A system for regulating flatness of a mask web

Abstract

The application provides a system for adjusting flatness of a mask roll. The system comprises a horizontal straight transmission area of the mask roll formed by a plurality of conveying rollers, a flatness adjusting roller group, a line laser scanner and a computing processing module. All rollers of the flatness adjusting roller group press against the segmented area of the mask roll to completely cover the width of the mask roll. The computing processing module continuously obtains a reflected light band deformation image of the line laser on the upper surface of the mask roll in the scanning area through the line laser scanner and inputs the image into a pre-trained lightweight binary neural network to determine whether the flatness of the mask roll in the scanning area is qualified. When the flatness of the mask roll is unqualified, the height of each roller of the flatness adjusting roller group is adjusted according to the continuous cross-sectional profile of the upper surface of the mask roll in the scanning area until the flatness of the mask roll in the scanning area is qualified. The technical scheme provided by the application can quickly adjust the flatness of the mask roll during the transmission process and improve the production efficiency of the mask roll.

Description

TECHNICAL FIELD

[0001] The technical scheme provided by the present application relates to the technical field of high-precision mask roll / film processing, and particularly relates to a system for adjusting flatness of mask roll. BACKGROUND

[0002] Mask roll flatness adjustment is a key technology in metal plate processing, aiming to eliminate plate shape defects (such as waviness, warping, and buckling) caused by internal stress generated in the rolling, coiling, and transportation processes, and to ensure that the material meets the high-precision processing requirements. It is usually necessary to process the mask roll when it is being wound to ensure that its flatness meets the requirements. In addition, the width of the mask roll is becoming larger and larger, which will cause uneven tension on the left and right sides of the mask roll, leading to wrinkles in the mask roll during the running process and easy breakage during rolling, thereby affecting the smoothness of the substrate running and the stability of the production quality.

[0003] The existing technical scheme mainly adds a set of horizontal pressure rollers across the width of the mask roll when the mask roll is running, and when the tension on the two sides of the mask roll is detected to be inconsistent by the pressure sensors arranged on both sides of the conveying roller, one end of the pressure roller is lowered or lifted to balance the tension on both sides of the mask roll. The existing mask roll flatness adjustment system has the following disadvantages:

[0004] 1. Low adjustment efficiency: The existing mask roll flatness adjustment system often requires manual adjustment of the height of the pressure roller, which is time-consuming and difficult to meet the needs of high-speed production lines.

[0005] 2. Difficult to monitor the flatness of the mask roll inside: Since the existing flatness adjustment system only has force sensors on the left and right sides, it mainly monitors the imbalance of the tension on the two sides (i.e., single-sided sagging), and it is difficult to monitor the overall waviness and local bulging of the mask roll inside.

[0006] 3. Difficult to ensure that the flatness of the mask roll meets the requirements: Since the pressure roller is across the mask roll in the width direction, its one end is lifted or lowered (even if it is driven by a motor plus a feedback mechanism), which actually becomes an inclined pressure roller, making it difficult to effectively handle the overall waviness and local bulging of the mask roll, especially as the width of the mask roll increases, the corresponding disadvantages become more prominent. SUMMARY

[0007] In view of the above-mentioned deficiencies of the existing mask roll flatness adjusting system, the present application provides a technical solution capable of comprehensively monitoring the flatness of the mask roll and effectively adjusting the flatness of the mask roll. The technical solution adopts a specially designed flatness adjusting roller group as an adjusting actuator, continuously obtains the reflected light band deformation image formed by the line laser in the width direction of the mask roll based on a line laser scanner to determine whether the flatness of the mask roll is qualified. When unqualified, the corresponding continuous cross-section profile of the upper surface of the mask roll is referred to assist in decision-making to lift or press the rollers in the flatness adjusting roller group, so as to ensure that the flatness of the mask roll in transmission meets the standard.

[0008] The present application provides a technical solution for a system for adjusting the flatness of a mask roll. The system comprises a plurality of conveying rollers, a flatness adjusting roller group, a line laser scanner and a computing and processing module.

[0009] The rotation shafts of the plurality of conveying rollers are in the Y-axis direction and are arranged in a straight line in the X-axis direction to form a horizontal straight line transmission area of the mask roll. The flatness adjusting roller group comprises a plurality of rollers and corresponding height adjusting mechanisms. The height adjusting mechanism can comprise a servo motor and a linear guide rail, and the servo motor drives the roller to lift or descend on the linear guide rail. Each roller presses a segmented area of the mask roll in the Y-axis direction, and all the rollers press the segmented areas of the mask roll which are superimposed to completely cover the mask roll in the Y-axis direction (i.e. across the mask roll in the width direction). The mask roll first passes through the working area of the flatness adjusting roller group and then passes through the scanning area of the line laser scanner.

[0010] The computing and processing module continuously obtains the reflected light band deformation image formed by the line laser emitted by itself on the upper surface of the mask roll through the line laser scanner to determine in real time whether the flatness of the mask roll in the scanning area is qualified. When the flatness is unqualified, the plurality of conveying rollers are controlled to pause conveying the mask roll, and the flatness adjusting roller group is controlled to adjust the flatness until the flatness of the mask roll in the scanning area is qualified, the flatness adjustment is stopped, and the plurality of conveying rollers are controlled to continue conveying the mask roll.

[0011] Further, the line laser emitted by the line laser scanner is perpendicular to the surface of the mask roll and its conveying direction, and covers the mask roll in the width direction of the mask roll, and the deformed image of the reflected light band is captured by the built-in high-precision camera. The line laser scanner is configured to transmit the captured deformed image of the reflected light band to the computing processing module in real time, and only when the computing processing module feeds back that the flatness of the mask roll in the scanning area is "unqualified", the continuous cross-sectional profile image of the upper surface of the mask roll is calculated (usually the 3D coordinates of each point are calculated by "triangulation method"). The above-mentioned configuration of the line laser scanner can omit a large amount of time for calculating the continuous cross-sectional profile image of the mask roll in actual operation of the system (the case of qualified flatness of the mask roll accounts for most of the time), thereby improving the processing efficiency of the whole system.

[0012] Further, the computing processing module inputs the real-time obtained deformed image of the reflected light band into a flatness detection model to identify whether the flatness of the surface of the mask roll irradiated by the current line laser is qualified; if not, feeds back "unqualified" information to the line laser scanner, and receives the corresponding continuous cross-sectional profile image uploaded by the line laser scanner as a basis for lifting or pressing the corresponding roller in the flatness adjusting roller group.

[0013] Correspondingly, the flatness detection model is trained by using a first neural network model and a reflected light band deformed image sample of the mask roll with an artificial classification label. The reflected light band deformed image sample is obtained by scanning the mask roll in the scanning area by using the line laser scanner. The artificial classification label at least includes "qualified" and "unqualified"; the "unqualified" reflected light band deformed image sample includes the following types: single-side collapse, overall wave, and local bulge. Preferably, the first neural network is a lightweight binary neural network MobileNetV3-small.

[0014] The technical scheme provided in the present application can not only comprehensively detect the flatness of the mask roll and effectively handle various uneven conditions such as single-side collapse, overall wave, and local bulge of the mask roll, but also can greatly improve the processing efficiency and yield of the mask roll due to fast recognition speed, high accuracy and efficiency of flatness adjustment when applied to actual production process. The technical scheme provided in the present application is suitable for processing various specifications of mask rolls, especially large-width mask rolls. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be considered as limiting the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0016] Figure 1 The schematic diagram of the system for adjusting flatness of the mask roll in one embodiment of the present application.

[0017] Figure 2a 、 Figure 2b The top view and bottom view of the flatness adjusting roller set in the embodiment shown in Figure 1 The top view and bottom view of the flatness adjusting roller set in the embodiment shown in DETAILED DESCRIPTION

[0018] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be described clearly and completely in combination with the drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0019] Therefore, the detailed description of the embodiments of the present application provided in the drawings below is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of the present application.

[0020] It should be noted that: similar reference numbers and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0021] In the description of the present application, it should be noted that the terms "inner", "outer", "upper", "lower", "vertical" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the present application is usually placed, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", "third" and the like are only used for differentiation, and cannot be understood as indicating or implying relative importance.

[0022] Some embodiments of the present application will be described in detail with reference to the drawings. The features of the embodiments described below can be combined with each other in the case of no conflict.

[0023] As Figure 1 shown in the embodiments, the system for adjusting the flatness of the mask roll provided by the present application comprises: a plurality of conveying rollers 4 (usually aluminum rollers), a flatness adjusting roller set 2, a line laser scanner 1 and a computing processing module 5.

[0024] Figure 1 In the embodiments, the rotation axes of the plurality of conveying rollers 4 are all in the Y-axis direction, and the plurality of conveying rollers 4 are arranged in a straight line in the X-axis direction (the transmission direction of the mask roll) to form a horizontal straight transmission area of the mask roll. The mask roll 3 is closely attached to the conveying rollers 4 and is conveyed from right to left by the conveying rollers 4.

[0025] The flatness adjusting roller set 2 comprises a plurality of rollers 21 and corresponding height adjusting mechanisms (not shown). As Figure 2a , 2b shown, each roller 21 presses against a segmented area of the mask roll 3 in the width direction of the mask roll 3, and all the rollers 21 press against the segmented areas of the mask roll 3 to completely cover the width of the mask roll 3. The height adjusting mechanism of the roller 21 can comprise a servo motor and a linear guide rail. The servo motor drives the roller 21 to rise or fall on the linear guide rail.

[0026] The line laser scanner 1 is arranged above the horizontal straight transmission area of the mask roll. The mask roll 3 first passes through the working area of the flatness adjusting roller set 2, and then passes through the scanning area of the line laser scanner 1. When the line laser emitted by the line laser scanner 1 forms a reflected light band deformation image on the mask roll 3, the reflected light band deformation image is captured by the built-in high-precision camera of the line laser scanner 1. The computing processing module 5 continuously obtains the reflected light band deformation image of the line laser emitted on the surface of the mask roll 3 through the line laser scanner 1, and determines whether the flatness of the mask roll 3 in the scanning area is qualified in real time according to the reflected light band deformation image. If not, the mask roll is paused (by controlling the plurality of conveying rollers 4 to pause), and the corresponding roller 21 of the flatness adjusting roller set 2 is controlled to rise or press down to adjust the flatness of the mask roll 3, until the flatness of the mask roll 3 in the scanning area is qualified, and then the plurality of conveying rollers 4 are controlled to continue conveying the mask roll 3.

[0027] Further, the line laser emitted by the line laser scanner 1 is perpendicular to the surface of the mask roll 3 and its conveying direction, and crosses the mask roll 3 in the width direction of the mask roll 3; the corresponding reflected light band deformation image is captured by the high-precision camera built in the line laser scanner 1, and the processing link of calculating the 3D coordinates of each point of the mask roll in the line laser irradiation area is omitted. This can inform the processing program of the line laser scanner to ignore the calculation of the 3D coordinates of each point of the mask roll through "interrupt" triggering / sending messages, etc., that is, through the way of "interrupt" or message passing, to inform the processing program built in the line laser scanner itself not to perform subsequent processing of calculating the 3D coordinates of each point of the mask roll (the processing program built in the line laser scanner defaults to calculate the surface profile of the scanning object based on the captured reflected light band deformation image). This can omit a large amount of time for the line laser scanner to calculate the profile of the mask roll in the line laser irradiation area in actual production process, and improve the overall processing speed of the system.

[0028] Further, the calculation processing module 5 acquires and inputs the reflected light band deformation image into the flatness detection model to identify whether the flatness of the mask roll 3 surface area irradiated by the line laser is qualified. If not, the height of each roller 21 is adjusted based on the defect type output by the flatness detection model until the reflected light band deformation image acquired by the line laser scanner 1 in real time is judged as qualified by the flatness detection model.

[0029] Correspondingly, the flatness detection model is trained by using the reflected light band deformation image samples of the mask roll 3 with artificial classification labels to obtain a first neural network model. The artificial classification labels of the reflected light band deformation image samples can be obtained by artificial marking according to the continuous cross-sectional profile image further calculated by the line laser scanner 1. The artificial classification labels at least include "qualified" and "unqualified"; wherein the "unqualified" reflected light band deformation image samples cover types such as "single side collapse", "overall wave", and "local bulge". Preferably, the first neural network is a lightweight MobileNetV3-small (binary neural network).

[0030] The flatness detection model uses only the reflection light band deformation image of the line laser on the mask roll when judging the flatness of the mask roll, and the continuous cross-section profile image of the mask roll can save a large amount of 3D left point calculation (usually using triangulation method) and improve processing efficiency. When the flatness detection model judges as "unqualified", the built-in program of the line laser scanner calculates the corresponding continuous cross-section profile image of the upper surface of the mask roll according to the reflection light band deformation image (the line laser scanner on the market mainly uses "triangulation method" to obtain the profile of each point in the area irradiated by the line laser on the mask roll). Based on the continuous cross-section profile image, the computer can assist in determining the roller that needs to be adjusted and the adjustment direction. For example, if the mask roll "collapses on the left side", the roller on the left side can be pressed down; if "overall wave" appears, the roller on one side can be fixed, and the other rollers pressing the mask roll can be pressed down or lifted in sequence. By pressing / lifting the rollers on the mask roll, the flatness of the mask roll in the scanning area of the line laser scanner can be changed. Since the reflection light band deformation image obtained by the line laser scanner in real time is used as a reference image, the system for adjusting the flatness of the mask roll has the function of feedback adjustment.

[0031] The system for adjusting the flatness of the mask roll provided in the present application organically combines the line laser scanner and artificial intelligence technology to improve the comprehensiveness and accuracy of identifying the flatness of the mask roll; and the design of the flatness adjustment roller group effectively adjusts various conditions of the "uneven" mask roll. In addition, the system for adjusting the flatness of the mask roll provided in the present application also improves the identification and adjustment efficiency of the flatness of the mask roll in actual production by optimizing the identification process and saving a large amount of coordinate calculation. The technical solution provided in the present application has no limitation on the size and thickness of the mask roll, and is especially suitable for processing large-width and high-precision mask rolls.

[0032] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Those skilled in the art can make various modifications and changes to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numbers and letters represent similar items in the following drawings, and once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

Claims

1. A system for regulating the flatness of a masking web, characterized by, The system comprises a plurality of conveying rollers, a flatness adjusting roller set, a line laser scanner and a computing processing module; The rotation shafts of the plurality of conveying rollers are in the Y-axis direction and are arranged in a straight line in the X-axis direction to form a horizontal straight line transmission area of the mask roll; the flatness adjusting roller set comprises a plurality of rollers and corresponding height adjusting mechanisms, each roller presses a segmented area of the mask roll in the Y-axis direction, and all the rollers press the segmented areas of the mask roll in the Y-axis direction to completely cover the mask roll; the mask roll first passes through the working area of the flatness adjusting roller set and then passes through the scanning area of the line laser scanner; The computing processing module continuously obtains a reflected light band deformation image formed by the line laser on the upper surface of the mask roll through the line laser scanner, determines whether the flatness of the mask roll in the scanning area is qualified based on the reflected light band deformation image in real time, and if not, calculates a continuous cross-section profile image of the upper surface of the mask roll, controls the plurality of conveying rollers to pause conveying the mask roll and controls the flatness adjusting roller set to adjust the flatness until the flatness of the mask roll in the scanning area is qualified, then stops the flatness adjustment and controls the plurality of conveying rollers to continue conveying the mask roll.

2. The system of claim 1, wherein, The line laser emitted by the line laser scanner is perpendicular to the surface of the mask roll and its conveying direction, and covers the mask roll in the width direction of the mask roll, and the reflected light band deformation image is captured by the built-in high-precision camera.

3. The system of claim 2, wherein, The computing processing module inputs the reflected light band deformation image obtained in real time into a flatness detection model to identify whether the flatness of the mask roll surface irradiated by the current line laser is qualified; if not, feedback the unqualified information to the line laser scanner, and receive the corresponding continuous cross-section profile image uploaded by the line laser scanner as the basis for lifting or pressing the corresponding rollers of the flatness adjusting roller set.

4. The system of claim 3, wherein, The flatness detection model adopts a reflected light band deformation image sample of the mask roll with an artificial classification label to train a first neural network model; the reflected light band deformation image sample is obtained by scanning the mask roll in the scanning area by the line laser scanner, and the artificial classification label at least includes qualified and unqualified; the unqualified reflected light band deformation image sample includes the following types: Single side collapse, overall wave, local bulge.

5. The system of claim 4, wherein, The first neural network is a lightweight binary neural network MobileNetV3-small.

6. The system of any one of claims 1-5, wherein, The height adjusting mechanism comprises a servo motor and a linear guide rail; the servo motor drives the roller to lift or descend on the linear guide rail.

Images