Full-automatic transparent bottle curved surface printing detection control system

Abstract

The invention discloses a full-automatic transparent bottle curved surface printing detection control system, and relates to the technical field of automatic control, and the main scheme is as follows: obtaining a transparent bottle curved surface printing image through an image acquisition module; the intelligent image processing module is used for accurately analyzing the acquired image, so that the detection speed is increased; image information of the image acquisition module and the intelligent image processing module is transmitted to the central control module for comprehensive processing, and a parameter control instruction C and a fault control instruction H are sent out according to a processing result, so that the stability of the system is ensured; the feedback adjusting module adjusts the detection equipment according to the parameter control instruction C and the fault control instruction H, so that the detection efficiency is improved; the evaluation module judges whether the printing effect is qualified or not according to the comprehensive evaluation value M and the comprehensive evaluation threshold value Ma and reflects the actual condition of the printing effect; the early warning module gives out early warning when the printing qualified rate U is lower than the printing qualified rate threshold value Uc.

Description

Technical Field

[0001] The invention relates to the technical field of automatic control, in particular to a full-automatic transparent bottle curved surface printing detection and control system. Background Art

[0002] As modern consumers’ demand for personalized products grows, the printing of transparent bottles needs to meet different design, pattern and color requirements, which requires the printing inspection and control system to be able to flexibly adapt to various personalized printing needs to ensure that each printed product meets specific design standards. Traditional transparent bottle curved surface printing inspection mainly relies on manual visual inspection, which is labor-intensive, inefficient, subjective, and unreliable. It is easy to cause visual fatigue and easily cause missed inspections, and cannot meet the requirements of modern production efficiency and accuracy. At the same time, industry norms and standards have increasingly stringent requirements on product packaging quality, and companies need to adopt advanced inspection technologies to ensure that products meet quality standards. Summary of the invention

[0003] 1. Technical issues to be solved

[0004] In view of the deficiencies in the prior art, the present invention provides a fully automatic transparent bottle curved surface printing detection and control system, which acquires the transparent bottle curved surface printing image through an image acquisition module, thereby reducing the influence of ambient light and avoiding the degradation of image quality due to uneven light; the acquired image is analyzed through an intelligent image processing module, and the image features can be converted into specific quantitative indicators, which is conducive to improving the detection speed; the central control module realizes centralized management of the entire system data by receiving image information from the image acquisition module and the intelligent image processing module, which is conducive to improving the stability of production.

[0005] (II) Technical solution

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a fully automatic transparent bottle curved surface printing detection and control system, comprising:

[0007] An image acquisition module is used to obtain a printed image of a transparent bottle curved surface;

[0008] Intelligent image processing module, used to accurately analyze the collected images to obtain the color deviation evaluation value R, defect evaluation value D, and pattern clarity evaluation value A;

[0009] The central control module is used to receive and comprehensively process the image information of the image acquisition module and the intelligent image processing module; preset the defect threshold T and the color deviation range S; generate the parameter control instruction C according to the color deviation evaluation value R, the defect evaluation value D, the preset defect threshold T and the color deviation range S;

[0010] Monitor the system's operating status in real time, obtain operating status data, and obtain the fault assessment index K based on the operating status data; preset the fault threshold K h , according to the fault assessment index K and fault threshold K h Generate a fault control instruction H; and determine whether the system has a fault according to the fault control instruction H;

[0011] A feedback adjustment module, used for receiving a parameter control instruction C and a fault control instruction H, and adjusting the detection device according to the parameter control instruction C and the fault control instruction H;

[0012] The evaluation module is used to receive the data from the intelligent image processing module, and calculate the comprehensive evaluation value M according to the pattern clarity evaluation value A and the color deviation evaluation value R, and preset the comprehensive evaluation threshold M a , according to the comprehensive evaluation value M and the comprehensive evaluation threshold M a Determine whether the printing effect is qualified;

[0013] The early warning module is used to calculate the printing pass rate U within a unit time t and preset the printing pass rate threshold U c , according to the printing qualification rate U and the printing qualification rate threshold U c Determine whether to issue a warning.

[0014] In the preferred embodiment of the above-mentioned fully automatic transparent bottle curved surface printing detection and control system: the image acquisition module is equipped with multiple cameras with adjustable angles, which can shoot the transparent bottle from multiple angles and obtain multi-angle printing images; at the same time, the camera is installed on a rotatable robotic arm, and the angle and distance of the camera are automatically adjusted according to the shape, size and position of the printing area of ​​the transparent bottle; the camera is equipped with an adaptive optical lens to detect the light and intensity of the scene in real time, and automatically adjust the focal length, aperture and sensitivity according to the light conditions on the scene; and a ring-shaped LED fill light is set around the camera.

[0015] In the preferred embodiment of the fully automatic transparent bottle curved surface printing detection and control system, the formula for calculating the color deviation evaluation value R is:

[0016]

[0017] Where R is the color deviation evaluation value, indicating the degree of color deviation. The larger R is, the greater the color deviation is. p is the pixel position in the image, and p is a positive integer. R p is the red component of pixel p; G p is the green component of pixel p; B p is the blue component of pixel p; R p , G p , B p The value range is 0 to 255; is the standard red component; is the standard green component; is the standard blue component; The value range is 0 to 255.

[0018] In the preferred embodiment of the fully automatic transparent bottle curved surface printing detection and control system, the formula for calculating the defect evaluation value D is:

[0019]

[0020] Where D is the final defect evaluation value, indicating the severity of the defect. The larger D is, the more serious the defect is. N is the number of features extracted. The value range of N is 0 to 255 and N is a positive integer. F i is the value of the i-th feature, i∈N; is the average value of all eigenvalues; W is the weight coefficient, and the value range of W is 0 to 1.

[0021] In the preferred embodiment of the fully automatic transparent bottle curved surface printing detection and control system, the formula for calculating the pattern clarity evaluation value A is:

[0022]

[0023] Where A is the pattern clarity evaluation value. The larger the pattern clarity evaluation value A is, the clearer the pattern is. m is the number of rows in the image. n is the number of columns in the image. Both m and n are positive integers. (x，y) is the pixel value at the coordinate (x, y), I (x，y) The value range of I is 0 to 255; (x+1，y) is the pixel value at the coordinate (x+1, y), I (x+1，y) The value range of I is 0 to 255; (x，y+1) is the pixel value at the coordinate (x, y+1), I (x，y+1) The value range is 0 to 255; x and y are both positive integers.

[0024] In the preferred solution of the above-mentioned fully automatic transparent bottle curved surface printing detection and control system: the formula for generating the control instruction C is:

[0025] C=f(D、T、R、S)

[0026]

[0027] Among them, C is a parameter control instruction, and the parameter control instruction C includes instructions C1 and C2; instruction C1 is to adjust the motor speed and printing pressure; instruction C2 is to continue execution; T is a preset defect threshold, ranging from 0 to 1; S is an acceptable color deviation range, ranging from 1 to 10 color difference units.

[0028] In the preferred embodiment of the fully automatic transparent bottle curved surface printing detection and control system, the operation data at least includes the performance parameter P l and state parameter Q j ; According to the performance parameters P of the testing equipment l and state parameter Q j The formula for calculating the fault assessment index K is:

[0029]

[0030] Wherein, K is the fault assessment index; v is the number of performance parameters, the value range of v is 5 to 50 and v is a positive integer; u is the number of state parameters, the value range of u is 3 to 50 and u is a positive integer; P l is the actual value of the lth performance parameter, l∈v; P (l，ref) is the reference value of the first performance parameter; Q j is the actual value of the jth state parameter, j∈u; Q (j,ref) is the reference value of the jth state parameter; ω l is the performance parameter P l The weight coefficient of j is the state parameter Q j The weight coefficient of l , δ j The value range of is 0~1, and ω l +δ j =1;

[0031] According to the fault assessment index K and fault threshold K h The formula for generating the fault control instruction H is:

[0032] H=f(K,K h )

[0033] The criteria for judging whether the system is faulty are:

[0034]

[0035] Among them, H is the fault control instruction; the fault control instruction H includes instruction H1 and instruction H2, instruction H1 means a fault occurs; instruction H2 means no fault occurs; the fault threshold K h The value range is 0 to 1000.

[0036] In the preferred solution of the above-mentioned fully automatic transparent bottle curved surface printing detection and control system: the method for adjusting according to the parameter control instruction C is:

[0037] When receiving instruction C1, the motor speed and printing pressure need to be adjusted;

[0038] The formula for calculating the adjusted motor speed e is:

[0039] e=g×V

[0040]

[0041] Among them, e is the speed of the motor after adjustment, and its value range is 0~e max ; V is the speed setting value issued by the central control module, and its value range is 0~V max ;e max V is the maximum speed of the motor, ranging from 100 rpm to 2000 rpm; max is the maximum speed setting value, ranging from 100 rpm to 2000 rpm; g is the proportional coefficient, which is calculated from the maximum speed e max and maximum speed setting value V max Decide;

[0042] Calculate the adjusted printing pressure E new The formula is:

[0043] E new =E old +ΔE

[0044] Among them, E new is the adjusted printing pressure; E old is the printing pressure before adjustment; ΔE is the pressure adjustment amount, ranging from -10 to 10;

[0045] When receiving instruction C2, there is no need to adjust the motor speed and printing pressure;

[0046] The method for adjusting according to the fault control instruction H is:

[0047] When command H1 is received, the system is in a fault state and the feedback regulation module should make the following adjustments:

[0048] Immediately stop the current related operations; use sound and light to alarm and notify relevant personnel; adjust system configuration and switch to backup equipment; record fault information to provide complete data for subsequent fault analysis and processing;

[0049] When instruction H2 is received, the system operates normally and no adjustment is required.

[0050] In the preferred solution of the above-mentioned fully automatic transparent bottle curved surface printing detection and control system: the method for judging whether the printing effect is qualified is:

[0051] M=α×A-β×R

[0052] Wherein, M is the comprehensive evaluation value of printing effect, the larger M is, the better printing effect is; α is the weight coefficient of the pattern clarity evaluation value A, ranging from 0.2 to 0.7; β is the weight coefficient of the color deviation evaluation value R, ranging from 0.3 to 0.6; and α+β=1;

[0053] According to the comprehensive evaluation value M and the comprehensive evaluation threshold M a The specific standards for judging whether the printing effect is qualified are:

[0054]

[0055] In the preferred solution of the above-mentioned fully automatic transparent bottle curved surface printing detection and control system: the method for determining whether to issue an early warning is:

[0056] According to the number of qualified printings Z per unit time t m and the total number of prints per unit time t Z n The formula for calculating the printing qualification rate U is:

[0057]

[0058] Among them, U is the printing pass rate within unit time t, and its value range is 0 to 1. The larger the value, the higher the pass rate.

[0059] According to the printing qualification rate U and the printing qualification rate threshold U c The specific criteria for determining whether to issue an early warning are:

[0060]

[0061] (III) Beneficial effects

[0062] The present invention provides a fully automatic transparent bottle curved surface printing detection and control system, which has the following beneficial effects:

[0063] (1) Through the image acquisition module, various types of transparent bottle curved surface printing images can be obtained to meet diverse production needs and provide reliable quality inspection information for different printing designs;

[0064] (2) The intelligent image processing module converts image features into specific quantitative indicators, making quality monitoring in the production process more scientific and accurate, improving the detection speed, meeting the needs of high-speed production lines, saving time and labor costs, and improving production efficiency;

[0065] (3) Through comprehensive processing of image information, the central control module can integrate information from multiple modules, thereby improving the accuracy of evaluating the printing quality of transparent bottles; by presetting the defect threshold T and color deviation range S, the central control module provides a clear quality standard for the printing process, improving the consistency and stability of production; by analyzing the operating data, it can be determined whether the system has a fault, thereby improving the accuracy and timeliness of fault detection as well as the intelligence level and operating efficiency of the system;

[0066] (4) The feedback adjustment module adjusts the detection equipment according to the parameter control instruction C and the fault control instruction H, which is conducive to adapting to different production needs and material characteristics and improving printing quality; at the same time, timely detection and handling of faults is conducive to reducing the scrap rate, improving production efficiency and reducing production costs;

[0067] (5) The evaluation module can accurately reflect the actual situation of printing effects by evaluating the printing effects, provide quantifiable evaluation standards for printing quality, and facilitate quality control and improvement of the production process.

[0068] (6) The early warning module is activated when the printing pass rate U is lower than the printing pass rate threshold U c Early warnings are issued in real time, allowing operators to adjust production parameters in a timely manner to prevent the production of more defective products, which is conducive to improving product qualification rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 The present invention is a schematic diagram of the system composition of a fully automatic transparent bottle curved surface printing detection and control system. DETAILED DESCRIPTION

[0070] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] See also Figure 1 The present invention provides a fully automatic transparent bottle curved surface printing detection and control system, comprising:

[0072] An image acquisition module is used to obtain a printed image of a transparent bottle curved surface;

[0073] Specifically, the image acquisition module is equipped with multiple cameras with adjustable angles, which can shoot transparent bottles from multiple angles and obtain multi-angle printed images; each camera uses a CMOS sensor with an imaging capability of 55 million pixels;

[0074] The camera is installed on a rotatable mechanical arm, which is driven by a motor and can automatically adjust the angle and distance of the camera according to the shape, size and position of the printing area of ​​the transparent bottle. Specifically, when the diameter of the transparent bottle is less than 5 cm, the camera automatically approaches the bottle body and the distance is kept between 10 cm and 15 cm; when the diameter of the transparent bottle is greater than or equal to 5 cm, the system starts multiple cameras to work together, automatically calculates and adjusts the angle between the cameras according to the diameter and shape of the transparent bottle, so that the camera can cover the entire curved surface of the bottle body;

[0075] The camera is equipped with an adaptive optical lens to detect the light and intensity of the scene in real time, and automatically adjust the focal length, aperture and sensitivity according to the light conditions on site. Specifically, when the light intensity is lower than 500 lux, the lens increases the aperture and improves the sensitivity; when the light intensity is between 500 lux and 2000 lux, the lens does not need to be adjusted; when the light intensity is higher than 2000 lux, the lens decreases the aperture and reduces the sensitivity to avoid overexposure of the image;

[0076] At the same time, a ring-shaped LED fill light is set around the camera; when a shadow is detected on the bottle, the fill light automatically increases its brightness; when part of the image is too bright, the fill light automatically reduces its brightness to reduce the impact of reflections.

[0077] In the above solution, by equipping multiple cameras with adjustable angles, labor costs and detection time can be reduced, which is conducive to improving detection quality and accuracy.

[0078] Intelligent image processing module, used to accurately analyze the collected images to obtain the color deviation evaluation value R, defect evaluation value D, and pattern clarity evaluation value A;

[0079] Specifically, the formula for calculating the color deviation evaluation value R is:

[0080]

[0081] It should be noted that this formula calculates the R of each pixel p Value, G p Value, B p Values ​​and Standards value, value, The distance between the values ​​is used to obtain the color deviation evaluation value R. The larger the distance, the greater the color deviation. p , G p , B p The value range of is 0 to 255, which is obtained by the image acquisition device. The larger the value, the higher the color intensity. The value range is 0 to 255, which is set according to the standard color of the product.

[0082] Specifically, the formula for calculating the defect assessment value D is:

[0083]

[0084] It should be noted that this formula is based on the idea of ​​variance. First, each eigenvalue F is calculated. i With the feature mean The average value of the square of the deviation is then calculated by square root to get the standard deviation, which is then multiplied by the weight coefficient W to get the final defect assessment value D; the standard deviation can reflect the degree of dispersion of the data. The greater the dispersion, the more serious the defect; where F i is the value of the i-th feature, obtained by extracting features from the image; W is the weight coefficient, ranging from 0 to 1, set according to the defect type.

[0085] Specifically, the formula for calculating the pattern clarity evaluation value A is:

[0086]

[0087] It should be noted that the formula calculates the square root of the sum of the squares of the differences between adjacent pixels in the horizontal and vertical directions, and averages them to obtain the pattern clarity evaluation value A; wherein the value range of the number of image rows m and the number of image columns n is 500 to 5000, which is determined by the size of the image.

[0088] In the above scheme, the intelligent image processing module can convert image features into specific quantitative indicators, which is conducive to providing comparable evaluation standards for printing quality and achieving strict control of printing quality.

[0089] The central control module is used to receive and comprehensively process the image information of the image acquisition module and the intelligent image processing module; preset the defect threshold T and the color deviation range s; generate the parameter control instruction C according to the color deviation evaluation value R, the defect evaluation value D, the preset defect threshold T and the color deviation range S;

[0090] Monitor the system's operating status in real time, obtain operating status data, and obtain the fault assessment index K based on the operating status data; preset the fault threshold K h , according to the fault assessment index K and fault threshold K h Generate a fault control instruction H; and determine whether the system has a fault according to the fault control instruction H;

[0091] Specifically, the formula for generating the control instruction C is:

[0092] C=f(D、T、R、S)

[0093]

[0094] It should be noted that when at least one of the two situations occurs, that is, the defect assessment value D exceeds the preset defect threshold T or the color deviation assessment value R is not within the color deviation range S, a control instruction C1 is generated; otherwise, that is, when the defect assessment value D does not exceed the preset defect threshold T and the color deviation assessment value R is within the color deviation range S, an instruction C2 is generated; wherein T is the preset defect threshold, ranging from 0 to 1, set according to product quality requirements; S is the acceptable color deviation range, ranging from 1 to 10 color difference units, determined according to the color standards and quality requirements of the product.

[0095] Specifically, the operating data includes at least the performance parameter P l and state parameter Q j ; According to the performance parameters P of the testing equipment l and state parameter Q j The formula for calculating the fault assessment index K is:

[0096]

[0097] It should be noted that this formula calculates the actual value of the performance parameter P l and performance parameter reference value P (l，ref) The deviation and actual value of the state parameter Q j and the state parameter reference value Q (j,ref) The deviation is calculated by weighted square sum to calculate the fault assessment index K; wherein the number of performance parameters v and the number of state parameters u are determined according to the performance parameters and state parameters that need to be monitored in the system; the performance parameter reference value P (l，ref) and the state parameter reference value Q (j,ref) Determined according to the rated performance of the equipment; weight coefficient ω l The value range is 0 to 1, which is set according to the importance of the performance parameter to the normal operation of the system; the weight coefficient δ j The value range of is 0 to 1, which is set according to the importance of the state parameter to the normal operation of the system;

[0098] The criteria for judging whether the system is faulty are:

[0099]

[0100] Among them, the fault threshold K h The value range is 0 to 1000, which is determined according to the quality requirements of different products.

[0101] In the above scheme, the central control module can integrate the information of multiple modules, avoiding the problems of information dispersion and processing confusion, and improving the integrity and coordination of the system; generating control instructions based on the comprehensively processed image information avoids the limitations and errors of single unit judgment, which is conducive to improving printing quality and stability.

[0102] A feedback adjustment module, used for receiving a parameter control instruction C and a fault control instruction H, and adjusting the detection device according to the parameter control instruction C and the fault control instruction H;

[0103] Specifically, the method for adjusting according to the parameter control instruction C is:

[0104] When receiving instruction C1, the motor speed and printing pressure need to be adjusted;

[0105] The formula for calculating the adjusted motor speed e is:

[0106] e=g×V

[0107]

[0108] Among them, V is the speed setting value issued by the central control module, and its value range is 0~V max , calculated by the central control module based on the detection results and control strategy;

[0109] Calculate the adjusted printing pressure E new The formula is:

[0110] E new =E old +ΔE

[0111] Among them, ΔE is the pressure adjustment amount, with a value range of -10 to 10, which is calculated by the central control module based on the detection results and control strategy;

[0112] When instruction C2 is received, there is no need to adjust the motor speed and printing pressure.

[0113] The method for adjusting according to the fault control instruction H is:

[0114] When command H1 is received, the system is in a fault state and the feedback regulation module should make the following adjustments:

[0115] Immediately stop the current related operations; use sound and light to alarm and notify relevant personnel; adjust the system configuration according to the type and severity of the fault and switch to the backup equipment; record the time, manifestation and measures taken of the fault to provide complete data for subsequent fault analysis and processing;

[0116] When instruction H2 is received, the system operates normally and no adjustment is required.

[0117] In the above scheme, the feedback regulation module adjusts the detection equipment according to the parameter control instruction C, which can improve the printing quality and adapt to different production requirements and material characteristics; at the same time, by receiving the fault control instruction H and taking corresponding measures, it can avoid further expansion of the fault and reduce the impact on production, which is conducive to helping maintenance personnel locate the fault point, improve the efficiency of troubleshooting, and improve the stability and reliability of the system.

[0118] The evaluation module is used to receive the data from the intelligent image processing module, and calculate the comprehensive evaluation value M according to the pattern clarity evaluation value A and the color deviation evaluation value R, and preset the comprehensive evaluation threshold M a , according to the comprehensive evaluation value M and the comprehensive evaluation threshold M a Determine whether the printing effect is qualified;

[0119] Specifically, the formula for evaluating the printing effect based on the pattern clarity evaluation value A and the color deviation evaluation value R is:

[0120] M=α×A-β×R

[0121] It should be noted that the formula calculates the weighted result of the pattern clarity evaluation value A and the color deviation evaluation value R to obtain the printing result evaluation value M. The larger the M, the better the printing effect. Among them, α is the weight coefficient of the pattern clarity evaluation value A, ranging from 0.2 to 0.7, determined according to the product quality requirements; β is the weight coefficient of the color deviation evaluation value R, ranging from 0.3 to 0.6, determined according to the color standard of the product.

[0122] Specifically, according to the comprehensive evaluation value M and the comprehensive evaluation threshold M a The specific standards for judging whether the printing effect is qualified are:

[0123]

[0124] Among them, the comprehensive evaluation threshold M a Set according to product quality requirements.

[0125] In the above scheme, by evaluating the printing effect, it is possible to provide a standard for production personnel to evaluate the printing quality, which is conducive to screening and processing products that do not meet the standards; at the same time, through the size of the evaluation value, the quality of the printing effect can be understood, providing a basis for control and optimization in the printing production process.

[0126] The early warning module is used to calculate the printing pass rate U within a unit time t and preset the printing pass rate threshold U c , according to the printing qualification rate U and the printing qualification rate threshold Uc Determine whether to issue an early warning;

[0127] Specifically, the method for determining whether to issue an early warning is:

[0128] According to the number of qualified printings Z per unit time t m and the total number of prints per unit time t Z n The formula for calculating the printing qualification rate U is:

[0129]

[0130] Among them, the unit time t is set according to the production cycle;

[0131] According to the printing qualification rate U and the printing qualification rate threshold U c The specific criteria for determining whether to issue an early warning are:

[0132]

[0133] Among them, the printing pass rate threshold U c Set according to product quality requirements.

[0134] In the above scheme, the early warning module is used to detect when the printing qualification rate U is lower than the printing qualification rate threshold U. c Timely warnings can help companies formulate more reasonable production plans, maintenance strategies and quality control measures to improve production efficiency.

[0135] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware or in combination with computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0136] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the 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.

Claims

1. A fully automatic transparent bottle curved surface printing detection and control system, characterized by: include: An image acquisition module is used to obtain a printed image of a transparent bottle curved surface; Intelligent image processing module, used to accurately analyze the collected images to obtain the color deviation evaluation value R, defect evaluation value D, and pattern clarity evaluation value A; A central control module, used for receiving and comprehensively processing image information from the image acquisition module and the intelligent image processing module; Preset a defect threshold T and a color deviation range S; generate a parameter control instruction C according to the color deviation evaluation value R, the defect evaluation value D, the defect threshold T and the color deviation range S; Monitor the system's operating status in real time, obtain operating status data, and obtain the fault assessment index K based on the operating status data; preset the fault threshold K h , according to the fault assessment index K and fault threshold K h Generate a fault control instruction H; and determine whether the system has a fault according to the fault control instruction H; A feedback adjustment module, used for receiving a parameter control instruction C and a fault control instruction H, and adjusting the detection device according to the parameter control instruction C and the fault control instruction H; The evaluation module is used to receive the data from the intelligent image processing module, and calculate the comprehensive evaluation value M according to the pattern clarity evaluation value A and the color deviation evaluation value R, and preset the comprehensive evaluation threshold M a , according to the comprehensive evaluation value M and the comprehensive evaluation threshold M a Determine whether the printing effect is qualified; The early warning module is used to calculate the printing pass rate U within a unit time t and preset the printing pass rate threshold U c , according to the printing qualification rate U and the printing qualification rate threshold U c Determine whether to issue a warning.

2. The fully automatic transparent bottle curved surface printing detection and control system according to claim 1, characterized in that: The image acquisition module is equipped with multiple cameras with adjustable angles, which can shoot transparent bottles from multiple angles and obtain printed images from multiple angles. The camera is installed on a rotatable mechanical arm, and the angle and distance of the camera are automatically adjusted according to the shape, size and position of the printing area of ​​the transparent bottle. The camera is equipped with an adaptive optical lens to detect the light and intensity of the scene in real time, and automatically adjust the focal length, aperture and sensitivity according to the light conditions on the scene. And set up a ring LED fill light around the camera.

3. The fully automatic transparent bottle curved surface printing detection and control system according to claim 2, characterized in that: The formula for calculating the color deviation evaluation value R is: Where R is the color deviation evaluation value, indicating the degree of color deviation. The larger R is, the greater the color deviation is. p is the pixel position in the image, and p is a positive integer. R p is the red component of pixel p; G p is the green component of pixel p; B p is the blue component of pixel p; R p , G p , B p The value range is 0 to 255; is the standard red component; is the standard green component; is the standard blue component; The value range is 0 to 255.

4. The fully automatic transparent bottle curved surface printing detection and control system according to claim 3 is characterized by: The formula for calculating the defect assessment value D is: Where D is the final defect evaluation value, indicating the severity of the defect. The larger D is, the more serious the defect is. N is the number of features extracted. The value range of N is 0 to 255 and N is a positive integer. F i is the value of the i-th feature, i∈N; is the average value of all eigenvalues; W is the weight coefficient, and the value range of W is 0 to 1.

5. The fully automatic transparent bottle curved surface printing detection and control system according to claim 4, characterized in that: The formula for calculating the pattern clarity evaluation value A is: Where A is the pattern clarity evaluation value. The larger the pattern clarity evaluation value A is, the clearer the pattern is. m is the number of rows in the image. n is the number of columns in the image. Both m and n are positive integers. (x，y) is the pixel value at the coordinate (x, y), I (x，y) The value range of I is 0 to 255; (x+1，y) is the pixel value at the coordinate (x+1, y), I (x+1，y) The value range of I is 0 to 255; (x，y+1) is the pixel value at the coordinate (x, y+1), I (x，y+1) The value range is 0 to 255; x and y are both positive integers.

6. The fully automatic transparent bottle curved surface printing detection and control system according to claim 5, characterized in that: The formula for generating the control instruction C is: C=f(D、T、R、S) Among them, C is a parameter control instruction, and the parameter control instruction C includes instructions C1 and C2; instruction C1 is to adjust the motor speed and printing pressure; instruction C2 is to continue execution; T is a preset defect threshold, ranging from 0 to 1; S is an acceptable color deviation range, ranging from 1 to 10 color difference units.

7. The fully automatic transparent bottle curved surface printing detection and control system according to claim 6, characterized in that: The operating data at least includes performance parameters P l and state parameter Q j ; According to the performance parameters P of the testing equipment l and state parameter Q j The formula for calculating the fault assessment index K is: Wherein, K is the fault assessment index; v is the number of performance parameters, the value range of v is 5 to 50 and v is a positive integer; u is the number of state parameters, the value range of u is 3 to 50 and u is a positive integer; P l is the actual value of the lth performance parameter, l∈v; P (l，ref) is the reference value of the first performance parameter; Q j is the actual value of the jth state parameter, j∈u; Q (j,ref) is the reference value of the jth state parameter; ω l is the performance parameter P l The weight coefficient of j is the state parameter Q j The weight coefficient of l , δ j The value range of is 0~1, and ω l +δ j =1; According to the fault assessment index K and fault threshold K h The formula for generating the fault control instruction H is: H=f(K,K h ) The criteria for judging whether the system is faulty are: Among them, H is the fault control instruction; the fault control instruction H includes instruction H1 and instruction H2, instruction H1 means a fault occurs; instruction H2 means no fault occurs; the fault threshold K h The value range is 0 to 1000.

8. The first fully automatic transparent bottle curved surface printing detection and control system according to claim 7 is characterized by: The method for adjustment according to parameter control instruction C is: When receiving instruction C1, the motor speed and printing pressure need to be adjusted; The formula for calculating the adjusted motor speed e is: e=g×V Among them, e is the speed of the motor after adjustment, and its value range is 0~e max ; V is the speed setting value issued by the central control module, and its value range is 0~V max ;e max V is the maximum speed of the motor, ranging from 100 rpm to 2000 rpm; max is the maximum speed setting value, ranging from 100 rpm to 2000 rpm; g is the proportional coefficient, which is calculated from the maximum speed e max and maximum speed setting value V max Decide; Calculate the adjusted printing pressure E new The formula is: E new =E old +ΔE Among them, E new is the adjusted printing pressure; E old is the printing pressure before adjustment; ΔE is the pressure adjustment amount, ranging from -10 to 10; When receiving instruction C2, there is no need to adjust the motor speed and printing pressure; The method for adjusting according to the fault control instruction H is: When command H1 is received, the system is in a fault state and the feedback regulation module should make the following adjustments: Immediately stop the current related operations; use sound and light to alarm and notify relevant personnel; adjust system configuration and switch to backup equipment; record fault information to provide complete data for subsequent fault analysis and processing; When instruction H2 is received, the system operates normally and no adjustment is required.

9. The first fully automatic transparent bottle curved surface printing detection and control system according to claim 8, characterized in that: The method to judge whether the printing effect is qualified is: The formula for evaluating the printing effect based on the pattern clarity evaluation value A and the color deviation evaluation value R is: M=α×A-β×R Wherein, M is the comprehensive evaluation value of printing effect, the larger M is, the better the printing effect is; α is the weight coefficient of the pattern clarity evaluation value A, ranging from 0.2 to 0.7; β is the weight coefficient of the color deviation evaluation value R, ranging from 0.3 to 0.6; and α+β=1; According to the comprehensive evaluation value M and the comprehensive evaluation threshold M a The specific standards for judging whether the printing effect is qualified are: 。 10. The fully automatic transparent bottle curved surface printing detection and control system according to claim 9, characterized in that: The method for determining whether to issue an early warning is: According to the number of qualified printings Z per unit time t m and the total number of prints per unit time t Z n The formula for calculating the printing qualification rate U is: Among them, U is the printing pass rate within unit time t, and its value range is 0 to 1. The larger the value, the higher the pass rate. According to the printing qualification rate U and the printing qualification rate threshold U c The specific criteria for determining whether to issue an early warning are:

Images