Method and apparatus for detecting defects in float glass

Abstract

The application discloses a kind of defect detection method and device of float glass, wherein the defect detection method of float glass includes: obtaining the fitting curve of deformation distance and optical deformation angle;Obtain the target image of the float glass to be measured, and obtain the deformation distance of the float glass to be measured according to the target image;Calibration fitting curve, and the deformation distance of the float glass to be measured is substituted into the calibrated fitting curve, to obtain the optical deformation angle of the float glass to be measured.The application realizes the online detection of the optical deformation angle of deformation defect on the float glass by detecting the deformation distance of the float glass online, and then substituting the deformation distance into the calibrated fitting curve of deformation distance and optical deformation angle, which eliminates the step of offline detection of the float glass using measurement tools such as zebra angle detector, so that users can quickly and accurately obtain deformation data of the float glass and evaluate deformation defects.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of glass detection, in particular to a defect detection method and device for float glass. BACKGROUND

[0002] Float glass is a kind of glass that is melted uniformly, enters the tin trough through the flow channel, and is naturally spread into a glass ribbon on the surface of the molten tin liquid due to its own gravity and surface tension, and then is made by external force pulling and temperature adjustment. Because the thickness of float glass is relatively uniform and the transparency is also relatively high, the application of float glass is more and more widely.

[0003] Especially now, in response to the requirements of environmental protection and energy saving, most of the float glass begins to be tempered and coated. In this process, a metal fixed support is placed on the upper surface of the float glass to ensure the parallelism of the glass. However, due to the difference in material properties between the glass material and the metal fixed support, the expansion coefficients of the two are very different, which makes it difficult to ensure the uniformity of the flatness of the float glass after tempering. The surface of the float glass is prone to defects such as edge collapse, concave-convex, white spots, pressure injury, scratches and deformation, so it is very important to detect the surface of the float glass.

[0004] The existing online detection technology can only obtain the range of deformation (i.e. deformation distance) for the detection of deformation of float glass, and evaluate the deformation defect based on the deformation distance. If further detection of the optical deformation angle (i.e. zebra angle) of the float glass is needed, an offline detection by a zebra angle detector or other measuring tools is required, and the detection process is very complex. SUMMARY

[0005] The main purpose of the present application is to provide a defect detection method for float glass, which aims to solve the problem that the existing online monitoring technology cannot detect the optical deformation angle of the float glass.

[0006] To achieve the above purpose, the present application provides a defect detection method for float glass, which comprises:

[0007] obtaining a fitting curve of the deformation distance and the optical deformation angle;

[0008] obtaining a target image of the float glass to be tested, and obtaining the deformation distance of the float glass to be tested according to the target image;

[0009] calibrating the fitting curve, and substituting the deformation distance of the float glass to be tested into the calibrated fitting curve to obtain the optical deformation angle of the float glass to be tested.

[0010] In some embodiments, the obtaining of the fitting curve of the deformation distance and the optical deformation angle comprises:

[0011] placing multiple lenses with different diopters at a detection position, and collecting a calibration image of each lens; obtaining a deformation distance of the lens according to the calibration image, so as to perform data fitting on the diopter and the deformation distance of the lens, and obtaining a first function relationship;

[0012] obtaining an optical deformation angle of the lens, so as to perform data fitting on the diopter and the optical deformation angle of the lens, and obtaining a second function relationship;

[0013] calculating a fitting curve of the deformation distance and the optical deformation angle according to the first function relationship and the second function relationship.

[0014] In some embodiments, the placing multiple lenses with different diopters at a detection position, and collecting a calibration image of each lens; obtaining a deformation distance of the lens according to the calibration image, so as to perform data fitting on the diopter and the deformation distance of the lens, and obtaining a first function relationship comprises:

[0015] obtaining the calibration image of the lens by a line scan camera;

[0016] selecting a plurality of sample regions on the calibration image at intervals along the length direction, and obtaining deformation distances of the calibration image located in the plurality of sample regions;

[0017] fitting the deformation distances of the plurality of sample regions with the diopter to generate a plurality of initial models;

[0018] fitting the plurality of initial models to obtain the first function relationship.

[0019] In some embodiments, the multiple lenses include lenses with diopters of 0 dpt, ±20 mdpt, ±40 mdpt, ±60 mdpt, ±80 mdpt, and ±100 mdpt.

[0020] In some embodiments, the calibration fitting curve comprises:

[0021] placing three lenses with diopters of 0 and ±100 mdpt at the detection position, and obtaining deformation distances corresponding to the three lenses;

[0022] calibrating the fitting curve according to the deformation distances corresponding to the three lenses.

[0023] In some embodiments, the obtaining a target image of the float glass to be measured comprises:

[0024] collecting transmitted light and reflected light of a surface of the float glass to be measured;

[0025] generating the target image of the float glass to be measured.

[0026] In some embodiments, the generating the target image of the to-be-tested float glass further comprises:

[0027] According to the target image, a defect on the to-be-tested float glass is obtained, and a size of the defect is calculated.

[0028] The defect comprises one or more of a crack, dust, a bubble, an inclusion, a tin spot, and a scratch.

[0029] The application further provides a defect detection device for float glass, comprising:

[0030] A standard calibration module comprises a plurality of lenses with different diopters, and is configured to obtain a deformation distance of the lenses and an optical deformation angle of the lenses.

[0031] An imaging light source module is configured to irradiate the to-be-tested float glass to generate a target image.

[0032] An image acquisition module is configured to acquire the target image.

[0033] A data processing module is connected to the standard calibration module and the image acquisition module, and is configured to generate and calibrate a fitting curve according to the deformation distance of the lenses and the optical deformation angle of the lenses, obtain a deformation distance in the target image, and substitute the deformation distance in the target image into the fitting curve to obtain the optical deformation angle of the to-be-tested float glass.

[0034] In some embodiments, the imaging light source module comprises:

[0035] A reflection light source is configured to irradiate the to-be-tested float glass to generate reflected light.

[0036] A transmission light source is configured to emit light rays of two different wavelengths.

[0037] A filter is arranged between the transmission light source and the to-be-tested float glass, and a plurality of light-blocking segments are arranged on the filter at intervals. The light-blocking segments are configured to allow only one of the light rays of the two different wavelengths to pass through, so that the light rays of the two different wavelengths form striped light and uniform backlight after passing through the filter. The striped light and the uniform backlight are configured to irradiate the to-be-tested float glass to generate transmitted light.

[0038] In some embodiments, the data processing module comprises:

[0039] A data preprocessor is connected to the image acquisition module, and is configured to set a photographing parameter of the image acquisition module and process the target image to generate striped data.

[0040] a data processor connected with the standard calibration module and the data preprocessor, used for receiving the deformation distance of the lens and the optical deformation angle of the lens and generating the fitting curve; and the data processor can receive the fringe data and output the deformation distance of the float glass to be measured according to the fringe data;

[0041] an industrial computer connected with the data processor, used for receiving the deformation distance of the float glass to be measured, substituting the deformation distance of the float glass to be measured into the fitting curve, and outputting the optical deformation angle of the float glass to be measured to an external device.

[0042] The technical scheme provided by the present application realizes the online detection of the optical deformation angle of the deformation defect on the float glass by detecting the deformation distance of the float glass online and substituting the deformation distance into the fitting curve of the deformation distance and the optical deformation angle after calibration, so that the step of detecting the float glass offline by using a measuring tool such as a zebra angle detector is omitted, and the user can quickly and accurately obtain the deformation data of the float glass and evaluate the deformation defect, which is convenient for the user to timely adjust the production scheme and solve the problems in the production process. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 a flow chart of the embodiment of the defect detection method of the float glass according to the present application;

[0044] Figure 2 a flow chart of another embodiment of the defect detection method of the float glass according to the present application;

[0045] Figure 3 a flow chart of still another embodiment of the defect detection method of the float glass according to the present application;

[0046] Figure 4 a flow chart of still another embodiment of the defect detection method of the float glass according to the present application;

[0047] Figure 5 a flow chart of still another embodiment of the defect detection method of the float glass according to the present application;

[0048] Figure 6 a flow chart of still another embodiment of the defect detection method of the float glass according to the present application;

[0049] Figure 7 a structural schematic view of the defect detection device of the float glass according to the present application;

[0050] Figure 8 a structural schematic view of the data processing module in the defect detection device of the float glass according to the present application;

[0051] Figure 9Fig. 1 is a schematic diagram of a calibration image in an embodiment of the defect detection device for float glass of the present application;

[0052] Figure 10 Fig. 2 is a schematic diagram of a cosine function of the fringe data in an embodiment of the defect detection device for float glass of the present application; Figure 9

[0053] Reference signs:

[0054] 100, standard calibration module; 200, imaging light source module; 300, image acquisition module; 400, data processing module; 410, data preprocessor; 420, data processor; 430, industrial computer. DETAILED DESCRIPTION

[0055] The embodiments of the present application will be described in detail below with reference to the drawings. It should be noted that the embodiments described are only some of the embodiments of the present application, but not all of them. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of the present application.

[0056] It should be noted that all directional indications, such as up, down, left, right, front, back, etc., are only used to explain the relative position relationship, movement condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directional indications will also change accordingly.

[0057] It should also be noted that when an element is referred to as being "fixed to" or "set on" another element, it can be directly on the other element or can have a middle element. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or can have a middle element.

[0058] In addition, the description of "first", "second", etc. in the present application is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of various embodiments can be combined with each other, but it must be based on the realization of a person skilled in the art, and when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, and is not within the scope of protection required by the present application.

[0059] The present application proposes a defect detection method for float glass, referring to Figure 1 The defect detection method comprises:

[0060] ​Step S100: Obtain a fitting curve between the deformation distance and the optical deformation angle.

[0061] The actual measurement data of the deformation distance and the optical deformation angle can be obtained through experiments, and then the fitting curve is generated by fitting the obtained measurement data. For example, a group of float glass samples can be selected, and different degrees of deformation treatment can be performed on these samples, which should be as close as possible to the deformation conditions that may occur in the actual production process of float glass, so that the data has sufficient accuracy. Then, the optical measuring instrument is used to measure the float glass samples to obtain the optical deformation angle and the deformation distance after deformation. Then, a mathematical model (such as polynomial fitting, linear fitting or nonlinear fitting) is used to generate a fitting curve between the deformation distance and the optical deformation angle. Alternatively, different degrees of deformation of the float glass can be simulated by using finite element analysis (FEA) and optical simulation software, and then the deformation distance of the float glass is obtained, and the influence of different deformation on the optical deformation angle is simulated. Finally, the simulation data is fitted to obtain the fitting curve between the deformation distance and the optical deformation angle. It can be understood that the historical data of the deformation distance and the optical deformation angle corresponding to different degrees of deformation of the float glass can also be collected, and then a regression model (such as linear regression, support vector regression, neural network, etc.) is used to fit the data to generate a fitting curve between the deformation distance and the optical deformation angle.

[0062] Step S200: Obtain a target image of the float glass to be measured, and obtain the deformation distance of the float glass to be measured according to the target image.

[0063] In this embodiment, machine vision technology is used to detect surface defects of float glass. Machine vision technology uses machines instead of personnel to make measurements and judgments. Further, this embodiment usually uses a high-definition lens and a line scan camera to capture a target image. The deformation distance can be obtained by comparing the deviation between the target image and the standard image. For example, a stripe light source (which can emit stripe light) can be used to irradiate the float glass to be measured. If the surface of the float glass to be measured is flat, the obtained target image will be a neat stripe. If the surface of the float glass to be measured is deformed, the stripe in the obtained target image will be distorted, and the distortion degree can be calculated to obtain the deformation distance of the float glass to be measured.

[0064] Step S300: Calibrate the fitting curve, and substitute the deformation distance of the float glass to be measured into the calibrated fitting curve to obtain the optical deformation angle of the float glass to be measured.

[0065] Since the experimental environment deviates from the actual production environment, the light source, the position of the float glass and the position and model of the camera will all affect the detection result. Therefore, before applying the fitting curve, the fitting curve needs to be calibrated to improve the accuracy of the detection result. Specifically, a number of float glass samples can be detected in the actual production environment, and the data obtained after detection (i.e. the deformation distance and the optical deformation angle) are substituted into the fitting curve to analyze the error of the fitting curve. The error between the data of the float glass samples and the fitting curve is reduced by adjusting the parameters of the fitting curve. The correction of the parameters can be completed by linear regression correction, polynomial correction, local weighted regression, least squares method, machine learning calibration, etc. The present application does not limit this.

[0066] The technical solution provided by the present application realizes online detection of the optical deformation angle of the deformation defect on the float glass by detecting the deformation distance of the float glass online and substituting the deformation distance into the fitting curve of the deformation distance and the optical deformation angle after calibration, thereby saving the step of offline detection of the float glass using a measurement tool such as a zebra angle detector, enabling the user to quickly and accurately obtain the deformation data of the float glass and evaluate the deformation defect, and facilitating the user to timely adjust the production scheme and solve the problems in the production process.

[0067] As shown in Figure 2 S100 includes the following steps:

[0068] S110: Place a plurality of lenses with different diopters at a detection position and collect a calibration image of each lens; obtain the deformation distance of the lens according to the calibration image, thereby data fitting the diopter and the deformation distance of the lens to obtain a first functional relationship;

[0069] S120: Obtain the optical deformation angle of the lens, thereby data fitting the diopter and the optical deformation angle of the lens to obtain a second functional relationship;

[0070] S130: Calculate the fitting curve of the deformation distance and the optical deformation angle according to the first functional relationship and the second functional relationship.

[0071] In this embodiment, since the refractive power (used to measure the ability of the lens to refract light) of the lens itself is known and fixed, the lens is used as a sample, a calibration image of the lens is collected and the corresponding deformation distance of the lens is calculated, and then the deformation distance is fitted with the corresponding refractive power parameter of the lens to generate the relationship between the deformation distance and the refractive power, i.e. the first functional relationship. Then, the optical deformation angle of the lens can be measured by a zebra angle tester or other equipment, or the optical deformation angle of the lens can be obtained by a transmission deformation test method, a stress birefringence method, an optical profiler or the like, and then the optical deformation angle is fitted with the corresponding refractive power parameter of the lens to generate the relationship between the refractive power and the optical deformation angle, i.e. the second functional relationship. Finally, the first functional relationship and the second functional relationship can be fitted into a new model, i.e. the fitting curve of the deformation distance and the optical deformation angle.

[0072] It can be understood that the lens with a refractive power in a suitable range can be selected according to actual needs, for example, if the general deformation of the float glass in the production process is large, a plurality of lenses with a large refractive power can be selected as samples, so as to improve the accuracy of the finally obtained fitting curve. In this embodiment, the lens with a known refractive power is selected as a sample, and then the fitting curve of the deformation distance and the optical deformation angle is calculated by taking the refractive power as an intermediate parameter, the experimental process is simple, the workload of calculation is reduced, and the efficiency of online testing of the light deformation angle of the float glass is further improved.

[0073] As shown in Figure 3 , in some embodiments, step S110 comprises:

[0074] Step S111: acquiring a calibration image of the lens by a line scan camera;

[0075] Step S112: selecting a plurality of sample regions on the calibration image at intervals along the length direction and acquiring the deformation distance of the calibration image in the plurality of sample regions;

[0076] Step S113: fitting the deformation distance of the plurality of sample regions with the refractive power to generate a plurality of initial models;

[0077] Step S114: fitting the plurality of initial models to obtain the first functional relationship.

[0078] The calibration image is usually a fringe image, and the deformation distance can be obtained by calculating the distance of the fringe boundary movement. As shown in Figure 9 and Figure 10 , the fringe in the calibration image can be represented as a cosine function, which is set as F(x), which is a fixed value inherent to the light source and does not change; the function formed by detection is f(x), which changes according to the detection glass. In order to amplify the change of x, it can be multiplied by another cosine function R(x) with a smaller period, and the final functions t(x) and T(x) are obtained:

[0079] t(x) = f(x) R(x)

[0080] T(x) = F(x) R(x)

[0081] The shift of the stripe in the x direction can be calculated by comparing t(x) and T(x).

[0082] When the deformation distance is very small, the change of x cannot be accurately detected and calculated in actual testing, because the pixels of the camera are limited and cannot be segmented with high precision, but y is the energy value, which can be controlled to obtain smaller resolution, and the phase change of the cosine function is not only reflected in the horizontal coordinate x, but also in the vertical coordinate y, so the shift of y value can be calculated to calculate the change of the phase, and the specific calculation process is:

[0083] The change in the y direction is amplified by multiplying itself,

[0084] G(x) = F(x) F(x)

[0085] T'(x) = f(x) F(x)

[0086] The shift in the y direction can be obtained by comparing G(x) and T'(x).

[0087] Since the y direction is more reflected in the small deformation, it is not possible to calculate the larger deformation, and the x cannot reflect the small deformation. We calculate the deformation of x as dx, and the deformation of y as dy, and finally the deformation distance is represented as d = dx + dy.

[0088] Due to the existence of lens distortion, the calibration image captured by the line scan camera will produce different degrees of deformation and distortion, so in this embodiment, the deformation distance is calculated at each place of the calibration image, and then the relationship between the deformation distance of the multiple lenses and the diopter is obtained, that is, the initial model, and then the multiple initial models are fitted to obtain the first function relationship, which realizes the correction of the lens distortion to a certain extent and improves the accuracy of the first function relationship.

[0089] For example, the establishment of the initial model can be performed at one sixth, one half and five sixths of the calibration image, and finally the first function relationship is obtained by fitting. Since the distortion of the image is more serious at the edge, the sample area is set at the edge position of the calibration image, which further improves the accuracy of the first function relationship.

[0090] In some embodiments, the multiple lenses include lenses with diopters of 0 dpt, ±20 mdpt, ±40 mdpt, ±60 mdpt, ±80 mdpt and ±100 mdpt.

[0091] Wherein the positive diopter represents the diopter of the convex lens, which is used to simulate the float glass with convex deformation, and the negative diopter represents the diopter of the concave lens, which is used to simulate the float glass with concave deformation. Since the deformation degree of the float glass is usually small, the lenses with a diopter within 100 mdpt are used as samples in this embodiment for testing, so as to better simulate the actual deformation condition, so that the fitting curve of the deformation distance and the optical deformation angle is more accurate.

[0092] As shown in Figure 4 In some embodiments, the calibration fitting curve includes:

[0093] Step S310: Place three lenses with a diopter of 0 and ±100 mdpt in the detection position, and obtain the corresponding deformation distances of the three lenses;

[0094] Step S320: Calibrate the fitting curve according to the corresponding deformation distances of the three lenses.

[0095] Wherein the lens with a diopter of 0 dpt (i.e. flat glass) has no focusing ability and will not cause any optical deformation or deviation, and can be regarded as an ideal reference sample without optical deformation. Therefore, when calibrating the fitting curve, the lens with a diopter of 0 dpt provides a reference point for judging the measurement result of the system without optical deviation, so as to verify the initial accuracy of the fitting curve and ensure that the fitting curve can start from zero. The diopter of ±100 mdpt can cover more extreme optical deformation scenarios, and the significant optical deformation effect can be detected during testing, so that the result with obvious optical deformation is obtained, and reliable reference points of the fitting curve in a wider diopter range are ensured. At the same time, the lenses with a large span of diopter are used as samples for calibrating the fitting curve, which can more effectively reduce the fitting error, enhance the robustness of the fitting curve, further balance the deviation of the fitting curve in the positive and negative directions, and improve the accuracy of the fitting curve.

[0096] As shown in Figure 5 In some embodiments, obtaining the target image of the float glass to be tested includes:

[0097] Step S210: Collecting the transmission light and reflection light on the surface of the float glass to be tested;

[0098] Step S220: Generating the target image of the float glass to be tested.

[0099] In this embodiment, the transmission light and reflection light on the surface of the float glass to be tested are collected in real time to generate and obtain the target image of the float glass to be tested in real time. Compared with only collecting the transmission light, the light intensity of the obtained target image is increased, and the image quality of the obtained target image is improved.

[0100] As shown in Figure 6As shown, in some embodiments, after generating the target image of the to-be-tested float glass, further comprising:

[0101] Step S230: obtaining defects on the to-be-tested float glass according to the target image, and calculating the size of the defects;

[0102] The defects include one or more of cracks, dust, bubbles, inclusions, tin spots, and scratches.

[0103] The defects on the float glass can be identified based on an image processing algorithm. For example, an edge detection algorithm (such as Sobel, Canny, etc.) can be used to identify more obvious defects such as cracks and scratches on the surface of the glass. Alternatively, a defect template (such as an image of a float glass with bubbles) can be pre-set, and the to-be-tested image can be matched with the defect template to identify defects that match the template. Deep learning techniques such as convolutional neural networks can also be used to train the system with a large amount of data to automatically identify and classify defects.

[0104] There are also various ways to calculate the size of the defects. For example, the number of pixels in the defect area can be counted, and the total number of pixels in the defect area can be calculated. Then, based on the image resolution (the number of pixels per unit length, usually in pixels per millimeter), the number of pixels can be converted into the actual length or area. For example, if an image contains 100 pixels per millimeter, and a defect area has a width of 50 pixels, the actual width is 0.5 millimeters. For irregularly shaped defects (such as cracks and scratches), a minimum circumscribed rectangle can be fitted to approximate the size of the defect.

[0105] The deformation detection and defect detection of the float glass are integrated in the same detection process in this embodiment, which can complete accurate detection of the float glass in real time on the production line, reduces the time cost, and enables users to quickly find problems in the production process of the float glass, thereby improving the yield of the float glass.

[0106] The present application further provides a defect detection device for float glass, referring to Figure 7 , comprising:

[0107] The standard calibration module 100 includes a plurality of lenses with different diopters, which are used to obtain the deformation distance of the lens and the optical deformation angle of the lens.

[0108] The imaging light source module 200 is used to irradiate the to-be-tested float glass to generate a target image.

[0109] The image acquisition module 300 is used to acquire the target image.

[0110] The data processing module 400 is connected with the standard calibration module 100 and the image acquisition module 300, and is used for generating and calibrating a fitting curve according to the deformation distance of the lens and the optical deformation angle of the lens, acquiring the deformation distance in the target image, and substituting the deformation distance in the target image into the fitting curve to obtain the optical deformation angle of the float glass to be measured.

[0111] In the embodiment, the deformation distance of the float glass is detected online by the image acquisition module 300, and the deformation distance is substituted into the fitting curve of the deformation distance and the optical deformation angle after calibration, so that the online detection of the optical deformation angle of the deformation defect on the float glass is realized, the step of detecting the float glass offline by using a zebra angle detector or the like is omitted, and the user can quickly and accurately acquire the deformation data of the float glass and evaluate the deformation defect, so that the user can timely adjust the production scheme and solve the problems in the production process.

[0112] In some embodiments, the imaging light source module 200 includes:

[0113] The reflection light source can irradiate the float glass to be measured to generate reflected light;

[0114] The transmission light source can emit light of two different wavelengths;

[0115] The filter is arranged between the transmission light source and the float glass to be measured, and a plurality of light blocking segments are arranged on the filter in intervals, the light blocking segments can only allow one of the light of the two different wavelengths to pass through, so that the light of the two different wavelengths forms a striped light and a uniform backlight after passing through the filter, and the striped light and the uniform backlight can irradiate the float glass to be measured to generate transmitted light.

[0116] In the embodiment, the light emitted by the transmission light source becomes a striped light and a uniform backlight after passing through the filter, wherein the striped light is used for calculating the deformation distance of the float glass, and the uniform backlight is used for defect detection and defect size calculation of the float glass.

[0117] The filter can form the light blocking segments arranged at intervals by laser film removal, the light blocking segments are covered with a film layer that can only allow a certain monochromatic light to pass through and cut off other wavelengths of light, and other areas of the filter can pass through light of any wavelength.

[0118] For example, a double-color LED that can emit light of wavelengths A and B is used as the transmission light source, and the light of the two wavelengths can be lit respectively to facilitate the use of time division multiplexing technology to form two images. The filter is arranged above the double-color LED, and the light blocking segments can cut off light of wavelength B, so that when the double-color LED emits light of wavelength A only, a uniform backlight is formed, and when the double-color LED emits light of wavelength B only, a striped light is formed.

[0119] As Figure 8 shown, in some embodiments, the data processing module 400 comprises:

[0120] a data preprocessor 410 connected to the image acquisition module 300, configured to set the photographing parameters of the image acquisition module 300 and process the target image to generate the fringe data;

[0121] a data processor 420 connected to the standard calibration module 100 and the data preprocessor 410, configured to receive the deformation distance of the lens and the optical deformation angle of the lens and generate a fitting curve; and the data processor 420 can receive the fringe data and output the deformation distance of the measured float glass according to the fringe data;

[0122] an industrial computer 430 connected to the data processor 420, configured to receive the deformation distance of the measured float glass, substitute the deformation distance of the measured float glass into the fitting curve, and output the optical deformation angle of the measured float glass to an external device.

[0123] The data preprocessor 410 can be one or more of a field programmable gate array, a digital signal processor, and a graphics processing unit, and the data processor 420 can be a high-performance central processing unit or a graphics processor. The external device can be a display device, a mobile terminal, etc., so that the user can view the optical deformation angle of the measured float glass in time.

[0124] The above only describes some or preferred embodiments of the present application, neither the text nor the drawings can limit the scope of protection of the present application, any equivalent structural transformation using the content of the present application specification and drawings, or direct / indirect application in other related technical fields are included in the scope of protection of the present application.

Claims

1. A method of detecting defects in float glass, characterized in that, The method comprises the following steps: obtaining a fitting curve of the deformation distance and the optical deformation angle; obtaining a target image of the float glass to be measured, and obtaining the deformation distance of the float glass to be measured according to the target image; calibrating the fitting curve, and substituting the deformation distance of the float glass to be measured into the calibrated fitting curve to obtain the optical deformation angle of the float glass to be measured; The method comprises the following steps: placing a plurality of lenses with different diopters at a detection position, and collecting a calibration image of each lens; obtaining the deformation distance of the lens according to the calibration image, thereby performing data fitting on the diopter and the deformation distance of the lens to obtain a first functional relationship; obtaining the optical deformation angle of the lens, thereby performing data fitting on the diopter and the optical deformation angle of the lens to obtain a second functional relationship; calculating the fitting curve of the deformation distance and the optical deformation angle according to the first functional relationship and the second functional relationship.

2. The method of detecting defects in float glass according to claim 1, wherein The method comprises the following steps: placing a plurality of lenses with different diopters at a detection position, and collecting a calibration image of each lens; obtaining the deformation distance of the lens according to the calibration image, thereby performing data fitting on the diopter and the deformation distance of the lens to obtain a first functional relationship comprises the following steps: obtaining the calibration image of the lens by a line scan camera; selecting a plurality of sample regions on the calibration image at intervals along the length direction, and obtaining the deformation distance of the calibration image in the plurality of sample regions; fitting the deformation distance of the plurality of sample regions with the diopter to generate a plurality of initial models; 3. The method of claim 2, wherein the step of detecting the defect of the float glass is performed by using a camera. fitting the plurality of initial models to obtain the first functional relationship.

4. The method of claim 1, wherein the step of detecting the defect of the float glass is performed by using a camera. The plurality of lenses comprise lenses with diopters of 0 dpt, ±20 mdpt, ±40 mdpt, ±60 mdpt, ±80 mdpt and ±100 mdpt. The method comprises the following steps: placing three lenses with diopters of 0 and ±100 mdpt at the detection position, and obtaining the deformation distance corresponding to the three lenses; 5. The method of detecting defects in float glass according to any one of claims 1 to 4, characterized in that, calibrating the fitting curve according to the deformation distance corresponding to the three lenses. The method comprises the following steps: collecting the transmitted light and the reflected light of the surface of the float glass to be measured; 6. The method of claim 5, wherein the step of detecting the defect of the float glass is performed by using a camera. generating the target image of the float glass to be measured. After the target image of the float glass to be measured is generated, the method further comprises the following steps: obtaining defects on the float glass to be measured according to the target image, and calculating the size of the defects; 7. An apparatus for detecting defects in float glass, characterized in that, wherein the defects comprise one or more of cracks, dust, bubbles, inclusions, tin spots and scratches. The method comprises the following steps: a standard calibration module comprising a plurality of lenses with different diopters, for obtaining the deformation distance of the lens and the optical deformation angle of the lens; an imaging light source module for irradiating the float glass to be measured to generate a target image; an image collection module for collecting the target image; a data processing module connected to the standard calibration module and the image collection module, for generating and calibrating a fitting curve according to the deformation distance of the lens and the optical deformation angle of the lens, and obtaining the deformation distance in the target image, and substituting the deformation distance in the target image into the fitting curve to obtain the optical deformation angle of the float glass to be measured. The data processing module is specifically used for: placing multiple lenses with different diopters at a detection position and collecting calibration images of each lens, obtaining the deformation distance of the lens according to the calibration images, and performing data fitting on the diopter and the deformation distance of the lens to obtain a first function relationship; obtaining the optical deformation angle of the lens, and performing data fitting on the diopter and the optical deformation angle of the lens to obtain a second function relationship; calculating the fitting curve of the deformation distance and the optical deformation angle according to the first function relationship and the second function relationship.

8. The apparatus for detecting defects in float glass according to claim 7, wherein The imaging light source module comprises: a reflection light source, which can irradiate the float glass to be measured to generate reflected light; a transmission light source, which can emit light rays of two different wavelengths; a filter, which is arranged between the transmission light source and the float glass to be measured, and a plurality of light blocking segments are arranged on the filter at intervals, the light blocking segments can only allow one of the light rays of the two different wavelengths to pass through, so that the light rays of the two different wavelengths form stripe light and uniform backlight after passing through the filter, and the stripe light and the uniform backlight can irradiate the float glass to be measured to generate transmitted light.

9. The apparatus for detecting defects in float glass according to claim 8, wherein, The data processing module comprises: a data preprocessor connected to the image acquisition module, which is used to set the photographing parameters of the image acquisition module and process the target image to generate stripe data; a data processor connected to the standard calibration module and the data preprocessor, which is used to receive the deformation distance of the lens and the optical deformation angle of the lens and generate the fitting curve; and the data processor can receive the stripe data and output the deformation distance of the float glass to be measured according to the stripe data; an industrial computer connected to the data processor, which is used to receive the deformation distance of the float glass to be measured, substitute the deformation distance of the float glass to be measured into the fitting curve, and output the optical deformation angle of the float glass to be measured to an external device.

Images