Screen printing pattern learning and correction method using artificial intelligence, and system and program for performing the same

Abstract

A screen printing pattern learning method using artificial intelligence according to one embodiment of the present invention may include: a step of a target pattern generating unit generating a target pattern; a step of a printing pattern collecting unit acquiring a first printing pattern in which the target pattern is screen-printed on a printing object under a first printing variable group condition; a step of an error value calculating unit comparing the target pattern with the first printing pattern to calculate a first position-specific error value; and a step of a correction value calculating unit calculating a first position-specific correction value for correcting the first position-specific error value; and a step of a correction value learning unit learning a position-specific correction value for the printing variable group condition using artificial intelligence.

Description

[Technical Field]

[0001] The present invention relates to a screen printing pattern learning and correction method using artificial intelligence, and a program and system for performing the same. More particularly, the present invention relates to a screen printing pattern learning and correction method using artificial intelligence, which uses artificial intelligence to reflect and correct errors that occur in a printing pattern when the screen printing pattern is printed, to generate a target pattern, thereby preventing errors from occurring in the printing pattern, and a program and system for performing the same. [Background technology]

[0002] FIG. 1 shows a print pattern distorted by distortion generated in a conventional screen printing process, and FIG. 2 shows an error map of FIG. In the conventional screen printing process, even if the target pattern printed on the plate is accurately created, distortion occurs in the pattern position during printing, resulting in a decrease in the accuracy of the printed pattern's position. As shown in Figure 1, even when a straight line is printed, it is distorted and printed like a curve due to distortion that occurs during the printing process, and this can be displayed on an error map as shown in Figure 2. An error map is a diagram that shows the amount of error that occurs from the intended printing position for each position on the printing object.

[0003] Due to these problems, a method is used in which distortion is reflected in the target pattern in the opposite direction to the distortion that is expected in advance when making a plate. However, the appearance and degree of distortion differ depending on the printing method and printing process conditions, so in practice, the process of making a plate, measuring the distortion, making the plate again, and measuring the distortion again is repeated many times.

[0004] Also, rather than aligning all of the positions of the detailed patterns in the printing area, correction may be performed by aligning only the alignment marks as a whole.

[0005] This method reduces productivity and accuracy, and many studies have been conducted to improve it, but satisfactory results have not yet been achieved. Summary of the Invention [Problem to be solved by the invention]

[0006] An object of one aspect of the present invention is to provide a screen printing pattern learning and correction method using artificial intelligence, which uses artificial intelligence to reflect and correct errors that occur in a printing pattern when the screen printing pattern is printed, to generate a target pattern, thereby preventing errors from occurring in the printing pattern, and a program and system for performing the same. [Means for solving the problem]

[0007] A screen printing pattern learning method using artificial intelligence according to one embodiment of the present invention may include: a step of a target pattern generation unit generating a target pattern; a step of a print pattern collection unit acquiring a first print pattern in which the target pattern is screen-printed on a printing object under a first print variable group condition; a step of an error value calculation unit comparing the target pattern with the first print pattern to calculate a first position-specific error value; and a step of a correction value calculation unit calculating a first position-specific correction value for correcting the first position-specific error value. The error map generation method may include a step of performing an error map generation method from a first print variable group condition to an n-th print variable group condition (where n is a natural number of 2 or more); and a step of a correction value learning unit learning a position-specific correction value for the print variable group condition using artificial intelligence, wherein the print variable group includes at least one of a printing gap H, a printing pressure, a printing speed, a platemaking type, and a squeegee material. The error value calculation unit may calculate error values in the x and y directions at error measurement points of the print pattern corresponding to the error measurement points of the target pattern.

[0008] A method for correcting a screen printing pattern using artificial intelligence according to one embodiment of the present invention may include: a step of performing an error map generation method from a first printing variable group condition to an n-th printing variable group condition (where n is a natural number greater than or equal to 2), the error map generation method including: a step of a target pattern generation unit generating a target pattern; a step of a printing pattern collection unit acquiring a first printing pattern in which the target pattern is screen-printed on a printing object under a first printing variable group condition; a step of an error value calculation unit comparing the target pattern with the first printing pattern to calculate a first position-specific error value; and a step of a correction value calculation unit calculating a first position-specific correction value for correcting the first position-specific error value; a step of a correction value learning unit learning a position-specific correction value for the printing variable group condition using artificial intelligence; and a step of the target pattern generation unit modifying the target pattern to reflect the learned position-specific correction value to form a corrected target pattern, wherein the printing variable group includes at least one of a printing gap H, a printing pressure, a printing speed, a plate-making type, and a squeegee material, and the error value calculation unit may calculate error values in the x and y directions at error measurement points of the printing pattern corresponding to error measurement points of the target pattern.

[0009] A program according to an embodiment of the present invention includes: a step of a target pattern generating unit generating a target pattern; a step of a print pattern collecting unit acquiring a first print pattern in a state where the target pattern is screen-printed on a printing object under a first print variable group condition; a step of an error value calculating unit comparing the target pattern with the first print pattern to calculate a first position-specific error value; and a step of a correction value calculating unit calculating a first position-specific correction value for correcting the first position-specific error value, the step of performing an error map generating method from a first print variable group condition to an n-th print variable group condition (where n is a natural number equal to or greater than 2); and a correction value learning unit learning a correction value for a human The method may be a computer program stored on a medium for executing a step of learning position-specific correction values for printing variable group conditions using artificial intelligence, and the target pattern generation unit may further execute a step of forming a corrected target pattern by modifying the target pattern based on the learned position-specific correction values, wherein the printing variable group includes at least one of a printing gap H, a printing pressure, a printing speed, a plate-making type, and a squeegee material, and the error value calculation unit may calculate error values in the x and y directions at error measurement points of the printing pattern corresponding to the error measurement points of the target pattern.

[0010] A screen printing pattern learning system using artificial intelligence according to one embodiment of the present invention may include a target pattern generation unit that generates a target pattern; a print pattern collection unit that acquires 1st to nth print patterns, which are the state in which the target pattern is screen-printed on a printing object under 1st to nth print variable group conditions (where n is a natural number of 2 or more); an error value calculation unit that compares the target pattern with the 1st to nth print patterns and calculates 1st to nth position-specific error values; a correction value calculation unit that calculates 1st to nth position-specific correction values that correct the 1st to nth position-specific error values; and a correction value learning unit that learns the 1st to nth position-specific correction values for the 1st to nth print variable group conditions using artificial intelligence, wherein the print variable groups may include at least one of printing gap H, printing pressure, printing speed, plate making type, and squeegee material, and the error value calculation unit may calculate error values in the x and y directions at error measurement points of the print pattern that correspond to error measurement points of the target pattern.

[0011] A screen printing pattern correction system using artificial intelligence according to one embodiment of the present invention includes a target pattern generation unit that generates a target pattern; a print pattern collection unit that acquires 1st to nth print patterns, which are the state in which the target pattern is screen-printed on a printing object under 1st to nth print variable group conditions (where n is a natural number greater than or equal to 2); an error value calculation unit that compares the target pattern with the 1st to nth print patterns and calculates 1st to nth position-specific error values; a correction value calculation unit that calculates 1st to nth position-specific correction values that correct the 1st to nth position-specific error values; and a correction value learning unit that learns the 1st to nth position-specific correction values for the 1st to nth print variable group conditions using artificial intelligence. The target pattern generation unit can modify the target pattern to reflect the learned 1st to nth position-specific correction values to form a corrected target pattern. The print variable groups can include at least one of printing gap H, printing pressure, printing speed, plate making type, and squeegee material. The error value calculation unit can calculate error values in the x and y directions at error measurement points of the print pattern that correspond to error measurement points of the target pattern. [Effects of the Invention]

[0012] The method for learning and correcting a screen printing pattern using artificial intelligence and the program and system for performing the method according to an embodiment of the present invention generate a target pattern by using artificial intelligence to reflect and correct errors that occur in the printing pattern when printing the screen printing pattern in advance, thereby shortening the printing process time and preventing errors from occurring in the printing pattern. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a diagram showing a distorted print pattern caused by distortion generated in a conventional screen printing process. [Figure 2] 2 is a diagram showing FIG. 1 as an error map. [Figure 3]1 is a diagram illustrating a schematic diagram of a system for performing a screen printing pattern learning method using artificial intelligence according to an embodiment of the present invention. [Figure 4] 1 is a diagram illustrating steps of a screen printing pattern learning method using artificial intelligence according to an embodiment of the present invention. [Figure 5] 1 is a diagram schematically illustrating the principle of screen printing. [Figure 6] 10 is a diagram showing an error map showing error measurement points of a target pattern and error values at the error measurement points; [Figure 7] 1 is a diagram illustrating steps of a method for correcting a screen printing pattern using artificial intelligence according to an embodiment of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0014] The present invention can be modified in various ways and can have various embodiments, and specific embodiments are illustrated in the drawings and will be described in detail in the detailed description. However, this is not intended to limit the present invention to the specific embodiments, and it should be understood that the present invention includes all modifications, equivalents, and alternatives that fall within the spirit and technical scope of the present invention.

[0015] In describing the present invention, if it is determined that a detailed description of related publicly known technology may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. Furthermore, numbers (e.g., first, second, etc.) used in the description of this specification are merely identification symbols for distinguishing one component from another.

[0016] Furthermore, in this specification, when a component is referred to as being "coupled" or "connected" to another component, it should be understood that the component may be directly coupled or connected to the other component, but may also be coupled or connected via an intermediate component, unless otherwise specified.

[0017] In addition, in this specification, a component represented by "part" may mean that two or more components are combined into one component, or one component may be divided into two or more components based on more specific functions. Furthermore, each of the components described below may additionally perform some or all of the functions performed by other components in addition to its main function, and of course, some of the main functions performed by each component may be exclusively performed by other components.

[0018] Hereinafter, embodiments according to the technical concept of the present invention will be described in detail one by one.

[0019] Figure 3 is a diagram showing a schematic diagram of a system for performing a screen printing pattern learning and correction method using artificial intelligence according to an embodiment of the present invention. Figure 4 is a diagram showing each step of a screen printing pattern learning method using artificial intelligence according to an embodiment of the present invention. Figure 5 is a diagram showing a schematic diagram of the principle of screen printing.

[0020] The screen printing pattern learning system using artificial intelligence according to an embodiment of the present invention may include a target pattern generating unit 110, a print pattern collecting unit 120, an error value calculating unit 130, a correction value calculating unit 140, and a correction value learning unit 150. The screen printing pattern learning method performed by the screen printing pattern learning system using artificial intelligence according to an embodiment of the present invention may perform the following error map generating method.

[0021] First, the target pattern generator 110 generates a target pattern (S110). The target pattern is the shape of the original pattern that can be produced if no errors occur, and is generated and saved in the form of an image or drawing. The target pattern is attached to a fixed screen 12 surrounded by a frame 11 of a plate 10.

[0022] Next, the print pattern collection unit 120 can acquire a first print pattern in which the target pattern is screen-printed on the printing object 31 under the first printing variable group conditions (S120). That is, ink is applied to the screen 12 of the plate 10 on which the target pattern is attached, and the ink is printed on the printing object 31 below the plate 10 by pressing with the squeegee 21, and the image of the printed print pattern can be saved by a method such as photography.

[0023] Here, the printing variable group can include at least one printing variable from among printing gap H, printing pressure, printing speed, plate type, and squeegee material. The printing gap H refers to the distance between the plate 10 and the printing object 31, the printing pressure refers to the pressure with which the squeegee 21 presses the printing object 31, the printing speed refers to the speed at which the squeegee 21 moves, and the plate type refers to the type of screen 12.

[0024] The number of cases that can be created by the printing variables of a printing variable group can be calculated by multiplying the number of cases for the printing gap H, the number of cases for the printing pressure, the number of cases for the printing speed, the number of cases for the plate making type, and the number of cases for the squeegee material. A condition for the number of cases of any one of the printing variable groups can be called a first printing variable group condition, and a condition for the number of cases of another printing variable group can be called a second printing variable group condition, and up to an n-th printing variable group condition can be created (where n is a natural number greater than or equal to 2, and the maximum value is the product of the numbers of cases of the five printing variables).

[0025] For example, if the printing gap H can be set to three types, the printing pressure can be set to 20 types, the printing speed can be set to five types, 10 types of plate making can be used, and four types of squeegee material can be selected, then a maximum of 12,000 combinations of printing variables can be produced.

[0026] Next, the error value calculation unit 130 can compare the target pattern with the first printed pattern to calculate a first position-specific error value (S130). FIG. 6(a) shows error measurement points on the target pattern, and FIG. 6(b) shows an error map showing error values at the error measurement points. The error value calculation unit 130 can calculate error values in the x and y directions at error measurement points on the printed pattern that correspond to the error measurement points on the target pattern. The error map can display the error values as arrow directions and lengths using information on the x and y directions of the error values, thereby visually indicating the direction and magnitude of the error values.

[0027] Next, the correction value calculation unit 140 may calculate a first position-specific correction value at the first error measurement point to correct the first position-specific error value obtained under the first printing variable group condition (S140). The position-specific correction value may be calculated at all error measurement points and may be obtained by assigning opposite signs to the x- and y-directional values of the error value. For example, if the x- and y-directional values of the error value are -4 and 7, respectively, the position-specific correction value may be 4 and -7.

[0028] The error map generating method including steps S110 to S140 can be performed from the first printing variable group condition to the n-th printing variable group condition.

[0029] Next, the correction value learning unit 150 can learn position-specific correction values for all printing variable group conditions using a method such as machine learning or deep learning through artificial intelligence (S150).The correction value learning unit 150 can calculate position-specific correction values between the first error measurement point and the second error measurement point based on the position-specific correction values obtained at all error measurement points.

[0030] 7 shows the steps of a screen printing pattern correction method using artificial intelligence according to an embodiment of the present invention. The screen printing pattern correction method is configured such that, after the screen printing pattern learning method, the target pattern generation unit 110 modifies the target pattern by reflecting the learned position-specific correction value, thereby forming a corrected target pattern.

[0031] The screen-printing pattern correction method performed by the screen-printing pattern correction system using artificial intelligence according to an embodiment of the present invention may perform the following error map generation method.

[0032] First, the target pattern generator 110 can generate a target pattern (S210).

[0033] Next, the print pattern collection unit 120 can acquire a first print pattern in which the target pattern is screen-printed on the printing object 31 under the first print variable group conditions (S220). Here, the print variable group can include at least one of the printing gap H, printing pressure, printing speed, plate making type, and squeegee material.

[0034] Next, the error value calculation unit 130 may compare the target pattern with the first print pattern to calculate a first position-specific error value (S230). The error value calculation unit 130 may calculate error values in the x and y directions at error measurement points of the print pattern corresponding to the error measurement points of the target pattern.

[0035] Next, the correction value calculation unit 140 may calculate a first position-specific correction value for correcting the first position-specific error value at the first error measurement point (S240).

[0036] The error map generation method including steps S210 to S240 may be performed from the first printing variable group condition to the n-th printing variable group condition (where n is a natural number equal to or greater than 2).

[0037] Next, the correction value learning unit 150 can learn position-specific correction values for all printing variable group conditions using a method such as machine learning or deep learning through artificial intelligence (S250).

[0038] Next, the target pattern generator 110 can modify the target pattern by reflecting the learned position-specific correction value, thereby forming a corrected target pattern (S260).

[0039] A computer program stored on a medium for executing a screen printing pattern learning and correction method using artificial intelligence according to an embodiment of the present invention can perform an error map generation method including the following steps.

[0040] First, the target pattern generator 110 can be configured to generate a target pattern.

[0041] Next, the print pattern collection unit 120 may acquire a first print pattern in which the target pattern is screen-printed on the printing object under the conditions of a first print variable group, where the print variable group may include at least one of a printing gap H, a printing pressure, a printing speed, a plate-making type, and a squeegee material.

[0042] Next, the error value calculation unit 130 may compare the target pattern with the first print pattern to calculate a first position-specific error value. The error value calculation unit 130 may calculate error values in the x and y directions at error measurement points of the print pattern corresponding to the error measurement points of the target pattern.

[0043] Next, the correction value calculation unit 140 may calculate a first position-specific correction value for correcting the first position-specific error value.

[0044] The error map generating method including steps S210 to S240 may be performed from the first printing variable group condition to the n-th printing variable group condition (where n is a natural number equal to or greater than 2).

[0045] Next, the correction value learning unit 150 can learn position-specific correction values for the printing variable group conditions using artificial intelligence.

[0046] Next, the target pattern generator 110 can modify the target pattern by reflecting the learned position-specific correction value, thereby forming a corrected target pattern.

[0047] The functional operations and embodiments of the present invention described herein can be embodied in digital electronic circuitry, computer software, firmware, or hardware, or in combinations of one or more of them, including the structures disclosed herein and their structural equivalents.

[0048] The subject embodiments described herein may be embodied as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a program medium of some type for execution by or to control the operation of a data processing apparatus. The program medium of some type may be a radio wave-type signal or a computer-readable medium. The radio wave-type signal is an artificially generated signal, such as a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to an appropriate receiver device for execution by a computer. The computer-readable medium may be a machine-readable storage device, a machine-readable storage substrate, a memory device, a combination of materials that affect a machine-readable radio wave-type signal, or a combination of one or more of these.

[0049] A computer program (also known as a program, software, software application, script or code) may be written in any form of programming language, including compiled or interpreted languages, a priori or procedural languages, and may be deployed in any form, including as a stand-alone program, a module, component, subroutine or other unit suitable for use in a computing environment.

[0050] A computer program does not necessarily correspond to a file in a file system: a program may be stored in a single file provided to the requested program, or in multiple interacting files (e.g., a file storing one or more modules, subprograms, or pieces of code), or as part of a file containing other programs or data (e.g., one or more scripts stored in a markup language document).

[0051] A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communications network.

[0052] The processes and logic flows described herein can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output.

[0053] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read-only memory or a random access memory or both.

[0054] The essential elements of a computer are one or more memory devices for storing instructions and data and a processor for executing instructions. A computer also typically includes or is operatively coupled to receive data from or transmit data to, or perform both of these operations, one or more mass storage devices for storing data, such as magnetic, magneto-optical, or optical disks. However, a computer need not have such devices.

[0055] The description set forth herein sets forth the best mode of the invention and provides examples to explain the invention and to enable any person skilled in the art to make and use the invention. The specification so written is not intended to limit the invention to the specific terms set forth therein.

[0056] Thus, although the present invention has been described in detail with reference to the examples set forth above, those skilled in the art can make modifications, changes and variations thereto without departing from the scope of the present invention. [Explanation of symbols]

[0057] 110: Target pattern generation unit 120: Print pattern collection unit 130: Error value calculation unit 140: Correction value calculation unit 150: Correction value learning unit

Claims

1. In a screen printing pattern learning method using artificial intelligence, a step in which a target pattern generation unit generates a target pattern; A step in which the print pattern collection unit acquires a first print pattern in a state in which the target pattern is screen-printed on the print object under the first print variable group condition; an error value calculation unit comparing the target pattern with the first print pattern to calculate a first position-specific error value; performing an error map generating method, including a step of calculating a first position-specific correction value by a correction value calculation unit to correct the first position-specific error value, from a first printing variable group condition to an n-th printing variable group condition (where n is a natural number equal to or greater than 2); and a correction value learning unit learning a position-specific correction value for a printing variable group condition by artificial intelligence; A method for learning screen printing patterns using artificial intelligence.

2. The printing variable group is 2. The screen printing pattern learning method using artificial intelligence according to claim 1, wherein the learning includes at least one of a printing gap (H), a printing pressure, a printing speed, a plate making type, and a squeegee material.

3. The error value calculation unit 2. The screen printing pattern learning method using artificial intelligence according to claim 1, further comprising calculating error values in the x and y directions at error measurement points of the printed pattern corresponding to the error measurement points of the target pattern.

4. After the screen printing pattern learning method of claim 1, The method for correcting a screen printing pattern using artificial intelligence includes the step of forming a corrected target pattern by modifying the target pattern by the target pattern generator, using the learned position-specific correction value.

5. The printing variable group is 5. The screen printing pattern correction method using artificial intelligence according to claim 4, wherein the correction includes at least one of a printing gap (H), a printing pressure, a printing speed, a type of plate making, and a squeegee material.

6. The error value calculation unit 5. The method for correcting a screen printing pattern using artificial intelligence according to claim 4, further comprising calculating error values in the x and y directions at error measurement points of the printed pattern corresponding to the error measurement points of the target pattern.

7. A computer program stored on a non-transitory recording medium containing an instruction, the instruction comprising: a step in which a target pattern generation unit generates a target pattern; A step in which the print pattern collection unit acquires a first print pattern in a state in which the target pattern is screen-printed on the print object under the first print variable group condition; an error value calculation unit comparing the target pattern with the first print pattern to calculate a first position-specific error value; performing an error map generating method, including a step of calculating a first position-specific correction value by a correction value calculation unit to correct the first position-specific error value, from a first printing variable group condition to an n-th printing variable group condition (where n is a natural number equal to or greater than 2); and A computer program stored in a non-transitory recording medium configured to cause a correction value learning unit to execute a step of learning position-specific correction values for printing variable group conditions using artificial intelligence.

8. 8. The computer program stored on a non-transitory recording medium of claim 7, further causing the target pattern generator to perform a step of correcting the target pattern by reflecting the learned position-specific correction value to form a corrected target pattern.

9. The printing variable group is 8. The computer program stored on the non-transitory recording medium according to claim 7, further comprising at least one of a printing gap (H), a printing pressure, a printing speed, a plate making type, and a squeegee material.

10. The error value calculation unit 8. The computer program stored on a non-transitory recording medium of claim 7, wherein the computer program calculates error values in the x and y directions at error measurement points of the printed pattern that correspond to error measurement points of the target pattern.

11. In a screen printing pattern learning system using artificial intelligence, a target pattern generation unit that generates a target pattern; a print pattern collection unit (where n is a natural number equal to or greater than 2) that acquires first to n print patterns in which the target pattern is screen-printed on a print target under first to n print variable group conditions, respectively; an error value calculation unit that compares the target pattern with the first to nth print patterns and calculates first to nth position-specific error values; a correction value calculation unit that calculates correction values for the first to n positions to correct the error values for the first to n positions, respectively; and A screen printing pattern learning system using artificial intelligence, including a correction value learning unit that learns correction values for first to n positions for first to n printing variable group conditions using artificial intelligence.

12. The printing variable group is 12. The screen printing pattern learning system using artificial intelligence according to claim 11, wherein the learning includes at least one of a printing gap (H), a printing pressure, a printing speed, a plate making type, and a squeegee material.

13. The error value calculation unit 12. The screen printing pattern learning system using artificial intelligence according to claim 11, wherein error values in the x and y directions are calculated at error measurement points of the printed pattern that correspond to error measurement points of the target pattern.

14. A screen printing pattern learning system according to claim 11, The target pattern generator modifies the target pattern by reflecting the learned correction values for each of the first to n positions, thereby forming a corrected target pattern.

15. The printing variable group is 15. The screen printing pattern correction system using artificial intelligence according to claim 14, wherein the correction includes at least one of a printing gap (H), a printing pressure, a printing speed, a plate making type, and a squeegee material.

16. The error value calculation unit 15. The screen printing pattern correction system using artificial intelligence according to claim 14, wherein error values in the x and y directions are calculated at error measurement points of the printed pattern that correspond to error measurement points of the target pattern.

Images