub-region.

4. The tipping paper printing automation control method based on image detection according to claim 3 is characterized in that: The logic for obtaining the tension instability index of each sub-region is as follows: The edge texture dynamic information of each preprocessed sub-region in the surface feature information of the tipping paper printing process is extracted, specifically including the ratio of image edge pixels of each sub-region in the wrinkled area at different times during a period of time in the tipping paper printing process, the average change rate of the edge angle and the standard deviation of the gray value of the image edge pixels, and they are calibrated as , and , Indicates that during the printing process of the tipping paper In the wrinkle area The ratio of image edge pixels in the sub-region to the total pixels, Indicates that during the printing process of the tipping paper In the wrinkle area The average rate of change of the edge angle of each sub-region is Indicates that during the printing process of the tipping paper In the wrinkle area The standard deviation of the grayscale values ​​of the edge pixels of the image in the sub-regions, , , and All are positive integers; Calculate the tension instability index of each sub-area. The specific calculation formula is as follows: In the formula, For the The tension instability index of each sub-region.

5. The tipping paper printing automation control method based on image detection according to claim 4, characterized in that: Generate the light intensity anomaly index for each sub-area and tension instability index A wrinkle impact assessment model was constructed, and the comprehensive assessment coefficients of each sub-area were generated by weighted summation. The specific calculation formula is as follows: In the formula, For the The comprehensive evaluation coefficient of each sub-region is and are the light intensity anomaly index of each sub-area and tension instability index The non-zero weight coefficient of .

6. The tipping paper printing automation control method based on image detection according to claim 5, characterized in that: Determine the pre-set comprehensive evaluation coefficient threshold range , and after determination, the comprehensive evaluation coefficients of each sub-region generated A comparison is performed, and the influence of each sub-area in the wrinkled area on the generated printing alignment parameters is evaluated according to the comparison results. According to the evaluation results, each sub-area in the wrinkled area is divided into a non-influence area, a low-influence area and a high-influence area. The specific comparison analysis and division are as follows: like , the sub-region in the wrinkled region has no influence on the generated printing alignment parameters, and the sub-region is divided into a non-influence region; like , the influence degree of the sub-region in the wrinkled region on the generation of printing alignment parameters is low, and the sub-region is divided into a low-influence region; like The influence degree of this sub-region in the wrinkled region on the generation of printing alignment parameters is high, and the sub-region is divided into a high-influence region.

7. The tipping paper printing automation control method based on image detection according to claim 6, characterized in that: According to the division results of each sub-area in the wrinkle area, different printing control measures are respectively carried out for the unaffected area, the low-impact area and the high-impact area, specifically: For the sub-areas divided into unaffected areas, the printing control measures adopted are: maintain the existing printing alignment parameter settings without additional dynamic adjustments, give priority to ensuring the continuity and efficiency of the overall printing process, and monitor the status of the area in real time to prevent the hidden impact of potential changes on printing quality; For the sub-areas classified as low-impact areas, the printing control measures adopted are: dynamically adjusting the printing alignment parameters, using compensation algorithms to correct the slight deviations caused by wrinkling to ensure the accuracy of the printed pattern, and regularly evaluating the compensation effect to ensure that the adjustment of the printing alignment parameters is consistent with the stability of the overall system operation; For the sub-areas classified as high-impact areas, the printing control measures taken are: suspending the printing operation in the area, triggering the system's automatic tension adjustment function to eliminate wrinkling, and at the same time sending an alarm to the operator to notify him to perform manual inspection and maintenance. After the wrinkling phenomenon is alleviated, the printing parameters are recalibrated and the printing process is resumed.

Images