Online real-time detection method for microscopic waviness of float glass

Abstract

The invention relates to an on-line real-time detection method for the microscopic waviness of float glass. The method comprises the following steps: acquiring an image of the surface of a projection curtain of the float glass; creating a micro waviness classifier; calculating a maximum value of gray values of all pixels in a stripe range in the stripe gray image; generating a microcosmic waviness type according to the microcosmic waviness classifier; and generating a classification code according to the type, grade, detail, characteristic and position information of the microscopic waviness. According to the online real-time detection method for the microcosmic waviness of the float glass, the microcosmic waviness of the float glass is calculated through a machine vision image processing method, the online detection method is used for online detection and sorting of the microcosmic waviness of the float glass, and the defect that existing float glass detection equipment cannot detect optical deformation of the glass online is overcome. And the glass rib defects in float glass production can be effectively detected.

Description

Technical Field

[0001] The present invention belongs to the technical field of glass detection, and particularly relates to an on-line real-time detection method for the microscopic waviness of float glass. Background Art

[0002] Due to the flatness, thickness uniformity, and transparency, float glass meets the requirements of high-precision processing and installation. Moreover, due to its high light transmittance, low reflectivity, low scattering rate, thermal stability, and impact resistance, float glass is widely used in the construction, decoration, and precision electronics industries. Machine vision extracts and processes information from the images of objective things through the visual functions simulated by a computer, and then conducts detection and measurement.

[0003] With the continuous improvement of the quality requirements for float glass in other industries, the existing zebra method and microscopic waviness detection method can only conduct manual off-line sampling inspections on the glass ribs of float glass. The manual off-line sampling inspection method for glass ribs cannot adapt to and meet the existing requirements and ensure product quality. The on-line detection method for float glass based on machine vision can effectively detect common defects such as bubbles, inclusions, tin sticking, and cracks in glass production, but cannot detect the glass ribs that cause minor optical deformations. Summary of the Invention

[0004] The technical problem of the present invention is to propose an on-line real-time detection method for the microscopic waviness of float glass, solve the optical deformation of the glass ribs caused by minor optical deformations in the production process of float glass in the existing detection technology, and improve the accuracy of detecting float glass.

[0005] The object of the present invention is to solve the above problems. The technical solution of the present invention is an on-line real-time detection method for the microscopic waviness of float glass, including the following steps: S1: Collect the image on the surface of the projection screen of the float glass; S2: Create a microscopic waviness classifier; S3: Calculate the maximum value of the gray values of all pixels within the stripe range in the stripe gray image; S4: Generate the microscopic waviness type according to the microscopic waviness classifier; S5: Generate a classification code according to the microscopic waviness type, grade, details, characteristics, and position information.

[0006] Further, in step S1, when collecting the image on the surface of the projection screen of the float glass, it includes forming a stripe gray image by performing real-time scanning on the picture through a high-speed linear scanning camera.

[0007] Preferably, in step S1, the stripe gray image is a linear stripe in which the light of the LED projection light passes through the glass and is projected onto the projection cloth, and the brightness is inconsistent on the projection cloth due to the difference in the transmittance of the glass.

[0008] Further, in step S2, creating a micro-ripple classifier includes graphic features, as well as the ripple and gray values corresponding to different types and grades.

[0009] Preferably, the gray value table entry includes the gradient threshold of each type of stripe gray image; the micro-ripple table entry includes the micro-ripple of each float glass specimen corresponding to the maximum value of each gradient; the micro-ripple table entry includes the range of micro-ripple values for each quality grade.

[0010] Preferably, the method for constructing the gray value - micro-ripple mapping table includes the following sub-steps: 1) Select float glass specimens with different gradient micro-ripples, measure the micro-ripples of the specimens by the micro-ripple detection method, and input them into the gray value - micro-ripple mapping table entry; 2) Collect the stripe gray images of the specimens with different micro-ripples in the gray value - micro-ripple mapping table entry; 3) Calculate the maximum value of the gray values of all pixels within the stripe range in the stripe gray image, and input it into the gray table entry of the gray - micro-ripple mapping table.

[0011] Further, step S3 includes the following sub-steps: 1) Collect the gray values of all pixel points within the stripe range in the collected image, and generate a list of image pixel gray values; 2) Calculate the maximum gray value within the stripe range in the image through the MAX function, and set it as the maximum gray value of the stripe image.

[0012] Further, step S4 includes the following sub-steps: S41. Classify and determine the gray value of the stripe image according to the micro-ripple classifier, and generate type, grade, details, characteristics, and position information; S42 Calculate the position of the micro-ripple of the float glass.

[0013] Preferably, step S42 includes the following sub-steps: S42 includes the following sub-steps: 1) Set the mechanical origin of the machine tool; 2) Set the workpiece transverse origin X0 by scanning the boundary of the float glass tooth mark through the camera group; 3) Set the workpiece longitudinal origin Y0 by scanning the starting point of the glass drawing direction through the camera; 4) Generate the workpiece transverse coordinate X1 by measuring the distance from the position of the glass rib to the workpiece transverse origin; 5) Generate the transverse world coordinate X1 by measuring the distance from the position of the glass rib to the mechanical origin; 6) Generate the longitudinal coordinates Y1 and Y2 of the workpiece by calculating the drawing distance of the glass. The calculation formula is as follows: ; ; In the formula, S represents the drawing speed, T represents the running time, and L represents the stripe length.

[0014] 7) Generate the workpiece coordinates X1, Y1 and the world coordinates X1, Y1 respectively; Further, step S5 includes the following sub-steps: 1) Preset the microscopic waviness classification code according to the microscopic waviness classifier, and create a microscopic waviness classification code table; 2) Mark according to the stripe image workpiece coordinates, type and grade information using the microscopic waviness classification code table.

[0015] Compared with the prior art, the beneficial effects of the present invention include: 1) The present invention proposes an on-line real-time detection method for the microscopic waviness of float glass. By calculating the microscopic waviness of float glass through machine vision image processing method, it is used for on-line inspection and sorting of the microscopic waviness of float glass, solves the deficiency that the existing float glass detection equipment cannot detect the optical deformation of glass on-line, and effectively detects the glass rib defects in the production of float glass.

[0016] 2) The present invention proposes an on-line real-time detection method for the microscopic waviness of float glass, which has a fast on-line detection speed and high accuracy for the defects of float glass, reduces the labor intensity of workers, and meets the real-time requirements for on-line detection of the microscopic waviness of float glass. Description of the Drawings

[0017] The present invention will be further described below in conjunction with the drawings and embodiments; Figure 1 It is a plan view of the on-line real-time detection equipment for the microscopic waviness of float glass according to the embodiment of the present invention; Figure 2 It is a side view of the on-line real-time detection equipment for the microscopic waviness of float glass according to the embodiment of the present invention; Figure 3 It is a top view of the on-line real-time detection equipment for the microscopic waviness of float glass according to the embodiment of the present invention; Figure 4 It is a linear brightness stripe diagram for on-line real-time detection of the microscopic waviness of float glass according to the embodiment of the present invention; Figure 5 It is a stripe brightness diagram for on-line real-time detection of the microscopic waviness of float glass according to the embodiment of the present invention; Figure 6 It is a determination result diagram for on-line real-time detection of the microscopic waviness of float glass according to the embodiment of the present invention. Detailed Embodiments

[0018] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0019] As Figure 1 shown, an on-line real-time detection method for the microscopic waviness of float glass includes the following steps: S1: Collect images of the surface of the projection screen of the float glass.

[0020] In step S1, collecting the images of the surface of the projection screen of the float glass includes forming a striped grayscale image by performing real-time scanning of the picture with a high-speed linear scanning camera.

[0021] In step S1, the striped grayscale image is a linear stripe in which the light of the LED projection light passes through the glass and is projected onto the projection screen, and the brightness is inconsistent on the projection screen due to the difference in transmittance of the glass.

[0022] As Figures 1 to 3 shown, the on-line real-time detection system for the microscopic waviness of the float glass of the present invention includes: a dedicated LED lamp group, a transmission roller path, a camera group and a projection screen assembly.

[0023] As Figure 4 shown, when using the on-line real-time detection of the microscopic waviness of the float glass of the present invention, the detection of the float glass usually consists of 4 linear stripes with inconsistent brightness.

[0024] S2: Create a microscopic waviness classifier.

[0025] In step S2, the microscopic waviness classifier includes graphic features, as well as waviness and grayscale values corresponding to different types and grades, as shown in Table 1.

[0026] Table 1

[0027] S3: Calculate the maximum value of the grayscale values of all pixels within the stripe range in the striped grayscale image.

[0028] Step S3 includes the following sub-steps: 1) Collect the grayscale values of all pixel points within the stripe range in the collected image and generate a list of image pixel grayscale values; 2) Calculate the maximum grayscale value within the stripe range in the image through the MAX function and set it as the grayscale value of the stripe image, as Figure 5 shown; S4: Generate the microscopic waviness type according to the microscopic waviness classifier.

[0029] Step S4 includes the following sub-steps: S41. Classify and determine the gray values of the stripe images according to the micro-ripple classifier, and generate information on type, grade, details, characteristics, and position. The details include the defect serial number ID, date, and time. The characteristics include length, ripple, and gray value. The position includes horizontal and vertical coordinate values, as Figure 6 shown; S42. Calculate the position of the micro-ripple, including the following sub-steps: 1) Set the mechanical origin of the machine tool; 2) Set the workpiece horizontal origin X0 by scanning the boundary of the float glass tooth mark through the camera group; 3) Set the workpiece vertical origin Y0 by scanning the starting point of the glass drawing direction through the camera; 4) Generate the workpiece horizontal coordinate X1 by measuring the distance from the position of the glass rib to the workpiece horizontal origin; 5) Generate the horizontal world coordinate X1 by measuring the distance from the position of the glass rib to the mechanical origin; 6) Generate the workpiece vertical coordinates Y1 and Y2 by calculating the glass drawing distance. The formula for the drawing distance is: ; ; In the formula, S represents the drawing speed, T represents the running time, and L represents the stripe length; 7) Generate the workpiece coordinates X1, Y1 and the world coordinates X1, Y1 respectively.

[0030] S5: Generate classification codes based on information such as the micro-ripple type, grade, details, characteristics, and position.

[0031] Step S5 includes the following sub-steps: 1) Preset the micro-ripple classification codes according to the micro-ripple classifier, and create a micro-ripple classification code table, as shown in Table 2:

[0032] 2) Mark using the micro-ripple classification code table according to the workpiece coordinates, type, and grade information of the stripe image.

[0033] The above embodiments are only the preferred technical solutions of the present invention and should not be regarded as limitations on the present invention. The protection scope of the present invention should be the technical solutions recorded in the claims, including equivalent replacement solutions of the technical features in the technical solutions recorded in the claims. That is, equivalent replacement improvements within this scope are also within the protection scope of the present invention.

Claims

1. An on-line real-time detection method for the microscopic waviness of float glass, characterized in that, It includes the following steps: S1: Collect the image of the surface of the float glass projection screen; S2: Create a microscopic waviness classifier; S3: Calculate the maximum value of the gray values of all pixels within the stripe range in the stripe gray image; S4: Generate the microscopic waviness type according to the microscopic waviness classifier; S5: Generate a classification code according to the microscopic waviness type, grade, details, characteristics and position information.

2. The on-line real-time detection method for the microscopic waviness of float glass according to claim 1, characterized in that, In step S1, the collection of the image of the surface of the float glass projection screen includes forming a stripe gray image by performing real-time scanning of the picture through a high-speed linear scanning camera.

3. The on-line real-time detection method for microscopic waviness of float glass according to claim 2, characterized in that, In step S1, the stripe gray image is a linear stripe in which the light of the LED projection light passes through the glass and is projected onto the projection screen, and the glass shows inconsistent brightness on the projection screen due to the difference in transmittance.

4. The online real-time detection method for the microscopic waviness of float glass according to claim 1, characterized in that, In step S2, the creation of the microscopic waviness classifier includes graphic features, as well as the waviness and gray values corresponding to different types and grades.

5. The on-line real-time detection method for microscopic waviness of float glass according to claim 4, characterized in that, The gray value table entry includes the gradient threshold of each type of stripe gray image; the microscopic waviness table entry includes the microscopic waviness of each float glass specimen corresponding to the maximum value of each gradient; the microscopic waviness table entry includes the range of microscopic waviness values of each quality grade.

6. The on-line real-time detection method for microscopic waviness of float glass according to claim 4, characterized in that, The method for constructing the microscopic waviness classifier includes the following sub-steps: 1) Select float glass specimens with different gradient microscopic waviness, measure the microscopic waviness of the specimens by the microscopic waviness detection method, and input them into the gray value - microscopic waviness mapping table entry; 2) Collect the stripe gray images of the specimens with different microscopic waviness in the gray value - microscopic waviness mapping table entry; 3) Calculate the maximum value of the gray values of all pixels within the stripe range in the stripe gray image, and input it into the gray - microscopic waviness mapping table gray value table entry.

7. The on-line real-time detection method for the microscopic waviness of float glass according to claim 1, characterized in that, Step S3 includes the following sub-steps: 1) Collect the gray values of all pixel points within the stripe range in the collected image, and generate a list of image pixel gray values; 2) Calculate the maximum gray value within the stripe range in the image through the MAX function, and set it as the maximum value of the stripe image gray value.

8. The online real-time detection method for microscopic waviness of float glass according to claim 1, characterized in that, Step S4 includes the following sub-steps: S41. Classify and determine the gray value of the stripe image according to the microscopic waviness classifier, and generate type, grade, details, characteristics and position information; S42. Calculate the microscopic waviness position, including the following sub-steps: 1) Set the mechanical origin of the machine tool; 2) Set the workpiece transverse origin X0 by scanning the boundary of the float glass tooth mark through the camera group; 3) Set the workpiece longitudinal origin Y0 by scanning the starting point of the glass drawing direction through the camera; 4) Generate the workpiece transverse coordinate X1 by measuring the distance from the position of the glass rib to the workpiece transverse origin; 5) Generate the transverse world coordinate X1 by measuring the distance from the position of the glass rib to the mechanical origin; 6) Generate the workpiece longitudinal coordinates Y1 and Y2 by calculating the glass drawing distance; 7) Generate the workpiece coordinates X1, Y1 and the world coordinates X1, Y1 respectively.

9. The on-line real-time detection method for microscopic waviness of float glass according to claim 8, characterized in that, The formula for calculating the drawing distance is: ； ; In the formula, S represents the drawing speed, T represents the running time, and L represents the stripe length.

10. The on-line real-time detection method for microscopic waviness of float glass according to claim 1, characterized in that, Step S5 includes the following sub-steps: 1) Preset the microscopic waviness classification code according to the microscopic waviness classifier, and create a microscopic waviness classification code table; 2) Based on the workpiece coordinates, type, and grade information of the stripe image, use the microscopic waviness classification code table for marking.

Images