Industrial product data interconnection method and system

Abstract

The invention particularly relates to an industrial product data interconnection method and system. The system comprises a data acquisition module; a data analysis module; and a quality judgment module. According to the invention, in the data analysis module, for forming related data, the product is divided into sub-regions in detail, the crack and damage area is accurately calculated, and the corner integrity is evaluated; related printing data are considered from multiple aspects such as pixel point contrast, color difference values and glossiness deviation, and compared with a traditional quality detection method, the method is not limited to surface or single-dimension detection any more; various fine defects and errors occurring in the forming and printing process of a product can be accurately captured, and cracks in the product or color deviation of printed patterns can be accurately recognized and quantitatively evaluated; the multi-dimensional data are comprehensively processed through a scientific algorithm, the obtained quality evaluation coefficient can reflect the product quality condition more truly and comprehensively, and the accuracy and reliability of quality evaluation are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial production technology, and in particular to an industrial product data interconnection method and system. Background Art

[0002] In today's fiercely competitive industrial production landscape, product quality is directly linked to a company's survival and development. For industrial products involving molding and printing processes, such as plastics and packaging, quality control presents numerous challenges.

[0003] Traditional quality inspection methods primarily rely on manual spot checks. These checks are inefficient and unable to conduct comprehensive and detailed inspections of mass-produced products, posing a significant risk of missed inspections. Furthermore, manual judgments are highly subjective, and different inspectors have varying understandings and judgment criteria for quality standards, making it difficult to ensure consistent and accurate inspection results. This can lead to defective products entering the market, damaging a company's reputation and increasing after-sales costs. During the production process, data such as product structural integrity and dimensional accuracy generated in the molding process is isolated from data such as image clarity and color accuracy generated in the printing process. This data is scattered across various devices and record documents, lacking effective interconnection and integration mechanisms. Production managers struggle to quickly obtain comprehensive and accurate product quality information, conduct in-depth data-based analysis, and accurately identify the root causes of production problems.

[0004] Therefore, a method and system for interconnecting industrial product data is needed to analyze the interconnected product data during the production and processing process to address the above-mentioned problems. Summary of the Invention

[0005] The purpose of the present invention is to solve the above problems and to propose an industrial product data interconnection method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: An industrial product data interconnection system, comprising: Data acquisition module: acquires various test data of the product during the processing, including molding-related data and printing-related data; Data analysis module: Analyzes molding-related data and printing-related data to obtain molding defect coefficients and printing error coefficients; comprehensively processes the molding defect coefficients and printing error coefficients to obtain quality assessment coefficients; Quality judgment module: classify product quality levels based on quality assessment coefficients; Decision support module: perform corresponding processing according to the quality level of the product.

[0007] Preferably, the data acquisition module includes: The image information of the product after molding and after printing is obtained, and the molded product image and the printed product image information are preprocessed in turn and recorded as molding-related data and printing-related data respectively; the preprocessing includes grayscale conversion, noise reduction, contrast enhancement and size normalization.

[0008] Preferably, the process of obtaining the molding defect coefficient is as follows: Divide the product into multiple sub-areas based on the set area, and obtain image information corresponding to each sub-area of ​​the product based on the sub-areas divided by the product; Extract crack and damage-related features from the image information in each sub-region and mark the extracted features as the crack and damage areas of each sub-region of the product; perform pixel count on the marked crack and damage areas of each sub-region of the product and calculate the number of pixels in the crack and damage areas of each sub-region of the product; Based on the image resolution, the number of pixels in the crack area and the damaged area in each sub-area of ​​the product is converted into the actual area to obtain the crack area and damaged area in each sub-area of ​​the product; After comprehensive analysis of the crack area and damage area in each sub-region, the defect value of each sub-region is obtained; the defect values ​​of each sub-region are arranged in descending order, and the maximum defect value is extracted and recorded as the maximum defect value; Obtain the contour image of the product, obtain the contour edge based on the edge detection algorithm, and track the contour edge; obtain the curvature radius in the tangent direction between adjacent points on the contour edge, and preset the curvature radius threshold. The points corresponding to the curvature radius greater than the curvature radius threshold are recorded as corner points; Count all corner points, mark the areas where all corner points are located and record them as product corners; After analyzing the corners of the product, the corner integrity is obtained; The forming defect coefficient is obtained by comprehensively processing the maximum defect value and the edge and corner integrity.

[0009] Preferably, analyzing the corners of the product to obtain the corner integrity specifically includes: Compare each corner profile with the standard corner profile in turn to obtain the overlap length between each corner profile and the standard corner profile, divide the overlap length by the total length of the standard corner profile to obtain the overlap degree; calculate the average of each overlap degree to obtain the average overlap degree; The minimum overlap is preset, and the overlap deviation value is obtained by calculating the difference between the average overlap and the minimum overlap; Mark the parts where the standard corner outline and the individual corner outlines do not overlap; And with the standard corner outline as the starting point, draw a straight line perpendicular to the standard corner outline until the straight line touches the corner outline, record the straight line as the deviation line, calculate the length of the deviation line, and take the longest deviation line as the deviation length of the corner; Obtain the deviation length of each corner in turn, sort the deviation lengths of each corner in descending order, and extract the maximum deviation length; The overlap deviation value and the maximum deviation length are combined to obtain the edge and corner integrity.

[0010] Preferably, obtaining the printing error coefficient includes: After obtaining the printed product image information and pre-processing the image, obtain all pixels of the text and pattern on the product pixel map, calculate the contrast between each pixel and its adjacent pixels, and calculate the contrast of all pixels of the text and pattern on the product; divide the contrast of all pixels by the total number of pixels to obtain the average contrast; After extracting the maximum contrast from all contrasts, the difference between the maximum contrast and the average contrast is calculated to obtain the contrast deviation value; Get all the pixels of the text and pattern on the product pixel map value, and preset each pixel Standard value, each pixel point in turn The value corresponds to The color difference value of each pixel is obtained by performing difference calculation on the standard value; the maximum color difference value and the minimum color difference value are extracted, and the color difference extreme value is obtained by subtracting the minimum color difference value from the maximum color difference value; Divide the product into several areas, and record each divided area as a measurement area; obtain the glossiness of each measurement area, perform sum calculation, and divide it by the number of measurement areas to obtain the average glossiness; Calculate the difference between the glossiness of each area and the average glossiness to obtain the corresponding glossiness deviation value. Set the allowable range of glossiness deviation value. Mark the areas corresponding to glossiness deviation values ​​that are not within the allowable range as abnormal areas. Count all abnormal areas and divide the number of abnormal areas by the total number of areas divided into the product to obtain the abnormality ratio. The contrast deviation value, color difference extreme value, and abnormality ratio are calculated using the corresponding formula to obtain the printing error coefficient.

[0011] Preferably, the product is classified into quality grades according to the quality assessment coefficient; Three groups of threshold value ranges are preset, each group of threshold value ranges corresponds to a quality level, and the quality assessment coefficient is matched with the three groups of threshold value ranges to obtain the quality level corresponding to the quality assessment coefficient; the quality levels include qualified, defective and unqualified.

[0012] Preferably, the corresponding processing according to the quality grade of the product specifically includes: When the quality level corresponding to the quality assessment coefficient is qualified: the product enters the next processing step normally; When the quality level corresponding to the quality assessment coefficient is defective: analyze the molding defect coefficient and printing error coefficient of the defective product to determine the source of the defect; When the quality level corresponding to the quality assessment coefficient is unqualified: the unqualified products produced will be scrapped.

[0013] An industrial product data interconnection method, comprising: Data collection: Acquire molding-related data and printing-related data of products during processing; Data analysis: Analyze molding-related data and printing-related data separately to obtain molding defect coefficients and printing error coefficients; then comprehensively process the molding defect coefficients and printing error coefficients to obtain the quality assessment coefficients; Quality judgment: Classify the product quality level according to the quality assessment coefficient; Classification processing: Carry out corresponding processing according to the quality level of the product; The product is qualified and enters the next processing step normally; Product defects: analyze the molding defect coefficient and printing error coefficient of defective products to determine the source of the defects; If the product is unqualified, the unqualified products produced will be scrapped.

[0014] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention divides the product into sub-areas in the data analysis module for molding-related data, accurately calculates cracks and damaged areas, and evaluates the integrity of corners. For printing-related data, it considers multiple aspects such as pixel contrast, color difference value, and gloss deviation. Compared with traditional quality inspection methods, it is no longer limited to surface or single-dimensional inspection. It can accurately capture various subtle defects and errors that occur in the product during the molding and printing process. Whether it is cracks inside the product or color deviations of the printed pattern, they can be accurately identified and quantitatively evaluated. Through scientific algorithms, these multi-dimensional data are comprehensively processed to obtain a quality assessment coefficient that can more realistically and comprehensively reflect the product quality status, greatly improving the accuracy and reliability of quality assessment.

[0015] 2. The present invention divides products into three levels: qualified, defective and unqualified according to the quality assessment coefficient through the quality judgment module, and the decision support module takes targeted measures according to different levels; for qualified products, it promotes them to smoothly enter the next processing step, and records the production data in detail to accumulate a data basis for the continuous optimization of subsequent production processes; when a product is judged to be defective, the system analyzes the molding defect coefficient and the printing error coefficient, compares them with the preset threshold, quickly and accurately locates the source of the defect, and guides maintenance personnel to quickly carry out equipment inspection and maintenance work, thereby reducing production downtime caused by equipment problems and reducing the defective rate; for unqualified products, they are scrapped in time and relevant information is recorded in detail. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Further details, features and advantages of the present application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 Flowchart of the present invention. DETAILED DESCRIPTION

[0017] Several embodiments of the present application will be described in more detail below with reference to the accompanying drawings so that those skilled in the art can implement the present application. The present application can be embodied in many different forms and for many different purposes and should not be limited to the embodiments described herein. These embodiments are provided to make the present application comprehensive and complete and to fully convey the scope of the present application to those skilled in the art. The embodiments do not limit the present application.

[0018] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless expressly defined as such herein.

[0019] See also Figure 1 As shown, the present invention provides a technical solution: An industrial product data interconnection system, comprising: Data acquisition module: acquires various test data of the product during the processing, including molding-related data and printing-related data; The camera captures image information of the product after molding and printing, and pre-processes the molded product image and the printed product image information in turn, recording them as molding-related data and printing-related data respectively; the pre-processing includes grayscale conversion, noise reduction, contrast enhancement, and size normalization; Grayscale conversion: If a color image is obtained, converting the image to grayscale can reduce the amount of data and eliminate the interference that may be caused by color information. In some cases, the key features of the product may be mainly reflected in the grayscale value, such as detecting the texture and cracks on the product surface. Noise reduction: During the acquisition process, images may be affected by various noises, such as sensor noise and ambient light noise. Noise affects the clarity and details of the image. Noise reduction can be used to remove these noises and improve image quality. Common noise reduction methods include mean filtering, median filtering, and Gaussian filtering. Contrast enhancement: Improving the contrast of an image can make the details in the image clearer, facilitating subsequent feature extraction and recognition. For example, histogram equalization and other methods can be used to adjust the grayscale distribution of the image to make the brightness range of the image more reasonable, thereby highlighting the characteristics of the product. Size normalization: Adjusting images to a uniform size facilitates subsequent processing and analysis. Images acquired under different shooting conditions may have different sizes and resolutions. Normalization can bring the images to the same spatial scale, facilitating feature comparison and model training. Data analysis module: Analyzes molding-related data and printing-related data to obtain molding defect coefficients and printing error coefficients; comprehensively processes the molding defect coefficients and printing error coefficients to obtain quality assessment coefficients; The process of obtaining the molding defect coefficient is as follows: Divide the product into multiple sub-areas based on the set area, and obtain image information corresponding to each sub-area of ​​the product based on the sub-areas divided by the product; Extract crack and damage-related features from the image information in each sub-region and mark the extracted features as the crack and damage areas of each sub-region of the product; perform pixel count on the marked crack and damage areas of each sub-region of the product and calculate the number of pixels in the crack and damage areas of each sub-region of the product; Based on the image resolution, the number of pixels in the crack area and the damaged area in each sub-area of ​​the product is converted into the actual area to obtain the crack area and damaged area in each sub-area of ​​the product; After comprehensive analysis of the crack area and damage area in each sub-region, the defect value of each sub-region is obtained; the defect values ​​of each sub-region are arranged in descending order, and the maximum defect value is extracted and recorded as the maximum defect value; Preset the weight factors of the crack area and the damaged area, multiply the crack area and the damaged area by their corresponding weight factors, and then sum them to obtain the defect value; Obtain the contour image of the product, obtain the contour edge based on the edge detection algorithm, and track the contour edge; obtain the curvature radius in the tangent direction between adjacent points on the contour edge, and preset the curvature radius threshold. The points corresponding to the curvature radius greater than the curvature radius threshold are recorded as corner points; Count all corner points, mark the areas where all corner points are located and record them as product corners; After analyzing the corners of the product, the corner integrity is obtained; Specifically include: Compare each corner profile with the standard corner profile in turn to obtain the overlap length between each corner profile and the standard corner profile, divide the overlap length by the total length of the standard corner profile to obtain the overlap degree; calculate the average of each overlap degree to obtain the average overlap degree; The minimum overlap is preset, and the overlap deviation value is obtained by calculating the difference between the average overlap and the minimum overlap; Mark the parts where the standard corner outline and the individual corner outlines do not overlap; And with the standard corner outline as the starting point, draw a straight line perpendicular to the standard corner outline until the straight line touches the corner outline, record the straight line as the deviation line, calculate the length of the deviation line, and take the longest deviation line as the deviation length of the corner; Obtain the deviation length of each corner in turn, sort the deviation lengths of each corner in descending order, and extract the maximum deviation length; The overlap deviation value and the maximum deviation length are combined to obtain the corner integrity; Preset the weight factors of the overlap deviation value and the maximum deviation length, and calculate the product of the overlap deviation value and the maximum deviation length with their corresponding weight factors and then sum them to obtain the corner integrity; The forming defect coefficient is obtained by comprehensively processing the maximum defect value and the edge and corner integrity; The acquisition of printing error coefficient includes: After obtaining the printed product image information and pre-processing the image, obtain all pixels of the text and pattern on the product pixel map, calculate the contrast between each pixel and its adjacent pixels, and calculate the contrast of all pixels of the text and pattern on the product; divide the contrast of all pixels by the total number of pixels to obtain the average contrast; For example, record the calculated contrast of each pixel and then summarize it. For example, after calculation and statistics, the sum of the contrast of all pixels is 500,000 (this is just an assumed value, and the actual value will vary depending on the image content); Given that the image has a total of 40,000 pixels, the sum of the contrast ratios of all pixels (500,000) is divided by the total number of pixels (40,000), which is 500,000 / 40,000 = 12.5. The resulting value of 12.5 is the average contrast ratio of all pixels in the text and pattern on this product image. By calculating the average contrast ratio, you can measure the clarity of printed text and images. A high average contrast ratio indicates clear edges and a good visual effect. A low average contrast ratio may indicate issues with print quality, such as blurred text and images. After extracting the maximum contrast from all contrasts, the difference between the maximum contrast and the average contrast is calculated to obtain the contrast deviation value; Get all the pixels of the text and pattern on the product pixel map value, and preset each pixel Standard value, each pixel point in turn The value corresponds to The color difference value of each pixel is obtained by performing difference calculation on the standard value; the maximum color difference value and the minimum color difference value are extracted, and the color difference extreme value is obtained by subtracting the minimum color difference value from the maximum color difference value; For example, use image processing software or programming languages ​​(such as Python's Pillow library) to obtain the color value of each pixel. In RGB color mode, each pixel consists of three components: red (R), green (G), and blue (B), and the value range is usually 0 to 255; For example, the pixel with coordinates (20, 30) in the image has a color value of (150, 80, 60), which means that the red component value of the pixel is 150, the green component value is 80, and the blue component value is 60. Traverse the entire image and obtain the color values ​​of all 10,000 pixels. Assume that a standard color value is preset for each pixel based on the product's design requirements or quality standards. For example, for the pixel at coordinates (20, 30), its corresponding standard color value is (160, 90, 70). This standard value is preset for all 10,000 pixels in the image. After calculating the color difference values ​​of all pixels, traverse all color difference values, find the maximum and minimum values, and subtract the minimum color difference value from the maximum color difference value to get the color difference extreme value; The color difference extreme value can reflect the difference between the color of the pixel in this product image and the standard color. The larger the color difference extreme value, the greater the degree of color deviation in the image, which may indicate printing quality problems or other color inconsistencies. The smaller the color difference extreme value, the better the consistency between the image color and the standard color. Divide the product into several areas, and record each divided area as a measurement area; obtain the glossiness of each measurement area, perform sum calculation, and divide it by the number of measurement areas to obtain the average glossiness; Calculate the difference between the glossiness of each area and the average glossiness to obtain the corresponding glossiness deviation value. Set the allowable range of glossiness deviation value. Mark the areas corresponding to glossiness deviation values ​​that are not within the allowable range as abnormal areas. Count all abnormal areas and divide the number of abnormal areas by the total number of areas divided into the product to obtain the abnormality ratio. The contrast deviation value, color difference extreme value, and abnormality ratio are calculated using the corresponding formula to obtain the printing error coefficient; The contrast deviation value, color difference extreme value, and abnormal proportion are marked as 、 、 , and substitute into the formula: ; Get the printing error coefficient ;in 、 、 They are the preset reference contrast deviation value, reference color difference extreme value, and reference abnormality ratio. 、 、 are the weight factors corresponding to the contrast deviation value, color difference extreme value, and abnormality ratio respectively; After normalizing the molding defect coefficient and the printing error coefficient, the molding defect coefficient and the printing error coefficient are used as the two right-angled sides of a right triangle, and the remaining side is connected to form a complete right triangle. The area of ​​the right triangle is calculated and recorded as the quality assessment coefficient; Quality judgment module: classify product quality levels based on quality assessment coefficients; Classify product quality grades based on quality assessment coefficients; Three groups of threshold value ranges are preset, each group of threshold value ranges corresponds to a quality level, and the quality assessment coefficient is matched with the three groups of threshold value ranges to obtain the quality level corresponding to the quality assessment coefficient; the quality levels include qualified, defective and unqualified; Decision support module: perform corresponding processing according to the quality level of the product; Specifically include: When the quality level corresponding to the quality assessment coefficient is qualified: the product enters the next processing step normally, and the production data of the product is recorded and archived in detail to provide a basis for subsequent production data analysis in order to continuously optimize the production process; When the quality level corresponding to the quality assessment coefficient is defective: analyzing the molding defect coefficient and printing error coefficient of the defective product, respectively presetting a molding defect coefficient threshold and a printing error coefficient threshold, and comparing the molding defect coefficient and the printing error coefficient of the defective product with the corresponding molding defect coefficient threshold and the printing error coefficient threshold to determine the source of the defect; When the molding defect coefficient of the product is greater than the molding defect coefficient threshold, the relevant equipment for product molding is inspected; when the printing error coefficient is greater than the printing error coefficient threshold, the printing equipment of the product is inspected; When the quality level corresponding to the quality assessment coefficient is unqualified: the unqualified products produced will be scrapped to prevent them from entering the market; at the same time, detailed information such as the quantity, batch, and production time of the unqualified products will be recorded for subsequent tracing and analysis; An industrial product data interconnection method, comprising: Data collection: Acquire molding-related data and printing-related data of products during processing; Data analysis: Analyze molding-related data and printing-related data separately to obtain molding defect coefficients and printing error coefficients; then comprehensively process the molding defect coefficients and printing error coefficients to obtain the quality assessment coefficients; Quality judgment: Products are classified into quality grades based on the quality assessment coefficient. Three groups of threshold value ranges are preset, each of which corresponds to a quality grade. The quality assessment coefficient is matched with the three groups of threshold value ranges to obtain the quality grade corresponding to the quality assessment coefficient. The quality grades include qualified, defective, and unqualified. Classification processing: Carry out corresponding processing according to the quality level of the product; The product is qualified and enters the next processing step normally; Product defects: analyze the molding defect coefficient and printing error coefficient of defective products to determine the source of the defects; If the product is unqualified, the unqualified products that have been produced will be scrapped to prevent them from entering the market; at the same time, detailed records of the quantity, batch, production time and other information of the unqualified products will be kept for subsequent traceability and analysis.

[0020] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The influencing weight factors and specific coefficient values ​​in the formula are set by technical personnel in this field according to actual conditions, and can be adjusted and modified later.

[0021] The above description of the embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An industrial product data interconnection system, characterized in that: include: Data acquisition module: obtain various test data of products during processing; Including molding related data and printing related data; Data analysis module: Analyzes molding-related data and printing-related data to obtain molding defect coefficient and printing error coefficient; The molding defect coefficient and the printing error coefficient are processed comprehensively to obtain the quality assessment coefficient; Quality judgment module: classify product quality levels based on quality assessment coefficients; Decision support module: perform corresponding processing according to the quality level of the product.

2. An industrial product data interconnection system according to claim 1, characterized in that: The data acquisition module includes: The image information of the product after molding and after printing is obtained, and the molded product image and the printed product image information are preprocessed in turn and recorded as molding-related data and printing-related data respectively; the preprocessing includes grayscale conversion, noise reduction, contrast enhancement and size normalization.

3. The industrial product data interconnection system according to claim 2, characterized in that: The process of obtaining the molding defect coefficient is as follows: Divide the product into multiple sub-areas based on the set area, and obtain image information corresponding to each sub-area of ​​the product based on the sub-areas divided by the product; Extract crack and damage-related features from the image information in each sub-region and mark the extracted features as the crack and damage areas of each sub-region of the product; perform pixel count on the marked crack and damage areas of each sub-region of the product and calculate the number of pixels in the crack and damage areas of each sub-region of the product; Based on the image resolution, the number of pixels in the crack area and the damaged area in each sub-area of ​​the product is converted into the actual area to obtain the crack area and damaged area in each sub-area of ​​the product; After comprehensive analysis of the crack area and damage area in each sub-region, the defect value of each sub-region is obtained; the defect values ​​of each sub-region are arranged in descending order, and the maximum defect value is extracted and recorded as the maximum defect value; Obtain the contour image of the product, obtain the contour edge based on the edge detection algorithm, and track the contour edge; obtain the curvature radius in the tangent direction between adjacent points on the contour edge, and preset the curvature radius threshold. The points corresponding to the curvature radius greater than the curvature radius threshold are recorded as corner points; Count all corner points, mark the areas where all corner points are located and record them as product corners; After analyzing the corners of the product, the corner integrity is obtained; The forming defect coefficient is obtained by comprehensively processing the maximum defect value and the edge and corner integrity.

4. The industrial product data interconnection system according to claim 3, characterized in that: The corner integrity is obtained by analyzing the corners of the product, specifically including: Compare each corner profile with the standard corner profile in turn to obtain the overlap length between each corner profile and the standard corner profile, divide the overlap length by the total length of the standard corner profile to obtain the overlap degree; calculate the average of each overlap degree to obtain the average overlap degree; The minimum overlap is preset, and the overlap deviation value is obtained by calculating the difference between the average overlap and the minimum overlap; Mark the parts where the standard corner outline and the individual corner outlines do not overlap; And with the standard corner outline as the starting point, draw a straight line perpendicular to the standard corner outline until the straight line touches the corner outline, record the straight line as the deviation line, calculate the length of the deviation line, and take the longest deviation line as the deviation length of the corner; Obtain the deviation length of each corner in turn, sort the deviation lengths of each corner in descending order, and extract the maximum deviation length; The overlap deviation value and the maximum deviation length are combined to obtain the edge and corner integrity.

5. The industrial product data interconnection system according to claim 4, characterized in that: The acquisition of printing error coefficient includes: After obtaining the printed product image information and pre-processing the image, obtain all pixels of the text and pattern on the product pixel map, calculate the contrast between each pixel and its adjacent pixels, and calculate the contrast of all pixels of the text and pattern on the product; divide the contrast of all pixels by the total number of pixels to obtain the average contrast; After extracting the maximum contrast from all contrasts, the difference between the maximum contrast and the average contrast is calculated to obtain the contrast deviation value; Get all the pixels of the text and pattern on the product pixel map value, and preset each pixel Standard value, each pixel point in turn The value corresponds to The color difference value of each pixel is obtained by performing difference calculation on the standard value; the maximum color difference value and the minimum color difference value are extracted, and the color difference extreme value is obtained by subtracting the minimum color difference value from the maximum color difference value; Divide the product into several areas, and record each divided area as a measurement area; obtain the glossiness of each measurement area, perform sum calculation, and divide it by the number of measurement areas to obtain the average glossiness; Calculate the difference between the glossiness of each area and the average glossiness to obtain the corresponding glossiness deviation value. Set the allowable range of glossiness deviation value. Mark the areas corresponding to glossiness deviation values ​​that are not within the allowable range as abnormal areas. Count all abnormal areas and divide the number of abnormal areas by the total number of areas divided into the product to obtain the abnormality ratio. The contrast deviation value, color difference extreme value, and abnormality ratio are calculated using the corresponding formula to obtain the printing error coefficient.

6. The industrial product data interconnection system according to claim 5, characterized in that: The product quality grade is divided according to the quality assessment coefficient; Three groups of threshold value ranges are preset, each group of threshold value ranges corresponds to a quality level, and the quality assessment coefficient is matched with the three groups of threshold value ranges to obtain the quality level corresponding to the quality assessment coefficient; The quality levels include qualified, defective and unqualified.

7. An industrial product data interconnection system according to claim 6, characterized in that: Carry out corresponding treatment according to the quality level of the product, including: When the quality level corresponding to the quality assessment coefficient is qualified: the product enters the next processing step normally; When the quality level corresponding to the quality assessment coefficient is defective: analyze the molding defect coefficient and printing error coefficient of the defective product to determine the source of the defect; When the quality level corresponding to the quality assessment coefficient is unqualified: the unqualified products produced will be scrapped.

8. An industrial product data interconnection method, using an industrial product data interconnection system according to any one of claims 1 to 7, characterized in that: include: Data collection: Acquire molding-related data and printing-related data of products during processing; Data analysis: After analyzing the molding-related data and printing-related data respectively, the molding defect coefficient and printing error coefficient are obtained; The molding defect coefficient and the printing error coefficient are processed comprehensively to obtain the quality assessment coefficient; Quality judgment: Classify the product quality level according to the quality assessment coefficient; Classification processing: Carry out corresponding processing according to the quality level of the product; The product is qualified and enters the next processing step normally; Product defects: analyze the molding defect coefficient and printing error coefficient of defective products to determine the source of the defects; If the product is unqualified, the unqualified products produced will be scrapped.

Images