An optimization method for making printing plates in screen printing

Abstract

The present invention provides a method for optimizing the plate making of screen printing, which relates to the field of printing technology and includes: extracting image features of a printing image to be screen printed to obtain first image features; performing plate making prediction based on the first image features and the printing parameters of a target device in combination with a machine learning model to determine first plate making parameters of the target device; performing plate making based on the first plate making parameters to obtain a first plate making result, and performing quality detection on the first plate making result based on a preset scanning device to obtain a first detection result; and optimizing the first plate making parameters of the target device based on the first detection result. By extracting features of the printing image and performing plate making prediction, more accurate plate making parameters can be obtained, thereby performing plate making and performing real-time detection on the plate making result, so as to adjust the plate making parameters in a timely manner, which can make the plate making of the target device based on the printing image more accurate and efficient.

Description

Technical Field

[0001] The present invention relates to the field of printing technology, and in particular to a method for optimizing the plate making of screen printing. Background Art

[0002] At present, screen printing, as a printing process with a long history, shows wide application value in many fields such as artistic creation and industrial production. However, the traditional plate-making process relies on manual operation, which has problems such as time-consuming, error-prone, and high cost. Therefore, in recent years, some automated and semi-automated devices have been introduced into the plate-making link.

[0003] However, the existing plate-making link still lacks a systematic intelligent optimization scheme, resulting in a relatively low overall efficiency of screen printing.

[0004] Therefore, the present invention provides a method for optimizing the plate making of screen printing. Summary of the Invention

[0005] The present invention provides a method for optimizing the plate making of screen printing, which is used to extract the features of the printed image and perform plate-making prediction to obtain more accurate plate-making parameters, so as to perform plate making, and perform real-time detection on the plate-making result, so as to adjust the plate-making parameters in time, so that the plate making of the target device based on the printed image is more accurate and efficient.

[0006] The present invention provides a method for optimizing the plate making of screen printing, including:

[0007] Step 1: Extract the image features of the printed image to be screen-printed to obtain the first image features;

[0008] Step 2: Combine the first image features and the printing parameters of the target device with a machine learning model to perform plate-making prediction, so as to determine the first plate-making parameters of the target device;

[0009] Step 3: Perform plate making based on the first plate-making parameters to obtain the first plate-making result, and perform quality inspection on the first plate-making result to obtain the first inspection result;

[0010] Step 4: Optimize the first plate-making parameters of the target device based on the first inspection result.

[0011] According to the present invention, extracting the image features of the printed image to be screen-printed to obtain the first image features includes:

[0012] Step 11: Capture the printed image to be screen-printed based on a preset high-definition camera to obtain the first printed image;

[0013] Step 12: Process the first printed image based on image preprocessing technology to obtain the second printed image;

[0014] Step 13: Extract features and perform feature recognition on the second printed image based on a deep learning algorithm, so as to obtain the first image features of the second printed image.

[0015] According to the present invention, combining the first image features and the printing parameters of the target device with a machine learning model for plate-making prediction, so as to determine the first plate-making parameters of the target device, including:

[0016] Step 21: Determine the initial plate-making prediction model of the target device based on the first image features and the real-time printing parameters of the target device;

[0017] Step 22: Train the initial plate-making prediction model based on the historical printing parameters and the corresponding historical image features of the historical printing process of the target device to obtain the first plate-making prediction model;

[0018] Step 23: Extract each model parameter corresponding to the first plate-making prediction model to obtain the first plate-making parameters of the target device.

[0019] According to the present invention, plate-making is performed based on the first plate-making parameters to obtain the first plate-making result, including:

[0020] Step 01: Input the first plate-making parameters into the target plate-making device, so as to realize image plate-making of the second printed image and obtain the first plate-making result;

[0021] Step 02: Real-time obtain the real-time plate-making state during the image plate-making process based on a preset integrated sensor;

[0022] Step 03: Perform state judgment on the real-time plate-making state at each plate-making moment of the image plate-making, so as to judge whether the real-time plate-making state at each plate-making moment belongs to the standard plate-making state range of the target device, and thus adjust the first plate-making parameters of the target device.

[0023] According to the present invention, image plate-making of the second printed image includes: steps of completing screen cleaning, photosensitive glue coating, exposure, and development based on the second printed image.

[0024] According to the present invention, judging whether the real-time plate-making state at each plate-making moment belongs to the standard plate-making state range of the target device, and thus adjusting the first plate-making parameters of the target device, including:

[0025] Step 031: Determine the real-time plate-making state S at each plate-making moment;

[0026] ; where S is the real-time plate-making state at the current plate-making moment, is the gray value of the i-th plate-making detection point at the current plate-making moment, is the standard gray value of the i-th plate-making detection point at the current plate-making moment, is the data transmission error of the preset integrated sensor, is the plate-making speed of the i-th plate-making detection point at the current plate-making moment, is the plate-making speed of the i-th plate-making detection point at the previous plate-making moment, is the speed conversion coefficient, is the state influence weight of the gray value of the plate-making detection point on the plate-making state, is the state influence weight of the plate-making speed on the plate-making state, and n is the number of plate-making detection points in the image plate-making process of the target device;

[0027] Step 032: Compare the real-time plate-making state at the current plate-making moment with the standard plate-making state range of the target device at the current plate-making moment;

[0028] If the real-time plate-making state belongs to the standard plate-making state range of the target device at the current plate-making moment, it is determined that the real-time plate-making state at the current plate-making moment is qualified;

[0029] Otherwise, it is determined that the real-time plate-making state at the current plate-making moment is unqualified, and the first plate-making parameter of the target device is adjusted in real time.

[0030] According to the quality detection of the first plate-making result provided by the present invention, a first detection result is obtained, including:

[0031] Step 31: Extract the plate-making image from the first plate-making result to obtain the first plate-making image;

[0032] Step 32: Perform image processing on the first plate-making image to obtain a second plate-making image, and extract the image features of the second plate-making image to obtain second image features;

[0033] Among them, the second plate-making image and the second image features are the first plate-making results of the target device for screen printing;

[0034] Step 33: Obtain the first image parameters of the second printing image and obtain the second image parameters of the second plate-making image;

[0035] Step 34: Compare the parameter differences of the corresponding sub-parameters in the first image parameters and the second image parameters to obtain a first parameter difference value;

[0036] Step 35: Combine the first parameter difference value with the corresponding image parameter type to determine the parameter matching degree of each sub-parameter in the second image parameters and the first image parameters;

[0037] If the parameter matching degree corresponding to each sub-parameter is greater than the preset standard parameter matching degree, the second plate-making image and the second printing image are subjected to a first comparison to obtain a first comparison result;

[0038] If there are sub-parameters in the parameter matching degree of the sub-parameters that are not greater than the preset standard parameter matching degree, extract the first sub-parameters corresponding to the first image parameters and the second sub-parameters corresponding to the second image parameters;

[0039] Compare the parameter values of the first sub-parameters and the second sub-parameters, and adjust the sub-parameters with larger parameter values, so as to obtain the adjusted third image parameters, and use the image parameters that have not been adjusted as the fourth image parameters, so that the sub-parameters of each parameter type in the third image parameters are consistent with the sub-parameters of the corresponding parameter type in the fourth image parameters;

[0040] Based on the third image parameters, adjust the corresponding image to obtain the adjusted third plate-making image, and use the image corresponding to the fourth image parameters as the fourth plate-making image;

[0041] Perform a first comparison on the third plate-making image and the fourth plate-making image to obtain a first comparison result;

[0042] Step 36: Perform a corresponding comparison on the first image feature and the second image feature to obtain a second comparison result;

[0043] Step 37: Based on the first comparison result and the second comparison result, comprehensively obtain a first detection result of the target device for plate-making based on the first plate-making parameters.

[0044] According to the plate-making optimization of the first plate-making parameters of the target device provided by the present invention, including:

[0045] Step 41: Obtain the printing accuracy of the target device for screen printing, so as to obtain the maximum error result of screen printing corresponding to the current printing accuracy;

[0046] Step 42: Compare the maximum error result of screen printing with the first detection result, so as to determine the first plate-making defect of the target device based on the comparison result;

[0047] Step 43: Compare the first plate-making defect with the preset defect database, so as to determine the defect optimization plan corresponding to the first plate-making defect;

[0048] Step 44: Based on the defect optimization plan, perform corresponding parameter adjustment on the first plate-making parameters of the target device to obtain second plate-making parameters;

[0049] Step 45: Determine the second plate-making prediction model of the target device based on the second plate-making parameters, and perform plate-making optimization based on the second plate-making prediction model.

[0050] Compared with the prior art, the beneficial effects of the present invention are as follows: A method for optimizing the plate-making of screen printing provided by the present invention extracts the features of the printed image and predicts the plate-making, obtains more accurate plate-making parameters, thereby performs plate-making, and detects the plate-making result in real time, so as to adjust the plate-making parameters in time, which can make the plate-making of the target device based on the printed image more accurate and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0052] Figure 1 It is a flowchart of a method for optimizing the plate-making of screen printing provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0054] Embodiment 1:

[0055] An embodiment of the present invention provides a method for optimizing the plate-making of screen printing, as Figure 1 shown, including:

[0056] Step 1: Extract the image features of the printed image to be screen-printed to obtain the first image features;

[0057] Step 2: Combine the first image features and the printing parameters of the target device with a machine learning model for plate-making prediction, so as to determine the first plate-making parameters of the target device;

[0058] Step 3: Perform plate-making based on the first plate-making parameters to obtain the first plate-making result, and perform quality inspection on the first plate-making result to obtain the first inspection result;

[0059] Step 4: Optimize the first plate-making parameters of the target device based on the first inspection result.

[0060] In this embodiment, screen printing refers to a printing method that uses a screen as the base plate and transfers the ink through the mesh holes of the graphic part to the substrate by the extrusion of a squeegee. It is applicable to various materials such as paper, plastic, metal, glass, etc., and can produce fine patterns and texts.

[0061] In this embodiment, the printed image refers to the printed image that the target device needs to perform screen printing on. Among them, the printed image is captured based on a preset high-precision camera. Capturing images based on a high-precision camera can improve the plate-making efficiency and accuracy in the plate-making process.

[0062] In this embodiment, the first image feature refers to the feature information that can represent the image content extracted from the printed image. For example, the first image features include the color, texture, shape, spatial relationship, etc. of the image.

[0063] In this embodiment, the printing parameters refer to various parameters that affect the printing quality and effect, such as the type of ink, the pressure of the squeegee, the printing speed, etc. The selection and setting of printing parameters are crucial for the printing quality of the target device to perform screen printing.

[0064] In this embodiment, the machine learning model is an algorithm or system that learns through training data and predicts new data. In plate-making prediction, the machine learning model can predict the optimal plate-making parameters based on image features and printing parameters.

[0065] In this embodiment, plate-making prediction refers to the process of using technical means such as machine learning models to predict the optimal plate-making parameters based on image features and printing parameters. Conducting plate-making prediction helps reduce the trial-and-error cost in the plate-making process and improve the plate-making efficiency and quality.

[0066] In this embodiment, the first plate-making parameter is the optimal plate-making parameter obtained by prediction based on the machine learning model and applicable to the target device.

[0067] In this embodiment, the first plate-making result is the printing plate obtained after plate-making based on the first plate-making parameter.

[0068] In this embodiment, quality inspection refers to extracting the plate-making image in the first plate-making result and comparing the extracted plate-making result with the standard plate-making result (i.e., the second printed image), so as to determine the plate-making quality based on the comparison result.

[0069] In this embodiment, the first detection result refers to the result obtained after quality inspection of the first plate-making result.

[0070] In this embodiment, plate-making optimization refers to the process of adjusting and improving the plate-making parameters according to the quality inspection results. Through plate-making optimization, the plate-making quality and printing effect can be further improved.

[0071] The beneficial effects of the above technical solution are as follows: By extracting the features of the printed image and predicting the plate making, more accurate plate making parameters are obtained, and then plate making is carried out. The plate making result is detected in real time, and the plate making parameters are adjusted in time, so that the plate making of the target device based on the printed image is more accurate and efficient.

[0072] Embodiment 2:

[0073] Based on Embodiment 1, image feature extraction is performed on the printed image to be screen printed, and the first image feature is obtained, including:

[0074] Step 11: Capture the printed image to be screen printed based on a preset high-definition camera to obtain the first printed image;

[0075] Step 12: Process the first printed image based on image preprocessing technology to obtain the second printed image;

[0076] Step 13: Perform feature extraction and feature recognition on the second printed image based on a deep learning algorithm to obtain the first image feature of the second printed image.

[0077] In this embodiment, screen printing refers to a printing method that uses a screen as the plate base. Through the extrusion of a squeegee, the ink is transferred to the printing substrate through the mesh holes of the graphic part. It is applicable to various materials such as paper, plastic, metal, glass, etc., and can produce fine patterns and texts.

[0078] In this embodiment, the first printed image refers to the printed image that the target device needs to screen print. Among them, the first printed image is captured based on a preset high-precision camera. Capturing images based on a high-precision camera can improve the plate making efficiency and plate making accuracy in the plate making process.

[0079] In this embodiment, the second printed image is a printed image obtained by performing image preprocessing on the first printed image in ways such as denoising and enhancing contrast. Image preprocessing can improve the image quality of the printed image.

[0080] In this embodiment, the deep learning algorithm is an important algorithm in the field of machine learning. It builds a deep neural network model to perform multi-layer abstraction and representation on the input data, so as to realize the effective processing and analysis of complex data. In the field of image processing, the deep learning algorithm can extract the deep features in the image and provide strong support for subsequent image recognition, classification and other tasks.

[0081] In this embodiment, feature extraction refers to the process of extracting information from an image that can represent the content or characteristics of the image. In deep learning algorithms, feature extraction is usually achieved by training a neural network model, which can learn the key features in the image and represent them as high-dimensional vectors or feature maps.

[0082] In this embodiment, feature recognition is to further analyze and recognize the extracted features on the basis of feature extraction to determine whether there are specific contents or patterns in the image. For example, in deep learning algorithms, feature recognition is usually achieved by training a classifier or a regressor, which can use the extracted features to predict the category, location, or other attributes of the image.

[0083] In this embodiment, the first image feature refers to the feature information that can represent the image content extracted from the second printed image. For example, the first image features include the color, texture, shape, spatial relationship, etc. of the image.

[0084] The beneficial effects of the above technical solution are as follows: By performing image processing on the printed image and extracting image features, the determination of image parameters of the printed image can be made more accurate, so as to obtain a more accurate plate-making prediction model for plate-making prediction, making the plate-making of the target device based on the printed image more accurate and efficient.

[0085] Embodiment 3:

[0086] Based on Embodiment 2, the first image feature and the printing parameters of the target device are combined with a machine learning model for plate-making prediction, so as to determine the first plate-making parameters of the target device, including:

[0087] Step 21: Determine the initial plate-making prediction model of the target device based on the first image feature and the real-time printing parameters of the target device;

[0088] Step 22: Train the initial plate-making prediction model based on the historical printing parameters and the corresponding historical image features of the historical printing process of the target device to obtain the first plate-making prediction model;

[0089] Step 23: Extract each model parameter corresponding to the first plate-making prediction model to obtain the first plate-making parameters of the target device.

[0090] In this embodiment, the real-time printing parameters refer to various parameters that affect the printing quality and effect, such as the type of ink, the pressure of the squeegee, the printing speed, etc. The selection and setting of printing parameters are crucial for the printing quality of the target device for screen printing.

[0091] In this embodiment, the initial plate-making prediction model is a simulation prediction model that can be used for simulation according to the first image feature and the real-time printing parameters of the target device.

[0092] In this embodiment, the historical printing parameters and historical image features refer to the historical printing parameters and corresponding historical image features of the target device during the historical plate-making process. Among them, the parameter types of the historical printing parameters are the same as those of the real-time printing parameters, and the feature types of the historical image features are the same as those of the first image features.

[0093] In this embodiment, the first plate-making prediction model is a prediction model obtained by optimizing the initial plate-making prediction model according to the historical printing parameters and historical image features of the target device, which is more suitable for predicting the plate-making parameters of the target device.

[0094] In this embodiment, the first plate-making parameter refers to the optimal plate-making parameter suitable for the target device obtained by predicting plate-making based on the first plate-making prediction model.

[0095] The beneficial effects of the above technical solutions are as follows: By training a machine learning model, the first plate-making prediction model is obtained, so as to determine the first plate-making parameter of the target device for plate-making, which helps to reduce the trial-and-error cost in the plate-making process and improve the plate-making efficiency and quality.

[0096] Embodiment 4:

[0097] Based on Embodiment 3, plate-making is carried out based on the first plate-making parameter, and the first plate-making result is obtained, including:

[0098] Step 01: Input the first plate-making parameter into the target plate-making device to realize image plate-making of the second printed image and obtain the first plate-making result;

[0099] Step 02: Based on a preset integrated sensor, real-time plate-making status during the image plate-making process is obtained in real time;

[0100] Step 03: Perform status judgment on the real-time plate-making status at each plate-making moment of image plate-making, so as to judge whether the real-time plate-making status at each plate-making moment belongs to the standard plate-making status range of the target device, and thus adjust the first plate-making parameter of the target device.

[0101] In this embodiment, the first plate-making result is a printing plate obtained after plate-making based on the first plate-making parameter.

[0102] In this embodiment, the real-time plate-making status is the plate-making status at each plate-making moment during the image plate-making process of the target device captured by a preset integrated sensor. Among them, the real-time plate-making status is related to the plate-making speed of the target device and the difference between the gray value of the plate-making detection point and the standard gray value.

[0103] In this embodiment, the standard plate-making state range is determined in advance based on the plate-making accuracy of the target device, where the value of the standard plate-making state range is (0.9, 1).

[0104] The beneficial effect of the above technical solution is that by using the plate-making parameters determined by the plate-making prediction model to perform plate-making on the target device, the plate-making efficiency can be improved and the trial-and-error cost in the plate-making process can be reduced.

[0105] Embodiment 5:

[0106] Based on Embodiment 4, image plate-making is performed on the second printed image, including: completing the steps of screen cleaning, photosensitive glue coating, exposure, and development based on the second printed image.

[0107] The beneficial effect of the above technical solution is that by using the prediction model for plate-making prediction to determine the plate-making parameters, and then performing image plate-making on the target device, it helps to reduce the trial-and-error cost in the plate-making process and improve the plate-making efficiency and quality.

[0108] Embodiment 6:

[0109] Based on Embodiment 4, the first plate-making parameter of the target device is adjusted, including:

[0110] Step 031: Determine the real-time plate-making state S at each plate-making moment;

[0111] ; where S is the real-time plate-making state at the current plate-making moment, is the gray value of the i-th plate-making detection point at the current plate-making moment, is the standard gray value of the i-th plate-making detection point at the current plate-making moment, is the data transmission error of the preset integrated sensor, is the plate-making speed of the i-th plate-making detection point at the current plate-making moment, is the plate-making speed of the i-th plate-making detection point at the previous plate-making moment, is the speed conversion coefficient, is the state influence weight of the gray value of the plate-making detection point on the plate-making state, is the state influence weight of the plate-making speed on the plate-making state, and n is the number of plate-making detection points in the image plate-making process of the target device;

[0112] Step 032: Compare the real-time plate-making state at the current plate-making moment with the standard plate-making state range of the target device at the current plate-making moment;

[0113] If the real-time plate-making state belongs to the standard plate-making state range of the target device at the current plate-making moment, it is determined that the real-time plate-making state at the current plate-making moment is qualified;

[0114] Otherwise, it is determined that the real-time plate-making state at the current plate-making moment is unqualified, and the first plate-making parameters of the target device are adjusted in real time.

[0115] In this embodiment, the real-time plate-making state is based on the plate-making state at each plate-making moment during the image plate-making process of the target device captured by a preset integrated sensor. Among them, the real-time plate-making state is related to the plate-making speed of the target device and the difference between the gray value of the plate-making detection point and the standard gray value.

[0116] In this embodiment, the standard plate-making state range is determined in advance based on the plate-making accuracy of the target device. Among them, the value of the standard plate-making state range is (0.9, 1).

[0117] The beneficial effect of the above technical solution is that by using the plate-making parameters determined by the plate-making prediction model to perform plate-making on the target device, the plate-making efficiency can be improved, and the trial-and-error cost during the plate-making process can be reduced.

[0118] Embodiment 7:

[0119] Based on Embodiment 4, quality inspection is performed on the first plate-making result to obtain a first inspection result, including:

[0120] Step 31: Extract the plate-making image from the first plate-making result to obtain a first plate-making image;

[0121] Step 32: Perform image processing on the first plate-making image to obtain a second plate-making image, and extract the image features of the second plate-making image to obtain second image features;

[0122] Among them, the second plate-making image and the second image features are the first plate-making results of the target device for screen printing;

[0123] Step 33: Obtain the first image parameters of the second printed image, and obtain the second image parameters of the second plate-making image;

[0124] Step 34: Compare the parameter differences of the corresponding sub-parameters in the first image parameters and the second image parameters to obtain a first parameter difference value;

[0125] Step 35: Combine the first parameter difference value with the corresponding image parameter type to determine the parameter matching degree of each sub-parameter in the second image parameters and the first image parameters;

[0126] If the parameter matching degree corresponding to each sub-parameter is greater than the preset standard parameter matching degree, the second plate-making image and the second printed image are subjected to a first comparison to obtain a first comparison result;

[0127] If there are sub-parameters in the parameter matching degree of the sub-parameters that are not greater than the preset standard parameter matching degree, extract the first sub-parameters corresponding to the first image parameters and the second sub-parameters corresponding to the second image parameters;

[0128] Compare the parameter values of the first sub-parameters and the second sub-parameters, and adjust the sub-parameters with larger parameter values to obtain the adjusted third image parameters, and use the unadjusted image parameters as the fourth image parameters, so that the sub-parameters of each parameter type in the third image parameters are the same as the corresponding sub-parameters of the fourth image parameters;

[0129] Based on the third image parameters, adjust the corresponding image to obtain the adjusted third plate-making image, and use the image corresponding to the fourth image parameters as the fourth plate-making image;

[0130] Perform a first comparison on the third plate-making image and the fourth plate-making image to obtain a first comparison result;

[0131] Step 36: Perform a corresponding comparison between the first image feature and the second image feature to obtain a second comparison result;

[0132] Step 37: Based on the first comparison result and the second comparison result, comprehensively obtain a first detection result of the target device for plate-making based on the first plate-making parameters.

[0133] In this embodiment, the first plate-making image refers to the plate-making image included in the first plate-making result.

[0134] In this embodiment, the second plate-making image is a plate-making image obtained by performing image processing on the first plate-making image based on image preprocessing technology.

[0135] In this embodiment, the second image feature is the feature information extracted from the second plate-making image that can represent the image content. For example, the second image feature includes the color, texture, shape, spatial relationship, etc. of the image.

[0136] In this embodiment, the second plate-making image and the second image feature are the first plate-making results of the target device for screen printing.

[0137] In this embodiment, the first image parameters refer to the image parameters included in the second printed image, and the second image parameters refer to the image parameters included in the second plate-making image. Among them, the image parameters include image resolution, image size, image color, etc.

[0138] In this embodiment, the first parameter difference value refers to the parameter difference value of the corresponding sub-parameters between the first image parameters and the second image parameters. For example, if the image resolution in the first image parameters is 1920x1080 and the image resolution in the second image parameters is 1080x1080, then the corresponding first parameter difference value is (840,0).

[0139] In this embodiment, the parameter matching degree is related to the first parameter difference value and the corresponding image parameter type. Among them, the more important the image parameter type is for the image, the smaller the first parameter difference value is, and the higher the corresponding parameter matching degree is.

[0140] In this embodiment, the first comparison result refers to comparing the image parameters of the second plate-making image with the image parameters of the second printed image.

[0141] In this embodiment, the third image parameter means that when there are sub-parameters in the parameter matching degree of the sub-parameters of the image parameters that are not greater than the preset standard parameter matching degree, the first sub-parameter corresponding to the first image parameter and the second sub-parameter corresponding to the second image parameter are extracted, and the parameter values of the first sub-parameter and the second sub-parameter are compared, so as to adjust the parameter value of the larger sub-parameter to obtain the adjusted image parameter, and the image parameter corresponding to the smaller sub-parameter is the fourth image parameter.

[0142] In this embodiment, the image corresponding to the third image parameter is the third plate-making image, and the image corresponding to the fourth image parameter is the fourth plate-making image.

[0143] In this embodiment, the second comparison result refers to the comparison result obtained by comparing the first image feature and the second image feature.

[0144] In this embodiment, the first detection result is the result obtained by comprehensively determining and detecting the image plate-making quality of the target device based on the image comparison result and the image feature comparison result.

[0145] The beneficial effects of the above technical solution are: by comparing the plate-making image of the plate-making result with the second printed image, and then detecting the plate-making result in real time based on the comparison result, the plate-making parameters can be adjusted in time, so that the plate-making of the target device based on the printed image is more accurate and efficient.

[0146] Embodiment 8:

[0147] Based on Embodiment 7, the first plate-making parameters of the target device are optimized based on the first detection result, including:

[0148] Step 41: Obtain the printing accuracy of the target device for screen printing, so as to obtain the maximum error result of screen printing corresponding to the current printing accuracy;

[0149] Step 42: Compare the maximum error result of screen printing with the first detection result, so as to determine the first plate-making defect of the target device based on the comparison result;

[0150] Step 43: Compare the first plate-making defect with a preset defect database to determine a defect optimization solution corresponding to the first plate-making defect;

[0151] Step 44: Based on the defect optimization solution, perform corresponding parameter adjustment on the first plate-making parameters of the target device to obtain second plate-making parameters;

[0152] Step 45: Determine a second plate-making prediction model of the target device based on the second plate-making parameters, and perform plate-making optimization based on the second plate-making prediction model.

[0153] In this embodiment, the first plate-making defects include line breaks, color deviations, etc.

[0154] In this embodiment, the defect optimization solution refers to solutions such as defect correction for the first plate-making defect or re-plate-making.

[0155] In this embodiment, the second plate-making parameters are plate-making parameters obtained by performing corresponding parameter adjustment on the first plate-making parameters of the target device based on the defect optimization solution.

[0156] In this embodiment, the second plate-making prediction model is a plate-making prediction model obtained by adjusting the corresponding model parameters of the first plate-making prediction model based on the second plate-making parameters.

[0157] In this embodiment, plate-making optimization refers to the process of adjusting and improving plate-making parameters according to the quality inspection results. Through plate-making optimization, the plate-making quality and printing effect can be further improved.

[0158] The beneficial effects of the above technical solution are: By comparing and analyzing the first detection result, the plate-making defects of the target device are determined, and a defect optimization solution is determined for plate-making optimization, which can make the plate-making optimization of the target device more timely and accurate.

[0159] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: They can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the plate-making of screen printing, characterized in that, Including: Step 1: Extract image features of the printing image to be screen-printed to obtain the first image features; Step 2: Combine the first image features and the printing parameters of the target device with a machine learning model for plate-making prediction to determine the first plate-making parameters of the target device; Step 3: Perform plate-making based on the first plate-making parameters to obtain the first plate-making result, and perform quality inspection on the first plate-making result to obtain the first inspection result; Step 4: Optimize the plate-making parameters of the target device based on the first inspection result; Among them, Step 3 includes: Step 01: Input the first plate-making parameters into the target plate-making device to achieve image plate-making of the second printing image and obtain the first plate-making result; Step 02: Obtain the real-time plate-making status during the image plate-making process based on a preset integrated sensor; Step 03: Judge the real-time plate-making status at each plate-making moment of the image plate-making to determine whether the real-time plate-making status at each plate-making moment belongs to the standard plate-making status range of the target device, so as to adjust the first plate-making parameters of the target device. Specifically, it includes: Step 031: Determine the real-time plate-making status S at each plate-making moment; ; where S is the real-time plate-making status at the current plate-making moment, is the gray value of the i-th plate-making detection point at the current plate-making moment, is the standard gray value of the i-th plate-making detection point at the current plate-making moment, is the data transmission error of the preset integrated sensor, is the plate-making speed of the i-th plate-making detection point at the current plate-making moment, is the plate-making speed of the i-th plate-making detection point at the previous plate-making moment, is the speed conversion coefficient, is the state influence weight of the gray value of the plate-making detection point on the plate-making status, is the state influence weight of the plate-making speed on the plate-making status, and n is the number of plate-making detection points in the image plate-making process of the target device; Step 032: Compare the real-time plate-making status at the current plate-making moment with the standard plate-making status range of the target device at the current plate-making moment; If the real-time plate-making status belongs to the standard plate-making status range of the target device at the current plate-making moment, it is determined that the real-time plate-making status at the current plate-making moment is qualified; Otherwise, it is judged that the real-time plate-making status at the current plate-making moment is unqualified, and the first plate-making parameters of the target device are adjusted in real time.

2. The plate-making optimization method for screen printing according to claim 1, wherein Extracting image features of the printing image to be screen-printed to obtain the first image features includes: Step 11: Capture the printing image to be screen-printed based on a preset high-definition camera to obtain the first printing image; Step 12: Process the first printing image based on image preprocessing technology to obtain the second printing image; Step 13: Extract features and perform feature recognition on the second printing image based on a deep learning algorithm to obtain the first image features of the second printing image.

3. The method for optimizing the plate making of screen printing according to claim 2, characterized in that, Combining the first image features and the printing parameters of the target device with a machine learning model for plate-making prediction to determine the first plate-making parameters of the target device includes: Step 21: Determine the initial plate-making prediction model of the target device based on the first image features and the real-time printing parameters of the target device; Step 22: Train the initial plate-making prediction model based on the historical printing parameters and the corresponding historical image features of the historical printing process of the target device to obtain the first plate-making prediction model; Step 23: Extract each model parameter corresponding to the first plate-making prediction model to obtain the first plate-making parameters of the target device.

4. The method for optimizing the plate-making of screen printing according to claim 1, wherein Performing image plate-making on the second printing image includes: completing the steps of screen cleaning, photosensitive glue coating, exposure, and development based on the second printing image.

5. A method for optimizing the plate-making of screen printing according to claim 1, characterized in that, Performing quality inspection on the first plate-making result to obtain the first inspection result includes: Step 31: Extract the plate-making image in the first plate-making result to obtain the first plate-making image; Step 32: Perform image processing on the first plate-making image to obtain a second plate-making image, and extract the image features of the second plate-making image to obtain second image features; Among them, the second plate-making image and the second image features are the first plate-making results of the target device for screen printing; Step 33: Obtain the first image parameters of the second printed image and obtain the second image parameters of the second plate-making image; Step 34: Compare the parameter differences of the corresponding sub-parameters in the first image parameters and the second image parameters to obtain a first parameter difference value; Step 35: Combine the first parameter difference value with the corresponding image parameter type to determine the parameter matching degree of each sub-parameter in the second image parameters and the first image parameters; If the parameter matching degree corresponding to each sub-parameter is greater than the preset standard parameter matching degree, then perform a first comparison between the second plate-making image and the second printed image to obtain a first comparison result; If there are sub-parameters whose parameter matching degrees are not greater than the preset standard parameter matching degree among the parameter matching degrees of the sub-parameters, then extract the first sub-parameters of the corresponding first image parameters and the second sub-parameters of the corresponding second image parameters; Compare the parameter values of the first sub-parameters and the second sub-parameters, and adjust the sub-parameters with larger parameter values to obtain adjusted third image parameters, and use the image parameters that have not been adjusted as fourth image parameters, so that the sub-parameters of each parameter type in the third image parameters are consistent with the sub-parameters of the corresponding parameter type in the fourth image parameters; Based on the third image parameters, adjust the corresponding image to obtain an adjusted third plate-making image, and use the image corresponding to the fourth image parameters as the fourth plate-making image; Perform a first comparison between the third plate-making image and the fourth plate-making image to obtain a first comparison result; Step 36: Perform a corresponding comparison between the first image features and the second image features to obtain a second comparison result; Step 37: Based on the first comparison result and the second comparison result, comprehensively obtain a first detection result of the target device for plate-making based on the first plate-making parameters.

6. The plate-making optimization method for screen printing according to claim 5, characterized in that, Perform plate-making optimization on the first plate-making parameters of the target device based on the first detection result, including: Step 41: Obtain the printing accuracy of the target device for screen printing, so as to obtain the maximum error result of screen printing corresponding to the current printing accuracy; Step 42: Compare the maximum error result of screen printing with the first detection result, so as to determine the first plate-making defect of the target device based on the comparison result; Step 43: Compare the first plate-making defect with the preset defect database, so as to determine the defect optimization scheme corresponding to the first plate-making defect; Step 44: Based on the defect optimization scheme, perform corresponding parameter adjustment on the first plate-making parameters of the target device to obtain second plate-making parameters; Step 45: Determine the second plate-making prediction model of the target device based on the second plate-making parameters, and perform plate-making optimization based on the second plate-making prediction model.

Images