A monitoring method and device for side seam glue wiping machine

Abstract

The present invention relates to the technical field of monitoring of glue wiping machines, and discloses a monitoring method and device for a side seam glue wiping machine. The method is executed by a processor, including obtaining a real-time image of the workpiece surface through an image acquisition module arranged on the glue wiping path; preprocessing the real-time image of the workpiece surface to obtain a rubber strip image to be tested; calculating the pixel value slope of the rubber strip image to be tested, and identifying the rubber strip gap according to the pixel value slope; performing edge detection operations to obtain the rubber strip width; performing binarization processing according to the rubber strip image to be tested to obtain a black and white image of the rubber strip to be tested; performing black and white pixel point detection operations to obtain broken line defect points; performing quality judgment operations according to the broken line defect points and the rubber strip gap to obtain the quality of the rubber strip; and calculating the yield rate of the side seam glue wiping machine according to the quality of the rubber strip. The method determines the quality of the rubber strip by image detection, thereby reflecting the yield rate of the glue wiping machine, greatly improving the accuracy of monitoring.

Description

Technical Field

[0001] The invention relates to the technical field of glue wiping machine monitoring, and in particular to a monitoring method and device for a side seam glue wiping machine. Background Art

[0002] During the side seam gluing process, the side seam gluing machine wipes the glued side seam through reciprocating motion to form the side seam glue strip.

[0003] In the prior art, the forming quality of the side seam rubber strips is generally tested by manual sampling. Workers use calipers, magnifying glasses and other testing tools to check the appearance of the side seam rubber strips to see if there are quality defects such as cracks and deformations. The yield rate of the side seam glue erasing machine is determined based on the quality of the side seam rubber strips.

[0004] However, the existing technology completely relies on manual labor, which is prone to missed inspections and cannot accurately reflect the yield rate of the side seam glue wiping machine. Summary of the invention

[0005] The invention provides a monitoring method and device for a side seam glue wiping machine, so as to achieve accurate reflection of the yield rate of the side seam glue wiping machine.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a monitoring method for a side seam gluing machine, comprising:

[0007] The real-time image of the workpiece surface is obtained by the image acquisition module arranged on the eraser path;

[0008] Preprocessing the real-time image of the workpiece surface to obtain an image of the rubber strip to be tested;

[0009] Calculating the pixel value slope of the image of the rubber strip to be tested according to the image of the rubber strip to be tested, and identifying the gap of the rubber strip according to the pixel value slope;

[0010] Performing edge detection on the image of the rubber strip to be tested to obtain the width of the rubber strip;

[0011] According to the image of the rubber strip to be tested, binarization processing is performed to obtain a black and white image of the rubber strip to be tested;

[0012] According to the black and white image of the rubber strip to be tested and the width of the rubber strip, a black and white pixel point detection operation is performed to obtain a broken line defect point;

[0013] According to the broken line defect point and the gap of the rubber strip, a quality determination operation is performed to obtain the quality of the rubber strip;

[0014] According to the quality of the rubber strip, the yield rate of the side seam glue wiping machine is calculated.

[0015] Preferably, the real-time image of the workpiece surface is obtained by an image acquisition module arranged on the eraser path, including:

[0016] The encoded real-time image of the workpiece surface sent by the image acquisition module is received, and the encoded real-time image of the workpiece surface is decoded to obtain the real-time image of the workpiece surface.

[0017] Preferably, the preprocessing of the real-time image of the workpiece surface to obtain the image of the rubber strip to be tested includes:

[0018] Perform grayscale processing on the real-time image of the workpiece surface to obtain a grayscale image of the workpiece surface;

[0019] According to the grayscale image of the workpiece surface, quality judgment is performed, and the real-time image of the workpiece surface is divided into a qualified image and an unqualified image, and the qualified image is retained;

[0020] A filtering operation is performed on the qualified quality image to remove noise and miscellaneous points in the qualified quality image to obtain the image of the rubber strip to be tested.

[0021] Preferably, the step of calculating the pixel value slope of the rubber strip image to be tested according to the rubber strip image to be tested, and identifying the rubber strip gap according to the pixel value slope comprises:

[0022] According to the image of the rubber strip to be tested, the slope of the pixel value of each row of pixels is calculated;

[0023] Compare the pixel value slope with the preset slope threshold to obtain the mutation pixel point;

[0024] Connect adjacent mutation pixel points to obtain a mutation pixel curve;

[0025] The number of pixel points on the sudden pixel curve is compared with a preset number threshold. When the number of pixel points on the sudden pixel curve is greater than the preset number threshold, it is determined to be a rubber strip gap.

[0026] Preferably, the calculating the pixel value change rate of each row of pixels includes:

[0027] Pixel value slope calculation formula:

[0028]

[0029]

[0030] Among them, the image The pixel position is , No. The pixel position is , No. The pixel position is , No. The pixel value in pixels , No. The pixel value in pixels , No. The pixel value in pixels , No. The pixel value change rate is , No. The pixel value change rate is , No. The pixel value slope is .

[0031] Preferably, performing edge detection operation according to the image of the rubber strip to be tested to obtain the width of the rubber strip includes:

[0032] Processing the image of the rubber strip to be tested by using an edge detection algorithm to obtain the edge contour of the rubber strip;

[0033] The width of the adhesive strip is determined by calculating the pixel distance between two corresponding pixel points on the edge contour of the adhesive strip.

[0034] Preferably, the binary processing is performed on the image of the adhesive strip to be tested, and the black and white image of the adhesive strip to be tested includes:

[0035] According to the gray value of each pixel in the image of the rubber strip to be tested, the gray value of each pixel is compared with a preset threshold value to obtain a binary comparison result;

[0036] According to the binary comparison result, the pixel points whose grayscale values ​​are greater than or equal to the preset threshold are assigned white, and the pixel points whose grayscale values ​​are less than the preset threshold are assigned black.

[0037] Preferably, the black and white pixel point detection operation is performed according to the black and white image of the rubber strip to be tested and the width of the rubber strip to obtain the broken line defect point, including:

[0038] In the black and white image of the rubber strip to be tested, the horizontal coordinates of the white pixels are extracted to determine the maximum and minimum values ​​of the horizontal coordinates;

[0039] Calculate the coordinates of black pixels within the width of the rubber strip;

[0040] When the coordinates of the black pixel point are between the minimum and maximum values ​​of the horizontal coordinates of the rubber strip, it is determined that there is no broken line defect point in the rubber strip path. When the horizontal coordinates of the black pixel point are outside the minimum and maximum values, it is determined that there is a broken line defect point in the rubber strip path.

[0041] Preferably, the quality determination is performed based on the broken wire defect point and the rubber strip gap to obtain the quality of the rubber strip, including:

[0042] Determine the position of the broken wire defect point and the gap of the rubber strip to obtain the position relationship between the broken wire defect point and the gap of the rubber strip;

[0043] According to the positional relationship, determining whether the rubber strip is a defective rubber strip or a good rubber strip;

[0044] Among them, when the gap of the rubber strip and the broken line defect point are located at the same coordinate position, it is a defective rubber strip; when the gap of the rubber strip and the broken line defect point are located at different coordinate positions, it is a good rubber strip.

[0045] In a second aspect, the present invention provides a monitoring device for a side seam gluing machine, comprising:

[0046] An image acquisition module is arranged on the eraser path to obtain a real-time image of the workpiece surface;

[0047] An image preprocessing module preprocesses the real-time image of the workpiece surface to obtain an image of the rubber strip to be tested;

[0048] A gap recognition module calculates the pixel value slope of the image of the rubber strip to be tested according to the image of the rubber strip to be tested, and identifies the gap of the rubber strip according to the pixel value slope;

[0049] A width detection module performs edge detection operation according to the image of the rubber strip to be tested to obtain the width of the rubber strip;

[0050] The image binarization module performs binarization processing on the image of the rubber strip to be tested to obtain a black and white image of the rubber strip to be tested;

[0051] A defect point recognition module performs a black and white pixel point detection operation according to the black and white image of the rubber strip to be tested and the width of the rubber strip to obtain a broken line defect point;

[0052] A quality analysis module performs quality determination based on the wire break defect points and the rubber strip gap to obtain the quality of the rubber strip;

[0053] The glue wiping machine evaluation module calculates the yield rate of the side seam glue wiping machine based on the quality of the glue strip.

[0054] In a third aspect, the present invention further provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any one of the above-mentioned methods for monitoring the side seam glue erasing machine when executing the computer program.

[0055] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for monitoring the side seam glue erasing machine.

[0056] Compared with the prior art, the present invention has the following beneficial effects: The present invention relates to the technical field of monitoring of glue erasing machines, and discloses a monitoring method and device for a side seam glue erasing machine. The method is executed by a processor, including obtaining a real-time image of the workpiece surface through an image acquisition module arranged on the glue erasing path; preprocessing the real-time image of the workpiece surface to obtain a rubber strip image to be tested; calculating the pixel value slope of the rubber strip image to be tested, and identifying the rubber strip gap according to the pixel value slope; performing edge detection operations to obtain the rubber strip width; performing binarization processing according to the rubber strip image to be tested to obtain a black and white image of the rubber strip to be tested; performing black and white pixel point detection operations to obtain broken line defect points; performing quality judgment operations according to the broken line defect points and the rubber strip gap to obtain the quality of the rubber strip; and calculating the yield rate of the side seam glue erasing machine according to the quality of the rubber strip. The present method determines the quality of the rubber strip by image detection, thereby reflecting the yield rate of the glue erasing machine and greatly improving the accuracy of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic flow chart of a monitoring method for a side seam glue erasing machine provided by a first embodiment of the present invention;

[0058] Figure 2 It is a schematic structural diagram of a monitoring device for a side seam glue erasing machine provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] Reference Figure 1 The first embodiment of the present invention provides a monitoring method for a side seam gluing machine, comprising the following steps:

[0061] Step S11, obtaining a real-time image of the workpiece surface through an image acquisition module arranged on the eraser path;

[0062] Step S12, preprocessing the real-time image of the workpiece surface to obtain an image of the rubber strip to be tested;

[0063] Step S13: calculating the pixel value slope of the image of the rubber strip to be tested according to the image of the rubber strip to be tested, and identifying the gap of the rubber strip according to the pixel value slope;

[0064] Step S14, performing edge detection operation according to the image of the rubber strip to be tested to obtain the width of the rubber strip;

[0065] Step S15, performing binarization processing on the image of the rubber strip to be tested to obtain a black and white image of the rubber strip to be tested;

[0066] Step S16, performing a black and white pixel point detection operation according to the black and white image of the rubber strip to be tested and the width of the rubber strip to obtain a disconnection defect point;

[0067] Step S17, performing a quality determination operation according to the broken wire defect point and the rubber strip gap to obtain the quality of the rubber strip;

[0068] Step S18, calculating the yield rate of the side seam glue wiping machine according to the quality of the glue strip.

[0069] In step S11, the real-time image of the workpiece surface is obtained by an image acquisition module arranged on the eraser path, including:

[0070] The encoded real-time image of the workpiece surface sent by the image acquisition module is received, and the encoded real-time image of the workpiece surface is decoded to obtain the real-time image of the workpiece surface.

[0071] In an optional embodiment, the image acquisition module uses a high-resolution industrial camera to ensure that the subtle features of the workpiece surface can be captured. The high-resolution industrial camera can provide clear and delicate images, making subsequent image processing and analysis more accurate and reliable; at the same time, the image acquisition module can be properly protected and adjusted according to the working environment of the glue eraser and the characteristics of the workpiece; there are dust, water vapor and other factors in the working environment, and a protective shell is installed to protect the camera lens to prevent it from being contaminated and damaged; according to the size, shape and color of the workpiece and other characteristics, the camera's focal length, angle and exposure time and other parameters can be adjusted to improve the stability and accuracy of image acquisition; in addition, it is also possible to consider using multiple image acquisition modules to shoot the workpiece surface from different angles, so that more comprehensive image information can be obtained and the quality of the rubber strip can be detected more accurately; multiple cameras can be distributed at different positions on the glue erasing path to ensure that each key part of the workpiece can be covered to avoid detection blind spots.

[0072] It should be noted that when decoding the real-time image of the encoded workpiece surface, the efficiency and accuracy of the decoding algorithm should be ensured to reduce image distortion and information loss; an efficient decoding algorithm can quickly restore the encoded image to a clear original image, reduce processing time, and improve the real-time performance of the monitoring system; an accurate decoding algorithm can ensure the quality of the image, avoid blurring, distortion and other problems, and ensure that subsequent image processing and analysis can be based on accurate image data. At the same time, in order to improve the real-time performance of the monitoring method, parallel processing technology is used to accelerate image decoding and subsequent image processing steps; parallel processing technology can make full use of multi-core processors or distributed computing resources, and distribute image processing tasks to multiple processing units at the same time, greatly shortening the processing time; in addition, the image acquisition module should be calibrated and maintained regularly to ensure its performance and accuracy; regular calibration can ensure that the parameters of the camera are accurate and avoid affecting the image quality due to parameter drift; maintenance work includes cleaning the lens, checking the connection lines, etc., to ensure that the image acquisition module is always in good working condition.

[0073] In step S12, the real-time image of the workpiece surface is preprocessed to obtain the image of the rubber strip to be tested, including:

[0074] The real-time image of the workpiece surface is gray-processed to obtain a gray-scale image of the workpiece surface; quality judgment is performed based on the gray-scale image of the workpiece surface, and the real-time image of the workpiece surface is divided into a qualified quality image and an unqualified quality image, and the qualified quality image is retained; the qualified quality image is filtered to remove noise and spots in the qualified quality image to obtain an image of the rubber strip to be tested.

[0075] In an optional embodiment, when performing grayscale processing, different grayscale conversion algorithms are used, and the most suitable method is selected according to the actual situation to ensure that the grayscale image can accurately reflect the characteristics of the workpiece surface; in the quality judgment process, contrast and clarity are set as quality indicators, and the quality of the image is determined by a comprehensive evaluation of these indicators; for images with unqualified quality, they are marked and the reasons are recorded for subsequent analysis and improvement. In the filtering operation, different filter types and parameters can be tried to achieve the best denoising effect. At the same time, a variety of filtering methods are combined to improve the accuracy and stability of filtering.

[0076] It should be noted that when performing grayscale processing, the key information of the image will be retained to avoid excessive grayscale causing loss of important features. The quality judgment standard will be reasonably set according to the specific application scenarios and requirements, and will be continuously optimized and adjusted. In the filtering operation, adaptive filtering is used to avoid excessive filtering so as not to affect the details and clarity of the image. The filtering algorithm and parameters should be evaluated and updated regularly to adapt to different workpieces and environmental changes.

[0077] In step S13, the pixel value slope of the rubber strip image to be tested is calculated according to the rubber strip image to be tested, and the rubber strip gap is identified according to the pixel value slope, including:

[0078] According to the image of the rubber strip to be tested, the pixel value slope of each row of pixels is calculated; the pixel value slope is compared with a preset slope threshold to obtain a mutation pixel point; adjacent mutation pixel points are connected to obtain a mutation pixel curve;

[0079] The number of pixel points on the sudden pixel curve is compared with a preset number threshold. When the number of pixel points on the sudden pixel curve is greater than the preset number threshold, it is determined to be a rubber strip gap.

[0080] In an optional embodiment, when determining the preset slope threshold and number threshold, statistical analysis is performed through a large amount of experimental data to find the parameter values ​​that are most suitable for the current workpiece and erasing process. For the connection of mutation pixel points, different connection algorithms are used to ensure the accuracy and continuity of the connection. The obtained mutation pixel curve is smoothed and other further optimization processes are performed to improve the accuracy of rubber strip gap recognition.

[0081] It should be noted that when calculating the slope of pixel values, appropriate calculation methods and parameters are selected to avoid large calculation errors; the preset slope threshold and number threshold will be reasonably adjusted according to actual conditions, and will be verified and updated regularly.

[0082] In an optional implementation manner, the calculating the pixel value change rate of each row of pixels includes:

[0083] Pixel value slope calculation formula:

[0084]

[0085]

[0086] Among them, the image The pixel position is , No. The pixel position is , No. The pixel position is , No. The pixel value in pixels , No. The pixel value in pixels , No. The pixel value in pixels , No. The pixel value change rate is , No. The pixel value change rate is , No. The pixel value slope is .

[0087] It should be noted that the significance of the calculation method is to accurately quantify pixel changes and provide an accurate data basis for identifying the gap between the rubber strips. By calculating the change rate of two adjacent pixels on the vertical axis (pixel value) and the horizontal axis (position), the brightness change trend of the image in the local area can be accurately reflected. This is very important for detecting objects with specific brightness characteristics such as rubber strips, because there may be differences in brightness between the rubber strip and the workpiece surface. By calculating the pixel value change rate, this difference can be better captured. This formula also provides basic data for subsequent calculations. The difference in the rate of change of two adjacent pixels is further considered, and the difference in position and pixel value is combined for normalization processing. This can more sensitively detect the mutation points of pixel value changes, and has higher accuracy in identifying subtle features such as rubber strip gaps. Because rubber strip gaps usually appear as sudden changes in pixel values, this algorithm can effectively capture these mutation points, thereby improving the accuracy of rubber strip gap identification. In addition, the normalization processing also makes the algorithm more adaptable under different image sizes and resolutions, thereby improving the versatility of the algorithm.

[0088] In step S14, performing edge detection operation according to the image of the rubber strip to be tested to obtain the width of the rubber strip includes:

[0089] The image of the rubber strip to be tested is processed by using an edge detection algorithm to obtain the edge contour of the rubber strip; and the width of the rubber strip is determined by calculating the pixel distance between two corresponding pixel points on the edge contour of the rubber strip.

[0090] In an optional embodiment, when selecting an edge detection algorithm, a comparative experiment is conducted between the Canny edge detection algorithm and the Sobel edge detection algorithm, and the most suitable algorithm is selected according to the actual image effect and computational efficiency. At the same time, the parameters of the edge detection algorithm are adjusted and optimized to better extract the edge contour of the rubber strip. For complex workpiece surfaces and rubber strip shapes, image processing techniques such as morphological processing are combined to further improve the accuracy of edge detection.

[0091] It should be noted that when calculating the width of the rubber strip, it is necessary to ensure that the two corresponding pixel points selected are representative and can accurately reflect the actual width of the rubber strip. The impact of factors such as image resolution and scaling on the width calculation should be considered, and appropriate corrections and calibrations should be made. The edge detection and width calculation process should be verified and evaluated regularly to ensure the reliability and stability of the results.

[0092] It should be noted that the Canny edge detection algorithm is a widely used edge detection algorithm. It uses a Gaussian filter to smooth the image to reduce the impact of noise; uses first-order partial derivative finite difference to calculate the gradient amplitude and direction of the image; the gradient amplitude is calculated by respectively calculating the horizontal and vertical gradient components according to the formula, and the gradient direction is calculated from the horizontal and vertical gradient components according to the formula; non-maximum suppression is performed to refine the edge of the gradient amplitude, that is, for each pixel, its gradient amplitude is compared with the gradient amplitudes of two adjacent pixels along its gradient direction; if it is not a local maximum, it is set to zero, and finally a dual threshold is used to detect and connect the edges. By setting high and low thresholds, pixels with gradient amplitudes greater than the high threshold are determined as strong edge pixels, pixels with gradient amplitudes less than the low threshold are determined as non-edge pixels, and pixels between the two are determined as edge pixels based on their connection with strong edge pixels.

[0093] It should also be noted that Sobel is mainly used to detect edges in images, and preprocessing such as Gaussian smoothing can be performed to reduce the impact of noise. Construct a Sobel operator consisting of two 3x3 matrices, which are used to calculate horizontal and vertical gradients respectively; for each pixel in the image, convolve its surrounding pixels with the corresponding Sobel operator to obtain horizontal and vertical gradient components; use the formula to calculate the gradient amplitude and direction of each pixel based on the horizontal and vertical gradient components; set a threshold to mark pixels with gradient amplitudes greater than the threshold as edge pixels, and pixels with amplitudes less than the threshold as non-edge pixels. The threshold can be adjusted according to actual conditions to obtain better edge detection effects.

[0094] In step S15, the image of the adhesive strip to be tested is binarized to obtain a black and white image of the adhesive strip to be tested, including:

[0095] According to the grayscale value of each pixel in the image of the rubber strip to be tested, the grayscale value of each pixel is compared with a preset threshold to obtain a binary comparison result; according to the binary comparison result, the pixel points whose grayscale values ​​are greater than or equal to the preset threshold are assigned white, and the pixel points whose grayscale values ​​are less than the preset threshold are assigned black.

[0096] In an optional embodiment, when determining the preset threshold, the Otsu method is used to automatically determine the threshold to adapt to different image features and lighting conditions. The Otsu method automatically determines an optimal threshold by calculating the grayscale histogram of the image, so that the variance between the two types of pixels after segmentation is maximized, thereby achieving a better binarization effect; the Otsu method analyzes a large number of sample images, calculates a suitable threshold range, collects and analyzes images of different types of workpieces and erased glue conditions, and finds the threshold range that can be better binarized in various situations, providing reliable parameters for subsequent processing. The Otsu method can further process the binarized image according to actual needs to optimize the binarization result; for example, corrosion and expansion operations can remove some small noise points, connect disconnected edges, and make the binarized image clearer and more accurate.

[0097] It should be noted that when performing binarization, the quality and characteristics of the image should be fully considered to avoid loss of important information or misjudgment due to improper threshold selection. Different images may have different contrast, brightness and noise levels, so it is necessary to select a suitable threshold according to the specific situation. At the same time, different images should be tested and adjusted to ensure the accuracy and stability of the binarization results. By binarizing multiple sample images and comparing them with the actual rubber strip characteristics, the threshold and processing method are continuously adjusted to achieve the best effect; with the changes in the use time, working environment and other factors of the eraser, the characteristics of the image may change. The threshold should be checked and updated regularly to adapt to possible changes to ensure that the binarization process can always accurately reflect the characteristics of the rubber strip.

[0098] In step S16, the black and white pixel point detection operation is performed according to the black and white image of the rubber strip to be tested and the width of the rubber strip to obtain the broken line defect point, including:

[0099] In the black and white image of the rubber strip to be tested, the transverse coordinates of the white pixels are extracted to determine the maximum and minimum values ​​of the transverse coordinates; within the width of the rubber strip, the coordinates of the black pixels are calculated; when the coordinates of the black pixels are between the minimum and maximum values ​​of the transverse coordinates of the rubber strip, it is determined that there are no broken wire defects in the rubber strip path; when the transverse coordinates of the black pixels are outside the minimum and maximum values, it is determined that there are broken wire defects in the rubber strip path.

[0100] In an optional embodiment, the black and white pixels are detected and analyzed multiple times to improve the accuracy of the detection of broken wire defect points. Different scanning directions are used for detection, such as scanning from left to right, from right to left, from top to bottom, from bottom to top, etc., so that the rubber strip area can be more comprehensively covered to avoid missing some potential broken wire defect points due to a single scanning direction; or different sizes of windows can be used for detection. Smaller windows can detect defects in local areas more finely, while larger windows can better grasp the overall rubber strip shape. By flexibly using different window sizes, more accurate judgments can be made on broken wire defect points at different scales; combined with edge detection technology, the location and range of broken wire defect points can be further confirmed. Edge detection can help determine the boundary of the rubber strip. When black pixels are found to appear near the edge and are determined to be possible broken wire defect points, their accuracy can be further verified through the results of edge detection, thereby improving the reliability of judgment. For complex rubber strip patterns or shapes, more advanced algorithms, such as machine learning algorithms, are used to detect and classify broken wire defects. Machine learning algorithms can automatically identify different types of broken wire defect features by learning from a large amount of sample data, and can make adaptive adjustments based on new image data to better adapt to various complex rubber strip situations.

[0101] It should be noted that when performing black and white pixel detection operations, attention should be paid to the accuracy and stability of the rubber strip width. The measurement error of the rubber strip width may affect the judgment result of the broken line defect point. Therefore, it is necessary to adopt reliable measurement methods and equipment, and perform regular calibration and maintenance. For example, a high-precision measuring instrument can be used to measure the rubber strip width multiple times to take the average value, or the accuracy of the measuring equipment can be verified by comparing with objects of known standard size; for the detected broken line defect points, detailed records and analysis should be made for subsequent quality control and improvement measures, and the location, size, shape and other information of the defect points should be recorded, and the causes of the defect points should be analyzed, such as whether it is a failure of the eraser, raw material problems, etc., so as to take targeted improvement measures to improve product quality.

[0102] In step S17, the quality of the rubber strip is determined based on the broken wire defect point and the rubber strip gap to obtain the quality of the rubber strip, including:

[0103] The positions of the broken wire defect point and the rubber strip gap are determined to obtain the positional relationship between the broken wire defect point and the rubber strip gap; based on the positional relationship, the rubber strip is determined to be a defective rubber strip or a good rubber strip; wherein, when the rubber strip gap and the broken wire defect point are located at the same coordinate position, the rubber strip is a defective rubber strip; when the rubber strip gap and the broken wire defect point are located at different coordinate positions, the rubber strip is a good rubber strip.

[0104] In an optional embodiment, in order to make a more accurate quality judgment, the present invention adopts a high-precision coordinate calculation system to accurately determine the specific positions of broken wire defects and rubber strip gaps, ensuring that the accuracy of position judgment reaches an extremely high level, and uses complex algorithm models to conduct in-depth analysis of position relationships, which can distinguish different degrees of position overlap, thereby more carefully judging the quality of the rubber strip. At the same time, a multi-dimensional image feature fusion method is introduced to combine multiple features such as color, texture, and shape to comprehensively consider the overall quality of the rubber strip. For complex rubber strip shapes and various defect combinations, a highly adaptable quality judgment model is adopted, which can automatically adjust and optimize according to different actual conditions to improve the reliability and accuracy of the judgment.

[0105] It should be noted that in the process of quality judgment, algorithms and models that have been verified and optimized through a large number of experiments are used to ensure the accuracy and stability of the judgment results. Targeted adjustments and optimizations are made for different types of rubber strips and eraser processes to adapt to various complex production situations. At the same time, various data generated during the judgment process are recorded and analyzed in detail to provide a strong basis for subsequent quality improvement and process optimization.

[0106] The present invention obtains a real-time image of the workpiece surface through an image acquisition module arranged on the rubber wiping path. The real-time image of the workpiece surface is obtained through an image acquisition module such as a high-resolution industrial camera, so as to provide a raw data basis for subsequent rubber strip quality detection, capture the subtle features of the workpiece surface, and ensure that the subsequent image processing and analysis have an accurate and reliable basis; the real-time image of the workpiece surface is pre-processed to obtain the image of the rubber strip to be tested, and the image is pre-processed by grayscale processing, quality judgment and filtering operations, etc., which can remove noise and miscellaneous points in the image, retain the image of qualified quality, highlight the features of the rubber strip, and prepare for subsequent precise detection; the pixel value slope of the rubber strip image to be tested is calculated, and the rubber strip gap is obtained according to the pixel value slope. By calculating the pixel value slope and identifying the rubber strip gap, the gap position in the rubber strip can be accurately located, providing an important indicator for evaluating the quality of the rubber strip; an edge detection operation is performed to obtain the rubber strip width, and the edge detection operation can determine the width of the rubber strip, which is very important for evaluating the size of the rubber strip. It is very important to check whether the size meets the requirements and to detect the integrity of the rubber strip; based on the image of the rubber strip to be tested, a binarization process is performed to obtain a black and white image of the rubber strip to be tested. The binarization process simplifies the image into black and white, highlighting the difference between the rubber strip and the background, which is convenient for the subsequent analysis and detection of the characteristics of the rubber strip; a black and white pixel point detection operation is performed to obtain the broken line defect point. The detection of black and white pixel points can accurately find the broken line defect point in the rubber strip, which is very important for judging the quality of the rubber strip and helps to timely discover and deal with rubber strips with quality problems; based on the broken line defect point and the rubber strip gap, a quality judgment operation is performed to obtain the quality of the rubber strip. The quality judgment is performed by comprehensively considering factors such as the broken line defect point and the rubber strip gap, which can comprehensively and accurately evaluate the quality of the rubber strip and provide a basis for subsequent quality control and improvement; based on the quality of the rubber strip, the yield rate of the side seam glue wiping machine is calculated, which can intuitively reflect the production quality level of the glue wiping machine and provide important data support for production management and decision-making. The method determines the quality of the rubber strip by means of image detection, thereby reflecting the yield rate of the rubber erasing machine and greatly improving the accuracy of monitoring.

[0107] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0108] Step S21, arranging an image acquisition module on the glue wiping path of the side seam glue wiping machine, obtaining a real-time image acquisition area of ​​the head of the side seam glue wiping machine, and obtaining an image of the rubber strip to be tested acquired by the image acquisition module.

[0109] Step S22, using the image acquisition module to judge the quality of the rubber strip image, if the image quality is low, then the image is discarded, if the image quality is high, then the image is retained;

[0110] Step S23, using the pixel points with larger slope changes to identify gaps;

[0111] Step S24, using Hough transform technology to perform edge detection on black and white pixels, determining the broken wire defect point by calculating the area occupied by the black and white pixels, and determining whether the broken wire defect point in the gap is located above the gap;

[0112] Step S25: if the broken wire defect point is located above the gap, no bad rubber strip warning is issued;

[0113] Step S26, if the broken wire defect point is located below the gap, the white pixels contained in the broken wire defect point are processed by threshold segmentation technology and region growing technology to obtain the defect area of ​​the broken wire defect point, and obtain the position and size of the defect area;

[0114] Step S27, when multiple image acquisition modules simultaneously have bad rubber strip warning signals, output rubber strip production abnormality signals;

[0115] Step S28, if the magnitude relationship between the grayscale values ​​of black and white pixels in adjacent images collected by the multiple image collection modules changes and there is a bad rubber strip warning signal, a rubber strip falling abnormality signal is output;

[0116] Step S29: when multiple image acquisition modules do not have bad rubber strip warning signals at the same time, they output normal rubber strip production signals.

[0117] Step S31, arranging an image acquisition module on the glue wiping path of the side seam glue wiping machine, obtaining a real-time image acquisition area of ​​the head of the side seam glue wiping machine, and obtaining an image of the rubber strip to be tested acquired by the image acquisition module;

[0118] Step S32: Use the image acquisition module to judge the quality of the adhesive strip image. If the image quality is low, the image is discarded; if the image quality is high, the image is retained.

[0119] Step S33, using the pixel points with larger slope changes to identify gaps;

[0120] Step S34, using Hough transform technology to perform edge detection on black and white pixels, determining the broken wire defect point by calculating the area occupied by the black and white pixels, and determining whether the broken wire defect point in the gap is located above the gap;

[0121] Step S35: if the broken wire defect point is located above the gap, no bad rubber strip warning is issued;

[0122] Step S36: if the broken wire defect point is located below the gap, the white pixels contained in the broken wire defect point are processed by threshold segmentation technology and region growing technology to determine whether the broken wire defect point in the gap is located above the gap;

[0123] Step S37: if the broken wire defect point in the gap is located above the gap, no bad rubber strip warning is issued;

[0124] Step S38, if the broken wire defect point in the gap is located below the gap, determine whether the difference in grayscale value of the rubber strip between the left image and the right image exceeds 10%;

[0125] Step S39, performing threshold segmentation and region growing techniques on the rubber strip image to obtain the defect area and location size of the rubber strip;

[0126] Step S310, the images collected by the multiple image acquisition modules are used to determine the location of the rubber strip breakage, and if the location of the rubber strip breakage is adjacent to the location, a rubber strip fall-off abnormality signal is output;

[0127] Step S311: When the rubber strip break positions between the multiple image acquisition modules are not adjacent positions, manual processing is performed.

[0128] The embodiments are preferred implementations of the present invention, but the present invention is not limited to the above-mentioned implementations. Any obvious improvements, substitutions or modifications that can be made by those skilled in the art without departing from the essential content of the present invention belong to the protection scope of the present invention.

[0129] The present invention obtains a real-time image of the workpiece surface through an image acquisition module arranged on the rubber wiping path. The real-time image of the workpiece surface is obtained through an image acquisition module such as a high-resolution industrial camera, so as to provide an original data basis for subsequent rubber strip quality detection, capture the subtle features of the workpiece surface, and ensure that the subsequent image processing and analysis have an accurate and reliable basis; the real-time image of the workpiece surface is pre-processed to obtain the image of the rubber strip to be tested, and the image is pre-processed by grayscale processing, quality judgment and filtering operations, etc., so as to remove noise and miscellaneous points in the image, retain the image of qualified quality, highlight the features of the rubber strip, and prepare for subsequent precise detection; the pixel value slope of the rubber strip image to be tested is calculated, and the rubber strip gap is obtained according to the pixel value slope. By calculating the pixel value slope and identifying the rubber strip gap, the gap position in the rubber strip can be accurately located, providing an important indicator for evaluating the quality of the rubber strip; an edge detection operation is performed to obtain the rubber strip width, and the edge detection operation can determine the width of the rubber strip. This is very important for evaluating whether the size of the rubber strip meets the requirements and detecting the integrity of the rubber strip; according to the image of the rubber strip to be tested, binarization processing is performed to obtain a black and white image of the rubber strip to be tested. Binarization processing simplifies the image into black and white, highlighting the difference between the rubber strip and the background, which is convenient for subsequent analysis and detection of the characteristics of the rubber strip; black and white pixel point detection operation is performed to obtain the broken line defect point. Detecting black and white pixel points can accurately find the broken line defect point in the rubber strip, which is crucial for judging the quality of the rubber strip and helps to timely discover and deal with rubber strips with quality problems; according to the broken line defect point and the gap of the rubber strip, a quality judgment operation is performed to obtain the quality of the rubber strip. The quality judgment is made by comprehensively considering factors such as the broken line defect point and the gap of the rubber strip, which can comprehensively and accurately evaluate the quality of the rubber strip and provide a basis for subsequent quality control and improvement; according to the quality of the rubber strip, the yield rate of the side seam glue wiping machine is calculated, which can intuitively reflect the production quality level of the glue wiping machine. This method determines the quality of the rubber strip by image detection, thereby reflecting the yield rate of the glue wiping machine, greatly improving the accuracy of monitoring.

[0130] Reference Figure 2 The first embodiment of the present invention provides a monitoring device for a side seam gluing machine, comprising:

[0131] An image acquisition module is arranged on the eraser path to obtain a real-time image of the workpiece surface;

[0132] An image preprocessing module preprocesses the real-time image of the workpiece surface to obtain an image of the rubber strip to be tested;

[0133] A gap recognition module calculates the pixel value slope of the image of the rubber strip to be tested according to the image of the rubber strip to be tested, and identifies the gap of the rubber strip according to the pixel value slope;

[0134] A width detection module performs edge detection operation according to the image of the rubber strip to be tested to obtain the width of the rubber strip;

[0135] The image binarization module performs binarization processing on the image of the rubber strip to be tested to obtain a black and white image of the rubber strip to be tested;

[0136] A defect point recognition module performs a black and white pixel point detection operation according to the black and white image of the rubber strip to be tested and the width of the rubber strip to obtain a broken line defect point;

[0137] A quality analysis module performs quality determination based on the wire break defect points and the rubber strip gap to obtain the quality of the rubber strip;

[0138] The glue wiping machine evaluation module calculates the yield rate of the side seam glue wiping machine based on the quality of the glue strip.

[0139] It should be noted that the monitoring device for a side seam glue wiping machine provided in an embodiment of the present invention is used to execute all process steps of a monitoring method for a side seam glue wiping machine in the above embodiment, and the working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0140] The embodiment of the present invention further provides a terminal device. The terminal device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a monitoring program for a side seam gluing machine. When the processor executes the computer program, the steps in the above-mentioned monitoring method embodiments for the side seam gluing machine are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the defect point identification module.

[0141] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0142] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of terminal devices and do not constitute a limitation on the terminal device. The terminal device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0143] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0144] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0145] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0146] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0147] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A monitoring method for a side seam glue wiping machine, characterized in that: Executed by the processor, including: The real-time image of the workpiece surface is obtained by the image acquisition module arranged on the eraser path; Preprocessing the real-time image of the workpiece surface to obtain an image of the rubber strip to be tested; Calculating the pixel value slope of the image of the rubber strip to be tested according to the image of the rubber strip to be tested, and identifying the gap of the rubber strip according to the pixel value slope; Performing edge detection on the image of the rubber strip to be tested to obtain the width of the rubber strip; According to the image of the rubber strip to be tested, binarization processing is performed to obtain a black and white image of the rubber strip to be tested; According to the black and white image of the rubber strip to be tested and the width of the rubber strip, a black and white pixel point detection operation is performed to obtain a broken line defect point; According to the broken line defect point and the gap of the rubber strip, a quality determination operation is performed to obtain the quality of the rubber strip; According to the quality of the rubber strip, the yield rate of the side seam glue wiping machine is calculated; The step of calculating the pixel value slope of the rubber strip image to be tested according to the rubber strip image to be tested, and identifying the rubber strip gap according to the pixel value slope includes: According to the image of the rubber strip to be tested, the slope of the pixel value of each row of pixels is calculated; Compare the pixel value slope with the preset slope threshold to obtain the mutation pixel point; Connect adjacent mutation pixel points to obtain a mutation pixel curve; According to the number of pixel points on the sudden pixel curve, the number is compared with a preset number threshold, and when the number of pixel points on the sudden pixel curve is greater than the preset number threshold, it is determined to be a gap in the rubber strip; Wherein, the black and white pixel point detection operation is performed according to the black and white image of the rubber strip to be tested and the width of the rubber strip to obtain the broken line defect point, including: In the black and white image of the rubber strip to be tested, the horizontal coordinates of the white pixels are extracted to determine the maximum and minimum values ​​of the horizontal coordinates; Calculate the coordinates of black pixels within the width of the rubber strip; When the coordinates of the black pixel point are between the minimum and maximum values ​​of the horizontal coordinates of the rubber strip, it is determined that there is no disconnection defect point in the rubber strip path; when the horizontal coordinates of the black pixel point are outside the minimum and maximum values, it is determined that there is a disconnection defect point in the rubber strip path; Wherein, the quality determination is performed according to the broken line defect point and the rubber strip gap to obtain the quality of the rubber strip, including: Determine the position of the broken wire defect point and the gap of the rubber strip to obtain the position relationship between the broken wire defect point and the gap of the rubber strip; According to the positional relationship, determining whether the rubber strip is a defective rubber strip or a good rubber strip; Among them, when the gap of the rubber strip and the broken line defect point are located at the same coordinate position, it is a defective rubber strip; when the gap of the rubber strip and the broken line defect point are located at different coordinate positions, it is a good rubber strip.

2. The monitoring method of a side seam glue wiping machine according to claim 1, characterized in that: The method of obtaining a real-time image of the workpiece surface by an image acquisition module arranged on the eraser path includes: The encoded real-time image of the workpiece surface sent by the image acquisition module is received, and the encoded real-time image of the workpiece surface is decoded to obtain the real-time image of the workpiece surface.

3. The monitoring method of a side seam glue wiping machine according to claim 1, characterized in that: The preprocessing of the real-time image of the workpiece surface to obtain the image of the rubber strip to be tested includes: Perform grayscale processing on the real-time image of the workpiece surface to obtain a grayscale image of the workpiece surface; According to the grayscale image of the workpiece surface, quality judgment is performed, and the real-time image of the workpiece surface is divided into a qualified image and an unqualified image, and the qualified image is retained; A filtering operation is performed on the qualified quality image to remove noise and miscellaneous points in the qualified quality image to obtain the image of the rubber strip to be tested.

4. The monitoring method of a side seam glue wiping machine according to claim 1, characterized in that: The calculating the pixel value change rate of each row of pixels includes: Pixel value slope calculation formula: Among them, the image The pixel position is , No. The pixel position is , No. The pixel position is , No. The pixel value in pixels , No. The pixel value in pixels , No. The pixel value in pixels , No. The pixel value change rate is , No. The pixel value change rate is , No. The pixel value slope is .

5. The monitoring method of a side seam glue wiping machine according to claim 1, characterized in that: The method of performing edge detection operation according to the image of the rubber strip to be tested to obtain the width of the rubber strip comprises: Processing the image of the rubber strip to be tested by using an edge detection algorithm to obtain the edge contour of the rubber strip; The width of the adhesive strip is determined by calculating the pixel distance between two corresponding pixel points on the edge contour of the adhesive strip.

6. The monitoring method of a side seam glue wiping machine according to claim 1, characterized in that: The binary processing is performed according to the image of the adhesive strip to be tested, and the black and white image of the adhesive strip to be tested includes: According to the gray value of each pixel in the image of the rubber strip to be tested, the gray value of each pixel is compared with a preset threshold value to obtain a binary comparison result; According to the binary comparison result, the pixel points whose grayscale values ​​are greater than or equal to the preset threshold are assigned white, and the pixel points whose grayscale values ​​are less than the preset threshold are assigned black.

7. A monitoring device for a side seam gluing machine, characterized in that: include: An image acquisition module is arranged on the eraser path to obtain a real-time image of the workpiece surface; An image preprocessing module preprocesses the real-time image of the workpiece surface to obtain an image of the rubber strip to be tested; A gap recognition module calculates the pixel value slope of the image of the rubber strip to be tested according to the image of the rubber strip to be tested, and identifies the gap of the rubber strip according to the pixel value slope; A width detection module performs edge detection operation according to the image of the rubber strip to be tested to obtain the width of the rubber strip; The image binarization module performs binarization processing on the image of the rubber strip to be tested to obtain a black and white image of the rubber strip to be tested; A defect point recognition module performs a black and white pixel point detection operation according to the black and white image of the rubber strip to be tested and the width of the rubber strip to obtain a broken line defect point; A quality analysis module performs quality determination based on the wire break defect points and the rubber strip gap to obtain the quality of the rubber strip; The glue wiping machine evaluation module calculates the yield rate of the side seam glue wiping machine based on the quality of the glue strips; The step of calculating the pixel value slope of the rubber strip image to be tested according to the rubber strip image to be tested, and identifying the rubber strip gap according to the pixel value slope includes: According to the image of the rubber strip to be tested, the slope of the pixel value of each row of pixels is calculated; Compare the pixel value slope with the preset slope threshold to obtain the mutation pixel point; Connect adjacent mutation pixel points to obtain a mutation pixel curve; According to the number of pixel points on the sudden pixel curve, the number is compared with a preset number threshold, and when the number of pixel points on the sudden pixel curve is greater than the preset number threshold, it is determined to be a gap in the rubber strip; Wherein, the black and white pixel point detection operation is performed according to the black and white image of the rubber strip to be tested and the width of the rubber strip to obtain the broken line defect point, including: In the black and white image of the rubber strip to be tested, the horizontal coordinates of the white pixels are extracted to determine the maximum and minimum values ​​of the horizontal coordinates; Calculate the coordinates of black pixels within the width of the rubber strip; When the coordinates of the black pixel point are between the minimum and maximum values ​​of the horizontal coordinates of the rubber strip, it is determined that there is no disconnection defect point in the rubber strip path; when the horizontal coordinates of the black pixel point are outside the minimum and maximum values, it is determined that there is a disconnection defect point in the rubber strip path; Wherein, the quality determination is performed according to the broken line defect point and the rubber strip gap to obtain the quality of the rubber strip, including: Determine the position of the broken wire defect point and the gap of the rubber strip to obtain the position relationship between the broken wire defect point and the gap of the rubber strip; According to the positional relationship, determining whether the rubber strip is a defective rubber strip or a good rubber strip; Among them, when the gap of the rubber strip and the broken line defect point are located at the same coordinate position, it is a defective rubber strip; when the gap of the rubber strip and the broken line defect point are located at different coordinate positions, it is a good rubber strip.

Images