Production intelligent quality information detection and analysis method based on big data

Abstract

The invention relates to the technical field of big data, and discloses a production intelligent quality information detection and analysis method based on big data. After a printing pressure parameter, a printing ink parameter and a printing precision parameter are extracted from the qualified printed matter image, a printing pressure effect coefficient, a printing ink balance coefficient and a printing precision reduction coefficient are calculated, then a quality monitoring comprehensive model is established to calculate a comprehensive printing quality index, and then whether the quality of the printed matter is qualified or not is judged. According to the intelligent quality detection system, qualified and unqualified printed matters are placed in a classified mode, the unqualified printed matters are recycled in a unified mode, the unqualified printed matters are screened out through image detection of the printed matters, the unqualified printed matters are secondarily screened out through parameter analysis, and intelligent quality detection of printing machine production is achieved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically to a production intelligent quality information detection and analysis method based on big data. Background Art

[0002] With the continuous progress of the printing industry and the intensification of market competition, the quality requirements of printed products are getting higher and higher. Traditional printed product quality inspection mainly relies on manual visual inspection. This method is not only inefficient, but also easily affected by human factors, resulting in instability and subjectivity of the inspection results. Therefore, the development of a method that can automatically, accurately and efficiently detect the quality of printed products has become an urgent need of the industry. The development of automation technology has provided a new solution for printed product quality inspection. By introducing automated equipment and systems, online inspection and real-time monitoring of printed product quality can be achieved, which can not only improve the inspection efficiency, but also ensure the accuracy and stability of the inspection results.

[0003] However, there are many types of printed products, including different materials, colors, sizes, and printing processes. Automation technology may face problems with recognition accuracy and stability when processing some complex printed products. The production process of printed products involves multiple links, and each link may affect the quality of the printed products. If only a single test is performed in a certain link, the overall quality may not be fully evaluated due to variables in other links, resulting in inaccurate results, thereby affecting the credibility of the judgment results. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a production intelligent quality information detection and analysis method based on big data to solve the problems existing in the above-mentioned background technology.

[0005] The present invention provides the following technical solution: a production intelligent quality information detection and analysis method based on big data, comprising the following steps:

[0006] Step S01: Extracting images of printed products: Scanning and analyzing printed products using image processing technology, and comparing the actual printed images with the standard template images to detect whether the surface quality of the printed products is qualified;

[0007] Step S02: extracting data from the image of the printed product that has passed the inspection in step S01: converting the image data into numerical values, including printing pressure parameters, printing ink parameters and printing precision parameters, through a graphic digitizing instrument;

[0008] Step S03: performing data processing on the printing pressure parameters in step S02: inputting the printing pressure parameters into the printing pressure analysis mathematical model through the printing pressure analysis mathematical model, and calculating the printing pressure effect coefficient;

[0009] Step S04: performing data processing on the printing ink parameters in step S02: inputting the printing ink parameters into the ink balance calculation mathematical model through the ink balance calculation mathematical model, and calculating the printing ink balance coefficient;

[0010] Step S05: performing data processing on the printing accuracy parameters in step S02: inputting the printing accuracy parameters into the printing accuracy detection mathematical model through the printing accuracy detection mathematical model, and calculating the printing accuracy restoration coefficient;

[0011] Step S06: Establishing a comprehensive quality monitoring model: Based on the printing pressure effect coefficient in step S03, the printing ink balance coefficient in step S04 and the printing accuracy restoration coefficient in step S05, a comprehensive quality monitoring model is established to calculate a comprehensive printing quality index;

[0012] Step S07: judging the comprehensive printing quality index in step S06: judging whether the quality of the printed product is qualified according to the comprehensive printing quality index, and placing the qualified and unqualified printed products by categories;

[0013] Step S08: Collect unqualified printed materials in a unified manner: Collect unqualified printed materials in step S07 and unqualified printed materials in step S01 in a unified manner, and indicate the reasons for the unqualified printed materials.

[0014] Preferably, the step S01 uses image processing technology to scan and analyze the printed matter, including: color feature extraction: extracting the color histogram, color moment and color set of the printed matter to evaluate the consistency and accuracy of the color; texture feature extraction: using the grayscale co-occurrence matrix to extract the texture information of the image; shape feature extraction: for printed matters containing specific shapes and patterns, extracting edge and contour shape features.

[0015] Preferably, the printing pressure parameters in step S02 include: elastic modulus E of the printing material, absolute deformation of the printing rubber , the original thickness of the printed rubber d, the inner diameter of the cylinder l, the Poisson's ratio of the printed material As well as the printing cylinder radius r, printing ink parameters include ink viscosity , the porosity of the printed paper c, atmospheric pressure , printing time t, ink reflectivity , ink standard reflectivity As well as the ink thickness D, the printing accuracy parameters include the pixel coordinates of each positioning point in the printing template and the pixel coordinates of the corresponding points in the print .

[0016] Preferably, in step S03, the printing pressure parameters are input into the printing pressure analysis mathematical model through the printing pressure analysis mathematical model, and the specific content of calculating the printing pressure effect coefficient is as follows:

[0017] Step S11: Calculate the printing pressure using the following formula: ,in represents the printing pressure, E represents the elastic modulus of the printing material, represents the absolute deformation of the printed rubber, and d represents the original thickness of the printed rubber;

[0018] Step S12: Calculate the printing pressure effect coefficient, the calculation formula is: , where Yp represents the printing pressure effect coefficient, represents the printing pressure, l represents the inner diameter of the cylinder, represents the Poisson’s ratio of the printing material, E represents the elastic modulus of the printing material, and r represents the radius of the printing roller.

[0019] Preferably, in step S04, the printing ink parameters are input into the ink balance calculation mathematical model through the ink balance calculation mathematical model, and the specific content of the printing ink balance coefficient is calculated as follows:

[0020] Step S11: Calculate the ink penetration rate during the printing process, the calculation formula is: , where vc represents the ink penetration rate during printing, represents the viscosity of the ink, c represents the porosity of the printed paper, Indicates printing pressure, represents the atmospheric pressure, and t represents the printing time;

[0021] Step S12: Calculate the printing ink balance coefficient, the calculation formula is: , where Yv represents the printing ink balance coefficient, Indicates the ink reflectivity, It represents the standard reflectivity of ink, D represents the thickness of ink, and vc represents the penetration rate of ink during printing.

[0022] Preferably, in step S05, the printing accuracy parameters are input into the printing accuracy detection mathematical model through the printing accuracy detection mathematical model, and the specific content of the printing accuracy restoration coefficient is calculated as follows:

[0023] Step S11: locating the pixel coordinates of each positioning point in the printing template, recorded as , locate the pixel coordinates of the corresponding points in the printed matter, recorded as ;

[0024] Step S12: Calculate the printing accuracy restoration coefficient, the calculation formula is: , where Mx represents the printing accuracy restoration coefficient, Represents the horizontal coordinate of the pixel of each positioning point in the printing template, Represents the vertical coordinate of the pixel of each positioning point in the printing template, Indicates the horizontal coordinate of the pixel corresponding to each point in the print, Indicates the horizontal coordinate of the pixel corresponding to each point in the print.

[0025] Preferably, in step S06, based on the printing pressure effect coefficient in step S03, the printing ink balance coefficient in step S04 and the printing accuracy restoration coefficient in step S05, a comprehensive quality monitoring model is established to calculate the comprehensive printing quality index, and the calculation formula is: , where Zm represents the comprehensive printing quality index, Yp represents the printing pressure effect coefficient, Yv represents the printing ink balance coefficient, and Mx represents the printing accuracy restoration coefficient. , and Represents a constant.

[0026] Preferably, the step S07 compares the comprehensive printing quality index Zm with a preset printing quality threshold If the comprehensive printing quality index Zm is greater than or equal to the preset printing quality threshold , the printed product quality is judged to be qualified. If the comprehensive printing quality index Zm is less than the preset printing quality threshold , then the printed product quality is judged to be unqualified.

[0027] Preferably, in step S08, the printed materials that fail the test are uniformly recycled, the printed materials that fail the test in step S01 are marked as failed in the first test, and the printed materials that fail the test in step S07 are marked as failed in the second test.

[0028] Technical effects and advantages of the present invention:

[0029] The present invention is provided with step S01: extracting images of printed products, step S02: extracting data from the images of the printed products that have passed the inspection in step S01, step S03: processing data on the printing pressure parameters in step S02, step S04: processing data on the printing ink parameters in step S02, step S05: processing data on the printing precision parameters in step S02, step S06: establishing a comprehensive quality monitoring model, step S07: judging the comprehensive printing quality index in step S06, and step S08: uniformly recycling the printed products that have failed the inspection. In short, a production intelligent quality information detection and analysis method based on big data can screen out unqualified printed products by detecting images of printed products, and screen out unqualified printed products for the second time by parameter analysis, so as to quickly complete the detection tasks of a large number of printed products. Compared with the traditional manual detection method, the intelligent detection significantly improves the detection efficiency, reduces the time required for detection, and realizes the intelligent quality detection of printing press production. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 The figure is a flow chart of a production intelligent quality information detection and analysis method based on big data. DETAILED DESCRIPTION

[0031] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The present invention involves a method for intelligent production quality information detection and analysis based on big data and is not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0032] The present invention provides a production intelligent quality information detection and analysis method based on big data, comprising the following steps:

[0033] Step S01: Extracting images of printed products: Scanning and analyzing printed products using image processing technology, and comparing the actual printed images with the standard template images to detect whether the surface quality of the printed products is qualified;

[0034] Step S02: extracting data from the image of the printed product that has passed the inspection in step S01: converting the image data into numerical values, including printing pressure parameters, printing ink parameters and printing precision parameters, through a graphic digitizing instrument;

[0035] Step S03: performing data processing on the printing pressure parameters in step S02: inputting the printing pressure parameters into the printing pressure analysis mathematical model through the printing pressure analysis mathematical model, and calculating the printing pressure effect coefficient;

[0036] Step S04: performing data processing on the printing ink parameters in step S02: inputting the printing ink parameters into the ink balance calculation mathematical model through the ink balance calculation mathematical model, and calculating the printing ink balance coefficient;

[0037] Step S05: performing data processing on the printing accuracy parameters in step S02: inputting the printing accuracy parameters into the printing accuracy detection mathematical model through the printing accuracy detection mathematical model, and calculating the printing accuracy restoration coefficient;

[0038] Step S06: Establishing a comprehensive quality monitoring model: Based on the printing pressure effect coefficient in step S03, the printing ink balance coefficient in step S04 and the printing accuracy restoration coefficient in step S05, a comprehensive quality monitoring model is established to calculate a comprehensive printing quality index;

[0039] Step S07: judging the comprehensive printing quality index in step S06: judging whether the quality of the printed product is qualified according to the comprehensive printing quality index, and placing the qualified and unqualified printed products by categories;

[0040] Step S08: Collect unqualified printed materials in a unified manner: Collect unqualified printed materials in step S07 and unqualified printed materials in step S01 in a unified manner, and indicate the reasons for the unqualified printed materials.

[0041] In this embodiment, it should be specifically explained that the scanning and analysis of printed products using image processing technology in step S01 includes: color feature extraction: extracting the color histogram, color moment and color set of the printed product, evaluating the consistency and accuracy of the color, and simply describing the global distribution of colors in an image through the color histogram, that is, the proportion of different colors in the entire image. The color moment calculates the color moment of the image to obtain a comprehensive color feature vector for image classification and retrieval tasks;

[0042] Texture feature extraction: The texture information of the image is extracted using the gray-level co-occurrence matrix. The calculation process of the gray-level co-occurrence matrix is ​​as follows: Assume that the size of image I is M×N, the gray level is L, and the gray-level co-occurrence matrix H is an L×L matrix, where H(i, j) represents the number of times a pixel with gray level i and a pixel with gray level j appear at the same time in a specific direction and distance. The specific calculation steps are as follows:

[0043] Select a direction and distance parameter: The direction and distance parameter d can be set according to actual needs;

[0044] Iterate over each pixel in the image: for each pixel (a, b), calculate its neighboring pixels in the selected direction and distance ;

[0045] Get pixel (a, b) and Gray levels i and j;

[0046] In the gray-level co-occurrence matrix H, add 1 to the value of H(i, j);

[0047] Repeat the above steps until all pixels in the image are traversed;

[0048] The final gray-level co-occurrence matrix H contains the spatial dependency information between different gray levels in the image and is used to extract the texture features of the image;

[0049] Shape feature extraction: For printed materials containing specific shapes and patterns, edge and contour shape features are extracted.

[0050] In this embodiment, it should be specifically explained that the printing pressure parameters in step S02 include: elastic modulus E of the printing material, absolute deformation of the printing rubber , the original thickness of the printed rubber d, the inner diameter of the cylinder l, the Poisson's ratio of the printed material As well as the printing cylinder radius r, printing ink parameters include ink viscosity , the porosity of the printed paper c, atmospheric pressure , printing time t, ink reflectivity , ink standard reflectivity As well as the ink thickness D, the printing accuracy parameters include the pixel coordinates of each positioning point in the printing template and the pixel coordinates of the corresponding points in the print .

[0051] In this embodiment, it should be specifically explained that in step S03, the printing pressure parameters are input into the printing pressure analysis mathematical model through the printing pressure analysis mathematical model, and the specific content of calculating the printing pressure effect coefficient is as follows:

[0052] Step S11: Calculate the printing pressure using the following formula: ,in represents the printing pressure, E represents the elastic modulus of the printing material, represents the absolute deformation of the printed rubber, and d represents the original thickness of the printed rubber;

[0053] Step S12: Calculate the printing pressure effect coefficient, the calculation formula is: , where Yp represents the printing pressure effect coefficient, represents the printing pressure, l represents the inner diameter of the cylinder, represents the Poisson’s ratio of the printing material, E represents the elastic modulus of the printing material, and r represents the radius of the printing roller.

[0054] In this embodiment, it should be specifically explained that in step S04, the printing ink parameters are input into the ink balance calculation mathematical model through the ink balance calculation mathematical model, and the specific content of the printing ink balance coefficient calculated is as follows:

[0055] Step S11: Calculate the ink penetration rate during the printing process, the calculation formula is: , where vc represents the ink penetration rate during printing, represents the viscosity of the ink, c represents the porosity of the printed paper, Indicates printing pressure, represents the atmospheric pressure, and t represents the printing time;

[0056] Step S12: Calculate the printing ink balance coefficient, the calculation formula is: , where Yv represents the printing ink balance coefficient, Indicates the ink reflectivity, It represents the standard reflectivity of ink, D represents the thickness of ink, and vc represents the penetration rate of ink during printing.

[0057] In this embodiment, it should be specifically explained that in step S05, the printing accuracy parameters are input into the printing accuracy detection mathematical model through the printing accuracy detection mathematical model, and the specific content of the printing accuracy restoration coefficient is calculated as follows:

[0058] Step S11: locating the pixel coordinates of each positioning point in the printing template, recorded as , locate the pixel coordinates of the corresponding points in the printed matter, recorded as ;

[0059] Step S12: Calculate the printing accuracy restoration coefficient, the calculation formula is: , where Mx represents the printing accuracy restoration coefficient, Represents the horizontal coordinate of the pixel of each positioning point in the printing template, Represents the vertical coordinate of the pixel of each positioning point in the printing template, Indicates the horizontal coordinate of the pixel corresponding to each point in the print, Indicates the horizontal coordinate of the pixel corresponding to each point in the print.

[0060] In this embodiment, it should be specifically explained that in step S06, based on the printing pressure effect coefficient in step S03, the printing ink balance coefficient in step S04 and the printing accuracy restoration coefficient in step S05, a comprehensive quality monitoring model is established to calculate the comprehensive printing quality index, and the calculation formula is: , where Zm represents the comprehensive printing quality index, Yp represents the printing pressure effect coefficient, Yv represents the printing ink balance coefficient, and Mx represents the printing accuracy restoration coefficient. , and Represents a constant.

[0061] In this embodiment, it should be specifically explained that the step S07 compares the comprehensive printing quality index Zm with the preset printing quality threshold. If the comprehensive printing quality index Zm is greater than or equal to the preset printing quality threshold , the printed product quality is judged to be qualified. If the comprehensive printing quality index Zm is less than the preset printing quality threshold , then the printed product quality is judged to be unqualified.

[0062] In this embodiment, it should be specifically explained that step S08 collects the unqualified printed materials in a unified manner, marks the unqualified printed materials in step S01 as unqualified in the first test, and marks the unqualified printed materials in step S07 as unqualified in the second test.

[0063] The difference between the present embodiment and the prior art mainly lies in that the present embodiment is provided with step S01: image extraction of printed matter, step S02: data extraction of the image of the printed matter that has passed the inspection in step S01, step S03: data processing of the printing pressure parameter in step S02, step S04: data processing of the printing ink parameter in step S02, step S05: data processing of the printing precision parameter in step S02, step S06: establishment of a comprehensive quality monitoring model, step S07: judgment of the comprehensive printing quality index in step S06, step S08: unified recycling of the printed matter that has failed the inspection. In short, a production intelligent quality information detection and analysis method based on big data can screen out the printed matter that has failed the inspection by detecting the image of the printed matter, and screen out the printed matter that has failed the inspection by parameter analysis for the second time, so as to quickly complete the inspection task of a large number of printed matters. Compared with the traditional manual inspection method, the intelligent inspection significantly improves the inspection efficiency, reduces the time required for inspection, and realizes the intelligent quality inspection of the printing press production.

[0064] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0065] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A production intelligent quality information detection and analysis method based on big data, characterized by: The following steps are involved: Step S01: Extracting images of printed products: Scanning and analyzing printed products using image processing technology, and comparing the actual printed images with the standard template images to detect whether the surface quality of the printed products is qualified; Step S02: extracting data from the image of the printed product that has passed the inspection in step S01: converting the image data into numerical values, including printing pressure parameters, printing ink parameters and printing precision parameters, through a graphic digitizing instrument; Step S03: performing data processing on the printing pressure parameters in step S02: inputting the printing pressure parameters into the printing pressure analysis mathematical model through the printing pressure analysis mathematical model, and calculating the printing pressure effect coefficient; Step S04: performing data processing on the printing ink parameters in step S02: inputting the printing ink parameters into the ink balance calculation mathematical model through the ink balance calculation mathematical model, and calculating the printing ink balance coefficient; Step S05: performing data processing on the printing accuracy parameters in step S02: inputting the printing accuracy parameters into the printing accuracy detection mathematical model through the printing accuracy detection mathematical model, and calculating the printing accuracy restoration coefficient; Step S06: Establishing a comprehensive quality monitoring model: Based on the printing pressure effect coefficient in step S03, the printing ink balance coefficient in step S04 and the printing accuracy restoration coefficient in step S05, a comprehensive quality monitoring model is established to calculate a comprehensive printing quality index; Step S07: judging the comprehensive printing quality index in step S06: judging whether the quality of the printed product is qualified according to the comprehensive printing quality index, and placing the qualified and unqualified printed products by categories; Step S08: Collect unqualified printed materials in a unified manner: Collect unqualified printed materials in step S07 and unqualified printed materials in step S01 in a unified manner, and indicate the reasons for the unqualified printed materials.

2. According to the big data-based production intelligent quality information detection and analysis method of claim 1, it is characterized by: In step S01, the image processing technology is used to scan and analyze the printed matter, including: color feature extraction: extracting the color histogram, color moment and color set of the printed matter to evaluate the consistency and accuracy of the color; texture feature extraction: extracting the texture information of the image using the gray level co-occurrence matrix; shape feature extraction: for printed matters containing specific shapes and patterns, extracting edge and contour shape features.

3. According to the big data-based production intelligent quality information detection and analysis method of claim 1, it is characterized by: The printing pressure parameters in step S02 include: elastic modulus E of the printing material, absolute deformation of the printing rubber , the original thickness of the printed rubber d, the inner diameter of the cylinder l, the Poisson's ratio of the printed material As well as the printing cylinder radius r, printing ink parameters include ink viscosity , the porosity of the printed paper c, atmospheric pressure , printing time t, ink reflectivity , ink standard reflectivity As well as the ink thickness D, the printing accuracy parameters include the pixel coordinates of each positioning point in the printing template and the pixel coordinates of the corresponding points in the print .

4. The method for intelligent production quality information detection and analysis based on big data according to claim 1 is characterized in that: In step S03, the printing pressure parameters are input into the printing pressure analysis mathematical model through the printing pressure analysis mathematical model, and the specific content of the printing pressure effect coefficient is calculated as follows: Step S11: Calculate the printing pressure using the following formula: ,in represents the printing pressure, E represents the elastic modulus of the printing material, represents the absolute deformation of the printed rubber, and d represents the original thickness of the printed rubber; Step S12: Calculate the printing pressure effect coefficient, the calculation formula is: , where Yp represents the printing pressure effect coefficient, represents the printing pressure, l represents the inner diameter of the cylinder, represents the Poisson’s ratio of the printing material, E represents the elastic modulus of the printing material, and r represents the radius of the printing roller.

5. The method for intelligent production quality information detection and analysis based on big data according to claim 1 is characterized in that: In step S04, the printing ink parameters are input into the ink balance calculation mathematical model through the ink balance calculation mathematical model, and the specific content of the printing ink balance coefficient is calculated as follows: Step S11: Calculate the ink penetration rate during the printing process, the calculation formula is: , where vc represents the ink penetration rate during printing, represents the viscosity of the ink, c represents the porosity of the printed paper, Indicates printing pressure, represents the atmospheric pressure, and t represents the printing time; Step S12: Calculate the printing ink balance coefficient, the calculation formula is: , where Yv represents the printing ink balance coefficient, Indicates the ink reflectivity, It represents the standard reflectivity of ink, D represents the thickness of ink, and vc represents the penetration rate of ink during printing.

6. The method for intelligent production quality information detection and analysis based on big data according to claim 1, characterized in that: In step S05, the printing accuracy parameters are input into the printing accuracy detection mathematical model through the printing accuracy detection mathematical model, and the specific content of the printing accuracy restoration coefficient is calculated as follows: Step S11: locating the pixel coordinates of each positioning point in the printing template, recorded as , locate the pixel coordinates of the corresponding points in the printed matter, recorded as ; Step S12: Calculate the printing accuracy restoration coefficient, the calculation formula is: , where Mx represents the printing accuracy restoration coefficient, Represents the horizontal coordinate of the pixel of each positioning point in the printing template, Represents the vertical coordinate of the pixel of each positioning point in the printing template, Indicates the horizontal coordinate of the pixel corresponding to each point in the print, Indicates the horizontal coordinate of the pixel corresponding to each point in the print.

7. The method for intelligent production quality information detection and analysis based on big data according to claim 1, characterized in that: In step S06, a comprehensive quality monitoring model is established based on the printing pressure effect coefficient in step S03, the printing ink balance coefficient in step S04, and the printing accuracy restoration coefficient in step S05 to calculate the comprehensive printing quality index. The calculation formula is: , where Zm represents the comprehensive printing quality index, Yp represents the printing pressure effect coefficient, Yv represents the printing ink balance coefficient, and Mx represents the printing accuracy restoration coefficient. , and Represents a constant.

8. The method for intelligent production quality information detection and analysis based on big data according to claim 1, characterized in that: The step S07 compares the comprehensive printing quality index Zm with the preset printing quality threshold If the comprehensive printing quality index Zm is greater than or equal to the preset printing quality threshold , the printed product quality is judged to be qualified. If the comprehensive printing quality index Zm is less than the preset printing quality threshold , then the printed product quality is judged to be unqualified.

9. The method for intelligent production quality information detection and analysis based on big data according to claim 1, characterized in that: The step S08 collects the unqualified printed materials in a unified manner, marks the unqualified printed materials in the step S01 as unqualified for the first test, and marks the unqualified printed materials in the step S07 as unqualified for the second test.

Images